检索结果-内蒙古大学图书馆

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Xiaofeng Qin Zijie Sun Meiyun Du Yu-An Zhang Bingfeng Li Rende Song Department of Computer Technology and Applications Qinghai University Xining China Department of Mechanical Engineering Qinghai University Xining China Yushu Prefecture Animal Husbandry and Veterinary Station Yushu Qinghai China

ISBN: (纸本)9781538680988;9781538680971

In recent years, sustainable economic development is a hot topic in various fields. The development of animal husbandry in Qinghai Tibet Plateau is the key industry in this region and the sustainable development of ecology, environment and economy is an urgent problem to be studied. This paper focuses on the visualization of the alpine meadow yak grazing model, shielding the internal implementation of the model and embedding the genetic algorithm, which greatly simplifies the process of solving the model, improves the possibility of new technologies being promoted in pastoral areas and provides a platform for subsequent research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FSO Links with Spatial Diversity Over Strong Atmospheric Turbulence Channels

FSO Links with Spatial Diversity Over Strong Atmospheric Tur...

引用

2008 IEEE International Conference on Communications(ICC 2008)

作者： Theodoros A.Tsiftsis Harilaos G.Sandalidis George K.Karagiannidis Murat Uysal Department of Electrical and Computer Engineering Aristotle University of Thessaloniki54124 ThessalonikiGreece Department of Informatics with Biomedical Applications University of Central Greece35100 LamiaGreece Department of Electrical and Computer Engineering of University of Waterloo WaterlooOntarioCanadaN2L 3G1

Free-space optical(FSO) communication has received much attention in recent years as a cost-effective,licensefree and wide-bandwidth access technique for high data rates *** performance of FSO communication,however,severely suffers from turbulence-induced fading caused by atmospheric *** laser transmitters and/or receivers can be placed at both ends to mitigate the turbulence fading and exploit the advantages of spatial *** diversity is particularly crucial for strong turbulence channels in which single-input single-output(SISO) link performs extremely ***-induced strong turbulence fading in outdoor FSO systems can be modeled as a multiplicative random process which follows the K *** this paper,we investigate the error rate performance of FSO systems for K-distributed atmospheric turbulence channels and potential advantages of spatial diversity deployments at the transmitter and/or *** results demonstrate significant diversity gains of multiple transmitter/receivers deployment in FSO *** further present efficient approximated closed-form expressions for the average bit-error rate(BER) of multiple-input single-output(MISO) and single-input multiple-output(SIMO) FSO *** analytical tools are reliable alternatives to time-consuming Monte Carlo simulation of FSO systems where BER targets as low as 10 9 are typically aimed to achieve.

关键词： FSO Links with Spatial Diversity Over Strong Atmospheric Turbulence Channels Spatial

来源：评论

学校读者我要写书评

暂无评论

An Examination of Machine Learning Techniques for Automating and Optimizing VLSI Design

An Examination of Machine Learning Techniques for Automating...

引用

Science, Technology, engineering and Management (ICSTEM), International Conference on

作者： R. Jeyarohini R Sathya S. P. Sellapaandi P Kavitha D. Raja Ramesh Aparajita Mukherjee Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India Department of Computer Applications Alpha Arts and Science College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering R.M.K. Engineering College Kavaraipettai Tamil Nadu India Department of Electronics and Communication Engineering MVGR College of Engineering(A) Vizianagaram Andhra Pradesh India Department of Computer Science and Engineering IEM-UEM Kolkata India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

This research examines the use of machine learning (ML) techniques to automate and optimise Very Large Scale Integration (VLSI) design procedures. Very large scale integrated circuits (VLSI) require a number of laborious and complex processes to be designed, such as placement, routing, and logic synthesis. Historically, manual involvement and specialised knowledge have been needed to complete these jobs. The goal of this research is to use machine learning approaches to increase chip performance, improve design efficiency, and streamline the workflows involved in VLSI design. Numerous machine learning (ML) techniques, including evolutionary algorithms, reinforcement learning, and supervised learning, are being investigated to determine their efficacy in automating design tasks, optimising design parameters, and cutting down on design cycle durations. This research shows that incorporating machine learning techniques into VLSI design processes is not only possible but also advantageous through extensive tests and case studies. The results of this study are highly relevant to the semiconductor industry in this era of sophisticated microelectronics. They could open the door to more scalable and effective VLSI design processes

关键词： Supervised learning Electronics industry Reinforcement learning Manuals Evolutionary computation Very large scale integration Routing

来源：评论

学校读者我要写书评

暂无评论

Transformer Monitoring and Security System Using IoT

Transformer Monitoring and Security System Using IoT

引用

Innovative Practices in Technology and Management (ICIPTM), International Conference on

