检索结果-内蒙古大学图书馆

5th International Conference on Data Science and information technology, DSIT 2022

作者： Zhang, Yue Zhang, Dong Guo, Feng Wang, Xiaotong Duan, Yihai Zhang, Xiaonan School of Electrical and Information Engineering Zhengzhou University Zhengzhou China Inspur Electronic Information Industry Co. Ltd. System Software R&D Dept. Jinan China Inspur Electronic Information Industry Co. Ltd. System Software R&D Dept. Zhengzhou China Compute Science and Technology Harbin Institute of Technology Weihai Weihai China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

With the development of the Internet and the digital age continues to advance, traditional operation and maintenance methods can no longer meet the maintenance of large-scale distributed systems, AIOps emerges as the times require. In AIOps, finding anomalies is a top priority. PCA (Principal Component Analysis) is a traditional machine learning algorithm, which is used for log anomaly detection using the dimensionality reduction feature of PCA algorithm, the advantages of this detection method are: fast detection and simple model. However, the anomaly detection effect is not satisfactory, because when extracting the features of log data, the sequence features and semantic features cannot be sufficiently mined, resulting in a lower accuracy rate. For this problem, we propose a feature extraction improvement model. This model is based on Bi-LSTM (Bidirectional Long Short Term Memory) deep network to improve the feature extraction method of PCA model, extracting semantic features of log sequences by exploiting the ability of long short-term memory network to grasp contextual information, and feed the vector representation matrix containing the semantic features into the PCA anomaly detection network for anomaly detection. The model is validated on HDFS open source dataset and Inspur server dataset, and the results show that the F1-measure of this model is 36.3 % higher than that of the traditional PCA model, and 1.1 % higher than that of the single Bi-LSTM model. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Impact of bit error on video transmission over wireless networks and error resiliency

Impact of bit error on video transmission over wireless netw...

引用

2011 International Conference on Image information Processing, ICIIP 2011

作者： Purandare, R.G. Kshirsagar, S.P. Koli, S.M. Gohokar, V.V. Dept. of Electronics and Telecommunications Vishwakarma Institute of Information Technology Pune Maharashtra India AnchorTek Techno Consultancy Pvt. Ltd. Pune Maharashtra India Dept. of Electronics and Telecommunications Smt. Kashibai Navale College of Engineering Pune Maharashtra India Dept. of Electronics and Telecommunications Sant. Gajanan Maharaj College of Engineering India

ISBN: (纸本)9781612848617

To improve the robustness of video transmission over heterogeneous wireless network various error resilient tools are deployed. The impact of bit errors on the perceived video quality depends on several factors, such as error resilience of the data format, error concealment mechanism used and characteristics of the bit error pattern. In this paper the impact of bit error is analyzed and various error resilient tools implemented at the transmitter side, at the receiver and the ones requiring interactive feedback on dynamic channel conditions are discussed. The paper also covers a few cross layer optimization techniques. © 2011 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

A PID control Algorithm for Path Tracking of a Nonholonomic Car-Like Robot

A PID Control Algorithm for Path Tracking of a Nonholonomic ...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Indrazno Siradjuddin Dimas Adi Prayoga Sapto Wibowo Yan Watequlis Syaifudin Rendi Pambudi Wicaksono Mas Nurul Achmadiah Dept. of Electrical Engineering State Polytechnic of Malang Malang Indonesia Dept. of Information Technology State Polytechnic of Malang Malang Indonesia Dept. Of Computer Control Engineering State Polytechnic of Madiun Madiun Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

A car-like robot with an Ackermann steering system is a type of nonholonomic which is characterised by a set of first-order differential constraints on its configuration variables, which are not integrable. This distinctive characteristic gives rise to complex issues in the construction of feedback controllers. This research proposes reactive control using a feedback controller using PID algorithm for a car-like robot navigation. The proposed method controls the steering angle of the car-like robot to follow the prescribed path with a constant longitudinal robot velocity. The open-loop car-like dynamical system has been formulated in the form of state-space model. Two PID controllers in parallel computed the lateral position error and the yaw angle error. The summation of the two outputs from the PID controllers was inputted into the state-space model. The PID controller parameters were selected based on trial and error. The simulation results confirm the effectiveness of the proposed control algorithm.

