检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chen, Xiaomeng Wu, Yuchi Yi, Xinlei Huang, Minyi Shi, Ling The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden The Digital Futures Stockholm10044 Sweden The School of Mathematics and Statistics Carleton University OttawaONK1S 5B6 Canada

Information compression techniques are majorly employed to address the concern of reducing communication cost over peer-to-peer links. In this paper, we investigate distributed Nash equilibrium (NE) seeking problems in a class of noncooperative games over directed graphs with information compression. To improve communication efficiency, a compressed distributed NE seeking (C-DNES) algorithm is proposed to obtain a NE for games, where the differences between decision vectors and their estimates are compressed. The proposed algorithm is compatible with a general class of compression operators, including both unbiased and biased compressors. Moreover, our approach only requires the adjacency matrix of the directed graph to be row-stochastic, in contrast to past works that relied on balancedness or specific global network parameters. It is shown that C-DNES not only inherits the advantages of conventional distributed NE algorithms, achieving linear convergence rate for games with restricted strongly monotone mappings, but also saves communication costs in terms of transmitted bits. Finally, numerical simulations illustrate the advantages of C-DNES in saving communication cost by an order of magnitude under different compressors. © 2022, CC BY.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Evaluation of smart metering network and billing system using bluetooth, ZigBee, and GSM

引用

AIP Conference Proceedings 2022年第1期2644卷

作者： Ahmed Oleiwi Abdulrida Al-Ubodi Israa Badr Nasser Al-Mashhadani 1Department of Computer Engineering College of Engineering Al-Nahrain University Baghdad Iraq 2Department of Biomedical Engineering College of Engineering University of Warith Al-Anbiyaa Iraq

The necessity of managing energy through smart devices has become a significant issue in recent years. Though, the intelligent use of smart devices is an essential component in creating smart cities. Hence, it leads to establishing a smart grid as an infrastructure for smart cities. The smart grid infrastructure consists of smart meters, which is more reliable than digital meters for billing generation. A real-time smart meter system design is proposed and tested in this work. The measured voltage, current, and power factor for energy are multiplied every second and summed up for overall energy consumption, and this process applies to every consumer. Then, the energy consumption of each house is collected from a single region by sending them to the DCU (Data Concentrator Unit). Methods of transferring data in the proposed system consist of three technologies. The first one is the Bluetooth used between the smart socket and the smart meter. This technology was used due to the short distance between the two devices. The second one is Xbee, and it connects the smart meter and the DCU. This technology is used due to the distance between the two devices and the number of smart meters connected in one DCU. The last technology is GSM (Global System for Mobile Communications), and it is used between the DCU and the server to transfer data since this technology can cover long distances. Energy providers will have to implement innovative Time-of-Use (TOU) pricing strategies to implement the above process. A smart meter has the potential to encourage consumers to shift demand from peak hours to off-peak hours or reduce peak demand. And upon the real experiment of the system, it was found that the error rate in the voltage sensor used in the system was 0.26%, and the error rate in the current sensor used was 0.6%. These numbers indicate the reliability of the system because they are acceptable values.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Employee performance assessment system based on smart method (case study: Banda Aceh Military Court I-01)

引用

AIP Conference Proceedings 2023年第1期2484卷

作者： Zalfie Ardian Arifah Che Alhadi Gusti Mas Panji 1Department of Information System Faculty of Computer Science Universitas Ubudiyah Indonesia Indonesia 2Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Terengganu Malaysia 3Department of Informatics Engineering Faculty of Computer Science Universitas Ubudiyah Indonesia Indonesia

Employee performance assessment is the evaluation of the employee's performances recorded at the end of every month. This approach is currently used at the Military Court Office I-01 Banda Aceh. The main aim of this assessment is to measure employee's performances in achieving their targets. The results will be used as the measuring key, where an employee is only eligible to receive the allowance, if the targets are successfully fulfilled. At this moment, the assessment form has to be filled in manually by each employee, and they will be later assessed manually by the assessors. This manual process undeniably has many disadvantages, especially in terms of accuracy and efficiency. To solve this problem, the Employee Performance Information System was designed using the SMART (Simple Multi Attribute Technique). The assessments were based on eight indicators, i.e; performance, attendance, the proportion of performance targets, behavioral scores, number of tasks, services, overtime, and monthly rewards earned. The weights for each variable were assessed, and keyed into the system. The values for each variable were compared, and results were generated. In SMART, the weighting is measured as a scale between 0 and 10, thus it is easier to make calculations and comparison. The obtained results (SI-TUKIN) indicated that the system is capable of evaluating and analysing the employee's performances, quickly and effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and computer Vision Techniques in Continuous Beehive Monitoring Applications: A Survey

