Résumé

Predicting Gestational Diabetes Mellitus (GDM) is crucial for
pregnant women to enable regular monitoring of their blood sugar levels and
adherence to a healthy diet. Early intervention can significantly lower the risk
of developing this condition. To assess this risk, Machine Learning (ML) and
Deep Learning techniques are employed. However, traditional ML models often
face challenges in accurately predicting GDM risk due to the complex
processing required to optimize their hyperparameters for the best performance.
This study presents a feature selection for GDM prediction using AutoML-XAI
techniques (Automatic Machine Learning – eXplainable Artificial Intelligence
techniques) approach, which aims to automatically predict GDM risk as
accurate as possible while providing meaningful interpretations of the
predictive results used in feature selection. The AutoML models generated
utilize a Kaggle dataset and several combinations of features selected based on
their scores of importance determinated with XAI techniques such as SHAP

(Shapley Additive Explanations) and LIME (Local Interpretable Model-
agnostic Explanations). The proposed approach of autoML and features

selection with XAI techniques leads to the creation of a precise, efficient, and
easily interpretable model which surpasses other machine learning models in
predicting GDM risk without the need for human intervention. The scores of
importance of features are involved in the feature selection process and
multiple AutoML models are generated and assessed, with the optimal AutoML
model being established automatically.

Résumé

Stock markets have an important impact on economic growth of countries. The prediction
of stock market indexes has been a complex task for last years. Indeed, many researches and financial analysts are highly interested in the research area of stock market prediction. In this paper, we propose a novel framework, titled AutoCNN based on artificial intelligence techniques, to predict future stock market indexes. AutoCNN is composed mainly of three stages: (1) CNN for Automatic Feature Extraction, (2) The Halving Grid Search algorithm is combined to CNN model for stock indexes prediction and (3) Evaluation and recommendation. To validate our AutoCNN, we conduct experiments on two financial datasets that are extracted in the period between 2018 and 2023, which includes several events such as economic, health and geopolitical international crises. The performance of AutoCNN model is quantified using various metrics. It is benchmarked against different models and it proves strong prediction abilities. AutoCNN contributes to emerging technologies and innovation in the financial sector by automating decision-making, leveraging advanced pattern recognition, and enhancing the overall decision support system for investors in the digital economy.

Résumé

Stock markets are highly volatile, complex, non-linear, and stochastic. Therefore, predicting stock market behavior is one of finance’s most complex challenges. Recently, political, health, and economic crises have profoundly impacted global stock prices, leading researchers to use machine learning to predict prices and analyze financial data. This article delves into two primary facets: firstly, examining stock price responses to the Russia-Ukraine war and the COVID-19 pandemic by assessing volatility and draw-downs from 2018 to 2023. Secondly, we introduce a framework named StockPredCris, designed to predict future stock indices employing two machine learning algorithms: Support Vector Regression (SVR) and eXtreme Gradient Boosting (XGBoost). Our experiments are conducted on four major stock market indices (NASDAQ, Russell 2000, DAX, and SSE) using a combination of historical stock index data and COVID-19 pandemic data. The performance of the implemented models is evaluated using five regression metrics along with the CPU time metric. The results of SVR demonstrates superior performance and signifcantly outperforms the other considered models for benchmarking. For instance, SVR achieved 0.0 MSE and 99.99% R for the four stock indices, with training times between 0.005 and 0.007 seconds. We recommend SVR for predicting future stock prices during crises. This study offers valuable insights for financial decision-makers, guiding them in making informed choices by understanding stock market reactions to major global crises, while addressing the uncertainty and fear of investors.

Résumé

The continuous development of Internet infrastructures and the evolution of digital electronics, particularly Nano-computers, are making the Internet of Things (IoT) emergent. Despite the progress, these IoT objects suffer from a crucial problem which is their limited power supply. IoT objects are often deployed as an ad-hoc network. To minimize their consumption of electrical energy, clustering techniques are used. In this paper, a centralized clustering algorithm with single-hop routing based on a genetic algorithm and Improved k-means is proposed. The proposed approach is compared with the LEACH, K-means and OK-means algorithms. Simulation results show that the proposed algorithm performs well in terms of network lifetime and energy consumption.

Résumé

Gestational Diabetes Mellitus (GDM) is a type of diabetes that develops during pregnancy. It is important for pregnant women to monitor their blood sugar levels regularly and follow a healthy diet. However, early intervention can greatly reduce risk of this type of diabetes. Machine Learning and Deep Learning techniques are utilized to predict this risk based on an individual's symptoms, lifestyle, and medical history. By identifying key features such as age, insulin, body mass index, and glucose levels, machine learning models such as Random Forest and XGBoost are used in this research work to classify patients at risk of a gestational diabetes. In addition, we propose an explainable feature selection approach to improve the accuracy of machine learning models for GDM prediction. This method involves iteratively eliminating features that exhibit a negative contribution as determined by the SHAP (Shapley Additive explanations) feature attribution explanations for the model’s predictions

Résumé

In today's society, social networks are vital for communication, allowing individuals to influence each other significantly. Opinion leaders play a crucial role in shaping opinions, attitudes, beliefs, motivations, and behaviors. Recognizing this, companies seek to identify influential users who resonate with their target audience to leverage their impact. Consequently, detecting opinion leaders in social networks has become essential. This paper aims to provide a comprehensive literature review on opinion leader detection. We present a detailed overview of various methods and approaches developed in this field, examining their strengths and weaknesses to identify the most effective strategies for different social networks. Additionally, we highlight key trends, challenges, and future directions in opinion leader detection. Our goal is to equip companies with the necessary knowledge to harness the power of opinion leaders for enhancing marketing and communication strategies. For researchers, this paper serves as a foundational resource, outlining the current state of the art and identifying gaps in the literature for future studies. Ultimately, we strive to advance the understanding of effective opinion leader detection and utilization within the dynamic landscape of social networks.

