rss_2.0Sciendo RSS Feed for Journal of Artificial Intelligence and Soft Computing Researchhttps://sciendo.com/journal/JAISCRhttps://www.sciendo.comhttps://sciendo-parsed.s3.eu-central-1.amazonaws.com/6472065b215d2f6c89db92d9/cover-image.jpghttps://sciendo.com/journal/JAISCR140216https://sciendo.com/article/10.2478/jaiscr-2023-0014<abstract> <title style='display:none'>Abstract</title> <p>In recent years, various models based on convolutional neural networks (CNN) have been proposed to solve the cardiac arrhythmia detection problem and achieved saturated accuracy. However, these models are often viewed as “blackbox” and lack of interpretability, which hinders the understanding of cardiologists, and ultimately hinders the clinical use of intelligent terminals. At the same time, most of these approaches are supervised learning and require label data. It is a time-consuming and expensive process to obtain label data. Furthermore, in human visual cortex, the importance of lateral connection is same as feed-forward connection. Until now, CNN based on lateral connection have not been studied thus far. Consequently, in this paper, we combines CNNs, lateral connection and autoencoder (AE) to propose the building blocks of lateral connection convolutional autoencoder neural networks (LCAN) for cardiac arrhythmia detection, which learn representations in an unsupervised manner. Concretely, the LCAN contains a convolution layer, a lateral connection layer, an AE layer, and a pooling layer. The LCAN detects salient wave features through the lateral connection layer. The AE layer and competitive learning is used to update the filters of the convolution network—an unsupervised process that ensures similar weight distribution for all adjacent filters in each convolution layer and realizes the neurons’ semantic arrangement in the LCAN. To evaluate the performances of the proposed model, we have implemented the experiments on the well-known MIT–BIH Arrhythmia Database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results show that the LCAN is not only effective, but also a useful tool for arrhythmia detection.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2023-00142023-06-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2023-0015<abstract> <title style='display:none'>Abstract</title> <p>In this paper, an intelligent approach to the Short-Term Wind Power Prediction (STWPP) problem is considered, with the use of various types of Deep Neural Networks (DNNs). The impact of the prediction time horizon length on accuracy, and the influence of temperature on prediction effectiveness have been analyzed. Three types of DNNs have been implemented and tested, including: CNN (Convolutional Neural Networks), GRU (Gated Recurrent Unit), and H-MLP (Hierarchical Multilayer Perceptron). The DNN architectures are part of the Deep Learning Prediction (DLP) framework that is applied in the Deep Learning Power Prediction System (DLPPS). The system is trained based on data that comes from a real wind farm. This is significant because the prediction results strongly depend on weather conditions in specific locations. The results obtained from the proposed system, for the real data, are presented and compared. The best result has been achieved for the GRU network. The key advantage of the system is a high effectiveness prediction using a minimal subset of parameters. The prediction of wind power in wind farms is very important as wind power capacity has shown a rapid increase, and has become a promising source of renewable energies.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2023-00152023-06-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2023-0012<abstract> <title style='display:none'>Abstract</title> <p>In recent years, many studies have attempted to use deep learning for moving object detection. Some research also combines object detection methods with traditional background modeling. However, this approach may run into some problems with parameter settings and weight imbalances. In order to solve the aforementioned problems, this paper proposes a new way to combine ViBe and Faster-RCNN for moving object detection. To be more specific, our approach is to confine the candidate boxes to only retain the area containing moving objects through traditional background modeling. Furthermore, in order to make the detection able to more accurately filter out the static object, the probability of each region proposal then being retained. In this paper, we compare four famous methods, namely GMM and ViBe for the traditional methods, and DeepBS and SFEN for the deep learning-based methods. The result of the experiment shows that the proposed method has the best overall performance score among all methods. The proposed method is also robust to the dynamic background and environmental changes and is able to separate stationary objects from moving objects. Especially the overall <italic>F</italic>-measure with the CDNET 2014 dataset (like in the dynamic background and intermittent object motion cases) was 0,8572.