Tawfik Masrour

Université Moulay Ismail de Meknes | UMI · Applied Mathematics

In modern industrial settings, the enhancement of laser welding efficiency and quality is deemed critical. This paper presents an approach that integrates the Internet of Things (IoT) and real-time monitoring systems to address porosity in laser welding. A system was developed employing acoustic, vibration, and thermal sensors to collect real-time...

Overdispersed black-box variational inference uses importance sampling to decrease the variance of the Monte Carlo gradient in variational inference. This is achieved by using an overdispersed proposal distribution that belongs to the same exponential family as the variational distribution. This paper seeks to dynamically improve this proposal dist...

The manual execution of failure mode and effects analysis (FMEA) is time-consuming and error-prone. This article presents an approach in which large language models (LLMs) are integrated into FMEA. LLMs improve and accelerate FMEA with human in the loop. The discussion looks at software tools for FMEA and emphasizes that the tools must be tailored...

In recent years, the advancement of convolutional neural networks (CNNs) has been driven by the pursuit of higher classification accuracy in image tasks. However, achieving optimal performance often requires extensive manual design, incorporating domain-specific knowledge and problem-understanding. This approach often results in highly complex netw...

Bayes by Backprop is a variational inference method based on the reparametrization trick to assure backpropagation in Bayesian neural networks. Generally, the approximate distributions used in Bayes by backprop method are made unimodal to facilitate the use of the reparametrization trick. But frequently, the modelling of some tasks requires more so...

In the context of Industry 4.0 and smart manufacturing, production factories are increasingly focusing on process optimization, high product customization, quality improvement, cost reduction, and energy saving by implementing a new type of digital solutions that are mainly driven by Internet of Things (IoT), artificial intelligence, big data, and...

Lenient Multiagent Reinforcement Learning 2 (LMRL2) is an Independent Learners Algorithm for cooperative multiagent systems that is known to outperform other Independent Learners Algorithms in terms of convergence. However, the algorithm takes longer to converge. In this paper, we first present a new formulation of LMRL2, and then, based on this ne...

In this study, we address the challenge of accurately solving physical problems involving complex partial differential equations using deep learning methods. Traditional approaches typically employ uniformly sampled points from the entire domain as training data. In practical PDE problems, achieving uniform precision across the entire domain is oft...

The numerical solution of partial differential equations (PDEs) is a crucial component of scientific computing. The idea of using a neural network to approximate PDE solutions is natural given the success of neural networks in many approximation problems. The main idea is to train a neural network to minimize the residual of the differential operat...

Due to climate change and increasing global energy demands, lithium-ion batteries (LIBs) have recently gained increasing interest, particularly in electric vehicle applications (EV) and energy storage systems (ESS), due to their valuable features such as high energy density, fast charging ability, and long lifespan. The battery management system (B...

Brain tumors (BT) pose a significant health risk due to their uncontrolled and abnormal cell proliferation. Recent advances in deep learning (DL) have revolutionized medical imaging diagnostics; however, applying machine learning (ML) for automatic BT classification faces challenges related to limited and low-quality data accessibility [1]. Moreove...

The Distributed Q-learning algorithm is known to converge in the case of deterministic multiagent systems. However, the algorithm fails to converge in the presence of the stochasticity problem due to the over-estimation of action values. In this article, we present a new relaxation of the Distributed Q-learning by introducing a new update rule for...

Convolutional neural networks (CNNs) are very powerful learning method in the deep learning framework. However, they contain a very large number of parameters, which restricts their utilization in platform-limited devices. Searching for an appropriate and simple convolutional neural network architecture with an optimal number of parameters is still...

Convolutional Neural Network (CNN) is a famous type of deep feed-forward network that has proved a significant success in the area of computer vision. Despite this success, the choice of the optimal architecture for a given problem remains a challenging issue. The performance of CNN is significantly impacted by a few of its hyper-parameters. In thi...

