The enforcement of the General Data Protection Regulation (GDPR) represents a great challenge for online social networks (OSNs). Several OSNs are making significant changes to their systems to achieve compliance with GDPR. OSNs are required to obtain meaningful consent from users to achieve GDPR compliance. GDPR recognizes user's consent as a legitimate ground for personal data processing in the context of online social networks. This article presents a comparative study about the criteria for valid consent under GDPR and existing consent seeking practices of OSNs. In order to simplify the comparative process, Facebook is taken as a case study for online social networks. In conclusion of the comparative study, we argue that existing consent mechanisms in OSNs are not GDPR compliant. To achieve GDPR compliance in online social networks, we advocate a blockchain-based approach for consent management. This paper paves the way for designing a blockchain-based GDPR compliant consent management model for personal data processing in online social networks.
{"title":"GDPR Compliant Consent Driven Data Protection in Online Social Networks: A Blockchain-Based Approach","authors":"J. Ahmed, Sule YAYILGAN YILDIRIM, Mariusz Nowostaki, Raghvendra Ramachandra, Ogerta Elezaj, Mohamad Abomohara","doi":"10.1109/ICICT50521.2020.00054","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00054","url":null,"abstract":"The enforcement of the General Data Protection Regulation (GDPR) represents a great challenge for online social networks (OSNs). Several OSNs are making significant changes to their systems to achieve compliance with GDPR. OSNs are required to obtain meaningful consent from users to achieve GDPR compliance. GDPR recognizes user's consent as a legitimate ground for personal data processing in the context of online social networks. This article presents a comparative study about the criteria for valid consent under GDPR and existing consent seeking practices of OSNs. In order to simplify the comparative process, Facebook is taken as a case study for online social networks. In conclusion of the comparative study, we argue that existing consent mechanisms in OSNs are not GDPR compliant. To achieve GDPR compliance in online social networks, we advocate a blockchain-based approach for consent management. This paper paves the way for designing a blockchain-based GDPR compliant consent management model for personal data processing in online social networks.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116905563","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00093
Gokhan Sagirlar, John D. Sheehan, E. Ragnoli
Enabling blockchain technology into IoT can help to achieve a proper distributed consensus based IoT system that overcomes disadvantages of today’s centralized infrastructures, such as, among others, high cloud server maintenance costs, weakness for supporting time-critical IoT applications, security and trust issues. However, meeting requirements posed by IoT in blockchain domain is not an easy endeavour. [1] proposes Hybrid-IoT, as a step towards decentralizing IoT with the help of blockchain technology. Hybrid-IoT consists of multiple PoW sub-blockchains to achieve distributed consensus among IoT devices and an inter-connector framework, to execute transactions between sub-blockchains. In this paper, we take the first step towards designing an inter-connector for multiple blockchains for IoT that is specifically tailored for the Hybrid-IoT architecture. We also provide a detailed security discussion, in order to identify threats and we provide discussion on how to cope with threats.
{"title":"On the Design of Co-operating Blockchains for IoT","authors":"Gokhan Sagirlar, John D. Sheehan, E. Ragnoli","doi":"10.1109/ICICT50521.2020.00093","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00093","url":null,"abstract":"Enabling blockchain technology into IoT can help to achieve a proper distributed consensus based IoT system that overcomes disadvantages of today’s centralized infrastructures, such as, among others, high cloud server maintenance costs, weakness for supporting time-critical IoT applications, security and trust issues. However, meeting requirements posed by IoT in blockchain domain is not an easy endeavour. [1] proposes Hybrid-IoT, as a step towards decentralizing IoT with the help of blockchain technology. Hybrid-IoT consists of multiple PoW sub-blockchains to achieve distributed consensus among IoT devices and an inter-connector framework, to execute transactions between sub-blockchains. In this paper, we take the first step towards designing an inter-connector for multiple blockchains for IoT that is specifically tailored for the Hybrid-IoT architecture. We also provide a detailed security discussion, in order to identify threats and we provide discussion on how to cope with threats.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"1084 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127430671","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00032
Nawaf O. Alsrehin, Mu’tasem A. Al-Taamneh
Face recognition is the process of identifying a person by their facial characteristics from a digital image or a video frame. Face recognition has extensive applications and there will be a massive development in future technologies. The main contribution of this research is to perform a comparative study between different statistical-based face recognition techniques, namely: Eigen-faces, Fisher-faces, and Local Binary Patterns Histograms (LBPH) to measure their effectiveness and efficiency using real-database images. These recognizers still used on top of commercial face recognition products. Additionally, this research is comprehensively comparing 17 face-recognition techniques adopted in research and industry that use artificial-neural network, criticize and categories them into an understandable category. Also, this research provides some directions and suggestions to overcome the direct and indirect issues for face recognition. It has found that there is no existing recognition method that the community of face recognition has agreed on and solves all the issues that face the recognition, such as different pose variation, illumination, blurry and low-resolution images. This study is important to the recognition communities, software companies, and government security officials. It has a direct impact on drawing clear path for new face recognition propositions. This study is one of the studies with respect to the size of its reviewed approaches and techniques.
