Papers by Lhassane Idoumghar
IEEE Access, 2022
Recent advances in hardware and communication technologies have accelerated the deployment of bil... more Recent advances in hardware and communication technologies have accelerated the deployment of billions of wireless sensors. This transformation has created a wide range of applications adapted to the evolving trends of our daily life requirements. Wireless sensor networks (WSNs) could be deployed in several target areas including buildings, forests, oceans, and smart cities. Nevertheless, finding the optimal location for each sensor node is a challenging task, typically when the environment involves heterogeneous obstacles. Many approaches and methods have been proposed to deal with the problem of WSN deployment, each addressing one or more objectives and constraints, such as network coverage, lifetime, connectivity, and energy consumption. The purpose of this survey paper is to provide the needed background to understand and study the WSNs deployment problem with a focus on its two key aspects: the optimization model and the solving methods based on artificial intelligence (AI). Additionally, it covers recent works on WSNs deployment and identifies their advantages and limitations. Furthermore, simulation experiments were carried out to compare the performance of widely used algorithms in the context of WSNs deployment problem, primarily genetic algorithm, particle swarm optimization, flower pollination, and ant colony optimization. Finally, this paper discusses and highlights several open challenges and research issues that must be explored in the future.
This paper provides a comparison study of the quality services of RPL protocols in low-power and ... more This paper provides a comparison study of the quality services of RPL protocols in low-power and lossy net- works (LLN). We evaluate and compare our proposed protocol which is an extension of RPL based on Operator Calculus (OC), called RPL-OC, with the standard and other RPL variants. OC based approach is applied to extract the feasible end-to-end paths while assigning a rank to each one. The goal is to provide a tuple that containing the most efficient paths in end-to-end manner by considering more network metrics instead of one. Further, to address some significant issues of the performance analysis, a statistical test has been performed in order to determine whether the proposed protocol outperforms others or not by using Friedman test. The results show that there is a strong indication that four different protocols were analyzed and compared. It reveals that the proposed scheme outperforms others, especially in terms of end-to-end delay and energy consumption which allow ensuring quality of services requirements for Internet of Things (IoT) or smart city applications.
IEEE Sensors Journal, Jul 1, 2021
Today, diseases and illnesses are becoming the most dangerous enemy to humans. The number of pati... more Today, diseases and illnesses are becoming the most dangerous enemy to humans. The number of patients is increasing day after day accompanied with the emergence of new types of viruses and diseases. Indeed, most hospitals suffer from the deficiency of qualified staff needed to continuously monitor patients and act when an urgent situation is detected. Recently, wireless body sensor network (WBSN) has been considered as an efficient technology for real-time health-monitoring applications. It provides a low cost solution for hospitals, performs a relief for staff and allows doctors to remotely track patients. However, the huge amount of data collected by sensors produce two major challenges for WBSN: the quickly depletion of the available sensor energy and the complex decision making by the doctor. In this article, we propose an efficient Patient-to-Doctor (P2D) framework for real-time health monitoring and decision making. P2D works on two levels: sensors and coordinator. At the sensor level, P2D allows to save the sensor energy, by adapting its sensing frequency, and to directly detect any abnormal situation of the patient. Whilst, at the coordinator level, P2D allows to store an archive for each patient, predict the patient situation during the next periods of time and make a suitable decision by the doctors. We conducted a set of simulations on real health data in order to show the relevance of our platforms compared to other existing systems.
The rapid growing of Internet of things (IoT) is one of the most important factors of integrating... more The rapid growing of Internet of things (IoT) is one of the most important factors of integrating WSN in smart buildings. Furthermore, the presence of these sensors and technologies allow improving the accuracy of the measured data while reducing buildings energy consumption and guaranteeing the comfort required by the indoor users. However, finding the optimal sensor nodes positions in an indoor environment with heterogeneous obstacles is the keystone to ensure a full sensing coverage with a full connectivity. To meet this challenge, various initiatives have been proposed in the literature. First, we summarize the main developed solutions to optimize WSN deployment in an indoor/outdoor environment. Then, we propose our conceptual approach that relies on exploiting BIM (Building information modeling) database to get real time and valid information about the target area. Indeed, the proposed solution can be integrated within BIM tools as a plugin in order to optimize sensors deployment in real time by taking into account nodes and obstacles heterogeneity at the same time.
