Search

The fashion industry is at the brink of radical transformation. The emergence of Artificial Intelligence (AI) in fashion applications creates many opportunities for this industry and make fashion a better space for everyone. Interesting to this matter, we proposed a virtual try-on interface to stimulate consumers purchase intentions and facilitate their online buying decision process. Thus, we present, in this paper, our flexible person generation system for virtual try-on that aiming to treat the task of human appearance transfer across images while preserving texture details and structural coherence of the generated outfit. This challenging task has drawn increasing attention and made huge development of intelligent fashion applications. However, it requires different challenges, especially in the case of a wide divergences between the source and target images. To solve this problem, we proposed a flexible person generation framework called

The exponential increase in new coronavirus disease 2019 (COVID-19) cases and deaths has made COVID-19 the leading cause of death in many countries. Thus, in this study, we propose an efficient technique for the automatic detection of COVID-19 and pneumonia based on X-ray images. A stacked denoising convolutional autoencoder (SDCA) model was proposed to classify X-ray images into three classes: normal, pneumonia, and COVID-19. The SDCA model was used to obtain a good representation of the input data and extract the relevant features from noisy images. The proposed model's architecture mainly composed of eight autoencoders, which were fed to two dense layers and SoftMax classifiers. The proposed model was evaluated with 6356 images from the datasets from different sources. The experiments and evaluation of the proposed model were applied to an 80/20 training/validation split and for five cross-validation data splitting, respectively. The metrics used for the SDCA model were the classification accuracy, precision, sensitivity, and specificity for both schemes. Our results demonstrated the superiority of the proposed model in classifying X-ray images with high accuracy of 96.8%. Therefore, this model can help physicians accelerate COVID-19 diagnosis.

In this paper, we present a learning algorithm for the Elman Recurrent Neural Network (ERNN) based on Biogeography-Based Optimization (BBO). The proposed algorithm computes the weights, initials inputs of the context units and self-feedback coefficient of the Elman network. The method applied for four benchmark problems: Mackey Glass and Lorentz equations, which produce chaotic time series, and to real life classification; iris and Breast Cancer datasets. Numerical experimental results show improvement of the performance of the proposed algorithm in terms of accuracy and MSE eror over many heuristic algorithms.

The Ultra-Large-Scale Software (ULSS) systems development challenges today’s software management and development approaches. Northrop et al. (2006) revealed three broad areas of challenges [1]. To deal with those challenges, they propose an interdisciplinary portfolio of research. In particular, we address the design and evolution challenge by focusing on the design area of research. In order to regulate the ULSS systems, the traditional software engineering tools face challenges as they are top-down so they deal with each domain model separately. To address the domain diversity like in the smart city systems, we propose the Framework for Agile Regulated Ultra Large Scale Software System (FARUL3S) to look at the ULSS system from bottom-up. The FARUL3S is a user-centered solution that aims at combining the complex adaptive system, the financial economics as well as the engineering systems design. Our contribution aims to regulate and constrain the ULSS systems by using architectural agreements and other rules. In this paper, we provide a detailed description of the FARUL3S steps. Our Framework generates a system Design Rule Hierarchy (DRH) so it can be used to constrain the entire system design. In the future, we will provide an illustration of the FARUL3S adoption on the management and design of different smart city services to ensure the efficiency of our solution.

Particle swarm optimization system based on the distributed architecture over multiple sub-swarms has shown its efficiency for static optimization and has not been studied to solve dynamic multi-objective problems (DMOPs). When solving DMOP, tracking the best solutions over time and ensuring good exploitation and exploration are the main challenging tasks. This study proposes a novel Dynamic Pareto bi-level Multi-Objective Particle Swarm Optimization (DPb-MOPSO) algorithm including two parallel optimization levels. At the first level, all solutions are managed in a single search space. When a dynamic change is successfully detected in the objective values, the Pareto ranking operator is used to enable a multiple sub-swarm’ subdivisions and processing which drives the second level of enhanced exploitation. A dynamic handling strategy based on random detectors is used to track the changes of the objective function due to time-varying parameters. A response strategy consisting in re-evaluate all unimproved solutions and replacing them with newly generated ones is also implemented. Inverted generational distance, mean inverted generational distance, and hypervolume difference metrics are used to assess the DPb-MOPSO performances. All quantitative results are analyzed using Friedman's analysis of variance while the Lyapunov theorem is used for stability analysis. Compared with several multi-objective evolutionary algorithms, the DPb-MOPSO is robust in solving 21 complex problems over a range of changes in both the Pareto optimal set and Pareto optimal front. For 13 UDF and ZJZ functions, DPb-MOPSO can solve 8/13 and 7/13 on IGD and HVD with moderate changes. For the 8 FDA and dMOP benchmarks, DPb-MOPSO was able to resolve 4/8 with severe change on MIGD, and 5/8 for moderate and slight changes. However, for the 3 kind of environmental changes, DPb-MOPSO assumes 4/8 of the solving function on IGD and HVD metrics.

