Search

As social media has become a ubiquitous part of daily life, researchers made a great progress in identifying the emotion in user-generated texts. However, it is a challenging task as people express their emotion in explicit and implicit ways. This paper focuses on the problem of identifying sentiments from implicit sentences which contain no emotional word or phrase. Most of the existing sentiment classification models cannot identify the sentiments accurately since they usually focus on extracting features from grammatical information without taking contextual information into account. In this paper, we argue that the contextual information is the key to identify sentiments in implicit sentences. Moreover, multiple features extracting from different aspects should be taken into account to improve sentiment identification. This paper proposes a multi-feature neural network model considering three aspects: contextual information, syntactic information and semantic information. To better get the semantic information of the sentence, we propose an attention mechanism based on contextual affective space. The experimental results on the SMP2019-ECISA dataset demonstrate that our model outperforms the previous systems and strong neural baselines.

Computer, Internet, and Smartphone have changed our life as never before. Today, we cannot even imagine our life without these technologies. If we look around, we find everything, everywhere connected and controlled by system and software. We find amazing software and mobile applications which have become nerve of our daily life. Our dependency on this software and systems is so and so much that it is scary even to imagine, what if this system fails at any point in time. There is always a threat surrounded by various types of cyber-attacks. Every day cybercriminals are evolving their attacking strategy. Cyber-attacks using ever-more sophisticated malware are the major cause of concern for all types of users. Cyber-world has witnessed rapid changes in malware attacking strategy in the recent past. The volume, velocity, and complexity of malware are posing new challenges for malware detection systems. A scalable malware detection system with the capability to detect complex attacks is the time of need. In this paper, we have proposed a scalable malware detection system using big data and a machine learning approach. The machine learning model proposed in the system is implemented using Apache Spark which supports distributed learning. Locality-sensitive hashing is used for malware detection, which significantly reduces the malware detection time. A five-stage iterative process has been used to carry out the implementation and experimental analysis. The proposed model shown in the paper has achieved 99.8% accuracy. The proposed model has also significantly reduced the learning and malware detection time compared to models proposed by other researchers.

Twitter is an intensely utilized platform for disaster events and emergencies. Therefore, Twitter is an important resource for providing the essential information. Named entity recognition (NER), which is the process of determining the elementary units in a text and classifying them with pre-defined categories, plays a significant role to extract essential and usefulness information. However, NER is a challenging task due to the utilized informal text in the Twitter platform such as grammatical errors and nonstandard abbreviations. In this paper, recurrent neural network (RNN)-based approaches considering diversity of activation functions and optimization functions with NER tools are utilized to extract named entities such as organization, person, and location from the tweets. Inputs for RNN models are provided via two different NER tools which are natural language toolkit (NLTK) and general architecture for text engineering (Gate). Then, pre-labeled data are trained via GloVe word embedding technique, and RNN model variants such as LSTM, BLSTM, and GRU are demonstrated. Therefore, outperforming models among RNN variants are presented for predicting named entities. Yellowbrick interpreter is used for evaluation of the proposed method and Wilcoxon signed-rank test are applied on results of two different data sets to demonstrate consistency of the proposed method. In addition, comparison is made with existing machine learning methods. The experiments by utilizing the Nepal earthquake Twitter data set show that the RNN-based approaches achieve good results in finding named entities. In emergencies, the results of this paper can help in reducing the efforts of event location detection and provide better disaster management.

Fuzzy grey cognitive maps (FGCMs) have been widely adopted to support cause-and-effect decision-making under uncertainty. However, capturing the information for the initial state vector and the relationship matrix from various specialists can be cumbersome, which may affect the convergence of FGCMs or cause them to reach a chaotic state. To address this issue, this paper presents a novel group decision approach based on the combination of grey clustering (GC) and fuzzy grey cognitive maps for assessing causal relationships in uncertain environments. The main contribution consists in applying GC as a mean to obtain the initial state vector from the relationship matrix data. This halves the required inputs to the users, reducing uncertainty in the computational model. Also, the proposition brings a method for aggregating the linguistic judgements of multiple decision-makers when assessing causal relationships. The proposition also differs from others in the literature by providing results with lower imprecision levels, named greyness, and lower number of required iterations for the FGCM-based system to converge. A real application was conducted in a technology start-up to test the approach to practical implications. Results allowed the identification of important elements regarding the company’s profile and performance, aiding prioritization and enabling the development of action plans. This paper also includes a comparison of other representative models with the proposed approach, which led to more accurate results. Hence, this study addresses the need for new alternatives to improve the reliability and convergence of FGCM-based systems. Finally, suggestions for future applications are proposed.

