Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 3, 2023
《计算机与信息科学》，Vol. 16, No. 3, 2023
{"title":"Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 3","authors":"Chris Lee","doi":"10.5539/cis.v16n3p36","DOIUrl":"https://doi.org/10.5539/cis.v16n3p36","url":null,"abstract":"Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 3, 2023","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"1 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72643293","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}
Sadiku Aminu Sani, Amina Ibrahim, Abuhuraira Ado Musa, M. Dahiru, Muhammad Ahmad Baballe
Traditional methods for evaluating water quality have a number of drawbacks. They need expensive, specialized equipment as well as knowledgeable employees first. Second, data loss may result from human error. Thirdly, because people rather than algorithms will be analyzing the obtained data, these schemes cannot foresee future patterns. Additionally, changes in the characteristics of water may result from the sample transit process. Therefore, it is challenging to consistently check water quality using outdated monitoring techniques. The disadvantages of traditional environmental monitoring techniques have been covered in this study.
{"title":"Drawbacks of Traditional Environmental Monitoring Systems","authors":"Sadiku Aminu Sani, Amina Ibrahim, Abuhuraira Ado Musa, M. Dahiru, Muhammad Ahmad Baballe","doi":"10.5539/cis.v16n3p30","DOIUrl":"https://doi.org/10.5539/cis.v16n3p30","url":null,"abstract":"Traditional methods for evaluating water quality have a number of drawbacks. They need expensive, specialized equipment as well as knowledgeable employees first. Second, data loss may result from human error. Thirdly, because people rather than algorithms will be analyzing the obtained data, these schemes cannot foresee future patterns. Additionally, changes in the characteristics of water may result from the sample transit process. Therefore, it is challenging to consistently check water quality using outdated monitoring techniques. The disadvantages of traditional environmental monitoring techniques have been covered in this study.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"71 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83337061","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}
Basra Farooq Dar, M. Nadeem, S. Khalid, Farzana Riaz, Yasir Mahmood, Ghias Hameed
Cancer Classification & Prediction Is Vitally Important for Cancer Diagnosis. DNA Microarray Technology Has Provided Genetic Data That Has Facilitated Scientists Perform Cancer Research. Traditional Methods of Classification Have Certain Limitations E.G. Traditionally A Proposed DSS Uses A Single Classifier at A Time for Classification or Prediction Purposes. To Increase Classification Accuracy, Reject Option Classifiers Has Been Proposed in Machine Learning Literature. In A Reject Option Classifier, A Rejection Region Is Defined and The Samples Fall in That Region Are Not Classified by The Classifier. The Unclassifiable Samples Are Rejected by Classifier in Order to Improve Classifier’s Accuracy. However, These Rejections Affect the Prediction Rate of The Classifier as Well. To Overcome the Problem of Low Prediction Rates by Increased Rejection of Samples by A Single Classifier, the “Delegating Classifiers” Provide Better Accuracy at Less Rejection Rate. Different Classifiers Such as Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), K Nearest Neighbor (KNN) Etc. Have Been Proposed. Moreover, Traditionally, Same Learner Is Used As “Delegated” And “Delegating” Classifier. This Research Has Investigated the Effects of Using Different Machine Learning Classifiers in Both of The Delegated and Delegating Classifiers, And the Results Obtained Showed That Proposed Method Gives High Accuracy and Increases the Prediction Rate.