A newly introduced method called Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting method is applied and extended in this study to forecast numerical values. Unlike traditional forecasting techniques which forecast only future values, our proposed method provides a new extension to correct the predicted values which is done by forecasting the estimated error. Experimental results demonstrated that the proposed method has a high accuracy both in training and testing data and outperform the state-of-the-art RNN models on Mackey-Glass, NARMA, Lorenz and Henon map datasets.

A novel approach is presented to reduced annotation based on Deep Active Learning for Arabic text detection in Natural Scene Images.- A new Arabic text images dataset (7k images) using the Google Street View service named TSVD.- A new semi-automatic method for generating natural scene text images from the streets.- Training samples is reduced to 1/5 of the original training size on average.- Much less training data to achieve better dice index : 0.84

Multifactorial Optimization (MFO) and Evolutionary Transfer Optimization (ETO) are new optimization challenging paradigms for which the multi-Objective Particle Swarm Optimization system (MOPSO) may be interesting despite limitations. MOPSO has been widely used in static/dynamic multi-objective optimization problems, while its potentials for multi-task optimization are not completely unveiled. This paper proposes a new Distributed Multifactorial Particle Swarm Optimization algorithm (DMFPSO) for multi-task optimization. This new system has a distributed architecture on a set of sub-swarms that are dynamically constructed based on the number of optimization tasks affected by each particle skill factor. DMFPSO is designed to deal with the issues of handling convergence and diversity concepts separately. DMFPSO uses Beta function to provide two optimized profiles with a dynamic switching behaviour. The first profile, Beta-1, is used for the exploration which aims to explore the search space toward potential solutions, while the second Beta-2 function is used for convergence enhancement. This new system is tested on 36 benchmarks provided by the CEC’2021 Evolutionary Transfer Multi-Objective Optimization Competition. Comparatives with the state-of-the-art methods are done using the Inverted General Distance (IGD) and Mean Inverted General Distance (MIGD) metrics. Based on the MSS metric, this proposal has the best results on most tested problems.

The Ultra-Large-Scale Software (ULSS) systems development challenges today’s software management and development approaches. Northrop et al. (2006) revealed three broad areas of challenges [1]. To deal with those challenges, they propose an interdisciplinary portfolio of research. In particular, we address the design and evolution challenge by focusing on the design area of research. In order to regulate the ULSS systems, the traditional software engineering tools face challenges as they are top-down so they deal with each domain model separately. To address the domain diversity like in the smart city systems, we propose the Framework for Agile Regulated Ultra Large Scale Software System (FARUL3S) to look at the ULSS system from bottom-up. The FARUL3S is a user-centered solution that aims at combining the complex adaptive system, the financial economics as well as the engineering systems design. Our contribution aims to regulate and constrain the ULSS systems by using architectural agreements and other rules. In this paper, we provide a detailed description of the FARUL3S steps. Our Framework generates a system Design Rule Hierarchy (DRH) so it can be used to constrain the entire system design. In the future, we will provide an illustration of the FARUL3S adoption on the management and design of different smart city services to ensure the efficiency of our solution.

Exploration of the deep sea and ocean in the marine industry has continued to gain interest in recent years. To get the detailed imaging of deep sea layers, marine vessels and robots are fitted with advanced imaging technologies. There are certain factors like water properties and impurities that affect the quality of the photographs captured by the underwater imaging devices. As sea water absorbs colors, so processing of sea imaging data becomes more challenging. Water light attenuation is a phenomenon that is caused by the absorbance and scattering factors. Certain studies showed that the existence of certain intrinsic shortcomings are attributed to the appearance of objects and ambient noise in underwater images. As a result, it is difficult in a real-time system to distinguish objects from their surroundings in these images. We measures the algorithms performance with respect to various aspects, effect of the hardware and software parts for underwater images and critical review of different underwater image enhancement algorithms. First, we describe some well-known techniques of spatial and frequency domains. Then, we list the existing quantitative measurements which are required to measure the quality of the enhanced image. Finally, the performance of various up-to-date existing methods is compared based on the outcomes of standard quantitative measurements, and factors such as requirements/suitability, and technical aspects, are included. Furthermore, a variety of image databases used for image contrast enhancement is discussed in detail. This study expands the scope for other researchers to understand the important characteristics of different underwater image contrast enhancement methods, and also provides future research directions.

