Digital Group

@inproceedings{martin-prin_1890,

title = {A Distributed SAT-based Framework for Closed Frequent Itemset Mining},

author = {Julien Martin-Prin and Imen Ouled Dlala and Nicolas Travers and Said Jabbour},

url = {https://adma2022.uqcloud.net/important_date.html},

year  = {2022},

date = {2022-11-01},

booktitle = {International Conference on Advanced Data Mining and Applications},

publisher = {Springer},

address = {Brisbane, Australia},

abstract = {Frequent Itemset Mining is an essential part of data mining. SAT-based approaches that extract frequent itemsets in big data encounter significant challenges when computing power and storage capacity are limited. This paper proposes an efficient distributed SAT-based framework for the Closed Frequent Itemset Mining problem (CFIM) which minimizes communications throughout the distributed architecture and reduces bottlenecks due to shared memory. Moreover, it enhances scalability and fault tolerance. This approach makes use of a Computation-Distributed Paradigm to enumerate efficiently the set of all closed itemsets, by reducing the processing time. To the best of our knowledge, this paper presents the first attempt towards a distributed SAT-based approach for CFIM. An extensive empirical evaluation on various real-word datasets shows the efficiency of the approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{prevoteau_1921,

title = {Propagation Measure on Circulation Graphs for Tourism Behavior Analysis},

author = {Hugo Prevoteau and Sonia Djebali and Zhao Laiping and Nicolas Travers},

url = {https://bda2022.sciencesconf.org/resource/page/id/13},

year  = {2022},

date = {2022-10-01},

booktitle = {Bases de Données Avancées},

address = {Clermont-Ferrand, France},

abstract = {Social network analysis has widespread in recent years, especially in digital tourism. Indeed the large amount of data that tourists produce during their travels represents an effective source to un- derstand their behavior and is of great importance for tourism stakeholders. This paper studies the propagation effect of tourists on the territory thanks to geotagged circulation graphs.

A new weighted measure is introduced for circulation charac- terization based on both topologies and distances. This measure helps to determine the behavior of tourists on local and global areas. An optimization strategy based on spanning trees is applied to reduce the computation on the whole graph while keeping a good approximation of the behavior.},

keywords = {},

pubstate = {online},

tppubtype = {inproceedings}

}

@inproceedings{prevoteau_1749,

title = {Propagation Measure on Circulation Graphs for Tourism Behavior Analysis},

author = {Hugo Prevoteau and Sonia Djebali and Zhao Laiping and Nicolas Travers},

url = {https://www.sigapp.org/sac/sac2022/index.html},

year  = {2022},

date = {2022-04-01},

booktitle = {ACM Symposium on Applied Computing},

publisher = {ACM},

address = {Brno, Czec Republic},

abstract = {Social network analysis has widespread in recent years, especially in digital tourism. Indeed the large amount of data that tourists produce during their travels represents an effective source to understand their behavior and is of great importance for tourism stakeholders. This paper studies the propagation effect of tourists on the territory thanks to geotagged circulation graphs. Those graphs reflect traffic flows which need to be analyzed over time and space. A new weighted measure is introduced for circulation characterization based on both topologies and distances. This measure helps to determine the behavior of tourists on local and global areas. An optimization strategy based on spanning trees is applied to reduce the computation on the whole graph while keeping a good approximation of the behavior. The approach is simulated on various graphs and evaluated experimentaly over a real dataset at various geographic zones, scales, communities, and time.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{haikal_1767,

title = {Place Embedding across Cities in Location-based Social Networks},

author = {Christophe Haikal and Pegah Alizadeh and Christophe Rodrigues and Bi Chongke},

url = {https://www.sigapp.org/sac/sac2022/file2022/TOC-Jan-23-2022.pdf},

year  = {2022},

date = {2022-04-01},

booktitle = {ACM Symposium on Applied Computing},

address = {Brno, Czech Republic},

abstract = {In the urban computing field, analysing human mobility patterns are used to understand tourists and residents behaviours, or urban areas functionalities. Transferring the information from one city to another also assists urban strategists in comparing two cities

and applying their knowledge from one to another, such as plan- ning new touristic attractions or implementing some successful urban strategies in new cities. For this goal, in this work, we propose a twofold semi-supervised approach: we first propose a place embedding method based on users mobility trajectories in each city individually, second we learn a place translation function between two cities using the set of reviews written for each place. The translation function is based on measuring textual and semantic

