Pub Date : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8992972
Miguel F. Villegas, Juan Carlos Torres Munoz, Abdulrahman M.R. Alrashidi, D. Dow
Old age is associated with declines in vision, hearing, sensory function, motor function, and cognition. These declines make managing activities of daily living harder. Computer mobile devices could help, but many elderly people find the interface too small and navigation too complex. A larger computer interface in a natural setting, such as a tabletop, could provide a more usable interface and be able to provide better assistance for some elderly people. The purpose of this project was to develop a prototype human computer interface that projects images onto a tabletop, uses an imaging system to identify hand position over the tabletop in relation to the projected image, detects menu selections of the hand over projected buttons, and takes actions, such as displaying the selected next menu. A prototype was developed using custom LabView programs for generation of images of menu selections to be projected, image processing and control of the system. Hand recognition was simplified by having the user wear a white glove with a black square on the back for the imaging system to search for. Button selection was recognized by holding the hand over a projected menu button for several seconds. The prototype function showed promise. Further testing and development will be necessary toward wider implementation. Such a projected tabletop human computer interface may improve computer derive assistance for elderly people compared to mobile or computer display interfaces.
{"title":"Tabletop Human Computer Interface to Assist Elderly with Tasks of Daily Living","authors":"Miguel F. Villegas, Juan Carlos Torres Munoz, Abdulrahman M.R. Alrashidi, D. Dow","doi":"10.1109/UEMCON47517.2019.8992972","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8992972","url":null,"abstract":"Old age is associated with declines in vision, hearing, sensory function, motor function, and cognition. These declines make managing activities of daily living harder. Computer mobile devices could help, but many elderly people find the interface too small and navigation too complex. A larger computer interface in a natural setting, such as a tabletop, could provide a more usable interface and be able to provide better assistance for some elderly people. The purpose of this project was to develop a prototype human computer interface that projects images onto a tabletop, uses an imaging system to identify hand position over the tabletop in relation to the projected image, detects menu selections of the hand over projected buttons, and takes actions, such as displaying the selected next menu. A prototype was developed using custom LabView programs for generation of images of menu selections to be projected, image processing and control of the system. Hand recognition was simplified by having the user wear a white glove with a black square on the back for the imaging system to search for. Button selection was recognized by holding the hand over a projected menu button for several seconds. The prototype function showed promise. Further testing and development will be necessary toward wider implementation. Such a projected tabletop human computer interface may improve computer derive assistance for elderly people compared to mobile or computer display interfaces.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124502263","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8992933
A. Annagrebah, E. Bechetoille, I. Laktineh, H. Chanal
This paper reports the development of an adjustable, Time-to-Digital Converter (TDC) based on two vernier Ring Oscillators (RO). The TDC aims to measure timing in Resistive Plate Chamber (RPC) detector for CMS experiment. Considering previous designs, the contribution from power supply noise and intrinsic transistor noise had been minimizing with differential stages and proper transistor sizing. To reduce the timing resolution and deadtime inherent to Vernier TDC architecture, as many Phase Detector (PD) as possible had been implemented. Such functionality permits to choose whether reducing the dead time or measuring redundantly the start-stop time difference for an improved precision. The prototype TDC fabricated in a 130-nm technology consumes 8.5 mW power under 1.2-V supply. The measurement of this chip shown a timing accuracy of 5.48 ps at a timing resolution of 8 ps for the first data allowed by the first phase detection.
