Search

Epileptic seizure prediction using multi-channel electroencephalogram (EEG) signals is very important in clinical therapy. A large number of channels lead to high computational complexity with low model performance. To improve the performance and reduce the overfitting that arises due to the use of unrelevant channels, the present paper proposed a channel selection method to study the brain region activation related to epileptic seizure. Our method is bio-inspired and cognitive since it integrates the novel binary many-objective particle swarm optimization with a ConvLSTM model. The proposed method has two advantages. First, it performed a new initialization strategy based on channel weighting with mutual information, thereby promoting the fast convergence of the optimization algorithm. Second, it captures spatio-temporal information from raw EEG segments thanks to the ConvLSTM model. The selected sub-channels are optimized as many-objective optimization problem that includes maximizing F1-score, sensitivity, specificity, and minimizing the ratio rate of selected channels. Our results have shown a performance of up to 97.94 % with only one EEG channel. Interestingly, when using all the EEG channels available, lower performance was achieved compared to the case when EEG channels were selected by our approach. This study revealed that it is possible to predict epileptic seizures using a few channels, which provides evidence for the future development of portable EEG seizure prediction devices. [ABSTRACT FROM AUTHOR]

Epilepsy affect almost 1% of the worldwide population. An early diagnosis of seizure types is a crucial patient-dependent step for the treatment selection process. The selection of the proper treatment relies on the correct identification of the seizure type. As such, identifying the seizure type has the biggest immediate influence on therapy than the seizure detection, reducing the neurologist's efforts when reading and detecting seizures in EEG recordings. Most of the existing seizure detection and classification methods are conceptualized following the patient-dependent schema thus fail to perform well with unknown cases. Our work focuses on patient-independent schema for seizure type classification and pays more attention to the explainability of the underlying attention mechanism of our method. Using a channel-wise attention mechanism, a quantification of the EEG channels contribution is enabled. Therefore, results become more interpretable and a visualization of brain lobes contribution by seizure types is allowed. We evaluate our model for seizure detection and type classification on CHB-MIT and the recently released TUH EEG Seizure, respectively. Our model is able to classify 8 seizure types with an accuracy of 98.41%, directly from raw EEG data without any preprocessing. A case study showed a high correlation between the neurological baselines and the interpretable results of our model. [ABSTRACT FROM AUTHOR]

Home health services arise from the need for hospitals to care for patients and/or dependent persons who, due to special conditions, require hospitalisation and/or care at home. The organisation of this service impacts the quality and cost of health services, which implies the programming of medical and social staff and the design of their daily routes. This literature review presents a description of the problem and a taxonomy of its characteristics and restrictions. It summarises the state-of-the-art decision-making solutions to deal with the home health care routing and scheduling problem and studies related objectives and constraints. [ABSTRACT FROM AUTHOR]

Particle Swarm Optimization (PSO) is a population-based metaheuristic belonging to the class of Swarm Intelligence (SI) algorithms. Nowadays, its effectiveness on many hard problems is no longer to be proven. Nevertheless, it is known to be strongly sensitive on the choice of its settings and weak for local search. In this paper, we propose a new algorithm, called QUAntum Particle Swarm Optimization (QUAPSO) based on quantum superposition to set the velocity PSO parameters, simplifying the settings of the algorithm. Another improvement, inspired by Kangaroo Algorithm (KA), was added to PSO in order to optimize its efficiency in local search. QUAPSO was compared with a set of six well-known algorithms from the literature (two parameter sets of classical PSO, KA, Differential Evolution, Simulated Annealing Particle Swarm Optimization, Bat Algorithm and Simulated Annealing Gaussian Bat Algorithm). The experimental results show that QUAPSO outperforms the competing algorithms on a set of 30 test functions. [ABSTRACT FROM AUTHOR]

The proposed method has obvious advantages in terms of the retrieval time and retrieval effect and provides new ideas for multimedia image and video retrieval. The prevalence and global reach of social multimedia have led to people finding unlawful and unethical ways to use socially connected virtual groups. Food image classification and image retrieval have been proposed by Drs. [Extracted from the article]

Today, advances in 3D modeling make it possible to identically reproduce objects, animals, humans and even entire scenes. The broad applications concern video games, virtual reality or augmented reality and cinema, for example. In this article, we propose a new method to build a 3D scene directly from several complementary photographs. The positions of the objects for which we already have a 3D model will be determined by triangulation, thanks to the information extracted from the photographs, such as the outline of the objects on the images. Each pixel of the images is converted into a value that gives its distance to the nearest outline. The 3D model of the objects is then projected on the converted images, and the triangulation is done using a cost function that gives the distance of each projection of the objects to their respective outlines. A projection is considered perfect when its distance to its outlines is null, which means that the cost function gives a score of zero as well. We propose to solve this optimization problem by means of two algorithms, namely Simulated Annealing (SA) and quantum particle swarm optimization (QUAPSO). [ABSTRACT FROM AUTHOR]

