Pub Date : 2021-10-22DOI: 10.1080/0952813X.2021.1960638
Gaurav Jee, GM Harshvardhan, Mahendra Kumar Gourisaria, Vijander Singh, S. Rautaray, M. Pandey
ABSTRACT The COVID-19 pandemic is one of the rarest events of global crises where a viral pathogen infiltrates every part of the world, leaving every country face an inevitable threat of having to lock down major cities and economic hubs and put firm restrictions on citizens thus slowing down the economy. The risk of removal of lockdowns is the emergence of new waves of a pandemic causing a surge in new cases. These facts necessitate the containment of the virus when the lockdowns end. Wearing masks in crowded places can help restrict the spread of the virus through minuscule droplets in the air. Through the automatic detection, enumeration, and localisation of masks from closed-circuit television footage, it is possible to keep violations of post-COVID regulations in check. In this paper, we leverage the Single-Shot Detection (SSD) framework through different base convolutional neural networks (CNNs) namely VGG16, VGG19, ResNet50, DenseNet121, MobileNetV2, and Xception to compare performance metrics attained by the different variations of the SSD and determine the efficacies for the best base network model for automatic mask detection in a post COVID world. We find that Xception performs best among all the other models in terms of mean average precision.
{"title":"Efficacy Determination of Various Base Networks in Single Shot Detector for Automatic Mask Localisation in a Post COVID Setup","authors":"Gaurav Jee, GM Harshvardhan, Mahendra Kumar Gourisaria, Vijander Singh, S. Rautaray, M. Pandey","doi":"10.1080/0952813X.2021.1960638","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1960638","url":null,"abstract":"ABSTRACT The COVID-19 pandemic is one of the rarest events of global crises where a viral pathogen infiltrates every part of the world, leaving every country face an inevitable threat of having to lock down major cities and economic hubs and put firm restrictions on citizens thus slowing down the economy. The risk of removal of lockdowns is the emergence of new waves of a pandemic causing a surge in new cases. These facts necessitate the containment of the virus when the lockdowns end. Wearing masks in crowded places can help restrict the spread of the virus through minuscule droplets in the air. Through the automatic detection, enumeration, and localisation of masks from closed-circuit television footage, it is possible to keep violations of post-COVID regulations in check. In this paper, we leverage the Single-Shot Detection (SSD) framework through different base convolutional neural networks (CNNs) namely VGG16, VGG19, ResNet50, DenseNet121, MobileNetV2, and Xception to compare performance metrics attained by the different variations of the SSD and determine the efficacies for the best base network model for automatic mask detection in a post COVID world. We find that Xception performs best among all the other models in terms of mean average precision.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"25 1","pages":"345 - 364"},"PeriodicalIF":2.2,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87938850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-29DOI: 10.1080/0952813X.2021.1970824
Sivaram Rajeyyagari
ABSTRACT Smart devices and people existing on the internet are connected to smart objects or things in the Internet of Things (IoT) technology. To protect the user information, it is required to detect malicious actions in the IoT environment. Even though different threat detection methods are introduced in the IoT technology, detecting malicious activity is still a significant challenge in the communication network. Hence, in this research work, an effective Cuckoo Search Chicken Swarm (CSCS) optimisation algorithm is proposed to detect the malicious threat in the network effectively. At first, the user activity information is simulated from the IoT network and stored in the user activity log. The user activity log file is forwarded to the feature extraction module, where the features, like logon, device, file, email, and Hypertext Transfer Protocol (HTTP) are extracted using the window length. For each user, the features are extracted with respect to the time stamp. Then, the dynamic feature index is constructed, and the threat detection is performed using the deep Long Short-Term Memory (LSTM) classifier, which is trained using the proposed CSCS algorithm. The proposed CSCS algorithm is designed by integrating the Cuckoo Search (CS) algorithm and the Chicken Swarm Optimisation (CSO) algorithm. Moreover, the proposed algorithm attained better performance with respect to the metrics, like namely F1-score, precision, and recall as 0.915, 0.975, and 0.884 by varying the k-value and 0.9286, 0.9235, and 0.9337 by varying the training data using window size as 10, respectively.