arXiv

引用

arXiv 2022年

作者： Bilik, Simon Zemcik, Tomas Kratochvila, Lukas Ricanek, Dominik Richter, Miloslav Zambanini, Sebastian Horak, Karel Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3058/10 Brno61600 Czech Republic Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Yliopistonkatu 34 Lappeenranta53850 Finland Computer Vision Lab Institute of Visual Computing & Human-Centered Technology Faculty of Informatics TU Wien Favoritenstr. 9/193-1 ViennaA-1040 Austria

Wide use and availability of machine learning and computer vision techniques allows development of relatively complex monitoring systems in many domains. Besides the traditional industrial domain, new applications appears also in biology and agriculture, where they may be used to detect infections, parasites and weeds, but also for automated monitoring and early warning systems. This goes in concordance with the introduction of the easily accessible hardware and development kits such as the Arduino, or RaspberryPi families. In this paper, we survey 50 papers focusing on the methods of automated beehive monitoring using computer vision techniques. Particularly on the pollen and Varroa mite detection together with the bee traffic monitoring. Such systems could also be used for monitoring of honeybee colonies and for the inspection of their health state, which could potentially identify dangerous states before the situation is critical, or to better plan periodic bee colony inspections and therefore save significant costs. Further on, we also include analysis of the research trends in this application field and we outline the possible directions of new development. Our paper is also aimed at veterinary and apidology professionals and experts, who may not be familiar with machine learning to introduce them to its capabilities, hence each family of techniques is prefaced by a brief theoretical introduction and motivation related to its base method. We hope that this paper will inspire other scientists to use machine learning techniques for other applications in beehive monitoring. © 2022, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A review of computer vision techniques for the analysis of vehicles

引用

AIP Conference Proceedings 2022年第1期2481卷

作者： Aastha Gour Durgaprasad Gangodkar Vikas Tripathi 1Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India 2Department of Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand India

Due to the increasing number of vehicles on the roads, a traffic analysis system is of peak importance. Various computer vision techniques and video analytics are used in the traffic analysis system to get useful information. This acquired information can be later used to make crucial judgements in real-time environment. This paper presents a comprehensive literature review in traffic analysis especially in the domains like moving vehicle detection, object identification and traffic volume estimation. The tabulated data presents the different algorithms along with their achieved performances. The paper also provides the limitations and the future scope of the discussed approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theoretical investigation of a nano scale all-optical 1 × 2 demultiplexer

引用

AIP Conference Proceedings 2023年第1期2651卷

作者： Saif Hasan Abdulnabi Mohammed Nadhim Abbas 1Department of Electronic and Communications Engineering Faculty of Engineering University of Kufa Iraq 3Department of Computer Technical Engineering College of Information Technology Imam Ja'afar Alsadiq University / Al-Najaf Al-Ashraf Iraq 2Department of Electrical Engineering College of Engineering University of Baghdad Iraq

In this paper, we have suggest, design, and simulate an all optical 1*2 demultiplexer (Demux) depended on Insulator-Metal-Insulator (IMI) plasmonic multilayer structure. The proposed structure offers an operating wavelength at 1550 nm and the design area is (350 nm* 350 nm). In this work, Finite Element Method (FEM) is used by using COMSOL Multiphasic software (version 5.4). The working principle of the proposed device (plasmonic Demux) depends on destructive and constructive interference, which occurs on input signal, selector signal, and control signal. The borderline between Logic 0 and Logic 1 at the output is 0.5 that is called transmission threshold. The performance of the proposed structure is measured by three parameters; Transmission, Extension Ratio, and Modulation Depth (MD). This devise shows, in some cases, the transmission value reaches more than 80%, Extension Ratio (3.5 dB), and very high MD value (97.6%). The proposed structure has a major role in building the arithmetic logic unit (ALU) and photonics integrated circuits (ICs).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of crime predictions using machine learning algorithms with geospatial features

引用

AIP Conference Proceedings 2022年第1期2393卷

作者： M. Raja Suguna R. Beaulah Jeyavathana K. V. Kanimozhi 1Department of Computer Science and Engineering Saveetha School of Engineering Chennai India 2Saveetha Institution of Medical and Technical Sciences Chennai India

