In recent years, violence detection has gradually turned into an important research area in computer vision, and have proposed many models with high accuracy. However, the unsatisfactory generalization ability of these methods over different datasets. In this paper, the authors propose a violence detection method based on C3D two-stream network for spatiotemporal features. Firstly, the authors preprocess the video data of RGB stream and optical stream respectively. Secondly, the authors feed the data into two C3D networks to extract features from the RGB flow and the optical flow respectively. Third, the authors fuse the features extracted by the two networks to obtain a final prediction result. To testify the performance of the proposed model, four different datasets (two public datasets and two self-built datasets) are selected in this paper. The experimental results show that our model has good generalization ability compared to state-of-the-art methods, since it not only has good ability on large-scale datasets, but also performs well on small-scale datasets.
{"title":"Violence Detection With Two-Stream Neural Network Based on C3D","authors":"zanzan Lu, Xu Xia, Hongrun Wu, Chen Yang","doi":"10.4018/ijcini.287601","DOIUrl":"https://doi.org/10.4018/ijcini.287601","url":null,"abstract":"In recent years, violence detection has gradually turned into an important research area in computer vision, and have proposed many models with high accuracy. However, the unsatisfactory generalization ability of these methods over different datasets. In this paper, the authors propose a violence detection method based on C3D two-stream network for spatiotemporal features. Firstly, the authors preprocess the video data of RGB stream and optical stream respectively. Secondly, the authors feed the data into two C3D networks to extract features from the RGB flow and the optical flow respectively. Third, the authors fuse the features extracted by the two networks to obtain a final prediction result. To testify the performance of the proposed model, four different datasets (two public datasets and two self-built datasets) are selected in this paper. The experimental results show that our model has good generalization ability compared to state-of-the-art methods, since it not only has good ability on large-scale datasets, but also performs well on small-scale datasets.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90677909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA32
N. Visalakshi, S. Shanthi, K. Lakshmi
{"title":"MapReduce-Based Crow Search-Adopted Partitional Clustering Algorithms for Handling Large-Scale Data","authors":"N. Visalakshi, S. Shanthi, K. Lakshmi","doi":"10.4018/IJCINI.20211001.OA32","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA32","url":null,"abstract":"","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74551018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the limited search space in the existing performance optimization ap-proaches at software architectures of cloud applications (SAoCA) level, it is difficult for these methods to obtain the cloud resource usage scheme with optimal cost-performance ratio. Aiming at this problem, this paper firstly de-fines a performance optimization model called CAPOM that can enlarge the search space effectively. Secondly, an efficient differential evolutionary op-timization algorithm named MODE4CA is proposed to solve the CAPOM model by defining evolutionary operators with strategy pool and repair mechanism. Further, a method for optimizing performance at SAoCA level, called POM4CA is derived. Finally, two problem instances with different sizes are taken to conduct the experiments for comparing POM4CA with the current representative method under the light and heavy workload. The ex-perimental results show that POM4CA method can obtain better response time and spend less cost of cloud resources.
{"title":"A Multi-Objective Differential Evolutionary Optimization Method for Performance Optimization of Cloud Application","authors":"Xin Du, Youcong Ni, Peng Ye, Ruliang Xiao","doi":"10.4018/ijcini.295808","DOIUrl":"https://doi.org/10.4018/ijcini.295808","url":null,"abstract":"Due to the limited search space in the existing performance optimization ap-proaches at software architectures of cloud applications (SAoCA) level, it is difficult for these methods to obtain the cloud resource usage scheme with optimal cost-performance ratio. Aiming at this problem, this paper firstly de-fines a performance optimization model called CAPOM that can enlarge the search space effectively. Secondly, an efficient differential evolutionary op-timization algorithm named MODE4CA is proposed to solve the CAPOM model by defining evolutionary operators with strategy pool and repair mechanism. Further, a method for optimizing performance at SAoCA level, called POM4CA is derived. Finally, two problem instances with different sizes are taken to conduct the experiments for comparing POM4CA with the current representative method under the light and heavy workload. The ex-perimental results show that POM4CA method can obtain better response time and spend less cost of cloud resources.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84966503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA28
Jothi Prabha Appadurai, R. Bhargavi
Dyslexia is a learning disorder that can cause difficulties in reading or writing. Dyslexia is not a visual problem, but many dyslexics have impaired magnocellular system, which causes poor eye control. Eye-trackers are used to track eye movements. This research work proposes a set of significant eye movement features that are used to build a predictive model for dyslexia. Fixation and saccade eye events are detected using the dispersion-threshold and velocity-threshold algorithms. Various machine learning models are experimented. Validation is done on 185 subjects using 10-fold cross-validation. Velocity-based features gave high accuracy compared to statistical and dispersion features. Highest accuracy of 96% was achieved using the hybrid kernel support vector machine-particle swarm optimization model followed by the xtreme gradient boosting model with an accuracy of 95%. The best set of features are the first fixation start time, average fixation saccade duration, the total number of fixations, total number of saccades, and ratio between saccades and fixations.
