-
2024, Abir Chaabani, Nadia Ben Azzouna,
Hybrid genetic algorithm for solving an online vehicle routing problem with time windows and heterogeneous fleet
23rd International Conference on Hybrid Intelligent Systems (HIS'23), 437-446, Springer Nature Switzerland, 2024
Abstract
The Vehicle Routing Problem (VRP) is a well-known optimization problem in which we aim traditionally to minimize transportation costs while satisfying customer demands. In fact, most logistics companies use a heterogeneous fleet with varying capacities and costs, presenting a more complex variant known as Rich VRP (RVRP). In this paper, we present a mathematical formulation of the RVRP, considering both hard time windows and dynamically changing requests to be as close as possible to real-life logistics scenarios. To solve this challenging problem, we propose a Hybrid Genetic Algorithm (HGA). The experimental study highlights the out-performance of our proposal when evaluated alongside other algorithms on the same benchmark problems. Additionally, we conduct a sensitivity analysis to illustrate how resilient the algorithm is when problem parameters are altered.
Thouraya Sakouhi,Clustering-based multidimensional sequential pattern mining of semantic trajectories
International Journal of Data Mining, Modelling and Management, 16(2), 148-175., 2024
Abstract
Knowledge discovery from mobility data is about identifying behaviours from trajectories. In fact, mining masses of trajectories is required to have an overview of this data, notably, investigate the relationship between different entities movement. Most state-of-the-art work in this issue operates on raw trajectories. Nevertheless, behaviours discovered from raw trajectories are not as rich and meaningful as those discovered from semantic trajectories. In this paper, we establish a mining approach to extract patterns from semantic trajectories. We propose to apply sequential pattern mining based on a pre-processing step of clustering to alleviate the former’s temporal complexity. Mining considers the spatial and temporal dimensions at different levels of granularity providing then richer and more insightful patterns about humans behaviour. We evaluate our work on tourists semantic trajectories in Kyoto. Results showed the effectiveness and efficiency of our model compared to state-of-the-art work.
Moez Elarfaoui, Nadia Ben AzzounaCLUSTERING BASED ON HYBRIDIZATION OF GENETIC ALGORITHM AND IMPROVED K-MEANS (GA-IKM) IN AN IOT NETWORK
International Journal of Wireless & Mobile Networks (IJWMN), Vol.16, No.6, December 2024, 2024
Abstract
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.
Alia Maaloul, Meriam Jemel, Nadia Ben AzzounaXAI based feature selection for gestational diabetes Mellitus prediction
10th International Conference on Control, Decision and Information Technologies (CoDIT), Vallette, Malta, 2024, pp. 1939-1944, 2024
Abstract
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
, , , Ameni Azzouz, , ,Sequencing a tri-criteria multiple job classes and customer orders problem on a single machine by using heuristics and simulated annealing method
Operational Research, 24(1), 2., 2024
Abstract
Multiple-job-class sequencing problems solve a group of jobs belonging to multiple classes, where to decrease the processing time, jobs in the same class tend to be performed together with the same setup time. In contrast, customer order scheduling problems focus on completing all jobs (belonging to different classes) in the same order at the same time to reduce shipping costs. Because related studies on multiple-job-class sequencing problems with more than one criterion are quite limited in the current research community, this study investigates tri-criteria scheduling problems with multiple job classes and customer orders on a single machine, where the goal is to minimize a linear combination of the makespan, total completion times of all jobs, and sum of the ranges of all orders. Due to the high complexity of the proposed problem, mixed integer programming is developed to formulate the problem, and a branch-and-bound method along with a lower bound and a property is utilized for finding the optimal schedules. Then, two heuristics and a simulated annealing algorithm are proposed to solve the problem approximately. The simulation results of the proposed heuristics and algorithm are evaluated through statistical methods.
, Siwar Mejri,A comprehensive study on social networks analysis and mining to detect opinion leaders
International Journal of Computers and Applications, 46(8), 641–650., 2024
Abstract
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.
Meriam Jemel, Alia Maaloul, Nadia Ben AzzounaXAI based feature selection for gestational diabetes Mellitus prediction
CoDIT 2024: 1939-1944, 2024
Abstract
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.
Wiem Ben Ghozzi, Zahra Kodia, Nadia Ben AzzounaFatigue Detection for the Elderly Using Machine Learning Techniques
10th International Conference on Control, Decision and Information Technologies (CoDIT), Vallette, Malta, 2024, pp. 2055-2060, doi: 10.1109/CoDIT62066.2024.10708516., 2024
Abstract
Elderly fatigue, a critical issue affecting the health and well-being of the aging population worldwide, presents as a substantial decline in physical and mental activity levels. This widespread condition reduces the quality of life and introduces significant hazards, such as increased accidents and cognitive deterioration. Therefore, this study proposed a model to detect fatigue in the elderly with satisfactory accuracy. In our contribution, we use video and image processing through a video in order to detect the elderly’s face recognition in each frame. The model identifies facial landmarks on the detected face and calculates the Eye Aspect Ratio (EAR), Eye Fixation, Eye Gaze Direction, Mouth Aspect Ratio (MAR), and 3D head pose. Among the various methods evaluated in our study, the Extra Trees algorithm outperformed all others machine learning methods, achieving the highest results with a sensitivity of 98.24%, specificity of 98.35%, and an accuracy of 98.29%.
Kalthoum RezguiLarge Language Models for Healthcare: Applications, Models, Datasets, and Challenges
-, 2024
Abstract
Large Language Models (LLMs) are being increasingly explored and used in healthcare for their potential applications. These models show the capacity to impact clinical care, research, and medical education significantly. In this research, we shed light on the transformative potential of LLMs in reshaping the healthcare landscape, emphasizing their role in enhancing patient care, improving decision-making processes, and advancing medical research. While the application of LLMs in healthcare presents immense opportunities, this research, also, addresses critical challenges and limitations. Concerns regarding the accuracy, reliability, and ethical implications of LLMs in medical contexts are highlighted, emphasizing the need for continuous monitoring and evaluation to ensure patient safety and data privacy. By exploring the opportunities and challenges associated with LLMs in healthcare, this study contributes to a deeper understanding of the implications and future directions of this technology in the healthcare sector.
Rihab Chaouch, Jihene Tounsi, , Sabeur ElkosantiniMixed Integer Programming For Patient Admission Scheduling in Hospital Network
This work presents a mixed-integer programming model to optimize patient admission scheduling in hospital networks, with the aim of improving bed assignment and coordination of care., 2024
Abstract
The Patient Admission Scheduling (PAS) process involves efficiently managing the admission of patients to specific beds within relevant departments while addressing all their medical needs over a defined time horizon. This study delves into PAS within hospital network, emphasizing the collaborative nature of their interactions. Collaborative interactions are a common challenge in hospitals, where they need to collaborate and share resources to allocate patients to a limited number of beds within a specified timeframe, ensuring all necessary medical conditions are met. To address this challenge, a mixed-integer mathematical programming model for the PAS problem within hospital network is proposed with the aim of minimizing a weighted sum of unsatisfied constraints.
