Computational Intelligence Methods Research Articles

Standalone Smart Irrigation System: An Analysis of Reliability Incorporating BPNN Technique under Various Failures

Observing the huge requirements of water and energy for traditional irrigation and contracting resources, the utility of a smart irrigation system has become necessary. A system that is capable of saving water depends on renewable energy resources for power requirements and runs automatically. Water-saving automatic irrigation systems powered by renewable energy could be a solution to India's rising demand for energy and water. In the current paper, the author has proposed an analysis of a standalone smart irrigation system for its reliability and functional behaviour under various operational events of failures and repairs. The authors have implemented an intelligent computational method because of the increased degradation in system function due to the complex structure of the proposed irrigation system. The system's mathematical formulation is stated in terms of neural networks, and a back propagation neural network technique is applied for fast and comparatively better outcomes. The author has determined state probabilities and other reliability parameters by means of neural networks in the proposed smart irrigation system. To improve the accuracy and consistency of reliability parameters, a Feed Forward Back Propagation Neural Network (FFBPNN) is applied. FFBPNN's learning mechanism can optimize the values of parameters by modifying neural weights. The MATLAB codes are used by the authors to demonstrate the numerical examples, and iterations are repeated until the precision in error tends to 0.0001. The sensitivity and cost of the system are also analyzed, which can help in managing the real-time operations of the system.

A novel intelligent cognitive computing-based APT malware detection for Endpoint systems

Detecting and warning Advanced Persistent Threat (APT) malware in Endpoint is essential because the current trend of APT attacker groups is to find ways to spread malware to users and then escalate privileges in the system. In this study, to improve the ability to detect APT malware on Endpoint machines, we propose a novel intelligent cognitive calculation method based on a model combining graph embeddings and Attention using processes generated by executable files. The proposed intelligent cognitive computation method performs 3 main tasks: i) extracting behaviors of processes; ii) aggregating the malware behaviors based on the processes; iii) detecting APT malware based on behavior analysis. To carry out the task (i), we propose to use several data mining techniques: extracting processes from Event IDs in the operating system kernel; extracting abnormal behaviors of processes. For task (ii), a graph embedding (GE) model based on the Graph Convolutional Networks (GCN) network is proposed to be used. For task (iii), based on the results of task (ii), the paper proposes to use a combination of the Convolutional Neural Network (CNN) network and Attention network (called CNN-Attention). The novelty and originality of this study is an intelligent cognitive computation method based on the use, combination, and synchronization of many different data mining techniques to compute, extract, and represent relationships and correlations among APT malware behaviors from processes. Based on this new intelligent cognitive computation method, many meaningful anomalous features and behaviors of APT malware have been synthesized and extracted. The proposals related to data mining methods to extract malware’s features and the list of malware’s behaviors provided in this paper are new information that has not been published in previous studies. In the experimental section, to demonstrate the effectiveness of the proposed method in detecting APT malware, the study has compared and evaluated it with other approaches. Experimental results in the paper have shown the outstanding efficiency of the proposed method when ensuring all metrics from 96.6% or more (that are 2% to 6% higher than other approaches). Experimental results in the paper have proven that our proposed method not only has scientifically significant but also has practical meaning because the method has helped to improve the efficiency of analyzing and detecting APT malware on Endpoint devices. In addition, this research result also has opened up a new approach for the task of detecting other anomalies on the Endpoint such as malware, unauthorized intrusion, insider, etc.

A Hybrid Computational Intelligence Method of Newton's Method and Genetic Algorithm for Solving Compatible Nonlinear Equations

Abstract In order to solve the system of compatible nonlinear equations, the author proposes a hybrid computational intelligence method of Newton's method and genetic algorithm. First, the Quasi-Newton Methods (QN) method is given. Aiming at the local convergence of the algorithm, it is easy to cause the solution to fail. By embedding the QN operator in the Genetic Algorithm (GA) and defining the appropriate fitness, thus, a hybrid computational intelligence algorithm of CNLE is obtained that combines the advantages of GA and QN method, which has both faster convergence and higher probability of solving. Experimental results show that: The value of the selection probability pn of the QN operator also directly affects the solution efficiency. Generally speaking, for strong nonlinear CNLE composed of multimodal functions, pn can be larger; For weakly nonlinear CNLE composed of functions with fewer extreme points and stronger monotonicity, pn can be smaller. It is demonstrated that the computational results show that this method significantly outperforms the GA and QN methods.