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2023-00122023-06-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2023-0011<abstract> <title style='display:none'>Abstract</title> <p>There are many design problems need to be optimized in various fields of engineering, and most of them belong to the NP-hard problem. The meta-heuristic algorithm is one kind of optimization method and provides an effective way to solve the NP-hard problem. Salp swarm algorithm (SSA) is a nature-inspired algorithm that mimics and mathematically models the behavior of slap swarm in nature. However, similar to most of the meta-heuristic algorithms, the traditional SSA has some shortcomings, such as entrapment in local optima. In this paper, the three main strategies are adopted to strengthen the basic SSA, including chaos theory, sine-cosine mechanism and the principle of quantum computation. Therefore, the SSA variant is proposed in this research, namely SCQ-SSA. The representative benchmark functions are employed to test the performances of the algorithms. The SCQ-SSA are compared with the seven algorithms in high-dimensional functions (1000 dimensions), seven SSA variants and six advanced variants on benchmark functions, the experiment reveals that the SCQ-SSA enhances resulting precision and alleviates local optimal problems. Besides, the SCQ-SSA is applied to resolve three classical engineering problems: tubular column design problem, tension/compression spring design problem and pressure vessel design problem. The design results indicate that these engineering problems are optimized with high accuracy and superiority by the improved SSA. The source code is available in the URL: <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://github.com/ye-zero/SCQSSA/tree/main/SCQ-SSA">https://github.com/ye-zero/SCQSSA/tree/main/SCQ-SSA</ext-link>.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2023-00112023-06-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2023-0013<abstract> <title style='display:none'>Abstract</title> <p>Recently, measuring users and community influences on social media networks play significant roles in science and engineering. To address the problems, many researchers have investigated measuring users with these influences by dealing with huge data sets. However, it is hard to enhance the performances of these studies with multiple attributes together with these influences on social networks. This paper has presented a novel model for measuring users with these influences on a social network. In this model, the suggested algorithm combines Knowledge Graph and the learning techniques based on the vote rank mechanism to reflect user interaction activities on the social network. To validate the proposed method, the proposed method has been tested through homogeneous graph with the building knowledge graph based on user interactions together with influences in real-time. Experimental results of the proposed model using six open public data show that the proposed algorithm is an effectiveness in identifying influential nodes.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2023-00132023-06-23T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0008<abstract><title style='display:none'>Abstract</title><p>The autonomous navigation of robots in unknown environments is a challenge since it needs the integration of a several subsystems to implement different functionality. It needs drawing a map of the environment, robot map localization, motion planning or path following, implementing the path in real-world, and many others; all have to be implemented simultaneously. Thus, the development of autonomous robot navigation (ARN) problem is essential for the growth of the robotics field of research. In this paper, we present a simulation of a swarm intelligence method is known as Particle Swarm Optimization (PSO) to develop an ARN system that can navigate in an unknown environment, reaching a pre-defined goal and become collision-free. The proposed system is built such that each subsystem manipulates a specific task which integrated to achieve the robot mission. PSO is used to optimize the robot path by providing several waypoints that minimize the robot traveling distance. The <italic>Gazebo</italic> simulator was used to test the response of the system under various envirvector representing a solution to the optimization problem.onmental conditions. The proposed ARN system maintained robust navigation and avoided the obstacles in different unknown environments. vector representing a solution to the optimization problem.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00082019-08-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0007<abstract><title style='display:none'>Abstract</title><p>The lack of attention during the driving task is considered as a major risk factor for fatal road accidents around the world. Despite the ever-growing trend for autonomous driving which promises to bring greater road-safety benefits, the fact is today’s vehicles still only feature partial and conditional automation, demanding frequent driver action. Moreover, the monotony of such a scenario may induce fatigue or distraction, reducing driver awareness and impairing the regain of the vehicle’s control. To address this challenge, we introduce a non-intrusive system to monitor the driver in terms of fatigue, distraction, and activity. The proposed system explores state-of-the-art sensors, as well as machine learning algorithms for data extraction and modeling. In the domain of fatigue supervision, we propose a feature set that considers the vehicle’s automation level. In terms of distraction assessment, the contributions concern (i) a holistic system that covers the full range of driver distraction types and (ii) a monitoring unit that predicts the driver activity causing the faulty behavior. By comparing the performance of Support Vector Machines against Decision Trees, conducted experiments indicated that our system can predict the driver’s state with an accuracy ranging from 89% to 93%.