{"title":"Face Recognition Techniques using Statistical and Artificial Neural Network: A Comparative Study","authors":"Nawaf O. Alsrehin, Mu’tasem A. Al-Taamneh","doi":"10.1109/ICICT50521.2020.00032","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00032","url":null,"abstract":"Face recognition is the process of identifying a person by their facial characteristics from a digital image or a video frame. Face recognition has extensive applications and there will be a massive development in future technologies. The main contribution of this research is to perform a comparative study between different statistical-based face recognition techniques, namely: Eigen-faces, Fisher-faces, and Local Binary Patterns Histograms (LBPH) to measure their effectiveness and efficiency using real-database images. These recognizers still used on top of commercial face recognition products. Additionally, this research is comprehensively comparing 17 face-recognition techniques adopted in research and industry that use artificial-neural network, criticize and categories them into an understandable category. Also, this research provides some directions and suggestions to overcome the direct and indirect issues for face recognition. It has found that there is no existing recognition method that the community of face recognition has agreed on and solves all the issues that face the recognition, such as different pose variation, illumination, blurry and low-resolution images. This study is important to the recognition communities, software companies, and government security officials. It has a direct impact on drawing clear path for new face recognition propositions. This study is one of the studies with respect to the size of its reviewed approaches and techniques.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122066221","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00080
Maria Zafar, Seerat Iqbal Cheema
Session initiation protocol deployments in VoIP networks primarily emerged with an aim to ensure high scalability, simplicity and flexibility. Despite all the listed advantages, the increasing SIP signaling traffic needs to invoke methods attempting to mitigate overload and fail over that the data centers are usually facing. In this paper, a load balancing model based on cluster based replication architecture is proposed to achieve high capacity and a highly available architecture. We quantitatively measure the improvements by implementing asterisk and openSIP based server setup for voice exchange for the indication of scalable and redundant architecture. In the past years, high availability was achieved by host per host redundancy declaring it as an expensive technique for hardware. Our proposed technique is suitable for a redundant system with mission critical applications and can be offered to extend the service level by sharing the running virtual machines while duplicating the resources. The proposed model implemented in our test-bed configured three asterisk servers and the node statistics are tested via cacti server to guarantee the failover technique. The experimental results establish that the proposed model reduce low server utilization and lack of power proportionality. The proposed solution is unique in its way that it is also recommended for complex and unmanageable environment without relying on add on balancing methods.
{"title":"An Efficient Architecture for Network Information Management","authors":"Maria Zafar, Seerat Iqbal Cheema","doi":"10.1109/ICICT50521.2020.00080","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00080","url":null,"abstract":"Session initiation protocol deployments in VoIP networks primarily emerged with an aim to ensure high scalability, simplicity and flexibility. Despite all the listed advantages, the increasing SIP signaling traffic needs to invoke methods attempting to mitigate overload and fail over that the data centers are usually facing. In this paper, a load balancing model based on cluster based replication architecture is proposed to achieve high capacity and a highly available architecture. We quantitatively measure the improvements by implementing asterisk and openSIP based server setup for voice exchange for the indication of scalable and redundant architecture. In the past years, high availability was achieved by host per host redundancy declaring it as an expensive technique for hardware. Our proposed technique is suitable for a redundant system with mission critical applications and can be offered to extend the service level by sharing the running virtual machines while duplicating the resources. The proposed model implemented in our test-bed configured three asterisk servers and the node statistics are tested via cacti server to guarantee the failover technique. The experimental results establish that the proposed model reduce low server utilization and lack of power proportionality. The proposed solution is unique in its way that it is also recommended for complex and unmanageable environment without relying on add on balancing methods.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126881649","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00091
Pablo Pico-Valencia, J. A. Holgado-Terriza, Xavier Quiñónez-Ku
The Internet of Things (IoT) is an approach that arose as an alternative to handle billions of digital devices, people and services of the real-world which are interconnected over Internet. In this paper, we present a comprehensive survey where main paradigms associated with IoT -Internet of Services (IoS), Internet of People (IoP), Internet of Content (IoC) and the emerging Internet of Agents (IoA)- are outlined. We analyze these paradigms in terms of their definition, scope, goals and their correlation with the IoT in order to identify the main challenges that will involve to the next generation of the IoT applying a process of agentification to achieve more autonomous, collaborative and intelligent IoT systems.
