Pub Date : 2021-10-01DOI: 10.4018/IJCINI.20211001.OA41
R. Lebsir, Abdesslem Layeb, F. Tahi
This paper presents a strategy to tackle the multiple sequence alignment (MSA) problem, which is one of the most important tasks in the biological sequence analysis. Its role is to align the sequences in their entirety to derive relationships and common characteristics between a set of protein or nucleotide sequences. The MSA problem was proved to be an NP-Hard problem. The proposed strategy incorporates a new idea based on the well-known divide-and-conquer paradigm. This paper presents a novel method of clustering sequences as a preliminary step to improve the final alignment; this decomposition can be used as an optimization procedure with any MSA aligner to explore promising alignments of the search space. In their solution, the authors proposed to align the clusters in a parallel and distributed way in order to benefit from parallel architectures. The strategy was tested using classical benchmarks like BAliBASE, Sabre, Prefab4, and Oxm, and the experimental results show that it gives good results by comparing to the other aligners.
{"title":"A Greedy Clustering Algorithm for Multiple Sequence Alignment","authors":"R. Lebsir, Abdesslem Layeb, F. Tahi","doi":"10.4018/IJCINI.20211001.OA41","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA41","url":null,"abstract":"This paper presents a strategy to tackle the multiple sequence alignment (MSA) problem, which is one of the most important tasks in the biological sequence analysis. Its role is to align the sequences in their entirety to derive relationships and common characteristics between a set of protein or nucleotide sequences. The MSA problem was proved to be an NP-Hard problem. The proposed strategy incorporates a new idea based on the well-known divide-and-conquer paradigm. This paper presents a novel method of clustering sequences as a preliminary step to improve the final alignment; this decomposition can be used as an optimization procedure with any MSA aligner to explore promising alignments of the search space. In their solution, the authors proposed to align the clusters in a parallel and distributed way in order to benefit from parallel architectures. The strategy was tested using classical benchmarks like BAliBASE, Sabre, Prefab4, and Oxm, and the experimental results show that it gives good results by comparing to the other aligners.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"46 1","pages":"1-17"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75927404","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}
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":"108 1","pages":"1-17"},"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.oa7
O. Popova, B. Popov, V. Karandey, V. Afanasyev
Today, effective management of information requires an in-depth study of its internal organization. The structural organization of information affects the efficiency of choosing a method for solving the problem and the qualitative presentation of information about the subject area. Therefore, the article proposes a new semiotic structural approach to assessing the structuredness of information in a subject area, as well as theoretical, practical, and general logical methods for studying the process of search research as a single system. The authors proposed and investigated the structured information coeffi-cient, which the authors propose to consider in several aspects - with respect to the search research model presented by the traditional algorithm, and the structured subject area. The article presents theo-retical positions, derives the formula of coefficients for different cases, carries out calculations on the example of the subject area “optimization methods”, constructs graphs based on the calculated data, and draws conclusions.
{"title":"Obtaining the Dynamic Coefficients of Structuredness for Assessing a Domain","authors":"O. Popova, B. Popov, V. Karandey, V. Afanasyev","doi":"10.4018/ijcini.20211001.oa7","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa7","url":null,"abstract":"Today, effective management of information requires an in-depth study of its internal organization. The structural organization of information affects the efficiency of choosing a method for solving the problem and the qualitative presentation of information about the subject area. Therefore, the article proposes a new semiotic structural approach to assessing the structuredness of information in a subject area, as well as theoretical, practical, and general logical methods for studying the process of search research as a single system. The authors proposed and investigated the structured information coeffi-cient, which the authors propose to consider in several aspects - with respect to the search research model presented by the traditional algorithm, and the structured subject area. The article presents theo-retical positions, derives the formula of coefficients for different cases, carries out calculations on the example of the subject area “optimization methods”, constructs graphs based on the calculated data, and draws conclusions.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"24 1","pages":"1-24"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81645488","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.OA42
Chen Zhao, T. Utsuro, Yasuhide Kawada
This paper addresses the problem of automatic recognition of out-of-topic documents from a small set of similar documents that are expected to be on some common topic. The objective is to remove documents of noise from a set. A topic model based classification framework is proposed for the task of discovering out-of-topic documents. This paper introduces a new concept of annotated {it search engine suggests}, where this paper takes whichever search queries were used to search for a page as representations of content in that page. This paper adopted word embedding to create distributed representation of words and documents, and perform similarity comparison on search engine suggests. It is shown that search engine suggests can be highly accurate semantic representations of textual content and demonstrate that our document analysis algorithm using such representation for relevance measure gives satisfactory performance in terms of in-topic content filtering compared to the baseline technique of topic probability ranking.
