Pub Date : 2019-02-01DOI: 10.23919/ICACT.2019.8702005
Jinhong Yang, Chul-Soo Kim, Md. Mehedi Hassan Onik
There is a growing interest in personal data mining and user profiling to improve the surveillance practices for rapid analysis of underlying business patterns. User profiling from Personally Identifiable Information (PII) is one such technique to breach personal data privacy in mobile devices, web browser, smart homes, Internet of Things (IoT) etc. This study proposes a PII risk factor by bringing aggregated risk modelling of personal information in the IoT environment. Intuitively, most of the IoT devices are produced by identical manufacturers. Similarly, smart devices typically assemble facts from plentiful devices where collected information’s owners are mutually inclusive. Proposed Massive Personal Information Clustering (MPIC) model shows that IoT product manufacturing companies can cluster PII collected from a) IoT device managing application and b) device data flow. Subsequently, owner-centric aggregated IoT device data can reveal user ID, which was not considered by other studies. Our approach was validated by satisfactory data analysis from IoT standardization organization (Open Connectivity Forum), Android and iOS app store. The analysis shows 80-90 percent of available IoT devices are manufactured by 6-10 major companies with 5 potential PII threats. Personal information like location, email, biological ID, contextual actions and social graph are at risk if collective information gathering (aggregation) through multiple IoT devices are not correctly measured. Finally, research directions in establishing privacy preservation in smart IoT ecosystem are advocated.
{"title":"Aggregated Risk Modelling of Personal Data Privacy in Internet of Things","authors":"Jinhong Yang, Chul-Soo Kim, Md. Mehedi Hassan Onik","doi":"10.23919/ICACT.2019.8702005","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8702005","url":null,"abstract":"There is a growing interest in personal data mining and user profiling to improve the surveillance practices for rapid analysis of underlying business patterns. User profiling from Personally Identifiable Information (PII) is one such technique to breach personal data privacy in mobile devices, web browser, smart homes, Internet of Things (IoT) etc. This study proposes a PII risk factor by bringing aggregated risk modelling of personal information in the IoT environment. Intuitively, most of the IoT devices are produced by identical manufacturers. Similarly, smart devices typically assemble facts from plentiful devices where collected information’s owners are mutually inclusive. Proposed Massive Personal Information Clustering (MPIC) model shows that IoT product manufacturing companies can cluster PII collected from a) IoT device managing application and b) device data flow. Subsequently, owner-centric aggregated IoT device data can reveal user ID, which was not considered by other studies. Our approach was validated by satisfactory data analysis from IoT standardization organization (Open Connectivity Forum), Android and iOS app store. The analysis shows 80-90 percent of available IoT devices are manufactured by 6-10 major companies with 5 potential PII threats. Personal information like location, email, biological ID, contextual actions and social graph are at risk if collective information gathering (aggregation) through multiple IoT devices are not correctly measured. Finally, research directions in establishing privacy preservation in smart IoT ecosystem are advocated.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129108981","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701978
Sunwon Kang, Namgi Kim, Byoung-Dai Lee
In this paper, we propose a fine dust forecast model based on deep neural networks. The proposed model uses five kinds of air quality-related information as input variables and presents fine dust levels on an hourly basis. For training, we built training datasets by crawling air quality open data provided by the Korea Meteorological Administration and Seoul City. According to the experimental results, the proposed method achieved an RMSE of 8.966 for the prediction of fine dust levels after one hour.
{"title":"Fine Dust Forecast Based on Recurrent Neural Networks","authors":"Sunwon Kang, Namgi Kim, Byoung-Dai Lee","doi":"10.23919/ICACT.2019.8701978","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701978","url":null,"abstract":"In this paper, we propose a fine dust forecast model based on deep neural networks. The proposed model uses five kinds of air quality-related information as input variables and presents fine dust levels on an hourly basis. For training, we built training datasets by crawling air quality open data provided by the Korea Meteorological Administration and Seoul City. According to the experimental results, the proposed method achieved an RMSE of 8.966 for the prediction of fine dust levels after one hour.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120957188","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701908
Han Qing, Siji Chen, Md Liton Ali, Bin Shen
This paper investigates power-law detector (PLD) based wideband spectrum sensing schemes for OFDM cognitive radios. By exploiting signal assemblage (SA) feature of the primary user (PU), we first propose a heuristic iterative threshold test (HITT) to roughly detect the SA set boundary of the noise and PU signal; Subsequently, a signal assemblage cardinality measuring (SACM) method is developed to refine the HITT decisions. Operating in SA-based wideband sensing manner, the PLD greatly overcomes the ambiguity in differentiating weak PU subcarriers from noise and significantly meliorates the sensing performance, compared with the non-SA methods.