Work measurement is a critical aspect of industrial engineering, where various methods are employed to analyze work and optimize productivity. One of the primary tools used by industrial engineers is cycle time, which determines the time taken to complete tasks within a company. However, traditional human analysis of work can be challenging and tim...

In the manufacturing sector, the ability to predict key performance indicators (KPIs) such as Overall Equipment Efficiency (OEE) is crucial for process optimization and informed decision-making. Although several machine learning methods have been employed to forecast KPIs, their real-time predictive capabilities remain underutilized. This paper pre...

Deep learning has made significant progress in artificial intelligence, providing new solutions to a variety of previously challenging problems. However, standard deep learning algorithms only offer point estimates of the model, which fail to express the model uncertainty, leading to overconfident decisions. To address these issues, the Bayesian ap...

This research addresses the need for an advanced and efficient approach to ergonomic assessment by leveraging the METEO (Work and Organization Assessment Tool) method in conjunction with Artificial Intelligence (AI) and computer vision (CV). The primary objective is to identify and quantify the risk factors within work environments that contribute...

In this article, we introduce the Smooth Q-Learning algorithm for independent learners (distributed and non-communicative learners) in cooperative Markov games. Smooth Q-Learning aimed to solve the relative over-generalization and the stochasticity problems while also performing well in the presence of other non-coordination factors such as the mis...

This book presents use-cases of IoT, AI and Machine Learning (ML) for healthcare delivery and medical devices. It compiles 15 topics that discuss the applications, opportunities, and future trends of machine intelligence in the medical domain. The objective of the book is to demonstrate how these technologies can be used to keep patients safe and h...

Lithium-ion batteries are widely employed in industrial, consumer, and military applications. Nowadays, lithium-ion batteries’ technology is gaining the interest of both research and industry fields to ensure better performance of LIB by investing mostly in monitoring the internal and hidden states. The state of charge is one of the most critical...

The detection and localization of small and tiny defects on high-resolution images is considered one of the main challenges in the field of computer vision. In the manufacturing industry, the production speed and cycle time are considered the major target of a production process. For such reason, automated quality detection is getting even more com...

This study explores the application of machine learning algorithms for supporting complex product manufacturing quality through a focus on quality assurance and control. We aim to take advantage of ML technics to solve one of the complex manufacturing problems of the tempered glass manufacturing industry as a first attempt to automate product quali...

This article is about a new smoothing method for piecewise smooth functions. This smoothing method is based on formulating any piecewise smooth function as the expectation of a discrete random variable. By adopting this formulation, we show that smoothing apiecewise smooth function is equivalent to smooth a probability distribution. In addition, we...

We developed a self-optimizing decision system that dynamically minimizes the overall energy consumption of an industrial process. Our model is based on a deep reinforcement learning (DRL) framework, adopting three reinforcement learning methods, namely: deep Q-network (DQN), proximal policy optimization (PPO), and advantage actor–critic (A2C) algo...

This study introduce the application of machine learning algorithms for supporting the manufacturing quality control of a complex process as an alternative for the destructive testing methodologies. The choice of this application field was motivated by the lack of a robust engineering technique to assess the production quality in real time, this ar...

In the energy transition, controlling energy consumption is a challenge for everyone, especially for BIPV (Building Integrated Photovoltaics) buildings. Artificial Intelligence is an efficient tool to analyze fine prediction with a better accuracy. Intelligent sensors are implemented on the different equipments of a BIPV building to collect informa...

The aim of this paper is to offer a novel way of creating a collection of automated scenario-based tests to evaluate the safety of autonomous cars, especially those that mix simulation and real-world testing. Our methodology is built on formal methods, which combine a mathematical model to describe a scenario, define a relevant metric, and generate...

In this paper, we propose a smart planning and control system for autonomous vehicles in a high dimensional space. It is a complete unsupervised scheduler and motion planner. Many warehouses take advantage of using an automated material handling process for product transshipment to speed up procedures. However, the growth of the space dimensions be...

Key performance indicators are tools for management, decision support and forecasting; they reflect the strategy and vision of the company in terms of objectives and allow to always staying in step with the expectations of the stakeholders. Accurate forecasting of the indicators allows decisions to be reoriented to ensure performance optimization w...