Anxiety affects human capabilities and behavior as much as it affects productivity and quality of life. It is considered to be the main cause of depression and suicide. Anxious states are detectable by specialists by virtue of their acquired cognition and skills. There is a need for non-invasive reliable techniques that performs the complex task of anxiety detection. In our study, we investigate the impact of different parameters, notably: trial duration, feature type, feature combination and anxiety levels number. The system is evaluated using our own database containing recorded Electroencephalogram (EEG) signals from 23 participants during anxiety elicitation by means of face-to-face psychological stimuli. EEG signals were captured with an Emotiv Epoc headset as a cost-efficient wireless wearable equipment. Two labeling methods are used and results are presented accordingly. Our findings showed that anxiety is well elicited in 1 s. For Self Assessment Manikan SAM-based detection, Stacked Sparse Autoencoder (SSAE) with different type of features achieves 83.50% and 74.60% for 2 and 4 anxiety levels detection, respectively. Results are improved using the Hamilton-based method. We obtained a rate of 86.7% for 4 levels detection using SSAE. The presented results prove the benefits of the use of a low-cost EEG headset instead of medical non-wireless devices and create a starting point for new researches in the field of anxiety detection. [ABSTRACT FROM AUTHOR]

Optimal sizing of analog circuits is a hard and time-consuming challenge. Nowadays, analog designers are more than ever interested in developing solutions for automating such a task. In order to overcome well-known drawbacks of the conventional equation-based and simulation-based sizing techniques, analog designers are being attracted by the so-called metamodeling techniques and recently have used them for establishing accurate models of circuits' performances. Metamodels have been associated to optimization routines to maximize circuits' performances. In this work we deal with the newly proposed efficient global optimization (EGO) algorithm that intrinsically offers both the metamodel generation and the optimization routine. Furthermore, it performs the requested task by using a relatively very small number of performance evaluations. Firstly, we focus on the convergence rates of the EGO technique via twenty benchmark test problems. Then, we use EGO for the optimal design of a couple of analog CMOS circuits. Comparison between EGO performances and those obtained using two surrogate-assisted metaheuristics is provided to show potentialities of the proposed approach. Finally, The case of muti-objective problems is also considered. The multi-objective efficient global optimization algorithm is used for generating Pareto fronts of conflicting perormances of two analog circuits. Obtained results are compared to those of the conventional in-loop optimization technique. [ABSTRACT FROM AUTHOR]

The paper introduces a new design control strategy for finite time stabilization of uncertain discrete systems. The proposed control method uses the First Order Sliding Mode Control (FOSMC), the Linear Quadratic Regulator (LQR) and Genetic Algorithms (GA). The key idea of combining two control strategies lies in the fact that a robust controller tackles the uncertainties when the optimal controller performances are unaffected. Firstly, as the performances of the Sliding Mode Control (SMC) greatly depends on the choice of the sliding surface, a novel method based on the resolution of a Sylvester equation is proposed. Secondly, to ensure the robustness in the whole space, the Integral Sliding Mode Control (ISMC) is combined with the above LQR method. Rigorous stability analysis for the closed-loop system is given and proves that the system states are always bounded even the unknown disturbances. In order to handle the problem accompanying the LQR synthesis as well as the gain of the robust compensator, a multi-objective optimization problem considering a set of competing objectives is solved using GA. For that, a novel dynamically aggregated objective function is proposed. A set of non-dominated optimal solutions are provided to the control engineer and then may select the most adequate solution among the resulting optimal Pareto set. The novel method has successfully solved the robust stabilization of two known benchmarks and the different results asserts not merely the efficiency as well as the quality of the designed controller but also its supremacy compared to some existing ones. [ABSTRACT FROM AUTHOR]

An efficient covering of the search space is an important issue when dealing with metaheuristics. Sensitivity analysis methods aim at evaluating the influence of each variable of a problem on a model (i.e. objective function) response. Such methods provide knowledge on the function behavior and would be suitable for guiding metaheuristics. To evaluate correctly the dimensions influences, usual sensitivity analysis methods need a lot of evaluations of the objective function or are constrained with an experimental design. In this paper, we propose a new method, with a low computational cost, which can be used into metaheuristics to improve their search process. This method is based on two global sensitivity analysis methods: the linear correlation coefficient technique and Morris’ method. We propose to transform the global study of a non linear model into a local study of quasi-linear sub-parts of the model, in order to evaluate the global influence of each input variable on the model. This sensitivity analysis method will use evaluations of the objective function done by the metaheuristic to compute a weight of each variable. Then, the metaheuristic will generate new solutions choosing dimensions to offset, according to these weights. The tests done on usual benchmark functions of sensitivity analysis and continuous optimization (CEC 2013) reveal two issues. Firstly, our sensitivity analysis method provides good results, it correctly ranks each dimension’s influence. Secondly, integrating a sensitivity analysis method into a metaheuristic (here, Differential Evolution and ABC with modification rate) improves its results. [ABSTRACT FROM AUTHOR]