{"title":"Signal Assemblage Based Wideband Spectrum Sensing for OFDM Cognitive Radios","authors":"Han Qing, Siji Chen, Md Liton Ali, Bin Shen","doi":"10.23919/ICACT.2019.8701908","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701908","url":null,"abstract":"This paper investigates power-law detector (PLD) based wideband spectrum sensing schemes for OFDM cognitive radios. By exploiting signal assemblage (SA) feature of the primary user (PU), we first propose a heuristic iterative threshold test (HITT) to roughly detect the SA set boundary of the noise and PU signal; Subsequently, a signal assemblage cardinality measuring (SACM) method is developed to refine the HITT decisions. Operating in SA-based wideband sensing manner, the PLD greatly overcomes the ambiguity in differentiating weak PU subcarriers from noise and significantly meliorates the sensing performance, compared with the non-SA methods.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"319 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124511617","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701977
Sangha Choi, Wooshik Kim, Sugjoon Yoon
MATLAB has been widely used for providing a variety of functions and tools in engineering computing, numerical analysis, modeling and visualization. In particular, through 3D animation, MATLAB has advantages for M&S (Modeling & Simulation). High Level Architecture (HLA) is a general standard for interoperability and reusability in M&S. 3D animation has been used in the distributed simulations for the simulation analysis. In the distributed simulations, objects or entities continuously occur changes. Each change requires modifying its 3D animation objects or entities. It would be a problem in larger simulation environment. This paper proposes the method of an automatic-generate-3D-animation builder in MATLAB. The 3D-animation builder supports advantages of the HLA based distributed simulations. In this paper, we introduce design of a 3D-animation builder. We also present the example of an HLA-based simulation with the 3D-animation builder that could fully support the advantages of HLA simulation.
{"title":"Design of 3D Animation Builder with HLA Based Distributed Simulations","authors":"Sangha Choi, Wooshik Kim, Sugjoon Yoon","doi":"10.23919/ICACT.2019.8701977","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701977","url":null,"abstract":"MATLAB has been widely used for providing a variety of functions and tools in engineering computing, numerical analysis, modeling and visualization. In particular, through 3D animation, MATLAB has advantages for M&S (Modeling & Simulation). High Level Architecture (HLA) is a general standard for interoperability and reusability in M&S. 3D animation has been used in the distributed simulations for the simulation analysis. In the distributed simulations, objects or entities continuously occur changes. Each change requires modifying its 3D animation objects or entities. It would be a problem in larger simulation environment. This paper proposes the method of an automatic-generate-3D-animation builder in MATLAB. The 3D-animation builder supports advantages of the HLA based distributed simulations. In this paper, we introduce design of a 3D-animation builder. We also present the example of an HLA-based simulation with the 3D-animation builder that could fully support the advantages of HLA simulation.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124131601","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8702043
T. Jo
This research is concerned with the string vector based version of the KNN which is the approach to the text categorization. Traditionally, texts have been encoded into numerical vectors for using the traditional version of KNN, and encoding so leads to the three main problems: huge dimensionality, sparse distribution, and poor transparency. In order to solve the problems, this research propose that texts should be encoded into string vectors the similarity measure between string vectors is defined, and the KNN is modified into the version where string vector is given its input. The proposed KNN version is validated empirically by comparing it with the traditional KNN version on the three collections: NewsPage.com, Opiniopsis, and 20NewsGroups. The goal of this research is to improve the text categorization performance by solving them.
