Pub Date : 2018-02-01DOI: 10.23919/ICACT.2018.8323857
Seung-Woo Lee, In-Ki Hwang, Hun-sik Kang
Multiple FPGAs are used for high-speed and large amount of data transfer and also designed to implement DSP functions. The consecutive PRBS patterns are used for bit synchronization and data alignment between high-speed multi-channel interfaces of FPGAs.
{"title":"Data alignment for multi-channel high-speed interfaces using PRBS patterns","authors":"Seung-Woo Lee, In-Ki Hwang, Hun-sik Kang","doi":"10.23919/ICACT.2018.8323857","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323857","url":null,"abstract":"Multiple FPGAs are used for high-speed and large amount of data transfer and also designed to implement DSP functions. The consecutive PRBS patterns are used for bit synchronization and data alignment between high-speed multi-channel interfaces of FPGAs.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128857695","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323731
K. Sung, Kyoungwook Min, Jeongdan Choi
In this paper, we describe in detail the driving information logging used in developing an autonomous vehicle. The recorded vehicle information is used to identify the cause of problems in the system or undesired operations. Driving information logging can be used in many areas such as analysis of problems in the study of autonomous driving system and analysis of accident risk.
{"title":"Driving information logger with in-vehicle communication for autonomous vehicle research","authors":"K. Sung, Kyoungwook Min, Jeongdan Choi","doi":"10.23919/ICACT.2018.8323731","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323731","url":null,"abstract":"In this paper, we describe in detail the driving information logging used in developing an autonomous vehicle. The recorded vehicle information is used to identify the cause of problems in the system or undesired operations. Driving information logging can be used in many areas such as analysis of problems in the study of autonomous driving system and analysis of accident risk.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116966163","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323691
Ming-Shen Jian, Yi-Chang Wang, Bo Wu, Yu-En Cheng
In this paper, the Hybrid Cloud Computing for User Location-aware Augmented Reality Construction is proposed including three layers: Estimation Layer, Scenario Layer, and Presentation Layer. Based on “Angle of the Arrival” position method in Estimation Layer, the location-aware information of individual user can be considered. According to Scenario Layer, the various augmented reality contents can be rapidly and dynamically re-established. Three types of virtual machines including scenario virtual machine, material and physical parameter database, and re-direction management are proposed Based on the proposed system structure, the cost of AR construction can be reduced for the various display devices.
{"title":"Hybrid cloud computing for user location-aware augmented reality construction","authors":"Ming-Shen Jian, Yi-Chang Wang, Bo Wu, Yu-En Cheng","doi":"10.23919/ICACT.2018.8323691","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323691","url":null,"abstract":"In this paper, the Hybrid Cloud Computing for User Location-aware Augmented Reality Construction is proposed including three layers: Estimation Layer, Scenario Layer, and Presentation Layer. Based on “Angle of the Arrival” position method in Estimation Layer, the location-aware information of individual user can be considered. According to Scenario Layer, the various augmented reality contents can be rapidly and dynamically re-established. Three types of virtual machines including scenario virtual machine, material and physical parameter database, and re-direction management are proposed Based on the proposed system structure, the cost of AR construction can be reduced for the various display devices.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133004525","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323933
Youngsam Kim, Soohyung Kim
Wi-Fi fingerprint-based localization systems are widely used for indoor localization as it only needs Wi-Fi network infrastructure that exists almost everywhere nowadays. However, it can be vulnerable to environmental change if Wi-Fi fingerprint-based localization system uses fixed Wi-Fi fingerprint database as training dataset and has no method for updating training dataset. In this paper, we propose AR-WFL system including update phase that can reflect environmental change periodically and prevent performance degradation. The proposed AR-WFL system is based on crowdsourcing and no dedicated annotator exists. In addition, we adopt active learning scheme with uncertainty selective sampling algorithm to maximize cost-efficiency of the update phase. We evaluate the performance of the update phase as location estimation accuracy using a dataset we collected for 2 months. It shows that average accuracy is increased by 1.83%p using update phase with uncertainty sampling algorithm compared with the system without an update phase.
