检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Industrial Electronics: Developments and Applications, ICIDeA 2023

作者： Srinivasan, V. Parthasarathy, M. Kumar, M. Pavin Vaishnavi, S. Sri Ramakrishna Engineering College Department of Mechanical Engineering Coimbatore India Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350381979

Ladle monitoring systems are essential for optimizing steel melting operations. They improve material and equipment flow, reduce wait times, increase overall production, enable quick problem response, and ensure steel quality. Traditional ladle tracking methods utilizing sensors require a wide frequency band for data transmission. However, sensor technology has limitations such as high cost, limited range, signal interference, poor integration, wear, and tear. Thus, an additional layer of security is needed. To address these issues, a proposed solution suggests implementing a machine vision system for ladle tracking and management in steel factories. This vision-based system uses a live video captured by a camera as input to detect the ladle. The template matching algorithm is employed to compare the ladle template with the image's covered window, allowing the system to identify the ladle's ID and the zone where it is located. Various techniques for template matching are compared, and the most suitable one for the application is selected based on the results. The matched templates are stored in a database using Python SQLite3. The ladle tracking positions can be accessed through a web application, which also provides the capability to track individual ladles. The results demonstrate that implementing a vision-based tracking system for ladles in steel factories offers optimal outcomes with minimal hardware expenses. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Polyp image segmentation based on improved planet optimization algorithm using reptile search algorithm

引用

Neural computing and Applications 2025年第8期37卷 6327-6349页

作者： Abd Elaziz, Mohamed Al-qaness, Mohammed A. A. Al-Betar, Mohammed Azmi Ewees, Ahmed A. Department of Mathematics Faculty of Science Zagazig University Zagazig Egypt College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China Faculty of Computer Science and Engineering Galala University Suze435611 Egypt Ajman University Ajman346 United Arab Emirates College of Computing and Information Technology University of Bisha Bisha Saudi Arabia Department of Computer Damietta University Damietta Egypt Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan

To recognize the potential for colon polyps to develop into cancer over time, early diagnosis is crucial for preventative healthcare. Timely identification significantly improves the prognosis and treatment outcomes for colorectal cancer patients. Image segmentation is crucial in medical image analysis for accurate diagnosis and treatment planning. Therefore, in this study, we present an alternative multilevel thresholding polyp segmentation method (MPOA) to enhance the segmentation of polyp images. The proposed method is based on enhancing the planet optimization algorithm (POA) by integrating operators from the reptile search algorithm (RSA). The evaluation of the developed MPOA is tested with different polyp images and compared with other image segmentation approaches. The results highlight the superior capability of MPOA, as evidenced by various performance measures in effectively segmenting polyp images. Furthermore, metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and fitness values demonstrate that MPOA outperforms the basic version of POA and other methods. The evaluation outcomes underscore the significant impact of RSA in enhancing the performance of POA for the segmentation of polyp images. © The Author(s) 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

End To End Comments Filtering Feature Using Sentimental Analysis 3

End To End Comments Filtering Feature Using Sentimental Anal...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation computing, ICSTSN 2024

作者： Sindhu, A. Jayakumar, D. Sasivardhini, S. Ramkumar, M.O. Rajmohan, R. IFET College of Engineering Computer Science and Engineering Tamil Nadu Villupuram India SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Villupuram India

ISBN: (纸本)9798350391565

In the age of digital communication, social media platforms have become essential tools for interaction and information sharing worldwide. However, these platforms often face the challenge of managing negative and harsh comments, which threaten to disrupt a healthy online environment. This paper presents an innovative end-to-end comments filtering feature that uses sentiment analysis to detect and mitigate such undesirable comments. The proposed system employs advanced Multilingual Sentiment Analysis techniques using Long Short-Term Memory (LSTM) networks and the Naive Bayes Classifier to analyze comments in Tamil, Tanglish (a blend of Tamil and English), and *** negative comments are identified, the system filters and deletes them, sends warning emails to offending users, and blocks repeat offenders. This approach not only curtails harmful content but also discourages users from posting negative comments in the future. Experimental results demonstrate the system's effectiveness in significantly reducing negative comments and maintaining a positive online community. The combination of LSTM networks and Naive Bayes Classifier provides a robust framework for sentiment analysis and automated moderation, paving the way for healthier social media environments. © 2024 IEEE.

关键词： Electronic mail filters

来源：评论

学校读者我要写书评

暂无评论

IDRISI-D: Arabic and English Datasets and Benchmarks for Location Mention Disambiguation over Disaster Microblogs 1

IDRISI-D: Arabic and English Datasets and Benchmarks for Loc...