{"title":"A Multi-Phase Time-to-Digital Converter Differential Vernier Ring Oscillator","authors":"A. Annagrebah, E. Bechetoille, I. Laktineh, H. Chanal","doi":"10.1109/UEMCON47517.2019.8992933","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8992933","url":null,"abstract":"This paper reports the development of an adjustable, Time-to-Digital Converter (TDC) based on two vernier Ring Oscillators (RO). The TDC aims to measure timing in Resistive Plate Chamber (RPC) detector for CMS experiment. Considering previous designs, the contribution from power supply noise and intrinsic transistor noise had been minimizing with differential stages and proper transistor sizing. To reduce the timing resolution and deadtime inherent to Vernier TDC architecture, as many Phase Detector (PD) as possible had been implemented. Such functionality permits to choose whether reducing the dead time or measuring redundantly the start-stop time difference for an improved precision. The prototype TDC fabricated in a 130-nm technology consumes 8.5 mW power under 1.2-V supply. The measurement of this chip shown a timing accuracy of 5.48 ps at a timing resolution of 8 ps for the first data allowed by the first phase detection.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121249977","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 : 2019-10-01DOI: 10.1109/uemcon47517.2019.8993023
Ankita Roy
Breast cancer is one of the main causes of cancer death worldwide. In the midst of the treatment of different disorders and diseases, one critical aspect in saving a patient is early detection. Correct detection and assessment of mammograms is hindered by human-error and inter-observer variations between pathologists. Existing convolutional neural network structures have shown promise in detection, but are hindered in their requirements for very large datasets to train on. The purpose of this paper is to explore a streamlined method classification of hematoxylin and eosin (H&E) stained tissue cancer mammograms into non-carcinomas and carcinomas using a small training set. This is done by the creation of more sample sets through changing elements of the data such as shear ratio and rotation. We assumed a 4-layer DCNN (deep convolutional neural network). We first train the DCNN with our augmented dataset, increasing dataset size by x200. We implement a highly accurate and reduced chance of overfitting gradient boosting algorithm. The overall classification accuracy of benign versus malignant was 88%.
{"title":"Deep Convolutional Neural Networks for Breast Cancer Detection","authors":"Ankita Roy","doi":"10.1109/uemcon47517.2019.8993023","DOIUrl":"https://doi.org/10.1109/uemcon47517.2019.8993023","url":null,"abstract":"Breast cancer is one of the main causes of cancer death worldwide. In the midst of the treatment of different disorders and diseases, one critical aspect in saving a patient is early detection. Correct detection and assessment of mammograms is hindered by human-error and inter-observer variations between pathologists. Existing convolutional neural network structures have shown promise in detection, but are hindered in their requirements for very large datasets to train on. The purpose of this paper is to explore a streamlined method classification of hematoxylin and eosin (H&E) stained tissue cancer mammograms into non-carcinomas and carcinomas using a small training set. This is done by the creation of more sample sets through changing elements of the data such as shear ratio and rotation. We assumed a 4-layer DCNN (deep convolutional neural network). We first train the DCNN with our augmented dataset, increasing dataset size by x200. We implement a highly accurate and reduced chance of overfitting gradient boosting algorithm. The overall classification accuracy of benign versus malignant was 88%.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122004924","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993051
Md Inzamam Ul Haque, Damian Valles
In this paper, continued work of a research project is discussed which achieved the end goal of the project - to build a mobile device application that can teach children with Autism Spectrum Disorder (ASD) to recognize human facial expressions utilizing computer vision and image processing. Universally, there are seven facial expressions categories: angry, disgust, happy, sad, fear, surprise, and neutral. To recognize all these facial expressions and to predict the current mood of a person is a difficult task for a child. A child with ASD, this problem presents itself in a more sophisticated manner due to the nature of the disorder. The main goal of this research was to develop a deep Convolutional Neural Network (DCNN) for facial expression recognition, which can help young children with ASD to recognize facial expressions, using mobile devices. The Kaggle's FER2013 and Karolinska Directed Emotional Faces (KDEF) dataset have been used to train and test with the DCNN model, which can classify facial expressions from different viewpoints and in different lighting contrasts. An 86.44% accuracy was achieved with good generalizability for the DCNN model. The results show an improvement of the DCNN accuracy in dealing with lighting contrast changes, and the implementation of image processing before performing the facial expression classification. As a byproduct of this research project, an app suitable for the iOS platform was developed for running both the DCNN model and image processing algorithm. The app can be used by speech-language pathologies, teacher, care-takers, and parents as a technological tool when working with children with ASD.