{"title":"A Classification Framework of Identifying Major Documents With Search Engine Suggestions and Unsupervised Subtopic Clustering","authors":"Chen Zhao, T. Utsuro, Yasuhide Kawada","doi":"10.4018/IJCINI.20211001.OA42","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA42","url":null,"abstract":"This paper addresses the problem of automatic recognition of out-of-topic documents from a small set of similar documents that are expected to be on some common topic. The objective is to remove documents of noise from a set. A topic model based classification framework is proposed for the task of discovering out-of-topic documents. This paper introduces a new concept of annotated {it search engine suggests}, where this paper takes whichever search queries were used to search for a page as representations of content in that page. This paper adopted word embedding to create distributed representation of words and documents, and perform similarity comparison on search engine suggests. It is shown that search engine suggests can be highly accurate semantic representations of textual content and demonstrate that our document analysis algorithm using such representation for relevance measure gives satisfactory performance in terms of in-topic content filtering compared to the baseline technique of topic probability ranking.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"3 1","pages":"1-15"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82076285","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.oa5
Arnab MITRA
Enhanced data security and privacy are one of the major concerns in today’s digital society. The role of Primes towards the enhancements of data security and privacy is undeniable. Though several prime generations were presented, yet a cost effective and an easy to implement generation of Prime sequence should always have an advantage targeting real life applications. Hence, prime sequence generation using Cellular Automata (CA) is presented in this article as CA based modelling are easy to implement at the cost of flip-flops. The main contribution of this research is to explore the natural sequence of primes (i.e., primes A000040) with a special class of group CA, at fixed boundary environment; which may potentially be used as a Prime source towards the enhancements of data security and privacy. Experimental results confirm that the first 50 members of A000040 series may be explored at automata size 8 only. Detailed investigations towards the CA configuration and its dynamics in view of the generation of prime A000040 sequence, are also presented in this article.
{"title":"On the Exploration of the Natural Sequence of Primes With Cellular Automata Targeting Enhanced Data Security and Privacy","authors":"Arnab MITRA","doi":"10.4018/ijcini.20211001.oa5","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa5","url":null,"abstract":"Enhanced data security and privacy are one of the major concerns in today’s digital society. The role of Primes towards the enhancements of data security and privacy is undeniable. Though several prime generations were presented, yet a cost effective and an easy to implement generation of Prime sequence should always have an advantage targeting real life applications. Hence, prime sequence generation using Cellular Automata (CA) is presented in this article as CA based modelling are easy to implement at the cost of flip-flops. The main contribution of this research is to explore the natural sequence of primes (i.e., primes A000040) with a special class of group CA, at fixed boundary environment; which may potentially be used as a Prime source towards the enhancements of data security and privacy. Experimental results confirm that the first 50 members of A000040 series may be explored at automata size 8 only. Detailed investigations towards the CA configuration and its dynamics in view of the generation of prime A000040 sequence, are also presented in this article.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"57 1","pages":"1-18"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82373099","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.OA35
Vishal Vishnoi, S. Tiwari, R. Singla
{"title":"Controller Design for Temperature Control of MISO Water Tank System: Simulation Studies","authors":"Vishal Vishnoi, S. Tiwari, R. Singla","doi":"10.4018/IJCINI.20211001.OA35","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA35","url":null,"abstract":"","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"75 1","pages":"1-13"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83810529","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.OA39
Nagaraju Devarakonda, Ravi Kumar Saidala, Raviteja Kamarajugadda
In data analysis applications for extraction of useful knowledge, clustering plays an important role. The major shortcoming of traditional clustering algorithms is exhibiting poor performance in solving complex data cluster problems. This research paper introduces a novel hybrid optimization technique-based clustering approach. This paper is designed with two main objectives: designing efficient function optimization algorithm and developing advanced data clustering approach. In achieving the first objective, the standard TOA is first enhanced by hybridizing with Lévy flight trajectory and benchmarked on 23 functions. A new clustering approach is developed by conjoining k-means algorithm and Lévy flight TOA. The numerical complexity of the proposed novel clustering approach was tested on 10 UCI clustering datasets and four web document cluster problems. Several simulation experiments were conducted and an analysis of the results was done. The obtained graphical and statistical analysis reveals that the proposed novel clustering approach yields better quality clusters. based hybrid TOA for solving global function optimization problems as well as different data cluster problems. From the simulation experiments and analysis the proposed clustering approach is a suitable addition to clustering domains for solving complex data clustering problems. The NFL theorem logically proved that there is not any single optimization technique existed that can solve all sorts of optimization problems. In this work Lévy flight trajectory algorithm was used to enhance the standard TOA. In future work, other performance boosting up methods can be investigated. The future research also can development of new and novel nature-inspired Metaheuristics.