Careful monitoring of plant conditions and their diagnosis are necessary, but a human cannot control a large area of land where the crop grows. This paper proposes the solution of this problem. Early diagnosis and accurate detection of plant leaf diseases can prevent the spread of the disease. In the last decade, machine learning methods and image classification tools have been used to identify and diagnose plant diseases. This paper proposes an accurate approach to identify plant leaf diseases based on the deep convolutional neural network and gated recurrent units. The PlantVillage dataset of damaged and healthy plant leaves images is used. The proposed model is trained to identify common plant leaf diseases of 14 species. The experimental results are compared to other well-known models. This study shows that the proposed model based on deep learning provides the best solution in the diagnosis of plant diseases with high accuracy, and that the gated recurrent unit neural network considered as a classifier can improve the accuracy of the convolutional neural network model. The comparison results demonstrated that the proposed approach achieved higher performance than other models.

Deep learning (DL) is gaining significant prevalence in every field of study due to its domination in training large data sets. However, several applications are utilizing machine learning (ML) methods from the past several years and reported good performance. However, their limitations in terms of data complexity give rise to DL methods. Intrusion detection is one of the prominent areas in which researchers are extending DL methods. Even though several excellent surveys cover the growing body of research on this subject, the literature lacks a detailed comparison of ML methods such as ANN, SVM, fuzzy approach, swarm intelligence and evolutionary computation methods in intrusion detection, particularly on recent research. In this context, the present paper deals with the systematic review of ML methods and DL methods in intrusion detection. In addition to reviewing ML and DL methods, this paper also focuses on benchmark datasets, performance evaluation measures and various applications of DL methods for intrusion detection. The present paper summarizes the recent work, compares their experimental results for detecting network intrusions. Furthermore, current research challenges are identified for helping fellow researchers in the era of DL-based intrusion detection.

The new energy vehicle system is in the initial stage of application, so the probability of fault is greater. Therefore, its reliability urgently needs to be improved. In order to improve the fault diagnosis effect of new energy vehicles, this paper proposes a fault diagnosis system of new energy vehicle electric drive system based on improved machine learning and also proposes several typical fault detection and diagnosis methods. Through the study of the operating characteristics and structural characteristics of the electric drive system and the analysis of the fault mechanism, this paper classifies the main faults of the electric drive system according to the self-test requirements of the electric drive system and the online diagnosis requirements and presents the self-test fault tree and online diagnosis fault tree of the electric drive system. In addition, this paper designs experiments to verify the performance of the system proposed by this paper, simulates the current common system fault conditions, and uses the system constructed in this paper to perform system fault diagnosis. The research results show that the performance of the fault diagnosis system for drive energy vehicles constructed in this paper is reliable.

Nowadays, political parties have widely adopted social media for their party promotions and election campaigns. During the election, Twitter and other social media platforms are used for political coverage to promote the party and its candidates. This research discusses and estimates the stability of many volumetric social media approaches to forecast election results from social media activities. Numerous machine learning approaches are applied to opinions shared on social media for predicting election results. This paper presents a machine learning model based on sentiment analysis to predict Pakistan's general election results. In a general election, voters vote for their favorite party or candidate based on their personal interests. Social media has been extensively used for the campaign in Pakistan general election 2018. Using a machine learning technique, we provide a five-step process to analyze the overall election results, whether fair or unfair. The work is concluded with detailed experimental results and a discussion on the outcomes of sentiment analysis for real-world forecasting and approval for general elections in Pakistan.