{"title":"Facial Expression Recognition Using DCNN and Development of an iOS App for Children with ASD to Enhance Communication Abilities","authors":"Md Inzamam Ul Haque, Damian Valles","doi":"10.1109/UEMCON47517.2019.8993051","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993051","url":null,"abstract":"In this paper, continued work of a research project is discussed which achieved the end goal of the project - to build a mobile device application that can teach children with Autism Spectrum Disorder (ASD) to recognize human facial expressions utilizing computer vision and image processing. Universally, there are seven facial expressions categories: angry, disgust, happy, sad, fear, surprise, and neutral. To recognize all these facial expressions and to predict the current mood of a person is a difficult task for a child. A child with ASD, this problem presents itself in a more sophisticated manner due to the nature of the disorder. The main goal of this research was to develop a deep Convolutional Neural Network (DCNN) for facial expression recognition, which can help young children with ASD to recognize facial expressions, using mobile devices. The Kaggle's FER2013 and Karolinska Directed Emotional Faces (KDEF) dataset have been used to train and test with the DCNN model, which can classify facial expressions from different viewpoints and in different lighting contrasts. An 86.44% accuracy was achieved with good generalizability for the DCNN model. The results show an improvement of the DCNN accuracy in dealing with lighting contrast changes, and the implementation of image processing before performing the facial expression classification. As a byproduct of this research project, an app suitable for the iOS platform was developed for running both the DCNN model and image processing algorithm. The app can be used by speech-language pathologies, teacher, care-takers, and parents as a technological tool when working with children with ASD.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122026752","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993064
Mohammad Aminul Hoque, Ragib Hasan
Security is a huge challenge in vehicular networks due to the large size of the network, high mobility of nodes, and continuous change of network topology. These challenges are also applicable to the vehicular fog, which is a new computing paradigm in the context of vehicular networks. In vehicular fog computing, the vehicles serve as fog nodes. This is a promising model for latency-sensitive and location-aware services, which also incurs some unique security and privacy issues. However, there is a lack of a systematic approach to design security solutions of the vehicular fog using a comprehensive threat model. Threat modeling is a step-by-step process to analyze, identify, and prioritize all the potential threats and vulnerabilities of a system and solve them with known security solutions. A well-designed threat model can help to understand the security and privacy threats, vulnerabilities, requirements, and challenges along with the attacker model, the attack motives, and attacker capabilities. Threat model analysis in vehicular fog computing is critical because only brainstorming and threat models of other vehicular network paradigms will not provide a complete scenario of potential threats and vulnerabilities. In this paper, we have explored the threat model of vehicular fog computing and identified the threats and vulnerabilities using STRIDE and CIAA threat modeling processes. We posit that this initiative will help to improve the security and privacy system design of vehicular fog computing.