{"title":"Improving the Classification Ability of Delegating Classifiers Using Different Supervised Machine Learning Algorithms","authors":"Basra Farooq Dar, M. Nadeem, S. Khalid, Farzana Riaz, Yasir Mahmood, Ghias Hameed","doi":"10.5539/cis.v16n3p22","DOIUrl":"https://doi.org/10.5539/cis.v16n3p22","url":null,"abstract":"Cancer Classification & Prediction Is Vitally Important for Cancer Diagnosis. DNA Microarray Technology Has Provided Genetic Data That Has Facilitated Scientists Perform Cancer Research. Traditional Methods of Classification Have Certain Limitations E.G. Traditionally A Proposed DSS Uses A Single Classifier at A Time for Classification or Prediction Purposes. To Increase Classification Accuracy, Reject Option Classifiers Has Been Proposed in Machine Learning Literature. In A Reject Option Classifier, A Rejection Region Is Defined and The Samples Fall in That Region Are Not Classified by The Classifier. The Unclassifiable Samples Are Rejected by Classifier in Order to Improve Classifier’s Accuracy. However, These Rejections Affect the Prediction Rate of The Classifier as Well. To Overcome the Problem of Low Prediction Rates by Increased Rejection of Samples by A Single Classifier, the “Delegating Classifiers” Provide Better Accuracy at Less Rejection Rate. Different Classifiers Such as Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), K Nearest Neighbor (KNN) Etc. Have Been Proposed. Moreover, Traditionally, Same Learner Is Used As “Delegated” And “Delegating” Classifier. This Research Has Investigated the Effects of Using Different Machine Learning Classifiers in Both of The Delegated and Delegating Classifiers, And the Results Obtained Showed That Proposed Method Gives High Accuracy and Increases the Prediction Rate.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"43 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83301390","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}
Nghia T. Nguyen, Long Luu, Phuong Vo, Sang Nguyen, Cuong T. Do, Ngoc-Thanh Nguyen
Dynamic adaptive streaming over HTTP (DASH) has been widely used in video streaming recently. In DASH, the client downloads video chunks in order from a server. The rate adaptation function at the video client enhances the user?s quality-of-experience (QoE) by choosing a suitable quality level for each video chunk to download based on the network condition. Today networks such as content delivery networks, edge caching networks, content centric networks, etc. usually replicate video contents on multiple cache nodes. We study video streaming from multiple sources in this work. In multi-source streaming, video chunks may arrive out of order due to different conditions of the network paths. Hence, to guarantee a high QoE, the video client needs not only rate adaptation, but also chunk scheduling. Reinforcement learning (RL) has emerged as the state-of-the-art control method in various fields in recent years. This paper proposes two algorithms for streaming from multiple sources: RL-based adaptation with greedy scheduling (RLAGS) and RL-based adaptation and scheduling (RLAS). We also build a simulation environment for training and evaluation. The efficiency of the proposed algorithms is proved via extensive simulations with real-trace data.
{"title":"Reinforcement learning - based adaptation and scheduling methods for multi-source DASH","authors":"Nghia T. Nguyen, Long Luu, Phuong Vo, Sang Nguyen, Cuong T. Do, Ngoc-Thanh Nguyen","doi":"10.2298/csis220927055n","DOIUrl":"https://doi.org/10.2298/csis220927055n","url":null,"abstract":"Dynamic adaptive streaming over HTTP (DASH) has been widely used in video\u0000 streaming recently. In DASH, the client downloads video chunks in order from\u0000 a server. The rate adaptation function at the video client enhances the\u0000 user?s quality-of-experience (QoE) by choosing a suitable quality level for\u0000 each video chunk to download based on the network condition. Today networks\u0000 such as content delivery networks, edge caching networks, content centric\u0000 networks, etc. usually replicate video contents on multiple cache nodes. We\u0000 study video streaming from multiple sources in this work. In multi-source\u0000 streaming, video chunks may arrive out of order due to different conditions\u0000 of the network paths. Hence, to guarantee a high QoE, the video client needs\u0000 not only rate adaptation, but also chunk scheduling. Reinforcement learning\u0000 (RL) has emerged as the state-of-the-art control method in various fields\u0000 in recent years. This paper proposes two algorithms for streaming from\u0000 multiple sources: RL-based adaptation with greedy scheduling (RLAGS) and\u0000 RL-based adaptation and scheduling (RLAS). We also build a simulation\u0000 environment for training and evaluation. The efficiency of the proposed\u0000 algorithms is proved via extensive simulations with real-trace data.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"95 1","pages":"157-173"},"PeriodicalIF":1.4,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80450473","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}
These trends in business librarianship and data librarianship matter for the management of today’s academic libraries and this topic is important to discuss because librarians must respond to the developments in data science and big data. Industry leaders such as Yuanqing Yango, CEO of Lenovo refer to “new IT” and the coming revolution stemming from the usage of smart devices, edge and cloud computing, 5G networks, and (AI) Artificial Intelligence (Lenovo, 2022). Lenovo (2022) researchers undertook a study of 500 Chief Technology Officers (CTOs)from diverse industries to ascertain their perceptions about the future of technology. Both scholars and industry leaders alike agree that the technologies that will dominate will be forged so that humanity can meet the challenges of the future and the control of information will be at the forefront of these changes. Information professionals must learn about and master the technologies that industry leaders are reimagining as innovations that will try to improve our lives because librarianship is becoming increasingly data-driven. Faculty, staff, and students rely on information professionals to help them to understand the role of “new IT” and the opportunities that it creates. We also need more informed professionals because research is data-driven. More decision makers are using big data to make effective organizational decisions. Librarians must be cognizant of the trends that are governing innovations in technology to effectively provide information services to key stakeholders.
