Pub Date : 2018-10-01DOI: 10.1109/ICTC.2018.8539605
Jae-Hyuck Park, Yookyung Kim
This paper deals with a problem of digital communication which samples a signal compressively below its symbol rate and restores the original message symbols. We propose a method to optimize the sensing and restoration modules by designing them as the encoder and decoder of a convolutional autoencoder. The network learns end-to-end through simulation data. Our architecture has an efficient mechanism to solve this compressive symbol detection problem and it shows strong performance and fast speed empirically.
{"title":"Convolutional Autoencoder for Compressive Symbol Detection","authors":"Jae-Hyuck Park, Yookyung Kim","doi":"10.1109/ICTC.2018.8539605","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539605","url":null,"abstract":"This paper deals with a problem of digital communication which samples a signal compressively below its symbol rate and restores the original message symbols. We propose a method to optimize the sensing and restoration modules by designing them as the encoder and decoder of a convolutional autoencoder. The network learns end-to-end through simulation data. Our architecture has an efficient mechanism to solve this compressive symbol detection problem and it shows strong performance and fast speed empirically.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133929156","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539375
Yared Zerihun Bekele, Young-June Choi
To accommodate the massive connectivity of Internet-of-Things (IoT) such as a smart meter application for cellular networks, 3GPP has standardized Machine Type Communication (MTC) and cellular IoT. The data transmission of such IoT exhibits a time-controlled and an event-driven feature which delivers short messages with low data rate but supports massive connectivity. In MTC and its advanced system including eMTC and 5G-NR, legacy data and IoT data share radio resource; thus, any existing scheduler can handle both types of data separately. In this paper, we prove that existing schedulers that favor instantaneous channel quality do not work effectively for IoT data. Based on this property, we suggest a modified First Maximum Expansion (m-FME) algorithm that removes channel feedback. Through simulation, we confirm that m-FME outperforms existing schedulers.
{"title":"Scheduling for Machine Type Communications in LTE Systems","authors":"Yared Zerihun Bekele, Young-June Choi","doi":"10.1109/ICTC.2018.8539375","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539375","url":null,"abstract":"To accommodate the massive connectivity of Internet-of-Things (IoT) such as a smart meter application for cellular networks, 3GPP has standardized Machine Type Communication (MTC) and cellular IoT. The data transmission of such IoT exhibits a time-controlled and an event-driven feature which delivers short messages with low data rate but supports massive connectivity. In MTC and its advanced system including eMTC and 5G-NR, legacy data and IoT data share radio resource; thus, any existing scheduler can handle both types of data separately. In this paper, we prove that existing schedulers that favor instantaneous channel quality do not work effectively for IoT data. Based on this property, we suggest a modified First Maximum Expansion (m-FME) algorithm that removes channel feedback. Through simulation, we confirm that m-FME outperforms existing schedulers.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132924969","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539636
Junghyun Kim, Seongjae Moon, Youngwoo Kim, Sunghoon Hong
Simple modulation technique named polar modulation for converting QAM symbol to real and positive symbol is well known that the does not require the complicated process like Hermitian symmetry. However, there is a problem that the Euclidean distance between polar modulated symbols is uneven in constellation, thereby increasing the error probability of a specific symbol. In this paper, we propose an efficient polar modulation scheme which uses CR to uniform the Euclidean distance between polar modulated symbol. Simulation result shows that the proposed method has better BER gain and power consumption compared with general polar modulation.