Résumé

The integration of social networking concepts into the IoT environment has led to the Social Internet of Things
(SIoT) paradigm which enables connected devices and people to facilitate information sharing, interact, and
enable a variety of attractive applications. However, with this emerging paradigm, people feel cautious and
wary. They worry about violating their privacy and revealing their data. Without trustworthy mechanisms to
guarantee the reliability of user’s communications and interactions, the SIoT will not reach enough popularity
to be considered as a cutting-edge technology. Accordingly, trust management becomes a major challenge
to improve security and provide qualified services. Therefore, we overcome these issues through proposing
an adaptive trust management model based on Adaptive Neuro-Fuzzy Inference System (ANFIS) in order to
estimate the trust level of objects in the Social Internet of Things. We formalized and implemented a new trust
management model built ANFIS, to analyze different trust parameters, estimate the trust level of objects and
distinguish malicious behavior from benign behaviors. Experimentation made on a real data set proves the
performance and the resilience of our trust management model.

Résumé

The cold start problem has always been a major challenge for recommender systems. It arises when the system lacks rating records for new users or items. Addressing the challenge of providing personalized recommendations in the cold start scenario is crucial. This research proposes a new hybrid recommender system named CoDFi-DL which combines demographic and enhanced collaborative filtering. The demographic filtering is performed through a deep neural network (DNN) and used to solve the new user cold start problem. The enhanced collaborative filtering component of our model focuses on delivering personalized recommendations through a neighborhood-based method. The major contribution in this research is the DNN-based demographic filtering which overcomes the new user cold start problem and enhances the collaborative filtering process. Our system significantly improves the relevancy of the recommendation task and thus provides personalized recommended items to cold users. To evaluate the effectiveness of our approach, we conducted experiments on real multi-label datasets, 1M and 100K MovieLens. CoDFi-DL recommender system showed higher performance in comparison with baseline methods, achieving lower RMSE rates of 0.5710 on the 1M MovieLens dataset and 0.6127 on the 100K MovieLens dataset.

Résumé

Internet users are overwhelmed by the vast number of services and products to choose from. This data deluge has led to the need for recommender systems. Simultaneously, the explosion of interactions on social networks is constantly increasing. These interactions produce a large amount of content that incites organizations and individuals to exploit it as a support for decision making. In our research, we propose, Twit-CoFiD, a hybrid recommender system based on tweet sentiment analysis which performs a demographic filtering to use its outputs in an enhanced collaborative filtering enriched with a sentiment analysis component. The demographic filtering, based on a Deep Neural Network (DNN), allows to overcome the cold start problem. The sentiment analysis of Twitter data combined with the enhanced collaborative filtering makes recommendations more relevant and personalized. Experiments were conducted on 1M and 100K Movielens datasets. Our system was compared to other existing methods in terms of predictive accuracy, assessed using Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) metrics. It yielded improved results, achieving lower RMSE and MAE rates of 0.4474 and 0.3186 on 100K Movielens dataset and of 0.3609 and 0.3315 on 1M Movielens dataset.

Résumé

The rapid expansion of contextual information from smartphones and Internet of Things (IoT) devices paved the way for Context-Aware Recommendation Systems (CARS). This abundance of contextual data heralds a transformative era for traditional recommendation systems. In alignment with this trend, we propose a novel model which provides personalized recommendations based on context. Our approach uses K-means algorithm to cluster users based on contextual features. Then, the model performs collaborative filtering based on matrix factorization with enhanced contextual biases to provide relevant recommendations. We demonstrated the performance of our method through experiments conducted on the movie recommender dataset LDOS-CoMoDa. The experimental results showed the effective performance of our proposal compared to reference methods, achieving an RMSE of 0.7416 and an MAE of 0.6183.

Résumé

Business Process as a Service (BPaaS) has recently emerged from the synergy between business process management and cloud computing, allowing companies to outsource and migrate their businesses to the cloud. BPaaS management refers to the set of operations (decomposition, customization, placement, etc.) that maintain a high-quality of the deployed cloud-based businesses. Like its ancestor SaaS, BPaaS placement consists on the dispersion of its composing fragments over multiple cloud availability zones (CAZ). These latter are characterized by their huge, diverse and dynamic data, which are exploited to select the high-performance servers holding BPaaS fragments, while preserving their constraints. These fragments’ relations and their placement schemes constitute a dynamic BPaaS information network. However, the few existing BPaaS solutions adopt a static placement strategy, while it is important to take the CAZ dynamic and uncertain nature into account. Also, current solutions do not properly model the BPaaS environment. To offer an efficient BPaaS placement scheme, we combine prediction and learning capabilities, which will help identify the migrating fragments and their new hosting servers. We first model the BPaaS context as a heterogeneous information network. Then, we apply an incremental representation learning approach to facilitate its processing. Using the principles of proximity-aware representation learning, we infer useful knowledge regarding BPaaS fragments and the available servers at different CAZ. Finally based on the degree of closeness between the BPaaS environment’s entities (e.g., fragments, servers), we select the optimum cloud availability zone on which the resource-consuming BPaaS fragments are migrated based on a proposed placement scheme. Obtained results were very promising compared to traditional BPaaS placement solutions.

Résumé

Résumé

Multimodal data, which includes various data formats such as image, video, text, and sensor data, is essential for urban traffic management. The lack of proven multimodal transportation data has been a significant challenge for urban planners, leading to biased or incomplete estimates of travel demand, mode choice, and network performance. Multimodal data integration offers a valuable resource for understanding and optimizing traffic control and management. However, the heterogeneity of the data, various kinds of noise, alignment of modalities, and techniques to handle missing data are some of the challenges that arise. This paper presents a novel multimodal dataset which is the first of its kind, its scraped from England Highways, incorporating speed, flow, and camera images for the M60, M25, and M1 motorways. The dataset provides a comprehensive view of traffic behavior at specific junctions, enabling detailed analysis and real-world applications. By integrating previously disparate data sources, this dataset offers a valuable resource for understanding and optimizing traffic control and management. The paper outlines the dataset's development, including the gathering of speed and flow data, and the use of image scraping techniques to capture CCTV images. The potential applications of the dataset for traffic control, planning, and optimization are also discussed. Overall, this multimodal dataset represents a significant contribution to the field, with implications for the development of advanced traffic management systems and the improvement of transportation infrastructure

