Publications

Many of our publications can be accessed on researchgate

Short-term Solar Power Forecasting Considering Cloud Coverage and Ambient Temperature Variation Effects

Wed, 01 Aug 2018 00:00:00 GMT

Short-term Solar Power Forecasting Considering Cloud Coverage and Ambient Temperature Variation Effects

Heidari Gandoman, F., H.E.Abdel Aleem, S., Omar, N., Ahmadi, A. & Q.Alenezi, F. 1 Aug 2018 In : Renewable Energy. 123, p. 793-805 793 p., 123

Research output: ResearchArticle

The use of solar photovoltaic (PV) systems as green renewable sources for electricity generation in modern power networks is steadily increasing. One of the problems with using PV units in developing countries and small companies is access to a simple model to assess the short-time output of a solar cell. For example, a robust model that is capable of analyzing cloud variations and ambient temperature (important factors impacting the PV output) to assess short-term PV output would be very helpful. This article proposes a new methodology to assess the impacts of these factors on the hourly output power of a PV system. Our results showed that the proposed model has the ability to assess PV output by using the hourly data of cloud and ambient temperature change. To validate the model, the output was compared to results of measurements from PV systems installed in Sanandaj and Rasht cities located in North-West (latitude 35.31 and longitude 47.00) and North (latitude 37.28 and longitude 49.58) Iran, respectively. Also, the standardized root-mean-square error method (nRMSE) was used to validate the high accuracy of the proposed method.
Original languageEnglish
Article number123
Pages (from-to)793-805
Number of pages793
JournalRenewable Energy
Volume123
StatePublished - 1 Aug 2018

From Early-Stage-Researchers to Academic Entrepreneurs: underlying dynamics of the transformation process

Mon, 02 Jul 2018 00:00:00 GMT

This conceptual paper contributes to the state-of-the-art in literature by bringing together research about the skills and personality traits of Academic Entrepreneurs (AE) and the creation and exploitation of knowledge networks. Academic Entrepreneurship (AE) describes activities academics undertake to commercialize their research results. Research in this field has been mainly retrospective, considering the phenomena of established AEs, often missing to investigate the trajectory towards AE through longitudinal research. Combining these literature streams in an integrative framework allows us to identify the research gap: the trajectory of Early-Stage-Researchers (ESR) (predoctoral researchers) towards AE, and particularly its underlying dynamics. Within these dynamics, we shed light on the influence of stable personality traits and working context variables on the development of skills for (1) the creation and exploitation of networks through which knowledge is acquired and disseminated, and (2) skills for the creation/discovery and the recognition of entrepreneurial opportunities. These relationships are presented in a relational model, which also provides the basis for our propositions that will be tested in an empirical longitudinal setting. We discuss theoretical implications and present our future work.
Original languageEnglish
StateUnpublished - 2 Jul 2018
EventR&D Management Conference 2018 - Politecnico di Milano, Milano, Italy
Duration: 1 Jul 20184 Jul 2018

Conference

ConferenceR&D Management Conference 2018
CountryItaly
CityMilano
Period1/07/184/07/18

Profit-driven decision tree approaches for uplift modeling

Sun, 01 Jul 2018 00:00:00 GMT

Profit-driven decision tree approaches for uplift modeling

Devriendt, F., Petrides, G., Lessmann, S. & Verbeke, W. Jul 2018 EURO 2018: 29th European Conference on Operational Research. Euro: The Association of European Operational Research Societies, p. 193 1 p.

Research output: ResearchMeeting abstract (Book)

Uplift modeling is a type of predictive modeling that estimates the incremental effect of performing some action on customer behavior. This allows for a high degree of customization and improved targeting selection in marketing campaigns with the aim to maximize the effect of the campaign and the returns on marketing investment. In previous work, we have extended the maximum profit measure towards uplift modeling for identifying the use in terms of profitability of an uplift model.
In this paper, we take it one step further and consider the profit maximization objective during the model construction phase. We focus on adapting existing uplift decision trees, which in turn are direct generalizations of standard decision trees such as CART and C4.5. Inspired by the literature on cost-sensitive learning techniques, we develop and evaluate an array of approaches to replace the impurity measure in the splitting criterion of decision trees by including components of the maximum profit measure. We present the results of an experimental study, comparing the performance of the various proposed implementations with existing approaches such as uplift random forests on two real-world datasets. To evaluate, we adopt both profit and qini-based model performance assessment approaches.
Original languageEnglish
Title of host publicationEURO 2018: 29th European Conference on Operational Research
PublisherEuro: The Association of European Operational Research Societies
Pages193
Number of pages1
StatePublished - Jul 2018
EventEURO 2018 - Valencia, Spain
Duration: 8 Jul 201811 Jul 2018
Conference number: 29
http://euro2018valencia.com/

Conference

ConferenceEURO 2018
Abbreviated titleEURO 2018
CountrySpain
CityValencia
Period8/07/1811/07/18
Internet address

Sampling techniques for uplift modeling for improved stability and performance

Sun, 01 Jul 2018 00:00:00 GMT

Sampling techniques for uplift modeling for improved stability and performance

Robert, D., Devriendt, F., Petrides, G. & Verbeke, W. Jul 2018 EURO 2018: 29th European Conference on Operational Research. Euro: The Association of European Operational Research Societies, p. 193 1 p.

Research output: ResearchMeeting abstract (Book)

In this study, we investigate the impact of data sampling on the stability
of uplift models. The aim of uplift modelling is to predict people’s
reaction to a campaign offering incentives towards taking a particular
action, such as buying a product or not churning from a service.
In the literature, it has been reported that uplift models can be unstable
performance-wise (in terms of the Qini measure for example)
and may consequently be deemed unreliable. We investigate whether
model stability can be improved by modifying the class ratio using
data sampling techniques, without worsening the performance in the
process. Specifically, we use both under- and oversampling, as well as
the methods smote and rose. Whereas the first two remove or duplicate
records, the latter two artificially generate new records taking account
of their neighbourhood while potentially also removing records.
The uplift models are built considering uplift random forests, and the
methods of Lo and Generalized Lai. In our experimental design, we
take account of different class ratios and we use a number of direct
marketing datasets. Furthermore, we check whether these new models
show an increased performance, studying whether there exists a tradeoff
between stability and performance. In some cases, we observe that
sampling methods have a positive impact on both the stability and performance
of uplift models, but this depends on the method and dataset
used.
Original languageEnglish
Title of host publicationEURO 2018: 29th European Conference on Operational Research
PublisherEuro: The Association of European Operational Research Societies
Pages193
Number of pages1
StatePublished - Jul 2018
EventEURO 2018 - Valencia, Spain
Duration: 8 Jul 201811 Jul 2018
Conference number: 29
http://euro2018valencia.com/

Conference

ConferenceEURO 2018
Abbreviated titleEURO 2018
CountrySpain
CityValencia
Period8/07/1811/07/18
Internet address

In-Life Range Modularity for Electric Vehicles: The Environmental Impact of a Range-Extender Trailer System

Thu, 21 Jun 2018 00:00:00 GMT

In-Life Range Modularity for Electric Vehicles: The Environmental Impact of a Range-Extender Trailer System

Hooftman, N. S., Messagie, M., Joint, F., Segard, J-B. & Coosemans, T. 21 Jun 2018 In : Applied Sciences. 8, 7, 19 p.

Research output: Research - peer-reviewArticle

Purpose: In the light of decarbonizing the passenger car sector, several technologies are available today. In this paper, we distinguish plug-in hybrid electric vehicles (PHEV), electric vehicles (EV) with a modest battery capacity of 40 kWh, and long-range EVs with 90 kWh installed. Given that the average motorist only rarely performs long-distance trips, both the PHEV and the 90 kWh EV are considered to be over-dimensioned for their purpose, although consumers tend to perceive the 40 kWh EV’s range as too limiting. Therefore, in-life range modularity by means of occasionally using a range-extender trailer for a 40 kWh EV is proposed, based on either a petrol generator as a short-term solution or a 50 kWh battery pack. Method: A life cycle assessment (LCA) is presented for comparing the different powertrains for their environmental impact, with the emphasis on local air quality and climate change. Therefore, the combination of a 40 kWh EV and the trailer options is benchmarked with a range of conventional cars and EVs, differentiated per battery capacity. Next, the local impact per technology is discussed on a well-to-wheel base for the specific situation in Belgium, with specific attention given to the contribution of non-exhaust emissions of PM due to brake, tyre, and road wear. Results: From a life cycle point of view, the trailer concepts outperform the 90 kWh EV for the discussed midpoint indicators as the latter is characterized by a high manufacturing impact and by a mass penalty resulting in higher contributions to non-exhaust PM formation. Compared to a petrol PHEV, both trailers are found to have higher contributions to diminished local air quality, given the relatively low use phase impact of petrol combustion. Concerning human toxicity, the impact is proportional to battery size, although the battery trailer performs better than the 90 kWh EV due to its occasional application rather than carrying along such high capacity all the time. For climate change, we see a clear advantage of both the petrol and the battery trailer, with reductions ranging from one-third to nearly sixty percent, respectively. Conclusion: Whereas electrified powertrains have the potential to add to better urban air quality, their life cycle impact cannot be neglected as battery manufacturing remains a substantial contributor to the EV’s overall impact. Therefore, in-life range modularity helps to reduce this burden by offering an extended range only when it is needed. This is relevant to bridge the years up until cleaner battery chemistries break through, while the energy production sector increases the implementation of renewables. Petrol generator trailers are no long-term solution but should be seen as an intermediate means until battery technology costs have further dropped to make it economically feasible to commercialize battery trailer range-extenders. Next, active regulation is required for non-exhaust PM emissions as they could dominate locally in the future if more renewables would be applied in the electricity production process
Original languageEnglish
Number of pages19
JournalApplied Sciences
Volume8
Issue number7
StatePublished - 21 Jun 2018