{"title":"Design of aging-resistant Wi-Fi fingerprint-based localization system with continuous active learning","authors":"Youngsam Kim, Soohyung Kim","doi":"10.23919/ICACT.2018.8323933","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323933","url":null,"abstract":"Wi-Fi fingerprint-based localization systems are widely used for indoor localization as it only needs Wi-Fi network infrastructure that exists almost everywhere nowadays. However, it can be vulnerable to environmental change if Wi-Fi fingerprint-based localization system uses fixed Wi-Fi fingerprint database as training dataset and has no method for updating training dataset. In this paper, we propose AR-WFL system including update phase that can reflect environmental change periodically and prevent performance degradation. The proposed AR-WFL system is based on crowdsourcing and no dedicated annotator exists. In addition, we adopt active learning scheme with uncertainty selective sampling algorithm to maximize cost-efficiency of the update phase. We evaluate the performance of the update phase as location estimation accuracy using a dataset we collected for 2 months. It shows that average accuracy is increased by 1.83%p using update phase with uncertainty sampling algorithm compared with the system without an update phase.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133953944","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323677
Y. Luo, Y. Li, F. Han, S. Huang
Recent studies show that features from deep layers of convolution neural network can represent the image more strongly. This paper proposes an effective retrieval system to achieve a grading retrieval which contains two stages. In the first pre-screening stage, we propose a novel method to generate both deep binary feature vectors and compressed vectors based on multiple deep layers. And the second refine-retrieval stage refine the retrieval result. Grading retrieval can make full use of the features extracted from different layers. And, the retrieval efficiency is guaranteed by binary features and compressed features in both stages. Experiment based on public retrieval datasets shows that the proposed system markedly improves the retrieval accuracy while enhancing the retrieval efficiency.
{"title":"Grading image retrieval based on CNN deep features","authors":"Y. Luo, Y. Li, F. Han, S. Huang","doi":"10.23919/ICACT.2018.8323677","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323677","url":null,"abstract":"Recent studies show that features from deep layers of convolution neural network can represent the image more strongly. This paper proposes an effective retrieval system to achieve a grading retrieval which contains two stages. In the first pre-screening stage, we propose a novel method to generate both deep binary feature vectors and compressed vectors based on multiple deep layers. And the second refine-retrieval stage refine the retrieval result. Grading retrieval can make full use of the features extracted from different layers. And, the retrieval efficiency is guaranteed by binary features and compressed features in both stages. Experiment based on public retrieval datasets shows that the proposed system markedly improves the retrieval accuracy while enhancing the retrieval efficiency.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134025069","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323657
Joon Yeol Yoon, W. Choi, J. O. Kim, Jae-Woo Ahn, Jong Beom Kim, S. Choi
This paper proposes a method of implementing a NIC (Network Interface Card) capable of data processing at 40Gbps. Recently, technologies such as cloud services, mobile, and big data have been developed and more and more traffic is increasing. Therefore, network equipment capable of processing such traffic at high speed is attracting attention. We developed a network card based on the TILE-Gx36 processor, which made it possible to process data at high speed. As a result of our experiments, we confirmed that data transmission and reception are working normally at 40Gbps.
{"title":"Design of multicore-based high performance load distribution system","authors":"Joon Yeol Yoon, W. Choi, J. O. Kim, Jae-Woo Ahn, Jong Beom Kim, S. Choi","doi":"10.23919/ICACT.2018.8323657","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323657","url":null,"abstract":"This paper proposes a method of implementing a NIC (Network Interface Card) capable of data processing at 40Gbps. Recently, technologies such as cloud services, mobile, and big data have been developed and more and more traffic is increasing. Therefore, network equipment capable of processing such traffic at high speed is attracting attention. We developed a network card based on the TILE-Gx36 processor, which made it possible to process data at high speed. As a result of our experiments, we confirmed that data transmission and reception are working normally at 40Gbps.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130487875","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323653
Shuaizhi Guo, Linlin Zheng, Xi Jin
Radio astronomy correlator shows its significance in astronomical measurements. However, computational cost presents a barrier because of the increasing of the array size as well as the number of antennas. So the correlators which deal with signals coming from all the antennas are extremely computationally intensive process. Efficient usage of hardware should be explored in order to meet this computational challenge. This paper focus on the most computationally expensive parts in radio astronomy correlator and accelerate it using single FPGA. Results shows that the proposed hardware designs speed up the computation by at least 150 times compared with single thread CPU implementation, and at least 4 times compared with FPGA design without optimization. The throughput of our design is also higher than fully parallel CPU solution for at least 10 times, and defeats FPGA implementation without optimization in most cases.
{"title":"Accelerating a radio astronomy correlator on FPGA","authors":"Shuaizhi Guo, Linlin Zheng, Xi Jin","doi":"10.23919/ICACT.2018.8323653","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323653","url":null,"abstract":"Radio astronomy correlator shows its significance in astronomical measurements. However, computational cost presents a barrier because of the increasing of the array size as well as the number of antennas. So the correlators which deal with signals coming from all the antennas are extremely computationally intensive process. Efficient usage of hardware should be explored in order to meet this computational challenge. This paper focus on the most computationally expensive parts in radio astronomy correlator and accelerate it using single FPGA. Results shows that the proposed hardware designs speed up the computation by at least 150 times compared with single thread CPU implementation, and at least 4 times compared with FPGA design without optimization. The throughput of our design is also higher than fully parallel CPU solution for at least 10 times, and defeats FPGA implementation without optimization in most cases.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130870293","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323687
F. Farahnakian, J. Heikkonen
One of the most challenging problems facing network operators today is network attacks identification due to extensive number of vulnerabilities in computer systems and creativity of attackers. To address this problem, we present a deep learning approach for intrusion detection systems. Our approach uses Deep Auto-Encoder (DAE) as one of the most well-known deep learning models. The proposed DAE model is trained in a greedy layer-wise fashion in order to avoid overfitting and local optima. The experimental results on the KDD-CUP'99 dataset show that our approach provides substantial improvement over other deep learning-based approaches in terms of accuracy, detection rate and false alarm rate.