Résumé

in recent years, traffic flow prediction has presented challenges in the management of transportation systems. It is a crucial part of Intelligent Transportation Systems (ITS). The complexities of various transportation data, spatial and temporal dependencies on road networks, and multimodalities, such as public transit, pedestrian flow, and bike sharing, make it a challenging task to forecast traffic flow accurately. Numerous works have been introduced to address these challenges, but few have simultaneously considered these factors, resulting in limited success. In this study, a model is proposed to integrate Graph Convolutional Networks (GCN) and Bidirectional Long Short-Term Memory (BiLSTM). This model utilizes the advantages of GCN in handling spatial data and capturing dependencies in road networks, combined with BiLSTM's capability in learning temporal dynamics. The proposed model can extract comprehensive features from various transportation data and effectively capture the spatial-temporal dependencies. By merging these features, it aims to generate more accurate and robust traffic flow predictions. This method addresses the limitations of existing methods that fail to consider spatial-temporal dependencies and multimodalities, leading to improved prediction accuracy and efficiency

Résumé

Financial markets are dynamic and open systems. They are subject to the influence of environmental changes. For this reason, predicting stock market prices is a difficult task for investors due to the volatility of the financial stock markets nature. Stock market forecasting leads investors to make decisions with more confidence based on the prediction of stock market price behavior. Indeed, a lot of analysts are greatly focused in the research domain of stock market prediction. Generally, the stock market prediction tools are categorized into two types of algorithms: (1) linear models like Auto Regressive (AR), Moving Average (MA), Auto-Regressive Integrated Moving Average (ARIMA), and (2) non-linear models like Autoregressive Conditionally Heteroscedastic (ARCH), Generalized Autoregressive Conditional Heteroskedasticity (GARCH) and recently Neural Network (NN)). This paper aspires to crucially predict the stock index movement for National Association of Securities Dealers Automated Quotations (NASDAQ) based on deep learning networks. We propose a hybrid stock price prediction model using Convolutional Neural Network (CNN) for feature selection and Neural Network models to perform the task of prediction. To evaluate the performance of the proposed models, we use five regression evaluation metrics: Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and R-Square (R2), and the Execution Time (ET) metric to calculate the necessary time for running each hybrid model. The results reveal that error rates in the CNN-BGRU model are found to be lower compared to CNN-GRU, CNN-LSTM, CNN-BLSTM and the the existing hybrid models. This research work produces a practical experience for decision makers on financial time series data.

Résumé

Internet of vehicles (IoV) can be considered as a superset of vehicular ad-hoc networks (VANETs). It extends VANET’s structure, applications and scale. Unlike, the traditional intelligent transportation system (ITS), IoV focus more on information interactions between vehicles, roadside units (RSU) and humans. The principal aim is to make people obtain road traffic information easily and in real-time, to ensure the travel convenience, and to increase the travel comfort. The goal behind the Internet of vehicles is essentially to be used in urban traffic environment to ensure network access for passengers and drivers. The environment of the IoV is the combination of different wireless network environment as well as road conditions. Despite its continuing expansion, the IOV contains different radio access technologies that lead to a heterogeneous network, and make it more crucial than the VANET. These drawbacks pose numerous challenges, especially the routing one. In IoV environment, the routing protocol must cope with events such as link failure and to find the best route to propagate the data toward the desired destination. In this paper, we mainly focus on surveying the IoV routing protocols, hence we present and compare unicast, multicast and broadcast protocols.

Résumé

Fake news has a worldwide impact and the potential to change political scenarios and human behavior, especially in a critical time like the COVID-19 pandemic. This work suggests a Soft Three-Level Voting Model (Soft T-LVM) for automatically classifying COVID-19 fake news. We train different individual machine learning algorithms and different ensemble methods in order to overcome the weakness of individual models. This novel model is based on the soft-voting technique to calculate the class with the majority of votes and to choose the classifiers to merge and apply at every level. We use the Grid search method to tune the hyper-parameters during the process of classification and voting. The experimental evaluation confirms that our proposed model approach has superior performance compared to the other classifiers.

Résumé

Identifying opinion leaders in social networks, particularly in social media, is a crucial marketing strategy. These individuals have a considerable influence on the purchasing decisions of their communities. Companies can benefit from collaborating with relevant opinion leaders in their market as this can increase their visibility, establish their credibility, and gain consumer trust, leading to increased sales, improved brand perception, and an expanded market share. Additionally, by gaining a comprehensive understanding of opinion leaders, companies can better comprehend the trends and preferences of their target audience. This allows them to tailor their marketing and product strategies more effectively. Identifying suitable influencers to endorse their products or services is a significant challenge for companies. The identification of opinion leaders is complicated by their informal and unstructured nature, as well as the varying selection criteria depending on the marketing campaign’s goals. While numerous research studies have focused on detecting opinion leaders in social networks based on content, interactions, or a combination of both, few have explored sentiment analysis of post content, received interactions, and user comments in relation to published posts. The purpose of this paper is to present an hybrid approach to detect opinion leaders in Facebook. This approach involves analyzing the trajectory of post content by examining interactions on the post, as well as mining the text content of the post itself and analyzing the users’comments sentiments.

Résumé

Résumé

Learning Classifier Systems (LCSs) are a kind of evolutionary machine learning algorithms that provide highly adaptive components to deal with real world problems. They have been widely used in resolving complex problems such as decision making and classification. LCSs are flexible algorithms that are able to construct, incrementally, a set of rules and evolve them through the Evolutionary Algorithm (EA). Despite their efficiency, LCSs are not capable of handling imperfect information, which may lead to reduced performance in terms of classification accuracy. We propose a new accuracy-based Michigan-style LCS that integrates the belief function theory in the supervised classifier system. The belief function or evidence theory represents an efficient framework for treating imperfect information. The new approach shows promising results in real world classification problems.