A study on the stability of uplift models

Fri, 15 Jun 2018 00:00:00 GMT

Original languageEnglish
StateUnpublished - 15 Jun 2018
EventBusiness Analytics Research Day - KU Leuven, Leuven, Belgium
Duration: 15 Jun 2018 → …
Conference number: 2018
https://data-lab.be/bard

Seminar

SeminarBusiness Analytics Research Day
Abbreviated titleBARD
CountryBelgium
CityLeuven
Period15/06/18 → …
Internet address

A survey & experimental evaluation of multiple treatment uplift modeling

Mon, 01 Jan 2018 00:00:00 GMT

Original languageEnglish
StateUnpublished - 15 Jun 2018
EventBusiness Analytics Research Day - KU Leuven, Leuven, Belgium
Duration: 15 Jun 2018 → …
Conference number: 2018
https://data-lab.be/bard

Seminar

SeminarBusiness Analytics Research Day
Abbreviated titleBARD
CountryBelgium
CityLeuven
Period15/06/18 → …
Internet address

The case for prescriptive analytics:profit-driven uplift modeling

Fri, 15 Jun 2018 00:00:00 GMT

The case for prescriptive analytics:profit-driven uplift modeling

Devriendt, F. & Verbeke, W. 15 Jun 2018

Research output: ResearchUnpublished abstract

To save costs, marketers often utilize traditional response modelling to target only those customers that are likely to respond to the marketing campaign. However, these models fail to differentiate between customers who respond favourably because of the campaign and customers that respond favourably on their own accord, regardless of the campaign. Uplift modelling aims to establish the net difference in customer behaviour resulting of a specific treatment that is given to the customer.
Several state-of-the-art techniques and methodologies are benchmarked on multiple private and public datasets, representing both cross/up-selling and retention campaigns. In evaluating the results, we highlight a couple of issues. One of those regards the evaluation of different uplift modelling techniques. Although different evaluation techniques exist to evaluate the performance of uplift models, the interpretability of the metrics is not so intuitive. Therefore, we propose a profit-driven approach towards uplift modelling which considers the costs of the campaign and the expected benefits. Our profit-driven approach allows us to identify the customers who are both highly influential and beneficial for a campaign. This approach allows for clear and interpretative knowledge to be used in future business decisions when setting up a new campaign.
Original languageEnglish
StateUnpublished - 15 Jun 2018
EventBusiness Analytics Research Day - KU Leuven, Leuven, Belgium
Duration: 15 Jun 2018 → …
Conference number: 2018
https://data-lab.be/bard

Seminar

SeminarBusiness Analytics Research Day
Abbreviated titleBARD
CountryBelgium
CityLeuven
Period15/06/18 → …
Internet address

Analysis of the 2017 Belgian new and second-hand car fleet: Ecoscore 2018

Wed, 13 Jun 2018 00:00:00 GMT

Original languageEnglish
Commissioning bodyLNE / BIM / AWAC
Number of pages47
StatePublished - 13 Jun 2018

Dual Enhancement of Power System Monitoring: Improved Probabilistic Multi-Stage PMU Placement with an Increased Search Space & Mathematical Linear Expansion to Consider Zero-Injection Bus

Sun, 03 Jun 2018 00:00:00 GMT

Dual Enhancement of Power System Monitoring: Improved Probabilistic Multi-Stage PMU Placement with an Increased Search Space & Mathematical Linear Expansion to Consider Zero-Injection Bus

M. Ali, Z., Razavi, S-E., Javadi, M. S., Heidari Gandoman, F. & Hossam Eldeen Abdel Aleem, S. 3 Jun 2018 In : Energies. 6, 11, p. 2-17

Research output: Research - peer-reviewArticle

This paper presents a mathematical linear expansion model for the probabilistic Multistage Phasor Measurement Unit (PMU) Placement (MPP) in which zero-injection buses (ZIBs), as well as communication channel limitations, are taken into consideration. From the linearization perspective, presenting a model formulizing the probabilistic concept of observability while modelling the ZIB
is of great significance, and has been done in this paper for the first time. More importantly, the proposed probabilistic MPP utilizes a technique disregarding the prevalent subsidiary optimizations for each planning stage. Although this technique, in turn, increases the problem complexity with
manifold variables, it guarantees the global optimal solution in a wider and thorough search space; while in the prevalent methods, some parts of the search space might be missed. Furthermore, the proposed model indicates more realistic aspects of the MPP where system operators are allowed to follow their intention about the importance of buses such as strategic ones based on monitoring the
priority principles. In addition, the model is capable of considering the network topology changes due to long-term expansions over the planning horizon. Finally, in order to demonstrate the effectiveness of the proposed formulation, the model is conducted on the IEEE 57-bus standard test system and the large scale 2383-bus Polish power system.
Original languageEnglish
Pages (from-to)2-17
JournalEnergies
Volume6
Issue number11
StatePublished - 3 Jun 2018

Longer and heavier vehicles in Belgium: A threat for the intermodal sector?

Fri, 01 Jun 2018 00:00:00 GMT

Longer and heavier vehicles in Belgium: A threat for the intermodal sector?

Meers, D., Van Lier, T. & Macharis, C. Jun 2018 In : Transportation Research Part D: Transport and Environment. 61, p. 459-470

Research output: Research - peer-reviewArticle

To achieve transport cost reductions and to reduce the environmental impact of road transport, different European countries are allowing or testing longer and heavier vehicles on their road network. In Belgium, the Flanders region started a trial in 2015 allowing a limited number of longer and heavier vehicles on a selection of approved routes. A concern among intermodal operators is however that an allowance of longer and heavier vehicles could trigger a reverse modal shift away from rail and inland waterways container transport. Starting from experiences in other European countries, this paper discusses the potential spatial impact of allowing longer and heavier vehicles on the market areas of intermodal transhipment terminals using a geographic information systems-based location analysis model. In a second step, external transport costs are incorporated in this model, to quantify the spatially diversified societal costs of a potential reverse modal shift.
Original languageEnglish
Pages (from-to)459-470
JournalTransportation Research Part D: Transport and Environment
Volume61
DOIs
StatePublished - Jun 2018

Iedereen aan boord?: Een besluitvormingsondersteunend instrument voor de Brusselse Noord-Zuid spoorverbinding

Mon, 28 May 2018 00:00:00 GMT

Iedereen aan boord?: Een besluitvormingsondersteunend instrument voor de Brusselse Noord-Zuid spoorverbinding

Te Boveldt, G. & Macharis, C. 28 May 2018 In : Brussels Studies. 2018, 124, p. n.v.t. (online journal) 124

Research output: Research - peer-reviewArticle

Translated title of the contributionAll aboard? : A decision-making instrument for the future of the Brussels North-South railway connection
Administrative complexity is a major challenge in the planning of large-scale projects in Brussels. For want of an overarching authority, multiple actors with different functions or powers have to make and implement a concerted decision. The COMCA method is used to determine the support for multi-actor, multi-level projects and thus to assist policy makers in their decisions. The various players are classified according to their role in the project. Project alternatives are assessed on criteria established by each of the actors. The desirability of each alternative is evaluated for each actor, but also for every group of actors responsible for a specific task in the project. This article describes how the method was applied as a participatory component in a study on infrastructural alternatives for the Brussels North-South rail link. Variants allowing for new rail links appear to be more promising for further study than the frequently examined doubling variants of the current North-South axis. However, the purpose of the application at this stage is not to offer a final solution, but to design an evaluation and consultation structure that provides input for the political decision-making process.
Original languageDutch
Article number124
Pages (from-to)n.v.t. (online journal)
JournalBrussels Studies
Volume2018
Issue number124
StatePublished - 28 May 2018

A High Efficiency and High Step-Down Conversion LDC Converter in Multifunctional On-Board Charger

Thu, 24 May 2018 00:00:00 GMT

A High Efficiency and High Step-Down Conversion LDC Converter in Multifunctional On-Board Charger

Vu, H. N., Tran, D-D., El Baghdadi, M., Van Mierlo, J. & Hegazy, O. 24 May 2018 Young Researchers Symposium, IEEE Benelux Chapter IAS/PES/PESC. p. 1-5 5 p.