2022 Ninth International Conference on Software Defined Systems (SDS)
2022 9th International Conference on Internet of Things: Systems, Management and Security (IOTSMS)
Sustainable Computing: Informatics and Systems
GLOBECOM 2022 - 2022 IEEE Global Communications Conference
2016 IEEE International Conference on Communications (ICC), 2016
The works on Search Based Software Engineering (SBSE) have been a big increase in the last decade... more The works on Search Based Software Engineering (SBSE) have been a big increase in the last decade. An approach to software engineering in which search based optimisation algorithms are applied to address problems in software engineering. SBSE has been applied to problems throughout the software engineering lifecycle, from requirements and project planning to maintenance and re-engineering. This paper provides a modification and an implementation of SBSE on evolutionary multi-objective based approach for deployment of wireless sensor network (WSN) with the presence of fixed obstacle. In this work a multi-objective evolutionary algorithms based on elitist non-dominated sorting genetic algorithm (NSGA-II) is proposed to address the deployment problem. Two functions namely ranking function and fitness function are used to select the best optimal solution from Pareto optimal fronts.
Communications in computer and information science, 2021
RAIRO - Operations Research
This paper presents a multi-objective mixed-integer non-linear programming model for a congested ... more This paper presents a multi-objective mixed-integer non-linear programming model for a congested multiple-server discrete facility location problem with uniformly distributed demands along the network edges. Regarding the capacity of each facility and the maximum waiting time threshold, the developed model aims to determine the number and locations of established facilities along with their corresponding number of assigned servers such that the traveling distance, the waiting time, the total cost, and the number of lost sales (uncovered customers) are minimized simultaneously. Also, this paper proposes modified versions of some of the existing heuristics and metaheuristic algorithms currently used to solve NP-hard location problems. Here, the memetic algorithm along with its modified version called the stochastic memetic algorithm, as well as the modified add and modified drop heuristics are used as the solution methods. Computational results and comparisons demonstrate that althoug...
International Journal of Remote Sensing, 2022
Urban areas are increasing since several years as a result of development of built-up areas, netw... more Urban areas are increasing since several years as a result of development of built-up areas, network infrastructure, industrial areas or other built-up areas. This urban sprawl has a considerable impact on natural areas by changing the functioning of ecosystems. Mapping and monitoring Urban Fabrics (UF) is therefore relevant for urban planning and management, risk analysis, human health or biodiversity. For this research, Sentinel-2 (level 2A) single-date images of the East of France, with a high spatial resolution (10m), are used to assess two semantic segmentation networks (U-Net) that we combined using feature fusion between a from scratch network and a pre-trained network on ImageNet. Moreover three spectral or textural indices have been added to the both networks in order to improve the classification results. The results showed a performance gain for the fusion methods in classifying several UF. However, there is a difference in performance depending on the urbanization gradient; highly urbanized areas provide a better distinction of some UF's classes than rural areas.
Evolutionary Computation in Combinatorial Optimization, 2021
International Journal of Computer Assisted Radiology and Surgery, 2019
Purpose Manual feedback from senior surgeons observing less experienced trainees is a laborious t... more Purpose Manual feedback from senior surgeons observing less experienced trainees is a laborious task that is very expensive, time-consuming and prone to subjectivity. With the number of surgical procedures increasing annually, there is an unprecedented need to provide an accurate, objective and automatic evaluation of trainees' surgical skills in order to improve surgical practice. Methods In this paper, we designed a convolutional neural network (CNN) to classify surgical skills by extracting latent patterns in the trainees' motions performed during robotic surgery. The method is validated on the JIGSAWS dataset for two surgical skills evaluation tasks: classification and regression. Results Our results show that deep neural networks constitute robust machine learning models that are able to reach new competitive state-of-the-art performance on the JIGSAWS dataset. While we leveraged from CNNs' efficiency, we were able to minimize its blackbox effect using the class activation map technique. Conclusions This characteristic allowed our method to automatically pinpoint which parts of the surgery influenced the skill evaluation the most, thus allowing us to explain a surgical skill classification and provide surgeons with a novel personalized feedback technique. We believe this type of interpretable machine learning model could integrate within "Operation Room 2.0"
2020 IEEE Congress on Evolutionary Computation (CEC), 2020
The amount of scientific conferences and journal articles continues to increase and new approache... more The amount of scientific conferences and journal articles continues to increase and new approaches are required to support users in finding relevant publications. This study investigates to what extent a new machine learning (ML) pipeline may preferentially identify links between similar scientific articles. The characteristics of intersections and unions of keywords, contextualized keywords (i.e., synsets) and neighbors are computed and used to train a ML model. Automated machine learning (AutoML) is then applied to ease the search for a new pipeline. Extensive experiments demonstrated that a newly designed ML model achieves an accuracy of 90% on a dataset of approximately 120,000 article pairs. These results suggest that application of ML for proposing new recommendation systems could have in the long term a positive impact in the literature.
