Pub Date : 2020-09-01DOI: 10.1109/TransAI49837.2020.00027
Shreya Choksi, Peter Hong, Sohyb Mashkoor, C. Taswell
With the continuing growth in use of large complex data sets for artificial intelligence applications (AIA), unbiased methods should be established for assuring the validity and reliability of both input data and output results. Advancing such standards will help to reduce problems described with the aphorism ‘Garbage In, Garbage Out’ (GIGO). This concern remains especially important for AIA tools that execute within the environment of interoperable systems which share, exchange, convert, and/or interchange data and metadata such as the Nexus-PORTAL-DOORS-Scribe (NPDS) cyberinfrastructure and its associated Learning Intelligence aNd Knowledge System (LINKS) applications. The PORTAL-DOORS Project (PDP) has developed the NPDS cyberinfrastructure with lexical PORTAL registries, semantic DOORS directories, hybrid Nexus diristries, and Scribe registrars. As a self-referencing and self-describing system, the NPDS cyberinfrastructure has been designed to operate as a pervasive distributed network of data repositories compliant with the Hierarchically Distributed Mobile Metadata (HDMM) architectural style. Building on the foundation of the NPDS cyberinfrastructure with its focus on data, PDP has now introduced LINKS applications with their focus on algorithms and analysis of the data. In addition, PDP has launched a pair of new websites at NPDSLINKS.net and NPDSLINKS.org which will serve respectively as the root of the NPDS cyberinfrastructure and the home for definitions and standards on quality descriptors and quantitative measures to evaluate the data contained within NPDS records. Prototypes of these descriptors and measures for use with NPDS and LINKS are introduced in this report. PDP envisions building better AIA and preventing the unwanted phenomenon of GIGO by using the combination of metrics to detect and reduce bias from data, the NPDS cyberinfrastructure for the data, and LINKS applications for the algorithms.
{"title":"NPDSLINKS: Nexus-PORTAL-DOORS-Scribe Learning Intelligence aNd Knowledge System","authors":"Shreya Choksi, Peter Hong, Sohyb Mashkoor, C. Taswell","doi":"10.1109/TransAI49837.2020.00027","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00027","url":null,"abstract":"With the continuing growth in use of large complex data sets for artificial intelligence applications (AIA), unbiased methods should be established for assuring the validity and reliability of both input data and output results. Advancing such standards will help to reduce problems described with the aphorism ‘Garbage In, Garbage Out’ (GIGO). This concern remains especially important for AIA tools that execute within the environment of interoperable systems which share, exchange, convert, and/or interchange data and metadata such as the Nexus-PORTAL-DOORS-Scribe (NPDS) cyberinfrastructure and its associated Learning Intelligence aNd Knowledge System (LINKS) applications. The PORTAL-DOORS Project (PDP) has developed the NPDS cyberinfrastructure with lexical PORTAL registries, semantic DOORS directories, hybrid Nexus diristries, and Scribe registrars. As a self-referencing and self-describing system, the NPDS cyberinfrastructure has been designed to operate as a pervasive distributed network of data repositories compliant with the Hierarchically Distributed Mobile Metadata (HDMM) architectural style. Building on the foundation of the NPDS cyberinfrastructure with its focus on data, PDP has now introduced LINKS applications with their focus on algorithms and analysis of the data. In addition, PDP has launched a pair of new websites at NPDSLINKS.net and NPDSLINKS.org which will serve respectively as the root of the NPDS cyberinfrastructure and the home for definitions and standards on quality descriptors and quantitative measures to evaluate the data contained within NPDS records. Prototypes of these descriptors and measures for use with NPDS and LINKS are introduced in this report. PDP envisions building better AIA and preventing the unwanted phenomenon of GIGO by using the combination of metrics to detect and reduce bias from data, the NPDS cyberinfrastructure for the data, and LINKS applications for the algorithms.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124405575","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00019
James Brown, Aaditya Raval, Mohd Anwar
Passive biometrics and behavioral analytics seek to identify users based on their unique patterns of activities. In this paper, we test the feasibility of using time-varying inertia data as passive biometrics to be used for user identification and authentication. We present a deep learning model for inertia pattern recognition that achieved a high accuracy of 87.17%. A fully-connected sequential deep neural network was trained on 6730 sensor data samples, each having 15 features: triaxial measurements from accelerometer, gyroscope, magnetometer, and rotational vector. We further discuss the potential impact of inertia pattern recognition for user identification and authentication.