Survey Paper Artificial and Computational Intelligence in the Internet of Things and Wireless Sensor Network

In this modern age, Internet of Things (IoT) and Wireless Sensor Network (WSN) as its derivatives have become one of the most popular and important technological advancements. In IoT, all things and services in the real world are digitalized and it continues to grow exponentially every year. This growth in number of IoT device in the end has created a tremendous amount of data and new data services such as big data systems. These new technologies can be managed to produce additional value to the existing business model. It also can provide a forecasting service and is capable to produce decision-making support using computational intelligence methods. In this survey paper, we provide detailed research activities concerning Computational Intelligence methods application in IoT WSN. To build a good understanding, in this paper we also present various challenges and issues for Computational Intelligence in IoT WSN. In the last presentation, we discuss the future direction of Computational Intelligence applications in IoT WSN such as Self-Organizing Network (dynamic network) concept.

Assessment of the voltage stability index of electric networks supplying charging stations using a multilayer perceptron

Ensuring power system voltage stability is one of the key challenges in power system planning and operation. At the moment, as a result of a number of technological incidents in the form of a violation of the stability of the voltage of the power system, multilayer perceptrons were tested on the territory of various countries.PURPOSE. Development of an intelligent approach to assessing the Load Stability Index (LSI) in the power system using computational intelligence methods (neural networks).METHODS. In the course of these studies, a method for estimating the ISI was used, which is used to monitor the stability of voltage in the power system using the "Smart Park" calculation method.RESULTS. The results of providing the development stage are obtained, which substantiate the possibility of using the Multilayer Perceptron (MLP) for estimating the IEL with a high degree of accuracy.CONCLUSION. In the course of these studies, the authors of the article put forward the following conclusions: an approach based on a multilayer perceptron (MPP) neural network with feed-forward is presented; an assessment of the ISI was carried out on the example of a power system using the calculation method "Smart Park"; the presented neural network approach does not depend on the open-circuit voltage on a particular load bus; the presence of indicators of active power, reactive power and voltage on the load bus is sufficient to assess the IPL; The MSP approach allows for an accurate assessment of the ISI even when the topology and operating conditions change. The obtained indicators can be applied in changing the methodology for assessing the stability of voltage in electrical systems and complexes and calculating their operating modes.

Single_cell_GRN: gene regulatory network identification based on supervised learning method and Single-cell RNA-seq data

Single-cell RNA-seq overcomes the shortcomings of conventional transcriptome sequencing technology and could provide a powerful tool for distinguishing the transcriptome characteristics of various cell types in biological tissues, and comprehensively revealing the heterogeneity of gene expression between cells. Many Intelligent Computing methods have been presented to infer gene regulatory network (GRN) with single-cell RNA-seq data. In this paper, we investigate the performances of seven classifiers including support vector machine (SVM), random forest (RF), Naive Bayesian (NB), GBDT, logical regression (LR), decision tree (DT) and K-Nearest Neighbor (KNN) for solving the binary classification problems of GRN inference with single-cell RNA-seq data (Single_cell_GRN). In SVM, three different kernel functions (linear, polynomial and radial basis function) are utilized, respectively. Three real single-cell RNA-seq datasets from mouse and human are utilized. The experiment results prove that in most cases supervised learning methods (SVM, RF, NB, GBDT, LR, DT and KNN) perform better than unsupervised learning method (GENIE3) in terms of AUC. SVM, RF and KNN have the better performances than other four classifiers. In SVM, linear and polynomial kernels are more fit to model single-cell RNA-seq data.

Neuroinformatics Insights towards Multiple Neurosyphilis Complications

Treponema pallidum subspecies pallidum causes syphilis, a sexually transmitted disease that infects more than 2.1 million pregnant women every year. Due to its maximum death rates and augmented risk of human immunodeficiency virus (HIV) infection, the disease is still a matter of debate in many low- and high-income countries. The infection has three stages that lead to several complications if left untreated and can lead to many tertiary complications in the brain, eyes, ears, heart, and pregnancy. Neurosyphilis is also known as the clinical result of infection of the central nervous system by Treponema pallidum subspecies pallidum. It can evolve at any time and from any stage of syphilis exposure. This review briefly explains the severe and multiple neurosyphilitic complications and recently identified cases related to neurosyphilis. We also explained computational neuroscience, neuroinformatics, and in silico models and techniques based on artificial intelligence and other computational and mathematical methods. These techniques have already been applied to several neurological and psychological brain complications and can be applied to neurosyphilis to better understand the persistence of the disease related to the brain that causes neurosyphilis.

LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease

Plant diseases play a significant role in agricultural production, in which early detection of plant diseases is deemed an essential task. Current computational intelligence and computer vision methods have been promising to improve disease diagnosis. Convolutional Neural Networks (CNN) models are capable of detecting plant diseases in an agricultural field and plantation leaf images. MobileNetV2 refers to an appropriate CNN model for mobile devices with subordinate parameters and model file sizes. However, the effectiveness of MobileNetV2 requires improvement to capture more critical features. Xception refers to the extension of InceptionV3 with fewer and excellent parameters in extracting features. This research suggests an ensemble of MobileNetV2 and Xception by concatenating the extracted features to improve plant disease detection performance. This study indicated that MobileNetV2, Xception, and ensemble model achieved 97.32%, 98.30%, and 99.10% accuracy when considering the entire Plant Village dataset. Particularly, MobileNetV2 and Xception models' accuracy improved by 1.8% and 0.8%, respectively. In addition, our model captures 99.52% of all metric scores in the user-defined dataset. Our model indicated better performance than the seven state-of-the-art CNN models, both individually and in ensemble design. It can be integrated with mobile devices, providing fewer parameters and model file size than an ensemble of MobileNetV2 with InceptionResnetV2, VGG19, and VGG16.

Intelligent Computing Methods for Contextual Driving in Smart Engineering Model Systems

An engineering model system (EMS) is a complex purposeful structure of representation and description type content that is developed during development and application; in other words, it represents the lifecycle of an industrial product. The essential improvements for systems operated that are autonomous, situation controlled, and include cyber physical features of products dramatically changed requirements relative to EMS. Engineering modeling platforms (EMPs) experienced major improvements to cope with new requirements by smart products. These improvements were related to system level representation, autonomous active model features, situation level reaction to changed contexts, system and physical level virtual execution, and the support of situation-level human intervention. The lifecycle support of smart product engineering requires EMS, which behaves as a digital twin of a physically existing products and has an active connection with its contextual world, particularly with cyber units of the cyber physical system that it represents. The work in this paper aimed to develop new methods that can be implemented in EMS under developments in EMP. This is a new area of research that is motivated and at the same time enforced by moving engineering activities into highly integrated and automated complex model spaces. This paper focuses on context driving and the autonomous features of EMS as well as utilization-organized intellectual-property-powered intelligent computing relative to the definition and application of contextually connected object parameters in EMS. It introduces several latest results by the authors as a contribution for EMS to cope with the new requirements. These contributions include a new scenario called the lifecycle representation of contexts (LRC) to enhance integration in EMS, handling contexts in contextually connected autonomous unit (CCAU), organizing the intelligent content of EMS in proposed level-sublevel structure of LRC, and examining findings about situation-level cooperation between human and autonomous process.

Extreme learning machine computational method of modeling energy gap of doped zinc selenide nano-material semiconductor

Zinc selenide (ZnSe) semiconductor belongs to a class of wide energy gap material with low visible region optical absorption, high optical coefficient (nonlinear) and fascinating optoelectronic as well as photocatalytic features which foster and strengthen its applications in resisting thermal shock, photoelectric fields (which include dielectric mirrors, shot wavelength lasers and light emitting diode), buffer layer of solar cell and many photocatalytic environmental cleanliness applications. Nanostructured ZnSe semiconductors occupy a special place in application domain due to the characteristic features attached to the crystallite size of the material which include high fluorescence quantum yields, solvent dispersibility and adjustable emission color among others. Effective utilization of nanostructured ZnSe semiconductor involves tuning of its energy gap through doping mechanisms which is accompanied with distortion in the parent lattice structure. In this contribution, extreme learning machine (ELM) computational intelligent method is proposed for predicting the band gap energy of doped ZnSe nanostructured semiconductor using the material crystallite size and lattice parameter as descriptors to the models. The developed ELM based model using sine (Sine), sigmoid (Sig) and transig (Trang) activation functions were compared with the existing SVR-GA and SPR models in the literature using various performance metrics. The developed Sine-ELM model shows superior performance over Sig-ELM, Trang-ELM, SVR-GA (2021) and SPR (2021) models with performance improvement of 12.74%, 64.89%, 68.87% and 75.62% using mean squared error (MSE) metric for testing data samples. The superiority of the model developed was further justified through validation with external set of data. The precision and superiority of the ELM based models developed would eventually ease quick characterization and tuning of energy gap of ZnSe nanostructured semiconductors for various applications.

