Pub Date : 2021-06-26DOI: 10.5121/csit.2021.110910
Mohamed N. Sweilam, N. Tolstokulakov
Depth estimation has made great progress in the last few years due to its applications in robotics science and computer vision. Various methods have been developed and implemented to estimate the depth, without flickers and missing holes. Despite this progress, it is still one of the main challenges for researchers, especially for the video applications which have more difficulties such as the complexity of the neural network which affects the run time. Moreover to use such input like monocular video for depth estimation is considered an attractive idea, particularly for hand-held devices such as mobile phones, nowadays they are very popular for capturing pictures and videos. Here in this work, we focus on enhancing the existing consistent depth estimation for monocular videos approach to be with less usage of memory and with using less number of parameters without having a significant reduction in the quality of the depth estimation.
{"title":"Enhancement of Consistent Depth Estimation for Monocular Videos Approach","authors":"Mohamed N. Sweilam, N. Tolstokulakov","doi":"10.5121/csit.2021.110910","DOIUrl":"https://doi.org/10.5121/csit.2021.110910","url":null,"abstract":"Depth estimation has made great progress in the last few years due to its applications in robotics science and computer vision. Various methods have been developed and implemented to estimate the depth, without flickers and missing holes. Despite this progress, it is still one of the main challenges for researchers, especially for the video applications which have more difficulties such as the complexity of the neural network which affects the run time. Moreover to use such input like monocular video for depth estimation is considered an attractive idea, particularly for hand-held devices such as mobile phones, nowadays they are very popular for capturing pictures and videos. Here in this work, we focus on enhancing the existing consistent depth estimation for monocular videos approach to be with less usage of memory and with using less number of parameters without having a significant reduction in the quality of the depth estimation.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42425149","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 : 2021-06-26DOI: 10.5121/csit.2021.110911
T. Xiao, Yu Sun
Drowsy driving is lethal- 793 died from accidents related to drowsy driving and 91000 accidents related to drowsy driving occurred [1]. However, drowsy driving and accidents related to drowsy driving are preventable. In this paper, we address the problem through an application that uses artificial intelligence to detect the eye openness of the user. The application can detect the eyes of the user via computer vision. Based on the user’s eye openness and frequencies, the sleepy driving condition can be inferred by this application. We applied our application to actual driving environments on the highway, both day and night, as well as within a normal control situation using a qualitative evaluation approach. The result shows that it is 88% effective during the day and 75% effective during nighttime. This result reveals effectiveness and accuracy of detection during daytime application under controlled testing, which is more flexible and efficient comparing to previous works. Effectiveness and accuracy for nighttime detection and detections with the presence of other distractions can be further improved.
{"title":"An Intelligent Mobile App to Detect Drowsy Driving with Artificial Intelligence","authors":"T. Xiao, Yu Sun","doi":"10.5121/csit.2021.110911","DOIUrl":"https://doi.org/10.5121/csit.2021.110911","url":null,"abstract":"Drowsy driving is lethal- 793 died from accidents related to drowsy driving and 91000 accidents related to drowsy driving occurred [1]. However, drowsy driving and accidents related to drowsy driving are preventable. In this paper, we address the problem through an application that uses artificial intelligence to detect the eye openness of the user. The application can detect the eyes of the user via computer vision. Based on the user’s eye openness and frequencies, the sleepy driving condition can be inferred by this application. We applied our application to actual driving environments on the highway, both day and night, as well as within a normal control situation using a qualitative evaluation approach. The result shows that it is 88% effective during the day and 75% effective during nighttime. This result reveals effectiveness and accuracy of detection during daytime application under controlled testing, which is more flexible and efficient comparing to previous works. Effectiveness and accuracy for nighttime detection and detections with the presence of other distractions can be further improved.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48003364","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 : 2021-06-26DOI: 10.5121/csit.2021.110901
V. Tregubov
The article describes applications of using voice recognition technology based on artificial intelligence to the educational process. The author presents a comparative analysis of existing examples artificial intelligence in the educational process. Artificial intelligence uses in specialized software it makes educational process more convenient for both the students and the teachers. There is a description of an application “Academic phrase bank" developed by author. The application consists of two specialising actions for Google assistant. The application allows to increase academic vocabulary, train of creating grammatically correct academic expressions, and memorize templates of academic phrases. In active mode, this application helps to create correct phrases of academic English and improve the abilities of understanding English speech.