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00072019-08-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0006<abstract><title style='display:none'>Abstract</title><p>Deep Neural Networks (DNN) are nothing but neural networks with many hidden layers. DNNs are becoming popular in automatic speech recognition tasks which combines a good acoustic with a language model. Standard feedforward neural networks cannot handle speech data well since they do not have a way to feed information from a later layer back to an earlier layer. Thus, Recurrent Neural Networks (RNNs) have been introduced to take temporal dependencies into account. However, the shortcoming of RNNs is that long-term dependencies due to the vanishing/exploding gradient problem cannot be handled. Therefore, Long Short-Term Memory (LSTM) networks were introduced, which are a special case of RNNs, that takes long-term dependencies in a speech in addition to short-term dependencies into account. Similarily, GRU (Gated Recurrent Unit) networks are an improvement of LSTM networks also taking long-term dependencies into consideration. Thus, in this paper, we evaluate RNN, LSTM, and GRU to compare their performances on a reduced TED-LIUM speech data set. The results show that LSTM achieves the best word error rates, however, the GRU optimization is faster while achieving word error rates close to LSTM.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00062019-08-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0009<abstract><title style='display:none'>Abstract</title><p>Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopamine-modulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00092019-08-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0010<abstract><title style='display:none'>Abstract</title><p>Big data research has become an important discipline in information systems research. However, the flood of data being generated on the Internet is increasingly unstructured and non-numeric in the form of images and texts. Thus, research indicates that there is an increasing need to develop more efficient algorithms for treating mixed data in big data for effective decision making. In this paper, we apply the classical K-means algorithm to both numeric and categorical attributes in big data platforms. We first present an algorithm that handles the problem of mixed data. We then use big data platforms to implement the algorithm, demonstrating its functionalities by applying the algorithm in a detailed case study. This provides us with a solid basis for performing more targeted profiling for decision making and research using big data. Consequently, the decision makers will be able to treat mixed data, numerical and categorical data, to explain and predict phenomena in the big data ecosystem. Our research includes a detailed end-to-end case study that presents an implementation of the suggested procedure. This demonstrates its capabilities and the advantages that allow it to improve the decision-making process by targeting organizations’ business requirements to a specific cluster[s]/profiles[s] based on the enhancement outcomes.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00102019-08-30T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0002<abstract><title style='display:none'>Abstract</title><p>An intrusion detection system (IDS) is an important feature to employ in order to protect a system against network attacks. An IDS monitors the activity within a network of connected computers as to analyze the activity of intrusive patterns. In the event of an ‘attack’, the system has to respond appropriately. Different machine learning techniques have been applied in the past. These techniques fall either into the clustering or the classification category. In this paper, the classification method is used whereby a neural network ensemble method is employed to classify the different types of attacks. The neural network ensemble method consists of an autoencoder, a deep belief neural network, a deep neural network, and an extreme learning machine. The data used for the investigation is the NSL-KDD data set. In particular, the detection rate and false alarm rate among other measures (confusion matrix, classification accuracy, and AUC) of the implemented neural network ensemble are evaluated.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00022019-05-09T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0005<abstract><title style='display:none'>Abstract</title><p>The present article describes a novel phrasing model which can be used for segmenting sentences of unconstrained text into syntactically-defined phrases. This model is based on the notion of attraction and repulsion forces between adjacent words. Each of these forces is weighed appropriately by system parameters, the values of which are optimised via particle swarm optimisation. This approach is designed to be language-independent and is tested here for different languages.