Target-DBPPred: An intelligent model for prediction of DNA-binding proteins using discrete wavelet transform based compression and light eXtreme gradient boosting

DNA-protein interaction is a critical biological process that performs influential activities, including DNA transcription and recombination. DBPs (DNA-binding proteins) are closely associated with different kinds of human diseases (asthma, cancer, and AIDS), while some of the DBPs are used in the production of antibiotics, steroids, and anti-inflammatories. Several methods have been reported for the prediction of DBPs. However, a more intelligent method is still highly desirable for the accurate prediction of DBPs. This study presents an intelligent computational method, Target-DBPPred, to improve DBPs prediction. Important features from primary protein sequences are investigated via a novel feature descriptor, called EDF-PSSM-DWT (Evolutionary difference formula position-specific scoring matrix-discrete wavelet transform) and several other multi-evolutionary methods, including F-PSSM (Filtered position-specific scoring matrix), EDF-PSSM (Evolutionary difference formula position-specific scoring matrix), PSSM-DPC (Position-specific scoring matrix-dipeptide composition), and Lead-BiPSSM (Lead-bigram-position specific scoring matrix) to encapsulate diverse multivariate features. The best feature set from the features of each descriptor is selected using sequential forward selection (SFS). Further, four models are trained using Adaboost, XGB (eXtreme gradient boosting), ERT (extremely randomized trees), and LiXGB (Light eXtreme gradient boosting) classifiers. LiXGB, with the best feature set of EDF-PSSM-DWT, has attained 6.69% and 15.07% higher performance in terms of accuracies using training and testing datasets, respectively. The obtained results verify the improved performance of our proposed predictor over the existing predictors.

Adaptive Differential Evolution Algorithm with Simulated Annealing for Security of IoT Ecosystems

With the wide application of the Internet of Things (IoT) in real world, the impact of the security on its development is becoming incrementally important. Recently, many advanced technologies, such as artificial intelligence (AI), computational intelligence (CI), and deep learning method, have been applied in different security applications. In intrusion detection system (IDS) of IoT, this paper developed an adaptive differential evolution based on simulated annealing algorithm (ASADE) to deal with the feature selection problems. The mutation, crossover, and selection processes of the self-adaptive DE algorithm are modified to avoid trapping in the local optimal solution. In the mutation process, the mutation factor is changed based on the hyperbolic tangent function curve. A linear function with generation is incorporated into the crossover operation to control the crossover factor. In the selection process, this paper adopts the Metropolis criterion of the SA algorithm to accept poor solution as optimal solution. To test the performance of the proposed algorithm, numerical experiments were performed on 29 benchmark functions from the CEC2017 and six typical benchmark functions. The experimental results indicate that the proposed algorithm is superior to the other four algorithms.

Computational Intelligence Methods for Smart Connectivity in IoT

Computational Intelligence Methods for Smart Connectivity in IoT

Study of the Angular Positioning of a Rotating Object Based on Some Computational Intelligence Methods

The paper presents the result of a study that can be included in the broader field of research aimed at increasing the performance of automatic motion control systems. The main contribution of the article is the comparative study of three control methods from the domain of computational intelligence—state feedback fuzzy control, neural predictive control, and neural model reference control—and three linear control methods—error feedback control, digital control, and state feedback control, in the case of positioning a rotating object around a central axis. The developed control structures were modeled and simulated using MATLAB/Simulink. The paper presents the chosen control structures; how to dimension them; the parameters of the linear, fuzzy, and neural regulators; the training parameters of the neural networks; and the characteristics of the variables of the control systems in the transient regime and the steady-state regime. Transient characteristics obtained for the six control structures are compared from the point of view of their control efficiency criteria. The differences in performance criteria between the control methods studied are small. All these studied methods make the regulated system to be carried on various state trajectories, short response times are obtained with aperiodic and asymptotic behavior, and the differences between the values of the efficiency indicators are small.

Pharmacogenomics: Relevance and opportunities for clinical pharmacology

Pharmacogenomics: Relevance and opportunities for clinical pharmacology

Particle Swarm Optimization in Residential Demand-Side Management: A Review on Scheduling and Control Algorithms for Demand Response Provision

Power distribution networks at the distribution level are becoming more complex in their behavior and more heavily stressed due to the growth of decentralized energy sources. Demand response (DR) programs can increase the level of flexibility on the demand side by discriminating the consumption patterns of end-users from their typical profiles in response to market signals. The exploitation of artificial intelligence (AI) methods in demand response applications has attracted increasing interest in recent years. Particle swarm optimization (PSO) is a computational intelligence (CI) method that belongs to the field of AI and is widely used for resource scheduling, mainly due to its relatively low complexity and computational requirements and its ability to identify near-optimal solutions in a reasonable timeframe. The aim of this work is to evaluate different PSO methods in the scheduling and control of different residential energy resources, such as smart appliances, electric vehicles (EVs), heating/cooling devices, and energy storage. This review contributes to a more holistic understanding of residential demand-side management when considering various methods, models, and applications. This work also aims to identify future research areas and possible solutions so that PSO can be widely deployed for scheduling and control of distributed energy resources in real-life DR applications.