{"title":"A Brief Survey of the Main Internet-Based Approaches. An Outlook from the Internet of Things Perspective","authors":"Pablo Pico-Valencia, J. A. Holgado-Terriza, Xavier Quiñónez-Ku","doi":"10.1109/ICICT50521.2020.00091","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00091","url":null,"abstract":"The Internet of Things (IoT) is an approach that arose as an alternative to handle billions of digital devices, people and services of the real-world which are interconnected over Internet. In this paper, we present a comprehensive survey where main paradigms associated with IoT -Internet of Services (IoS), Internet of People (IoP), Internet of Content (IoC) and the emerging Internet of Agents (IoA)- are outlined. We analyze these paradigms in terms of their definition, scope, goals and their correlation with the IoT in order to identify the main challenges that will involve to the next generation of the IoT applying a process of agentification to achieve more autonomous, collaborative and intelligent IoT systems.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126374700","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00033
Ming Xu, Z. Tian
An image cipher based on Latin cubes is presented in this paper. Latin cube is the high-dimensional form of Latin square. Although Latin squares have been widely used in image encryption, the applications of Latin cubes in image encryption are still relatively few. Analogous to Latin squares, Latin cubes also have some excellent cryptographic properties, such as discreteness and uniformity. Specifically, Latin cubes have 3D attribute. Based on these properties, a permutation scheme which is highly plaintext-related and a substitution scheme which has strong diffusivity have been constructed in this paper. Simulation results demonstrate that the proposed algorithm has high security. It is therefore very suitable for the insecure network environment.
{"title":"An Image Cipher Based on Latin Cubes","authors":"Ming Xu, Z. Tian","doi":"10.1109/ICICT50521.2020.00033","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00033","url":null,"abstract":"An image cipher based on Latin cubes is presented in this paper. Latin cube is the high-dimensional form of Latin square. Although Latin squares have been widely used in image encryption, the applications of Latin cubes in image encryption are still relatively few. Analogous to Latin squares, Latin cubes also have some excellent cryptographic properties, such as discreteness and uniformity. Specifically, Latin cubes have 3D attribute. Based on these properties, a permutation scheme which is highly plaintext-related and a substitution scheme which has strong diffusivity have been constructed in this paper. Simulation results demonstrate that the proposed algorithm has high security. It is therefore very suitable for the insecure network environment.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"170 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115823645","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00019
P. Bearse, Omar Manejwala, Atif Farid Mohammad, I. R. I. Haque
There is increasing evidence that better health outcomes for patients can be achieved with improvement in mental health. Loneliness, one such condition, is itself toxic consequently driving increase in both chronic disease morbidity and mortality. Thus, the early identification of loneliness and interventions to address it are of urgent importance. One potential mechanism for identifying loneliness rests in analyzing care provider notes which include details regarding a provider's interaction with patients and often provide insights about both mental and physical health. To automatically determine which patients are suffering from loneliness, a data science analysis based on natural language processing techniques was performed on clinical notes from 12 care providers for 128 patients. The analysis techniques included co-occurrence of uni-gram, bi-gram, tri-gram and quad-gram words; sentiment analysis using AFINN sentiment lexicon scores; and word usage frequencies. The results surfaced key challenges associated with determining the presence of loneliness suggested the importance of including validated clinical questionnaires specifically designed for identifying loneliness.
{"title":"An Initial Feasibility Study to Identify Loneliness Among Mental Health Patients from Clinical Notes","authors":"P. Bearse, Omar Manejwala, Atif Farid Mohammad, I. R. I. Haque","doi":"10.1109/ICICT50521.2020.00019","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00019","url":null,"abstract":"There is increasing evidence that better health outcomes for patients can be achieved with improvement in mental health. Loneliness, one such condition, is itself toxic consequently driving increase in both chronic disease morbidity and mortality. Thus, the early identification of loneliness and interventions to address it are of urgent importance. One potential mechanism for identifying loneliness rests in analyzing care provider notes which include details regarding a provider's interaction with patients and often provide insights about both mental and physical health. To automatically determine which patients are suffering from loneliness, a data science analysis based on natural language processing techniques was performed on clinical notes from 12 care providers for 128 patients. The analysis techniques included co-occurrence of uni-gram, bi-gram, tri-gram and quad-gram words; sentiment analysis using AFINN sentiment lexicon scores; and word usage frequencies. The results surfaced key challenges associated with determining the presence of loneliness suggested the importance of including validated clinical questionnaires specifically designed for identifying loneliness.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130957680","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00051
Badhrinarayan Malolan, Ankit Parekh, F. Kazi
Deep-Fakes have sparked concerns throughout the world because of their potentially explosive consequences. A dystopian future where all forms of digital media are potentially compromised and public trust in Government is scarce doesn't seem far off. If not dealt with the requisite seriousness, the situation could easily spiral out of control. Current methods of Deep-Fake detection aim to accurately solve the issue at hand but may fail to convince a lay-person of its reliability and thus, lack the trust of the general public. Since the fundamental issue revolves around earning the trust of human agents, the construction of interpretable and also easily explainable models is imperative. We propose a framework to detect these Deep-Fake videos using a Deep Learning Approach: we have trained a Convolutional Neural Network architecture on a database of extracted faces from FaceForensics' DeepFakeDetection Dataset. Furthermore, we have tested the model on various Explainable AI techniques such as LRP and LIME to provide crisp visualizations of the salient regions of the image focused on by the model. The prospective and elusive goal is to localize the facial manipulations caused by Faceswaps. We hope to use this approach to build trust between AI and Human agents and to demonstrate the applicability of XAI in various real-life scenarios.
