Search Results

In the present contribution, a robust output H∞ control ensuring the stability, reliability and security for nonlinear systems when actuator attacks (data deception attacks) occur. A new design method based on the polytopic rewriting of the attacked system as an uncertain one subject to external disturbances will be detailed. Robust polytopic state feedback observer sta-…

The paper presents two robust and efficient control algorithms based on (i) Optimal Control Allocation (OCA) and (ii) Nonlinear Model Predictive Control (NMPC). The robotics system consists of two rovers with mecanum wheels and mounted two 7-DOF arms carrying a common load. The overall system is an underdetermined one with non-holonomic constraints. The developed control…

We present in this contribution the distribution of a global multi-input-multi-output system in a sensor and actuator network. Based on controllability and observability, the global system is decentralized and the system properties are preserved as a result. This results in multiple decentralized local single-input-single-output systems with the same system order as the global system. As…

Renewable energy is an essential source of green growth for countries facing a shortage of fossil fuels. They offer a sustainable, inexhaustible, carbon-free solution to the future energy dependency of nations. Morocco, which has no traditional energy resources, depends entirely on the international primary energy market to meet its growing demand. For this reason, Morocco…

In different areas of industry (mining, food processing, pharmaceutical, manufacturing…), the problem of grain, aggregate and clusters flow arises during the handling activities especially loading and unloading. Thus, the study and control of the parameters that govern the flow of the granular medium and its interaction with its environment are key parameters to achieve the…

In this paper, an improved model has been proposed for investigating the impact of cyber-attacks on power systems regarding frequency disturbances and voltage disruption while changing the load called ICAPS. The proposed ICAPS model is formulated by five different controllers, such as LFC, AGC, AGC-PID, AVR, and AVR-PID, implemented in two sets of the system…

Applying black-box ML models in high-stakes fields like criminology, healthcare and real-time operating systems might create issues because of poor interpretability and complexity. Also, model building methods that include interpretability is now one of the growing research topics due to the absence of interpretability metrics that are both model-agnostic and quantitative. This paper introduces model…

Predicting the credit card default is important to the bank and other lenders. The credit default risk directly affects the interest charged to the borrower and the business decision of the lenders. However, very little research about this problem used the Generalized Linear Model (GLM). In this paper, we apply the GLM to predict the…

The main purpose in this work is to explore the fact that chaos, as a biological characteristic in the brain, should be used in an Artificial Neural Network (ANN) system. In fact, as long as chaos is present in brain functionalities, its properties need empirical investigations to show their potential to enhance accuracies in artificial…

The development of an aggregated system consisting of autonomously developed components is usually implemented as a self-contained unit. If such an aggregation is understood as a system of systems (SoS) that communicates via interfaces with its autonomous subsystems and components, the interfaces and communication exchange should play a central role in the architectural design. In…

With the development of Internet of Things technology and the widespread use of smart devices, artificial intelligence is now being applied as a decision-making tool in a variety of fields. To make machine learning models, including deep neural network models, more interpretable, various techniques have been proposed. In this paper, a method for explaining the…

An enduring vision of Artificial Intelligence is to build robots that can recognize and learn the visual world and who can speak about it in natural language. Automatic image description generation is a demanding problem in Computer Vision and Natural Language Processing. The applications of image description generation systems are in biomedicine, military, commerce, digital…

On Renewable Energy (RE), this field covers the most significant share of the world energy demand and challenges on the expensive measurement and maintenance equipment to be used. In all studies and designs, global solar radiation (GSR) measurements require assessment, estimation, and models to be applied together with the environment and meteorological data on installing…

Our world is characterised by uncertainty and complex, relational structures that carry temporal information, yielding large dynamic probabilistic relational models at the centre of many applications. We consider an example from logistics in which the transportation of cargoes using vessels (objects) driven by the amount of supply and the potential to generate revenue (relational) changes…

In 1998 we were talking about an NTIC era, and since the years 2010, we are tracing the beginning of a new era of technological development, called the era of digital transformation. During this new era companies have started to run towards the digitalization of their processes, which represent a large part of the market,…

Sustainable energy is gradually becoming the norm today due to greenhouse warming effects; as a result, the quests for different renewable energy sources such as photovoltaic cells as well as energy efficient electrical appliances are becoming popular. Therefore, this article explores the alternative energy case for thermoelectricity with focus on the steady-state mathematics, mixed modelings…

The SENSORIA Reference Modeling Language (SRML) aims at modelling composite services at a high level. Continuous time SRML extends SRML so that it can model services whose components can perform both discrete processes and continuous processes. In order to show how continuous time SRML is applied, in this paper, we systematically introduce our study on…

As artificial intelligence (AI) develops, it is expected that humans and AI will become more closely related than now. At the same time, however, the more closely humans and AI are related to each other, the more clearly they will face a moral dilemma, i.e., artificial intelligence will face a moral dilemma. To solve the…

Cyberbullying is a serious problem and caused an immense impact to the victim. To prevent the cyberbullying, the solution is to develop an automatic detection system. In this research, we propose a combined model for cyberbullying detection and emotion detection by using stacking method. The experiment is to create a better model for cyberbullying detection…

The data distribution used in model training is assumed to be similar with that when the model is applied. However, in some applications, data distributions may change over time. This situation is called the concept drift, which might decrease the model performance because the model is trained and evaluated in different distributions. To solve this…

The daily treats model reduction finite frequency (FFMR) design for Takagi Sugeno (T S) systems. This work is to FFMR design in such a way whether augmented model is steady get a reduced H? index in FF areas with noise is established as a prerequisite. To highlight the importance of suggested process, a practical application…

In this article, a fuzzy-based solution of coordination between behaviors of trajectory planning and obstacle avoiding in a RRP-typed SCARA robot control is presented. The first idea of the proposed solution is to divide a robot’s complex behavior into simpler parallel behaviors. The second key idea is a fuzzy-based coordination between these behaviors to make…

The objective of this research is to propose the estimator of the population mean for incomplete data by using information of simple linear relationship model in the data set. In addition, the factorization of the likelihood function is created to derive the maximum likelihood estimator for the population mean. The simulation study was conducted for…

Research focused on training and testing of dataset after Optimizing Software Component with the help of deep neural network mechanism. Optimized components are selected for training and testing to improve the accuracy at the time of software selection. Selected components are required to be attuned and accommodating as per requirement. Soft computing mechanism such as…

The paper presents the technique for the user-friendly numerical simulation of coupled oscillators described by the Kuramoto model. Oscillators couplings are defined as arbitrary 2?-periodic functions given by the Fourier series. Matlab procedure was developed to generate netlist for the equivalent electrical circuit diagram of the Kuramoto model. The input data of the procedure include…