IEEE Access
Recent advances in hardware and communication technologies have accelerated the deployment of bil... more Recent advances in hardware and communication technologies have accelerated the deployment of billions of wireless sensors. This transformation has created a wide range of applications adapted to the evolving trends of our daily life requirements. Wireless sensor networks (WSNs) could be deployed in several target areas including buildings, forests, oceans, and smart cities. Nevertheless, finding the optimal location for each sensor node is a challenging task, typically when the environment involves heterogeneous obstacles. Many approaches and methods have been proposed to deal with the problem of WSN deployment, each addressing one or more objectives and constraints, such as network coverage, lifetime, connectivity, and energy consumption. The purpose of this survey paper is to provide the needed background to understand and study the WSNs deployment problem with a focus on its two key aspects: the optimization model and the solving methods based on artificial intelligence (AI). Additionally, it covers recent works on WSNs deployment and identifies their advantages and limitations. Furthermore, simulation experiments were carried out to compare the performance of widely used algorithms in the context of WSNs deployment problem, primarily genetic algorithm, particle swarm optimization, flower pollination, and ant colony optimization. Finally, this paper discusses and highlights several open challenges and research issues that should be explored in the future.
2020 7th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2020
This paper provides a comparison study of the quality services of RPL protocols in low-power and ... more This paper provides a comparison study of the quality services of RPL protocols in low-power and lossy net- works (LLN). We evaluate and compare our proposed protocol which is an extension of RPL based on Operator Calculus (OC), called RPL-OC, with the standard and other RPL variants. OC based approach is applied to extract the feasible end-to-end paths while assigning a rank to each one. The goal is to provide a tuple that containing the most efficient paths in end-to-end manner by considering more network metrics instead of one. Further, to address some significant issues of the performance analysis, a statistical test has been performed in order to determine whether the proposed protocol outperforms others or not by using Friedman test. The results show that there is a strong indication that four different protocols were analyzed and compared. It reveals that the proposed scheme outperforms others, especially in terms of end-to-end delay and energy consumption which allow ensuring quality of services requirements for Internet of Things (IoT) or smart city applications.
Lecture Notes in Computer Science, 2018
In this paper, a high-level relay hybridization of three metaheuristics with different properties... more In this paper, a high-level relay hybridization of three metaheuristics with different properties is proposed. Our objective is to investigate the use of this kind of hybridization to tackle black-box optimization problems. Indeed, without any knowledge about the nature of the problem to optimize, combining the strengths of different algorithms, belonging to different classes of metaheuristics, may increase the probability of success of the optimization process. The proposed hybrid algorithm combines the multiple local search algorithm for dynamic optimization, the success-history based adaptive differential evolution, and the standard particle swarm optimization 2011 algorithm. An experimental analysis using two well-known benchmarks is presented, i.e. the Black-Box Optimization Benchmarking (BBOB) 2015 and the Black Box optimization Competition (BBComp). The proposed algorithm obtains promising results on both benchmarks. The ones obtained at BBComp show the relevance of the proposed hybridization.
2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019
Typical evolutionary algorithms for Unmanned Aerial Vehicles (UAV) path planning problem represen... more Typical evolutionary algorithms for Unmanned Aerial Vehicles (UAV) path planning problem represent solutions by considering a fixed number of way points, from which and by using an interpolation strategy they can generate the actual path. This paper proposed an alternative method in which the number of control points is determined during the optimization process. We investigate to what extent optimizing the number of these points during the search process could contribute to improve the results. Towards this goal, a novel approach is proposed which combines the standard teaching learning-based optimization (TLBO) with the ideas of mutation and crossover from genetic algorithm (GA). Experiments are conducted on a set of scenarios in two-dimension (2D) and three-dimension (3D) environments. The results demonstrate promising performance for solving the path planning problem of UAV.
2018 IEEE Congress on Evolutionary Computation (CEC), 2018
The performance of Differential Evolution (DE) algorithm strongly depends on its control paramete... more The performance of Differential Evolution (DE) algorithm strongly depends on its control parameters. Despite its efficiency and wide use, it might get trapped in local minimum due to premature convergence. In this study, a novel parameter adaptation strategy is proposed to address the mentioned problems. To do so, a pheromone matrix is employed to adjust parameter setting of the algorithm during the optimization process. Moreover, the convergence issue of DE is tackled by incorporating a new restart strategy. The performance of the proposed algorithm is firstly evaluated on the CEC 2011 real world problems test suite. Thereafter, we applied the algorithm to find optimized structure of a recent electric motor design considered for this study. The results reveal the competitive performance of the proposed approach with state-of-the-art algorithms.
Uploads
Papers by Lhassane Idoumghar