{"title":"Threat detection in Internet of Things using Cuckoo search Chicken Swarm optimisation algorithm","authors":"Sivaram Rajeyyagari","doi":"10.1080/0952813X.2021.1970824","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1970824","url":null,"abstract":"ABSTRACT Smart devices and people existing on the internet are connected to smart objects or things in the Internet of Things (IoT) technology. To protect the user information, it is required to detect malicious actions in the IoT environment. Even though different threat detection methods are introduced in the IoT technology, detecting malicious activity is still a significant challenge in the communication network. Hence, in this research work, an effective Cuckoo Search Chicken Swarm (CSCS) optimisation algorithm is proposed to detect the malicious threat in the network effectively. At first, the user activity information is simulated from the IoT network and stored in the user activity log. The user activity log file is forwarded to the feature extraction module, where the features, like logon, device, file, email, and Hypertext Transfer Protocol (HTTP) are extracted using the window length. For each user, the features are extracted with respect to the time stamp. Then, the dynamic feature index is constructed, and the threat detection is performed using the deep Long Short-Term Memory (LSTM) classifier, which is trained using the proposed CSCS algorithm. The proposed CSCS algorithm is designed by integrating the Cuckoo Search (CS) algorithm and the Chicken Swarm Optimisation (CSO) algorithm. Moreover, the proposed algorithm attained better performance with respect to the metrics, like namely F1-score, precision, and recall as 0.915, 0.975, and 0.884 by varying the k-value and 0.9286, 0.9235, and 0.9337 by varying the training data using window size as 10, respectively.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"761 1","pages":"729 - 753"},"PeriodicalIF":2.2,"publicationDate":"2021-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78811138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-05DOI: 10.1080/0952813X.2021.1974953
Dor Mizrahi, Ilan Laufer, Inon Zuckerman
ABSTRACT In divergent interest tacit coordination games there is a tradeoff between selecting a solution with a high individual payoff and one which is perceptually more salient to both players, i.e., a focal point. To construct a cognitive model of decision making in such games we need to consider both the social value orientation of the players and the game features. Therefore, the goal of this study was to construct a cognitive model for predicting the probability of selecting a focal point solution in these types of games. Using bootstrap aggregated ensemble of decision trees that was trained on the “bargaining table’ game behavioural data were able to predict when players will select a focal point solution. The binary classification achieved an accuracy level of 85%. The main contribution of the current study is the ability to model players behaviour based on the interaction between different SVOs and game features. This interaction enabled us to gain different insights regarding player’s behaviour. For example, a prosocial player often showed a tendency towards focal point solutions even when their personal gains were lower than that of the co-player. Thus, SVO is not a sufficient model for explaining behaviour in different divergent interest scenarios.
{"title":"Predicting focal point solution in divergent interest tacit coordination games","authors":"Dor Mizrahi, Ilan Laufer, Inon Zuckerman","doi":"10.1080/0952813X.2021.1974953","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1974953","url":null,"abstract":"ABSTRACT In divergent interest tacit coordination games there is a tradeoff between selecting a solution with a high individual payoff and one which is perceptually more salient to both players, i.e., a focal point. To construct a cognitive model of decision making in such games we need to consider both the social value orientation of the players and the game features. Therefore, the goal of this study was to construct a cognitive model for predicting the probability of selecting a focal point solution in these types of games. Using bootstrap aggregated ensemble of decision trees that was trained on the “bargaining table’ game behavioural data were able to predict when players will select a focal point solution. The binary classification achieved an accuracy level of 85%. The main contribution of the current study is the ability to model players behaviour based on the interaction between different SVOs and game features. This interaction enabled us to gain different insights regarding player’s behaviour. For example, a prosocial player often showed a tendency towards focal point solutions even when their personal gains were lower than that of the co-player. Thus, SVO is not a sufficient model for explaining behaviour in different divergent interest scenarios.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"18 1","pages":"933 - 953"},"PeriodicalIF":2.2,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83686308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-30DOI: 10.1080/0952813X.2021.1966841
Saied Asghari, N. J. Navimipour
ABSTRACT There are many issues and problems in cloud computing that researchers try to solve by using different techniques. Most of the cloud challenges are NP-hard problems; therefore, many meta-heuristic techniques have been used for solving these challenges. As a famous and powerful meta-heuristic algorithm, the Ant Colony Optimisation (ACO) algorithm has been recently used for solving many challenges in the cloud. However, in spite of the ACO potency for solving optimisation problems, its application in solving cloud issues in the form of a review article has not been studied so far. Therefore, this paper provides a complete and detailed study of the different types of ACO algorithms for solving the important problems and issues in cloud computing. Also, the number of published papers for various publishers and different years is shown. In this paper, available challenges are classified into different groups, including scheduling, resource allocation, load balancing, consolidation, virtual machine placement, service composition, energy consumption, and replication. Then, some of the selected important techniques from each category by applying the selection process are presented. Besides, this study shows the comparison of the reviewed approaches and also it highlights their principal elements. Finally, it highlights the relevant open issues and some clues to explain the difficulties. The results revealed that there are still some challenges in the cloud environments that the ACO is not applied to solve.