Fuzzy parameterized fuzzy soft matrices (fpfs-matrices) which can model problems involving fuzzy objects and parameters are one of the mathematical tools used to deal with decision-making problems. To utilize soft decision-making methods via fpfs-matrices in machine learning is likely to draw much scholarly attention. In this paper, we propose Comparison Matrix-Based Fuzzy Parameterized Fuzzy Soft Classifier (FPFS-CMC) in order to transfer modeling success of fpfs-matrices to machine learning. We then compare FPFS-CMC with Fuzzy Soft Set Classifier (FSSC), FussCyier, Fuzzy Soft Set Classification Using Hamming Distance (HDFSSC), and Fuzzy k-Nearest Neighbor (Fuzzy kNN) in consideration of accuracy, precision, recall, macro-F-score, and micro-F-score performance metrics, and 15 datasets in UCI Machine Learning Repository. Besides, we compare the proposed classifier with the state-of-the-art Support Vector Machine (SVM), Decision Tree (DT), and Adaptive Boosting (AdaBoost) in terms of five performance metrics herein. Afterward, the results from the experiments are analyzed by employing the Friedman and Nemenyi tests to assess the statistical significance of the differences in performances. Both experimental and statistical results show that FPFS-CMC outperforms the others. Finally, we provide the conclusive remarks and some suggestions for further research.

We have proposed MultiLexANFIS which is an adaptive neuro-fuzzy inference system (ANFIS) that incorporates inputs from multiple lexicons to perform sentiment analysis of social media posts. We classify tweets into two classes: neutral and non-neutral; the latter class includes both positive and negative polarity. This type of classification will be considered for applications that aim to test the neutrality of content posted by the users in social media platforms. In our proposed model, features are extracted by integrating natural language processing with fuzzy logic; hence, it is able to deal with the fuzziness of natural language in a very efficient and automatic manner. We have proposed a novel set of 64 rules for the proposed neuro-fuzzy network that can classify tweets correctly by working on fuzzy features fetched from VADER, AFINN and SentiWordNet lexicons. The proposed novel rules are domain independent, i.e., we can extend these rules for any textual data that employs lexicons. The antecedent and consequent parameters of the ANFIS are optimized by gradient descent and least squares estimate algorithms, respectively, in an iterative manner. The key contributions of this paper are: (1) a novel neuro-fuzzy system: MultiLexANFIS that takes as its input the positive and negative sentiment scores of tweets computed from multiple lexicons—VADER, AFINN and SentiWordNet, in order to classify the tweets into neutral and non-neutral content, (2) a novel set of 64 rules for the Sugeno-type fuzzy inference system—MultiLexANFIS, (3) single-lexicon-based ANFIS variants to classify tweets when multiple lexicons are not available and (4) comparison of MultiLexANFIS with different fuzzy, non-fuzzy and deep learning state of the art on various benchmark datasets revealing the superiority of our proposed neuro-fuzzy system for social sentiment analysis.

Mutation is the main operator of differential evolution (DE), as it is responsible for combining the information of distinct solutions to generate a donor vector. Aiming at improving the search effectivity of DE, previous research incorporated the calculation of centroids into the DE mutations. In some of the existing methods, the centroids are simply calculated as the center of some selected solutions (or, the entire population); in other cases, one-step clustering is used to perform a local search, or the centroids themselves are used as actual solutions in the population. As opposed to these methods, in this paper we extend some traditional DE mutation strategies to incorporate centroids calculated by deterministic hierarchical clustering. Experimental results on two sets of well-known benchmark problems show that the proposed cluster-centroid-based mutation strategies outperform, in general, the traditional rand/1 strategy, as well as several metaheuristics from the literature. Therefore, the use of clustering is an effective way to improve the search performance that could be exploited also in other population-based metaheuristics.

The efficiency of handball goalkeepers is a good predictor of team ranking in tournaments, but despite this, very few studies have been carried out into the performance characteristics of elite goalkeepers. This paper provides the criteria for evaluating a handball goalkeeper and applies a variety of soft-computing methodologies for estimating their weights. More specifically, a fuzzy multi-criteria decision-making method, a metaheuristic optimisation algorithm, and statistical and domain-knowledge-based methods were used to evaluate the actions of goalkeepers during the game. Computer experiments were performed for all the proposed methodologies, using data from the 2020 European Men’s Handball Championship, in order to estimate the weights of the indicators. Then, these weights were used to identify the best goalkeeper and identify and rank the top five goalkeepers as determined by the tournament organisers. The results obtained show that using the metaheuristic-based method is extremely helpful in quantifying the expert assessments, which are often challenging to express in a disaggregated form. The other two techniques offer a less optimal but more easily interpretable result for coaches and fans.

