检索结果-内蒙古大学图书馆

Optoelectronic device based failure management using content based multispectral image retrieval and deep learning model

引用

Optical and Quantum Electronics 2024年第2期56卷 239-239页

作者： Bhukya, Raghuram Arunsundar, B. Tatini, Narendra Babu Sadala, Triveni Mohan Elshafie, Hashim Qamar, Shamimul Deaprtment of Computer Science and Engineering Kakatiya Institute of Technologey and Science Telangana Warangal India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu Kattankulathur India Department of Internet of Things Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur India Department: CS & AI SR UNIVERSITY Telungana Warangal India Department of Computer Engineering College of Computer Science King Khalid University Main Campus Al Farah Abha 61421 Saudi Arabia Computer Science and Engineering College of Sciences and Arts King Khalid University Dhahran Al Janoub Campus Abha 64261 Saudi Arabia

The need for optoelectronic devices is growing right now, but the production of these devices is having a difficult time keeping up with the advancement of the machinery, instruments, and manufacturing techniques they support. Pictures from big, unlabeled image collections are commonly retrieved using a technique called content-based image retrieval (CBIR). The availability of photographs is also growing as internet growth and transmission networks increase. This study suggests brand-new image retrieval methods for multispectral images used in Optoelectronic device monitoring that are based on image segmentation and classification methods with deep learningtechniques for failure management. Optoelectronic device Monitoring field-based multispectral images were used as the input, which was then processed for noise removal, resizing, and *** c-means clustering-based image segmentation was used to divide up this processed image into its component parts. Following that, a hybrid multilayer transfer learning perception was used to classify the clustered segmented picture. The proposed technique has an accuracy of 95%, precision of 85%, recall of 75%, F-1 score of 63%, error rate of 51%, MAP of 55%;existing MRCN accuracy of 85%, precision of 75%, recall of 63%, F-1 score of 55%, error rate of 45%, MAP of 51%, OC-LBP accuracy of 89%, the precision of 79%, recall of 71%, F-1 score of 59%, error rate of 49%, MAP of 53%. © 2023, The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature.

关键词： Classification Deep learning Failure management Multispectral image retrieval Optoelectronic device Monitoring Segmentation

来源：评论

学校读者我要写书评

暂无评论

Forecasting Employees Churn Analysis using Selected Machine Learning Models

Forecasting Employees Churn Analysis using Selected Machine ...

引用

Automation, Computing and Renewable systems (ICACRS), International Conference on

作者： Sphurti Birajdar Irfan Abdul Karim Shaikh Sameer Yadav Abhishek Mishra L Chandra Sekhar Reddy Arivanantham Thangavelu Global Business School & Research Centre Dr. D.Y.Patil Vidyapeeth Pune Maharashtra India Faculty of Business Bahrain Polytechnic Bahrain Department of Commerce and Business Administration University of Allahabad Prayagraj Uttar Pradesh India Department of Management Studies Graphic Era Deemed to be University Dehradun Uttarakhand India HOD- CSE(Data Science) CMR College of Engineering & Technology kandlakoya (v) Hyderabad Telangana India Department of Computer Engineering Dr. D. Y. Patil College of Engineering and Innovation Varale Pune Maharashtra India

In the context of a business setting, the process of analysing and measuring the rate at which workers leave a company, as well as determining which people are most likely to depart, is referred to as employee churn analytics. This kind of analysis may also be used to anticipate which individuals are most likely to leave. Because of the continuously shifting requirements in many businesses, workers often find themselves in a position to pursue new employment opportunities. Because of this, companies are obligated to look for potential successors who already have the experience and education necessary to properly carry out the tasks that are involved with the role. In the event that a bottleneck occurs, the corporate sector will be required to make extra financial investments in order to return the organization’s workday to its previously established pattern of operation. During the course of investigation, the study analysis number of machine learning (ML) algorithms that concentrate on reviewing the history of an employee and evaluating a variety of characteristics in an efficient way. The purpose of these methods is to determine whether or not the employee will continue working for the firm or will at some point in the future depart the business.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Regression Network for Dental Implant Position Prediction

arXiv

引用

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Design of Leakage Current Monitoring system for Low Voltage Power Grid Based on NB-IoT 6th

Design of Leakage Current Monitoring System for Low Voltage ...