{"title":"Improving K Nearest Neighbor into String Vector Version for Text Categorization","authors":"T. Jo","doi":"10.23919/ICACT.2019.8702043","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8702043","url":null,"abstract":"This research is concerned with the string vector based version of the KNN which is the approach to the text categorization. Traditionally, texts have been encoded into numerical vectors for using the traditional version of KNN, and encoding so leads to the three main problems: huge dimensionality, sparse distribution, and poor transparency. In order to solve the problems, this research propose that texts should be encoded into string vectors the similarity measure between string vectors is defined, and the KNN is modified into the version where string vector is given its input. The proposed KNN version is validated empirically by comparing it with the traditional KNN version on the three collections: NewsPage.com, Opiniopsis, and 20NewsGroups. The goal of this research is to improve the text categorization performance by solving them.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134154426","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701911
Yunhan Long, R. Yamamoto, Taku Yamazaki, Y. Tanaka
With the demand for rapid exchanges of information, device to device (D2D) communications become one of the essential components of next-generation network architecture. To realize efficient D2D communication, peer discovery plays an important role since the discovery result strongly affects further performance. Most of the researches on peer discovery in D2D communication are based on discovering proximity devices to recognize nearby destination devices. In particular, some researches focus on time slot distribution to broadcast address information for discovering proximity devices. Moreover, other researches pay attention to user grouping with different beacon probing signals. However, these peer discovery mechanisms do not consider the risks that source devices may encounter malicious devices in real situations. As a solution to this, this paper proposes a peer discovery mechanism which applies the social network relationship information to exclude malicious devices. The proposed mechanism contributes to decrease the probability of encountering malicious devices and enhances the efficiency of peer discovery by excluding malicious devices. Simulations clarify that the base station (BS) extracts trusted candidates among devices to quantify the trust degree of devices based on the potential social information.
{"title":"A Deep Learning Based Social-aware D2D Peer Discovery Mechanism","authors":"Yunhan Long, R. Yamamoto, Taku Yamazaki, Y. Tanaka","doi":"10.23919/ICACT.2019.8701911","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701911","url":null,"abstract":"With the demand for rapid exchanges of information, device to device (D2D) communications become one of the essential components of next-generation network architecture. To realize efficient D2D communication, peer discovery plays an important role since the discovery result strongly affects further performance. Most of the researches on peer discovery in D2D communication are based on discovering proximity devices to recognize nearby destination devices. In particular, some researches focus on time slot distribution to broadcast address information for discovering proximity devices. Moreover, other researches pay attention to user grouping with different beacon probing signals. However, these peer discovery mechanisms do not consider the risks that source devices may encounter malicious devices in real situations. As a solution to this, this paper proposes a peer discovery mechanism which applies the social network relationship information to exclude malicious devices. The proposed mechanism contributes to decrease the probability of encountering malicious devices and enhances the efficiency of peer discovery by excluding malicious devices. Simulations clarify that the base station (BS) extracts trusted candidates among devices to quantify the trust degree of devices based on the potential social information.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131468015","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701893
Soonchul Jung, Taewon Choi, Yoon-Seok Choi, In-Su Jang, Jae Woo Kim, Jin-Seo Kim
Safeguarding intangible cultural heritage such as traditional painting is getting more critical, but the conventional way to preserve intangible heritage has been to simply record the performance and explanations of Living Human Treasures using video cameras. It cannot preserve the whole procedure and detailed performances of human experts. In this paper, we suggest a multisensory system that captures the core activities of Korean traditional painting while minimizing interference with their activities. The system captures the whole procedures of the activities by tracking the three-dimensional movements of the painter and the brushes, and recording information of the pigments and canvas. We captured the activities of two professional painters and analyzed the brush movements in various ways.