{"title":"Eye Movement Feature Set and Predictive Model for Dyslexia: Feature Set and Predictive Model for Dyslexia","authors":"Jothi Prabha Appadurai, R. Bhargavi","doi":"10.4018/IJCINI.20211001.OA28","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA28","url":null,"abstract":"Dyslexia is a learning disorder that can cause difficulties in reading or writing. Dyslexia is not a visual problem, but many dyslexics have impaired magnocellular system, which causes poor eye control. Eye-trackers are used to track eye movements. This research work proposes a set of significant eye movement features that are used to build a predictive model for dyslexia. Fixation and saccade eye events are detected using the dispersion-threshold and velocity-threshold algorithms. Various machine learning models are experimented. Validation is done on 185 subjects using 10-fold cross-validation. Velocity-based features gave high accuracy compared to statistical and dispersion features. Highest accuracy of 96% was achieved using the hybrid kernel support vector machine-particle swarm optimization model followed by the xtreme gradient boosting model with an accuracy of 95%. The best set of features are the first fixation start time, average fixation saccade duration, the total number of fixations, total number of saccades, and ratio between saccades and fixations.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86085001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA45
H. Hiraishi
This paper describes two types of a cognitive support tools for a pre-performance routine (PPR) in a darts game. PPRs entail the performance of determined motions before an action and are often executed in sports for the purpose of removing stress or raising concentration. The concentration-stabilizing phenomenon was discovered by the previous research, and it determined that the phenomenon appears more conspicuous in the case of experts and PPRs. A tool using a simple brainwaves sensor has been designed and shows us the current status of concentration and notifies us of the concentration-stabilizing phenomenon on a tablet computer. Another tool has been developed on a smart watch with a heart rate sensor. The smart watch indicated heartbeat as a “beep” sound to a user. It was designed based on a result that indicated that darts game scores tend to improve by throwing immediately after a heartbeat. The effectiveness of the tools were verified in several experiments.
{"title":"Cognitive Support Tools for a Pre-Performance Routine in a Darts Game","authors":"H. Hiraishi","doi":"10.4018/IJCINI.20211001.OA45","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA45","url":null,"abstract":"This paper describes two types of a cognitive support tools for a pre-performance routine (PPR) in a darts game. PPRs entail the performance of determined motions before an action and are often executed in sports for the purpose of removing stress or raising concentration. The concentration-stabilizing phenomenon was discovered by the previous research, and it determined that the phenomenon appears more conspicuous in the case of experts and PPRs. A tool using a simple brainwaves sensor has been designed and shows us the current status of concentration and notifies us of the concentration-stabilizing phenomenon on a tablet computer. Another tool has been developed on a smart watch with a heart rate sensor. The smart watch indicated heartbeat as a “beep” sound to a user. It was designed based on a result that indicated that darts game scores tend to improve by throwing immediately after a heartbeat. The effectiveness of the tools were verified in several experiments.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79624070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/ijcini.20211001.oa1
Sindhu Sumukha, C. GeorgePhilip
Vehicle crashes occur because of numerous factors. It leads to loss of lives and permanent incapacity. The budgetary expenses of both individuals as well as for the nation are influenced by vehicle crashes. According to Road accident statistics, a total of 464910 road accidents were reported in India, claiming 1,47,913 lives and causing injuries to 4,70,975 persons every year. In this work, the UK data set sourced from Kaggle is used. For the study, 17 attributes and 35k records of the year 2015 are considered. The data set is imbalanced, so to balance out the data, the over-sampling technique is used. Random Forest, Decision tree, Logistic Regression, and Gradient Naïve Bayes algorithms are used to predict the severity of Accidents. To evaluate the model, performance measures like Accuracy, Precision, Recall, F1-Score are used. When Accuracy, Precision, F1-Score performance measure is considered Random Forest yielded the best result. When Recall performance measure is used, Random forest for Fatal, Decision Trees for Serious, Logistic regression for Slight yielded the best result.
