Pub Date : 2020-12-01DOI: 10.1109/CSCI51800.2020.00096
A. Almalki, P. Wocjan
In this research, the world model has a modified RNN model carried out by a bi-directional gated recurrent unit (BGRU) as opposed to a traditional long short-term memory (LSTM) model. BGRU tends to use less memory while executing and training faster than an LSTM, as it uses fewer training parameters. However, the LSTM model provides greater accuracy with datasets using longer sequences. Based upon practical implementation, the BGRU model produced better performance results. In BGRU, the memory is combined with the network. There is no update gate and forget in the GRU. The forget and update gate are treated as one unit thus it is the primary reason of parameter reduction.
{"title":"Forecasting Method based upon GRU-based Deep Learning Model","authors":"A. Almalki, P. Wocjan","doi":"10.1109/CSCI51800.2020.00096","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00096","url":null,"abstract":"In this research, the world model has a modified RNN model carried out by a bi-directional gated recurrent unit (BGRU) as opposed to a traditional long short-term memory (LSTM) model. BGRU tends to use less memory while executing and training faster than an LSTM, as it uses fewer training parameters. However, the LSTM model provides greater accuracy with datasets using longer sequences. Based upon practical implementation, the BGRU model produced better performance results. In BGRU, the memory is combined with the network. There is no update gate and forget in the GRU. The forget and update gate are treated as one unit thus it is the primary reason of parameter reduction.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114622916","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00066
Sharad Sharma, S. Bodempudi, Aishwarya Reehl
Real-time data visualization can enhance decision making and empower teams with human-centric situational awareness insights. Decision making relies on data which comes in overwhelming velocity and volume, that one cannot comprehend it without some layer of abstraction. This research effort aims to demonstrate the data visualization of the COVID pandemic in real-time for the fifty states in the USA. Our proposed data visualization tool includes both conceptual and data-driven information. The data visualization includes stacked bar graphs, geographic representations of the data, and offers situational awareness of the COVID-19 pandemic. This paper describes the development and testing of the data visualization tool using the Unity gaming engine. Testing has been done with a real-time feed of the COVID-19 data set for immersive environment, non-immersive environment, and mobile environment.
{"title":"Real-Time Data Visualization to Enhance Situational Awareness of COVID pandemic","authors":"Sharad Sharma, S. Bodempudi, Aishwarya Reehl","doi":"10.1109/CSCI51800.2020.00066","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00066","url":null,"abstract":"Real-time data visualization can enhance decision making and empower teams with human-centric situational awareness insights. Decision making relies on data which comes in overwhelming velocity and volume, that one cannot comprehend it without some layer of abstraction. This research effort aims to demonstrate the data visualization of the COVID pandemic in real-time for the fifty states in the USA. Our proposed data visualization tool includes both conceptual and data-driven information. The data visualization includes stacked bar graphs, geographic representations of the data, and offers situational awareness of the COVID-19 pandemic. This paper describes the development and testing of the data visualization tool using the Unity gaming engine. Testing has been done with a real-time feed of the COVID-19 data set for immersive environment, non-immersive environment, and mobile environment.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121469660","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00033
A. Gouissem, K. Abualsaud, E. Yaacoub, T. Khattab, M. Guizani
Thanks to its low cost, small weight and energy efficiency, passive radio frequency identification (RFID) backscatter communications systems have attracted a lot of attention in several application fields. However, such devices have limited computational capabilities and resources which makes them unable to incorporate traditional security protocols and are there-fore vulnerable to several types of attacks including cloning and counterfeiting. Therefore, in this paper, a novel hybrid RFID tags identification and malicious devices detection system is proposed by exploiting the estimated tags locations and manufacturing imperfections. In particular, an iterative approach is proposed to estimate the minimum power response at each frequency of the tag in addition to its location. The conducted simulation results show the efficiency of this technique in detecting all the malicious tags and classify the legitimate ones under different network configurations.