作者： Sudhir Anakal Sangita Rani Kar A. Sangeetha Sritha P Dekka Satish Sajitha. L. P A. Rajendra Prasad Department of Computer Applications Sharnbasva University Karnataka India Department of Electrical & Electronics ITER Siksha ‘O’ Anusandhan Odisha India Department of Computer Science R.M.K College of Engineering & Technology Chennai India Department of Electrical & Electronics Bannari Amman Institute of Technology Chennai India Department of Computer Science Lendi Institute of Engineering & Technology Andhra Pradesh India Department of Computer Science R. M. K Engineering College Chennai India Department of Mechanical Engineering Sri Sai Ram Engineering College Chennai India

Temperature increases are a common source of problems in transformers. Temperature increases as load current increases. There are two ways to monitor the rise in load current. Use a potential transformer and a temperature sensor, respectively. Voltage drops and winding temperature rises as load current increases. By measuring these two variables with a voltage sensor and a temperature sensor, the transformer problem can be resolved. The quantity detected by the sensor will be relayed over IoT to the control room in order to inform it of the transformer's state. It operates totally on autopilot. The Node MCU8266 board (which consist of microcontroller and built-in Wi-Fi board) included with the sensor will activate the circuit breaker to protect the transformer when the fault level is high.

关键词： Temperature sensors Temperature measurement Voltage measurement Voltage transformers Current measurement Circuit breakers Windings

来源：评论

学校读者我要写书评

暂无评论

Analysis of Various Image Segmentation Techniques on Retinal OCT Images

Analysis of Various Image Segmentation Techniques on Retinal...

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： T. M. Sheeba S. Albert Antony Raj M. Anand Department of Computer Applications College of Science and Humanities SRM Institute of Science and Technology Chennai India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Chennai India

Image segmentation is one of the most important processes involved in image processing. Segmenting an image is breaking it up into smaller pieces, or segments. These are the areas where it is most helpful because processing the complete image would be inefficient for tasks like object recognition or image compression. Image segmentation is the process of dividing an image's elements for further processing. This article looked at a number of image segmentation techniques, including the threshold approach, edge-based method, and clustering-based method. The segmentation method that is most effective for separating images in OCT images is clustering-based segmentation. To reduce the speckle noise during preprocessing, the wiener filter approach is used. With regards to the threshold, edge-based (Sobel, Canny, Robert's), and clustering-based segmentation techniques, calculate MSE (mean square error) and PSNR (peak signal to noise ratio) values for the segmented image quality.

关键词： Image segmentation PSNR Wiener filters Image edge detection Clustering methods Mean square error methods Speckle

来源：评论

学校读者我要写书评

暂无评论

Gated Recurrent Units and Recurrent Neural Network Based Multimodal Approach for Automatic Video Summarization

引用

Traitement du Signal 2023年第3期40卷 1227-1234页

作者： Kaur, Lakhwinder Aljrees, Turki Kumar, Ankit Pandey, Saroj Kumar Singh, Kamred Udham Mishra, Pankaj Kumar Singh, Teekam Department of Electronics & Telecommunication Engineering Rungta College of Engineering and Technology Bhilai490024 India College of Computer Science and Engineering University of Hafr Al Batin Hafar Al Batin39524 Saudi Arabia Department of Computer Engineering & Applications GLA University Mathura281406 India Department of Computer Science and Information Engineering National Cheng Kung University Tainan701 Taiwan School of Computing Graphic Era Hill University Dehradun248002 India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun248002 India

A typical video record aggregation system requires the concurrent performance of a large number of image processing tasks, including but not limited to image acquisition, pre-processing, segmentation, feature extraction, verification, and description. These tasks must be executed with utmost precision to ensure smooth system performance. Among these tasks, feature extraction and selection are the most critical. Feature extraction involves converting the large-scale image data into smaller mathematical vectors, and this process requires great skill. Various feature extraction models are available, including wavelet, cosine, Fourier, histogram-based, and edge-based models. The key objective of any feature extraction model is to represent the image data with minimal attributes and no loss of information. In this study, we propose a novel feature-variance model that detects differences in video features and generates feature-reduced video frames. These frames are then fed into a GRU-based RNN model, which classifies them as either keyframes or non-keyframes. Keyframes are then extracted to create a summarized video, while non-keyframes are reduced. Various key-frame extraction models are also discussed in this section, followed by a detailed analysis of the proposed summarization model and its results. Finally, we present some interesting observations about the proposed model and suggest ways to improve it. © 2023 Lavoisier. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification of Songs Using Deep Learning

Emotion Classification of Songs Using Deep Learning

引用

Green Energy, Computing and Sustainable Technology (GECOST), International Conference on

作者： Nikita Mate Durva Akre Gaurav Patil Gopal Sakarkar Thomas Anung Basuki Department of Artificial Intelligence G. H. Raisoni College of Engineering Nagpur India D.Y. Patil Institute of Master of Computer Applications and Management Akurdi Pune India Department of Computer Science University of Southampton Malaysia