In modern times, digital medical images play a significant progression in clinical diagnosis to treat the populace earlier to hoard their lives. Magnetic resonance imaging (MRI) is one of the most advanced medical imaging modalities that facilitate scanning various parts of the human body like the head, chest, abdomen, and pelvis and identify the diseases. Numerous studies on the same discipline have proposed different algorithms, techniques, and methods for analyzing medical digital images, especially MRI. Most of them have mainly focused on identifying and classifying the images as either normal or abnormal. Computing brainpower is essential to understand and handle various brain diseases efficiently in critical situations. This paper knuckles down to design and implement a computer-aided framework, enhancing the identification of humans' cognitive power from their MRI Images. The proposed framework converts the 3D DICOM images into 2D medical images, pre-processing, enhancement, learning, and extracting various image information to classify it as normal or abnormal and provide the brain's cognitive power. This study widens the efficient use of machine learning methods, voxel residual network (VRN), with multimodality fusion architecture to learn and analyze the image to classify and predict cognitive power. The experimental results denote that the proposed framework demonstrates better performance than the existing approaches.

Development of safety features to prevent accident on the roads is one of the major challenges in the automobile industry. Driving with no prior information about the upcoming road can be dangerous. Not knowing about what’s coming down the road can disbalance the vehicle and lead to accident. Driving when tired or drunk can lead to major life risking accidents. The road accidents can be prevented by collecting the data of road’s characteristics and providing an alert to the driver if any distraction comes in the way. This paper introduces a concept of real-time monitoring of the driver and generating an alert when the driver gets sleepy or unconscious. Road analysis was also done to classify spots with high possibility of accidents and alerts generated for the same. The system thus covers two major reasons which cause heavy accidents on the road and provides solution to overcome them.

Bayesian inference shows that the distribution of the future event not only depends on the past events (prior), but also depends on the relation between the past and the future events (likelihood). However, the classical Bayesian methods do not consider the important contributions of recent data. In this paper, we propose a new Bayesian inference-based training method, which can be used as online training for Bayesian methods. We give the training methods for the exponential and the normal models. We successfully apply this method for the seismic parameter prediction using the data of central Italy from 2014 to 2017. Comparisons show our method is more effective than the other Bayesian methods.

Support vector machines (SVMs) are one of the most popular and widely-used approaches in modeling. Various kinds of SVM models have been developed in the literature of prediction and classification in order to cover different purposes. Fuzzy and crisp support vector machines are a well-known branch of modeling approaches that frequently applied for certain and uncertain modeling, respectively. However, each of these models can only be efficiently used in its specified domain and cannot yield appropriate and accurate results if the opposite situations have occurred. While the real-world systems and data sets often contain both certain and uncertain patterns that are complicatedly mixed together and need to be simultaneously modeled. In this paper, a generalized support vector machine (GSVM) is proposed that can simultaneously benefit the unique advantages of certain and uncertain versions of the traditional support vector machines in their own specialized categories. In the proposed model, the underlying data set is first categorized into two classes of certain and uncertain patterns. Then, certain patterns are modeled by a support vector machine, and uncertain patterns are modeled by a fuzzy support vector machine. After that, the function of the relationship, as well as the relative importance of each component, are estimated by another support vector machine, and subsequently, the final forecasts of the proposed model are calculated. Empirical results of wind speed forecasting indicate that the proposed method not only can achieve more accurate results than support vector machines (SVMs) and fuzzy support vector machines (FSVMs) but also can yield better forecasting performance than traditional fuzzy and nonfuzzy single models and traditional preprocessing-based hybrid models of SVMs.

