Youness Riouali

Medical imaging plays a crucial role in modern healthcare, facilitating the diagnosis and treatment of various diseases. The advent of deep learning has revolutionized the processing and analysis of medical images. This paper reviews recent literature on deep learning applications in medical imaging, focusing specifically on segmentation and classification for disease diagnosis and treatment. We discuss recent advancements in deep learning architectures tailored for these tasks, highlighting their relevance and effectiveness. The studies reviewed span the period from January 2023 to April 2024, concentrating on the latest deep learning methods proposed for breast cancer segmentation. Additionally, we explore the availability and characteristics of publicly available medical image datasets for breast cancer, emphasizing their importance in training and evaluating deep learning models. An overview of commonly used metrics for assessing model efficacy is provided, underscoring their role in quantifying performance. Furthermore, we address the challenges and limitations faced by deep learning methods in medical imaging. Through analysis and discussion, we propose innovative directions to address these challenges, paving the way for promising future applications in early disease detection and personalized treatment planning.

The feature selection task is a crucial phase in data analysis, aiming to identify a minimized set of relevant features for the target class, thereby eliminating irrelevant and redundant attributes used for model training. While population-based feature selection approaches offer prominent solutions for classification performance, their computational time can be prohibitive. To mitigate delays and optimize resource utilization, this study adopts machine learning operations (MLOps). MLOps involves the seamless transition of experimental Machine Learning models into production, serving them to end users and automating the feature selection phase. This paper introduces a novel feature selection method based on improved migrating bird optimization and its automated variant integrated into MLOps. Experiments conducted on six medical datasets validate the effectiveness of our proposed feature selection method in improving the outcomes of medical diagnosis systems. The results showcase satisfactory performance in terms of classification compared to concurrent feature selection algorithms.

The tremendous increase in the urban population highlights the need for more efficient transport systems and techniques to alleviate the increasing number of the resulting traffic-associated problems. Modeling and predicting road traffic flow are a critical part of intelligent transport systems (ITSs). Therefore, their accuracy and efficiency have a direct impact on the overall functioning. In this scope, a new approach for predicting the road traffic flow is proposed that combines the Petri nets model with a dynamic estimation of intersection turning movement counts to ensure a more accurate assessment of its performance. Thus, this manuscript extends our work by introducing a new feature, namely turning movement counts, to attain a better prediction of road traffic flow. A simulation study is conducted to get a better understanding of how predictive models perform in the context of estimating turning movements.

One of the most critical issues in modern cities is transportation management. Issues that are encountered in this regard, such as traffic congestion, high accidents rates and air pollution etc., have pushed the use of Intelligent Transportation System (ITS) technologies in order to facilitate the traffic management. Seen in this perspective, this paper brings forward a road traffic management system based on wireless sensor networks; it introduces the functional and deployment architecture of the system and focuses on the analysis component that uses a new extension of batches Petri nets for modeling road traffic flow. A real world implementation of visualization and data analysis components were carried out.

The traffic network and the quality of road transportation play an increasingly vital role in every economy's growth around the world and are part of the lifeblood of countries' trade and communications. With the continued growth in number of vehicles, it can be clearly seen that the existing road traffic management systems have reached their limits and can't cope with the daily challenges in a efficient way through the road jamming, remarkable increase in the number of accidents and traffic-related pollution. Seen in this perspective, this paper proposes a global system based on wireless sensor networks for managing road traffic networks of different scales; it therefore presents a functional and deployment architecture of the system. The paper presents also a simple use case of the proposed system in order to explain how to monitor the traffic flow. At the end, a real world implementation of some of the components, namely visualization and Traffic Modelling and Analytics that model the traffic flow dynamics evolution were provided.

Traffic flow modelling is an essential step for designing and controlling the transportation systems. It is not only necessary for improving safety and transportation efficiency, but also it can yield economic and environmental benefits. Consider the discrete and continuous aspects of traffic flow dynamics, hybrid Petri nets have proved to be a powerful tool for approaching this dynamics and describe the vehicle behavior accurately since they include both aspects. A new extension of hybrid petri net is presented in this paper for generalizing the traffic flow modelling through taking into account state dependencies on external rules which can be timed and also nondeterministic time such as stop sign or priority roads. Moreover, a segmentation of roads is proposed to deal with the accurate localization of events.

Missing data is an inevitable problem in wireless sensor network and the way missing values are handled can significantly affect the analysis results involving such data. To address data missing issues, spatial correlation and temporal correlation modeling can be applied. This paper aims at reviewing some popular spatial and temporal correlation based methods. The proposed review includes a critical overview through a summary of pros and cons of these methods and a comparison between them based on simulation results. To our best knowledge, there is no such comparative benchmarking study in the current literature.