{"title":"Identifying and Navigating the Current Trends in Business Librarianship and Data Librarianship","authors":"R. Pistone","doi":"10.5539/cis.v16n3p1","DOIUrl":"https://doi.org/10.5539/cis.v16n3p1","url":null,"abstract":"These trends in business librarianship and data librarianship matter for the management of today’s academic libraries and this topic is important to discuss because librarians must respond to the developments in data science and big data. Industry leaders such as Yuanqing Yango, CEO of Lenovo refer to “new IT” and the coming revolution stemming from the usage of smart devices, edge and cloud computing, 5G networks, and (AI) Artificial Intelligence (Lenovo, 2022). Lenovo (2022) researchers undertook a study of 500 Chief Technology Officers (CTOs)from diverse industries to ascertain their perceptions about the future of technology. Both scholars and industry leaders alike agree that the technologies that will dominate will be forged so that humanity can meet the challenges of the future and the control of information will be at the forefront of these changes. Information professionals must learn about and master the technologies that industry leaders are reimagining as innovations that will try to improve our lives because librarianship is becoming increasingly data-driven. Faculty, staff, and students rely on information professionals to help them to understand the role of “new IT” and the opportunities that it creates. We also need more informed professionals because research is data-driven. More decision makers are using big data to make effective organizational decisions. Librarians must be cognizant of the trends that are governing innovations in technology to effectively provide information services to key stakeholders.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"22 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83058175","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}
This study presents a measure-theoretic approach to estimate the upper bound on the total variation of the di erence between hypergeometric and binomial distributions using the Kullback-Leibler information divergence. The binomial distribution can be used to find the probabilities associated with the binomial experiments. But if the sample size is large relative to the population size, the experiment may not be binomial, and a binomial distribution is not a good choice to find the probabilities associated with the experiment. The hypergeometric probability distribution is the appropriate probability model to be used when the sample size is large compared to the population size. An upper bound for the total variation in the distance between the hypergeometric and binomial distributions is derived using only the sample and population sizes. This upper bound is used to demonstrate how the hypergeometric distribution uniformly converges to the binomial distribution when the population size increases relative to the sample size.
{"title":"On the Convergence of Hypergeometric to Binomial Distributions","authors":"Upul Rupassara, B. Sedai","doi":"10.5539/cis.v16n3p15","DOIUrl":"https://doi.org/10.5539/cis.v16n3p15","url":null,"abstract":"This study presents a measure-theoretic approach to estimate the upper bound on the total variation of the di erence between hypergeometric and binomial distributions using the Kullback-Leibler information divergence. The binomial distribution can be used to find the probabilities associated with the binomial experiments. But if the sample size is large relative to the population size, the experiment may not be binomial, and a binomial distribution is not a good choice to find the probabilities associated with the experiment. The hypergeometric probability distribution is the appropriate probability model to be used when the sample size is large compared to the population size. An upper bound for the total variation in the distance between the hypergeometric and binomial distributions is derived using only the sample and population sizes. This upper bound is used to demonstrate how the hypergeometric distribution uniformly converges to the binomial distribution when the population size increases relative to the sample size.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"257 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76190653","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}
The effect of the educational robot on the motor reaction on some karate skills> have revolutionized various aspects of life, including education and training. Which integrate artificial intelligence with the emotional aspect of the learner. And the overall learning process. By incorporating artificial intelligence, these programs can provide personalized learning experiences and meet individual needs. To calculate the improvement ratio and the difference between the means, as well as the effect size ratio, we can use the following formulas: Average motor reaction time Difference between means= Average motor reaction time Average skill performance time Effect Size Ratio= Difference between means= Standard Deviation Let's calculate these values for each skill: -85.55 Difference between means= -46.42 Difference between means= -88.9 Difference between means= -83.7 Difference between means= 88 Difference between means= -49.762 Effect Size Ratio= Difference between means= Standard Deviation Using the provided standard deviation of 0.078, let's calculate the effect size ratio for each skill: Difference between means= -33.815 Effect Size Ratio= Difference between means= -41.438 Effect Size Ratio= Difference between means= -41.894 Effect Size Ratio= Difference between means= -39.737 Effect Size Ratio= Difference between means= -49.762 Effect Size Ratio= Negative values indicate a decrease in performance. Noting that the results are negative is not evidence of poor results, but to measure the reaction rate and response speed, I need a little time through the treatments, The difference between means is -33.815, The effect size ratio is -433. Indicating a large effect size. The difference between means is -41.438, The effect size ratio is -530. Indicating a large effect size. The difference between means is -41.894, The effect size ratio is -536. Indicating a large effect size. The difference between means is -39.737, The effect size ratio is -509. Indicating a large effect size. The difference between means is -49.762, The effect size ratio is -63.79, indicating a large effect size by incorporating these recommendations.
