Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061567
Nadege Gladys Ndassimba, G. M. Kossingou, Edgard Ndassimba, Kéba Gueye, S. Ouya
This article proposes a solution to extend the functionalities of zeroconf outside of a local network to enable young people in conflict areas to benefit from quality distance learning. This proposal, based on a judicious choice of a VPN mode, allows distant teachers and learners in conflict areas to work as if they were face to face. To support the e-learning service, in this article a broadband network built on the technology of free spaces of television (TVWS) transmission channels is set up. This e-learning solution, using zeroconf protocol, gives the various actors the opportunity to collaborate on practical work in real time; it also helps to encourage the resumption of educational activities of refugees young students in conflict areas to fight against their attempts to integrate armed groups for lack of future prospects.
{"title":"The Impact of Zeroconf on the Education System of the Countries in Conflict: The Case of the Central African Republic","authors":"Nadege Gladys Ndassimba, G. M. Kossingou, Edgard Ndassimba, Kéba Gueye, S. Ouya","doi":"10.23919/ICACT48636.2020.9061567","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061567","url":null,"abstract":"This article proposes a solution to extend the functionalities of zeroconf outside of a local network to enable young people in conflict areas to benefit from quality distance learning. This proposal, based on a judicious choice of a VPN mode, allows distant teachers and learners in conflict areas to work as if they were face to face. To support the e-learning service, in this article a broadband network built on the technology of free spaces of television (TVWS) transmission channels is set up. This e-learning solution, using zeroconf protocol, gives the various actors the opportunity to collaborate on practical work in real time; it also helps to encourage the resumption of educational activities of refugees young students in conflict areas to fight against their attempts to integrate armed groups for lack of future prospects.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120972442","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061355
Xuebing Bai, Meng Zhou, Xu Qiao, Yao Zhang, Longxiang Yang
The cell-free massive multiple-input multiple-output (mMIMO) system is considered in this paper. In contrast to previous works, this paper quantizes the pilot and all the users' signals utilizing low-resolution analog-to-digital converters (ADCs) before they are transmitted to the central processing unit (CPU). The additive quantization noise model (AQNM) is used to characterize the quantization distortion. Moreover, a zero-forcing (ZF) receiver is advocated since it is free from inter-user interference. Based on the AQNM and the ZF receiver, a strict closed-form rate expression is derived, which motivates us to analyse the effect of quantization bits on the system performance. Simulation results show that 6-bit is the minimum quantized bit, which can achieve the same rate as a cell-free mMIMO system with perfect ADCs. In addition, 1-bit ADCs and 2-bit ADCs can result in severe rate degradation.
{"title":"Uplink Performance Analysis of Cell-Free MIMO with Low-Resolution ADCs and ZF Receiver","authors":"Xuebing Bai, Meng Zhou, Xu Qiao, Yao Zhang, Longxiang Yang","doi":"10.23919/ICACT48636.2020.9061355","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061355","url":null,"abstract":"The cell-free massive multiple-input multiple-output (mMIMO) system is considered in this paper. In contrast to previous works, this paper quantizes the pilot and all the users' signals utilizing low-resolution analog-to-digital converters (ADCs) before they are transmitted to the central processing unit (CPU). The additive quantization noise model (AQNM) is used to characterize the quantization distortion. Moreover, a zero-forcing (ZF) receiver is advocated since it is free from inter-user interference. Based on the AQNM and the ZF receiver, a strict closed-form rate expression is derived, which motivates us to analyse the effect of quantization bits on the system performance. Simulation results show that 6-bit is the minimum quantized bit, which can achieve the same rate as a cell-free mMIMO system with perfect ADCs. In addition, 1-bit ADCs and 2-bit ADCs can result in severe rate degradation.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124843949","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}
This study proposes an audiovisual quality assessment model for a popular gaming scenario, called the Multiplayer Online Battle Arena (MOBA) gaming. The subjective data about voice quality during conversation of the game players, the video quality, the overall quality, and the weighted percentage of voice and video have been gathered from 40 participants who competed in a small competition event of the Garena ROV (Arena of Valor) in Thailand. Then, three quarters of data have been used to create the model, while the last quarter of data has been used for model evaluation. After creating the model, it has been evaluated using Mean Absolute Percentage Error (MAPE) with three audiovisual quality evaluation models that provide good performances. It has been found that the proposed audiovisual quality assessment model provides better performance than previous works with MAPE of 6.16 %, while other models provide MAPE of 7.67 - 8.54%. Therefore, this evidence supports that the proposed model could be applied for evaluation of audiovisual quality based on the MOBA gaming scenario.