Machine Learning automatically creates analytical models that adapt to what is in the data. After a while, the algorithm is used to deliver accurate results, whether it’s making smarter credit decisions, entering into retail deals, medical diagnostics, or detecting fraud. The use of Deep Learning technology as a new machine learning tool has experi...

The classical approach of reinforcement learning for single agent is based on the concept of reward that comes only from the environment. By trial-and-error, the agent has to learn to maximize its total accumulated reward. Several algorithms and techniques were developed for a single agent reinforcement learning. Our purpose is to benefit from all...

Traffic accidents are the leading cause of death and serious injury. Many accidents occur at controlled intersections, such as those with traffic lights. Artificial intelligence consists of a wide range of computer techniques intended for problems such as pairing models, language processing and solving very complex and ill-defined problems. The art...

This research investigates the applicability of Deep Reinforcement Learning (DRL) to control the heating process parameters of tempered glass in industrial electric furnace. In most cases, these heating process parameters, also called recipe, are given by a trial and error procedure according to the expert process experience. In order to optimize t...

Automated guided vehicles system (AGVS) is a new logistics problem area, and the most demanded in terms of performance in view of the exponential growth of product traffic in the world. The present paper aims to to propose a new approach, to deal with AGVS problems, based on deep reinforcement learning algorithms, as an alternative to classic metho...

This book gathers selected papers from Artificial Intelligence and Industrial Applications (A2IA’2020), the first installment of an annual international conference organized by ENSAM-Meknes at Moulay Ismail University, Morocco. The 29 papers presented here were carefully reviewed and selected from 141 submissions by an international scientific com...

This book gathers the refereed proceedings of the Artificial Intelligence and Industrial Applications (A2IA’2020), the first installment of an annual international conference organized by the ENSAM-Meknes at Moulay Ismail University, Morocco. The 30 papers presented here were carefully reviewed and selected from 141 submissions by an international...

In this article, we present a new approach to construct smoothing approximations for piecewise smooth functions. This approach proposes to formulate any piecewise smooth function as the expectation of a random variable. Based on this formulation, we show that smoothing all elements of a defined space of piecewise smooth functions is equivalent to s...

The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often to...

In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from a final product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historica...

The automatic detection of structure defects based on computer vision is evolving, especially with constant advances in Deep Convolutional Neural Network. Several image-processing methods have been proposed over the years based on Deep Learning. Nevertheless, the studies are mainly concerned with the crack damage and do not takes into account the o...

Machine learning (a subset of Artificial Intelligence) automatically creates analytic models that adapt to what they find in the data. Over time, the algorithm “learns” how to deliver more accurate results, whether the goal is to make smarter credit decisions, retail offers, medical diagnoses or fraud detection. The use of Deep Learning technology...

The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often to...

In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from the product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historical tr...

The overall equipment effectiveness (OEE) is a performance measurement metric wildly used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often to...

This paper proposes a learning approach for dynamic parameterization of ant colony optimization algorithms. In fact, the specific optimal configuration for each optimization problem using these algorithms, whether at the level of preferences, the level of evaporation of the pheromone, or the number of ants, makes the dynamic approach an interested...

The purpose of this paper is developing dynamic strategies using proactive integration of decision criteria for Sustainable Supplier Selection. More specifically, we propose to solve a multi-objective problem with a Meta-heuristic, namely the Multi Ant Colony System. Our approach of Supplier Selection goes through several steps and several decision...

The representation of texts in the current methods of information extraction, and TextMining in general, does not always reflect the dependencies between descriptors. In the vector representation, for example, descriptors related are often considered to be either totally independent or totally similar. This type of approach can be considered as a c...

This contribution describes the possibility of extending to the elastic wave equation with the physical no stress boundary condition, the classical results on stable and unstable boundary observation. The proofs relies on one hand on the introduction of the equations satisfied by the divergence and the curl of the solution and on the other hand on...