{"title":"Hybrid Physical Layer Security for Passive RFID Communication","authors":"A. Gouissem, K. Abualsaud, E. Yaacoub, T. Khattab, M. Guizani","doi":"10.1109/CSCI51800.2020.00033","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00033","url":null,"abstract":"Thanks to its low cost, small weight and energy efficiency, passive radio frequency identification (RFID) backscatter communications systems have attracted a lot of attention in several application fields. However, such devices have limited computational capabilities and resources which makes them unable to incorporate traditional security protocols and are there-fore vulnerable to several types of attacks including cloning and counterfeiting. Therefore, in this paper, a novel hybrid RFID tags identification and malicious devices detection system is proposed by exploiting the estimated tags locations and manufacturing imperfections. In particular, an iterative approach is proposed to estimate the minimum power response at each frequency of the tag in addition to its location. The conducted simulation results show the efficiency of this technique in detecting all the malicious tags and classify the legitimate ones under different network configurations.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124356732","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00328
Álvaro Magri Nogueira da Cruz, Adriana Barbosa Santos, R. C. G. de Souza, Thiago Luiz Parolin
The scientific research developed in Brazil is prominent in the global scene. Despite this, it still lacks visibility outside the scientific sphere and better recognition for Brazilian researchers. This paper presents a web-based platform proposed to reinforce the open access initiatives to expand scientific knowledge. It is focused on publishing research articles by audiovisual format. The audiovisual resources can introduce another dynamic for scientific communication in Brazil. The characteristics and subcharacteristics of the ISO/IEC25010 quality model were adapted to define the platform’s design, its architecture and user interface.
{"title":"An open web-based platform for enhancing the visibility of Brazilian research","authors":"Álvaro Magri Nogueira da Cruz, Adriana Barbosa Santos, R. C. G. de Souza, Thiago Luiz Parolin","doi":"10.1109/CSCI51800.2020.00328","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00328","url":null,"abstract":"The scientific research developed in Brazil is prominent in the global scene. Despite this, it still lacks visibility outside the scientific sphere and better recognition for Brazilian researchers. This paper presents a web-based platform proposed to reinforce the open access initiatives to expand scientific knowledge. It is focused on publishing research articles by audiovisual format. The audiovisual resources can introduce another dynamic for scientific communication in Brazil. The characteristics and subcharacteristics of the ISO/IEC25010 quality model were adapted to define the platform’s design, its architecture and user interface.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124436394","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00140
Jongin Choe, SangHyun Seo
this paper introduces a method for recognizing real world objects in AR(Augmented Reality) environment and visualizing virtual information based on the objects. Existing AR shows high dependence on markers. The use range of the virtual space is limited to narrow marker space and the placement and tracking of virtual objects in a 3D is also limited to the space centered on the marker. The method constructs a map of the space in the form of a point cloud using SLAM, and performs real-world object recognition of the constructed wide AR space in real time. As a result, the degree of freedom of space utilization increases, and it is helpful in applying AR such as information display of real-world objects by accurately recognizing and localizing the location of objects existing in the real-world space.
{"title":"A 3D Real Object Recognition and Localization on SLAM based Augmented Reality Environment","authors":"Jongin Choe, SangHyun Seo","doi":"10.1109/CSCI51800.2020.00140","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00140","url":null,"abstract":"this paper introduces a method for recognizing real world objects in AR(Augmented Reality) environment and visualizing virtual information based on the objects. Existing AR shows high dependence on markers. The use range of the virtual space is limited to narrow marker space and the placement and tracking of virtual objects in a 3D is also limited to the space centered on the marker. The method constructs a map of the space in the form of a point cloud using SLAM, and performs real-world object recognition of the constructed wide AR space in real time. As a result, the degree of freedom of space utilization increases, and it is helpful in applying AR such as information display of real-world objects by accurately recognizing and localizing the location of objects existing in the real-world space.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124500011","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00245
Edward Eisenberger, Sai Teja Kutalam, Vamsi Varma Datla, Abdel-shakour Abuzneid
Cloud Storage is a cost-effective and agile platform for both users and businesses. Transferring data to and between Cloud Storage systems presents a vulnerability for the data. This paper proposes a method for securely migrating between Cloud Storage systems using Public Key Exchange and Cipher Block Chaining (CBC).
