2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)最新文献

筛选
英文 中文
Machine learning based SRM control using FPGAs for torque ripple minimization 基于机器学习的SRM控制,利用fpga实现转矩脉动最小化
Srinivasan Kandhasamy
{"title":"Machine learning based SRM control using FPGAs for torque ripple minimization","authors":"Srinivasan Kandhasamy","doi":"10.1109/ICAIIC48513.2020.9065241","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065241","url":null,"abstract":"Switched Reluctance Motor (SRM) is an attractive candidate for electric vehicles and much research is ongoing on motor and its control particularly in the last decade due to advancement in power electronics. Non-linear characteristics of SRM have been a challenge for control engineers for SRM control implementation. In such cases, learning models such as Artificial Neural Network (ANN), fuzzy logic, genetic algorithms etc., are helpful which are easier in terms of the programming and computation. One of the challenge for SRM application is its inherent torque ripple, which can affect drivability, vehicle dynamics and acoustics. Existing approaches for minimizing the ripple are based on standard normal Torque Sharing Function (TSF). In this paper, a novel approach is proposed to bring further reduction in the torque ripple in base, medium and high speed of the motor and also the implementation of this control algorithm is discussed. Two pre-trained ANN models are implemented one for providing run-time torque feedback and another one for calculating instantaneous reference currents for each phase. The novelty of this proposed approach is in providing a dynamic limiter for instantaneous current, based on the speed and torque error, in real time. The machine-learning model is implemented as a sequential logic on Xilinx Zynq-Ultrascale SoC Field Programmable Control Arrays (FPGA). The complete motor control is realized on the Programmable Logic (PL) part of the FPGA. FPGA utilization, along with timing diagram is evaluated for the ANN implementation, which could be used as a basis for selection of FPGAs.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"2013 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":"128010914","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}
引用次数: 2
$Q$ - TRANSFER: A Novel Framework for Efficient Deep Transfer Learning in Networking 迁移:网络中高效深度迁移学习的新框架
Trung V. Phan, Shabnam Sultana, Tri Gia Nguyen, T. Bauschert
{"title":"$Q$ - TRANSFER: A Novel Framework for Efficient Deep Transfer Learning in Networking","authors":"Trung V. Phan, Shabnam Sultana, Tri Gia Nguyen, T. Bauschert","doi":"10.1109/ICAIIC48513.2020.9065240","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065240","url":null,"abstract":"In this paper, we propose a novel framework, namely Q-TRANSFER, to address the insufficiency problem of the actual training data sets in modern networking platforms in order to push the application of deep learning in the context of communication networking. In particular, we adopt deep transfer learning, i.e., network-transfer, as a key technique to mitigate the data set insufficiency problem. Being aware of the negative transfer we - instead of trying to alleviate the negative transfer - aim to maximise the positive transfer. We examine a basic networking deep transfer learning system and formulate the optimisation problem of achieving the most beneficial knowledge from a source deep learning model. In order to circumvent the optimisation problem, we further propose to employ a reinforcement learning approach, i.e., Q-learning algorithm. As a case study, a DDoS attack detection method using a Multilayer Perceptrons algorithm (MLP) is taken to demonstrate the effectiveness and capabilities of the Q- TRANSFER framework. Results obtained from extensive experiments confirm that the most beneficial attack detection knowledge is derived from the source deep learning model by applying the Q-learning algorithm. The efficiency is increased up to 43.58 % compared to traditional deep transfer learning methods. To the best of our knowledge, this is the first study on optimising knowledge transfer for deep learning applications in the field of networking.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"211 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":"133972518","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}
引用次数: 17
Down-clocking Scheme using Deep Learning for Minimizing Energy Consumption in Wireless Networks 基于深度学习的无线网络能耗最小化降频方案
Jae-Hyeon Park, S. Jeong, Young-Joo Suh
{"title":"Down-clocking Scheme using Deep Learning for Minimizing Energy Consumption in Wireless Networks","authors":"Jae-Hyeon Park, S. Jeong, Young-Joo Suh","doi":"10.1109/ICAIIC48513.2020.9065016","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065016","url":null,"abstract":"Wi-Fi interface is known to consume a lot of energy in mobile devices, and Idle Listening (IL) dominates clients' energy consumption in Wi-Fi. In this paper, we propose IL down-clocking schemes using deep learning model to reduce the energy consumption in IL time. We exploit the orthogonal frequency-division multiplexing (OFDM) subcarrier addressing for the preamble design. To minimize preamble length for energy efficiency, we use a deep learning model with the recurrent neural network (RNN). Our experimental evaluation using OPNET network simulator and USRP/GNU Radio implementation shows that our scheme outperforms the state-of-the-art down-clocking scheme in both energy consumption and network throughput.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":"130844633","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}