本研究提出了一个流行游戏场景的视听质量评估模型，称为多人在线竞技(MOBA)游戏。本文收集了在泰国参加Garena ROV (Arena of Valor)小型比赛的40名参与者的语音质量主观数据、视频质量主观数据、整体质量主观数据以及语音和视频加权百分比主观数据。然后，四分之三的数据被用于创建模型，最后四分之一的数据被用于模型评估。在创建模型后，使用平均绝对百分比误差(MAPE)和三种提供良好性能的视听质量评估模型对其进行了评估。研究发现，本文提出的音像质量评价模型的MAPE值为6.16%，优于已有的音像质量评价模型，其他模型的MAPE值为7.67 ~ 8.54%。因此，这一证据支持该模型可以应用于基于MOBA游戏场景的视听质量评价。
{"title":"A Proposed Audiovisual Quality Assessment Model Associated with Multiplayer Online Battle Arena Game: A Pilot Study with ROV","authors":"Therdpong Daengsi, Phisit Pornpongtechavanich, Pongpisit Wuttidittachotti","doi":"10.23919/ICACT48636.2020.9061343","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061343","url":null,"abstract":"This study proposes an audiovisual quality assessment model for a popular gaming scenario, called the Multiplayer Online Battle Arena (MOBA) gaming. The subjective data about voice quality during conversation of the game players, the video quality, the overall quality, and the weighted percentage of voice and video have been gathered from 40 participants who competed in a small competition event of the Garena ROV (Arena of Valor) in Thailand. Then, three quarters of data have been used to create the model, while the last quarter of data has been used for model evaluation. After creating the model, it has been evaluated using Mean Absolute Percentage Error (MAPE) with three audiovisual quality evaluation models that provide good performances. It has been found that the proposed audiovisual quality assessment model provides better performance than previous works with MAPE of 6.16 %, while other models provide MAPE of 7.67 - 8.54%. Therefore, this evidence supports that the proposed model could be applied for evaluation of audiovisual quality based on the MOBA gaming scenario.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123448124","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061377
L. Cho, Meng-Fan Chuang, Sheng-Hsiang Fu, Chau-Yun Hsu
Phase-shift keying (PSK)-based multi-mode orthogonal frequency division multiplexing with block-wise index modulation (MM-OFDM-BIM) has been proposed as a novel OFDM-IM technique with adjustable-reliability transmission and low detection complexity. Although the phase normalization for PSK can reduce the complexity of the index modulation (IM) detection, the essence of constant symbol power of PSK limits its bit error rate (BER) performance. We propose a new constellation design to reallocate the original symbols into two-level power for PSK-based MM-OFDM-BIM while retaining the merit of phase normalization. By adopting the optimum power parameter, the numerical results demonstrate that the proposed scheme can effectively improve BER performance without increasing computational complexity.
{"title":"BER Reduction for PSK-Based MM-OFDM-BIM with Two-Level Symbol Power","authors":"L. Cho, Meng-Fan Chuang, Sheng-Hsiang Fu, Chau-Yun Hsu","doi":"10.23919/ICACT48636.2020.9061377","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061377","url":null,"abstract":"Phase-shift keying (PSK)-based multi-mode orthogonal frequency division multiplexing with block-wise index modulation (MM-OFDM-BIM) has been proposed as a novel OFDM-IM technique with adjustable-reliability transmission and low detection complexity. Although the phase normalization for PSK can reduce the complexity of the index modulation (IM) detection, the essence of constant symbol power of PSK limits its bit error rate (BER) performance. We propose a new constellation design to reallocate the original symbols into two-level power for PSK-based MM-OFDM-BIM while retaining the merit of phase normalization. By adopting the optimum power parameter, the numerical results demonstrate that the proposed scheme can effectively improve BER performance without increasing computational complexity.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116466081","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061225
Hamaciré El Hadj Kalil, A. Kora, S. Boumerdassi
This paper focuses on the Vehicle Ad-hoc NETwork (VANET), especially on the security of information exchanged in the network. We therefore propose in this document a secure communication protocol, based on VANET network standards. A lot of research is under way to make possible the large-scale deployment of VANETs. It is with this idea that we decided to propose a communication protocol based on an architecture organized in groups. For each group of vehicles, a Master is appointed who is the leader of the group. In our proposal, only a group Master can communicate with an RSU (Roadside Unit). In the literature, in general, the group leader takes care alone of managing the group. Here we involve the RSU in the group management to reduce the workload of the Master. In general, the organization of the group network lighten the workload of the RSU. But our proposal will also reduce the burden of the Master and thus significantly improve the performance of the network.