similarities of the reviews. Extensive experiments on two french metropolitan areas (Lille and Bordeaux) based on the extracted data from Trip-Advisor demonstrate the effectiveness of our approach.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mali_1804,

title = {A Global Model-Driven Denormalization Approach for Schema Migration},

author = {Jihane Mali and Ahvar Shohreh and Faten Atigui and Ahmed Azough and Nicolas Travers},

year  = {2022},

date = {2022-03-01},

booktitle = {International Conference on Research Challenges in Information Science},

publisher = {Springer},

address = {Barcelona, Spain},

abstract = {Abstract. With data's evolution in terms of volume, variety, and ve- locity, Information Systems (IS) administrators have to steadily adapt their data model and choose the best solution(s) to store and manage data in accordance with users' requirements. In this context, many exist- ing solutions transform a source data model into a target one, but none of them leads the administrator to choose the most suitable model by offering a limited solution space automatically calculated and adapted to his needs. We propose ModelDrivenGuide, an automatic global approach for leading the model transformation process. It starts by transforming the conceptual model into a logical model, and it defines refinement rules that help to generate all possible data models. Our approach then relies on a heuristic to reduce the search space by avoiding cycles and redun- dancies. We also propose a formalisation of the denormalization process and we discuss the completeness and the complexity of our approach.},

keywords = {},

pubstate = {accepted},

tppubtype = {inproceedings}

}

@inproceedings{talbi_1741,

title = {Feature Importance And Deep Learning For Android Malware Detection},

author = {Adam Talbi and Arthur Viens and Louis-Clément Leroux and Morgane François and Mathias Caillol and Nga Nguyen},

url = {https://icissp.scitevents.org/Home.aspx},

year  = {2022},

date = {2022-02-01},

booktitle = {International Conference on Information Systems Security and Privacy},

address = {Vienna, Austria},

abstract = {Effective and efficient malware detection is key in today's world to prevent systems from being compromised, to protect personal user data, and to tackle other security issues. In this paper, we worked on Android malware detection by using static analysis features and deep learning methods to separate benign applications from malicious ones. Custom feature vectors are extracted from the Drebin and the AndroZoo dataset and different data science methods of feature importance are used to improve the results of Deep Neural Network classification. 

Experimental results on the Drebin dataset were significant with 99.31% accuracy in malware detection. We extended our work on more recent applications with a complete pipeline for the AndroZoo dataset, with about 40,000 APKs used from 2014 to 2021 pre-tagged as reported malicious or not. The pipeline includes static features extracted from the manifest file and bytecode such as suspicious behaviors, restricted and suspicious API calls, etc. The accuracy result for AndroZoo is 97.7%, confirming the power of deep learning on Android malware detection.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{osmani_1768,

title = {Clustering Approach to Solve Hierarchical Classification Problem Complexity},

author = {Aomar Osmani and Massinissa Hamidi and Pegah Alizadeh},

url = {The proceeding is not ready yet. 

Even the list of accepted papers is not published yet. I will modify this part as soon as I have them.},

issn = {will be completed later},

year  = {2022},

date = {2022-01-01},

booktitle = {AAAI Conferece on Artificial Intelligence},

address = {Vancouver, Canada},

abstract = {In a large domain of classification problems for real applications, like human activity recognition, separable spaces between groups of concepts are easier to learn than each concept alone. This is because the search space biases required to separate groups of classes (or concepts) are more relevant than the ones needed to separate classes individually. For example, it is easier to learn the activities related to the body

movements group (running, walking) versus ?on-wheels? activities group (bicycling, driving a car), before learning more specific classes inside each of these groups. Despite the ob-

vious interest of this approach, our theoretical analysis shows a high complexity for finding an exact solution. We propose in this paper an original approach based on the association of clustering and classification approaches to overcome this limitation. We propose a better approach to learn the concepts by grouping classes recursively rather than learning them class by class. We introduce an effective greedy algorithm and two theoretical measures (namely cohesion and dispersion) to evaluate the connection between the clusters and the classes. Extensive experiments on the SHL dataset show that our approach improves classification performances while reducing the number of instances used to learn each concept.},

keywords = {},

pubstate = {accepted},

tppubtype = {inproceedings}

}

@inproceedings{guerard_1662,

title = {Tourists Profiling by Interest Analysis},

author = {Guillaume Guérard and Sonia Djebali and Quentin Gabot},

url = {https://link.springer.com/chapter/10.1007/978-3-030-95408-6_4},

issn = {978-3-030-95407-9},

year  = {2022},

date = {2022-01-01},

booktitle = {International Conference on Advanced Data Mining and Applications},

volume = {13088},

pages = {42-53},

publisher = {Springer, Cham},

address = {Virtual},

abstract = {With the recent digital revolution, analyzing of tourists' behaviors

and research elds associated with it have changed profoundly.