{"title":"Polar Modulation with CR Method for Optical Wireless Communication MIMO System","authors":"Junghyun Kim, Seongjae Moon, Youngwoo Kim, Sunghoon Hong","doi":"10.1109/ICTC.2018.8539636","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539636","url":null,"abstract":"Simple modulation technique named polar modulation for converting QAM symbol to real and positive symbol is well known that the does not require the complicated process like Hermitian symmetry. However, there is a problem that the Euclidean distance between polar modulated symbols is uneven in constellation, thereby increasing the error probability of a specific symbol. In this paper, we propose an efficient polar modulation scheme which uses CR to uniform the Euclidean distance between polar modulated symbol. Simulation result shows that the proposed method has better BER gain and power consumption compared with general polar modulation.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"457 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132995284","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539569
Kulani Sumanasekera, Shifan Mihilar, C. Wickramasinghe, Shiromi Arunathilake
A visual impairment is a functional limitation of the visual system, and the impairment restricts the individual from conducting many societal activities. The challenge of social isolation of the visually impaired community is not often addressed through research studies. The study aims to address the social isolation of the visually impaired community by implementing a voice-based smartphone application. The design for the initial solution was derived from a comprehensive literature review and analysis of data gathered from a survey using the local population of the study. The initial solution was tested in two phases to increase the usability of the application and to validate the solution. An action based approach was used with two iterations to identify an optimum design for the solution. The research follows a qualitative methodology, with several insights and suggestions from the study participants and subject matter experts on the successful implementation of the solution. The solution is refined to accommodate the suggestion of improvement from the study subjects, and the findings of the research are directly applicable to the visually impaired population in Sri Lanka
{"title":"\"Kawulu\": A Voice based Social Network using Smart Mobile Devices for the Visually Impaired Community in Sri Lanka","authors":"Kulani Sumanasekera, Shifan Mihilar, C. Wickramasinghe, Shiromi Arunathilake","doi":"10.1109/ICTC.2018.8539569","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539569","url":null,"abstract":"A visual impairment is a functional limitation of the visual system, and the impairment restricts the individual from conducting many societal activities. The challenge of social isolation of the visually impaired community is not often addressed through research studies. The study aims to address the social isolation of the visually impaired community by implementing a voice-based smartphone application. The design for the initial solution was derived from a comprehensive literature review and analysis of data gathered from a survey using the local population of the study. The initial solution was tested in two phases to increase the usability of the application and to validate the solution. An action based approach was used with two iterations to identify an optimum design for the solution. The research follows a qualitative methodology, with several insights and suggestions from the study participants and subject matter experts on the successful implementation of the solution. The solution is refined to accommodate the suggestion of improvement from the study subjects, and the findings of the research are directly applicable to the visually impaired population in Sri Lanka","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133714359","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539682
Hyeon-Jae Noh, Jungeun Lee, H. Yang
Spectrum sharing for radar and communications can maximize the utilization of frequency resource. Though several studies have considered the coexistence and joint transmission to accomplish the missions of radar target detection and wireless communications simultaneously, none of the previous studies have considered feasible scenarios. In this paper, we consider a feasible scenario under which all the multiple antennas at the base station are used for joint transmission of radar beams and communications signals. With a careful consideration of the channel models, a beam synthesis algorithm is reviewed for the shared antenna utilization for both radar and communications. Numerical evaluation is provided to investigate the trade-off between the radar and communications performance.
{"title":"Beam Synthesis under Feasible Scenarios for Radar and Communications Combined Systems","authors":"Hyeon-Jae Noh, Jungeun Lee, H. Yang","doi":"10.1109/ICTC.2018.8539682","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539682","url":null,"abstract":"Spectrum sharing for radar and communications can maximize the utilization of frequency resource. Though several studies have considered the coexistence and joint transmission to accomplish the missions of radar target detection and wireless communications simultaneously, none of the previous studies have considered feasible scenarios. In this paper, we consider a feasible scenario under which all the multiple antennas at the base station are used for joint transmission of radar beams and communications signals. With a careful consideration of the channel models, a beam synthesis algorithm is reviewed for the shared antenna utilization for both radar and communications. Numerical evaluation is provided to investigate the trade-off between the radar and communications performance.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117342384","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539577
S. Riyadi, Jaenudin, Laila Marrifatul Azizah, Cahya Damarjati, T. Hariadi
Mangosteen is the major commodity of fruit export from Indonesia. Only free-defect mangosteens are exported which were conventionally classified by human vision. In order to automate the classification between defect and free-defect mangosteen surface and handle high volume of export, machine vision has a great opportunity. The objective of this paper is to classify mangosteen surface images using discrete curvelet transform (DCT). The curvelet transform is a multiscale directional transform, which allows an optimal non-adaptive sparse representation of objects with edges. The methodology of this research involved pre-processing, implementation of DCT, statistical features extraction and classification using linear discriminant analysis. The method has been implemented on a number of 80 mangosteen images and validated using 4-fold cross validation method. The highest accuracy of classification between defect and non-defect surface is 92.5% obtained on second scale of DCT. In conclusion, the proposed method is able to evaluate mangosteen quality surfaces.