The emergence of high-dimensional data requires the design of new optimization methods. Indeed, conventional optimization methods require improvements, hybridization, or parameter tuning in order to operate in spaces of high dimensions. In this paper, we present a new adaptive variant of a pattern search algorithm to solve global optimization problems exhibiting such a character. The proposed method has no parameters visible to the user and the default settings, determined by almost no a priori experimentation, are highly robust on the tested datasets. The algorithm is evaluated and compared with 11 state-of-the-art methods on 20 benchmark functions of 1000 dimensions from the CEC'2010 competition. The results show that this approach obtains good performances compared to the other methods tested. [ABSTRACT FROM AUTHOR]

In the recent years, there has been a growing interest in wireless sensor networks ( WSN). Network's lifetime depends on energy efficiency and load balancing where connectivity is a very important factor. However, such connectivity can be lost due to the failure of some sensor nodes which creates disruptions to the network operations, lead to a reconfiguration of the network by generating energy losses, or in another case, the network mission fails. Energy conservation is a very important problem in WSN. In this paper, we propose a new solution for the connectivity problem when failure nodes are considered. The replacement of failed nodes is done in two phases: the first one is the search of redundant nodes using the clusterheads; the second phase is a restoration of connectivity. Performance evaluation of the proposed replacement approach shows that the results are globally satisfactory. [ABSTRACT FROM AUTHOR]

Model-driven engineering (MDE) and search-based software engineering (SBSE) are both relevant approaches to software engineering. MDE aims to raise the level of abstraction in order to cope with the complexity of software systems, while SBSE involves the application of metaheuristic search techniques to complex software engineering problems, reformulating engineering tasks as optimization problems. The purpose of this paper is to survey the relatively recent research activity lying at the interface between these two fields, an area that has come to be known as search-based model-driven engineering. We begin with an introduction to MDE, the concepts of models, of metamodels and of model transformations. We also give a brief introduction to SBSE and metaheuristics. Then, we survey the current research work centered around the combination of search-based techniques and MDE. The literature survey is accompanied by the presentation of references for further details. [ABSTRACT FROM AUTHOR]

In this paper, a novel method for the digital two-Degrees-Of-Freedom (2DOF) controller design, called canonical RST structure, is proposed and successfully implemented based on a Multi-Objective Particle Swarm Optimization (MOPSO) approach. This is a polynomial control structure allowing independently the regulation and the tracking of discrete-time systems. An application to the variable speed control of an electrical DC Drive is investigated. The RST design and tuning problem is formulated as a multi-objective optimization problem. The proposed MOPSO algorithm which is based on the Pareto dominance is used to identify the non-dominated solutions. This approach used the leader selection strategy that is called a geographically-based system. In addition, the adaptive grid method is used to produce well-distributed Pareto fronts in the multi-objective formalism. The well known NSGA-II and the proposed MOPSO algorithms are evaluated and compared with each other in terms of several performance metrics in order to show the superiority and the effectiveness of the proposed method. Simulation results demonstrate the advantages of the MOPSO-tuned RST control structure in terms of performance and robustness. [ABSTRACT FROM AUTHOR]

In this paper, we propose a grayscale image segmentation method based on a multiobjective optimization approach that optimizes two complementary criteria (region and edge based). The region-based fitness used is the improved spatial fuzzy c-means clustering measure that is shown performing better than the standard fuzzy c-means (FCM) measure. The edge-based fitness used is based on the contour statistics and the number of connected components in the image segmentation result. The optimization algorithm used is the multiobjective particle swarm optimization (MOPSO), which is well suited to handle continuous variables problems, the case of FCM clustering. In our case, each particle of the swarm codes the centers of clusters. The result of the multiobjective optimization technique is a set of Pareto-optimal solutions, where each solution represents a segmentation result. Instead of selecting one solution from the Pareto front, we propose a method that combines all solutions to get a better segmentation. The combination method takes place in two steps. The first step is the detection of high-confidence points by exploiting the similarity between the results and the membership degrees. The second step is the classification of the remaining points by using the high-confidence extracted points. The proposed method was evaluated on three types of images: synthetic images, simulated MRI brain images and real-world MRI brain images. This method was compared to the most widely used FCM-based algorithms of the literature. The results demonstrate the effectiveness of the proposed technique. [ABSTRACT FROM AUTHOR]

Particle swarm optimization is an optimization method based on a simulated social behavior displayed by artificial particles in a swarm, inspired from bird flocks and fish schools. An underlying component that influences the exchange of information between particles in a swarm, is its topological structure. Therefore, this property has a great influence on the comportment of the optimization method. In this study, we propose DCluster: a dynamic topology, based on a combination of two well-known topologies viz. Four- cluster and Fitness. The proposed topology is analyzed, and compared to six other topologies used in the standard PSO algorithm using a set of benchmark test functions and several well-known constrained and unconstrained engineering design problems. Our comparisons demonstrate that DCluster outperforms the other tested topologies and leads to satisfactory performance while avoiding the problem of premature convergence. [ABSTRACT FROM AUTHOR]