{"title":"Security in VANETs: Lightweight Protocol for Group-of-Vehicles Masters (LPGVM)","authors":"Hamaciré El Hadj Kalil, A. Kora, S. Boumerdassi","doi":"10.23919/ICACT48636.2020.9061225","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061225","url":null,"abstract":"This paper focuses on the Vehicle Ad-hoc NETwork (VANET), especially on the security of information exchanged in the network. We therefore propose in this document a secure communication protocol, based on VANET network standards. A lot of research is under way to make possible the large-scale deployment of VANETs. It is with this idea that we decided to propose a communication protocol based on an architecture organized in groups. For each group of vehicles, a Master is appointed who is the leader of the group. In our proposal, only a group Master can communicate with an RSU (Roadside Unit). In the literature, in general, the group leader takes care alone of managing the group. Here we involve the RSU in the group management to reduce the workload of the Master. In general, the organization of the group network lighten the workload of the RSU. But our proposal will also reduce the burden of the Master and thus significantly improve the performance of the network.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122310159","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061291
Jie Wang, Xi Jin, Wei Wu
Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) applications. However, due to the huge demand for computing and storage resources as well as the high power consumption, deploying DNN models on embedded devices is full of challenges. Recent works have shown that DNN models can be compressed by removing their inner redundancy without obviously performance decay. In this work, we propose a two stage pipeline way to compress the ResNet-14 model and test it on CIFAR-10 and SVHN dataset respectively. Firstly, we use a filter level pruning method to remove the less important filters with different compression rate, and a considerable computation costs are reduced. Secondly, we binarize the pruned model to further reduce the model size and computational complexity. The training results show that we achieve 87.7% accuracy with only 1.86Mb model size on CIFAR-10 and 96.2% accuracy with 1.34Mb on SVHN. Compared to the original model, we have 57% to 68% FLOPs reduction and 45.6× to 63.1× model size compression at the cost of roughly 4% accuracy drop. Finally, we implement the thin binarized ResNet-14 model on the Xilinx KC705 board with a shared, flexible accumulator, which can save 46.8% logic resources. And the entire network parameters are store into on-chip RAM, which can greatly reduce the energy consumption and memory overhead caused by off-chip accesses. The experimental results show that on CIFAR-10 dataset, we achieve an overall performance of 1200 FPS, energy efficiency of 571 FPS/W, which denote 2.3× and 3.6× improvements over the most recent work.
{"title":"TB-DNN: A Thin Binarized Deep Neural Network with High Accuracy","authors":"Jie Wang, Xi Jin, Wei Wu","doi":"10.23919/ICACT48636.2020.9061291","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061291","url":null,"abstract":"Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) applications. However, due to the huge demand for computing and storage resources as well as the high power consumption, deploying DNN models on embedded devices is full of challenges. Recent works have shown that DNN models can be compressed by removing their inner redundancy without obviously performance decay. In this work, we propose a two stage pipeline way to compress the ResNet-14 model and test it on CIFAR-10 and SVHN dataset respectively. Firstly, we use a filter level pruning method to remove the less important filters with different compression rate, and a considerable computation costs are reduced. Secondly, we binarize the pruned model to further reduce the model size and computational complexity. The training results show that we achieve 87.7% accuracy with only 1.86Mb model size on CIFAR-10 and 96.2% accuracy with 1.34Mb on SVHN. Compared to the original model, we have 57% to 68% FLOPs reduction and 45.6× to 63.1× model size compression at the cost of roughly 4% accuracy drop. Finally, we implement the thin binarized ResNet-14 model on the Xilinx KC705 board with a shared, flexible accumulator, which can save 46.8% logic resources. And the entire network parameters are store into on-chip RAM, which can greatly reduce the energy consumption and memory overhead caused by off-chip accesses. The experimental results show that on CIFAR-10 dataset, we achieve an overall performance of 1200 FPS, energy efficiency of 571 FPS/W, which denote 2.3× and 3.6× improvements over the most recent work.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122637298","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061505
Chang-Su Lee, Dongwoog Jung
Registering a large number of IoTs with a central main server and coordinating the collaboration of the IoT on that server for the services they want to provide can cause significant traffic to the network. If many IoTs request cooperation on the main server to provide services, many data will be concentrated on the main server and the network to which the IoT is connected, and the server will have to use its performance to the maximum for the many calculations of the collaboration required by the various IoTs. And the security level will have to be very high as the central main server has important information on all IoTs as well as collaborative calculations for service offerings, which can be targeted by hackers. To solve these problems, IoT structure and collaboration algorithm were designed and implemented by IoT to find cooperative partners through distributed social networking. If IoTs collaborate and provide services directly without a main server, they will avoid network traffic and security issues that are concentrated on the server.