{"title":"Explainable Deep-Fake Detection Using Visual Interpretability Methods","authors":"Badhrinarayan Malolan, Ankit Parekh, F. Kazi","doi":"10.1109/ICICT50521.2020.00051","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00051","url":null,"abstract":"Deep-Fakes have sparked concerns throughout the world because of their potentially explosive consequences. A dystopian future where all forms of digital media are potentially compromised and public trust in Government is scarce doesn't seem far off. If not dealt with the requisite seriousness, the situation could easily spiral out of control. Current methods of Deep-Fake detection aim to accurately solve the issue at hand but may fail to convince a lay-person of its reliability and thus, lack the trust of the general public. Since the fundamental issue revolves around earning the trust of human agents, the construction of interpretable and also easily explainable models is imperative. We propose a framework to detect these Deep-Fake videos using a Deep Learning Approach: we have trained a Convolutional Neural Network architecture on a database of extracted faces from FaceForensics' DeepFakeDetection Dataset. Furthermore, we have tested the model on various Explainable AI techniques such as LRP and LIME to provide crisp visualizations of the salient regions of the image focused on by the model. The prospective and elusive goal is to localize the facial manipulations caused by Faceswaps. We hope to use this approach to build trust between AI and Human agents and to demonstrate the applicability of XAI in various real-life scenarios.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133687010","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 : 2020-03-01DOI: 10.1109/ICICT50521.2020.00029
J. Pinzón-Arenas, R. Jiménez-Moreno
Obstacle detection has been a relevant issue for the implementation of autonomous robotic systems, within which increasingly robust algorithms have begun to be applied, especially Deep Learning techniques. However, these have not been widely used for the detection of obstacles in static robotic agents, contrary to what happens with mobile agents. For this reason, this work explores the use of one of these techniques, which is a neural network based on the Faster R-CNN, focused on detecting a specific obstacle (hands) in an application environment for a food assistance robot. For this purpose, a database containing 6205 training images and 1350 validation images was prepared, where 31 users perform different movements with their hands. To verify the capacity of the network, 3 architectures of different depths were implemented, which were evaluated and compared, resulting in the network of greater depth obtained the highest accuracy, of 77.4%, taking into account that the hands are not only still but also in movement, generating distortion in them and greater difficulty for their detection. Also, the internal behavior of the network was visualized through activations, to verify what it had learned, showing that it managed to focus on the hands, with some activations located in parts of the user's body such as face and arm.
{"title":"Obstacle Detection Using Faster R-CNN Oriented to an Autonomous Feeding Assistance System","authors":"J. Pinzón-Arenas, R. Jiménez-Moreno","doi":"10.1109/ICICT50521.2020.00029","DOIUrl":"https://doi.org/10.1109/ICICT50521.2020.00029","url":null,"abstract":"Obstacle detection has been a relevant issue for the implementation of autonomous robotic systems, within which increasingly robust algorithms have begun to be applied, especially Deep Learning techniques. However, these have not been widely used for the detection of obstacles in static robotic agents, contrary to what happens with mobile agents. For this reason, this work explores the use of one of these techniques, which is a neural network based on the Faster R-CNN, focused on detecting a specific obstacle (hands) in an application environment for a food assistance robot. For this purpose, a database containing 6205 training images and 1350 validation images was prepared, where 31 users perform different movements with their hands. To verify the capacity of the network, 3 architectures of different depths were implemented, which were evaluated and compared, resulting in the network of greater depth obtained the highest accuracy, of 77.4%, taking into account that the hands are not only still but also in movement, generating distortion in them and greater difficulty for their detection. Also, the internal behavior of the network was visualized through activations, to verify what it had learned, showing that it managed to focus on the hands, with some activations located in parts of the user's body such as face and arm.","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123956640","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 : 2020-03-01DOI: 10.1109/icict50521.2020.00002
{"title":"[Title page iii]","authors":"","doi":"10.1109/icict50521.2020.00002","DOIUrl":"https://doi.org/10.1109/icict50521.2020.00002","url":null,"abstract":"","PeriodicalId":445000,"journal":{"name":"2020 3rd International Conference on Information and Computer Technologies (ICICT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130665147","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：