Public health experts and healthcare professionals are gradually identifying sedentary activity as a population-wide, pervasive health risk. The purpose of this paper is to propose a method to identify the changes in posture during sedentary work and to give feedback by analysing the identified posture of the upper body, i.e. hands, shoulder, and head positioning. After capturing the image of the human pose, pre-processing of the image takes place with a bandpass filter, which helps to reduce the noise and morphological operation, which is used to carry out the process of dilation, erosion and opening of an image. To predict the results easily with the use of texture feature extraction, it helps to extract the image’s feature. Then, accuracy is predicted by using the deep neural network techniques, to predict the result accurately. After prediction and analysis, the feedback system is developed to alert individuals through the alarm system. The proposed method is formulated by using DNN for prediction in the MATLAB software tool. The results show accuracy, sensitivity and specificity of the prediction using a deep neural network are 97.2%, 88.7% and 99.1%. The proposed method is compared with the existing methods SVM, Random Forest and KNN algorithms. The accuracy, sensitivity and specificity of the existing algorithms are SVM with 77.6%, 57.4 and 97.8%; Random Forest with 80.6%, 63.7% and 97.5%; and KNN with 65.8%, 61.2%, and 95.1%. This concept helps to prevent the impact of sedentary activity on fatal and non-fatal cardiovascular and musculoskeletal diseases, respectively.

The sensor nodes are devices with extra capabilities of sensing, communicating and processing of the recorded data. The sensor-based wireless and IoT-enabled networks can contribute a precarious part of army command, defense control, defense communications, computerized based intelligence and surveillance, and above all the targeting systems. Examples of defense applications include monitoring of own army forces and enemy forces; monitoring of ammunition, monitoring of equipment, targeting at certain regions; and nuclear as well as biotechnology-based attack detection. With the advent of AI and latest technologies, a technical paradigm shift can be seen in monitoring the faults in sensor nodes that are capable to collect the data and entire decisions are inferred on the basis of this data. By deploying sensors in critical areas, all the movements can be followed in detail. Hence, instant fault location measurement of sensor nodes with the least complex approaches is the need of the hour. Therefore, a novel soft computing-based approach is proposed in this paper for measuring the fault in locations of sensor-based networks using fuzzy logic and neural networks with high accuracy. The proposed technique allows lower consumption of energy while locating the faults. The results demonstrate the superior performance of the proposed fault location scheme with respect to the network node loss, measurement error, and measurement time taken for detecting faults in locations of sensor nodes. The proposed fuzzy and neural network-based method outperforms the existing benchmarked techniques considered for comparative study.

In order to overcome the problems of low security and accuracy of traditional online social network data mining model, this paper proposes and constructs a new online social network data mining model based on blockchain. Based on the blockchain structure, the hash function in the blockchain is used to encrypt the online social network data to improve the security of the data. Based on the encrypted data, the fuzzy covariance matrix is used to obtain the data clustering center to complete the data clustering. According to the data clustering results, time series analysis method is used to mine online social network data. Experimental results show that, compared with the traditional mining model, this model can effectively improve the security of online social network data and improve the mining accuracy, with the highest mining accuracy of 97%.

The quality of the defect datasets is a critical issue in the domain of software defect prediction (SDP). These datasets are obtained through the mining of software repositories. Resent studies claims over the quality of the defect dataset. It is because of inconsistency between bug/clean fix keyword in fault reports and the corresponding link in the change management logs. Class Imbalance (CI) problem is also a big challenging issue in SDP models. The defect prediction method trained using noisy and imbalanced data leads to inconsistent and unsatisfactory results. Combined analysis over noisy instances and CI problem needs to be required. To the best of our knowledge, there are insufficient studies that have been done over such aspects. In this paper, we deal with the impact of noise and CI problem on five baseline SDP models; we manually added the various noise level (0 to 80%) and identified its impact on the performance of those SDP models. Moreover, we further provide guidelines for the possible range of tolerable noise for baseline models. We have also suggested the SDP model, which has the highest noise tolerable ability and outperforms over other classical methods. The True Positive Rate (TPR) and False Positive Rate (FPR) values of the baseline models reduce between 20\% to 30\% after adding 10% to 40% noisy instances. Similarly, the ROC (Receiver Operating Characteristics) values of SDP models reduces to 40% to 50%. The suggested model leads to avoid noise between 40% to 60% as compared to other traditional models.