{"title":"Evaluation of Mangosteen Surface Quality using Discrete Curvelet Transform","authors":"S. Riyadi, Jaenudin, Laila Marrifatul Azizah, Cahya Damarjati, T. Hariadi","doi":"10.1109/ICTC.2018.8539577","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539577","url":null,"abstract":"Mangosteen is the major commodity of fruit export from Indonesia. Only free-defect mangosteens are exported which were conventionally classified by human vision. In order to automate the classification between defect and free-defect mangosteen surface and handle high volume of export, machine vision has a great opportunity. The objective of this paper is to classify mangosteen surface images using discrete curvelet transform (DCT). The curvelet transform is a multiscale directional transform, which allows an optimal non-adaptive sparse representation of objects with edges. The methodology of this research involved pre-processing, implementation of DCT, statistical features extraction and classification using linear discriminant analysis. The method has been implemented on a number of 80 mangosteen images and validated using 4-fold cross validation method. The highest accuracy of classification between defect and non-defect surface is 92.5% obtained on second scale of DCT. In conclusion, the proposed method is able to evaluate mangosteen quality surfaces.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117322349","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539495
Jihye Moon, Sanghun Kim
Voice signal is an indicator finding a progression of diseases such as nerve disorder and muscle dysfunction. To improve the performance of medical diagnosis system using the voice signal, this paper suggests a new feature extraction method which combines higher-order statistics (HOS) and higher-order differential energy operator (DEO). For the experiment, Saarbruecken Voice Database (SVD) was used, and 687 healthy voice samples and 263 pathological voice samples which consist of Cysts, Paralysis, and Polyp were selected. In addition, the OpenSmile script which provides 6,373 features was used for comparison with our new features. To decide the most effective features, Gradient Boosting was conducted as a feature selector. Finally, 20 features including 15 combinations of HOS and DEO were chosen, and deep neural network(DNN) was trained using the new features. The best accuracy of 87.4% was obtained, which exceeds the best accuracy of 84.5% with the existing features. The finding suggests a possibility that the pathological voice can be efficiently detected with only statistical information without heavy computations such as convolutional neural networks. Due to the simple structure, we expect this approach will be easily applied to a variety of mobile systems.
{"title":"An approach on a combination of higher-order statistics and higher-order differential energy operator for detecting pathological voice with machine learning","authors":"Jihye Moon, Sanghun Kim","doi":"10.1109/ICTC.2018.8539495","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539495","url":null,"abstract":"Voice signal is an indicator finding a progression of diseases such as nerve disorder and muscle dysfunction. To improve the performance of medical diagnosis system using the voice signal, this paper suggests a new feature extraction method which combines higher-order statistics (HOS) and higher-order differential energy operator (DEO). For the experiment, Saarbruecken Voice Database (SVD) was used, and 687 healthy voice samples and 263 pathological voice samples which consist of Cysts, Paralysis, and Polyp were selected. In addition, the OpenSmile script which provides 6,373 features was used for comparison with our new features. To decide the most effective features, Gradient Boosting was conducted as a feature selector. Finally, 20 features including 15 combinations of HOS and DEO were chosen, and deep neural network(DNN) was trained using the new features. The best accuracy of 87.4% was obtained, which exceeds the best accuracy of 84.5% with the existing features. The finding suggests a possibility that the pathological voice can be efficiently detected with only statistical information without heavy computations such as convolutional neural networks. Due to the simple structure, we expect this approach will be easily applied to a variety of mobile systems.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"368 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115984437","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539388
R. Hakkun, Z. DioAlSabahA., K. Fathoni, Nana Ramadijanti, A. Basuki
Visual Novel Game as one of the game genres has many possibilities to be implemented with various kind of contents such as education, culture, and politic. Compare with other types, the number of published games nowadays still at a low. Moreover, the game with specific contents, especially local cultures, not ready yet. This paper proposes a framework for online visual game creation. Easiness of creating content is the main focus besides many features added. Instead of its online feature, the framework has a collaboration mode to enable users to interact with others to create games.