{"title":"Secure Cloud Storage Migration","authors":"Edward Eisenberger, Sai Teja Kutalam, Vamsi Varma Datla, Abdel-shakour Abuzneid","doi":"10.1109/CSCI51800.2020.00245","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00245","url":null,"abstract":"Cloud Storage is a cost-effective and agile platform for both users and businesses. Transferring data to and between Cloud Storage systems presents a vulnerability for the data. This paper proposes a method for securely migrating between Cloud Storage systems using Public Key Exchange and Cipher Block Chaining (CBC).","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128117487","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00141
Taemin Lee, Nahyuk Lee, Sanghyun Seo, Dongwann Kang
When people are looking at a landscape, we feel different depending on time/season. This part is based on the colors of the landscape, even if you look at the same landscape due to the visual elements. We wanted to analyze human emotions, especially based on color, among these visual elements. For this purpose, machine learning models were established according to color and human emotion changes were analyzed quantitatively over time. Finally, we analyzed how much color affects human emotions.
{"title":"A Study on the Prediction of Emotion from Image by Time-flow depend on Color Analysis","authors":"Taemin Lee, Nahyuk Lee, Sanghyun Seo, Dongwann Kang","doi":"10.1109/CSCI51800.2020.00141","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00141","url":null,"abstract":"When people are looking at a landscape, we feel different depending on time/season. This part is based on the colors of the landscape, even if you look at the same landscape due to the visual elements. We wanted to analyze human emotions, especially based on color, among these visual elements. For this purpose, machine learning models were established according to color and human emotion changes were analyzed quantitatively over time. Finally, we analyzed how much color affects human emotions.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121931352","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00197
Kori Painchaud, L. Deligiannidis
Internet of Things (IoT) devices can be defined as a collection of computing devices that communicate and transfer data with one another. As the popularity of IoT devices increases, users want to maximize the functionality of their devices. Voice-enabled IoT devices serve and assist the user by performing functions like playing music, controlling lights, setting alarms and reminders, and much more. The popularity of these devices has grown, and they appeal to consumers because of the available accessories that can be purchased and connected to, such as smart lights, smart shades, etc. These smart accessories can connect to devices such as the Google Home or the Amazon Echo, allowing the user to control multiple common house functions with their voice. This paper demonstrates how to control non-smart LED lights using voice commands with smart home devices. A service known as IFTTT, "If This, Then That", is utilized to add custom commands to two smart speakers. This paper shows how accessible and simple it is for an individual to control a non-smart device using voice commands, while shedding light on how the use of VPAs can aid people with disabilities. The security risks and threats of using IFTTT are addressed.