Research output: ResearchConference paper

This paper proposes a new hybrid converter (HC) topology for the low voltage dc-dc (LDC) converter in a Multifunctional On-board Charger (MOBC) application. The HC is an integration of a Phase-Shifted Full-Bridge (PSFB) converter and a Forward (FW) converter. These two converters share H-bridge switches at the primary side and the output capacitors at the secondary side. Compared with the conventional PSFB or FW converter, the proposed HC
can achieve a high step-down conversion. In addition, thanks to the sharing output capacitors at the secondary side, the input power can be delivered to the output load during the freewheeling interval of the PSFB converter. Hence, this can reduce the current ripple of the output inductor. In addition, the H-bridge switches of PSFB converter can achieve a full ZVS range, while the ZCS turn-off at the leading-leg is obtained by getting the trade-off between the leakage inductor and the output capacitor values.
Original languageEnglish
Title of host publicationYoung Researchers Symposium, IEEE Benelux Chapter IAS/PES/PESC
Pages1-5
Number of pages5
StatePublished - 24 May 2018

A novel state of charge and capacity estimation technique for electric vehicles connected to a smart grid based on inverse theory and a metaheuristic algorithm

Fri, 11 May 2018 00:00:00 GMT

Increasing interest in the successful coordination of electric vehicles and renewable energy sources has recently been shown by researchers and power generation companies, in large part due to its impact on de-carbonization of urban areas and its capability of contributing towards ancillary services. Nevertheless, this coordination requires a bi-directional communication infrastructure, between combined electric vehicles, renewable energy systems, and power plants since one of the main reasons of this combination is to address the temporal fluctuations in renewable power generation. This bi-directional communication enables the power grid to adapt to different power source structures and improves the acceptability of intermittent renewable energy generation. Whereas electric vehicles equipped with lithium-ion batteries appear to be feasible options for stationary energy storage systems, known as a new distributed generation, the flexibility of electric vehicles in vehicle-to-grid connections is completely dependent on the maximum practical capacity and state of charge of each vehicle. Hence this infrastructure for the integration of electric vehicles as new distributed generation and renewable energy systems with electrical grids, emphasizes the need for an off-board state estimation of electric vehicles in aggregators. Moreover, an accurate estimation of the state of health and state of charge when electric vehicles are not charged or discharged by a constant current profile is required to overcome the challenges of existing methods. Each of introduced methods has different limitations, which are presented in this article. This article proposes a novel off-board state estimation technique for such parameters as state of charge and maximum practical capacity by employing a metaheuristic algorithm and an adaptive neuro-fuzzy inference system to overcome the limitations of existing methods. Due to drawbacks of filtering techniques, inverse theory is used in this article to convert the filtering problem to an optimization problem in order to take advantage of its capability. The results exhibit not only a high convergence rate (low settling time) but also a high robustness.
Original languageEnglish
Pages (from-to)1047-1058
JournalEnergy
Volume155
DOIs
StatePublished - 11 May 2018

Electrochemical impedance spectroscopy characterization and parameterization of lithium nickel manganese cobalt oxide pouch cells: dependency analysis of temperature and state of charge

Tue, 08 May 2018 00:00:00 GMT

Characterizing lithium-ion batteries is of prime importance as it helps in understanding the safety, working temperature, voltage range, and power capabilities. Based on these results, we can then choose operating conditions which include safety protocols, application, and working environment. In this study, EIS studies of commercially available 20-Ah lithium-ion battery and a 28- Ah prototype cell with nickel manganese cobalt oxide (NMC)/graphite chemistry are used to determine the contribution of temperature and state of charge (SoC) towards the electrochemical impedance spectroscopy. These cells are manufactured for electric vehicle (EV) application. The electrode structure, particle size, stacking of the electrodes, and other entities for both the cells are provided to compare the similarities and differences between both the cells. Equivalent circuit modeling is used to analyze and comprehend the variation in impedance spectrum obtained for both the cells. It is observed that the ohmic resistance varies with both temperature and SoC and the variation with temperature is more significant for the prototype cell. The prototype cell showed better charge-transfer characteristics at lower temperatures when compared to the commercial cell.
Original languageEnglish
JournalIonics
StatePublished - 8 May 2018

Form Early-Stage-Research to Academic Entrepreneurship: underlying dynamics of the transformation process

Tue, 01 May 2018 00:00:00 GMT

Original languageEnglish
StateUnpublished - May 2018
EventA Multidisciplinary Perspective into Entrepreneurship: Research at the Cross Borders of Finance, Psychology and Entrepreneurship - Ghent, Belgium
Duration: 7 May 20188 May 2018

Workshop

WorkshopA Multidisciplinary Perspective into Entrepreneurship: Research at the Cross Borders of Finance, Psychology and Entrepreneurship
CountryBelgium
CityGhent
Period7/05/188/05/18

From Early-Stage-Research to Academic Entrepreneurship: knowledge acquisition through network creation

Tue, 01 May 2018 00:00:00 GMT

This conceptual paper proposes the state-of-the-art in literature about resource orchestration, entrepreneurial opportunities and the skills and personality of academic entrepreneurs that are combined in an integrative framework. Through evaluation of existing literature, we could identify a research gap, namely the trajectory of early-stage-researchers towards academic entrepreneurship. Within this trajectory we shed light on the influence of personality traits nd constraining working context variables on the development of skills for (1) the creation of networks through which knowledge is acquired and (2) skills for the emergence and recognition of entrepreneurial opportunities.
Original languageEnglish
StateUnpublished - May 2018
EventEu-SPRI Early Career Research Conference (ECC) - Valencia, Spain
Duration: 3 May 20185 May 2018

Conference

ConferenceEu-SPRI Early Career Research Conference (ECC)
CountrySpain
CityValencia
Period3/05/185/05/18

A centralized state of charge estimation technique for electric vehicles equipped with lithium-ion batteries in smart grid environment

Mon, 30 Apr 2018 00:00:00 GMT

Electric vehicles (EVs) not only act as a load in grid-to-vehicle but also as a storage system in vehicle-to-grid concept. Further, both renewable energy sources (RESs) and EVs can be classified under multi-distributed generations. In this regard, fossil-based power generation units as traditional back-ups or distributed generations can be replaced by a combination of renewable energy sources (RESs) and EVs to alleviate suffering from the fluctuation of renewable power generation units. However, successful coordination of electric vehicles and renewable energy systems require accurate state estimations of EVs such as state of charge (SoC) due to intermittent renewable energy output. Hence this combination emphasizes the need for an efficient method of SoC estimation. Since battery management system is in the initial stage of development, none of the proposed intelligent state of charge estimation techniques has been capable of being implemented in battery management system. In this regard, the present article proposes an off-board real-time state of charge estimation technique, can be implemented in fog computing architecture, for lithium-ion battery based on the National Aeronautics and Space Administration (NASA) database enabling to compare the outcome of the present article with the recent studies. In this article, a non-dominated sorting genetic algorithm II (NSGA-II) is combined with an artificial neural network (ANN) technique to estimate SoC of four batteries simultaneously. The results of the proposed technique indicate high convergence rate and high accurate estimation.
Original languageEnglish
Title of host publicationIEEE
DOIs
StatePublished - 30 Apr 2018

The case for prescriptive analytics: a novel maximum profit measure for evaluating and comparing customer churn prediction and uplift models

Mon, 30 Apr 2018 00:00:00 GMT

The case for prescriptive analytics: a novel maximum profit measure for evaluating and comparing customer churn prediction and uplift models

Devriendt, F. & Verbeke, W. 30 Apr 2018 Vrije Universiteit Brussel, Faculteit Economische en Sociale Wetenschappen & Solvay Business School, p. 1-29 29 p.(ES Working Paper; no. 12)

Research output: ResearchWorking paper

Prescriptive analytics and uplift modeling are receiving more attention from the business analytics research community and from industry as an alternative and improved paradigm of predictive analytics that supports data-driven decision making. Although it has been shown in theory that prescriptive analytics improves decision-making more than predictive analytics, no empirical evidence has been presented in the literature on an elaborated application of both approaches that allows for a fair comparison of predictive and uplift modeling. Such a comparison is in fact prohibited by a lack of available evaluation measures that can be applied to predictive and uplift models.
Therefore, in this paper, we introduce a novel evaluation metric called the maximum profit uplift measure that allows one to assess the performance of an uplift model in terms of the maximum potential profit that can be achieved by adopting an uplift model. The measure is developed for evaluating customer churn uplift models and for extending the existing maximum profit measure for evaluating customer churn prediction models. Both measures are subsequently applied to a case study to assess and compare the performance of customer churn prediction and uplift models. We find that uplift modeling outperforms predictive modeling and allows one to enhance the profitability of retention campaigns. The empirical results indicate that prescriptive analytics are superior to predictive analytics in the development of customer retention campaigns.
Original languageEnglish
PublisherVrije Universiteit Brussel, Faculteit Economische en Sociale Wetenschappen & Solvay Business School
Pages1-29
Number of pages29
StatePublished - 30 Apr 2018