Depression has become a common issue among IT industry professionals today. Lifestyle changes and new work culture increase the risk of depression among employees. Various companies and organizations offer mental health plans and try to pacify the work environment. However, the problem is already out of control. This research paper proposes an effective deep learning model for stress prediction among working employees with the help of lion optimization-based optimal artificial neural network (OANN) model. Here, the features are selected using optimal ANN technique and the diseases are predicted using lion optimization method. ANN technique eliminates inappropriate and unnecessary attributes in a significant manner, once the information on calculated characteristics and weight is disseminated to lion optimization classifier. The test results inferred that the artificial neural network is highly efficient than the current OANN algorithm method, based on lion optimization. The study evaluated the data and found that the performance of employees working under normal conditions was higher when compared to the performance of employees who work under stress. Furthermore, attitude-coping efforts may be a cognitive behavioral mechanism, which explains how workload is related to courage and work performance of employees with high stress level.

Automatic factor extraction is to extract the relevant facts from the case to assist the judge in the intelligent decision-making of civil disputes. Previously, the existing methods mainly focus on context-free word embeddings to deal with extraction tasks in the field of law, which cannot get a better semantic understanding of the text and in turn leads to an adverse extraction performance. Therefore, in this paper, a deep contextualized embeddings-based method called the knowledge-guided civil case fact elements extraction (KGCEE) model to automatically extract civil fact elements in the civil case domain is proposed. This approach is mainly based on the RoBERTa, but a few techniques make a more powerful model. Firstly, the model is retrained with civil domain data to provide more sensitive weight to initialize the model parameters in the downstream task. Secondly, the extraction is transformed into a sentence pairs task and we have incorporated data by leveraging label information to improve the generalization ability of the model. Thirdly, at the beginning of the KGCEE, we propose to inject part-of-speech information to the word embeddings to enhance the ability to capture the semantic and syntactic information, which aims to obtain better text representations. Finally, the KGCEE method is evaluated under civil domain data such as marriage and family, labor disputes and loan contracts originally from Chinese AI and Law (CAIL). The experimental results demonstrate that our KGCEE method outperforms other context-free word embeddings methods and other traditional transformer-based methods.

The main aim of this paper is to design and test new software application to support experts involved in decision-making in the field of energy security. The prototype named ESecFuzzy is designed for this purpose. It implements various fuzzy concepts (fuzzy rules, fuzzified input data, fuzzy variables utilized by fuzzy terms and related fuzzy sets) chosen to obtain reasoning in case of unclear, uncertain or even incomplete input data for reaching a conclusion about them. The research was conducted on a sample of 28 European Union countries over a ten-year period (2008–2017). The research outcomes are as follows: (a) ESecFuzzy application for energy security measurement was developed; (b) application testing; (c) measuring energy security on a given sample, and (d) evaluation of the accuracy and acceptability of fuzzy logic as an approach for energy security quantification. ESecFuzzy provides the experimenting with different input data (time series intersected with geospatial data) as well as fine-tuning of fuzzy rules in knowledge base. Through the evaluation and experimenting process, ESecFuzzy application demonstrated the advantage of fuzzy logic by obtaining the derived information based on mass of heterogeneous data organized in time series that indicate general trends in the target application domain.

The advent of cloud infrastructure in which third-party cloud services may retain sensitive consumer and company data in storage environments underlines the need to advocate for encryption and multi-tenant shared processing as a primary security mechanism. Digital information movement, storage, and processing are widely defined in terms of "Data in Motion,” "Data at Rest," and "Data in Usage," respectively. The implementation of security methods for each of these states can be viewed similarly. Transit data applies to data when being moved from one source of data to another. Transit data contains data sent across the network from back-end clients, programs, and repositories. There could be two data centers inside the same organizational network in the cloud, as a member of completely separate networks. This paper presents a novel architecture data-in-transit defender (DiTD), to protect data in transit; DiTD provides a novel security framework based on high-performance cloud computing. This protocol enables more efficient use of the key strength and time of symmetric block encrypted data, public-key cryptography (PUKC), cryptographic hash, and brief key exchange function.

