检索结果-内蒙古大学图书馆

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： V.M. Vinayagam A. Sathish K. Sreenivasulu D. Sreenu R. Snehit Y. Abhilash Reddy Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Chittoor Andhra Pradesh Department of Computer Science and Engineering(AI&ML) Siddharth Institute of Engineering & Technology Chittoor Andhra Pradesh

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

Although it has become a need in our daily lives, browsing the internet can be risky. New features and capabilities are always being added by browser vendors, which can increase the usability of websites but also increase their vulnerability to attacks. Because they aim to steal confidential data from gullible users, phishing websites pose a severe threat to internet security. In order to counter this issue, academics have created a number of methods, such as machine learning algorithms, for identifying phishing websites. By using extensive datasets of authentic and fraudulent websites, machine learning algorithms can be trained to identify patterns and traits that differentiate between the two. Then, before people become victims, these algorithms can be used to recognize and prevent phishing websites. Feature extraction is one method for detecting phishing websites using machine learning. In this method, different aspects of a website, like its content, age, and URL structure, are examined to detect phishing websites. Another approach involves using deep learning algorithms to automatically extract features and learn complex patterns in website data. Overall, machine learning-based phishing website detection techniques have shown promising results, achieving high accuracy rates and outperforming traditional rule-based methods. These strategies could become valuable weapons in the fight against online phishing attempts with more study and refinement.

关键词： Uniform resource locators Machine learning algorithms Accuracy Phishing Weapons User interfaces Feature extraction Fraud Telecommunication computing Usability

来源：评论

学校读者我要写书评

暂无评论

An Analyzation Of Data Privacy In Sharing And Storing Data In Cloud Environment

An Analyzation Of Data Privacy In Sharing And Storing Data I...

引用

International Conference on Electrical Energy Systems (ICEES)

作者： R.S. Subhasreevignani N. Babu D. Raji K.N. Sowmya S. Afreen Zaiba G. Reddy Abhishek Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Andhra Pradesh India Department of Computer Science and Engineering (AI&ML) Siddharth Institute of Engineering & Technology Andhra Pradesh India

ISBN: (数字)9798350353778

ISBN: (纸本)9798350353785

The Wide spread use of cloud storage services and their demonstrated power provide the foundational underpinning for the cloud computing industry rapid development. Nevertheless, a lot of security incidents still occur at the cloud storage layer due to deliberate attacks and management negligence, resulting in significant leaks of critical data. To address the issue, we inculate AES and Cryptographic Pseudo Random Number Generator Algorithms. The proposed standard illustrates the process of dividing the data into segments which is encrypted with aes individually to ensure the strong security for data. By distributing the scattered data segments among several cloud sites, security is improved and the possibility of a single point of failure is decreased. Securing access control mechanisms makes it easy for authorized individuals to access and decode data.

关键词： Industries Access control Cloud computing Data privacy Generators Cryptography Standards

来源：评论

学校读者我要写书评

暂无评论

Harnessing Machine Learning for Enhanced Distributed Computing in Wireless Network Systems

Harnessing Machine Learning for Enhanced Distributed Computi...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Rashmi, K. Anandhi, R.J. Singh, Navdeep Kumar, V. Surya Pavan Gupta, Krashnkant Albawi, Ali Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Information Science Engineering Bangalore India Lovely Professional University Phagwara India Mlr Institute Of Technology Department Of CSE-AI&ML Telangana Hyderabad India Amity University Greater Noida Department Of Electronics & Communication Engineering India College Of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350366846

A complete wireless network system for flexible resource sharing, spectrum management, security, and cross-layer optimization is described in this paper. Five algorithms comprise the system. These are ADS, QoS-ml, CLO, and DSM. Wireless networks adapt and grow, and these applications solve issues. Real-time resource allocation using predictive models enhances network performance, latency, and efficiency with the PRA algorithm. DSM uses adaptive spectrum utilization to reduce interference. ADS uses machine learning to detect unusual activity and implement flexible safety measures to make networks safer. QoS-ml improves routing options using real-time QoS data to ensure network-wide QoS. CLO alters layer connections, utilizes metrics across layers, and is continually searching for network improvements. A detailed analysis of the research examined each program's distinct qualities and how they function together. The discussion focused on how well the framework performed in various settings and was adaptable. In the conclusion, the algorithms' strengths and potential in distributed computing environments were highlighted. The recommended technique outperformed others in speed, latency, security, energy efficiency, scalability, and customer satisfaction. Performance trends, parameter distributions, and trade-offs were shown, making the structure more dependable. By offering a full, adaptive, and successful method, this study advances wireless network management. Optimizations, scalability, and real-world applications might be studied to ensure the system works in various conditions. In challenging and changing situations, the proposed architecture supports wireless network expansion. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Advancing Drowsiness Detection Using Head-Angle and Eye-Aspect Ratio