{"title":"Analysis of Traffic Accident Features and Crash Severity Prediction","authors":"Sindhu Sumukha, C. GeorgePhilip","doi":"10.4018/ijcini.20211001.oa1","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa1","url":null,"abstract":"Vehicle crashes occur because of numerous factors. It leads to loss of lives and permanent incapacity. The budgetary expenses of both individuals as well as for the nation are influenced by vehicle crashes. According to Road accident statistics, a total of 464910 road accidents were reported in India, claiming 1,47,913 lives and causing injuries to 4,70,975 persons every year. In this work, the UK data set sourced from Kaggle is used. For the study, 17 attributes and 35k records of the year 2015 are considered. The data set is imbalanced, so to balance out the data, the over-sampling technique is used. Random Forest, Decision tree, Logistic Regression, and Gradient Naïve Bayes algorithms are used to predict the severity of Accidents. To evaluate the model, performance measures like Accuracy, Precision, Recall, F1-Score are used. When Accuracy, Precision, F1-Score performance measure is considered Random Forest yielded the best result. When Recall performance measure is used, Random forest for Fatal, Decision Trees for Serious, Logistic regression for Slight yielded the best result.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80947414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/ijcini.20211001.oa47
Pham Van Hai, Eloanyi Samson Amaechi
Conventional methods used in brain tumors detection, diagnosis, and classification such as magnetic resonance imaging and computed tomography scanning technologies are unbridged in their results. This paper presents a proposed model combination, convolutional neural networks with fuzzy rules in the detection and classification of medical imaging such as healthy brain cell and tumors brain cells. This model contributes fully on the automatic classification and detection medical imaging such as brain tumors, heart diseases, breast cancers, HIV and FLU. The experimental result of the proposed model shows overall accuracy of 97.6%, which indicates that the proposed method achieves improved performance than the other current methods in the literature such as [classification of tumors in human brain MRI using wavelet and support vector machine 94.7%, and deep convolutional neural networks with transfer learning for automated brain image classification 95.0%], uses in the detection, diagnosis, and classification of medical imaging decision supports.
{"title":"Convolutional Neural Network Integrated With Fuzzy Rules for Decision Making in Brain Tumor Diagnosis","authors":"Pham Van Hai, Eloanyi Samson Amaechi","doi":"10.4018/ijcini.20211001.oa47","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa47","url":null,"abstract":"Conventional methods used in brain tumors detection, diagnosis, and classification such as magnetic resonance imaging and computed tomography scanning technologies are unbridged in their results. This paper presents a proposed model combination, convolutional neural networks with fuzzy rules in the detection and classification of medical imaging such as healthy brain cell and tumors brain cells. This model contributes fully on the automatic classification and detection medical imaging such as brain tumors, heart diseases, breast cancers, HIV and FLU. The experimental result of the proposed model shows overall accuracy of 97.6%, which indicates that the proposed method achieves improved performance than the other current methods in the literature such as [classification of tumors in human brain MRI using wavelet and support vector machine 94.7%, and deep convolutional neural networks with transfer learning for automated brain image classification 95.0%], uses in the detection, diagnosis, and classification of medical imaging decision supports.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74900621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA25
Qing Zhang, Ruwang Jiao, Sanyou Zeng, Z. Zeng
{"title":"Balancing Exploration and Exploitation With Decomposition-Based Dynamic Multi-Objective Evolutionary Algorithm","authors":"Qing Zhang, Ruwang Jiao, Sanyou Zeng, Z. Zeng","doi":"10.4018/IJCINI.20211001.OA25","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA25","url":null,"abstract":"","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79319035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/ijcini.20211001.oa18
V. Biju, C. Prashanth
The study's objective is to identify the non-linear relationship of differentially expressed genes that vary in terms of the tumour and normal tissue and correct for any variations among the RNA-Seq experiment focused on Oral squamous cell carcinoma samples from patients. A Laplacian Likelihood version of the Generalized Additive Model is proposed and compared with the regular GAM models in terms of the non-linear fitting. The Non-Linear machine learning approach of Laplacian Likelihood-based GAM could complement RNA-Seq Analysis mainly to interpret, validate, and prioritize the patient samples data of differentially expressed genes. The analysis eases the standard parametric presumption and helps discover complexity in the association between the dependent and the independent variable and parameter smoothing that might otherwise be neglected. Concurvity, standard error, deviance, and other statistical verification have been carried out to confirm Laplacian Likelihood-based GAM efficiency.