In recent decades, researches on optimizing the parameter of the artificial neural network (ANN) model has attracted significant attention from researchers. Hybridization of superior algorithms helps improving optimization performance and capable of solving complex applications. As a traditional gradient-based learning algorithm, ANN suffers from a slow learning rate and is easily trapped in local minima when training techniques such as gradient descent (GD) and back-propagation (BP) algorithm are used. The characteristics of randomization and selection of the best or near-optimal solution of metaheuristic algorithm provide an effective and robust solution; therefore, it has always been used in training of ANN to improve and overcome the above problems. New metaheuristic algorithms are proposed every year. Therefore, the review of its latest developments is essential. This article attempts to summarize the metaheuristic algorithms which have been proposed from the year 1975 to 2020 from various journals, conferences, technical papers, and books. The comparison of the popularity of the metaheuristic algorithm is presented in two time frames, such as algorithms proposed in the recent 20 years and those proposed earlier. Then, some of the popular metaheuristic algorithms and their working principle are reviewed. This article further categorizes the latest metaheuristic search algorithm in the literature to indicate their efficiency in training ANN for various industry applications. More and more researchers tend to develop new hybrid optimization tools by combining two or more metaheuristic algorithms to optimize the training parameters of ANN. Generally, the algorithm’s optimal performance must be able to achieve a fine balance of their exploration and exploitation characteristics. Hence, this article tries to compare and summarize the properties of various metaheuristic algorithms in terms of their convergence rate and the ability to avoid the local minima. This information is useful for researchers working on algorithm hybridization by providing a good understanding of the convergence rate and the ability to find a global optimum.

In recent times, the question of employability has become a critical concern not only for degree holders but for educational organizations. Hence, employability prediction models play an important role in analyzing the student’s capability to get employment. In this paper, a hybrid model of deep belief network and soft max regression (DBN-SR) is proposed for student employability prediction. Initially, pre-processing is performed on student’s data for removing irrelevant attributes to achieve data consistency. Further, to enhance the accuracy of the prediction model, the crow search algorithm-based feature selection model is employed to select the optimal subset of features from original features. Then, the selected subset of features is taken as the input of the deep belief network (DBN) for intrinsic feature learning to obtain high-level feature representation. Finally, the soft max regression (SR) is used to predict the class of students as employed or unemployed. The proposed employability prediction model achieves above 98% of accuracy which is comparatively 2.5%, 5% higher than the deep autoencoder and deep neural network-based models. The performance outcomes proved that the proposed DBN-SR model has been well suitable for predicting student’s employability.

The diagnosis of heart disease is found to be a serious concern, so the diagnosis has to be done remotely and regularly to take the prior action. In the present years, the diagnosis of heart disease has become a key research area for researchers and many models have been proposed in recent years. The diagnosis of heart disease can be done using optimization algorithms, and it provides results with good efficiency. The main objective of this paper is to propose a hybrid fuzzy-based decision tree algorithm for the process of prediction of heart disease at an early stage through the continuous and remote patient monitoring system. The results obtained from the proposed algorithm are compared with the various number of classifier algorithms like decision tree J48, naive Bayes, GA with FCM, KNN with NB, ANN, SVM with fuzzy in which the proposed HFDT algorithm provides better accuracy of 98.30%. From the above-obtained results, the proposed hybrid fuzzy-based decision tree algorithm efficiently predicts heart disease compared to the other classifier algorithms in the literature. The proposed work is implemented in the MATLAB environment using the heart disease dataset.

With the development of quality of life, people pay more and more attention to the surrounding environmental factors, especially air pollution. The problem of air pollution in China is becoming more and more serious, which poses a great threat to people’s health. Therefore, the prediction of air quality concentration is very important. PM2.5 is the primary indicator for evaluating the concentration of smog. Currently, studies have been proposed to predict the concentration of PM2.5. Before, most methods use traditional machine learning or real-time monitoring to predict pollution of PM2.5 value. However, the previous prediction methods cannot meet the requirement of the accuracy. For this end, this paper uses Convnet and Dense-based Bidirectional Gated Recurrent Unit to predict PM2.5 value which combined Convnet, Dense and Bi-GRU. The feature in air quality data was extracted from convnets without max-pooling instead another convolutional layer and Bi-GRU with additional Dense could provide a more accuracy result. Experiments show that the effectiveness of our method PM2.5 mass concentration prediction model provides a more superior method for PM2.5 mass concentration prediction.