引用

1st Arabic Natural Language Processing Conference, ArabicNLP 2023

作者： Suwaileh, Reem Elsayed, Tamer Imran, Muhammad Computer Science and Engineering Department Qatar University Qatar Qatar Computing Research Institute Hamad Bin Khalifa University Doha Qatar

ISBN: (纸本)9781959429272

Extracting and disambiguating geolocation information from social media data enables effective disaster management, as it helps response authorities;for example, locating incidents for planning rescue activities and affected people for evacuation. Nevertheless, the dearth of resources and tools hinders the development and evaluation of Location Mention Disambiguation (LMD) models in the disaster management domain. Consequently, the LMD task is greatly understudied, especially for the low resource languages such as Arabic. To fill this gap, we introduce IDRISI-D, the largest to date English and the first Arabic public LMD datasets. Additionally, we introduce a modified hierarchical evaluation framework that offers a lenient and nuanced evaluation of LMD systems. We further benchmark IDRISI-D datasets using representative baselines and show the competitiveness of BERT-based models. © 2023 Association for Computational Linguistics.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud computing Security through Deep Learning and Attention Mechanism Intrusion Detection Systems 4

Enhancing Cloud Computing Security through Deep Learning and...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Shukla, Sunil Singh, Jagendra Ramya, T. Rahul, Satyakam Mallick, Arnab Kumar Pandey, Pawan Graphic Era Hill University School of Computing Dehradun India Bennett University School of Computer Science Engineering & Technology Greater Noida India Cvr College of Engineering Department of CSE-DS Hyderabad India Mit Adt University School of Computer Science Engineering Pune India Indian Institute of Technology Madras Department of Computer Science Engineering Chennai India Raj Kumar Goel Institute of Technology Department of Computer Science Ghaziabad India

ISBN: (纸本)9798350349900

This research investigates the enhancement of cloud computing security through adaptive neural network intrusion detection systems, employing Deep Belief Networks (DBN) and Attention Mechanism. The study aims to address the growing concerns surrounding security threats in cloud environments by leveraging advanced machine learning techniques. Experimental evaluations were conducted to assess the performance of the proposed approach, with specific emphasis on detection accuracy, false positive rate, and computational efficiency. Results indicate that the DBN-based intrusion detection system achieved an average detection accuracy of 94.4%, with a false positive rate of 2.2% and a computational efficiency of 1 5 8. 4 milliseconds. In comparison, the IDS utilizing Attention Mechanism demonstrated superior performance, with an average detection accuracy of 96.2%, a false positive rate of 1.1%, and a computational efficiency of 153.2 milliseconds. These findings underscore the effectiveness of DBN and Attention Mechanism in bolstering the security posture of cloud computing environments. By integrating adaptive neural network-based intrusion detection systems, organizations can enhance threat detection capabilities, mitigate risks, and safeguard sensitive data and critical assets in the cloud. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Poster: FlexibleBP: Blood Pressure Monitoring Using Wrist-worn Flexible Sensor 24

Poster: FlexibleBP: Blood Pressure Monitoring Using Wrist-wo...

引用

22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024

作者： Zhang, Yujing Li, Bing Peng, Yanxi Li, Jiao Sun, Tao Zhang, Jin Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798400706974

We propose FlexibleBP, a novel cuffless blood pressure monitoring system using a wrist-worn flexible sensor to enhance comfort and accuracy. By capturing pulse wave signals from the radial artery, we develop a personalized estimation framework incorporating a Transformer model with fine-tuning. Experiments with 36 participants confirm FlexibleBP's accuracy, meeting AAMI standards. This work marks a step toward more user-friendly, advanced wearable BP monitoring solutions. © 2024 Copyright held by the owner/author(s).

关键词： Pressure regulators

来源：评论

学校读者我要写书评

暂无评论

Sign to Speak: Real-time Recognition for Enhance Communication 3

Sign to Speak: Real-time Recognition for Enhance Communicati...