Publication series

NameES Working Paper
No.12

Modelling, Analysis and Performance Evaluation of Power Conversion Unit in G2V/V2G Application—A Review

Fri, 27 Apr 2018 00:00:00 GMT

Modelling, Analysis and Performance Evaluation of Power Conversion Unit in G2V/V2G Application—A Review

GARCÉS QUÍLEZ, M. A. R. Í. A., Abdel Monem, M., El Baghdadi, M., Yang, Y., Van Mierlo, J. & Hegazy, O. 27 Apr 2018 In : Energies. 11, 1082, p. 1-24 24 p., 1082

Research output: Research - peer-reviewArticle

In response to climate change, which is caused by the increasing pollution of the environment and leads to the deterioration of human health, future electricity generations should reduce reliance on fossil fuels by growing the use of clean and renewable energy generation sources and by using clean vehicle technologies. Battery storage systems have been recognized as one of the most promising approaches for supporting the renewable energy generation sources and cleanly powering vehicles instead of burning gasoline and diesel fuel. However, the cost of batteries is still a prominent barrier for their use in stationary and traction applications. As a rule, the cost of batteries can be decreased by lowering material costs, enhancing process efficiencies, and increasing production volume. Another more effective solution is called Vehicle-to-grid (V2G) application. In V2G application, the battery system can be used to support the grid services, whereas the battery is still in the vehicle. To make a battery system economically viable for V2G/G2V applications, an effective power-electronics converter should be selected as well. This converter should be supported by an advanced control strategy. Therefore, this article provides a detailed technical assessment and review of V2G/G2V concepts, in conjunction with various power-electronics converter topologies. In this paper, modeling and detailed control strategies are fully designed and investigated in terms of dynamic response and harmonics. Furthermore, an extensive design and analysis of charging systems for low-duty/high-duty vehicles are also presented.
Original languageEnglish
Article number1082
Pages (from-to)1-24
Number of pages24
JournalEnergies
Volume11
Issue number1082
DOIs
StatePublished - 27 Apr 2018

Technical Assessment of Hybrid Powertrains for Energy-efficient Heavy-Duty Vehicles

Thu, 19 Apr 2018 00:00:00 GMT

Technical Assessment of Hybrid Powertrains for Energy-efficient Heavy-Duty Vehicles

Barrero Fernandez, R., Tran, D-D., Hegazy, O., Omar, N. & Van Mierlo, J. 19 Apr 2018 (Accepted/In press) Transport Research Arena (TRA) 2018.

Research output: ResearchConference paper

This article presents the approach used for the design optimization of heavy vehicles such as urban buses and delivery trucks as a part or the ORCA European Project. A methodology to find the optimal combination of hardware components and energy management strategy is presented and the use cases where it will be applied are described.
To achieve the optimal results, the vehicles need to be modeled with an appropriated methodology that allows for both performance evaluation and energy consumption assessment in short times. To achieve both objectives, the “forward” vehicle modeling, together with static or “low fidelity” models is proposed. Several simulation examples in both electric and conventional mode are given. These models will be used to assess several potential vehicles design, assess their performance, consumption and eventually estimate the total cost of ownership.
Original languageEnglish
Title of host publicationTransport Research Arena (TRA) 2018
StateAccepted/In press - 19 Apr 2018

Combining an Electrothermal and Impedance Aging Model to Investigate Thermal Degradation Caused by Fast Charging

Fri, 30 Mar 2018 00:00:00 GMT

Fast charging is an exciting topic in the field of electric and hybrid electric vehicles (EVs/HEVs). In order to achieve faster charging times, fast-charging applications involve high-current profiles which can lead to high cell temperature increase, and in some cases thermal runaways. There has been some research on the impact caused by fast-charging profiles. This research is mostly focused on the electrical, thermal and aging aspects of the cell individually, but these factors are never treated together. In this paper, the thermal progression of the lithium-ion battery under specific fast-charging profiles is investigated and modeled. The cell is a Lithium Nickel Manganese Cobalt Oxide/graphite-based cell (NMC) rated at 20 Ah, and thermal images during fast-charging have been taken at four degradation states: 100%, 90%, 85%, and 80% State-of-Health (SoH). A semi-empirical resistance aging model is developed using gathered data from extensive cycling and calendar aging tests, which is coupled to an electrothermal model. This novel combined model achieves good agreement with the measurements, with simulation results always within 2 °C of the measured values. This study presents a modeling methodology that is usable to predict the potential temperature distribution for lithium-ion batteries (LiBs) during fast-charging profiles at different aging states, which would be of benefit for Battery Management Systems (BMS) in future thermal strategies.
Original languageEnglish
Article number804
Number of pages15
JournalEnergies
Volume11
Issue number4
DOIs
StatePublished - 30 Mar 2018

Last mile configurations for e-commerce platform of the future: evaluation in terms of transport performance and external costs

Thu, 08 Mar 2018 00:00:00 GMT

The e-commerce sector in Belgium grew by 13% last year, and further growth is expected. That translates itself in a high number of related transport activities. The last mile segment of an e-commerce supply chain is characterized by its fragmentation, while it copes with the issues of free deliveries, next day deliveries, failed deliveries and (free) retours. The impact on the economy, environment and society is problematic. From the operators perspective, their logistic activities are confronted with rising congestion levels, client requirements and preferences, a limited willingness to pay and intervening governments (road pricing, pedestrian zones, low emission zones, time windows, etc.). When introducing an online platform, assembling different brands and businesses like a regular shopping street, one needs to take into account these factors for drawing the implemented logistic network.
This research presents eight different network configurations for such a new platform. Each configuration consists of a different share of homedeliveries, different collection points, use of regional versus dedicated centralized distribution center and different transport vehicles. The configurations are analyzed and compared in terms of their transport performance (vkm, time losses), CO2 emissions, noise nuisance, air pollution and external costs for accidents and infrastructure. The calculations are performed with the agent-based freight transport model TRABAM. The time perspective is 2023 – assuming that the platform is operating for five years.
Original languageEnglish
StatePublished - 8 Mar 2018
EventNECTAR Cluster 3 : The future of transport - Venice, Italy
Duration: 7 Mar 20189 Mar 2018

Conference

ConferenceNECTAR Cluster 3 : The future of transport
CountryItaly
CityVenice
Period7/03/189/03/18

Phase-change materials (PCM) for automotive applications: A review

Mon, 05 Mar 2018 00:00:00 GMT

Phase-change materials (PCM) for automotive applications: A review

Jaguemont, J., Omar, N., Van Mierlo, J. & Van Den Bossche, P. 5 Mar 2018 In : Applied Thermal Engineering. 132, p. 308-320

Research output: Research - peer-reviewArticle

In this paper, an extensive review of a battery thermal management systems (BTMSs) such as phase- change materials (PCMs) in the state of art is proposed. Nowadays, PCMs are particularly attractive and chosen as one of the most interesting cooling system in terms of high-energy storage density. In addi- tion, they are less bulky, complex and expensive than traditional cooling methods such as forced-air cool- ing or liquid cooling. Nonetheless, the integration of PCMs in a battery application calls for an analysis that will enable the researcher to proposed optimized BTMSs. Indeed, due to the lack of literature in this domain, the paper proposed to review all the existing studies on battery applications involving PCMs. Numerical analysis description, heat transfer theory along with the classification of the existing compo- nents for PCMs are also presented. This paper is based on previous reviews to help to update the thin number of references, which is considered by the authors as the major contribution
Original languageEnglish
Pages (from-to)308-320
JournalApplied Thermal Engineering
Volume132
StatePublished - 5 Mar 2018

A Literature Survey and Experimental Evaluation of the State-of-the-Art in Uplift Modeling: A Stepping Stone Toward the Development of Prescriptive Analytics

Thu, 01 Mar 2018 00:00:00 GMT

Prescriptive analytics extends on predictive analytics by allowing to estimate an outcome in function of control variables, allowing as such to establish the required level of control variables for realizing a desired outcome. Uplift modeling is at the heart of prescriptive analytics and aims at estimating the net difference in an outcome resulting from a specific action or treatment that is applied. In this article, a structured and detailed literature survey on uplift modeling is provided by identifying and contrasting various groups of approaches. In addition, evaluation metrics for assessing the performance of uplift models are reviewed. An experimental evaluation on four real-world data sets provides further insight into their use. Uplift random forests are found to be consistently among the best performing techniques in terms of the Qini and Gini measures, although considerable variability in performance across the various data sets of the experiments is observed. In addition, uplift models are frequently observed to be unstable and display a strong variability in terms of performance across different folds in the cross-validation experimental setup. This potentially threatens their actual use for business applications. Moreover, it is found that the available evaluation metrics do not provide an intuitively understandable indication of the actual use and performance of a model. Specifically, existing evaluation metrics do not facilitate a comparison of uplift models and predictive models and evaluate performance either at an arbitrary cutoff or over the full spectrum of potential cutoffs. In conclusion, we highlight the instability of uplift models and the need for an application-oriented approach to assess uplift models as prime topics for further research.
Original languageEnglish
Pages (from-to)13-41
JournalBig Data
Volume6
Issue number1
DOIs
StatePublished - 1 Mar 2018