{"title":"A Hybrid Between TOA and Lévy Flight Trajectory for Solving Different Cluster Problems","authors":"Nagaraju Devarakonda, Ravi Kumar Saidala, Raviteja Kamarajugadda","doi":"10.4018/IJCINI.20211001.OA39","DOIUrl":"https://doi.org/10.4018/IJCINI.20211001.OA39","url":null,"abstract":"In data analysis applications for extraction of useful knowledge, clustering plays an important role. The major shortcoming of traditional clustering algorithms is exhibiting poor performance in solving complex data cluster problems. This research paper introduces a novel hybrid optimization technique-based clustering approach. This paper is designed with two main objectives: designing efficient function optimization algorithm and developing advanced data clustering approach. In achieving the first objective, the standard TOA is first enhanced by hybridizing with Lévy flight trajectory and benchmarked on 23 functions. A new clustering approach is developed by conjoining k-means algorithm and Lévy flight TOA. The numerical complexity of the proposed novel clustering approach was tested on 10 UCI clustering datasets and four web document cluster problems. Several simulation experiments were conducted and an analysis of the results was done. The obtained graphical and statistical analysis reveals that the proposed novel clustering approach yields better quality clusters. based hybrid TOA for solving global function optimization problems as well as different data cluster problems. From the simulation experiments and analysis the proposed clustering approach is a suitable addition to clustering domains for solving complex data clustering problems. The NFL theorem logically proved that there is not any single optimization technique existed that can solve all sorts of optimization problems. In this work Lévy flight trajectory algorithm was used to enhance the standard TOA. In future work, other performance boosting up methods can be investigated. The future research also can development of new and novel nature-inspired Metaheuristics.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"3 1","pages":"1-25"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87498113","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.oa14
Kai Wang, Shasha Lv, Yongzhen Ke, Jing Guo, Rui Wang
Image aesthetic quality assessment has been a hot research topic in the field of image analysis during the last decade. Most recently, people have proposed comment type assessment to describe the aesthetics of an image using text automatically. However, existing works have rarely considered the quality of the aesthetic description. In this work, we propose a novel neural image aesthetic description network framework, named Deep Image Aesthetic Reviewer (DIAReviewer), based on Semantic Addition Transformer Model, the learning of Residual Network, and the Attention Mechanism in a single framework. Beyond that, we design a Semantic Addition module to compromise the image feature and semantic information to focus on the comment quality, such as fluency and complexity. We introduce a new image dataset named Aesthetic Review Dataset (ARD), which contains one or more aesthetic comments for each image. Finally, the experimental results on ARD show that our model outperforms other methods in content complexity and sentence fluency of aesthetic descriptions.
{"title":"Image Aesthetic Description Based on Semantic Addition Transformer Model","authors":"Kai Wang, Shasha Lv, Yongzhen Ke, Jing Guo, Rui Wang","doi":"10.4018/ijcini.20211001.oa14","DOIUrl":"https://doi.org/10.4018/ijcini.20211001.oa14","url":null,"abstract":"Image aesthetic quality assessment has been a hot research topic in the field of image analysis during the last decade. Most recently, people have proposed comment type assessment to describe the aesthetics of an image using text automatically. However, existing works have rarely considered the quality of the aesthetic description. In this work, we propose a novel neural image aesthetic description network framework, named Deep Image Aesthetic Reviewer (DIAReviewer), based on Semantic Addition Transformer Model, the learning of Residual Network, and the Attention Mechanism in a single framework. Beyond that, we design a Semantic Addition module to compromise the image feature and semantic information to focus on the comment quality, such as fluency and complexity. We introduce a new image dataset named Aesthetic Review Dataset (ARD), which contains one or more aesthetic comments for each image. Finally, the experimental results on ARD show that our model outperforms other methods in content complexity and sentence fluency of aesthetic descriptions.","PeriodicalId":43637,"journal":{"name":"International Journal of Cognitive Informatics and Natural Intelligence","volume":"34 1","pages":"1-14"},"PeriodicalIF":0.9,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89565745","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":"13 1","pages":"1-15"},"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.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":"31 1","pages":"1-18"},"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}
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：