{"title":"The Effect of the Educational Robot on the Motor Reaction on Some Karate Skills","authors":"Mohammed Ghazi","doi":"10.5539/cis.v16n3p7","DOIUrl":"https://doi.org/10.5539/cis.v16n3p7","url":null,"abstract":"The effect of the educational robot on the motor reaction on some karate skills> have revolutionized various aspects of life, including education and training. Which integrate artificial intelligence with the emotional aspect of the learner. And the overall learning process. By incorporating artificial intelligence, these programs can provide personalized learning experiences and meet individual needs. To calculate the improvement ratio and the difference between the means, as well as the effect size ratio, we can use the following formulas: Average motor reaction time Difference between means= Average motor reaction time Average skill performance time Effect Size Ratio= Difference between means= Standard Deviation Let's calculate these values for each skill: -85.55 Difference between means= -46.42 Difference between means= -88.9 Difference between means= -83.7 Difference between means= 88 Difference between means= -49.762 Effect Size Ratio= Difference between means= Standard Deviation Using the provided standard deviation of 0.078, let's calculate the effect size ratio for each skill: Difference between means= -33.815 Effect Size Ratio= Difference between means= -41.438 Effect Size Ratio= Difference between means= -41.894 Effect Size Ratio= Difference between means= -39.737 Effect Size Ratio= Difference between means= -49.762 Effect Size Ratio= Negative values indicate a decrease in performance. Noting that the results are negative is not evidence of poor results, but to measure the reaction rate and response speed, I need a little time through the treatments, The difference between means is -33.815, The effect size ratio is -433. Indicating a large effect size. The difference between means is -41.438, The effect size ratio is -530. Indicating a large effect size. The difference between means is -41.894, The effect size ratio is -536. Indicating a large effect size. The difference between means is -39.737, The effect size ratio is -509. Indicating a large effect size. The difference between means is -49.762, The effect size ratio is -63.79, indicating a large effect size by incorporating these recommendations.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"15 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82510743","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}
Autodect framework protects management information systems (MIS) and databases from user input SQL injection attacks. This framework overcomes intrusion or penetration into the system by automatically detecting and preventing attacks from the user input end. The attack intentions is also known since it is linked to a proxy database, which has a normal and abnormal code vector profiles that helps to gather information about the intent as well as knowing the areas of interest while conducting the attack. The information about the attack is forwarded to Autodect knowledge base (database), meaning that any successive attacks from the proxy database will be compared to the existing attack pattern logs in the knowledge base, in future this knowledge base-driven database will help organizations to analyze trends of attackers, profile them and deter them. The research evaluated the existing security frameworks used to prevent user input SQL injection; analysis was also done on the factors that lead to the detection of SQL injection. This knowledge-based framework is able to predict the end goal of any injected attack vector. (Known and unknown signatures). Experiments were conducted on true and simulation websites and open-source datasets to analyze the performance and a comparison drawn between the Autodect framework and other existing tools. The research showed that Autodect framework has an accuracy level of 0.98. The research found a gap that all existing tools and frameworks never came up with a standard datasets for sql injection, neither do we have a universally accepted standard data set.