Financing urban transportation infrastructure in a multi-actors environment: the role of value capture

Thu, 01 Mar 2018 00:00:00 GMT

Financing urban transportation infrastructure in a multi-actors environment: the role of value capture

Roukouni, A., Macharis, C., Basbas, S., Stephanis, B. & Mintsis, G. 1 Mar 2018 In : European Transport Research Review. 10, 1, 19 p., 14

Research output: Research - peer-reviewArticle

Purpose: A family of innovative financial mechanisms and tools for urban public transport, based on the value increment caused by enhanced accessibility, are lately gaining much popularity as a solution to the challenges posed by public financial resources’ shrinkage: Value Capture Finance (VCF). The effectiveness of applied transport financing policies depends significantly on the level of agreement among stakeholders, making collaboration a prerequisite for success. The research presented herein assesses alternative financing options for urban public transportation which are based on the VCF concept. Method: The Multi - Actor Multi-Criteria Analysis (MAMCA) developed by Macharis [1] is used. The methodology is unique in its field, as it includes in-depth involvement of all relevant stakeholders and reveals their way of thinking. Results: The proposed methodological framework is applied to the real-world case study of the under construction metro system of Thessaloniki, Greece. Three different financing scenarios are tested, and the criteria weight elicitation is performed through personal interviews with 70 stakeholders belonging to six different groups, namely: Government/Local Authorities, Transport Authorities, Universities/Research Institutions, Private Sector, Society and Professional Associations. Noteworthy similarities but also contradictions among stakeholder groups emerged, highlighted by the different criteria used for each group. Conclusion: The paper introduces the MAMCA as an ex - ante evaluation method for different VCF mechanisms for urban transportation infrastructure. MAMCA emerges as a robust methodology for this assessment, as it is proved to be capable of dealing with the VCF complexity and multidisciplinary nature.

Original languageEnglish
Article number14
Number of pages19
JournalEuropean Transport Research Review
Volume10
Issue number1
DOIs
StatePublished - 1 Mar 2018

Tackling Fragmented Last Mile Deliveries to Nanostores by Utilizing Spare Transportation Capacity—A Simulation Study

Wed, 28 Feb 2018 00:00:00 GMT

Tackling Fragmented Last Mile Deliveries to Nanostores by Utilizing Spare Transportation Capacity—A Simulation Study

Kin, B., Ambra, T., Verlinde, S. & Macharis, C. 28 Feb 2018 In : Sustainability. 10, 653, p. 1-15 15 p.

Research output: Research - peer-reviewArticle

Last mile deliveries in urban areas cause a disproportionate unsustainable impact, while it is also the most expensive part of the supply chain. This is particularly true for freight flows that are characterized by fragmentation. Logistically, this becomes apparent in vehicles that are driving around with a low vehicle fill rate, leading to the unnecessary presence of freight vehicles in our cities. This study focuses on the operational feasibility of utilizing the spare transportation capacity of a service-driven company as a potential solution to supply small independent retailers, or nanostores. The aim is to reduce inefficient vehicle movement. Based on a real-life implementation, we use SYnchronization Model for Belgian Inland Transport (SYMBIT), an agent-based model, to simulate various bundling scenarios. Results show the total vehicle kilometers and lead times to supply nanostores for the service-driven company to serve its customers. There is a potential to utilize spare capacity to supply nanostores while maintaining a decent service level. The number of vehicle kilometers driven highly depends on the location of the distribution center where the service-driven company operates. Based on these results, the conditions that have to be met to replicate this solution in other urban areas are discussed.
Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalSustainability
Volume10
Issue number653
StatePublished - 28 Feb 2018

A Combined Thermo-Electric Resistance Degradation model for Nickel Manganese Cobalt Oxide based Lithium-Ion cells

Thu, 15 Feb 2018 00:00:00 GMT

A Combined Thermo-Electric Resistance Degradation model for Nickel Manganese Cobalt Oxide based Lithium-Ion cells

De Hoog, J., Jaguemont, J., Nikolian, A., Van Mierlo, J., Van Den Bossche, P. & Omar, N. 15 Feb 2018 (Accepted/In press) In : Applied Thermal Engineering. 15 p.

Research output: Research - peer-reviewArticle

This paper presents a novel effort in combining an electro-thermal internal resistance model for Nickel Manganese Cobalt Oxide (NMC) cathode and graphite anode based cells, designed for predictive analysis for automotive applications. This unique approach provides insight in the degradation rate of the internal resistance with respect to the Depth of Discharge, Current rate, cycle number, storage State of Charge and storage time. The data used for the model development is courtesy of a huge test-campaign, spanning the course of 2.5 years, and provides a good insight in the behavior of what is considered to be a very promising battery cell technology for automotive applications. Experimental results show that the internal resistance evolution is strongly dependent on Depth of Discharge and temperature, while high storage State of Charges and high storage temperatures increase the degradation rate during calendaring aging. The combined electric and thermal models make it possible to estimate the influence of the current rate on the degradation of the internal resistance. The developed lifetime model is capable of correctly estimating the degradation and temperature behavior of static load profiles, while also providing insight in the evolution of the temperature profile and other cell characteristics.
Original languageEnglish
Number of pages15
JournalApplied Thermal Engineering
DOIs
StateAccepted/In press - 15 Feb 2018

Advances in Renewable Energies and Power Technologies: Volume 2: Geothermal and Biomass Energies, Fuel Cells, and Smart Grid

Wed, 14 Feb 2018 00:00:00 GMT

Advances in Renewable Energies and Power Technologies: Volume 2: Geothermal and Biomass Energies, Fuel Cells, and Smart Grid

M Sharaf, A., Omar, N., Heidari Gandoman, F., Faheem Zobaa, A. & Hossam Eldeen Abdel Aleem, S. 14 Feb 2018 Electric and hybrid vehicle drives and smart grid interfacing.

Research output: Research - peer-reviewChapter

Original languageEnglish
Title of host publicationElectric and hybrid vehicle drives and smart grid interfacing
StatePublished - 14 Feb 2018

Technical Viability of Battery Second Life: A Study from the Ageing Perspective

Fri, 02 Feb 2018 00:00:00 GMT

Technical Viability of Battery Second Life: A Study from the Ageing Perspective

Martinez-Laserna, E., Sarasketa-Zabala, E., Villarreal, I., Ioan Stroe, D., Swierczynski, M., Warnecke, A., Timmermans, J-M. P., Goutam, S., Omar, N. & Rodriguez, P. 2 Feb 2018 In : IEEE Transactions on Industry Applications. PP, 99, p. 1-1

Research output: Research - peer-reviewArticle

Reusing electric vehicle batteries once they have been retired from the automotive application is stated as one of the possible solutions to reduce electric vehicle costs. Many publications in literature have analysed the economic viability of such a solution, and some car manufacturers have recently started running several projects to demonstrate the technical viability of the so-called battery second life. Nevertheless, the degradation behaviour of second life batteries remains unknown and represents one of the biggest gaps in the literature. The present work aims at evaluating the effects of Lithium-ion (Li-ion) NMC/C battery State of Health (SOH) and ageing history over the second life performance, on two different applications: a residential demand management application and a power smoothing renewable integration application. The performance and degradation of second life batteries are assessed both at the cell level and at stack level. Homogeneous and heterogeneous stacks are analysed in order to evaluate the impact of cell-to-cell history and SOH differences over the battery performance and degradation behaviour. Results obtained showed a strong influence of the first life battery ageing history upon the second life battery performance and degradation. Thereby, proper monitoring and battery selection appears crucial to certify the technical viability of battery second life.
Original languageEnglish
Pages (from-to)1-1
Journal IEEE Transactions on Industry Applications
VolumePP
Issue number99
DOIs
StatePublished - 2 Feb 2018

Evaluating the impact of off-hour deliveries: An application of the TRansport Agent-BAsed model

Thu, 01 Feb 2018 00:00:00 GMT

Evaluating the impact of off-hour deliveries: An application of the TRansport Agent-BAsed model

Mommens, K. M., Lebeau, P., Verlinde, S., Van Lier, T. & Macharis, C. Feb 2018 In : Transportation Research Part D: Transport and Environment. 62, p. 102-111 10 p.