Résumé

In this study, various organizations that have participated in several road path-detecting experimentsare analyzed. However, the majority of techniques rely on attributes or form models built by humans to identifysections of the path. In this paper, a suggestion was made regarding a road path recognition structure that is dependenton a deep convolutional neural network. A tiny neural network has been developed to perform feature extraction toa massive collection of photographs to extract the suitable path feature. The parameters obtained from the model ofthe route classification network are utilized in the process of establishing the parameters of the layers that constitutethe path detection network. The deep convolutional path discovery network’s production is pixel-based and focuseson the identification of path types and positions. To train it, a detection failure job is provided. Failure in pathclassification and regression are the two components that make up a planned detection failure function. Instead oflaborious postprocessing, a straightforward solution to the problem of route marking can be found using observedpath pixels in conjunction with a consensus of random examples. According to the findings of the experiments, theclassification precision of the network for classifying every kind is higher than 98.3%. The simulation that was trainedusing the suggested detection failure function is capable of achieving an accuracy of detection that is 85.5% over atotal of 30 distinct scenarios on the road

Résumé

Studying driver behaviors has become a major concern for the transportation community, businesses, and the public. Thus, based on the simulation, we proposed an adaptive driving model in the car-following driving behavior and based on the normative behavior of the driver during decision-making and anticipation, whose intention is to ensure the objectives of imitation of ordinary human behavior and road safety. The presented model is based on a software agent paradigm to model a human driver and the Fuzzy Logic Theory to reflect the driver agent’s reasoning. To validate our model, we used the dataset from the program of the US Federal Highway Administration. In this context, we notice an excellent homogeneity in the deviation of the adopted trajectory of the autonomous driver agent from the adopted trajectories by the human drivers. Moreover, the advantage of our model is that it works with different velocities.

Résumé

Résumé

Sleep is an essential element that affects directly our daily life thus sleep analysis is a very interesting field. Sleep stages classification represents the base of all sleep analysis activities. However, the classification of sleep stages suffers from high uncertainty between its stages which could lead to degrade the performance of classification methods. To cope partially with this issue, we propose a new approach that deals with uncertainty especially with imprecision. Our method integrates the belief function theory in eXtended Classifier System (XCS). The proposed approach shows a good performance ability comparing to classical methods.

Résumé

Nowadays, companies are more and more adopting cloud technologies in the management of their business processes rising, then, the Business Process as a Service (BPaaS) model. In order to guarantee the consistency of the provisioned BPaaS, cloud providers should ensure a strategical management (e.g., allocation, migration, etc.) of their available resources (e.g., computation, storage, etc.) according to services requirements. Existing researches do not prevent resource provision problems before they occur. Rather, they conduct a real-time allocation of cloud resources. This paper makes use of historical resource usage information for providing enterprises and BPaaS providers with predictions of cloud availability zones’ states. For that, we first propose a Neural Network-based prediction model that exploits the superposition power of Quantum Computing and the evolutionary nature of the Genetic Algorithm, in order to optimize the accuracy of the predicted resource utilization. Second, we define a placement algorithm that, based on the prediction results, chooses the optimal cloud availability zones for each BPaaS fragment, i.e. under-loaded servers. We evaluated our approach using real cloud workload data-sets. The obtained results confirmed the effectiveness and the performance of our NNQGA approach, compared to traditional techniques.

Résumé

Traffic congestion has increased globally during the last decade representing an undoubted menace to the quality of urban life. A significant contribution can be made by the public transport system in reducing the problem intensity if it provides high-quality service. However, public transportation systems are highly complex because of the modes involved, the multitude of origins and destinations, and the amount and variety of traffic. They have to cope with dynamic environments where many complex and random phenomena appear and disturb the traffic network. To ensure good service quality, a control system should be used in order to maintain the public transport scheduled timetable. The quality service should be measured in terms of public transport key performance indicators (KPIs) for the wider urban transport system and issues. In fact, in the absence of a set of widely accepted performance measures and transferable methodologies, it is very difficult for public transport to objectively assess the effects of specific regulation system and to make use of lessons learned from other public transport systems. Moreover, vehicle traffic control tasks are distributed geographically and functionally, and disturbances might influence on many itineraries and occur simultaneously. Unfortunately, most existing traffic control systems consider only a part of the performance criteria and propose a solution without man-aging its influence on neighboring areas of the network. This paper sets the context of performance measurement in the field of public traffic management and presents the regulation support system of public transportation (RSSPT). The aim of this regulation support system is (i) to detect the traffic perturbation by distinguishing a critical performance variation of the current traffic, (ii) and to find the regulation action by optimizing the performance of the quality service of the public transportation. We adopt a multi-agent approach to model the system, as their distributed nature, allows managing several disturbances concurrently. The validation of our model is based on the data of an entire journey of the New York City transport system in which two perturbation scenarios occur. This net-work has the nation’s largest bus fleet and more subway and commuter rail cars than all other U.S. transit systems combined. The obtained results show the efficiency of our system especially in case many performance indicators are needed to regulate a disturbance situation. It demonstrates the advantage as well of the multiagent approach and shows how the agents of different neighboring zones on which the disturbance has an impact, coordinate and adapt their plans and solve the issue.

Résumé

The rise of terrorism over the past decade did not only hinder the development of some countries, but also it continues to destroy humanity. To face this concept of an emerging crisis, every country and every citizen is responsible for the fight against terrorism. As conventional plans became useless against terrorism, governments are required to establish innovative concepts and technologies to support units in this asymmetric war. In this paper, we propose a new multi-agent model for
counter-terrorism characterized by a methodical process and a flexibility to handle different contingency scenarios. The division of labour in our multi-agent model improves decision making and the structuring of organisational plans.

Résumé

Nowadays the world is suffering from the emergence of a new concept of war, it is the asymmetric warfare created by the terrorists' new combat doctrine. As the plans to face classic enemies have become unusual against terrorism, this calls for innovative concepts and technologies to support the units and to improve the capability of leaders and structure their choices. In this paper, we propose a multi agent architecture for action planning against terrorist attacks. It is characterized by rapid decisive responses and methodical steps to handle the situation, and by the flexibility to adapt a contingency scenario. We aim to create a multi-agent model that describes the relation between actors during the terrorist attack in order to find the best possible units distribution to neutralize the enemy.