{"title":"Towards Passive Authentication using Inertia Variations: An Experimental Study on Smartphones","authors":"James Brown, Aaditya Raval, Mohd Anwar","doi":"10.1109/TransAI49837.2020.00019","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00019","url":null,"abstract":"Passive biometrics and behavioral analytics seek to identify users based on their unique patterns of activities. In this paper, we test the feasibility of using time-varying inertia data as passive biometrics to be used for user identification and authentication. We present a deep learning model for inertia pattern recognition that achieved a high accuracy of 87.17%. A fully-connected sequential deep neural network was trained on 6730 sensor data samples, each having 15 features: triaxial measurements from accelerometer, gyroscope, magnetometer, and rotational vector. We further discuss the potential impact of inertia pattern recognition for user identification and authentication.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124609126","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00031
Matthias Hofstetter, R. Riedl, Thomas Gees, A. Koumpis, Thomas Schaberreiter
Issues related to digital security are, there is no doubt for this, of utmost importance in the development of methods and support measures for organisations to successfully prepare for as well as realise their digital transformation. While big organisations and businesses may afford to buy services or develop their own in-house know-how and tools, small and medium-sized businesses are not having the means for this, be them financial resources, human resources or technology itself. This dystopic situation may on the other hand offer an unexpected and – as of today – yet unprecedented chance for innovations in terms of bridging the gap and addressing the need with use of AI technologies and services. In the paper we elaborate on a scenario that we have been developing as part of a European project that is part of the European Horizons 2020 project CS-AWARE.
{"title":"Applications of AI in cybersecurity","authors":"Matthias Hofstetter, R. Riedl, Thomas Gees, A. Koumpis, Thomas Schaberreiter","doi":"10.1109/TransAI49837.2020.00031","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00031","url":null,"abstract":"Issues related to digital security are, there is no doubt for this, of utmost importance in the development of methods and support measures for organisations to successfully prepare for as well as realise their digital transformation. While big organisations and businesses may afford to buy services or develop their own in-house know-how and tools, small and medium-sized businesses are not having the means for this, be them financial resources, human resources or technology itself. This dystopic situation may on the other hand offer an unexpected and – as of today – yet unprecedented chance for innovations in terms of bridging the gap and addressing the need with use of AI technologies and services. In the paper we elaborate on a scenario that we have been developing as part of a European project that is part of the European Horizons 2020 project CS-AWARE.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130497226","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00032
Baicun Wang, Xingyu Li, T. Freiheit, B. Epureanu
Industry 4.0 or smart manufacturing is often regarded as cyber-physical systems exclude humans. However, humans are still the designers of these so-called human-out-the-loop systems. Humans are very important elements of Industry 4.0, especially with regard to learning and intelligence, even though the human’s role and full integration in these systems is often overlooked. This paper proposes a unified framework to further the understanding of learning and intelligence in human-cyber-physical systems (HCPS) and to provide a more realistic and holistic understanding of Industry 4.0. The elements and sub-systems of HCPS learning and intelligence are introduced, and the applications and challenges for implementation of human-centered Industry 4.0 are discussed.
{"title":"Learning and Intelligence in Human-Cyber-Physical Systems: Framework and Perspective","authors":"Baicun Wang, Xingyu Li, T. Freiheit, B. Epureanu","doi":"10.1109/TransAI49837.2020.00032","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00032","url":null,"abstract":"Industry 4.0 or smart manufacturing is often regarded as cyber-physical systems exclude humans. However, humans are still the designers of these so-called human-out-the-loop systems. Humans are very important elements of Industry 4.0, especially with regard to learning and intelligence, even though the human’s role and full integration in these systems is often overlooked. This paper proposes a unified framework to further the understanding of learning and intelligence in human-cyber-physical systems (HCPS) and to provide a more realistic and holistic understanding of Industry 4.0. The elements and sub-systems of HCPS learning and intelligence are introduced, and the applications and challenges for implementation of human-centered Industry 4.0 are discussed.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126385925","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00015
Saurabh Mithe, Katerina Potika
Graphs contain a plethora of valuable information about the underlying data which can be extracted, analyzed, and visualized using Machine Learning (ML). The challenge is that graphs are non-Euclidean structures, and cannot be directly used with ML techniques. In order to overcome this challenge, one way is to encode nodes into an equivalent Euclidean representation in the form of a low-dimensional vector, also called an embedding vector, and the encoding process is called node embedding. During the recent years, various ML techniques have been developed that learn the encoding of the nodes automatically. Some of these techniques, called Graph Convolutional Networks (GCN), use variants of the convolutional neural networks adapted for graphs. The focus of this paper is two-fold. Firstly, to develop a unified framework focusing on three major GCN techniques in order to analyze, evaluate, and compare their performance on select benchmark datasets for the task of node classification. And secondly, to implement a new attention aggregator for GraphSAGE, and compare the performance of the aggregator with the existing GCN methods as well as the other aggregators provided by GraphSAGE.