引用

3rd International Conference on applied Artificial Intelligence and computing, ICAAIC 2024

作者： Baghavathi Priya, S. Rao, P V R Subba Madeswaran, TamilSelvi Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India University of Technology and Applied Sciences Department of Information Technology Nizwa Oman

ISBN: (纸本)9798350375190

Recent developments in the area of research on sign language recognition have led to making use of deep learning techniques with the goal to assist the self-learning transition of sign language from one language to another. In order to detect and classify characters from photographs in multiple sign languages, a number of deep-learning models, have been deployed. SLR is a prominent area of study and technology that aims to mitigate speaking barriers for individuals who unable to talk and listen. This involves the development of tools capable of understanding and deciphering sign language movements, hence facilitating a wider range of interactions for those who are difficult of listening and speaking. This paper demonstrates a novel model called CNN Inception Net, which is a neural network based on convolution. The use of an Indian sign dataset enables the achievement of a notable performance rate of 98.9%, enabling precise recognition of actions in the language of signs. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Technique-based Optimal Energy Management in Smart Home Appliances

引用

IEIE Transactions on Smart Processing and computing 2024年第5期13卷 425-434页

作者： Shirley, C.P. Depaa, R.A.B. Priya, A. Sarala, R. Solanki, Rajdeep Singh Malini, K.V. Venkatakrishna Reddy, Ch. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Civil Engineering Dr. M.G.R Educational and Research Institute Maduravoyal Chennai95 India School of Architecture Koneru Lakshmaiah Educational Foundation Andhra Pradesh Guntur India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai Rameshwaram High Road Viraganoor Madurai625009 India Department of Computer Science Medi-Caps University Indore India Department of Electrical and Electronics Engineering Sri Sairam College of Engineering Anekal India Department of Electrical and Electronics Engineering Chaitanya Bharathi Institute of Technology Hyderabad75 India

This manuscript presents a hybrid method for optimal energy management in smart home appliances. The proposed approach combines the Ebola Optimization Search Algorithm (EOSA) with the performance of spiking neural networks (SNN). The key objective of the proposed strategy is cost reduction through day-ahead load scheduling while also considering the best demand response (DR), and self-consumption of photovoltaic (PV). The EOSA method manages air conditioning (AC) and ensures thermal comfort. In addition, the SNN method was used to predict the optimal system control signal. Comparative analysis with existing systems, such as PSO, RFA, and BCO, showed that the proposed strategy resulted in 13% cost savings. The proposed system considered parameters, such as solar radiation, occupant presence, and electricity prices. The proposed technique is implemented in the MATLAB software, and the performance is compared with existing approaches. The efficiency of the proposed approach is higher than the existing techniques. © 2024 The institute of Electronics and Information Engineers.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Improving Oil Spill Detection in Marine Environments Through Deep Learning Approaches 4

Improving Oil Spill Detection in Marine Environments Through...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Shanmukh, M. Phani Priya, S. Baghavathi Madeswaran, Tamilselvi Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India University of Technology and Applied Sciences Department of Information Technology Nizwa Oman

ISBN: (纸本)9798350343670

Oil spills represent a major environmental threat, particularly in marine ecosystems. Timely detection and segmentation of oil spills from satellite imagery is crucial for directing rapid response and remediation *** research concludes with an insights by developing a deep learning approach for automated detection and segmentation of oil spills from synthetic aperture radar (SAR) *** research implements and compares three algorithms PSPNET,DeepLapV3 and fully convolutional networks (FCN) with U-Net for semantic segmentation of SAR *** the networks are trained on a dataset of SAR images with pixel-wise labels indicating oil spill regions. This research also evaluates the segmentation performance using common metrics like intersection-over-union (IoU) and pixel-wise accuracy. Our results indicate that both FCN and U-Net can effectively detect and delineate oil spill regions, with U-Net demonstrating slightly higher IoU scores and with and accuracy of 95%. The deep learning models generalize well to unseen SAR images. Overall, this work demonstrates the feasibility of deep convolutional neural networks for automated analysis of SAR imagery to enable rapid oil spill response at marine environment. © 2024 IEEE.

关键词： Deep Learning Algorithms Oil Spill Detection Rapid Oil Spill Response Semantic Segmentation Synthetic Aperture Radar (SAR) Imagery

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning of Bigdata Set Using Randomized Measurements 7

Quantum Machine Learning of Bigdata Set Using Randomized Mea...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Minu, R.I. Nagarajan, G. Jabez, J. Yamini, G. SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Veltech Institute of Science and Technology Department of English Tamil Nadu India

ISBN: (纸本)9798350372816

Utilizing discriminative deep belief networks (DDBNs) within the framework of semi-supervised learning, this technique leverages a combination of a limited set of labeled samples to enhance intrusion prevention efficacy while reducing recognition errors. By integrating both non-local and local regularization techniques, the method effectively tackles the inherent challenge of high error rates in cyber prevention models. Additionally, this approach is designed for implementation on Quantum computing platforms, harnessing advanced machine learning algorithms to significantly improve cybersecurity measures. © 2024 IEEE.

关键词： Cybersecurity

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：