关键词： PI control Navigation Simulation Heuristic algorithms Steering systems State-space methods PD control Adaptive control Dynamical systems Robots

来源：评论

学校读者我要写书评

暂无评论

Development of interior permanent magnet motors with concentrated windings for reducing magnet eddy current loss

引用

IEEJ Transactions on Industry Applications 2009年第11期129卷 1022-1029+2页

作者： Yamazaki, Katsumi Kanou, Yuji Fukushima, Yu Ohki, Shunji Nezu, Akira Ikemi, Takeshi Mizokami, Ryoichi Dept. of E. E. C. E. Chiba Institute of Technology 2-17-1 Tsudanuma Narashino 275-0016 Japan Electronics Control Engineering Department Electronics and Power Electronics Engineering Division Electric Motor Engineering Group 2-10-1 Hironodai Zama 228-8502 Japan

In this paper, we present the development of interior magnet motors with concentrated windings, which reduce the eddy current loss of the magnets. First, the mechanism of the magnet eddy current loss generation is investigated by a simple linear magnetic circuit. Due to the consideration, an automatic optimization method using an adaptive finite element method is carried out to determine the stator and rotor shapes, which decrease the eddy current loss of the magnet. The determined stator and rotor are manufactured in order to proof the effectiveness by the measurement. © 2009 The Institute of Electrical Engineers of Japan.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Ceph-based storage server application 6

Ceph-based storage server application

引用

6th International Symposium on Digital Forensic and Security, ISDFS 2018

作者： Azginoǧlu, Nuh Eren, Mehmet Akif Çelik, Mete Aydin, Zafer Dept. of Computer Engineering Nevşehir Haci Bektaş Veli University Nevşehir Turkey Dept. of Information and Technology Nevşehir Haci Bektaş Veli University Nevşehir Turkey Dept.of Computer Engineering Erciyes University Kayseri Turkey Dept.of Computer Engineering Abdullah Gül University Kayseri Turkey

ISBN: (纸本)9781538634493

Ceph is a scalable and high performance distributed file system. In this study, a Ceph-based storage server was implemented and used actively. This storage system has been used as a disk of 40 virtual servers in 4 different Proxmox servers. Performance evaluation of the system has been conducted on virtual servers that holds Windows and Linux based operating systems. © 2018 IEEE.

关键词： File organization

来源：评论

学校读者我要写书评

暂无评论

Enhancing OCR Accuracy Using Convolutional Neural Networks: A Study on Spelling Correction in Handwritten Numerals 1

Enhancing OCR Accuracy Using Convolutional Neural Networks: ...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kaushik, Priyanka Dewal, Inder Singh Singh Rathore, Sajjan Singh, Vinay Kumar, Sani Bhavani, P.M. Sindhu Chandigarh University Dept. of Computer Science Engineering Chandigarh India Madhav University Dept. of Humanities & S.Science Pindwara India Usha Martin University Dept. of Com. & Information Technology Jharkhand India Mangalayatan University Dept. of Computer Eng. & Applications Aligarh India Meenakshi A.H.Edu. & Research Dept. of Humanities & Science Chennai India

ISBN: (纸本)9798350356816

Artificial neural networks have transformed machine learning and had a significant impact on a wide range of industries, including robotics, deep learning, healthcare, sports, and surveillance. Convolutional Neural Networks (CNNs) are unique among these developments because they combine cutting-edge deep learning methods with conventional Artificial Neural Networks (ANNs). CNNs are essential for tasks like data analysis, text classification, speech and face recognition, and pattern recognition in a variety of fields. In order to improve spelling correction, this article uses a dataset that was upgraded from the National Institute of Standards & technology (NIST) and includes 70,000 grayscale pictures of handwritten numbers. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Architecture of Web-EDA system based on Cloud computing and application for project management of IC design

Architecture of Web-EDA system based on Cloud computing and ...

引用

2010 International Conference on Anti-Counterfeiting, Security and Identification, 2010 ASID

作者： Lin, Xiaopeng Li, Yiyang Dai, Huaiyu Guo, Donghui Dept. of Physics Xiamen University Xiamen Fujian 361005 China Department of Electrical and Computer Engineering North Carolina State University Raleigh NC 27695-7911 United States Dept. of Electronic Engineering Xiamen University Xiamen Fujian 361005 China Dept. of Information Technology Xiamen Ocean Vocational College Xiamen Fujian 361005 China