{"title":"Voice Assistants with Artificial Intelligence for Improving Academic English","authors":"V. Tregubov","doi":"10.5121/csit.2021.110901","DOIUrl":"https://doi.org/10.5121/csit.2021.110901","url":null,"abstract":"The article describes applications of using voice recognition technology based on artificial intelligence to the educational process. The author presents a comparative analysis of existing examples artificial intelligence in the educational process. Artificial intelligence uses in specialized software it makes educational process more convenient for both the students and the teachers. There is a description of an application “Academic phrase bank\" developed by author. The application consists of two specialising actions for Google assistant. The application allows to increase academic vocabulary, train of creating grammatically correct academic expressions, and memorize templates of academic phrases. In active mode, this application helps to create correct phrases of academic English and improve the abilities of understanding English speech.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45180058","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 : 2021-06-19DOI: 10.5121/csit.2021.110811
Nilamadhaba Mohapatra, Namrata Sarraf, S. Sahu
Transformer Models have taken over most of the Natural language Inference tasks. In recent times they have proved to beat several benchmarks. Chunking means splitting the sentences into tokens and then grouping them in a meaningful way. Chunking is a task that has gradually moved from POS tag-based statistical models to neural nets using Language models such as LSTM, Bidirectional LSTMs, attention models, etc. Deep neural net Models are deployed indirectly for classifying tokens as different tags defined under Named Recognition Tasks. Later these tags are used in conjunction with pointer frameworks for the final chunking task. In our paper, we propose an Ensemble Model using a fine-tuned Transformer Model and a recurrent neural network model together to predict tags and chunk substructures of a sentence. We analyzed the shortcomings of the transformer models in predicting different tags and then trained the BILSTM+CNN accordingly to compensate for the same.
{"title":"Ensemble Model for Chunking","authors":"Nilamadhaba Mohapatra, Namrata Sarraf, S. Sahu","doi":"10.5121/csit.2021.110811","DOIUrl":"https://doi.org/10.5121/csit.2021.110811","url":null,"abstract":"Transformer Models have taken over most of the Natural language Inference tasks. In recent times they have proved to beat several benchmarks. Chunking means splitting the sentences into tokens and then grouping them in a meaningful way. Chunking is a task that has gradually moved from POS tag-based statistical models to neural nets using Language models such as LSTM, Bidirectional LSTMs, attention models, etc. Deep neural net Models are deployed indirectly for classifying tokens as different tags defined under Named Recognition Tasks. Later these tags are used in conjunction with pointer frameworks for the final chunking task. In our paper, we propose an Ensemble Model using a fine-tuned Transformer Model and a recurrent neural network model together to predict tags and chunk substructures of a sentence. We analyzed the shortcomings of the transformer models in predicting different tags and then trained the BILSTM+CNN accordingly to compensate for the same.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47989723","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 : 2021-06-19DOI: 10.5121/csit.2021.110805
P. Pospiech, Aleksander Marianski, M. Kedziora
The paper presents decentralized voting scheme for verified users while maintaining their anonymity. A blockchain network was applied, which is a decentralized and distributed database based on the Peer-to-Peer architecture. During the implementation, the Ethereum network was used. Thanks to this, it is possible to code the terms of the contract required to perform the transaction. Ethereum and the use of smart contracts were also discussed in paper. The implementation uses the blind signature protocol by David Chaum and encryption with the Rivest-Shamir-Adleman (RSA) algorithm. Presented in this paper scheme for blockchain decentralized voting for verified users with focus on anonymity is then fully implemented and identified potential issues are analysed and discussed.
{"title":"Blockchain Decentralized Voting for Verified Users with a Focus on Anonymity","authors":"P. Pospiech, Aleksander Marianski, M. Kedziora","doi":"10.5121/csit.2021.110805","DOIUrl":"https://doi.org/10.5121/csit.2021.110805","url":null,"abstract":"The paper presents decentralized voting scheme for verified users while maintaining their anonymity. A blockchain network was applied, which is a decentralized and distributed database based on the Peer-to-Peer architecture. During the implementation, the Ethereum network was used. Thanks to this, it is possible to code the terms of the contract required to perform the transaction. Ethereum and the use of smart contracts were also discussed in paper. The implementation uses the blind signature protocol by David Chaum and encryption with the Rivest-Shamir-Adleman (RSA) algorithm. Presented in this paper scheme for blockchain decentralized voting for verified users with focus on anonymity is then fully implemented and identified potential issues are analysed and discussed.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41727464","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 : 2021-06-19DOI: 10.5121/csit.2021.110809
P. Zhao, W. Cortes, Congyi Zhu, Tom Springer
Flip flops/Pulsed latches are one of the main contributors of dynamic power consumption. In this paper, a novel flip-flop (FF) using clock gating circuitry with embedded XOR, GEMFF, is proposed. Using post layout simulation with 45nm technology, GEMFF outperforms prior stateof-the-art flip-flop by 25.1% at 10% data switching activity in terms of power consumption.