It is now easier to examine behaviors of tourists using digital traces they

leave during their travels. The studies conducted on diverse aspects of

tourism focus on quantitative aspects of digital traces to reach its conclusions.

In this paper, we suggest a study focused on both qualitative and

quantitative aspect of digital traces to understand the dynamics governing

tourist behavior, especially those concerning attractions networks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hidouri_1766,

title = {On Minimal and Maximal High Utility Itemsets Mining using Propositional Satisfiability},

author = {amel Hidouri and Said Jabbour and Imen Ouled Dlala and Badran Raddaoui},

url = {https://doi.org/10.1109/BigData52589.2021.9671422},

issn = {978-1-6654-4599-3},

year  = {2021},

date = {2021-12-01},

booktitle = {IEEE International Conference on Big Data},

address = {Orlando, FL, USA},

abstract = {Mining high utility itemsets is a keystone data mining method for discovering useful itemsets yielding high utility values. Minimal and maximal high utility itemsets are

two examples of compact representations used to reduce the

output size due to not only the large but incomprehensible

number of patterns. Despite the variety of proposed solutions to

tackle this problem, it still provides methods with less flexibility.

In this paper, we present a novel method for translating the

problem of mining minimal and maximal high utility itemsets

into a propositional satisfiability problem. In order to find these

patterns of interest, we demonstrate that the task of minimal and maximal patterns is equivalent to enumerating the X-

minimal models of a given CNF formula. Then, to improve the

scalability issue, we harness a decomposition paradigm that splits

the transaction database into smaller and independent sub-bases, allowing an efficient enumeration of minimal and maximal high

utility itemsets. Finally, through extensive evaluation studies on

various real-world datasets, we demonstrate that our approach is

very competitive w.r.t. to the state-of-the-art specialized solutions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nguyen_1596,

title = {RobAFIS: Lessons Learned from a Robotic Systems Engineering Challenge},

author = {Nga Nguyen},

url = {https://2021.ieeeisse.org/wp-content/uploads/sites/37/2021/08/ISSE_2021_Program-02.pdf},

year  = {2021},

date = {2021-09-01},

booktitle = {2021 International Symposium on Systems Engineering Proceedings},

address = {Vienna, Austria},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tran_1562,

title = {LINKING FLEXIBILITY AND FIRM PERFORMANCE: THE MEDIATING ROLE OF INNOVATION CAPABILITIES},

author = {Thi Thanh Huong Tran and Nicholas Paparoidamis and Maud Van den Broeke},

url = {https://www.pdma.org/page/conference-central},

year  = {2021},

date = {2021-07-01},

booktitle = {JPIM Research Forum 2021},

address = {Maryland, USA},

abstract = {Flexibility is widely recognized as a valuable competitive tool for firms in today's dynamic and uncertain environment; however, existing research on its impact on firm performance reports mixed and contradictory results, which has prevented scholarly and practical advancement on the topic. Drawing on the resource-based view with a dynamic capability perspective, we develop a conceptual model to investigate the underlying mechanism of the impact of different flexibility dimensions on firm performance. Based on a sample of 200 companies operating in France, we provide empirical evidence that both exploratory and exploitative innovation play a significant and full mediating role in the link between volume and mix flexibility and firm performance whereas only exploratory innovation fully mediates the effect of new product flexibility on firm performance. Our findings contribute to existing theoretical knowledge and offer important managerial implications as well as fruitful future research avenues.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{belemkoabga_1586,

title = {Neural Network-Based Generation of Sport Summaries: a Preliminary Study},

author = {David Stéphane Belemkoabga and Aurélien Bossard and Abdallah Essa and Christophe Rodrigues and Kévin Sylla},

url = {https://ranlp.org/ranlp2021/proceedings.pdf},

year  = {2021},

date = {2021-07-01},

booktitle = {Proceedings of Recent Advances in Natural Language Processing},

pages = {152-159},

address = {Varna, Bulgaria},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{zigrand_1542,

title = {Machine Learning Guided Optimization for Demand Responsive Transport Systems},

author = {Louis Zigrand and Pegah Alizadeh and Emiliano Traversi and Roberto Wolfer Calvo},