{"title":"Automation-Based User Input Sql Injection Detection and Prevention Framework","authors":"Fredrick Ochieng Okello, D. Kaburu, Ndia G. John","doi":"10.5539/cis.v16n2p51","DOIUrl":"https://doi.org/10.5539/cis.v16n2p51","url":null,"abstract":"Autodect framework protects management information systems (MIS) and databases from user input SQL injection attacks. This framework overcomes intrusion or penetration into the system by automatically detecting and preventing attacks from the user input end. The attack intentions is also known since it is linked to a proxy database, which has a normal and abnormal code vector profiles that helps to gather information about the intent as well as knowing the areas of interest while conducting the attack. The information about the attack is forwarded to Autodect knowledge base (database), meaning that any successive attacks from the proxy database will be compared to the existing attack pattern logs in the knowledge base, in future this knowledge base-driven database will help organizations to analyze trends of attackers, profile them and deter them. The research evaluated the existing security frameworks used to prevent user input SQL injection; analysis was also done on the factors that lead to the detection of SQL injection. This knowledge-based framework is able to predict the end goal of any injected attack vector. (Known and unknown signatures). Experiments were conducted on true and simulation websites and open-source datasets to analyze the performance and a comparison drawn between the Autodect framework and other existing tools. The research showed that Autodect framework has an accuracy level of 0.98. The research found a gap that all existing tools and frameworks never came up with a standard datasets for sql injection, neither do we have a universally accepted standard data set.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"77 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89659890","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}
Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 2, 2023
《计算机与信息科学》，Vol. 16, No. 2, 2023
{"title":"Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 2","authors":"Chris Lee","doi":"10.5539/cis.v16n2p63","DOIUrl":"https://doi.org/10.5539/cis.v16n2p63","url":null,"abstract":"Reviewer Acknowledgements for Computer and Information Science, Vol. 16, No. 2, 2023","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"168 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74865019","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}
Wareef K. Aljohani, Reem Alshehri, Abrar A. Alghamdi, Mashael M. Aljuhani, Dareen A. Alrefaei, R. Aljohani, Abdulqader M. Almars
Many people become missing in Saudi Arabia every day, including children, young people, and the mentally ill as well as the elderly with Alzheimer’s. There are many missing people cases that are still unsolved. In Saudi Arabia, people use social media platforms such as Twitter to report missing people cases. The application of deep learning has been successful in a wide range of fields including computer vision and machine vision. In particular, face recognition techniques are effective in saving time and effort, especially when searching for missing individuals. Hence, the goal of this research is to solve this issue by developing a deep learning-based system for identifying missing individuals. This paper introduces a new system called Suhail. The system has been implemented and developed using Android Studio and open-source libraries such as TensorFlow. First, users or governments can report missing persons by uploading photos. Updates and information will then be shared with the rest of the system’s users (volunteers). Once a volunteer discovers a suspect, they scan their face using camera. Then, our application uses face recognition techniques to compare the suspect's photo with photos from the repository. Finally, once a comparison is found, our application contacts the suspect’s family, informs them of his location and then notifies the police that a missing person has been located. By using our application and face recognition systems, we help families and police locate and reach a missing person which saves time and effort. In this study, 759 participants were enrolled to evaluate the performance of the Suhail system. Engagement, aesthetics, and functionality are used to evaluate the user experience. The results of the experiment show that users enjoy the new features of the application and that the system is simple to use. Moreover, the system would help governments and individuals identify missing people faster.
{"title":"Suhail: A Deep Learning-Based System for Identifying Missing People","authors":"Wareef K. Aljohani, Reem Alshehri, Abrar A. Alghamdi, Mashael M. Aljuhani, Dareen A. Alrefaei, R. Aljohani, Abdulqader M. Almars","doi":"10.5539/cis.v16n2p36","DOIUrl":"https://doi.org/10.5539/cis.v16n2p36","url":null,"abstract":"Many people become missing in Saudi Arabia every day, including children, young people, and the mentally ill as well as the elderly with Alzheimer’s. There are many missing people cases that are still unsolved. In Saudi Arabia, people use social media platforms such as Twitter to report missing people cases. The application of deep learning has been successful in a wide range of fields including computer vision and machine vision. In particular, face recognition techniques are effective in saving time and effort, especially when searching for missing individuals. Hence, the goal of this research is to solve this issue by developing a deep learning-based system for identifying missing individuals. This paper introduces a new system called Suhail. The system has been implemented and developed using Android Studio and open-source libraries such as TensorFlow. First, users or governments can report missing persons by uploading photos. Updates and information will then be shared with the rest of the system’s users (volunteers). Once a volunteer discovers a suspect, they scan their face using camera. Then, our application uses face recognition techniques to compare the suspect's photo with photos from the repository. Finally, once a comparison is found, our application contacts the suspect’s family, informs them of his location and then notifies the police that a missing person has been located. By using our application and face recognition systems, we help families and police locate and reach a missing person which saves time and effort. In this study, 759 participants were enrolled to evaluate the performance of the Suhail system. Engagement, aesthetics, and functionality are used to evaluate the user experience. The results of the experiment show that users enjoy the new features of the application and that the system is simple to use. Moreover, the system would help governments and individuals identify missing people faster.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":"88 1","pages":""},"PeriodicalIF":1.4,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77995757","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：