ISBN: (纸本)9781665486644

The sentiment prediction of songs will have a vast quantity of applications within the current era, like the Music recommendation system for request, choosing the music for public gatherings like procession or restaurants to enhance the emotional standing of a personal or cluster, seemingly folks and customers. A song is one way to say something indirectly and one of the most adventurous parts is that the one song could express more than one emotion. We can use songs to apologize, congratulate, express happiness or unhappiness, etc. Emotion is a vital part of daily life: it affects choice-making, conception, human interdependence, and human understanding. There are units of positive emotions and negative emotions; positive emotions are units a lot related to human health also as work potency, whereas negative emotions could cause health issues. In this research paper, we are going to use Deep Learning Frameworks, which are mostly used for classification techniques like Multilayer Perceptron (MLP), Gated Recurrent Units(GRU), Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). In this paper, the dataset operated is the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) [1] for the enactment of audio categorization. As a result, we obtained graphs for each Deep Learning framework that is for training and validation loss, training and validation accuracy. After implementation, we got the highest accuracy for CNN that is 92.71% and the least accuracy for MLP that is 52.60% and for LSTM and GRU it lies between the range of 63% - 66%.

关键词： Deep learning Training Databases Multilayer perceptrons Logic gates Classification algorithms Internet

来源：评论

学校读者我要写书评

暂无评论

Cryptanalysis of an anonymous message authentication scheme for smart grid 13th

Cryptanalysis of an anonymous message authentication scheme ...

引用

13th International Conference on Genetic and Evolutionary Computing, ICGEC 2019

作者： Liang, Xiao-Cong Wu, Tsu-Yang Lee, Yu-Qi Wang, Tao Chen, Chien-Ming Chen, Yeh-Cheng School of Information Science and Engineering Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Department of Computer Science University of California DavisCA95616 United States

ISBN: (纸本)9789811533075

Authentication schemes are used to authenticate the identity of communication parties and widely applied to several environments. Recently, Wu et al. proposed an anonymous message authentication scheme in smart grid. However, we show that their scheme has several security weaknesses based on the CK adversarial model in this paper. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A control-design-based solution to robotic ecology: Autonomy of achieving cooperative behavior from a high-level astronaut command

A control-design-based solution to robotic ecology: Autonomy...

引用

作者： Wang, Jing Qu, Zhihua Ihlefeld, Curtis M. Hull, Richard A. Department of Electrical and Computer Engineering University of Central Florida Orlando FL 32816 United States Kennedy Space Center FL 32899 United States Lockheed Martin Missiles and Fire Control 5600 Sand Lake Rd. MP-450 Orlando FL 32819 United States School of Electrical and Computer Science University of Central Florida IEEE AIAA University of Central Florida Department of Electrical and Computer Engineering National Aeronautics and Space Administration Kennedy Space CenterKennedy Space Center Applied Physics Lab. Advanced Concepts Business Unit Science Applications International Corporation SAIC IEEE Control System Society

In this paper, we propose a cooperative control strategy for a group of robotic vehicles to achieve the specified task issued from a high-level astronaut command. The problem is mathematically formulated as designing the cooperative control for a general class of multiple-input-multiple-output (MIMO) dynamical systems in canonical form with arbitrary but finite relative degrees such that the outputs of the overall system converge to the explicitly given steady state. The proposed cooperative control for individual vehicle only need to use the sensed and communicated outputs information from its local neighboring vehicles. No fixed leader and time-invariant communication networks are assumed among vehicles. Particularly, a set of less-restrictive conditions on the connectivity of the sensor/communication networks are established, under which it is rigorously proven by using the newly found nice properties of the convergence of sequences of row stochastic matrices that the cooperative objective of the overall system can be achieved. Simulation results for a group of vehicles achieving a target and surrounding a specified object in formation are provided to support the proposed approach in this paper.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Content Moderation System using Adversarial Machine Learning

A Multimodal Content Moderation System using Adversarial Mac...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： A. Barveen M.K. Mohamed Faizal S. Geetha Department of Artificial Intelligence and Data Science M.I.E.T. Engineering College Trichy Tamilnadu Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Trichy Tamilnadu Department of Computer Applications University College of Engineering Trichy Tamilnadu

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Memes are a visual representation of images with text embedded in them that conveys the thoughts and feelings of a peculiar audience and is mainly intended to elicit humor. It is widely spread across social media platforms in the guise of sardonic images, humorous jokes, and several other viral sensations. After the profound success of the late fusion technique that combines multimodal features, researchers have used stacked LSTM to extract textual features, whereas VGG16 has been used to extract visual features. Apart from this, BiLSTM and CNN have been used to extract contextual features. This study suggests a unique deep learning-based method for classifying objectionable memes within a multimodal dataset to address this problem. The proposed system uses machine learning to train the classifier on labeled data, which allows it to categorize the information accurately. The proposed system uses both text and image data. To improve user experience and safety, offensive images are blurred, and offensive words are shuffled using adversarial training.

关键词： Training Learning systems Deep learning Visualization Technological innovation Social networking (online) Feature extraction

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：