引用

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Xu, GuanWei Zheng, RongJin Chang, Kuo-Chi School of Information Science and Engineering Fujian University of Technology Fuzhou China Fujian Institute of Engineering Smart Grid Simulation Analysis and Integrated Control of Fujian University Engineering Research Center Fuzhou Fujian China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9783030697167

Leakage current of low-voltage power grid lines will cause major safety hazards such as personal electric shock and electrical fire. Traditional leakage current protectors can not play their due protection role due to their quality problems and aging, and other reasons. When leakage current accidents occur, traditional manual troubleshooting is inefficient. Aiming at the safety of leakage current in a low-voltage power grid, a new leakage current monitoring system is designed based on NB-IoT technology. The system includes the detection and transmission of leakage current and the construction of the cloud platform, which can realize the real-time monitoring of leakage current in low-voltage power grid and prevent and solve the leakage current safety problems. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Leakage currents

来源：评论

学校读者我要写书评

暂无评论

Solar PV Power Forecasting Approach Based on Hybrid Deep Neural Network 6th

Solar PV Power Forecasting Approach Based on Hybrid Deep Neu...

引用

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Chang, Kuo-Chi Omer, Abdalaziz Altayeb Ibrahim Chu, Kai-Chun Chang, Fu-Hsiang Wang, Hsiao-Chuan Lin, Yuh-Chung Nguyen, Trong-The Sung, Tien-Wen Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China School of Information Science and Engineering Fujian University of Technology Fuzhou China School of Management Fujian University of Technology Fuzhou China Department of Tourism Shih-Hsin University Taipei Taiwan Institute of Environmental Engineering National Taiwan University Taipei Taiwan College of Mechanical & Electrical Engineering National Taipei University of Technology Taipei Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9783030697167

There are incredibly renewable outlets such as solar and wind intermittent, and machine reliability is hard to sustain with the intolerable balance of green energy resources. Because of population growth and technological development, global energy demand is increasing exponentially. However, civilization must address a stable energy source for two benefits, a cost-effective and sustainable basis for future renewable energy production. Solar Energy is a platform for green energy and is a potential means of solving problems that face a possible energy system. The power output is primarily determined by the properties of the incoming radiation and solar panels. Precise and accurate knowledge of these variables provides a consistent model for predicting the solar future. Solar power forecasts would have a significant effect on the viability of massive solar energy projects. This study presents a new approach to predict the expected amount of energy to be produced from Photovoltaics using a hybrid deep neural network based on a combination of extended short-term memory networks (LSTM) and convolutional neural networks (CNN), taking into account the energy of electrons and photons as well as elements and climatic conditions as input data. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction

arXiv

引用

arXiv 2023年

作者： Yang, Xinquan Xie, Jinheng Li, Xuguang Li, Xuechen Li, Xin Shen, Linlin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China National University of Singapore Singapore

When deep neural network has been proposed to assist the dentist in designing the location of dental implant, most of them are targeting simple cases where only one missing tooth is available. As a result, literature works do not work well when there are multiple missing teeth and easily generate false predictions when the teeth are sparsely distributed. In this paper, we are trying to integrate a weak supervision text, the target region, to the implant position regression network, to address above issues. We propose a text condition embedded implant position regression network (TCEIP), to embed the text condition into the encoder-decoder framework for improvement of the regression performance. A cross-modal interaction that consists of cross-modal attention (CMA) and knowledge alignment module (KAM) is proposed to facilitate the interaction between features of images and texts. The CMA module performs a cross-attention between the image feature and the text condition, and the KAM mitigates the knowledge gap between the image feature and the image encoder of the CLIP. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TCEIP achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fraud Detection in Online E-Commerce Transactions through Deep Learning Auto encoder Model

Enhancing Fraud Detection in Online E-Commerce Transactions ...