Research output: Research - peer-reviewArticle

The expected growth of freight transport should affect the performances of our transport system if we keep with the business as usual. Especially urban settings suffer from congestion and air pollution. Shifting deliveries to the night is considered as one promising solution to alleviate the growing congestion and emissions generated by freight transport. In order to check the compatibility
of night deliveries with its local environment, research has been mostly focused on the analysis of trials and on the impacts it has at a micro level. This paper aims at analysing the impact of night distribution at a macro level. It evaluates the contribution of off hour deliveries on the performances of the transport system. The paper will use TRABAM, a freight transport agent based model, to simulate the impact of different use of night distribution in supermarkets.
The organisation of the freight flows resulting from the new time constraints is then evaluated according the externalities generated by these flows. The analysis shows that a distribution where deliveries are possible only during the day performs the worst since it generates the highest external costs. The business as usual gives already some good performances since night distribution is already used by some supermarkets in Wallonia. But the scenario where a maximum
of one delivery per night is allowed to supermarkets is found to be the best trade-off between the benefits and drawbacks of night distribution.
Original languageEnglish
Pages (from-to)102-111
Number of pages10
JournalTransportation Research Part D: Transport and Environment
Volume62
DOIs
StatePublished - Feb 2018

Rurale roddels

Thu, 01 Feb 2018 00:00:00 GMT

Rurale roddels

Macharis, C. Feb 2018 Verkeersspecialist, 243, p. 26-26

Research output: SpecialistArticle

Original languageDutch
Pages26-26
JournalVerkeersspecialist
PublisherWolters Kluwer
StatePublished - Feb 2018

On the ageing of high energy lithium-ion batteries-comprehensive electrochemical diffusivity studies of Harvested Nickel Manganese Cobalt Electrodes

Tue, 23 Jan 2018 00:00:00 GMT

This paper examines the impact of the characterisation technique considered for the determination of the Li+ solid state diffusion coefficient in uncycled as in cycled Nickel Manganese Cobalt oxide (NMC) electrodes. As major characterisation techniques, Cyclic Voltammetry (CV), Galvanostatic Intermittent Titration Technique (GITT) and Electrochemical Impedance Spectroscopy (EIS) were systematically investigated. Li+ diffusion coefficients during the lithiation process of the uncycled and cycled electrodes determined by CV at 3.71 V are shown to be equal to 3.48 × 10-10 cm2·s-1 and 1.56 × 10-10 cm2·s-1, respectively. The dependency of the Li+ diffusion with the lithium content in the electrodes is further studied in this paper with GITT and EIS. Diffusion coefficients calculated by GITT and EIS characterisations are shown to be in the range between 1.76×10-15 cm2·s-1 and 4.06×10-12 cm2·s-1, while demonstrating the same decreasing trend with the lithiation process of the electrodes. For both electrode types, diffusion coefficients calculated by CV show greater values compared to those determined by GITT and EIS. With ageing, CV and EIS techniques lead to diffusion coefficients in the electrodes at 3.71 V that are decreasing, in contrast to GITT for which results indicate increasing diffusion coefficient. After long-term cycling, ratios of the diffusion coefficients determined by GITT compared to CV become more significant with an increase about 1 order of magnitude, while no significant variation is seen between the diffusion coefficients calculated from EIS in comparison to CV.

Original languageEnglish
Article number176
Number of pages18
JournalMaterials
Volume11
Issue number2
DOIs
StatePublished - 23 Jan 2018

Range-based Multi-Actor Multi-Criteria Analysis: A combined method of Multi-Actor Multi-Criteria Analysis and Monte Carlo simulation to support participatory decision making under uncertainty

Mon, 01 Jan 2018 00:00:00 GMT

Range-based Multi-Actor Multi-Criteria Analysis: A combined method of Multi-Actor Multi-Criteria Analysis and Monte Carlo simulation to support participatory decision making under uncertainty

Baudry, G., Macharis, C. & Vallee, T. 1 Jan 2018 In : European Journal of Operational Research. 264, 1, p. 257-269

Research output: Research - peer-reviewArticle

Concerns about environmental and social effects have made Multi-Criteria Decision Making (MCDM) increasingly popular. Decision making in complex contexts often – possibly always – requires addressing an aggregation of multiple issues to meet social, economic, legal, technical, and environmental objectives. These values at stake may affect different stakeholders through distributional effects characterized by a high and heterogeneous uncertainty that no social actors can completely control or understand. On this basis, we present a new process framework that aims to support participatory decision making under uncertainty: the range-based Multi-Actor Multi-Criteria Analysis (range-based MAMCA). On the one hand, the process framework explicitly considers stakeholders’ objectives at an output level of aggregation. On the other hand, by means of a Monte Carlo analysis, the method also provides an exploratory scenario approach that enables the capture of the uncertainty, which stems from the complex context evolution. Range-based MAMCA offers a unique participatory process framework that enables us (1) to identify the alternatives pros and cons for each stakeholder group; (2) to provide probabilities about the risk of supporting mistaken, or at least ill-suited, decisions because of the uncertainty regarding to the decision-making context; (3) to take the decision-makers’ limited control of the actual policy effects over the implementation of one or several options into account. The range-based MAMCA framework is illustrated by means of our first case study that aimed to assess French stakeholders’ support for different biofuel options by 2030.
Original languageEnglish
Pages (from-to)257-269
JournalEuropean Journal of Operational Research
Volume264
Issue number1
DOIs
StatePublished - 1 Jan 2018

Review of FACTS technologies and applications for power quality in smartgrids with renewable energy systems

Mon, 01 Jan 2018 00:00:00 GMT

Review of FACTS technologies and applications for power quality in smartgrids with renewable energy systems

Heidari Gandoman, F., Ahmadi, A., M Sharaf, A., Siano, P., Pou, J., Hredzak, B. & G. Agelidis, V. 1 Jan 2018 Renewable & Sustainable Energy Reviews, 1, 82, p. 502-514

Research output: VulgarizingArticle

In the last two decades, emerging use of renewable and distributed energy sources in electricity grid has creatednew challenges for the utility regarding the power quality, voltage stabilization and efficient energy utilization.Power electronic converters are extensively utilized to interface the emerging energy systems (without and withenergy storage) and smart buildings with the transmission and distribution systems. Flexible ac transmissionsystems (FACTSs) and voltage-source converters, with smart dynamic controllers, are emerging as a stabilizationand powerfiltering equipment to improve the power quality. Also, distributed FACTSs play an important role inimproving the power factor, energy utilization, enhancing the power quality, and ensuring efficient energyutilization and energy management in smart grids with renewable energy sources. This paper presents a lit-erature survey of FACTS technology tools and applications for power quality and efficient renewable energysystem utilization

Original languageEnglish
Pages502-514
JournalRenewable & Sustainable Energy Reviews
PublisherElsevier
DOIs
StatePublished - 1 Jan 2018

A quick on-line state of health estimation method for Li-ion battery with incremental capacity curves processed by Gaussian filter

Mon, 01 Jan 2018 00:00:00 GMT

This paper proposes an advanced state of health (SoH) estimation method for high energy NMC lithium-ion batteries based on the incremental capacity (IC) analysis. IC curves are used due to their ability of detect and quantify battery degradation mechanism. A simple and robust smoothing method is proposed based on Gaussian filter to reduce the noise on IC curves, and the signatures associated with battery ageing can therefore be accurately identified. A linear regression relationship is found between the battery capacity with the positions of features of interest (FOIs) on IC curves. Results show that the developed SoH estimation function from one single battery cell is able to evaluate the SoH of other batteries cycled under different cycling depth with less than 2.5% maximum errors, which proves the robustness of the proposed method on SoH estimation. With this technique, partial charging voltage curves can be used for SoH estimation and the testing time can be therefore largely reduced. This method shows great potential to be applied in reality, as it only requires static charging curves and can be easily implemented in battery management system (BMS).
Original languageEnglish
Pages (from-to)40-53
JournalJournal of Power Sources
Volume373
Issue number2018
StatePublished - Jan 2018

A Step Towards Demand Sensing: Employing EDI 852 Product Activity Data in Demand Forecasting

Mon, 01 Jan 2018 00:00:00 GMT

A Step Towards Demand Sensing: Employing EDI 852 Product Activity Data in Demand Forecasting

Van Belle, J. E. & Verbeke, W. Jan 2018 Third Conference on Business Analytics in Finance and Industry. Facultad de Ciencias Físicas y Matemáticas, Universidad de Chile, p. 40-40 1 p.