引用次数: 0
Radio Environment Map Construction with Joint Space-Frequency Interpolation 基于联合空频插值的无线电环境图构建
Koya Sato, Kei Inage, T. Fujii
{"title":"Radio Environment Map Construction with Joint Space-Frequency Interpolation","authors":"Koya Sato, Kei Inage, T. Fujii","doi":"10.1109/ICAIIC48513.2020.9065217","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065217","url":null,"abstract":"In this paper, we propose a radio environment map (REM) construction method that interpolates the received signal power over not only the spatial domain but also the frequency domain. REM is a tool for analyzing radio propagation, which is typically defined as a map that stores the received signal power. Crowdsourcing with spatial interpolation (e.g., Kriging) can accurately construct the REM, and the accurate REM improves the efficiency of spectrum use. However, crowdsourcing can only be performed over frequencies in which the mobile terminals can perform the sensing. Thus, conventional REM construction may only improve the spectral efficiency in the frequency in which the sensing can be performed. Our proposed method focuses on the fact that the average received signal power, which consists of path loss and shadowing, shows a strong correlation over the frequency domain. We show that utilizing correlations over both frequency and spatial domains can construct the REM even if the datasets are not available at the estimated environment.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"29 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":"115230132","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}
引用次数: 12
Image Quality Enhancement with Machine Learning Based Multi-Step Super-Resolution 基于机器学习的多步超分辨率图像质量增强
Niai Yano, Hiroshi Watanabe
{"title":"Image Quality Enhancement with Machine Learning Based Multi-Step Super-Resolution","authors":"Niai Yano, Hiroshi Watanabe","doi":"10.1109/ICAIIC48513.2020.9065207","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065207","url":null,"abstract":"Machine Learning based Super-Resolution techniques have recently been able to achieve good qualitative results. Convolutional Neural Networks have thus become the basis for recent studies on SR techniques. In this paper, we propose a novel Multi-Step Super-Resolution technique that applies previous methods that achieve good results. We also demonstrate that this proposed method achieves a significant improvement in both subjective visual quality and in reconstruction accuracy, relative to conventional methods.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"181 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":"124523886","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}
引用次数: 0
Voltage and Reactive Power Control by Parallel Modified Brain Storm Optimization 基于并行改进头脑风暴优化的电压和无功控制
Kaichi Matsumoto, Y. Fukuyama
{"title":"Voltage and Reactive Power Control by Parallel Modified Brain Storm Optimization","authors":"Kaichi Matsumoto, Y. Fukuyama","doi":"10.1109/ICAIIC48513.2020.9065267","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065267","url":null,"abstract":"This paper proposes voltage and reactive power control (VVC) by parallel modified brain storm optimization (parallel MBSO). VVC problems have been solved by various evolutionary computation methods because the problem is a mixed-integer nonlinear programing (MINLP) problem. Recently, the control interval of VVC is required to be shortened and a larger-scale VVC problem is also required to be solved in a limited short time considering high penetration of renewable energy and progress of deregulation in power systems. The proposed parallel MBSO based method is confirmed to be effective by comparison with the conventional canonical differential evolutionary particle swarm optimization and original BSO based methods.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"65 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":"116297320","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}
引用次数: 0
Implementation of Computation-Efficient Sensor Network for Kalman Filter-based Intelligent Position-Aware Application 基于卡尔曼滤波的智能位置感知应用中高效计算传感器网络的实现
Jisu Kwon, Daejin Park
{"title":"Implementation of Computation-Efficient Sensor Network for Kalman Filter-based Intelligent Position-Aware Application","authors":"Jisu Kwon, Daejin Park","doi":"10.1109/ICAIIC48513.2020.9065098","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065098","url":null,"abstract":"Most edge nodes operate under limited power conditions for reasons of unstable power supply or small battery capacity. Therefore, computations running on edge nodes need to be lightweight. There are extensive usages of the Kalman filter, this paper presents the implementation of a computation-efficient IoT sensor network which tracking the moving target with the Kalman filter. Rather than improving the Kalman filter itself, the Kalman filter operation performed at each node varies performance based on the information being sensed. The nodes are decreasing their data receiving interval according to the distance between the target and each node. Also, we use an arithmetic approximation with changing precision when receiving the target information. The presented computation-efficient sensor network evaluated under MATLAB simulation environment to prove its lower computation amount. Evaluation showed that the computation time at each node was reduced by 17.7% on average compared to the conventional sensor network followed by nodes with a fixed behavior. Besides, despite the cost of arithmetic approximation, the edge node estimates the velocity of the target with reasonable accuracy. Based on this result, this paper suggests that decreasing the computation load of whole sensor network by varying each node's calculation with a macro perspective.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"222 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120872523","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}