{"title":"Laplacian Likelihood-Based Generalized Additive Model for RNA-Seq Analysis of Oral Squamous Cell Carcinoma","authors":"V. Biju, C. Prashanth","doi":"10.4018/ijcini.20211001.oa18","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa18","url":null,"abstract":"The study's objective is to identify the non-linear relationship of differentially expressed genes that vary in terms of the tumour and normal tissue and correct for any variations among the RNA-Seq experiment focused on Oral squamous cell carcinoma samples from patients. A Laplacian Likelihood version of the Generalized Additive Model is proposed and compared with the regular GAM models in terms of the non-linear fitting. The Non-Linear machine learning approach of Laplacian Likelihood-based GAM could complement RNA-Seq Analysis mainly to interpret, validate, and prioritize the patient samples data of differentially expressed genes. The analysis eases the standard parametric presumption and helps discover complexity in the association between the dependent and the independent variable and parameter smoothing that might otherwise be neglected. Concurvity, standard error, deviance, and other statistical verification have been carried out to confirm Laplacian Likelihood-based GAM efficiency.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80480235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-01DOI: 10.4018/ijcini.20211001.oa30
Rangzhong Wu, Caie Hu, Z. Zeng, Sanyou Zeng, Jawdat S. Alkasassbeh
Most evolutionary optimization algorithms have already been used for antenna design and shown promising results on improving the performance of the antenna. However, for many real-world antenna optimization problems, they are difficult to solve in that there are highly constrained and multimodal difficulty. These difficulties impede the development of antenna design. In this paper, an elliptical slot microstrip patch antenna design with these difficulties is modeled as a constrained optimization problem (COP). To address the problem, a Dynamic Constrained Multiobjective Optimization Evolutionary Algorithm(DCMOEA) is used. The experimental results show that the optimum antenna with satisfying the design requirement is obtained, and as well as we find the radiation patch should be a whole ellipse instead of subtracting with two ellipses.
{"title":"Elliptical Slot Microstrip Patch Antenna Design Based on a Dynamic Constrained Multiobjective Optimization Evolutionary Algorithm","authors":"Rangzhong Wu, Caie Hu, Z. Zeng, Sanyou Zeng, Jawdat S. Alkasassbeh","doi":"10.4018/ijcini.20211001.oa30","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa30","url":null,"abstract":"Most evolutionary optimization algorithms have already been used for antenna design and shown promising results on improving the performance of the antenna. However, for many real-world antenna optimization problems, they are difficult to solve in that there are highly constrained and multimodal difficulty. These difficulties impede the development of antenna design. In this paper, an elliptical slot microstrip patch antenna design with these difficulties is modeled as a constrained optimization problem (COP). To address the problem, a Dynamic Constrained Multiobjective Optimization Evolutionary Algorithm(DCMOEA) is used. The experimental results show that the optimum antenna with satisfying the design requirement is obtained, and as well as we find the radiation patch should be a whole ellipse instead of subtracting with two ellipses.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":null,"pages":null},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86350324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：