url = {https://2021.ecmlpkdd.org/wp-content/uploads/2021/07/sub_383.pdf},

year  = {2021},

date = {2021-06-01},

booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database},

address = {Bilbao Spain (online)},

abstract = {Most of the time, objective functions used for solving staticcombinatorial  optimization  problems  cannot  deal  efficiently  with  theirreal-time counterparts. It is notably the case of Shared Mobility Systemswhere the dispatching framework must adapt itself dynamically to thedemand. More precisely, in the context of Demand Responsive Transport(DRT) services, various objective functions have been proposed in theliterature to optimize the vehicles routes. However, these objective func-tions are limited in practice because they discard the dynamic evolutionof  the  demand.  To  overcome  such  a  limitation,  we  propose  a  MachineLearning  Guided  Optimization  methodology  to  build  a  new  objectivefunction based on simulations and historical data. This way, we are ableto take the demand's dynamic evolution into account. We also presenthow to design the main components of the proposed framework to fit aDRT application: data generation and evaluation, training process andmodel  optimization.  We  show  the  efficiency  of  our  proposed  method-ology on real-world instances, obtained in a collaboration with PadamMobility, an international company developing Shared Mobility Systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{osmani_1543,

title = {Equational Model Guided by Real-time Sensor Data to Monitor Industrial Robots},

author = {Aomar Osmani and Pegah Alizadeh and Christophe Rodrigues},

url = {https://case2021.sciencesconf.org/},

year  = {2021},

date = {2021-06-01},

booktitle = {International Conference on Automation Science and Engineering},

address = {Lyon, France},

abstract = {The monitoring of industrial robots is often en-

sured by generic simulators which model the equational aspect

of the target machines. We propose an original approach to

complete the equational simulator of a milling machine using

the accumulated data from the used sensors. This approach cre-

ates a specific simulator for each machining situation by taking

the triplet (material, cutting tool, workpiece) into account. This

improvement brings great added value to the industrial experts

and improves the efficiency of industrial robots. It allows them

to better follow and interpret the behavior of machines during

the milling process. In addition to correct the simulator using

real data, our method detects also the anomalies during the

real manufacturing performance and fixes the minor bugs

along the observed real data during its continuous simulation

mimicry. The additional interest of our model remains the

precise definition of the complementary model between the real

system and the equational simulator. This makes it possible, by

using an inductive approach to search for regularities in the

model in order to better interpret the structural differences

between the model and the system and to better understand

the situations linked to their functionalities or undesirable

situations. The intensive experiments on real data validate our

model and open up many perspectives for future works.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{guerard_1601,

title = {Hidden Markov Model to Predict Tourists Visited Places},

author = {Guillaume Guérard and Sonia Djebali and Bi Chongke and Theo Demessance},

editor = {Vana Kalogeraki, Nick Koudas, Jianliang Xu},

url = {https://ieeexplore.ieee.org/abstract/document/9474900},

issn = {978-1-6654-2845-3},

year  = {2021},

date = {2021-06-01},

booktitle = {22nd IEEE International Conference on Mobile Data Management},

pages = {209-216},

publisher = {IEEE},

address = {virtual},

abstract = {Nowadays, social networks is become a popular means of analyzing tourist behavior, thanks to the digital traces left by travelers during their stays on these networks. 

The massive amount of data generated by the propensity of tourists to share comments and photos during their trip makes it possible to model their journeys and analyze their behavior. 

Predicting the next movement of tourist plays a key role in tourism marketing to understand demand and improve decision support. 



In this paper, we propose a method to understand and to learn tourists' movements based on social network data analysis to predict the future movements. The method relies on a machine learning grammatical inference algorithm. 

A major contribution in this paper is to adapt the grammatical inference algorithm to the context of big data. 

Our method produces a hidden Markov model representing the movements of a group of tourists. The hidden Markov model is flexible and editable with new data. 