{"title":"Clock Gating Flip-Flop using Embedded XoR Circuitry","authors":"P. Zhao, W. Cortes, Congyi Zhu, Tom Springer","doi":"10.5121/csit.2021.110809","DOIUrl":"https://doi.org/10.5121/csit.2021.110809","url":null,"abstract":"Flip flops/Pulsed latches are one of the main contributors of dynamic power consumption. In this paper, a novel flip-flop (FF) using clock gating circuitry with embedded XOR, GEMFF, is proposed. Using post layout simulation with 45nm technology, GEMFF outperforms prior stateof-the-art flip-flop by 25.1% at 10% data switching activity in terms of power consumption.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48318427","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 : 2021-06-19DOI: 10.5121/csit.2021.110806
A. Romanova
It is beneficial for document topic analysis to build a bridge between word embedding process and graph capacity to connect the dots and represent complex correlations between entities. In this study we examine processes of building a semantic graph model, finding document topics and validating topic discovery. We introduce a novel Word2Vec2Graph model that is built on top of Word2Vec word embedding model. We demonstrate how this model can be used to analyze long documents and uncover document topics as graph clusters. To validate topic discovery method we transfer words to vectors and vectors to images and use deep learning image classification.
{"title":"Detect Text Topics by Semantics Graphs","authors":"A. Romanova","doi":"10.5121/csit.2021.110806","DOIUrl":"https://doi.org/10.5121/csit.2021.110806","url":null,"abstract":"It is beneficial for document topic analysis to build a bridge between word embedding process and graph capacity to connect the dots and represent complex correlations between entities. In this study we examine processes of building a semantic graph model, finding document topics and validating topic discovery. We introduce a novel Word2Vec2Graph model that is built on top of Word2Vec word embedding model. We demonstrate how this model can be used to analyze long documents and uncover document topics as graph clusters. To validate topic discovery method we transfer words to vectors and vectors to images and use deep learning image classification.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48354220","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 : 2021-06-19DOI: 10.5121/csit.2021.110808
Rabea Emdas, Ahmed Alruwaili
Computer-based exams (CBEs) have been used in various courses, such as schools, universities and other training centres. As there are many educational institutions which have chosen to convert from paper test system to computer- based exam. However, adopting computer tests may lead to some difficulties for the students, which relates to technical defects and lake of computer skills of some students when they applying the computer based exams. The purpose of the essay was to determine negative and positive effects on the students of using computer-based exams and focus on some of suggesting solutions to the negative effects, such the exams to make continuous use of computer- based possible. In the first section the computer test, which could cause negative effects on students due to various levels of skills to use computer and some technical problems was examined. The design of the computer examination system requires careful planning and study from several aspects before becoming officially accepted, the computer-based exams still have a few problems which may lead to difficulties in using computer exams. Then the many benefits which could be gained by using computer-based exams, such as the student will be more independent with computer test were described. In addition, the students have accessible to the exams through the internet network. Finally, the effectiveness of certain strategy to solve the negative effects of computer-based exams were argued. developing the solutions of the technical problems are required for computer test, where improving the input methods questions and corrections. It was concluded that the computer exam, with adjustments, is more suitable for students.