{"title":"A unified framework on node classification using graph convolutional networks","authors":"Saurabh Mithe, Katerina Potika","doi":"10.1109/TransAI49837.2020.00015","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00015","url":null,"abstract":"Graphs contain a plethora of valuable information about the underlying data which can be extracted, analyzed, and visualized using Machine Learning (ML). The challenge is that graphs are non-Euclidean structures, and cannot be directly used with ML techniques. In order to overcome this challenge, one way is to encode nodes into an equivalent Euclidean representation in the form of a low-dimensional vector, also called an embedding vector, and the encoding process is called node embedding. During the recent years, various ML techniques have been developed that learn the encoding of the nodes automatically. Some of these techniques, called Graph Convolutional Networks (GCN), use variants of the convolutional neural networks adapted for graphs. The focus of this paper is two-fold. Firstly, to develop a unified framework focusing on three major GCN techniques in order to analyze, evaluate, and compare their performance on select benchmark datasets for the task of node classification. And secondly, to implement a new attention aggregator for GraphSAGE, and compare the performance of the aggregator with the existing GCN methods as well as the other aggregators provided by GraphSAGE.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123546925","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00011
Terence Griffin, Yu Cao, Benyuan Liu, M. Brunette
Tuberculosis (TB) is a contagious disease leading to the deaths of approximately 2 million people annually. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-CNN, Mask R-CNN, and Cascade versions of each, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that with a dataset of high-quality, object level annotations, object detection and segmentation of CXRs is possible and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis, if implemented within the corresponding health care system and adapted to existing clinical worktlows.
{"title":"Object Detection and Segmentation in Chest X-rays for Tuberculosis Screening","authors":"Terence Griffin, Yu Cao, Benyuan Liu, M. Brunette","doi":"10.1109/TransAI49837.2020.00011","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00011","url":null,"abstract":"Tuberculosis (TB) is a contagious disease leading to the deaths of approximately 2 million people annually. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-CNN, Mask R-CNN, and Cascade versions of each, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that with a dataset of high-quality, object level annotations, object detection and segmentation of CXRs is possible and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis, if implemented within the corresponding health care system and adapted to existing clinical worktlows.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129748032","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00018
Ying Fung Yiu, R. Mahapatra
Pathfinding problems often have to be solved under many constraints including limited processing time, memory, and computational power. The challenges become bigger as the size and complexity of the search space increase. Therefore, pathfinding on large and complex maps can result in performance bottlenecks. Researchers proposed to reduce the search space using preprocessing techniques such as hierarchical pathfinding to overcome the bottlenecks. In this paper we present a novel graph partition technique to boost the speed of pathfinding and preserve optimality for grid based environments. To overcome the weaknesses of clustering methods that are used in traditional hierarchical pathfinding algorithms, we propose to develop a graph decomposition algorithm that abstracts regions based on local features. The objective of our approach is to maintain the pathfinding optimality by only eliminating the regions that are obsolete. Thus, any possible solution path will not be eliminated during the search. Our experiment results show that a search space can be reduced as much as 47%, leading to much faster execution and less memory consumption.
{"title":"Regions Discovery Algorithm for Pathfinding in Grid Based Maps","authors":"Ying Fung Yiu, R. Mahapatra","doi":"10.1109/TransAI49837.2020.00018","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00018","url":null,"abstract":"Pathfinding problems often have to be solved under many constraints including limited processing time, memory, and computational power. The challenges become bigger as the size and complexity of the search space increase. Therefore, pathfinding on large and complex maps can result in performance bottlenecks. Researchers proposed to reduce the search space using preprocessing techniques such as hierarchical pathfinding to overcome the bottlenecks. In this paper we present a novel graph partition technique to boost the speed of pathfinding and preserve optimality for grid based environments. To overcome the weaknesses of clustering methods that are used in traditional hierarchical pathfinding algorithms, we propose to develop a graph decomposition algorithm that abstracts regions based on local features. The objective of our approach is to maintain the pathfinding optimality by only eliminating the regions that are obsolete. Thus, any possible solution path will not be eliminated during the search. Our experiment results show that a search space can be reduced as much as 47%, leading to much faster execution and less memory consumption.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125655149","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00029
Eren Kurshan, Honda Shen, Haojie Yu
In recent years, the unprecedented growth in digital payments fueled consequential changes in fraud and financial crimes. In this new landscape, traditional fraud detection approaches such as rule-based engines have largely become ineffective. AI and machine learning solutions using graph computing principles have gained significant interest. Graph neural networks and emerging adaptive solutions provide compelling opportunities for the future of fraud and financial crime detection. However, implementing the graph-based solutions in financial transaction processing systems has brought numerous obstacles and application considerations to light. In this paper, we overview the latest trends in the financial crimes landscape and discuss the implementation difficulties current and emerging graph solutions face. We argue that the application demands and implementation challenges provide key insights in developing effective solutions.