</p><p>The phrasing model’s performance is assessed per se, by calculating the segmentation accuracy against a golden segmentation. Operational testing also involves integrating the model to a phrase-based Machine Translation (MT) system and measuring the translation quality when the phrasing model is used to segment input text into phrases. Experiments show that the performance of this approach is comparable to other leading segmentation methods and that it exceeds that of baseline systems.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00052019-05-09T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0003<abstract><title style='display:none'>Abstract</title><p>This paper studies the global asymptotic stability and dissipativity problem for a class of neutral type stochastic Markovian Jump Static Neural Networks (NTSMJSNNs) with time-varying delays. By constructing an appropriate Lyapunov-Krasovskii Functional (LKF) with some augmented delay-dependent terms and by using integral inequalities to bound the derivative of the integral terms, some new sufficient conditions have been obtained, which ensure that the global asymptotic stability in the mean square. The results obtained in this paper are expressed in terms of Strict Linear Matrix Inequalities (LMIs), whose feasible solutions can be verified by effective MATLAB LMI control toolbox. Finally, examples and simulations are given to show the validity and advantages of the proposed results.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00032019-05-09T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0001<abstract><title style='display:none'>Abstract</title><p>Computational intelligence firmly made its way into the areas of consumer applications, banking, education, social networks, and security. Among all the applications, biometric systems play a significant role in ensuring an uncompromised and secure access to resources and facilities. This article presents a first multimodal biometric system that combines KINECT gait modality with KINECT face modality utilizing the rank level and the score level fusion. For the KINECT gait modality, a new approach is proposed based on the skeletal information processing. The gait cycle is calculated using three consecutive local minima computed for the distance between left and right ankles. The feature distance vectors are calculated for each person’s gait cycle, which allows extracting the biometric features such as the mean and the variance of the feature distance vector. For Kinect face recognition, a novel method based on HOG features has been developed. Then, K-nearest neighbors feature matching algorithm is applied as feature classification for both gait and face biometrics. Two fusion algorithms are implemented. The combination of Borda count and logistic regression approaches are used in the rank level fusion. The weighted sum method is used for score level fusion. The recognition accuracy obtained for multi-modal biometric recognition system tested on KINECT Gait and KINECT Eurocom Face datasets is 93.33% for Borda count rank level fusion, 96.67% for logistic regression rank-level fusion and 96.6% for score level fusion.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00012019-05-09T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2019-0004<abstract><title style='display:none'>Abstract</title><p>Cases where the derivative of a boundary value problem does not exist or is constantly changing, traditional derivative can easily get stuck in the local optima or does not factually represent a constantly changing solution. Hence the need for evolutionary algorithms becomes evident. However, evolutionary algorithms are compute-intensive since they scan the entire solution space for an optimal solution. Larger populations and smaller step sizes allow for improved quality solution but results in an increase in the complexity of the optimization process. In this research a population-distributed implementation for differential evolution algorithm is presented for solving systems of 2<italic>^nd</italic>-order, 2-point boundary value problems (BVPs). In this technique, the system is formulated as an optimization problem by the direct minimization of the overall individual residual error subject to the given constraint boundary conditions and is then solved using differential evolution in the sense that each of the derivatives is replaced by an appropriate difference quotient approximation. Four benchmark BVPs are solved using the proposed parallel framework for differential evolution to observe the speedup in the execution time. Meanwhile, the statistical analysis is provided to discover the effect of parametric changes such as an increase in population individuals and nodes representing features on the quality and behavior of the solutions found by differential evolution. The numerical results demonstrate that the algorithm is quite accurate and efficient for solving 2<italic>^nd</italic>-order, 2-point BVPs.