引用次数: 2
Resource Optimization in Satellite-Based Internet of Things 基于卫星的物联网资源优化
Feng Li, Kwok-Yan Lam
{"title":"Resource Optimization in Satellite-Based Internet of Things","authors":"Feng Li, Kwok-Yan Lam","doi":"10.1109/ICAIIC48513.2020.9065200","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065200","url":null,"abstract":"To realize the full potential of Internet of Things (IoT) for supporting anytime, anywhere high-quality wireless sensing or cyber-physical operations, especially when deployed in remote and isolated areas, the ability to adopt satellite-enabled IoT is one of the critical success factors. When IoT devices are equipped with satellite communication capabilities, the typical fully distributed topology model of IoT networks should be reconsidered. Besides, high energy efficiency scheme is needed to address the growing bandwidth demand of IoT assets. In this paper, we propose a resource optimization method in satellite-based IoT to address inter-cell interference and to maximize transmission capacity for the whole IoT networks. We formulate the stochastic distribution of numerous IoT terminals in satellite-oriented topology by introducing the mathematics model of Poisson point process so as to achieve the statistical probability of nodes' distance to the terrestrial fusion center. An optimal power allocation optimization objective is then attained. Due to the complexity of the objective function, we adopt a pattern search method to achieve the globally optimal solution for power allocation. Furthermore, numerical results are provided to verify the performances of our proposed method in terms of energy efficiency.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":"129896644","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}
引用次数: 4
Regional Weighted Generative Adversarial Network for LDR to HDR Image Conversion LDR到HDR图像转换的区域加权生成对抗网络
Sung-Woon Jung, Dong-Min Son, Hyuk-Ju Kwon, Sung-Hak Lee
{"title":"Regional Weighted Generative Adversarial Network for LDR to HDR Image Conversion","authors":"Sung-Woon Jung, Dong-Min Son, Hyuk-Ju Kwon, Sung-Hak Lee","doi":"10.1109/ICAIIC48513.2020.9064984","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9064984","url":null,"abstract":"For the image conversion from low dynamic range images to high dynamic range images, we considered the possibility of using the Generative Adversarial Network (GAN) as one of the deep neural network methods. Deep learning requires a lot of data before building a module, but once creation is done, it is convenient to use it. In this paper, we proposed a weighting map for a local luminance based learning to reconstruct locally tone-mapped images.","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"28 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":"128338613","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}
引用次数: 2
Predictive Analysis of Business Processes Using Neural Networks with Attention Mechanism 基于注意力机制的神经网络业务流程预测分析
Patrick Philipp, Rubén Jacob, Sebastian Robert, J. Beyerer
{"title":"Predictive Analysis of Business Processes Using Neural Networks with Attention Mechanism","authors":"Patrick Philipp, Rubén Jacob, Sebastian Robert, J. Beyerer","doi":"10.1109/ICAIIC48513.2020.9065057","DOIUrl":"https://doi.org/10.1109/ICAIIC48513.2020.9065057","url":null,"abstract":"The analysis of ongoing processes is an important task in business process management. This is not surprising, since (e.g.) being able to predict future events in processes enables companies to intervene at an early stage if deviations from a desired workflow are likely to occur. Subsequently, errors and associated financial losses can be prevented or avoided. A common basis for being able to predict future events is a sequence of previous events that are typically stored in a socalled event log. In this work we present a neural network with attention mechanism, which is trained using publicly available event logs (e.g. BPI Challenge 2013). Furthermore, we elaborate the proposed model with an extensive dataset of events of a worldwide known German software company. In addition to promising results (e.g.) with regard to n-gram models, the training time of the proposed model is shorter than that of typical reference models such as neural networks with a long short-term memory architecture (LSTM).","PeriodicalId":424681,"journal":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"37 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":"128681516","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}
引用次数: 10
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书