In the current pandemic, smart technologies such as cognitive computing, artificial intelligence, pattern recognition, chatbot, wearables, and blockchain can sufficiently support the collection, analysis, and processing of medical data for decision making. Particularly, to aid medical professionals in the disease diagnosis process, cognitive computing is helpful by processing massive quantities of data rapidly and generating customized smart recommendations. On the other hand, the present world is facing a pandemic of COVID-19 and an earlier detection process is essential to reduce the mortality rate. Deep learning (DL) models are useful in assisting radiologists to investigate the large quantity of chest X-ray images. However, they require a large amount of training data and it needs to be centralized for processing. Therefore, federated learning (FL) concept can be used to generate a shared model with no use of local data for DL-based COVID-19 detection. In this view, this paper presents a federated deep learning-based COVID-19 (FDL-COVID) detection model on an IoT-enabled edge computing environment. Primarily, the IoT devices capture the patient data, and then the DL model is designed using the SqueezeNet model. The IoT devices upload the encrypted variables into the cloud server which then performs FL on major variables using the SqueezeNet model to produce a global cloud model. Moreover, the glowworm swarm optimization algorithm is utilized to optimally tune the hyperparameters involved in the SqueezeNet architecture. A wide range of experiments were conducted on benchmark CXR dataset, and the outcomes are assessed with respect to different measures . The experimental outcomes pointed out the enhanced performance of the FDL-COVID technique over the other methods.

Generating video captioning automatically is an active and flouring research topic that involves the complex interactions between visual features and natural language generation. The attention mechanism obtains the key visual information corresponding to the word by removing redundant information. However, existing visual attention methods are indirectly guided by the hidden state of language model, ignoring the interactions between visual features obtained by attention mechanisms. Due to the existence of incomplete object or interference noise, attention mechanism with frame feature is hard to find correct regions-of-interest which closely related to the motion state. Worse still, at each time step, the hidden states have no access to the posterior decode states. The future predicted information is not fully utilized, which lead to the lack of detailed context-aware information. In this paper, we propose a novel video captioning framework with Memory-attended Semantic Context-aware Network (MaSCN) to capture the adjacent sequential dependency across multiple time stamps between different outputs for visual features. To exploit pivotal feature from coarse-grained to fine-grained, we introduce the attention module in MaSCN, which uses corresponding tailored Visual Semantic LSTM(VSLSTM) layers to more precisely map visual relationship information through multi-level attention mechanism. Besides, we integrate the visual features obtained through the attention mechanism as a late fusion. The visual semantic loss is used to explicitly memorize contextual information, capturing the fine-grained detailed cues. Compared with state-of-the-art approaches, the extensive experiments demonstrate the effectiveness of our method on MSVD and MSR-VTT datasets.

The idea of Ubiquitous education is not fresh and omnipresent apps that have spread from the Internet into smartphone applications over the decades, with the increasing deployment of sensor devices. The current increase of the Internet of Things (IoT) could allow a new form of ubiquitous learning mechanism to be moved by using affordable sensors, border control devices, and IoT middleware and parameters to create creative and creative ubiquitous learning designs. This development contributes to the innovative use of intelligent environments. The standard of living of people in smart environments is essential to smart transportation. Intelligent transportation includes motor configuration use of computers and sensors. Therefore, in this paper, the ubiquitous learning environment-assisted IoT (ULE-IoT) model in the vehicle has been proposed for an effective learning environment. ULE-IoT implements time computation and promotes close collaboration in the IoT-based intelligent transportation community. The proposed model can aid in automating railroads, highways, airways, and maritime transportation, improving consumer satisfaction with how items are moved, tracked, and delivered. The ULE-IoT is a generic approach for intelligent transportation systems using Advanced Analytics in virtual environments. The experimental findings indicate that ULE-IoT highest efficiency ratio of 98.76% in the learning environment.