ISBN: (纸本)9781424467327

Cloud computing is usually defined to deliver infrastructure, platform and software as services, which is available as a pay-as-you-go model for users. A paradigm of Cloud computing for EDA service is presented in this paper, and a hierarchical architecture of Web-EDA system implemented with Cloud computing is described in detail. Based on this proposed system structure, we developed a prototype of the Web-EDA system for sharing EDA Tools and project management of IC design. It shows that Cloud computing for EDA service is possible to be implemented distributedly and brings maximum benefit to both users and vendors. © 2010 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

TCN-CUTIE: A 1036 TOp/s/W, 2.72 µJ/Inference, 12.2 mW All-Digital Ternary Accelerator in 22 nm FDX technology

arXiv

引用

arXiv 2022年

作者： Scherer, Moritz Di Mauro, Alfio Fischer, Tim Rutishauser, Georg Benini, Luca Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland Dept. of Electrical Electronic and Information Engineering University of Bologna Italy

Tiny Machine Learning (TinyML) applications impose µJ/Inference constraints, with a maximum power consumption of tens of mW. It is extremely challenging to meet these requirements at a reasonable accuracy level. This work addresses the challenge with a flexible, fully digital Ternary Neural Network (TNN) accelerator in a RISC-V-based System-on-Chip (SoC). Besides supporting Ternary Convolutional Neural Networks, we introduce extensions to the accelerator design that enable the processing of time-dilated Temporal Convolutional Neural Networks (TCNs). The design achieves 5.5 µJ/Inference, 12.2 mW, 8000 Inferences/sec at 0.5 V for a Dynamic Vision Sensor (DVS) based TCN, and an accuracy of 94.5% and 2.72 µJ/Inference, 12.2 mW, 3200 Inferences/sec at 0.5 V for a non-trivial 9-layer, 96 channels-per-layer convolutional network with CIFAR-10 accuracy of 86%. The peak energy efficiency is 1036 TOp/s/W, outperforming the state-of-the-art silicon-proven TinyML quantized accelerators by 1.67x while achieving competitive accuracy. © 2022, CC BY-NC-ND.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions

arXiv

引用

arXiv 2022年

作者： Di Mauro, Alfio Prasad, Arpan Suravi Huang, Zhikai Spallanzani, Matteo Conti, Francesco Benini, Luca Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland Dept. of Electrical Electronic and Information Engineering University of Bologna Italy

Event-based sensors are drawing increasing attention due to their high temporal resolution, low power consumption, and low bandwidth. To efficiently extract semantically meaningful information from sparse data streams produced by such sensors, we present a 4.5TOP/s/W digital accelerator capable of performing 4-bits-quantized event-based convolutional neural networks (eCNN). Compared to standard convolutional engines, our accelerator performs a number of operations proportional to the number of events contained into the input data stream, ultimately achieving a high energy-to-information processing proportionality. On the IBM-DVS-Gesture dataset, we report 80uJ/inf to 261uJ/inf, respectively, when the input activity is 1.2% and 4.9%. Our accelerator consumes 0.221pJ/SOP, to the best of our knowledge it is the lowest energy/OP reported on a digital neuromorphic engine. © 2022, CC BY-NC-ND.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Passive and Asynchronous Wake-up Receiver for Acoustic Underwater Communication

arXiv

引用

arXiv 2024年

作者： Schulthess, Lukas Mayer, Philipp Benini, Luca Magno, Michele Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland Dept. of Electrical Electronic and Information Engineering University of Bologna Italy

Establishing reliable data exchange in an underwater domain using energy and power-efficient communication methods is crucial and challenging. Radio frequencies are absorbed by the salty and mineral-rich water and optical signals are obstructed and scattered after short distances. In contrast, acoustic communication benefits from low absorption and enables communication over long distances. Underwater communication must match low power and energy requirements as underwater sensor systems must have a long battery lifetime and need to work reliably due to their deployment and maintenance cost. For long-term deployments, the sensors’ overall power consumption is determined by the power consumption during idle state. It can be reduced by integrating asynchronous always-on wake-up circuits with nano-watt power consumption. However, this approach does reduce but not eliminate idle power consumption, leaving a margin for improvement. This paper presents a passive and asynchronous wake-up receiver for acoustic underwater communication enabling zero-power always-on listening. Zero-power listening is achieved by combining energy and information transmission using a low-power wake-up receiver that extracts energy out of the acoustic signal and eliminates radio frontend idle consumption. In-field evaluations demonstrate that the wake-up circuit requires only 63 µW to detect and compare an 8-bit UUID at a data rate of 200 bps up to a distance of 5 m and that the needed energy can directly be extracted from the acoustic signal. Copyright © 2024, The Authors. All rights reserved.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：