Research output: ResearchMeeting abstract (Book)

This paper deals with short-term demand forecasting of medicines in a US drugs factory based on historical sales and EDI 852
product activity data. Traditionally, demand forecasting relies on statistical methods such as ARIMA, and smoothing methods
such as exponential smoothing, to extrapolate the series of historical sales. Although these methods produce reasonably
accurate forecasts in many cases, companies are looking for an increasingly higher level of forecast accuracy to further enhance
the efficiency of their supply chains. With more and more diverse data becoming available at a higher velocity, it becomes
possible to employ non-traditional data sources and generate forecasts for increasingly shorter time periods. From this point of
view, in recent years, the concept of demand sensing emerged. However, in the scientific literature and empirical studies, the
concept has gained only very little attention to date. Essentially, demand sensing comes down to leveraging a combination of
near real-time (i.e. orders), downstream (ideally point-of-sale) and external data to improve the accuracy of short-term forecasts.
In their purest form, however, the traditional models do not allow for the inclusion of covariates. In this paper a particular type
of downstream data, EDI 852 product activity data (a data standard used for exchanging product related information between
the supplier and the (end)customer), is employed in producing short-term weekly demand forecasts obtained from linear,
dynamic (i.e. with ARIMA errors) and lasso regression and an ETS-X, artificial neural network and support vector regression
model. In order to produce the forecasts, three years of historical weekly factory sales data and weekly wholesaler sales, ending
inventory, on order quantities and receipts for the same time period are used. As a benchmark, also forecasts from an ARIMA
and ETS model are produced. To evaluate the forecast accuracy, we adopt a sliding window approach and measure
out-of-sample RMSE, MAE, MAPE and MASE, so that both comparison between the methods as well as comparison across
different series is facilitated. Our results clearly indicate that forecast accuracy can effectively be improved by leveraging
downstream data from wholesalers. The extent of improvement over traditional forecasting techniques varies between the
forecast items included in the study, as well as between the various models considered. Although linear models can already
produce considerable gains in accuracy levels, nonlinear methods tend to outperform.
Original languageEnglish
Title of host publicationThird Conference on Business Analytics in Finance and Industry
PublisherFacultad de Ciencias Físicas y Matemáticas, Universidad de Chile
Pages40-40
Number of pages1
ISBN (Electronic)0719-8981
StatePublished - Jan 2018
EventBAFI 2018 - Santiago, Chile
Duration: 17 Jan 201819 Jan 2018
Conference number: 3
http://www.bafi.cl/

Conference

ConferenceBAFI 2018
Abbreviated titleBAFI
CountryChile
CitySantiago
Period17/01/1819/01/18
Internet address

Technologies and control for sustainable transportation

Mon, 01 Jan 2018 00:00:00 GMT

Technologies and control for sustainable transportation

Macharis, C. & Veelenturf, L. P. Jan 2018 In : Transportation Research Part C: Emerging Technologies. 86, p. 168-170

Research output: Research - peer-reviewArticle

Original languageEnglish
Pages (from-to)168-170
JournalTransportation Research Part C: Emerging Technologies
Volume86
DOIs
StatePublished - Jan 2018

A robust profit measure for binary classification model evaluation

Mon, 01 Jan 2018 00:00:00 GMT

A robust profit measure for binary classification model evaluation

Garrido, F., Verbeke, W. & Bravo, C. 2018 In : Expert Systems with Applications. 92, p. 154-160 7 p.

Research output: Research - peer-reviewArticle

Using profit-based evaluation measures is a necessity in business-oriented contexts, as they aid companies in making cost-optimal decisions. Among the measures that effectively include the true nature of costs and benefits in binary classification, the expected maximum profit (EMP) has been used successfully for churn prediction and credit scoring, and defined in general for binary classification problems. However, despite its competitive results against the most frequently used measures, the EMP relies on a fixed probability distribution of costs and benefits, the range of which in real applications is not entirely known. In this paper, we propose to extend this measure by adding random shocks to these distributions. We call this new measure the R-EMP, following the convention of the analogous EMP measure. Our metric adds a stochastic component to each point of the cost-benefit distributions, assuming that costs and benefits have a fixed probability, but its distribution range is subject to an external shock, which can be different for each cost or benefit. The experimental setup is focused on a credit scoring application using a dataset of a Chilean financial institution, with the attribute selection for a logistic regression being accomplished using the AUC, EMP, H-measure, and R-EMP as the selection criteria. The results indicate that the R-EMP measure is the most robust metric for achieving the greatest profit for the company under uncertain external conditions.
Original languageEnglish
Pages (from-to)154-160
Number of pages7
JournalExpert Systems with Applications
Volume92
Early online date17 Sep 2017
DOIs
StatePublished - 2018

Can the crowd deliver? Analysis of crowd logistics’ types and stakeholder support

Mon, 01 Jan 2018 00:00:00 GMT

Can the crowd deliver? Analysis of crowd logistics’ types and stakeholder support

Buldeo Rai, H., Verlinde, S., Merckx, J. & Macharis, C. 2018 City Logistics 3: Towards Sustainable and Liveable Cities. Taniguchi, E. & Thompson, R. G. (eds.). Wiley-Blackwell, p. 89-109

Research output: ResearchConference paper

Today’s consumer has high expectations concerning retailers’ delivery services. Meanwhile, the impact of urban freight transport on cities intensifies. Crowd logistics is presented as an interesting innovation that responds to both developments. However, both practice and research contradict this claim. Our research aims to investigate which types of crowd logistics activities currently exist and which types are supported by the stakeholders involved. Therefore, we systematically review existing literature and execute a multi-actor multi-criteria analysis. Our findings indicate that stakeholders’ perceptions diverge significantly, which should be taken into account by both practitioners and policy-makers.
Original languageEnglish
Title of host publicationCity Logistics 3: Towards Sustainable and Liveable Cities
EditorsEiichi Taniguchi, Russell G. Thompson
PublisherWiley-Blackwell
Pages89-109
StatePublished - 2018
EventThe 10th International Conference on City Logistics - JW Marriott Phuket Resort and Spa Hotel, Phuket Island, Thailand
Duration: 14 Jun 201716 Jun 2017

Conference

ConferenceThe 10th International Conference on City Logistics
CountryThailand
CityPhuket Island
Period14/06/1716/06/17

Do you see what I see?: A simulation analysis of order bundling within a transparent user network in geographic space

Mon, 01 Jan 2018 00:00:00 GMT

Do you see what I see?: A simulation analysis of order bundling within a transparent user network in geographic space

Ambra, T., Caris, A. & Macharis, C. 2018 Do you see what I see? : A simulation analysis of order bundling within a transparent user network in geographic space. p. 1-16 16 p.

Research output: ResearchConference paper

Assuming the universal network openness, the users can tap into the PI network and place orders which will be assigned to the nearest available transport service and consequently delivered to the order sender. The objective of our paper is to investigate the impact of stochastic insertion of service points into existing dedicated freight flows of a service driven company. We simulate different transparency levels, routings and pick-up locations, and evaluate the impact in terms of altered lead-times, covered distances and fill rates. The novel aspects presented herein are 1) deliveries based on decentralized location detection of the nearest order sender, 2) dynamically changing speed parameters within specific geographic clusters based on geo-locations of agents to account for congestion levels, 3) more realistic routing strategies that consider the urban layout and 4) transparent querying of nearest agents in space and time that meet specific conditions such as current ongoing processes, available capacity and position. Finally, we identify impact from a holistic/system perspective based on emergence of individual asset performances.
Original languageEnglish
Title of host publicationDo you see what I see?
Subtitle of host publicationA simulation analysis of order bundling within a transparent user network in geographic space
Pages1-16
Number of pages16
StateUnpublished - 2018
Event5th International Physical Internet Conference - University of Groningen, Groningen, Netherlands
Duration: 18 Jun 201822 Jun 2018
https://www.pi.events/

Conference

Conference5th International Physical Internet Conference
Abbreviated titleIPIC 2018
CountryNetherlands
CityGroningen
Period18/06/1822/06/18
Internet address

From Desirable to Feasible: Fostering Inter-Institutional Cooperation with Competence-based Multi Criteria Analysis (COMCA)

Mon, 01 Jan 2018 00:00:00 GMT

Original languageEnglish
Title of host publicationMAMCA
PublisherEdward Elgar Publishing Ltd.
StateAccepted/In press - 2018

Geographies of transportation in the twenty-first century

Mon, 01 Jan 2018 00:00:00 GMT

Geographies of transportation in the twenty-first century

Szalkai, G., Jancsovics, A., Keserü, I., Macharis, C., Nemeth, B. & Oszter, V. 2018 New Geographies of the Globalized World. Solarz, M. W. (ed.). London and New York: Routledge, p. 93-114 (Routledge Studies in Human Geography; vol. 75)

Research output: Research - peer-reviewChapter

Original languageEnglish
Title of host publicationNew Geographies of the Globalized World
EditorsMarcin Wojciech Solarz
Place of PublicationLondon and New York
PublisherRoutledge
Pages93-114
ISBN (Print)978-1-138-67641-1
StatePublished - 2018

Publication series

NameRoutledge Studies in Human Geography
PublisherRoutledge
Volume75

Mobility is a serious game : a game to explore the future of mobility

Mon, 01 Jan 2018 00:00:00 GMT

Mobility is a serious game : a game to explore the future of mobility

Macharis, C. 2018 Mobility is a serious game : a game to explore the future of mobility. 18-02432