{"title":"The role of an ant colony optimisation algorithm in solving the major issues of the cloud computing","authors":"Saied Asghari, N. J. Navimipour","doi":"10.1080/0952813X.2021.1966841","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1966841","url":null,"abstract":"ABSTRACT There are many issues and problems in cloud computing that researchers try to solve by using different techniques. Most of the cloud challenges are NP-hard problems; therefore, many meta-heuristic techniques have been used for solving these challenges. As a famous and powerful meta-heuristic algorithm, the Ant Colony Optimisation (ACO) algorithm has been recently used for solving many challenges in the cloud. However, in spite of the ACO potency for solving optimisation problems, its application in solving cloud issues in the form of a review article has not been studied so far. Therefore, this paper provides a complete and detailed study of the different types of ACO algorithms for solving the important problems and issues in cloud computing. Also, the number of published papers for various publishers and different years is shown. In this paper, available challenges are classified into different groups, including scheduling, resource allocation, load balancing, consolidation, virtual machine placement, service composition, energy consumption, and replication. Then, some of the selected important techniques from each category by applying the selection process are presented. Besides, this study shows the comparison of the reviewed approaches and also it highlights their principal elements. Finally, it highlights the relevant open issues and some clues to explain the difficulties. The results revealed that there are still some challenges in the cloud environments that the ACO is not applied to solve.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"216 1","pages":"755 - 790"},"PeriodicalIF":2.2,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75596292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-30DOI: 10.1080/0952813X.2021.1971777
R. A. Ansag, Avelino J. Gonzalez
ABSTRACT This paper presents a review of research works from the last several years in automated story generation systems. These systems are categorised into interactive story generation systems and non-Interactive story generation systems. Interactive systems are those that collaborate with a user/author during the process of creating and/or executing the story. The extent of user interaction varies across systems but remains an integral part of the creation and/or the unfolding of the story. Non-Interactive systems concentrate on complete automation of the creative process involved in narrative generation to create diverse and interesting stories. Interactive story generators specifically designed for video game narratives are reviewed as a separate sub-class of interactive story generation systems. Also reviewed are the methods used for evaluation of story generation systems as a way to explore the possibility of having standard methods of evaluation within the research community. The paper includes a discussion of trends and directions of the research discipline.
{"title":"State-of-the-Art in Automated Story Generation Systems Research","authors":"R. A. Ansag, Avelino J. Gonzalez","doi":"10.1080/0952813X.2021.1971777","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1971777","url":null,"abstract":"ABSTRACT This paper presents a review of research works from the last several years in automated story generation systems. These systems are categorised into interactive story generation systems and non-Interactive story generation systems. Interactive systems are those that collaborate with a user/author during the process of creating and/or executing the story. The extent of user interaction varies across systems but remains an integral part of the creation and/or the unfolding of the story. Non-Interactive systems concentrate on complete automation of the creative process involved in narrative generation to create diverse and interesting stories. Interactive story generators specifically designed for video game narratives are reviewed as a separate sub-class of interactive story generation systems. Also reviewed are the methods used for evaluation of story generation systems as a way to explore the possibility of having standard methods of evaluation within the research community. The paper includes a discussion of trends and directions of the research discipline.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"216 1","pages":"877 - 931"},"PeriodicalIF":2.2,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79646554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-30DOI: 10.1080/0952813X.2021.1966839
Hema Krishnan, M. Elayidom, T. Santhanakrishnan
ABSTRACT In this paper, a novel sentiment analysis model is implemented, which consists of six stages: (i) Pre-processing, (ii) Keyword extraction and its sentiment categorisation, (iii) Semantic word extraction, (iv) Semantic similarity checking, (v) Feature extraction, and (vi) Classification. Initially, the Mongodb documented tweets are subjected to pre-processing that includes steps such as stop word removal, stemming, and blank space removal. Accordingly, from the pre-processed tweets, the keywords are extracted. Based on the extracted keywords, the prevailing semantic words are extracted after classifying the sentimental keywords. Further, the evaluation of the semantic similarity score with the keywords takes place. Also, it exploits joint holoentropy and cross holoentropy. Here, the extraction of weighted holoentropy features is the main contribution, where a weight function is multiplied by the holoentropy features. To improve the performance of classification, a constant term is used for calculating weight function. It is tuned or optimised in such a way that the accuracy of the proposed method is better. The optimisation strategy uses the hybrid model that merges Particle Swarm Optimisation (PSO) into Whale Optimisation Algorithm (WOA). Hence, the proposed algorithm is named as Swarm Velocity-based WOA (SV-WOA). Finally, the analysis is done to prove the efficiency of the proposed model.