引用

Intelligent systems and Advanced Applications (ICISAA), International Conference on

作者： K. Raghuveer Taviti Naidu Gongada Divya Nimma Mohd Aarif Keerthi Samudrala B Kiran Bala School of Management V.R. Siddhartha Engineering College (Deemed to be University) Kanuru A.P India Dept of Operations GITAM School of Business GITAM (Deemed to be) University Visakhapatnam India PhD in Computational Science University of Southern Mississippi Data Analyst in UMMC USA Department of Commerce Aligarh Muslim University Aligarh Uttar Pradesh India Department of CSE Marri laxman Reddy Institute Of Technology and Management India Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Fraud detection in internet transactions is crucial for maintaining security in digital transactions. Traditional methods often rely on rule-based systems or supervised learning algorithms, which struggle to capture complex patterns in fraudulent behaviour and require extensive manual feature engineering. In this study, a novel approach using deep learning auto encoder models is proposed to enhance fraud detection accuracy. Unlike conventional methods, this approach does not necessitate fraudulent data for training, as the auto encoder learns to reconstruct legitimate transactions and identify anomalies based on reconstruction error. The trained model is integrated into the market for real-time detection. Results demonstrate significant improvements in fraud detection accuracy compared to traditional methods, with reduced reliance on manual feature engineering and labelled fraudulent data. This approach offers a scalable and effective solution for detecting fraudulent activities in online e-commerce transactions, thereby safeguarding users and businesses from financial losses and maintaining trust in digital transactions. The autoencoder model expands detection accuracy by 2% over RF and 1% over SVM, with an AUCROC increase of 1%.

关键词： Deep learning Training Support vector machines Adaptation models Accuracy Manuals Real-time systems Fraud Electronic commerce business

来源：评论

学校读者我要写书评

暂无评论

Smart Warehouse Solutions for Efficient Onion Buffer Stock Management system

Smart Warehouse Solutions for Efficient Onion Buffer Stock M...

引用

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Ramakrishnan Raman L. Ramalingam Kamal Kishorbhai Sutaria Manika Kamthan S. Sangeetha S. Murugan Symbiosis International (Deemed University) Symbiosis Institute of Business Management Pune & Pune Maharashtra India Department of Artificial Intelligence and Data Science Chennai Institute of Technology (Autonomous) Chennai Tamil Nadu India Faculty of Engineering and Technology Parul Institute of Engineering and Technology Parul University Vadodara Gujarat India Symbiosis Law School Symbiosis International (Deemed University) Pune Maharashtra India Department of Computer Science and Engineering Karpagam College of Engineering Coimbatore Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

This research study presents an innovative smart warehouse system for onion buffer stock management. The system includes an RFID reader, a central controlling unit, a displaying unit, a temperature sensor, a moisture sensor, a relay, a cooling fan, storage nodes, and a cloud server. The RFID reader automatically tracks onion crates or pallets in the warehouse, enabling real-time visibility and traceability. The central controlling unit coordinates activities and collects data from sensors. Onions are stored at appropriate temperatures and moisture levels via sensors. Warehouse workers can monitor this data in real-time on the displaying unit once the central controlling unit processes it. Maintaining temperature and humidity need the relay and cooling fan. Based on sensor data, the main controlling unit activates the cooling fan to avoid onion spoiling. Storage nodes in the warehouse store onion bags and pallets. These nodes have RFID tags or sensors for convenient tracking of stock. data analysis, storage, and integration depend on the cloud server. It allows advanced data analytics, forecasting, and decision-making. It also helps suppliers, distributors, and retailers communicate and distribute products efficiently. Real-time visibility, smart monitoring, and proactive management of storage conditions advance efficient operations, prevent spoiling, and improve onion supply chain efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Short-Term Load Forecasting Accuracy in the Power systems Using a Hybrid CNN-GRU Model

Enhancing Short-Term Load Forecasting Accuracy in the Power ...