Crime constitutes an action which is punishable by law. Crime Analysis involves the predictions of occurrence of future crime, the time and place of crime and to have insights into the trends of crime. Models are created by machine learning algorithms using the spatial, temporal and the demographic features extracted from the crime dataset. Reverse Geocoding technique is used to extract spatial features and also visualize the locations of the crime from the crime dataset using ArcGIS API of python along with WebMap and WebScene component provided by the API. Crime Analysis assists the Police, Investigation departments for the prediction of future crime and also take required actions which involves the deployment of crops in the predicted place at the time of the crime. The hotspots are identified; the hotspot is the area co-ordinates where more frequent crimes occur. After identifying hotspots, more focus is given on those crime prone areas for preventing and controlling the crime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Student’s academic performance prediction by using ensemble techniques

引用

AIP Conference Proceedings 2022年第1期2555卷

作者： Nidhi Mukesh Kumar Disha Handa Shweta Agarwal 1Department of Computer Science and Engineering Chandigarh University Punjab India 140413 2Department of Computer Science and Engineering Chitkara University Institute of Engineering and Technology Chitkara University Himachal Pradesh India 173212

Data Mining is a discipline of Machine Learning which is used to find or extract the information from the huge database of any organization by using some informative techniques. These informative techniques are then divided into different categories like clustering, classification, regression and association rule mining etc. Data Mining is widely used techniques in different fields like education, telecommunication, hospital, hospitality industry etc. As education plays a crucial role in the life of a human being therefore its proper monitoring is also very important. Thus, to predict the academic performance of any student on time and to help students improve their academic perform different researcher is working in the field and tried to develop a system which help to improve the prediction result. In this paper, different classification algorithms are used on academic dataset of the student in conjunction with different ensemble learning algorithm to improve the prediction result as compared to prediction result given by simple classification algorithm. At the end a comparison is also given which show the performance improvement by ensemble learning as compared to simple classification. The maximum improvement is shown by Multilayer perceptron algorithm and it is up to 15%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generic object detection using deep learning

引用

AIP Conference Proceedings 2022年第1期2444卷

作者： M. Malathi C. Paramasivam K. Nagalakshmi Gospeline Christiana S. Sangeetha 1Department of Computer Science and Engineering Sethu Institute of Technology Virudhu Nagar Tamilnadu India 2Department of Mechanical Engineering Thiagarajar College of Engineering Madurai Tamilnadu India

Object discovery is one of the very important and challenging problems in computer computing, seeks to obtain the properties of objects from a large number of categories previously described in natural images. In particular, image classification that aims to see the semantic categories of objects in a given image. Object discovery is not only identifies item categories but also predicts the location of each item with a mandatory box. Semantic separation process aims to predict intelligent pixel separation to assign a specific category label to each pixel, thus providing a richer and more comprehensive understanding of the image. In depth learning strategies have emerged as a powerful strategy for reading presentations directly from the data and have led to significant success in the field of general acquisition. Given this period of rapid evolution, the aim of this paper is to provide a comprehensive analysis of the latest achievements in this field brought about in-depth learning strategies. Here, the deep learning object detection algorithm is implemented for accuracy and time effectiveness to show the correct label for a character of interest in a movie which will be more useful in surveillance of building, ATM centres etc. Finally, it concludes with a promising indication for future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-management system for plug-in hybrid electric vehicle using optimized artificial neural networks

引用

AIP Conference Proceedings 2022年第1期2519卷

作者： Balachandra Pattanaik Mukil Alagirisamy 1Department of Electrical and Computer Engineering Wollega University Nekemte Ethiopia Africa 2Department of Electrical Engineering Faculty of Engineering Lincoln University College Wisma Lincoln Malaysia

Hybrid Plug-in Electric vehicles (HPEV) are new automobiles that can operate on gasoline and electricity stored in a battery pack. As a result, by utilizing the cheaper renewable and nonrenewable energy sources accessible at the household electric outlet, these cars may considerably cut their fuel usage. As a result, PHEVs have the potential to reduce overall greenhouse gas emissions from vehicles dramatically. A simplified power train of a power split PHEV is modeled in this study. The primary goal of the research is to improve the PHEV’s fuel economy. To accomplish this, the aforementioned simplified model has been used to implement the Optimized Neural Network approach. An optimization problem is developed with Equivalent Fuel Consumption Minimization (EFCM) as the primary objective function and various constraints. The particle swarm optimization (PSO) methodology is used to improve the efficiency of HPEV, estimates by optimizing the process parameters of the ANN. In comparison to existing approaches, the suggested method can produce optimistic outcomes based on the simulation studies.

关键词：

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：