The capital city of France, Paris is selected to demonstrate the efficiency of the proposed methodology.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{djebali_1602,

title = {Bidding strategy of a seasonal storage and pump storage hydropower plants in reserve markets},

author = {Sonia Djebali and Guillaume Guérard and Laureen Deman and Quentin Boucher and Cedric Clastres},

url = {https://iaee2021online.org/download/contribution/fullpaper/1380/1380_fullpaper_20210614_063233.pdf},

year  = {2021},

date = {2021-06-01},

booktitle = {International Association for Energy Economics},

address = {virtual},

abstract = {The increasing share of intermittent sources of energy will increase the need for frequency-control reserves. However, the  current  supply  of  reserves  might  decrease  in  the  following  years.  The  share  of  gas-  and  coal-fuel  plants  in  the power mix is expected to decline in order to reduce greenhouse gas emissions. Hydropower technologies are often put forward as mature and low-carbon technologies able to contribute to cover this increasing need for reserves.  Their flexibility and storage capability allow them to support the stable operation of the grid. The procurement of reserves being  mostly  market-based  in  Europe,  the  market  design  should  send  the  correct  price  signals  to  encourage  the participation in these markets.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{maar_1475,

title = {The ambiguous role of fear of missing out in shaping the online experience and brand relationship of brand account followers on Instagram},

author = {Daniel Maar and Hajer Kefi and Mehmet A. Orhan},

url = {https://www.emac-online.org/},

year  = {2021},

date = {2021-05-01},

booktitle = {Proceedings of the European Marketing Academy EMAC 2021 Annual Conference},

address = {Madrid, Spain},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{guerard_1600,

title = {Tourism Management through the Big Data Paradigm},

author = {Guillaume Guérard and Sonia Djebali},

editor = {David Chavalarias, Hocine Cherifi},

url = {https://easychair.org/smart-program/FRCCS2021/},

year  = {2021},

date = {2021-05-01},

booktitle = {French Regional Conference on Complex Systems FRCCS},

publisher = {Springer - Applied Network Science Journal},

address = {virtual},

abstract = {This paper highlights the two-ways relationship between data and entities producing or generating these data in the context of tourism management. Indeed,  tourists leave various traces of their planning and trip on social media and networks. Moreover, studying those data to feed tourism marketing also affects the future data left by tourists. Understanding the intrinsic and extrinsic relationship between entities should significantly improve the knowledge in this research field.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{osmani_1499,

title = {Hierarchical Learning of Dependent Concepts for Human Activity Recognition},

author = {Aomar Osmani and Massinissa Hamidi and Pegah Alizadeh},

editor = {Karlapalem K. et al.},

url = {https://link.springer.com/chapter/10.1007/978-3-030-75765-6_7},

issn = {978-3-030-75764-9},

year  = {2021},

date = {2021-04-01},

booktitle = {Pacific-Asia Conference on Knowledge Discovery and Data Mining},

volume = {12713},

pages = {79-92},

publisher = {Springer, Cham},

address = {Dehli, India},

abstract = {In multi-class classification tasks, like human activity recog-

nition, it is often assumed that classes are separable. In real applications,

this assumption becomes strong and generates inconsistencies. Besides,

the most commonly used approach is to learn classes one-by-one against

the others. This computational simplification principle introduces strong

inductive biases on the learned theories. In fact, the natural connections

among some classes, and not others, deserve to be taken into account.

In this paper, we show that the organization of overlapping classes (mul-

tiple inheritances) into hierarchies considerably improves classification

performances. This is particularly true in the case of activity recognition

tasks featured in the SHL dataset. After theoretically showing the expo-

nential complexity of possible class hierarchies, we propose an approach

based on transfer affinity among the classes to determine an optimal hi-

erarchy for the learning process. Extensive experiments show improved

performances and a reduction in the number of examples needed to learn.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{teyssier_1813,

title = {Human-Like Artificial Skin Sensor for Physical Human-Robot Interaction},

author = {Marc Teyssier and Brice Parilusyan and Anne Roudaut and Jürgen Steimle},

editor = {IEEE},

url = {https://ieeexplore.ieee.org/document/9561152},

issn = {9781728190785},

year  = {2021},

date = {2021-04-01},

booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},

pages = {3626-3633},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

address = {Xi'an, China},

edition = {2021},

abstract = {Physical Human-Robot-Interaction (pHRI) is beneficial for communication in social interaction or to perform collaborative tasks but is also crucial for safety. While robotic devices embed sensors for this sole purpose, their design often is the results of a trade-off between technical capabilities and rarely considers human factors. We propose a novel approach to design and fabricate compliant Human-like artificial skin sensors for robots, with similar mechanical properties as human skin and capable of precisely detecting touch. Our artificial skin relies on the use of different silicone elastomers to replicate the human skin layers and comprises an embedded electrode matrix to perform mutual capacitance sensing. We present the sensor and describe its fabrication process which is scalable, low-cost and ensures flexibility, compliance and robustness. We introduce Muca, an open-source sensing development board and then evaluate the performance of the sensor.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}