Computational Intelligence Applications in Medicine and Biology

This special edition of the European Science Journal is devoted to applying computational intelligence methods to solving complex problems in medicine and biology.

Estimation of downhole cuttings concentration from experimental data – Comparison of empirical and fuzzy logic models

Proper selection of drilling parameters during planning phase to ensure an adequately clean well is the key to avoid costly drilling operational problems such as mechanical stuck pipe and high drillstring torque and drag resulting in not reaching the drilling target for highly deviated/ERD wells. Cuttings transport is a complex phenomenon influenced by different parameters such as flow rate, drillstring rotation, rate of penetration, eccentricity, well configuration, drilling fluid properties and cuttings properties. The complexity of the cuttings transport process has led to the use of alternative modeling approaches. In this paper, a computational intelligence method, fuzzy logic (FL), is chosen to develop a model to estimate downhole cuttings concentration. FL, resembling human reasoning, is capable of modeling non-linear functions of arbitrary complexity and dealing with imprecision in data. The FL model developed in the current work is based on 509 experimental observations involving 11 independent test parameters each. 25% of the collected dataset (excluding the test dataset) is used as cross-validation dataset and the rest is used as training dataset to avoid overfitting. The test dataset comprised of nine observations is used for comparing FL model estimates for downhole cuttings concentration to those made by two published empirical models which are based on dimensional analysis and critical drilling fluid velocity concept respectively. Comparison of the models on the test dataset shows that the developed FL model performs better than the two empirical models in all the three statistical measurements namely coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE).

Soft computing techniques for early diabetes prediction

Diabetes mellitus is a chronic, life-threatening, and complicated condition. Around 1.5 million deaths due to diabetes have been documented, according to a World Health Organization (WHO) estimation in 2019. In the world of medicine, predicting diabetes risk is a difficult and time-consuming task. Many past studies have been conducted to investigate and clarify diabetes symptoms and variables. To solve these persisting issues, however, more critical clinical criteria must be considered. A comparative analysis based on three soft computing strategies for diabetes prediction has been carried out and achieved in this work. Among the computational intelligence methods used in this study are fuzzy analytical hierarchy processes (FAHP), support vector machine (SVM), and artificial neural networks (ANNs). The techniques reveal promising performance in predicting diabetes reliably and effectively in terms of several classification evaluation metrics, according to experimental analysis and assessment conducted on 520 participants using a publicly available dataset.

A Machine Learning-Based Intelligence Approach for Multiple-Input/Multiple-Output Routing in Wireless Sensor Networks

Computational intelligence methods play an important role for supporting smart networks operations, optimization, and management. In wireless sensor networks (WSNs), increasing the number of nodes has a need for transferring large volume of data to remote nodes without any loss. These large amounts of data transmission might lead to exceeding the capacity of WSNs, which results in congestion, latency, and packet loss. Congestion in WSNs not only results in information loss but also burns a significant amount of energy. To tackle this issue, a practical computational intelligence approach for optimizing data transmission while decreasing latency is necessary. In this article, a Softmax-Regressed-Tanimoto-Reweight-Boost-Classification- (SRTRBC-) based machine learning technique is proposed for effective routing in WSNs. It can route packets around busy locations by selecting nodes with higher energy and lower load. The proposed SRTRBC technique is composed of two steps: route path construction and congestion-aware MIMO routing. Prior to constructing the route path, the residual energy of the node is determined. After that, the residual energy level is analyzed using softmax regression to determine whether or not the node is energy efficient. The energy-efficient nodes are located, and numerous paths between the source and sink nodes are established using route request and route reply. Following that, the SRTRBC technique is used for congestion-aware routing based on buffer space and bandwidth capability. The path that requires the least buffer space and has the highest bandwidth capacity is picked as the optimal route path among multiple paths. Finally, congestion-aware data transmission is used to minimize latency and data loss along the route path. The simulation considers a variety of performance metrics, including energy consumption, data delivery rate, data loss rate, throughput, and delay, in relation to the amount of data packets and sensor nodes.