Résumé

During last years, several competency management systems (CMSs) have been proposed to support the acquisition, allocation, and improvement of competencies. However, competency information and associated proofs are still not tracked and shared in a trustworthy and immutable way. In this context, blockchain technology provides a prominent manner to keep track of competencies and achievements and to ensure their sharing in a secure and transparent manner. Particularly, given the decentralized nature of immutable and distributed ledgers enabled by blockchain, the potential for using this revolutionary new technology for lifelong competency tracking and assessment is tremendous. In this paper, a functional architecture using smart contracts and blockchain is proposed to support competency tracking and assessment in learning networks. Thus, by implementing the proposed architecture, all the different stakeholders involved can be connected, namely, learners, authors, and assessors. Besides, a full traceability of acquired proofs of competencies and competency profiles is warranted, while ensuring their authenticity and integrity.

Résumé

Automatic sleep scoring has, recently, captured the attention of authors due to its importance in sleep abnormalities detection and treatments. The majority of the proposed works are based on supervised learning and considered mostly a single physiological signal as input. To avoid the exhausting pre-labeling task and to enhance the precision of the sleep staging process, we propose an unsupervised classification model for sleep stages identification based on a flexible architecture to handle different physiological signals. The efficiency of our approach was investigated using real data. Promising results were reached according to a comparative study carried out with the often used classification models.

Résumé

Sleep analysis is considered as an important process in sleep disorders identification and highly dependent of sleep scoring. Sleep scoring is a complex, time consuming and exhausting task for experts. In this paper, we propose an automatic sleep scoring model based on unsupervised learning to avoid the pre-labeling task. Taking advantage of the distributed nature of Multi-agent Systems (MAS), we propose a classification model based on various physiological signals coming from heterogeneous sources. The proposed model offers a totally cooperative learning to automatically score sleep into several stages based on unlabeled data. The existing heterogeneous adaptive agents are dealing with a dynamic environment of various physiological signals. The efficiency of our approach was investigated using real data. Promising results were reached according to a comparative study carried out with the often used classification models. The generic proposed model could be used in fields where data are coming from heterogeneous sources and classification rules are not predefined.

Résumé

Cloud computing is an emerging technology that is largely adopted by the current computing industry. With the growing number of Cloud services, Cloud providers' main focus is how to best offer efficient services (eg, SaaS, BPaaS, mobile services, etc) in order to hook the eventual customers. To meet this goal, services arrangement and placement in the cloud is becoming a serious problem because an optimal placement of these applications and their related data in accordance with the available resources can increase companies' benefits. Since there is a widespread deployment of business processes in the cloud, the hereinafter conducted research works aim to enhance the business processes' outsourcing by providing an optimized placement scheme that would attract cloud customers. In the light of these facts, the purpose of this paper is to deal with the BPaaS placement problem while optimizing both the total execution time and cloud resources' usage. To do so, we first determine the redundant BPaaS fragments using a DNA Fragment Assembly technique. We apply a variant of the Genetic Algorithm to resolve it. Then, we propose a placement algorithm, which produces an optimized placement scheme on the basis of the determined fragments relations. We follow that by an implementation of the whole placement process and a set of experimental results that have shown the feasibility and efficiency of the proposed approach.

Résumé

Perception is presented as a predominant concern in the functioning of a driving system, where it is necessary to understand how the information, events, and actions of each influence the state of the environment and the objectives of the driver, immediately and in the near future. In this context, we present in this paper a driving model composed of five layers which ensure the autonomy and road safety of a driver agent, in particular, we are interested in this article in the concept of perception which is translated by the first three layers of our driving model, which are: visual perception, comprehension and projection, where the execution of these three layers is based on the driving behavior adopted by the driver agent, which is in our case the car-following driving behavior. Furthermore, we present in this paper two simulation scenarios, the first one is realized based on urban area conditions, and the second one is conducted by using Next Generation SIMulation (NGSIM) dataset of a highway in Los Angeles, California. In this context, the experimental results present the effectiveness of our driving model based on the imitation of human behavior and according to reducing the duration of perception.

Résumé

Recent advances in Computational Intelligent Systems have focused on addressing complex problems related to the dynamicity of the environments. Generally in dynamic environments, data are presented as streams that may evolve over time and this is known by concept drift. Handling concept drift through ensemble classifiers has received a great interest in last decades. The success of these ensemble methods relies on their diversity. Accordingly, various diversity techniques can be used like block-based data, weighting-data or filtering-data. Each of these diversity techniques is efficient to handle certain characteristics of drift. However, when the drift is complex, they fail to efficiently handle it. Complex drifts may present a mixture of several characteristics (speed, severity, influence zones in the feature space, etc.) which may vary over time. In this case, drift handling is more complicated and requires new detection and updating tools. For this purpose, a new ensemble approach, namely EnsembleEDIST2, is presented. It combines the three diversity techniques in order to take benefit from their advantages and outperform their limits. Additionally, it makes use of EDIST2, as drift detection mechanism, in order to monitor the ensemble’s performance and detect changes. EnsembleEDIST2 was tested through different scenarios of complex drift generated from synthetic and real datasets. This diversity combination allows EnsembleEDIST2 to outperform similar ensemble approaches in terms of accuracy rate, and present stable behaviors in handling different scenarios of complex drift.

Résumé

Emotions in workplace is a topic that has increasingly at
tracted attention of both organizational practitioners and academics. This is due to the fundamental role emotions play in shaping human resources behaviors, performance, productivity, interpersonal relationships and engagement at work. In the current research, a computational social simulation approach is adopted to replicate and study the emotional experiences of employees in organizations. More speci cally, an emotional
agent-based model of an employee at work is proposed. The developed model is used in a computer simulator WEMOS (Workers EMotions in Organizations Simulator) to conduct certain analyzes in relation to the most likely emotions-evoking stimuli as well as the emotional content of several work-related stimuli. Simulation results can be employed to gain deeper understanding about emotions in the work life.