{"title":"Towards a Threat Model for Vehicular Fog Computing","authors":"Mohammad Aminul Hoque, Ragib Hasan","doi":"10.1109/UEMCON47517.2019.8993064","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993064","url":null,"abstract":"Security is a huge challenge in vehicular networks due to the large size of the network, high mobility of nodes, and continuous change of network topology. These challenges are also applicable to the vehicular fog, which is a new computing paradigm in the context of vehicular networks. In vehicular fog computing, the vehicles serve as fog nodes. This is a promising model for latency-sensitive and location-aware services, which also incurs some unique security and privacy issues. However, there is a lack of a systematic approach to design security solutions of the vehicular fog using a comprehensive threat model. Threat modeling is a step-by-step process to analyze, identify, and prioritize all the potential threats and vulnerabilities of a system and solve them with known security solutions. A well-designed threat model can help to understand the security and privacy threats, vulnerabilities, requirements, and challenges along with the attacker model, the attack motives, and attacker capabilities. Threat model analysis in vehicular fog computing is critical because only brainstorming and threat models of other vehicular network paradigms will not provide a complete scenario of potential threats and vulnerabilities. In this paper, we have explored the threat model of vehicular fog computing and identified the threats and vulnerabilities using STRIDE and CIAA threat modeling processes. We posit that this initiative will help to improve the security and privacy system design of vehicular fog computing.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126742648","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993017
J. Fernandes, Keye Li, J. Mirabile, Gregg Vesonder
Flocking behavior is an exercise in both control and coordination. Members need to move in near-perfect time with each other to maintain a safe, but compact, distance amongst themselves. This balance could have a number of useful applications, ranging from automated vehicles to power grid coordination. Moreover, per Reynolds (1987), flocking behavior can be summarized as an algorithm, which automated systems can easily consume. Inspired by this premise, the group blueprinted a robot flock using Turtlebot3 Burgers and Robot Operating System, or ROS. To begin, the group created an algorithm in Scratch, a graphical programming language. Per Reynolds' model, as long as each individual member knows and follows the algorithm, a flock will form without any outside influence. The group theorized that this modular approach would bide well with the ROS system of nodes and messages. By deeming each member a flocking node and having a remote “master” perform functions such as localization, the ROS framework would naturally support robot flocking. However, after transcribing their program to C++, the group found some ongoing issues in development. They struggled to adapt ROS's message commands into their program, and the Burgers' given localization program had trouble supporting a multi-robot flock. Regardless, with further research, the group still believes that ROS can give rise to a viable flock.
{"title":"Application of Robot Operating System in Robot Flocks","authors":"J. Fernandes, Keye Li, J. Mirabile, Gregg Vesonder","doi":"10.1109/UEMCON47517.2019.8993017","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993017","url":null,"abstract":"Flocking behavior is an exercise in both control and coordination. Members need to move in near-perfect time with each other to maintain a safe, but compact, distance amongst themselves. This balance could have a number of useful applications, ranging from automated vehicles to power grid coordination. Moreover, per Reynolds (1987), flocking behavior can be summarized as an algorithm, which automated systems can easily consume. Inspired by this premise, the group blueprinted a robot flock using Turtlebot3 Burgers and Robot Operating System, or ROS. To begin, the group created an algorithm in Scratch, a graphical programming language. Per Reynolds' model, as long as each individual member knows and follows the algorithm, a flock will form without any outside influence. The group theorized that this modular approach would bide well with the ROS system of nodes and messages. By deeming each member a flocking node and having a remote “master” perform functions such as localization, the ROS framework would naturally support robot flocking. However, after transcribing their program to C++, the group found some ongoing issues in development. They struggled to adapt ROS's message commands into their program, and the Burgers' given localization program had trouble supporting a multi-robot flock. Regardless, with further research, the group still believes that ROS can give rise to a viable flock.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126187217","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993015
J. P. Piotrowski, E. Yfantis, A. Campagna, Q. Cornu, G. Gallitano
Computer games are being controlled by joysticks or the keys of the computer keyboard, especially the four arrow keys, or the WASD, or both, and other keys of the keyboard. In this research paper we describe a new algorithm that replaces control with joystick or the arrow keys with voice commands. Thus, we replace the left arrow key with the voice command “left”, the right arrow key with the voice command “right”, the up-arrow key with the voice command “up”, and the down arrow key with the voice command “down”. In order to do that we first develop a new convolutional neural network architecture, then we teach the architecture how to recognize the words “lef”, “right”, “up”, “down”, with extremely high accuracy and very low probability of misclassification. Once the Convolutional Neural Network (CNN) is taught to recognize these words, we use the feedforward part of the network in our game programs so that they can capture, real time, the voice input commands of the player and play the game. The advantage of using the voice commands is that for many players it is easier, faster, eliminates the chance of pushing the wrong key by mistake, and provides a better player experience. We also present a pong game in Unity where the paddle controller uses our algorithm to control the two paddles of the game.