{"title":"Weighted holoentropy-based features with optimised deep belief network for automatic sentiment analysis: reviewing product tweets","authors":"Hema Krishnan, M. Elayidom, T. Santhanakrishnan","doi":"10.1080/0952813X.2021.1966839","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1966839","url":null,"abstract":"ABSTRACT In this paper, a novel sentiment analysis model is implemented, which consists of six stages: (i) Pre-processing, (ii) Keyword extraction and its sentiment categorisation, (iii) Semantic word extraction, (iv) Semantic similarity checking, (v) Feature extraction, and (vi) Classification. Initially, the Mongodb documented tweets are subjected to pre-processing that includes steps such as stop word removal, stemming, and blank space removal. Accordingly, from the pre-processed tweets, the keywords are extracted. Based on the extracted keywords, the prevailing semantic words are extracted after classifying the sentimental keywords. Further, the evaluation of the semantic similarity score with the keywords takes place. Also, it exploits joint holoentropy and cross holoentropy. Here, the extraction of weighted holoentropy features is the main contribution, where a weight function is multiplied by the holoentropy features. To improve the performance of classification, a constant term is used for calculating weight function. It is tuned or optimised in such a way that the accuracy of the proposed method is better. The optimisation strategy uses the hybrid model that merges Particle Swarm Optimisation (PSO) into Whale Optimisation Algorithm (WOA). Hence, the proposed algorithm is named as Swarm Velocity-based WOA (SV-WOA). Finally, the analysis is done to prove the efficiency of the proposed model.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"5 1","pages":"679 - 707"},"PeriodicalIF":2.2,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78711569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-30DOI: 10.1080/0952813X.2021.1966840
Sakina Othmani, N. Tatar
ABSTRACT In this paper, an impulsive Cohen-Grossberg bidirectional associative neural network with both time-varying and distributed delays is examined. Novel sufficient conditions for deriving stability with a desired rate, including the exponential one, are obtained. We consider a large class of admissible kernels encompassing the existing ones. Our findings cover the existing stability results in the literature. Finally, a numerical example is given for the validation of the theoretical outcomes.
{"title":"Stability for a retarded impulsive Cohen–Grossberg BAM neural network system","authors":"Sakina Othmani, N. Tatar","doi":"10.1080/0952813X.2021.1966840","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1966840","url":null,"abstract":"ABSTRACT In this paper, an impulsive Cohen-Grossberg bidirectional associative neural network with both time-varying and distributed delays is examined. Novel sufficient conditions for deriving stability with a desired rate, including the exponential one, are obtained. We consider a large class of admissible kernels encompassing the existing ones. Our findings cover the existing stability results in the literature. Finally, a numerical example is given for the validation of the theoretical outcomes.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"11 1","pages":"709 - 728"},"PeriodicalIF":2.2,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86934375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-27DOI: 10.1080/0952813X.2021.1970238
Chilankamol Sunny, Shibu Kumar K. B
ABSTRACT Cluster analysis is the most popular and often the foremost task in big data analytics as it helps in unearthing hidden patterns and trends in data. Traditional single-objective clustering techniques often suffer from accuracy fluctuations especially when applied over data groups of varying densities and imbalanced distribution as well as in the presence of outliers. This paper presents a multi-phase clustering solution that achieves good accuracy measures even in the case of noisy and not- well-separated data (linearly not separable data). The proposed design combines a two-stage Particle Swarm Optimisation (PSO) clustering with K-means logic and a state-of-the-art outlier removal technique. The use of two different optimisation criteria in the two stages of PSO clustering equips the model with the ability to escape local minima traps in the process of convergence. Extensive experiments featuring a wide variety of data have been carried out and the system could achieve accuracy levels as high as 99.9% and an average of 87.4% on notwell-separated data. The model has also been proved to be robust on eight out of the ten datasets of the Fundamental Clustering Problem Suit (FCPS), a benchmark for clustering algorithms.