Résumé

Emotions in workplace is a topic that has increasingly attracted attention of both organizational practitioners and academics. This is due to the fundamental role emotions play in shaping human resources behaviors, performance, productivity, interpersonal relationships and engagement at work. In the current research, a computational social simulation approach is adopted to replicate and study the emotional experiences of employees in organizations. More specifically, an emotional agent-based model of an employee at work is proposed. The developed model is used in a computer simulator WEMOS (Workers EMotions in Organizations Simulator) to conduct certain analyzes in relation to the most likely emotions-evoking stimuli as well as the emotional content of several work-related stimuli. Simulation results can be employed to gain deeper understanding about emotions in the work life.

Résumé

Road crashes are present as an epidemic in road traffic and continue to grow up, where, according to World Health Organization; they cause more than 1.24 million deaths each year and 20 to 50 million non-fatal injuries, so they should represent by 2020 the third leading global cause of illness and injury. In this context, we are interested in this paper to the car-following driving behavior problem, since it alone accounts for almost 70% of road accidents, which they are caused by the incorrect judgment of the driver to keep a safe distance. Thus, we propose in this paper a decision-making model based on bi-level modeling, whose objective is to ensure the integration between road safety and the reducing travel time. To ensure this objective, we used the fuzzy logic approach to model the anticipation concept in order to extract more unobservable data from the road environment. Furthermore, we used the fuzzy logic approach in order to model the driver behaviors, in particular, the normative behaviors. The experimental results indicate that the decision to increase in velocity based on our model is ensured in the context of respecting the road safety.

Résumé

Vehicular Ad hoc Networks (VANETs) are a particular case of Mobile Ad hoc Networks (MANETs). They are applied to exchange information among vehicles and between vehicles and a nearby fixed infrastructure. Unlike the MANETs, the VANETs have highly mobile nodes that cause a dynamic topology, a disconnected network, etc. Consequently, these features pose numerous challenges. One of them is routing. In a vehicular environment, the routing protocol needs to cope with events like link failure and to find an effective path to propagate the information toward the desired destination. In this context, we assume in this paper that the vehicles are intelligent and have a knowledge base about their communication environment. Our aim is to carry out the routing of the data based on swarm intelligence. The optimum route is explored using the Particle Swarm Optimisation (PSO). The proposed approach is called the Optimised Agent-based AODV Protocol for VANET (OptA2PV).

Résumé

For the purpose of improving the quality in Elearning process and overcoming the limitations of the current online educational environments, we propose to take into consideration the emotional states of students during Elearning sessions. Our objective is to ensure the ability of emotional intelligence: Emotion Recognition, in an eLearning environment. Thus, we present an architecture of Emotionally Intelligent Elearning System (EIES). Within the development of a computational probabilistic model of emotions, we proposed a Bayesian Network (BN) model to deal with emotions in Elearning environments and handle the uncertain nature of emotion recognition process. In a second phase, we focus on the incorporation of the emotion recognition in the Elearning systems by developing a simulation of EIES based on the BN model, able to predict the students’ affects. Consequently, we reached positive and promising results related to the fact that simulated EIES based on the BN model of emotions predicts correctly the student’s emotion when an event occurs during an Elearning session.

Résumé

Emotion mechanisms represent an important moderating factor of human behavior. Thus, they are necessary to produce realistic behavioral simulations. This work addresses this challenging issue by incorporating emotional processes into an agent model. We intend to show the potential of emotions and coping mechanisms to produce fast and human-like emotional behaviors, particularly, in emergency situations. We focus on the interplay of emotions and goals and its impact on agent behavior. Emotions constitute heuristics to agent decision making. They induce emotion-specific goals that orient agent goal adoption mechanisms and fasten its behavior selection.

Résumé

Vehicular Ad hoc Network (VANET) is a sub-family of Mobile Ad hoc Network (MANET). The principal goal of VANET is to provide communications between nearby nodes or between nodes and fixed infrastructure. Despite that VANET is considered as a subclass of MANET, it has for particularity the high mobility of vehicles producing the frequent changes of network topology that involve changing of road and varying node density of vehicles existing in this road. That‘s why, the most proposed clustering algorithms for MANET are unsuitable for VANET. Various searches have been recently published deal with clustering for VANETs, but most of them are focused on minimizing network overhead value, number of created clusters and had not considered the vehicles interests which defined as any related data used to differentiate vehicle from another. In this paper, we propose a novel clustering algorithm based on agent technology to improve routing in VANET.

Résumé

This paper provides an agent technology for
a decision support system. This system is designed to
detect and regulate the traffic of multimodal public
transport when many disturbances come simultaneously.
The objective of this system is to optimize the regulation
action by learning technique of regulator. The goal of this
research is to improve the quality of public transport
service provided to users and respect the use rules (safety
rules, business rules, commercial rules, etc.). So, to
improve the quality service of the user, we have to
optimize simultaneously several criteria like punctuality,
regularity and correspondence in disturbance case. In
this paper, we focus primarily on a multi agent system for
optimizing and learning of Regulation Support System of
a Multimodal Public Transport (RSSPT). We have
validated our strategy by simulating situation related to
existing transportation system.

Résumé

Recent advances in computational intelligent systems have focused on addressing complex problems related to the dynamicity of the environments. In increasing number of real world applications, data are presented as streams that may evolve over time and this is known by concept drift. Handling concept drift is becoming an attractive topic of research that concerns multidisciplinary domains such that machine learning, data mining, ubiquitous knowledge discovery, statistic decision theory, etc... Therefore, a rich body of the literature has been devoted to the study of methods and techniques for handling drifting data. However, this literature is fairly dispersed and it does not define guidelines for choosing an appropriate approach for a given application. Hence, the main objective of this survey is to present an ease understanding of the concept drift issues and related works, in order to help researchers from different disciplines to consider concept drift handling in their applications. This survey covers different facets of existing approaches, evokes discussion and helps readers to underline the sharp criteria that allow them to properly design their own approach. For this purpose, a new categorization of the existing state-of-the-art is presented with criticisms, future tendencies and not-yet-addressed challenges.