{"title":"Multisensory Capture System for the Preservation of Traditional Painting","authors":"Soonchul Jung, Taewon Choi, Yoon-Seok Choi, In-Su Jang, Jae Woo Kim, Jin-Seo Kim","doi":"10.23919/ICACT.2019.8701893","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701893","url":null,"abstract":"Safeguarding intangible cultural heritage such as traditional painting is getting more critical, but the conventional way to preserve intangible heritage has been to simply record the performance and explanations of Living Human Treasures using video cameras. It cannot preserve the whole procedure and detailed performances of human experts. In this paper, we suggest a multisensory system that captures the core activities of Korean traditional painting while minimizing interference with their activities. The system captures the whole procedures of the activities by tracking the three-dimensional movements of the painter and the brushes, and recording information of the pigments and canvas. We captured the activities of two professional painters and analyzed the brush movements in various ways.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131008298","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 : 2019-02-01DOI: 10.23919/icact.2019.8701889
{"title":"ICACT 2019 Welcome Message","authors":"","doi":"10.23919/icact.2019.8701889","DOIUrl":"https://doi.org/10.23919/icact.2019.8701889","url":null,"abstract":"","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133039079","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 : 2019-02-01DOI: 10.23919/ICACT.2019.8701923
Hyunsuk Choi, Nawab Muhammad Faseeh Qureshi, D. Shin
Machine learning is a state-of-the-art sub-project of artificial intelligence, that is been evolved for finding large-scale intelligent analytics in the distributed computing environment. In this paper, we perform comparative analytics onto dataset collected for the electricity usage of home based on the K-mean clustering algorithm using comparison to silhouette score with a ratio of 1/8 dataset. The performance evaluation shows that, the comparison index is similar in numbers of silhouette score even if dataset is smaller than before.
{"title":"Comparative Analysis of Electricity Consumption at Home through a Silhouette-score prospective","authors":"Hyunsuk Choi, Nawab Muhammad Faseeh Qureshi, D. Shin","doi":"10.23919/ICACT.2019.8701923","DOIUrl":"https://doi.org/10.23919/ICACT.2019.8701923","url":null,"abstract":"Machine learning is a state-of-the-art sub-project of artificial intelligence, that is been evolved for finding large-scale intelligent analytics in the distributed computing environment. In this paper, we perform comparative analytics onto dataset collected for the electricity usage of home based on the K-mean clustering algorithm using comparison to silhouette score with a ratio of 1/8 dataset. The performance evaluation shows that, the comparison index is similar in numbers of silhouette score even if dataset is smaller than before.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133334164","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 : 2019-02-01DOI: 10.23919/icact.2019.8702023
G. Fokin
Actual trends in current passive geolocation system development includes cooperation of flying segment based on receiver stations aboard Unmanned Aerial Vehicles (UAVs) with terrestrial segment including stationary ground receiver stations. Existing accuracy results achieves the order of tens and hundreds of meters in optimistic Line of Sight (LOS) conditions, however the problem of radio emission sources positioning with UAVs is especially relevant for search and rescue operations in heterogeneous terrain, when separate primary measurements obtained, for example, after reflections, could lead to a significant error. One possible way to improve the accuracy of positioning in such conditions is to use aerial passive geolocation based on UAVs with joint processing of Time Difference of Arrival (TDOA) and Angle of Arrival (AOA) primary measurements. The contribution of the current investigation is the development of mathematical model for positioning of radio emission sources with UAVs using TDOA-AOA measurement processing and performance evaluation of hybrid measurement processing with handling AOA noise.
{"title":"Passive Geolocation with Unmanned Aerial Vehicles using TDOA-AOA Measurement Processing","authors":"G. Fokin","doi":"10.23919/icact.2019.8702023","DOIUrl":"https://doi.org/10.23919/icact.2019.8702023","url":null,"abstract":"Actual trends in current passive geolocation system development includes cooperation of flying segment based on receiver stations aboard Unmanned Aerial Vehicles (UAVs) with terrestrial segment including stationary ground receiver stations. Existing accuracy results achieves the order of tens and hundreds of meters in optimistic Line of Sight (LOS) conditions, however the problem of radio emission sources positioning with UAVs is especially relevant for search and rescue operations in heterogeneous terrain, when separate primary measurements obtained, for example, after reflections, could lead to a significant error. One possible way to improve the accuracy of positioning in such conditions is to use aerial passive geolocation based on UAVs with joint processing of Time Difference of Arrival (TDOA) and Angle of Arrival (AOA) primary measurements. The contribution of the current investigation is the development of mathematical model for positioning of radio emission sources with UAVs using TDOA-AOA measurement processing and performance evaluation of hybrid measurement processing with handling AOA noise.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132294111","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：