{"title":"Voice Interactive Games","authors":"J. P. Piotrowski, E. Yfantis, A. Campagna, Q. Cornu, G. Gallitano","doi":"10.1109/UEMCON47517.2019.8993015","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993015","url":null,"abstract":"Computer games are being controlled by joysticks or the keys of the computer keyboard, especially the four arrow keys, or the WASD, or both, and other keys of the keyboard. In this research paper we describe a new algorithm that replaces control with joystick or the arrow keys with voice commands. Thus, we replace the left arrow key with the voice command “left”, the right arrow key with the voice command “right”, the up-arrow key with the voice command “up”, and the down arrow key with the voice command “down”. In order to do that we first develop a new convolutional neural network architecture, then we teach the architecture how to recognize the words “lef”, “right”, “up”, “down”, with extremely high accuracy and very low probability of misclassification. Once the Convolutional Neural Network (CNN) is taught to recognize these words, we use the feedforward part of the network in our game programs so that they can capture, real time, the voice input commands of the player and play the game. The advantage of using the voice commands is that for many players it is easier, faster, eliminates the chance of pushing the wrong key by mistake, and provides a better player experience. We also present a pong game in Unity where the paddle controller uses our algorithm to control the two paddles of the game.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125797633","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8992945
Trung-Thanh Nguyen, Amartya Hatua, A. Sung
Recently, the characteristics of robot autonomy, decentralized control, collective decision-making ability, high fault tolerance, etc. have significantly increased the applications of swarm robotics in targeted material delivery, precision farming, surveillance, defense and many other areas. In these multi-agent systems, safe collision avoidance is one of the most fundamental and important problems. Difference approaches, especially reinforcement learning, have been applied to solve this problem. This paper introduces a new cumulative learning approach which comprises of application of transfer learning with distributed multi-agent reinforcement learning techniques to solve collision-free navigation for swarm robotics. In our method, throughout the learning processes from the least complexity scenario to the most complex one, multiple agents can improve the shared policy through parameter sharing, reward shaping and multi-round multi-steps learning. We have adapted two policy gradient algorithms (TRPO and PPO) as the core of our distributed multiagent reinforcement learning method. The performance has shown that our new methodology can help reduce the training time and generate a robust navigation plan that can easily be generalized to complex in-door scenarios.
{"title":"Cumulative Training and Transfer Learning for Multi-Robots Collision-Free Navigation Problems","authors":"Trung-Thanh Nguyen, Amartya Hatua, A. Sung","doi":"10.1109/UEMCON47517.2019.8992945","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8992945","url":null,"abstract":"Recently, the characteristics of robot autonomy, decentralized control, collective decision-making ability, high fault tolerance, etc. have significantly increased the applications of swarm robotics in targeted material delivery, precision farming, surveillance, defense and many other areas. In these multi-agent systems, safe collision avoidance is one of the most fundamental and important problems. Difference approaches, especially reinforcement learning, have been applied to solve this problem. This paper introduces a new cumulative learning approach which comprises of application of transfer learning with distributed multi-agent reinforcement learning techniques to solve collision-free navigation for swarm robotics. In our method, throughout the learning processes from the least complexity scenario to the most complex one, multiple agents can improve the shared policy through parameter sharing, reward shaping and multi-round multi-steps learning. We have adapted two policy gradient algorithms (TRPO and PPO) as the core of our distributed multiagent reinforcement learning method. The performance has shown that our new methodology can help reduce the training time and generate a robust navigation plan that can easily be generalized to complex in-door scenarios.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125991717","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993081
Maxwell Ruggieri, Tzu-Tang Hsu, M. Ali
Security is an important factor when it comes to the development of software systems. In each of the developing steps of the software system we have to think of what security measure we can put for the design, development, and deployment of the software system. Having a high level of trust in security and quality in developing software systems is a crucial to creating successful application. Industry such as the Software Assurance Forum for Excellence in Code also known as “SAFECode” and Open Web Application Security Project or “OWASP”, both are a non-profit, global industry that led the organization to focus on improving the security of software. They laid down the basis of the best security practice in how to develop secure software system. In this paper we will be looking through different ways of secure practice through different research paper, looking for the difficulty in implementing these different practices, and recommending the solution to the problem.