Résumé

Emotions shape human behaviors particularly during stressful situations. This paper addresses this challenging issue by incorporating coping mechanisms into an emotional agent. Indeed, coping refers to cognitive and behavioral efforts employed by humans to overcome stressful situations. In our proposal, we intend to show the potential of the integration of coping strategies to produce fast and human-like behavioral responses in emergency situations. Particularly, we propose a coping model that reveals the effect of agent emotions on their action selection processes.

Résumé

Vehicular Ad-hoc Network (VANET) is a sub-family of Mobile Ad-hoc Network (MANET).The means goal of VANET is to provide communications between nearby nodes or between nodes and fixed infrastructure. Despite that VANET is considered as a subclass of MANET, it has for particularity the high mobility of vehicles producing the frequent changes of network topology that involve changing of road, varying node density and locations of vehicles existing in this road. That‘s why, the most proposed clustering algorithms for MANET are unsuitable for VANET. Various searches have been recently published deal with clustering for VANETs. But most of them are focused on minimizing network overhead value, number of created clusters and had not considered the vehicles interests which defined as any related data used to differentiate vehicle from another (such as traffic congestion, looking for free parking space, etc.). In this paper, we propose a novel clustering algorithm based on agent technology to solve the problems mentioned above and improve routing in VANET. Experimental part show promising results regarding the adoption of the proposed approach.

Résumé

Detecting changes in data streams attracts major attention in cognitive computing systems. The challenging issue is how to monitor and detect these changes in order to preserve the model performance during complex drifts. By complex drift, we mean a drift that presents many characteristics in the sometime. The most challenging complex drifts are gradual continuous drifts, where changes are only noticed during a long time period. Moreover, these gradual drifts may also be local, in the sense that they may affect a little amount of data, and thus make the drift detection more complicated. For this purpose, a new drift detection mechanism, EDIST2, is proposed in order to deal with these complex drifts. EDIST2 monitors the learner performance through a self-adaptive window that is autonomously adjusted through a statistical hypothesis test. This statistical test provides theoretical guarantees, regarding the false alarm rate, which were experimentally confirmed. EDIST2 has been tested through six synthetic datasets presenting different kinds of complex drift, and five real-world datasets. Encouraging results were found, comparing to similar approaches, where EDIST2 has achieved good accuracy rate in synthetic and real-world datasets and has achieved minimum delay of detection and false alarm rate.

Résumé

Detecting changes in data streams attracts major attention in cognitive computing systems. The challenging issue is how to monitor and detect these changes in order to preserve the model performance during complex drifts. By complex drift, we mean a drift that presents many characteristics in the sometime. The most challenging complex drifts are gradual continuous drifts, where changes are only noticed during a long time period. Moreover, these gradual drifts may also be local, in the sense that they may affect a little amount of data, and thus make the drift detection more complicated. For this purpose, a new drift detection mechanism, EDIST2, is proposed in order to deal with these complex drifts. EDIST2 monitors the learner performance through a self-adaptive window that is autonomously adjusted through a statistical hypothesis test. This statistical test provides theoretical guarantees, regarding the false alarm rate, which were experimentally confirmed. EDIST2 has been tested through six synthetic datasets presenting different kinds of complex drift, and five real-world datasets. Encouraging results were found, comparing to similar approaches, where EDIST2 has achieved good accuracy rate in synthetic and real-world datasets and has achieved minimum delay of detection and false alarm rate.

Résumé

In line with the multi-disciplinary growing interest in emotions and the scientific proof of their usefulness for taking decisions, scholars, in agent-oriented systems, start to account for emotions when building upon intelligence and realism in rational agents. As a result, several computational models of emotions were developed and new architectures for emotional artificial agents were proposed, in particular the Emotional Belief Desire Intention (EBDI) agents. In this paper, we provide a comprehensive description of two computational models which are used to generate immediate and expected emotions. These models will be incorporated within an EBDI agent architecture that takes into consideration these two types of emotions.

Résumé

Agent-Based Modeling and Simulation (ABMS) have been used to study a wide range of complex systems and several emergent behaviors across a variety of disciplines. However, very limited works have adopted these paradigms to provide insights to organizational psychology in general and to researches dealing with emotions at work in particular. The current research uses ABMS to study the emotions experienced in the organizational context; it focuses specifically on their impact on the quality of decisions made as a key factor of organizations success. In this paper, the emphasis is set on the emotion generation process. The proposed work introduces an agent-based model of the emotional experiences of employees within organizations. It adopts a cross-disciplinary approach and it brings another theoretical perspective to agent-based modeling of emotions at work. In fact, this model is based on the OCC appraisal theory to generate artificial emotions, but it also takes advantage of theoretical foundations from organization behavior and organization psychology. Simulation results can bring new insights to organizational researches. Moreover, the simulated system can serve as a human resources development tool used by employees at work to enhance their emotional awareness.

Résumé

In line with the multi-disciplinary growing interest in emotions and the scientific proof of their usefulness for taking decisions, scholars, in agent-oriented systems, start to account for emotions when building upon intelligence and realism in rational agents. As a result, several computational models of emotions were developed and new architectures for emotional artificial agents were proposed, in particular the Emotional Belief Desire Intention (EBDI) agents. In this paper, we provide a comprehensive description of two computational models which are used to generate immediate and expected emotions. These models will be incorporated within an EBDI agent architecture that takes into consideration these two types of emotions.

Résumé

Emotions have a considerable effect on human
behaviors and cognitive processes, especially during crisis
situations. Emotion modeling is therefore a key solution to
generate realistic social simulations in crisis situations. In this
context, we intend to model human emotional dynamics and to
study their effect on individual and collective behaviors during
emergency situations. In this paper, we focus on the first part of
this research work which consists in the modeling of emotion
generation in emergency situations. Thus, we provide first a
modeling of the disaster space in a rescue simulation context.
Then, we propose a computational model of the generated
human emotions, basing on the emergency environment. This
model uses the appraisal theories of emotions.