{"title":"Financial Crime & Fraud Detection Using Graph Computing: Application Considerations & Outlook","authors":"Eren Kurshan, Honda Shen, Haojie Yu","doi":"10.1109/TransAI49837.2020.00029","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00029","url":null,"abstract":"In recent years, the unprecedented growth in digital payments fueled consequential changes in fraud and financial crimes. In this new landscape, traditional fraud detection approaches such as rule-based engines have largely become ineffective. AI and machine learning solutions using graph computing principles have gained significant interest. Graph neural networks and emerging adaptive solutions provide compelling opportunities for the future of fraud and financial crime detection. However, implementing the graph-based solutions in financial transaction processing systems has brought numerous obstacles and application considerations to light. In this paper, we overview the latest trends in the financial crimes landscape and discuss the implementation difficulties current and emerging graph solutions face. We argue that the application demands and implementation challenges provide key insights in developing effective solutions.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131116971","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00020
M. Böhlen, W. Sujarwo
this paper gives an overview of the project Return to Bali that seeks to create a living dataset of ethnobotanically significant flora on the island of Bali and new methods through which underrepresented forms of knowledge can be documented, shared and made compatible within the logics of machine learning.
{"title":"Return to Bali","authors":"M. Böhlen, W. Sujarwo","doi":"10.1109/TransAI49837.2020.00020","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00020","url":null,"abstract":"this paper gives an overview of the project Return to Bali that seeks to create a living dataset of ethnobotanically significant flora on the island of Bali and new methods through which underrepresented forms of knowledge can be documented, shared and made compatible within the logics of machine learning.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129762570","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 : 2020-09-01DOI: 10.1109/TransAI49837.2020.00013
Najla Althuniyan, J. Sirrianni, Md Mahfuzer Rahman, X. Liu
People from different backgrounds share opinions about various issues over the Internet. The resulted discussions contain substantial information, from which we can derive the collective intelligence and the crowd wisdom. Several argumentation platforms have been developed to enable online deliberations with large-scale in-depth argumentation for effective online discussions. These platforms host structured argumentation networks that allow complex analytical models to mine the argumentation for collective intelligence. However, not all of those argumentation platforms were developed mobile applications. In this paper, we contribute with the design of a mobile application for cyber-argumentation. This mobile application supports intelligent cyber-argumentation and large-scale discussions and provides meaningful analytics on mobile devices. The platform has incorporated several analytical models to capture collective opinions, detect opinion polarization, and predict missing user opinions. An example is used to illustrate our design and models, and a system usability study of our application is presented. This application is an initial step to bring the multi-sided argumentation and deliberation into handheld devices and shows the potential in bringing multi-sided large-scale cyber-argumentation into the limited screen sizes platforms.
{"title":"Design and Analysis of Mobile App for Large-Scale Cyber-Argumentation","authors":"Najla Althuniyan, J. Sirrianni, Md Mahfuzer Rahman, X. Liu","doi":"10.1109/TransAI49837.2020.00013","DOIUrl":"https://doi.org/10.1109/TransAI49837.2020.00013","url":null,"abstract":"People from different backgrounds share opinions about various issues over the Internet. The resulted discussions contain substantial information, from which we can derive the collective intelligence and the crowd wisdom. Several argumentation platforms have been developed to enable online deliberations with large-scale in-depth argumentation for effective online discussions. These platforms host structured argumentation networks that allow complex analytical models to mine the argumentation for collective intelligence. However, not all of those argumentation platforms were developed mobile applications. In this paper, we contribute with the design of a mobile application for cyber-argumentation. This mobile application supports intelligent cyber-argumentation and large-scale discussions and provides meaningful analytics on mobile devices. The platform has incorporated several analytical models to capture collective opinions, detect opinion polarization, and predict missing user opinions. An example is used to illustrate our design and models, and a system usability study of our application is presented. This application is an initial step to bring the multi-sided argumentation and deliberation into handheld devices and shows the potential in bringing multi-sided large-scale cyber-argumentation into the limited screen sizes platforms.","PeriodicalId":151527,"journal":{"name":"2020 Second International Conference on Transdisciplinary AI (TransAI)","volume":"36 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131575395","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：