{"title":"Design and implementation of real-time information sharing system of IoT using distributed social network","authors":"Chang-Su Lee, Dongwoog Jung","doi":"10.23919/ICACT48636.2020.9061505","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061505","url":null,"abstract":"Registering a large number of IoTs with a central main server and coordinating the collaboration of the IoT on that server for the services they want to provide can cause significant traffic to the network. If many IoTs request cooperation on the main server to provide services, many data will be concentrated on the main server and the network to which the IoT is connected, and the server will have to use its performance to the maximum for the many calculations of the collaboration required by the various IoTs. And the security level will have to be very high as the central main server has important information on all IoTs as well as collaborative calculations for service offerings, which can be targeted by hackers. To solve these problems, IoT structure and collaboration algorithm were designed and implemented by IoT to find cooperative partners through distributed social networking. If IoTs collaborate and provide services directly without a main server, they will avoid network traffic and security issues that are concentrated on the server.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122194468","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061477
Nguyen Viet Ha, Le Van Hau, M. Tsuru
Transmission Control Protocol (TCP) still plays an essential role in various user applications for end-to-end reliable data transmission. However, TCP cannot get a high goodput performance in the lossy networks because it considers any packet loss to be a congestion signal and decreases the congestion window mistakenly. Therefore, TCP with Network Coding (termed TCP/NC) was proposed to recover the packet loss at the sink without retransmission if the number of coded packets is enough. However, the ACK packet needs to be sent for any arriving coded packet as a feedback of the end-to-end channel condition, resulting in a lower transmission performance in half-duplex networks, e.g., Power Line Communication. Therefore, we propose the ACK-Skipping scheme for TCP/NC to limit the number of ACK packets but still retain the necessary information, e.g., for channel estimation. The simulation result on ns-3 (Network Simulation 3) shows that the proposal achieves a higher goodput on PLC environment compared to TCP with Selective Acknowledgment and TCP Westwood+ as well as the recent variant of TCP/NC.
传输控制协议(TCP)在各种用户应用中仍然扮演着重要的角色，实现端到端可靠的数据传输。然而，TCP在有损耗的网络中无法获得良好的性能，因为它将任何丢包都视为拥塞信号，并错误地减小了拥塞窗口。因此，TCP with Network Coding(简称TCP/NC)被提出，如果编码的数据包数量足够多，则可以在不重传的情况下恢复sink的丢包。然而，对于任何到达的编码包，需要发送ACK包作为端到端信道条件的反馈，这导致在半双工网络中传输性能较低，例如电力线通信。因此，我们提出了TCP/NC的ACK跳过方案，以限制ACK数据包的数量，但仍然保留必要的信息，例如用于信道估计。在ns-3 (Network simulation 3)上的仿真结果表明，与TCP with Selective Acknowledgment和TCP Westwood+以及最近的TCP/NC变体相比，该方案在PLC环境下实现了更高的性能。
{"title":"Dynamic ACK skipping in TCP with Network Coding for Power Line Communication Networks","authors":"Nguyen Viet Ha, Le Van Hau, M. Tsuru","doi":"10.23919/ICACT48636.2020.9061477","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061477","url":null,"abstract":"Transmission Control Protocol (TCP) still plays an essential role in various user applications for end-to-end reliable data transmission. However, TCP cannot get a high goodput performance in the lossy networks because it considers any packet loss to be a congestion signal and decreases the congestion window mistakenly. Therefore, TCP with Network Coding (termed TCP/NC) was proposed to recover the packet loss at the sink without retransmission if the number of coded packets is enough. However, the ACK packet needs to be sent for any arriving coded packet as a feedback of the end-to-end channel condition, resulting in a lower transmission performance in half-duplex networks, e.g., Power Line Communication. Therefore, we propose the ACK-Skipping scheme for TCP/NC to limit the number of ACK packets but still retain the necessary information, e.g., for channel estimation. The simulation result on ns-3 (Network Simulation 3) shows that the proposal achieves a higher goodput on PLC environment compared to TCP with Selective Acknowledgment and TCP Westwood+ as well as the recent variant of TCP/NC.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129519274","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061370
Yanying Yang, Xianwei Xu
Vision is the most important source of information for Unmanned Underwater Vehicle(UUV), only a clear image can make it possible for a UUV to operate automatically, Due to strong absorption and light scattering for water, the image of underwater imaging has a serious degradation, whether in distance or in quality. Based on classical Retinex theory, this paper proposed an underwater image enhanced algorithm. For different channel of underwater image has apparently different energy, especially green channel has overwhelming power than others, we added a step to energy balance of the RGB three channel in classical Multi-Scale Retinex (MSR). Experiment data show that, compared to the traditional three-channel simple addition, our improvement can get more natural recovered underwater image.