{"title":"A deep auto-encoder based approach for intrusion detection system","authors":"F. Farahnakian, J. Heikkonen","doi":"10.23919/ICACT.2018.8323687","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323687","url":null,"abstract":"One of the most challenging problems facing network operators today is network attacks identification due to extensive number of vulnerabilities in computer systems and creativity of attackers. To address this problem, we present a deep learning approach for intrusion detection systems. Our approach uses Deep Auto-Encoder (DAE) as one of the most well-known deep learning models. The proposed DAE model is trained in a greedy layer-wise fashion in order to avoid overfitting and local optima. The experimental results on the KDD-CUP'99 dataset show that our approach provides substantial improvement over other deep learning-based approaches in terms of accuracy, detection rate and false alarm rate.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125132524","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323875
Seung-Hee Kim, Deokkyu Jung, Sang-Yun Lee, Sun-Joong Kim
To cope with the new media paradigm era toward user-centric service by using scene-based broadcast content, this paper proposes the scene-based metadata automatic generation method on small-size segmented unit, and open API provisioning method for metadata and its related video clip retrieval function. In order to fulfill this proposed essential technology, the smart broadcast platform is composed of following four enablers such as informal data management, semantic cluster, convergence-type metadata generation, and service control management. Through the opening of metadata resource in smart broadcast platform, the diverse and innovative broadcast media service that attracts users or business operators will provide more easily and conveniently. Eventually, it will also contribute to construction of smart media ecosystem with a virtuous cycle.
{"title":"Scene-based metadata generation and open API provisioning method for smart broadcast service","authors":"Seung-Hee Kim, Deokkyu Jung, Sang-Yun Lee, Sun-Joong Kim","doi":"10.23919/ICACT.2018.8323875","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323875","url":null,"abstract":"To cope with the new media paradigm era toward user-centric service by using scene-based broadcast content, this paper proposes the scene-based metadata automatic generation method on small-size segmented unit, and open API provisioning method for metadata and its related video clip retrieval function. In order to fulfill this proposed essential technology, the smart broadcast platform is composed of following four enablers such as informal data management, semantic cluster, convergence-type metadata generation, and service control management. Through the opening of metadata resource in smart broadcast platform, the diverse and innovative broadcast media service that attracts users or business operators will provide more easily and conveniently. Eventually, it will also contribute to construction of smart media ecosystem with a virtuous cycle.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116789769","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 : 2018-02-01DOI: 10.23919/ICACT.2018.8323771
J. K. Tamgno, Ndeye Rokhaya Diallo, C. Lishou
This paper is concerned by the fact that the health sector represents a major development challenge for emerging countries. However, it faces many challenges that affect the quality of care provided and makes it almost impossible to guarantee an adequate level of accessibility for all social classes of the population. These reasons motivated us to study a medical control system based on the Internet of Things that could significantly improve the conditions of medical care and ensure effective and effective medical follow-up by automating the process of taking during the consultations and by preserving the information thus obtained for restitution in case of emergency or medical follow-up of the patients. At the end of our study, we were able to define the challenges posed by technological tools in improving the conditions of health structures and to simulate the functioning of the system we designed.
{"title":"IoT-based medical control system","authors":"J. K. Tamgno, Ndeye Rokhaya Diallo, C. Lishou","doi":"10.23919/ICACT.2018.8323771","DOIUrl":"https://doi.org/10.23919/ICACT.2018.8323771","url":null,"abstract":"This paper is concerned by the fact that the health sector represents a major development challenge for emerging countries. However, it faces many challenges that affect the quality of care provided and makes it almost impossible to guarantee an adequate level of accessibility for all social classes of the population. These reasons motivated us to study a medical control system based on the Internet of Things that could significantly improve the conditions of medical care and ensure effective and effective medical follow-up by automating the process of taking during the consultations and by preserving the information thus obtained for restitution in case of emergency or medical follow-up of the patients. At the end of our study, we were able to define the challenges posed by technological tools in improving the conditions of health structures and to simulate the functioning of the system we designed.","PeriodicalId":228625,"journal":{"name":"2018 20th International Conference on Advanced Communication Technology (ICACT)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115546611","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：