A Novel Approach to Advancing Drowsiness Detection Using Hea...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： V Shashidhar Mueezuddin Ahmed Razeena M Rajesh K S Bharath J Rajarajeswari College of Engineering Bangalore Department of Computer Science & Engineering Rajarajeswari College of Engineering Bangalore Department of AI&ML Rajarajeswari College of Engineering Bangalore

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

Drowsiness is a significant risk factor for accidents, particularly in situations requiring sustained attention, such as driving or operating machinery. This research proposes an innovative methodology for detecting driver drowsiness using advanced computer vision algorithms and techniques. Our system employs a shapeshift predictor and face-tracking algorithms to monitor the driver's facial features and head movements. Specifically, it detects three distinct indicators of drowsiness: excessive head tilting to the right or left, significant drooping of the chin, and prolonged eye closure (defined as eyes remaining closed for more than 24 consecutive frames). When any of these conditions are met, an alarm is triggered, alerting the driver to their potentially hazardous state. The proposed system offers a robust and non-intrusive solution for real-time drowsiness monitoring, with potential applications in various fields where vigilance is critical for safety.

关键词： computer vision Tracking Surveillance Prediction algorithms Magnetic heads Real-time systems Sensors Facial features Vehicles Accidents

来源：评论

学校读者我要写书评

暂无评论

Diabetes Prediction in Teenagers using Machine Learning Algorithms

Diabetes Prediction in Teenagers using Machine Learning Algo...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Jayavrinda Vrindavanam Raye Haarika Sindhu MG Kilari Sumanth Kumar Department of Computer Science & Engineering (AI & ML) School of Engineering Dayananda Sagar University Bengaluru India

Diabetes Mellitus (DM) is a hazardous condition that can lead to worldwide health problems owing to an increase in blood glucose levels, age, lack of movement, high blood pressure, poor nutrition, and other factors. The aim of this study is to develop a system that can predict diabetes in individuals aged 10 to 30 by merging the results of different machine-learning algorithms. Machine learning is used for increasing performance and forecasting accuracy. Some of the methods used to detect diabetes early include Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), K Nearest Neighbours (KNN), and XGBoost. In comparison to the other methods, the random forest and XGBoost Classifiers algorithm outperformed all other ml algorithms, with a maximum accuracy of 86

关键词： Support vector machines Radio frequency Machine learning algorithms Computational modeling Forestry Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

INDICVOICES-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS 38

INDICVOICES-R: Unlocking a Massive Multilingual Multi-speake...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Sankar, Ashwin Anand, Srija Varadhan, Praveen Srinivasa Thomas, Sherry Singal, Mehak Kumar, Shridhar Mehendale, Deovrat Krishana, Aditi Raju, Giri Khapra, Mitesh AI4Bharat Department of Computer Science & Engineering Indian Institute of Technology Madras Tamil Nadu Chennai600036 India

Recent advancements in text-to-speech (TTS) synthesis show that large-scale models trained with extensive web data produce highly natural-sounding output. However, such data is scarce for Indian languages due to the lack of high-quality, manually subtitled data on platforms like LibriVox or YouTube. To address this gap, we enhance existing large-scale ASR datasets containing natural conversations collected in low-quality environments to generate high-quality TTS training data. Our pipeline leverages the cross-lingual generalization of denoising and speech enhancement models trained on English and applied to Indian languages. This results in IndicVoices-R (IV-R), the largest multilingual Indian TTS dataset derived from an ASR dataset, with 1,704 hours of high-quality speech from 10,496 speakers across 22 Indian languages. IV-R matches the quality of gold-standard TTS datasets like LJSpeech, LibriTTS, and IndicTTS. We also introduce the IV-R Benchmark, the first to assess zero-shot, few-shot, and many-shot speaker generalization capabilities of TTS models on Indian voices, ensuring diversity in age, gender, and style. We demonstrate that fine-tuning an English pre-trained model on a combined dataset of high-quality IndicTTS and our IV-R dataset results in better zero-shot speaker generalization compared to fine-tuning on the IndicTTS dataset alone. Further, our evaluation reveals limited zero-shot generalization for Indian voices in TTS models trained on prior datasets, which we improve by fine-tuning the model on our data containing diverse set of speakers across language families. We open-source code and data3 for all 22 official Indian languages. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Predictive Maintenance RAG framework for Power Plants: Enhancing QA with StyleDFS and Domain Specific Instruction Tuning

Intelligent Predictive Maintenance RAG framework for Power P...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Hong, Seongtae Shin, Joongmin Seo, Jaehyung Lee, Taemin Park, Jeongbae Cho, Manyoung Choi, Byeongho Lim, Heuiseok Department of Computer Science and Engineering Korea University Korea Republic of Human-inspired AI Research Korea Republic of GaonPlatform Korea Republic of