{"title":"Refined PSO Clustering for Not Well-Separated Data","authors":"Chilankamol Sunny, Shibu Kumar K. B","doi":"10.1080/0952813X.2021.1970238","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1970238","url":null,"abstract":"ABSTRACT Cluster analysis is the most popular and often the foremost task in big data analytics as it helps in unearthing hidden patterns and trends in data. Traditional single-objective clustering techniques often suffer from accuracy fluctuations especially when applied over data groups of varying densities and imbalanced distribution as well as in the presence of outliers. This paper presents a multi-phase clustering solution that achieves good accuracy measures even in the case of noisy and not- well-separated data (linearly not separable data). The proposed design combines a two-stage Particle Swarm Optimisation (PSO) clustering with K-means logic and a state-of-the-art outlier removal technique. The use of two different optimisation criteria in the two stages of PSO clustering equips the model with the ability to escape local minima traps in the process of convergence. Extensive experiments featuring a wide variety of data have been carried out and the system could achieve accuracy levels as high as 99.9% and an average of 87.4% on notwell-separated data. The model has also been proved to be robust on eight out of the ten datasets of the Fundamental Clustering Problem Suit (FCPS), a benchmark for clustering algorithms.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"232 1","pages":"831 - 847"},"PeriodicalIF":2.2,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74979639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-25DOI: 10.1080/0952813X.2021.1966842
M. S, Arockia Raj Y, Abhishek Kumar, V. A. Ashok Kumar, Ankit Kumar, E. D, V. D. A. Kumar, Chitra B, A. Abirami
ABSTRACT The leading cause of mortality is due to cardio vascular disease (CVD) globally. CVD is the major cause of death all over the world for the past years because an estimation of 17.5 million people died from CVD in 2012 and premature death from CVD is 37% below the age of 70. In health-care field, the data generated are large, critical, and more complex and multi-dimensional. In the current situation, the medical professionals working in the field of heart disease can predict up to 67% accuracy but the doctors need an accurate prediction of heart disease. The ultimate goal of this study is to early prediction of CVD by enhancing both predictive analysis and probabilistic classification. Deep learning techniques such as CNN and RNN emulate human cognition and learn from training examples to predict future events. As a result, the future prediction of the cardiovascular disease has been found. The prediction of CVD can be used for the prevention of COVID-19 disease using deep learning algorithm. So, this can be employed to detect the early stage of the disease. The importance of the CVD refers to the conditions like narrowed or blocked blood vessels which may lead to some other diseases like heart attack, chest pain or stroke.