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2019-00042019-05-09T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2018-0030<abstract><title style='display:none'>Abstract</title><p>Collaborative Clustering is a data mining task the aim of which is to use several clustering algorithms to analyze different aspects of the same data. The aim of collaborative clustering is to reveal the common underlying structure of data spread across multiple data sites by applying clustering techniques. The idea of collaborative clustering is that each collaborator shares some information about the segmentation (structure) of its local data and improve its own clustering with the information provided by the other learners. This paper analyses the impact of the quality and the diversity of the potential learners to the quality of the collaboration for topological collaborative clustering algorithms based on the learning of a Self-Organizing Map (SOM). Experimental analysis on real data-sets showed that the diversity between learners impact the quality of the collaboration. We also showed that some internal indexes of quality are a good estimator of the increase of quality due to the collaboration.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2018-00302018-12-31T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2018-0029<abstract><title style='display:none'>Abstract</title><p>The present paper¹ aims to propose a new type of information-theoretic method to maximize mutual information between inputs and outputs. The importance of mutual information in neural networks is well known, but the actual implementation of mutual information maximization has been quite difficult to undertake. In addition, mutual information has not extensively been used in neural networks, meaning that its applicability is very limited. To overcome the shortcoming of mutual information maximization, we present it here in a very simplified manner by supposing that mutual information is already maximized before learning, or at least at the beginning of learning. The method was applied to three data sets (crab data set, wholesale data set, and human resources data set) and examined in terms of generalization performance and connection weights. The results showed that by disentangling connection weights, maximizing mutual information made it possible to explicitly interpret the relations between inputs and outputs.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2018-00292018-12-31T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2018-0026<abstract><title style='display:none'>Abstract</title><p>Evolutionary Multi-agent System introduced by late Krzysztof Cetnarowicz and developed further at the AGH University of Science and Technology became a reliable optimization system, both proven experimentally and theoretically. This paper follows a work of Byrski further testing and analyzing the efficacy of this metaheuristic based on popular, high-dimensional benchmark functions. The contents of this paper will be useful for anybody willing to apply this computing algorithm to continuous and not only optimization.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2018-00262018-12-31T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2018-0027<abstract><title style='display:none'>Abstract</title><p>Advanced and accurate modelling of a Flapping Wing Micro Air Vehicle (FW MAV) and its control is one of the recent research topics related to the field of autonomous MAVs. Some desiring features of the FW MAV are quick flight, vertical take-off and landing, hovering, and fast turn, and enhanced manoeuvrability contrasted with similar-sized fixed and rotary wing MAVs. Inspired by the FW MAV’s advanced features, a four-wing Nature-inspired (NI) FW MAV is modelled and controlled in this work. The Fuzzy C-Means (FCM) clustering algorithm is utilized to construct the data-driven NIFW MAV model. Being model free, it does not depend on the system dynamics and can incorporate various uncertainties like sensor error, wind gust etc. Furthermore, a Takagi-Sugeno (T-S) fuzzy structure based adaptive fuzzy controller is proposed. The proposed adaptive controller can tune its antecedent and consequent parameters using FCM clustering technique. This controller is employed to control the altitude of the NIFW MAV, and compared with a standalone Proportional Integral Derivative (PID) controller, and a Sliding Mode Control (SMC) theory based advanced controller. Parameter adaptation of the proposed controller helps to outperform it static PID counterpart. Performance of our controller is also comparable with its advanced and complex counterpart namely SMC-Fuzzy controller.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2018-00272018-12-31T00:00:00.000+00:00https://sciendo.com/article/10.2478/jaiscr-2018-0028<abstract><title style='display:none'>Abstract</title><p>A topological property or index of a network is a numeric number which characterises the whole structure of the underlying network. It is used to predict the certain changes in the bio, chemical and physical activities of the networks. The 4-layered probabilistic neural networks are more general than the 3-layered probabilistic neural networks. Javaid and Cao [Neural Comput. and Applic., DOI 10.1007/s00521-017-2972-1] and Liu et al. [Journal of Artificial Intelligence and Soft Computing Research, 8(2018), 225-266] studied the certain degree and distance based topological indices (TI’s) of the 3-layered probabilistic neural networks. In this paper, we extend this study to the 4-layered probabilistic neural networks and compute the certain degree-based TI’s. In the end, a comparison between all the computed indices is included and it is also proved that the TI’s of the 4-layered probabilistic neural networks are better being strictly greater than the 3-layered probabilistic neural networks.</p></abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/jaiscr-2018-00282018-12-31T00:00:00.000+00:00en-us-1