Résumé

Analyzing human behaviors during emergency situations contributes to build efficient emergency management plans. Indeed, research shows that emotions have a major influence on human behavior particularly to respond to highly emotive events such as those happening in emergency situations. Therefore, it is recognized that they are necessary to produce human-like behaviors in artificial agents. In this paper, we present an emotional agent model of human civilians in an emergency context. The aim is to model and to simulate the emotion generation process and the impact of the elicited emotions on civilian behaviors in an emergency situation during a disaster.

Résumé

Agent based social simulations are becoming prevailing tools in the context of human behavior studies. Researchers in psychology, cognitive science and neuroscience have proved the prominent role of emotion on cognition and behavior. Particularly, during emergency situations, human emotional dynamics have a major effect on behavior. In this context, we aim to study the role of emotions in reproducing human-like emotional civilian agents. The objective of the current research work is to model and to simulate human emotional dynamics and their effect on the behaviors of civilians in emergencies. In this article, we describe an emotional agent model that integrates a computational model of emotions. Agent perceptions are subject to a cognitive appraisal process to generate agent emotions. These have an effect on the generation of agent behavior.

Résumé

Over the last decade, emotions have received considerable attention among scholars in agent oriented systems. In fact a large amount of computational models of emotions has been developed and a new generation of artificial agents has emerged to give rise to emotional agents, in particular the Emotional BDI (EBDI) agents. However, in spite of the several interesting studies that have been conducted to underline the role of emotions in decision-making, few works in the agent community have shed the light on the influences of both immediate and expected emotions to drive decision-making. In this context, we intend to propose a new conceptual model of EBDI agency that involves the interplay among immediate emotions, expected emotions and rational decisions of artificial agents.

Résumé

Multi-agent systems are widely used in renewable and natural resources management. Multi-agent systems are able to manage the complexity of such systems characterized by a large number of interacting entities with different levels of granularity and including dynamics of different contexts (ecological, economic, social). In this work, we propose a generic multi-level architecture for renewable and natural resources management.

Résumé

Detecting and monitoring changes during the learning process are important areas of research in many industrial applications. The challenging issue is how to diagnose and analyze these changes so that the accuracy of the learning model can be preserved. Recently, ensemble classifiers have achieved good results when dealing with concept drifts. This paper presents two ensembles learning algorithms BagEDIST and BoostEDIST, which respectively combine the Online Bagging and the Online Boosting with the drift detection method EDIST. EDIST is a new drift detection method which monitors the distance between two consecutive errors of classification. The idea behind this combination is to develop an ensemble learning algorithm which explicitly handles concept drifts by providing useful descriptions about location, speed and severity of drifts. Moreover, this paper presents a new drift diversity measure in order to study the diversity of base classifiers and see how they cope with concept drifts. From various experiments, this new measure has provided a clearer vision about the ensemble’s behavior when dealing with concept drifts.

Résumé

La classification dynamique s’intéresse au traitement des données non-stationnaires issues des environnements évolutifs dans le temps. Ces données peuvent présenter des dérives, qui affectent la performance du modèle d’apprentissage initialement construit. Aujourd’hui, beaucoup d’intérêts sont portés sur la surveillance, la mise à jour et le diagnostic de ces dérives afin d’améliorer la performance du modèle d’apprentissage. Dans ce contexte, une nouvelle méthode de détection de dérive basée sur la distance entre les erreurs de classification est présentée. Cette méthode, nommée EDIST, surveille la distribution des distances des erreurs de classification entre deux fenêtres de données afin de détecter une différence à travers un test d’hypothèse statistique. EDIST a été testée à travers des bases de données artificielles et réelles. Des résultats encourageants ont été trouvés par rapport à des méthodes similaires. EDIST a pu trouver les meilleurs taux d’erreur de classification dans la plupart des cas et a montré une robustesse envers le bruit et les fausses alarmes.

Résumé

In recent years, several semantic similarity and relatedness measures have been developed and applied in many domains including linguistics, biomedical informatics, GeoInformatics, and Semantic Web. This paper discusses different semantic measures which compute similarity and relatedness scores between concepts based on a knowledge representation model offered by ontologies and semantic networks. The benchmarks and approaches used for the evaluation of semantic similarity methods are also described. The aim of this paper is to give a comprehensive view of these measures which helps researchers to choose the best semantic similarity or relatedness metric for their needs.

Résumé

astoral systems in arid and semi arid areas are characterized by a continued deterioration. This degradation is the result of the mismanagement of resources in response to natural, economic and social mutations. These systems are considered as complex systems, given the large number of stakeholders in interaction and levels of granularity. To address this situation, analytical and systemic approaches are no longer adequate. In this paper, we propose a multi-agent based model of Tunisian pastoral dynamics taking into account the interaction dynamics of the different stakeholders and the different levels of granularity. The completion of this work is within the scope of the development of the Intelligent Decision Support System PASDES (Pastoral Strategies Definition System). PASDES aims to support pastoral strategic decision making in short and long terms.

Résumé

This paper proposes a state of the art of the user modeling and interfaces customization techniques. It presents and discusses techniques intended to be used by application's designers and also end-user based techniques. It specifies the characteristics modeled in these systems as well as the used technologies.

Résumé

Pastoral systems are considered as complex systems, given the number of entities and the multitude of interactions and levels of granularity. To conduct a study of such system taking into account the interactions and their results, analytical approaches are not adequate. In this paper, we present an agent-based model of the animal behavior in the pastoral system taking into account the selective food aspect. This model has been validated using a multi-agent based simulation implemented on the simulation platform Cormas. The obtained results reflect the importance of this aspect in the animal behavior and its effects on vegetation cover.

Résumé

Lateral Transshipments afford a valuable mechanism for compensating unmet demands only with on-hand inventory. In this paper we investigate the case where locations have a limited storage capacity. The problem is to determine how much to replenish each period to minimize the expected global cost while satisfying storage capacity constraints. We propose a Real-Coded Genetic Algorithm (RCGA) with a new crossover operator to approximate the optimal solution. We analyze the impact of different structures of storage capacities on the system behaviour. We find that Transshipments are able to correct the discrepancies between the constrained and the unconstrained locations while ensuring low costs and system-wide inventories. Our genetic algorithm proves its ability to solve instances of the problem with high accuracy.