{"title":"Prediction of cardiovascular disease using deep learning algorithms to prevent COVID 19","authors":"M. S, Arockia Raj Y, Abhishek Kumar, V. A. Ashok Kumar, Ankit Kumar, E. D, V. D. A. Kumar, Chitra B, A. Abirami","doi":"10.1080/0952813X.2021.1966842","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1966842","url":null,"abstract":"ABSTRACT The leading cause of mortality is due to cardio vascular disease (CVD) globally. CVD is the major cause of death all over the world for the past years because an estimation of 17.5 million people died from CVD in 2012 and premature death from CVD is 37% below the age of 70. In health-care field, the data generated are large, critical, and more complex and multi-dimensional. In the current situation, the medical professionals working in the field of heart disease can predict up to 67% accuracy but the doctors need an accurate prediction of heart disease. The ultimate goal of this study is to early prediction of CVD by enhancing both predictive analysis and probabilistic classification. Deep learning techniques such as CNN and RNN emulate human cognition and learn from training examples to predict future events. As a result, the future prediction of the cardiovascular disease has been found. The prediction of CVD can be used for the prevention of COVID-19 disease using deep learning algorithm. So, this can be employed to detect the early stage of the disease. The importance of the CVD refers to the conditions like narrowed or blocked blood vessels which may lead to some other diseases like heart attack, chest pain or stroke.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"5 1","pages":"791 - 805"},"PeriodicalIF":2.2,"publicationDate":"2021-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78984720","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-08-21DOI: 10.1080/0952813X.2021.1970237
K. Shrestha, O. H. Alsadoon, A. Alsadoon, Tarik A. Rashid, R. Ali, P. Prasad, Oday D. Jerew
ABSTRACT Accurate classification of Magnetic Resonance Images (MRI) is essential to accurately predict Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) conversion. Meanwhile, deep learning has been successfully implemented to classify and predict dementia disease. However, the accuracy of MRI image classification is low. This paper aims to increase the accuracy and reduce the processing time of classification through Deep Learning Architecture by using Elastic Net Regularisation in Feature Selection. The proposed system consists of Convolutional Neural Network (CNN) to enhance the accuracy of classification and prediction by using Elastic Net Regularisation. Initially, the MRI images are fed into CNN for features extraction through convolutional layers alternate with pooling layers, and then through a fully connected layer. After that, the features extracted are subjected to Principle Component Analysis (PCA) and Elastic Net Regularisation for feature selection. Finally, the selected features are used as an input to Extreme Machine Learning (EML) for the classification of MRI images. The result shows that the accuracy of the proposed solution is better than the current system. In addition to that, the proposed method has improved the classification accuracy by 5% on average and reduced the processing time by 30 ~ 40 seconds on average. The proposed system is focused on improving the accuracy and processing time of MCI converters/non-converters classification. It consists of features extraction, feature selection, and classification using CNN, FreeSurfer, PCA, Elastic Net, and Extreme Machine Learning. Finally, this study enhances the accuracy and the processing time by using Elastic Net Regularisation, which provides important selected features for classification.
{"title":"A novel solution of an elastic net regularisation for dementia knowledge discovery using deep learning","authors":"K. Shrestha, O. H. Alsadoon, A. Alsadoon, Tarik A. Rashid, R. Ali, P. Prasad, Oday D. Jerew","doi":"10.1080/0952813X.2021.1970237","DOIUrl":"https://doi.org/10.1080/0952813X.2021.1970237","url":null,"abstract":"ABSTRACT Accurate classification of Magnetic Resonance Images (MRI) is essential to accurately predict Mild Cognitive Impairment (MCI) to Alzheimer’s Disease (AD) conversion. Meanwhile, deep learning has been successfully implemented to classify and predict dementia disease. However, the accuracy of MRI image classification is low. This paper aims to increase the accuracy and reduce the processing time of classification through Deep Learning Architecture by using Elastic Net Regularisation in Feature Selection. The proposed system consists of Convolutional Neural Network (CNN) to enhance the accuracy of classification and prediction by using Elastic Net Regularisation. Initially, the MRI images are fed into CNN for features extraction through convolutional layers alternate with pooling layers, and then through a fully connected layer. After that, the features extracted are subjected to Principle Component Analysis (PCA) and Elastic Net Regularisation for feature selection. Finally, the selected features are used as an input to Extreme Machine Learning (EML) for the classification of MRI images. The result shows that the accuracy of the proposed solution is better than the current system. In addition to that, the proposed method has improved the classification accuracy by 5% on average and reduced the processing time by 30 ~ 40 seconds on average. The proposed system is focused on improving the accuracy and processing time of MCI converters/non-converters classification. It consists of features extraction, feature selection, and classification using CNN, FreeSurfer, PCA, Elastic Net, and Extreme Machine Learning. Finally, this study enhances the accuracy and the processing time by using Elastic Net Regularisation, which provides important selected features for classification.","PeriodicalId":15677,"journal":{"name":"Journal of Experimental & Theoretical Artificial Intelligence","volume":"15 1","pages":"807 - 829"},"PeriodicalIF":2.2,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73721074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：