{"title":"What are the Aspects of Adopting Computer-Based Exams and do they Impact Negatively on Students?","authors":"Rabea Emdas, Ahmed Alruwaili","doi":"10.5121/csit.2021.110808","DOIUrl":"https://doi.org/10.5121/csit.2021.110808","url":null,"abstract":"Computer-based exams (CBEs) have been used in various courses, such as schools, universities and other training centres. As there are many educational institutions which have chosen to convert from paper test system to computer- based exam. However, adopting computer tests may lead to some difficulties for the students, which relates to technical defects and lake of computer skills of some students when they applying the computer based exams. The purpose of the essay was to determine negative and positive effects on the students of using computer-based exams and focus on some of suggesting solutions to the negative effects, such the exams to make continuous use of computer- based possible. In the first section the computer test, which could cause negative effects on students due to various levels of skills to use computer and some technical problems was examined. The design of the computer examination system requires careful planning and study from several aspects before becoming officially accepted, the computer-based exams still have a few problems which may lead to difficulties in using computer exams. Then the many benefits which could be gained by using computer-based exams, such as the student will be more independent with computer test were described. In addition, the students have accessible to the exams through the internet network. Finally, the effectiveness of certain strategy to solve the negative effects of computer-based exams were argued. developing the solutions of the technical problems are required for computer test, where improving the input methods questions and corrections. It was concluded that the computer exam, with adjustments, is more suitable for students.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46907184","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 : 2021-06-19DOI: 10.5121/csit.2021.110802
A. Premkumar
Business network brings many organizations close together to achieve their desired goals and profit from it. People from different organizations may or may not know each other but still can be part of a business network. A major challenge with these business networks is how to provide trust among people and data security. Blockchain is another means through which many organizations in the current digital age are overcoming these problems with ease. Blockchains have also changed the way the business transactions with clients take place. Blockchain is a decentralized distributed ledger in a peer to peer network which can be public or private, and it enables individuals or companies to collaborate with each other to achieve trust and transparency between business and its clients. Many implementations of blockchain technology are widely available today. Each of them have their own strengths for a specific application domain. They can fundamentally alter electronic communications with a potential to affect all sorts of transaction processing systems. However, there are still many challenges of blockchain technology waiting to be solved such as scalability and adoptability. In this paper, we provide the knowledge on Blockchain technology and we present the applicability of blockchain in the business models and also discuss the relevant use cases for Banking and Supply Chain models.
{"title":"An Applicability of Blockchain Model in Business use Case - A Technical Approach","authors":"A. Premkumar","doi":"10.5121/csit.2021.110802","DOIUrl":"https://doi.org/10.5121/csit.2021.110802","url":null,"abstract":"Business network brings many organizations close together to achieve their desired goals and profit from it. People from different organizations may or may not know each other but still can be part of a business network. A major challenge with these business networks is how to provide trust among people and data security. Blockchain is another means through which many organizations in the current digital age are overcoming these problems with ease. Blockchains have also changed the way the business transactions with clients take place. Blockchain is a decentralized distributed ledger in a peer to peer network which can be public or private, and it enables individuals or companies to collaborate with each other to achieve trust and transparency between business and its clients. Many implementations of blockchain technology are widely available today. Each of them have their own strengths for a specific application domain. They can fundamentally alter electronic communications with a potential to affect all sorts of transaction processing systems. However, there are still many challenges of blockchain technology waiting to be solved such as scalability and adoptability. In this paper, we provide the knowledge on Blockchain technology and we present the applicability of blockchain in the business models and also discuss the relevant use cases for Banking and Supply Chain models.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44351900","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 : 2021-06-19DOI: 10.5121/csit.2021.110810
Tom Springer, Peiying Zhao
In this paper, we present a new hierarchical scheduling framework for periodic tasks in symmetric multiprocessor (SMP) platforms. Partitioned and global scheduling are the two main approaches used by SMP based systems where global scheduling is recommended for overall performance and partitioned scheduling is recommended for hard real-time performance. Our approach combines both the global and partitioned approaches of traditional SMP-based schedulers to provide hard real-time performance guarantees for critical tasks and improved response times for soft real-time tasks. Implemented as part of VxWorks, the results are confirmed using a real-time benchmark application, where response times were improved for soft real-time tasks while still providing hard real-time performance.
{"title":"Hierarchical Scheduling for Real-Time Periodic Tasks in Symmetric Multiprocessing","authors":"Tom Springer, Peiying Zhao","doi":"10.5121/csit.2021.110810","DOIUrl":"https://doi.org/10.5121/csit.2021.110810","url":null,"abstract":"In this paper, we present a new hierarchical scheduling framework for periodic tasks in symmetric multiprocessor (SMP) platforms. Partitioned and global scheduling are the two main approaches used by SMP based systems where global scheduling is recommended for overall performance and partitioned scheduling is recommended for hard real-time performance. Our approach combines both the global and partitioned approaches of traditional SMP-based schedulers to provide hard real-time performance guarantees for critical tasks and improved response times for soft real-time tasks. Implemented as part of VxWorks, the results are confirmed using a real-time benchmark application, where response times were improved for soft real-time tasks while still providing hard real-time performance.","PeriodicalId":72673,"journal":{"name":"Computer science & information technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44833138","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：