{"title":"Online Visual Novel Game Framework","authors":"R. Hakkun, Z. DioAlSabahA., K. Fathoni, Nana Ramadijanti, A. Basuki","doi":"10.1109/ICTC.2018.8539388","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539388","url":null,"abstract":"Visual Novel Game as one of the game genres has many possibilities to be implemented with various kind of contents such as education, culture, and politic. Compare with other types, the number of published games nowadays still at a low. Moreover, the game with specific contents, especially local cultures, not ready yet. This paper proposes a framework for online visual game creation. Easiness of creating content is the main focus besides many features added. Instead of its online feature, the framework has a collaboration mode to enable users to interact with others to create games.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115736798","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}
With the rapid development of the Internet and the innovative attacks, information security has become an important issue for system administrators and users. Because the traditional intrusion detection system is based on misuse detection technology, the disadvantage is that it needs constant updating of the feature database to cope with attacks from variant malware. This paper proposes a framework of deep learning model by using the TensorFlow platform and utilizes the NSL-KDD data set for training and testing the proposed framework. Experimental results show the proposed methodology can effectively classify malicious traffic categories.
{"title":"Classification of Malicious Traffic Using TensorFlow Machine Learning","authors":"Li-Der Chou, Chia-Wei Tseng, Meng-Sheng Lai, Wei-Yu Chen, Kuo-Chung Chen, Chia-Kuan Yen, Tsung-Fu Ou, Wei-Hsiang Tsai, Yi-Hsuan Chiu","doi":"10.1109/ICTC.2018.8539685","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539685","url":null,"abstract":"With the rapid development of the Internet and the innovative attacks, information security has become an important issue for system administrators and users. Because the traditional intrusion detection system is based on misuse detection technology, the disadvantage is that it needs constant updating of the feature database to cope with attacks from variant malware. This paper proposes a framework of deep learning model by using the TensorFlow platform and utilizes the NSL-KDD data set for training and testing the proposed framework. Experimental results show the proposed methodology can effectively classify malicious traffic categories.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116170262","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 : 2018-10-01DOI: 10.1109/ICTC.2018.8539658
Hyungjin Kim, S. Cho, Youngha Lee
Massive connectivity is one of the major goals of 5G mobile communications. The NB-IoT system achieves this goal using only a very narrow bandwidth. The NB-IoT system can also work together without affecting existing LTE systems. In this paper, we analyze the interferences of guardband NB-IoT system from the LTE system when they coexist.
{"title":"Interference Analysis of Guardband NB-IoT System","authors":"Hyungjin Kim, S. Cho, Youngha Lee","doi":"10.1109/ICTC.2018.8539658","DOIUrl":"https://doi.org/10.1109/ICTC.2018.8539658","url":null,"abstract":"Massive connectivity is one of the major goals of 5G mobile communications. The NB-IoT system achieves this goal using only a very narrow bandwidth. The NB-IoT system can also work together without affecting existing LTE systems. In this paper, we analyze the interferences of guardband NB-IoT system from the LTE system when they coexist.","PeriodicalId":417962,"journal":{"name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115295009","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：