Voice over IP (VoIP) services hold promise because of their offered features and low cost. Most VoIP networks depend on the Session Initiation Protocol (SIP) to handle signaling functions. The SIP is a text-based protocol that is vulnerable to many attacks. Denial of Service (DoS) and distributed denial of service (DDoS) attacks are the most harmful types of attacks, because they drain VoIP resources and render SIP service unavailable to legitimate users. In this paper, we present recently introduced approaches to detect DoS and DDoS attacks, and classify them based on various factors. We then analyze these approaches according to various characteristics, furthermore, we investigate the main strengths and weaknesses of these approaches. Finally, we provide some remarks for enhancing the surveyed approaches and highlight directions for future research to build effective detection solutions.

Many companies have transformed their telephone systems into Voice over IP (VoIP) systems. Although implementation is simple, VoIP is vulnerable to different types of attacks. The Session Initiation Protocol (SIP) is a widely used protocol for handling VoIP signaling functions. SIP is unprotected against attacks because it is a text-based protocol and lacks defense against the growing security threats. The Distributed Denial of Service (DDoS) attack is a harmful attack, because it drains resources, and prevents legitimate users from using the available services. In this paper, we formulate detection of DDoS attacks as a classification problem and propose an approach using token embedding to enhance extracted features from SIP messages. We discuss a deep learning model based on Recurrent Neural Networks (RNNs) developed to detect DDoS attacks with low and high-rate intensity. For validation, a balanced real traffic dataset was built containing three attack scenarios with different attack durations and intensities. Experiments show that the system has a high detection accuracy and low detection time. The detection accuracy was higher for low-rate attacks than that of traditional machine learning.

A new speech feature extraction technique called moving average multi directional local features (MA-MDLF) is presented in this paper. This method is based on linear regression (LR) and moving average (MA) in the time–frequency plane. Three-point LR is taken along time axis and frequency axis, and 3 points MA is taken along 45° and 135° in the time–frequency plane. The LR captures the voice onset\offset, formant contour, while the moving average captures the dynamics on time–frequency axes which can be seen as voiceprints. The MA-MDLF performance is compared to commonly used speech features in speaker recognition. The comparison is performed in a speaker recognition system (SRS) for three different conditions, namely clean speech, mobile speech, and cross channel. MA-MDLF has shown better performance than the baseline MFCC, RASTA-PLP and LPCC. In clean and mobile speech, MA-MDLF feature performs the best and also in the cross channel task MA-MDLF performed excellent. We also evaluated the MA-MDLF using three speech databases, namely KSU, LDC Babylon and TIMITdatabases, and found that MA-MDLF outperformed the other commonly used features with speech from all the three databases. The first and second databases are for Arabic speech while third is for English speech.

Numerous applications, such as material handling, manufacturing, security, and automated transportation systems, use mobile robots. Autonomous navigation remains one of the primary challenges of the mobile robot industry; many new control algorithms have been recently developed that aim to overcome this challenge. These algorithms are primarily related by their adoption of new strategies for avoiding obstacles and minimizing the travel time to a target along an optimal path. In this paper, we introduce four different navigation systems for an autonomous mobile robot (PowerBot) and compare them. The four systems are based on a fuzzy logic controller (FLC). The FLC of one system is tuned by an inexperienced human (naive), while the three other FLCs are optimized through a genetic algorithm (GA), particle swarm optimization (PSO), and a human expert. We hope the comparison answers the question of which is the best controller. In other words, “who can win?,”the naive, the GA, the PSO, or the expert, in fine tuning the membership functions of the navigation and obstacle avoidance behavior of the mobile robot? To answer this question, we used four different techniques for optimization (the naive FLC, GA, PSO, and FLC-expert) and used many criteria for comparison, whereas other research papers have dealt with two techniques at a time.

Display OmittedThe hybrid learning algorithm for FBBFNT model. A new hybrid learning algorithm is introduced to evolve the flexible beta basis function neural tree (FBBFNT) model.The Extended Genetic Programming (EGP) is used to optimize the structure of the FBBFNT.A new hybridization between Artificial Bee Colony (ABC) and Opposite-based Particle Swarm Optimization (OPSO) is proposed to optimize the parameters of FBBFNT.The proposed model is evaluated for benchmark problems drawn from time series prediction area. In this paper, a new hybrid learning algorithm is introduced to evolve the flexible beta basis function neural tree (FBBFNT). The structure is developed using the Extended Genetic Programming (EGP) and the Beta parameters and connected weights are optimized by the Hybrid Artificial Bee Colony algorithm. This hybridization is essentially based on replacing the random Artificial Bee Colony (ABC) position with the guided Opposite-based Particle Swarm Optimization (OPSO) position. Such modification can minimize the delay which might be lead by the random position, in reaching the global solution. The performance of the proposed model is evaluated for benchmark problems drawn from time series prediction area and is compared with those of related methods.