引用

International Conference on Electrical, Communication, and Computer engineering (ICECCE)

作者： Muhammad Ahsan Muhammad Osama Aziz Syed Ahmad Saleem Bokhari Muhammad Haris Mansoor Iqbal Kaleem Ullah Department of Computer Science University of Alabama at Birmingham Birmingham AL USA Buildings Energy Research Center University of Engineering and Technology Peshawar Pakistan Harvard Extension School Harvard University Cambridge MA USA Institute for Insight - J Mack Robinson College of Business Georgia State University Georgia USA Department of Computer Science University of Wah Wah Cantt Pakistan Department of Electrical Energy System CASE UET Peshawar Peshawar Pakistan

ISBN: (数字)9798331529437

ISBN: (纸本)9798331529444

In modern power systems, Short-Term Load Forecasting (STLF) is critical in ensuring the dynamic allocation of operational reserves and accurate prediction of electrical load demand. STLF is pertinent to grid operators to ensure system stability, allocate generation resources efficiently, and provide adequate reserves to deal with unexpected fluctuations. Considering the pivotal role of STLF, this paper introduces a hybrid deep learning model for short-term load forecasting, combining Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). The model features two parallel 32-filter convolutional layers (3×3 kernel, ReLU) for spatial feature extraction, followed by two series-connected GRU layers (42 units) to capture temporal dependencies. A final dense layer with ReLU activation generates the load forecast. This architecture effectively leverages CNNs for local pattern recognition and GRUs for modeling temporal sequences, offering a robust solution for accurate short-term load forecasting. Therefore, the efficacy of the CNN-GRU model is tested and validated using an extensive dataset sourced from the National Transmission & Dispatch Company (NTDC), Pakistan. The performance analysis reveals that hybrid CNN-GRU models achieve a substantial reduction in Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE), with values of 400.33, 2.89, 580.95, for single-step forecasts, respectively, and 1031.11, 5.31, and 733.19, for 24-hour forecasts. Furthermore, the simulation results demonstrate notable enhancements in load forecasting accuracy and robustness across various forecast horizons.

关键词： Accuracy Load forecasting Predictive models Power system stability Feature extraction Stability analysis Convolutional neural networks Kernel Forecasting Load modeling

来源：评论

学校读者我要写书评

暂无评论

Research Artifacts in Software engineering Publications: Status and Trends

arXiv

引用

arXiv 2024年

作者： Liu, Mugeng Huang, Xiaolong He, Wei Xie, Yibing Zhang, Jie M. Jing, Xiang Chen, Zhenpeng Ma, Yun Ministry of Education School of Computer Science Peking University Beijing China School of Software and Microelectronics Peking University Beijing China Department of Informatics King’s College London London United Kingdom National Key Laboratory of Data Space Technology and System Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute for Artificial Intelligence Peking University Beijing China

The Software engineering (SE) community has been embracing the open science policy and encouraging researchers to disclose artifacts in their publications. However, the status and trends of artifact practice and quality remain unclear, lacking insights on further improvement. In this paper, we present an empirical study to characterize the research artifacts in SE publications. Specifically, we manually collect 1,487 artifacts from all 2,196 papers published in top-tier SE conferences (ASE, FSE, ICSE, and ISSTA) from 2017 to 2022. We investigate the common practices (e.g., URL location and format, storage websites), maintenance activities (e.g., last update time and URL validity), popularity (e.g., the number of stars on GitHub and characteristics), and quality (e.g., documentation and code smell) of these artifacts. Based on our analysis, we reveal a rise in publications providing artifacts. The usage of Zenodo for sharing artifacts has significantly increased. However, artifacts stored in GitHub tend to receive few stars, indicating a limited influence on real-world SE applications. We summarize the results and provide suggestions to different stakeholders in conjunction with current guidelines. © 2024, CC BY.

关键词： Software engineering

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：