{"title":"A Underwater Image Enhanced Algorithm combined MSR and Channel Energy","authors":"Yanying Yang, Xianwei Xu","doi":"10.23919/ICACT48636.2020.9061370","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061370","url":null,"abstract":"Vision is the most important source of information for Unmanned Underwater Vehicle(UUV), only a clear image can make it possible for a UUV to operate automatically, Due to strong absorption and light scattering for water, the image of underwater imaging has a serious degradation, whether in distance or in quality. Based on classical Retinex theory, this paper proposed an underwater image enhanced algorithm. For different channel of underwater image has apparently different energy, especially green channel has overwhelming power than others, we added a step to energy balance of the RGB three channel in classical Multi-Scale Retinex (MSR). Experiment data show that, compared to the traditional three-channel simple addition, our improvement can get more natural recovered underwater image.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129531032","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 : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061414
M. Rana, Md Walid Hasan, A. Abdelhadi
The need and importance of automatic disease recognition such as electroencephalogram has grown over time. Driven by this motivation, this research demonstrates the electroencephalogram (EEG) signals reconstruction process using the finite impulse response, principle component analysis, feature extraction, and support vector machine (SVM). After mentioning related literature, the EEG signals are taken from biomedical database such as Temple University Hospital, Australia. Applying finite impulse filter to the noisy EEG signals, the motion artifacts have been effectively removed. Generally, EEG signal is a multidimensional so it is quite difficult to find out effective channel for different diseases. Applying principle component analysis over filtered EEG signals, dimensional reduced EEG signals are obtained. For classifying EEG signals, different statistical measured such as standard deviation and mean absolute deviation are applied. Moreover, the SVM is used to classify the EEG signal from the selected features. Finally, the system performance is evaluated by 27 patients EEG database. For each disease, it has taken 9 signals. For different signals, the SVM are trained and evaluate the performance. Simulation results show that the SVM provides better performance for higher number of signals.
{"title":"Diseases Detection from Electroencephalogram Signals Using Support Vector Machine","authors":"M. Rana, Md Walid Hasan, A. Abdelhadi","doi":"10.23919/ICACT48636.2020.9061414","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061414","url":null,"abstract":"The need and importance of automatic disease recognition such as electroencephalogram has grown over time. Driven by this motivation, this research demonstrates the electroencephalogram (EEG) signals reconstruction process using the finite impulse response, principle component analysis, feature extraction, and support vector machine (SVM). After mentioning related literature, the EEG signals are taken from biomedical database such as Temple University Hospital, Australia. Applying finite impulse filter to the noisy EEG signals, the motion artifacts have been effectively removed. Generally, EEG signal is a multidimensional so it is quite difficult to find out effective channel for different diseases. Applying principle component analysis over filtered EEG signals, dimensional reduced EEG signals are obtained. For classifying EEG signals, different statistical measured such as standard deviation and mean absolute deviation are applied. Moreover, the SVM is used to classify the EEG signal from the selected features. Finally, the system performance is evaluated by 27 patients EEG database. For each disease, it has taken 9 signals. For different signals, the SVM are trained and evaluate the performance. Simulation results show that the SVM provides better performance for higher number of signals.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129555281","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：