In this paper, we apply the Elman Neural Network (ENN) trained with Grey Wolf Optimizer (GWO) for time series predictions and data classification. The Grey Wolf Optimizer algorithm optimizes the network parameters. In order to evaluate the performance of the proposed method, we have carried out some experiments on two data sets: Mackey Glass, and Breast Cancer. We also give simulation examples to compare the effectiveness of the model with five known meta-heuristics methods in the literature. The results show that the GWO-ENN model produces a better generalization performance.

In this paper, a tree-based encoding method is introduced to represent the Beta basis function neural network. The proposed model called Flexible Beta Basis Function Neural Tree (FBBFNT) can be created and optimized based on the predefined Beta operator sets. A hybrid learning algorithm is used to evolving FBBFNT Model: the structure is developed using the Extended Genetic Programming (EGP) and the Beta parameters and connected weights are optimized by the Opposite-based Particle Swarm Optimization algorithm (OPSO). The performance of the proposed method is evaluated for benchmark problems drawn from control system and time series prediction area and is compared with those of related methods.

This paper proposes a hierarchical multi-dimensional differential evolution (HMDDE) algorithm, which is an automatic computational frame work for the optimization of beta basis function neural network (BBFNN) wherein the neural network architecture, weights connection, learning algorithm and its parameters are adapted according to the problem. In the HMDDE-designed neural network, the number of individuals of the population multi-dimensions is the number of beta neural networks. The population of HMDDE forms multiple beta networks with different structures at the higher level and each individual of the previous population is optimized at a lower hierarchical level to improve the performance of each individual. For the beta neural network consisting of m neurons, n individuals (different lengths) are formed in the upper level to optimize the structure of the beta neural network. In the lower level, the population within the same length is to optimize the free parameters of the beta neural network. To evaluate the comparative performance, we used benchmark problems drawn from identification system and time series prediction area. Empirical results illustrate that the HMDDE produces a better generalization performance.

Wireless sensor networks (WSN) differ from traditional wireless communication networks in several characteristics. One of these characteristics is power awareness. In order to save the overall energy of the system and to fairly balance the load among nodes, we propose a new clustering routing protocol based on coverage control which incorporates two modules: (1) a scheduling mechanism based on binary particle swarm optimisation (PSO); (2) a cluster based protocol using fuzzy C-means (FCM) algorithm. Yet, in cluster based approach, the cluster head (CH) is usually selected amongst the sensor nodes which can die quickly for this extra workload. To mitigate this problem, we introduce some energy-harvesting (EH) nodes in the network which serve as CH. Since, the EH nodes are more expensive than the sensors, we study, in this paper, how to efficiently deploy EH nodes. Simulation results show that our protocol achieves an obvious improvement on the network lifetime.

A novel learning algorithm is proposed for non linear modeling and identification by the use of the beta basis function neural network (BBFNN). The proposed method is a hierarchical particle swarm optimization (HPSO). The objective of this paper is to optimize the parameters of the beta basis function neural network (BBFNN) with high accuracy. The population of HPSO forms multiple beta neural networks with different structures at an upper hierarchical level and each particle of the previous population is optimized at a lower hierarchical level to improve the performance of each particle swarm. For the beta neural network consisting n particles are formed in the upper level to optimize the structure of the beta neural network. In the lower level, the population within the same length particle is to optimize the free parameters of the beta neural network. Experimental results on a number of benchmarks problems drawn from regression and time series prediction area demonstrate that the HPSO produces a better generalization performance.

Many methods for solving optimization problems, whether direct or indirect, rely upon gradient information and therefore may converge to a local optimum. Global optimization methods like Evolutionary algorithms, overcome this problem although these techniques are computationally expensive due to slow nature of the evolutionary process. In this work, a new concept is investigated to accelerate the particle swarm optimization. The opposition-based PSO uses the concept of opposite number to create a new population during the learning process to improve the convergence rate of generalization performance of the beta basis function neural network. The proposed algorithm uses the dichotomy research to determine the target solution. Detailed performance comparison of OPSO-BBFNN with learning algorithm on benchmarks problems drawn from regression and time series prediction area. The results show that the OPSO-BBFNN produces a better generalization performance.

This paper proposes and describes an effective utilization of the heuristic optimization. The focus of this research is on a hybrid method combining two heuristic optimization techniques; Differential evolution algorithms (DE) and particle swarm optimization (PSO), to train the beta basis function neural network (BBFNN). Denoted as PSO- DE, this hybrid technique incorporates concepts from DE and PSO and creates individuals in a new generation not only by crossover and mutation operations as found in DE but also by mechanisms of PSO. The results of various experimental studies using the Mackey time prediction have demonstrated the superiority of the hybrid PSO-DE approach over the other four search techniques in terms of solution quality and convergence rates.