物联网(IoT)设备可以定义为相互通信和传输数据的计算设备的集合。随着物联网设备的普及，用户希望最大限度地发挥其设备的功能。支持语音的物联网设备通过播放音乐、控制灯光、设置警报和提醒等功能为用户提供服务和帮助。这些设备的受欢迎程度越来越高，它们对消费者的吸引力在于可以购买和连接的配件，例如智能灯，智能遮光罩等。这些智能配件可以连接到诸如Google Home或Amazon Echo之类的设备，允许用户用他们的声音控制多个常见的家庭功能。本文演示了如何使用智能家居设备的语音命令来控制非智能LED灯。一项名为IFTTT的服务，即“If This, Then That”，用于向两个智能扬声器添加自定义命令。这篇论文展示了个人使用语音命令控制非智能设备是多么容易和简单，同时也揭示了vpa的使用如何帮助残疾人。讨论了使用IFTTT的安全风险和威胁。
{"title":"Customized Services Using Voice Assistants","authors":"Kori Painchaud, L. Deligiannidis","doi":"10.1109/CSCI51800.2020.00197","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00197","url":null,"abstract":"Internet of Things (IoT) devices can be defined as a collection of computing devices that communicate and transfer data with one another. As the popularity of IoT devices increases, users want to maximize the functionality of their devices. Voice-enabled IoT devices serve and assist the user by performing functions like playing music, controlling lights, setting alarms and reminders, and much more. The popularity of these devices has grown, and they appeal to consumers because of the available accessories that can be purchased and connected to, such as smart lights, smart shades, etc. These smart accessories can connect to devices such as the Google Home or the Amazon Echo, allowing the user to control multiple common house functions with their voice. This paper demonstrates how to control non-smart LED lights using voice commands with smart home devices. A service known as IFTTT, \"If This, Then That\", is utilized to add custom commands to two smart speakers. This paper shows how accessible and simple it is for an individual to control a non-smart device using voice commands, while shedding light on how the use of VPAs can aid people with disabilities. The security risks and threats of using IFTTT are addressed.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"353 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115923875","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00076
Tsenguun Tsogbadrakh, Amal Alhosban
Data mining classification methods can be a powerful tool when it comes to learning card game rules such as Poker. There are millions of possible combination in the game and making a decision tree to cover all the rules is not desirable. We used the J48 decision tree model of data mining software Weka and made parameter analysis. Then we show experimentally how the number of instances is affecting the correctness of the classification, and propose an equation to determine accuracy based on the number of instances in a data set. We examine several different attributes and the experiment shows high performance.
{"title":"Discovering a Learning Module for Poker’s Rule through Data Mining Algorithms","authors":"Tsenguun Tsogbadrakh, Amal Alhosban","doi":"10.1109/CSCI51800.2020.00076","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00076","url":null,"abstract":"Data mining classification methods can be a powerful tool when it comes to learning card game rules such as Poker. There are millions of possible combination in the game and making a decision tree to cover all the rules is not desirable. We used the J48 decision tree model of data mining software Weka and made parameter analysis. Then we show experimentally how the number of instances is affecting the correctness of the classification, and propose an equation to determine accuracy based on the number of instances in a data set. We examine several different attributes and the experiment shows high performance.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132074392","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 : 2020-12-01DOI: 10.1109/CSCI51800.2020.00312
Kaito Ishizaki, Kasuki Saruta, Hiroshi Uehara
Object detection requires an enormous amount of training data annotated by bounding boxes. All bounding boxes are manually drawn, which leads to highly expensive labor costs. Therefore, this study proposes automatic bounding box annotation of training data for object detection. The keypoints to identify object regions in pictures are extracted, which can then be used for drawing bounding boxes automatically, thus, reducing manual labor requirements. When our proposed method is used for pictures of road signs, keypoints that identify road sign regions in the pictures are detected; these keypoints are found to be highly accurate for drawing bounding boxes.
{"title":"Detecting Keypoints for Automated Annotation of Bounding Boxes using Keypoint Extraction","authors":"Kaito Ishizaki, Kasuki Saruta, Hiroshi Uehara","doi":"10.1109/CSCI51800.2020.00312","DOIUrl":"https://doi.org/10.1109/CSCI51800.2020.00312","url":null,"abstract":"Object detection requires an enormous amount of training data annotated by bounding boxes. All bounding boxes are manually drawn, which leads to highly expensive labor costs. Therefore, this study proposes automatic bounding box annotation of training data for object detection. The keypoints to identify object regions in pictures are extracted, which can then be used for drawing bounding boxes automatically, thus, reducing manual labor requirements. When our proposed method is used for pictures of road signs, keypoints that identify road sign regions in the pictures are detected; these keypoints are found to be highly accurate for drawing bounding boxes.","PeriodicalId":336929,"journal":{"name":"2020 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130185132","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：