{"title":"Security Considerations for the Development of Secure Software Systems","authors":"Maxwell Ruggieri, Tzu-Tang Hsu, M. Ali","doi":"10.1109/UEMCON47517.2019.8993081","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993081","url":null,"abstract":"Security is an important factor when it comes to the development of software systems. In each of the developing steps of the software system we have to think of what security measure we can put for the design, development, and deployment of the software system. Having a high level of trust in security and quality in developing software systems is a crucial to creating successful application. Industry such as the Software Assurance Forum for Excellence in Code also known as “SAFECode” and Open Web Application Security Project or “OWASP”, both are a non-profit, global industry that led the organization to focus on improving the security of software. They laid down the basis of the best security practice in how to develop secure software system. In this paper we will be looking through different ways of secure practice through different research paper, looking for the difficulty in implementing these different practices, and recommending the solution to the problem.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126735301","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 : 2019-10-01DOI: 10.1109/UEMCON47517.2019.8993056
Joong-Lyul Lee, Stephen C. Kerns, Sangjin Hong
Internet of Things (IoT) devices are becoming important and familiar products in our everyday lives. Yet, many of these IoT devices have a multitude of vulnerabilities that create a security risk, despite being products that bring a lot of convenience to our lives. Blockchain (BC) technology is gaining popularity these days due to the importance of data security. However, this BC technology is not suitable for IoT devices, because it requires a lot of computing power also IoT devices uses a limited amount of memory and has a lower performing CPU for cost reasons. Also, IoT devices collect a large amount of data and transmit that data every hour and every day to a cloud system to analyze or process the collected data. For this reason, network latency is an important factor in a cloud computing system. In this paper, we propose a secure and distributed 10T-Fog-Cloud Framework using BC to compensate for the security weaknesses of IoT nodes, the delay aware tree construction (DATC) algorithm that considers the service delay for fog-cloud computing, and the mobility of mobile IoT nodes for BC to deal with the triangular routing problem. To verify this proposed framework, we performed security analysis and experiments for the effectiveness of the algorithm through simulation and confirmed that the overall service delay was reduced by choosing the minimum delay path by the DATC algorithm.
{"title":"A Secure IoT-Fag-Cloud Framework Using Blockchain Based on DAT for Mobile IoT","authors":"Joong-Lyul Lee, Stephen C. Kerns, Sangjin Hong","doi":"10.1109/UEMCON47517.2019.8993056","DOIUrl":"https://doi.org/10.1109/UEMCON47517.2019.8993056","url":null,"abstract":"Internet of Things (IoT) devices are becoming important and familiar products in our everyday lives. Yet, many of these IoT devices have a multitude of vulnerabilities that create a security risk, despite being products that bring a lot of convenience to our lives. Blockchain (BC) technology is gaining popularity these days due to the importance of data security. However, this BC technology is not suitable for IoT devices, because it requires a lot of computing power also IoT devices uses a limited amount of memory and has a lower performing CPU for cost reasons. Also, IoT devices collect a large amount of data and transmit that data every hour and every day to a cloud system to analyze or process the collected data. For this reason, network latency is an important factor in a cloud computing system. In this paper, we propose a secure and distributed 10T-Fog-Cloud Framework using BC to compensate for the security weaknesses of IoT nodes, the delay aware tree construction (DATC) algorithm that considers the service delay for fog-cloud computing, and the mobility of mobile IoT nodes for BC to deal with the triangular routing problem. To verify this proposed framework, we performed security analysis and experiments for the effectiveness of the algorithm through simulation and confirmed that the overall service delay was reduced by choosing the minimum delay path by the DATC algorithm.","PeriodicalId":187022,"journal":{"name":"2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122280588","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：