Research output: ResearchConference paper

Our society is changing rapidly and its mobility system does not keep pace. We are still driving around in diesel cars, not internalising external costs, not using multimodality in its full potential, etc. Although there is more and more consensus that we should go for a more sustainable mobility system, it does not seem to be easy to implement it and to create a common vision of the future. Thinking about that future is also not that easy. For this reason we created the board game « Mobility is a serious game ». It enables to explore the future of mobility in three time horizons: near future (1 to 5 years), medium (5-10 years) and long (up to 30 years). It is an interactive setting where the players can put themselves into the roles of either a government (local or higher), a business (up to two players), an NGO (also maximum two players) and the public voice. This public voice has an important role as he/she will comment on the actions of the others players and so reward their actions with coins. The game has been tried out several times before launching it on a large event. The game enables to connect people, show empathy for each other's role and let new and collaborative ideas surface.
Original languageEnglish
Title of host publicationMobility is a serious game : a game to explore the future of mobility
StatePublished - 2018
EventTransportation Research Board 97th Annual Meeting - Washington, D.C., United States
Duration: 7 Jan 201811 Jan 2018

Conference

ConferenceTransportation Research Board 97th Annual Meeting
CountryUnited States
CityWashington, D.C.
Period7/01/1811/01/18

Rethinking mobility for a human city

Mon, 01 Jan 2018 00:00:00 GMT

Rethinking mobility for a human city

Macharis, C. & Keseru, I. 2018 In : Transport Reviews. 38, 3, p. 275-278

Research output: Research - peer-reviewArticle

Original languageEnglish
Pages (from-to)275-278
JournalTransport Reviews
Volume38
Issue number3
DOIs
StatePublished - 2018

Rhythmic Keccak: SCA Security and Low Latency in HW

Mon, 01 Jan 2018 00:00:00 GMT

Rhythmic Keccak: SCA Security and Low Latency in HW

Arribas, V., Bilgin, B., Petrides, G., Nikova, S. & Rijmen, V. 2018 In : IACR Transactions on Cryptographic Hardware and Embedded Systems. 2018, 1, p. 269-290 22 p.

Research output: Research - peer-reviewArticle

Glitches entail a great issue when securing a cryptographic implementation in hardware. Several masking schemes have been proposed in the literature that provide security even in the presence of glitches. The key property that allows this protection was introduced in threshold implementations as non-completeness. We address crucial points to ensure the right compliance of this property especially for low-latency implementations. Specifically, we first discuss the existence of a flaw in DSD 2017 implementation of Keccak by Gross et al. in violation of the non-completeness property and propose a solution. We perform a side-channel evaluation on the first-order and second-order implementations of the proposed design where no leakage is detected with up to 55 million traces. Then, we present a method to ensure a non-complete scheme of an unrolled implementation applicable to any order of security or algebraic degree of the shared function. By using this method we design a two-rounds unrolled first-order Keccak-f[200] implementation that completes an encryption in 20.61ns, the fastest SCA secure implementation in the literature to this date.
Original languageEnglish
Pages (from-to)269-290
Number of pages22
JournalIACR Transactions on Cryptographic Hardware and Embedded Systems
Volume2018
Issue number1
DOIs
StatePublished - 2018

Scenarios for the future of mobility in Europe: Combining the scenario technique with the Multi-Actor Multi-Criteria Analysis (MAMCA)

Mon, 01 Jan 2018 00:00:00 GMT

Mobility4EU is a project that aims to deliver a vision and action plan for the European transport system in 2030. It aims to identify societal trends that will influence future transport demand and supply and compile a portfolio of promising cross-modal technical and organisational solutions that address these trends. At the heart of this process lies the Multi-Actor Multi-Criteria Analysis (MAMCA) to assess the preferences of stakeholder groups across the whole transport and mobility spectrum (e.g. transport users, vehicle manufacturers, infrastructure managers, public authorities) regarding scenarios for 2030. While in previous applications of MAMCA, the scenarios were defined by the decision maker, this research proposes the combination of the intuitive logics scenario technique and the normative narrative method with MAMCA to appraise the preferences of fourteen stakeholder groups towards future scenarios for mobility in Europe by 2030 emphasizing the participative nature of the scenario building. Based on a survey of 33 stakeholders, we identified “policy & legislative framework” and “lifestyle & user behaviour” as pivotal uncertainties to steer the scenario building. They provided the basis for the development of four alternative scenarios: Data World, Digital Nomads, Slow is Beautiful, Minimum Carbon. Each narrative scenario describes future trends and technological, organisational or policy-related solutions to respond to the trends. In the next steps of the MAMCA a stakeholder analysis mapped relevant stakeholder groups and identified their objectives. The objectives were translated into criteria and each stakeholder group (224 stakeholders) weighted the importance of these criteria through an online survey. Then a panel of international experts evaluated the impact of each scenario on each criterion. Then we used the PROMETHEE method to produce a ranking of scenarios for each stakeholder group highlighting synergies and conflicts between the stakeholders. The scenarios Digital Nomads and Minimum Carbon are the highest rated for most of the stakeholder groups. This points to the importance of government intervention as both scenarios propose a pronounced role of governments in supporting innovation and interoperability. On the other hand, there is a disagreement whether the transport system should support an individualistic model of society, or a mobility system where resources are shared. These results were discussed with the stakeholders at a dedicated consensus-making workshop to come to a consensus on the consolidated scenario that best represents their objectives. This scenario has been taken forward to the Vision and Action Plan.
Original languageEnglish
StatePublished - 2018
EventFuture-oriented Technology Analysis 2018 - Brussels, Belgium
Duration: 4 Jun 20185 Jun 2018

Conference

ConferenceFuture-oriented Technology Analysis 2018
Abbreviated titleFTA2018
CountryBelgium
CityBrussels
Period4/06/185/06/18

Total Cost for Society: A Persona-based Analysis of Electric and Conventional Vehicles

Mon, 01 Jan 2018 00:00:00 GMT

Total Cost for Society: A Persona-based Analysis of Electric and Conventional Vehicles

De Clerck, Q., Van Lier, T., Messagie, M., Macharis, C., Van Mierlo, J. & Vanhaverbeke, L. 2018 In : Transportation Research Part D: Transport and Environment. p. xx 21 p., xx

Research output: Research - peer-reviewArticle

The purchase and usage of a car comes at a cost for the owner, i.e. the Total Cost of Ownership, but also causes costs to society, i.e. external costs. Summing up the privately borne costs with the publicly borne costs results in the Total Cost for Society.

To assess how ownership costs and external costs are currently balanced in the Total Cost for Society for different vehicle technologies, we present a persona-based analysis of the costs categories associated with the ownership and usage of electric and conventional cars within three passenger car segments. Six persona represent diverse driver profiles with different mobility patterns in Flanders (Belgium).

We find that the balance between ownership costs and external costs is highly variable given the assumed persona, while for each persona the ranking between the vehicle technologies themselves does not vary much.
Original languageEnglish
Article numberxx
Pages (from-to)xx
Number of pages21
JournalTransportation Research Part D: Transport and Environment
StatePublished - 2018

Transferia: solving local pain or bringing global gain?

Mon, 01 Jan 2018 00:00:00 GMT

Transferia: solving local pain or bringing global gain?

Meers, D., Vermeiren, T. & Macharis, C. 2018 In : International Journal of Logistics Research and Applications. 21, 2, p. 148-159

Research output: Research - peer-reviewArticle

Original languageEnglish
Pages (from-to)148-159
JournalInternational Journal of Logistics Research and Applications
Volume21
Issue number2
DOIs
StatePublished - 2018

Travel-based multitasking: review of the empirical evidence

Mon, 01 Jan 2018 00:00:00 GMT

Travel-based multitasking: review of the empirical evidence

KESERü, I. & Macharis, C. 2018 In : Transport Reviews. 38, 2, p. 162-183

Research output: Research - peer-reviewArticle

This paper reviews 58 studies with empirical evidence on travel-based multitasking, identifies gaps in terms of data collection methods and provides a comprehensive review of findings about the significance of variables with an impact on the prevalence and type of multitasking. We identified the limitations of quantitative or qualitative surveys and advocate a mixed methods approach to provide an in-depth understanding of travel-based multitasking. We revealed that cross-country comparisons are missing due to the lack of empirical evidence outside the developed countries. While there are indications of increasing multitasking with mobile devices, we found only two longitudinal surveys that provide evidence. We call for a standardisation of definitions of multitasking activities to enable more longitudinal research. We identified 75 variables that were tested for impact on travel-based multitasking in previous research, of which 60 were found to be significant. Sufficient evidence (i.e. minimum three papers), however, only exists for age, gender, trip duration, travel mode, trip purpose, time of the day and day of the week of the trip and the presence of a travel companion. Therefore, more research is suggested to determine the influence of attitude, comfort, availability of equipment, time use and spatial attributes on the type and prevalence of travel-based multitasking.

Original languageEnglish
Pages (from-to)162-183
JournalTransport Reviews
Volume38
Issue number2
Early online date28 Apr 2017
DOIs
StatePublished - 2018