ISBN: (纸本)9798891761667

Process plants are complex large-scale industrial facilities that convert raw materials or intermediate products into final products, requiring continuous processes with high safety and efficiency standards. In particular, in nuclear process plants, Predictive Maintenance System (PMS) plays a critical role in predicting equipment anomalies and performing preventive maintenance. However, current PMS relies heavily on the experience of a few experts, leading to knowledge loss upon their retirement and difficulty in swift response. Existing off-premise Question-Answering (QA) systems based on Large Language Models (LLM) face issues such as data leakage and challenges in domain-specific tuning. To address these problems, this study proposes an on-premise intelligent PMS framework utilizing a new chunking method, StyleDFS, which effectively reflects the structural information of documents. Additionally, we demonstrate that Instruction tuning using relevant domain-specific data improves LLM performance even under limited data conditions. © 2024 Association for Computational Linguistics.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Enhancing Legal Decision Making: WRIT Case Outcome Prediction with LegalBERT Embeddings and AdaBoost Classifier 2

Enhancing Legal Decision Making: WRIT Case Outcome Predictio...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： George, Angelina Jose, Alphonsa Ashik, F. Prabhakar, Priyanka Pati, Peeta Basa Parida, Shantipriya Amrita School of Computing Amrita Vishwa Vidyapeetham India Department of Computer Science & Engineering Bengaluru India Silo AI Helsinki Finland

ISBN: (纸本)9798350383652

Legal decision-making, the process of determining the outcome of court cases, is a pivotal aspect of the justice system. It involves evaluating evidence, interpreting laws, and ensuring justice is served. However, this process is challenging due to the complexity of legal cases, varying interpretations of laws, and the potential for lengthy court proceedings. In addition to these reasons, India also has one of the world's lowest ratios of judges to population. For swift and efficient disposal of justice, it is important to fast-track this process as much as possible. A traditional solution to this problem would take a considerable amount of time to show any meaningful results considering the current backlog of cases and the rate at which new cases are being filed each day. In order to overcome these difficulties, we employ text embeddings from LLM's with statistical classifiers to effectively and precisely forecast the outcomes for writ petitions. Our approach delivers an accuracy of 54% and a F1-score of 0.42 with LegalBERT embedder and AdaBoost classifier. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Pretraining for Improving Diagnostic and Therapeutic Entity Recognition in Electronic Medical Records

Deep Neural Pretraining for Improving Diagnostic and Therape...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Enquero, Shreya Patchala Sunil, G. Kumar, Suvarna Sunil Lavanya, Chunduri Siddhanti, Prateeksha Global-A Genpact Company Bangalore India School of Computer Science & Artificial Intelligence Sr University Warangal India Malla Reddy Engineering College for Women It Department Dhulapally Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Nitte Meenakshi Institute of Technology Department of Ai and Ml Yelahanka Bengaluru India

ISBN: (纸本)9798350313413

The predominance of compound agency, a lack of utterance components, and unclear entity boundaries all contribute to difficulties in distinguishing diagnostic and treatment entities in EMRs. Furthermore, obtaining electronic medical records in China may be difficult. A deep learning strategy that uses deep neural pretraining to improve diagnostic and therapeutic entity recognition in EMRs is proposed. A BERT-CRF model example is shown using a dataset of 10,000 EMRs. This paradigm combines the benefits of pretraining with the adaptability of CRF. The outcomes of the study show that deep brain pretraining might be used to improve the performance of NLP applications in the healthcare business. The use of a domain-specific corpus learning technique and an entity recognition model trained on a training dataset improves word embeddings. The suggested system achieved an accuracy (0.973), precision (0.909), recall (0.896), f1-score (0.902) and MCC (0.893) respectively. © 2023 IEEE.

关键词： BERT-CRF Model BiLSTM Model Cardiovascular Records Deep Learning Investigation Electronic Medical Records (EMRs) Entity Recognition Model Transformer-Conditional Random Fields

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Specification Testing on Heart Disease Detection Using Feed-Forward Neural Network

引用

SN computer science 2023年第6期4卷 850页

作者： Naresh, E. Darshan, S. L. Shiva Srinidhi, N.N. Niranjanmurthy, M. Dayananda, P. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of AI&ML BMSITM Avalahalli Bengaluru India

The proposed work highlights the importance of testing in machine-learning applications and the ensuing need to increase model quality to decrease the likelihood of errors. The proposed work considers patient health information that may be utilized for decision-making or prediction utilizing various computations, and in this instance, it emphasizes the development of artificial neural networks with the multilayer perceptron method to forecast cardiac abnormalities. The dataset employed in this work includes information about the patient’s demographics, clinical measures, and medical background. Utilizing this labelled dataset, one may estimate if each patient has heart disease or not. We developed a GUI to collect data about a new patient to accomplish the task specified. After the model is generated, effective functionality testing was performed on the model. As a result of the testing report’s assistance in identifying faults and defects, the artificial neural network’s accuracy ultimately improved as a result of its improved accuracy following correction. After undergoing feature testing, the application’s accuracy ascended to 96.69%, which is a higher percentage than was attained using any alternative method. © 2023, The Author(s).

关键词： ANN Functional testing Heart disease Machine learning Multilayer perceptron technique

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：