检索结果-内蒙古大学图书馆

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Joshi, Rahul Pandey, Krishna Kumari, Suman Gupta, Shashi Kant Mohanty, Mitali Salau, Ayodeji Olalekan Manav Rachna International Institute of Research & Studies Smeh Department of Journalism & Mass Communication Haryana India Eudoxia Research University Computer Science and Engineering New CastleDE United States Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Independent Researcher Haryana India

ISBN: (纸本)9798350364699

In this research, machine learning (ML) modernization technology is developed for Data Mining (DM) in smart healthcare. Internet-of-things (IoT) and ML are used in contemporary technologies to support DM approaches for predicting and interpreting data from different sources. The collection of data and its application domain have an impact on these techniques' effectiveness. The objective of this research is to examine the ML approach functions in smart healthcare and to analyze the DM technique for predicting breast cancer for smart healthcare. Initially, the datasets for breast cancer were gathered from public sources. The preprocessing of raw data samples is carried out using the min-max normalization technique. Then, follow the feature extraction stage with independent component analysis (ICA). A novel augmented beetle swarm-intelligent-driven quadratic support vector machine (ABS-QSVM) strategy is proposed to examine breast cancer. The Python platform is applied to implement the proposed method, and various metrics are analyzed. The experimental outcomes demonstrated that the ABS-QSVM approach achieved greater accuracy in healthcare examinations than other existing approaches. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Various COVID-19 Prediction Techniques

引用

IEIE Transactions on Smart Processing and Computing 2021年第4期10卷 323-329页

作者： Arora, Rakesh Kumar Gupta, Manoj Kumar Bhati, Bhoopesh Singh Department of Computer Science and Engineering Krishna Engineering College UP India Department of Computer Science and Engineering Trinity Institute of Innovations in Professional Studies UP India Department of Computer Science and Engineering Ambedkar Institute of Advanced Communication Technologies and Research Delhi India

There is no precise treatment available for COVID-19, but treatment of a number of signs/symptoms is possible. This treatment is provided in accordance with the clinical position of the patient. Furthermore, supplementary care is proven as efficient for infected people. COVID-19 prediction techniques follow various steps, which include dataset collection, pre-processing, feature extraction, and classification. Numerous COVID-19 prediction techniques have been proposed in the literature. In this paper, various techniques are systematically reviewed on the basis outcomes, advantages, and disadvantages. Copyrights © 2021 The institute of Electronics and Information Engineers

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Optimized Phishing Detection with Recurrent Neural Network and Whale Optimizer Algorithm

引用

computers, Materials & Continua 2024年第9期80卷 4895-4916页

作者： Brij Bhooshan Gupta Akshat Gaurav Razaz Waheeb Attar Varsha Arya Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPuneMaharashtra411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Ronin Institute MontclairNJ 07043USA Management Department College of Business AdministrationPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)HomantinHong KongChina

Phishing attacks present a persistent and evolving threat in the cybersecurity land-scape,necessitating the development of more sophisticated detection *** machine learning approaches to phishing detection have relied heavily on feature engineering and have often fallen short in adapting to the dynamically changing patterns of phishingUniformResource Locator(URLs).Addressing these challenge,we introduce a framework that integrates the sequential data processing strengths of a Recurrent Neural Network(RNN)with the hyperparameter optimization prowess of theWhale Optimization Algorithm(WOA).Ourmodel capitalizes on an extensive Kaggle dataset,featuring over 11,000 URLs,each delineated by 30 *** WOA’s hyperparameter optimization enhances the RNN’s performance,evidenced by a meticulous validation *** results,encapsulated in precision,recall,and F1-score metrics,surpass baseline models,achieving an overall accuracy of 92%.This study not only demonstrates the RNN’s proficiency in learning complex patterns but also underscores the WOA’s effectiveness in refining machine learning models for the critical task of phishing detection.

关键词： Phishing detection Recurrent Neural Network(RNN) Whale Optimization Algorithm(WOA) cybersecurity machine learning optimization

来源：评论

学校读者我要写书评

暂无评论

FDD Massive MIMO: How to Optimally Combine UL Pilot and Limited DL CSI Feedback?

FDD Massive MIMO: How to Optimally Combine UL Pilot and Limi...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Kim, Jungyeon Choi, Jinseok Park, Jeonghun Alkhateeb, Ahmed Lee, Namyoon Pohang University of Science and Technology Department of Electrical Engineering Pohang Korea Republic of Korea Advanced Institute of Science and Technology School of Electrical Engineering Daejeon Korea Republic of Yonsei University School of Electrical and Electronic Engineering Seoul Korea Republic of Arizona State University School of Electrical Computer and Energy Engineering AZ United States Korea University School of Electrical Engineering Seoul Korea Republic of

ISBN: (纸本)9798350351255

In frequency-division duplexing (FDD) multipleinput multiple-output (MIMO) systems, obtaining accurate downlink channel state information (CSI) becomes challenging due to the tremendous feedback overhead that increases with the number of antennas. Using uplink pilots to estimate downlink CSI is a promising approach that can eliminate the need for CSI feedback, but its accuracy decreases significantly as the number of channel paths increases. In this paper, we propose a mean square error (MSE)-optimal downlink channel reconstruction method that jointly utilizes uplink CSI and limited downlink CSI. With the MSE-optimal estimator, we derive the MSE as a function of the number of feedback bits for channel phase quantization and show the optimal feedback bit allocation method to minimize the MSE. Harnessing robust downlink precoding, we demonstrate that the proposed downlink channel reconstruction is sufficient to achieve a sum-spectral efficiency comparable to that with perfect downlink CSI. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Custom Transformer-Based Approach for Enhanced Bengali Automatic Speech Recognition 1

Custom Transformer-Based Approach for Enhanced Bengali Autom...

引用

1st International Conference on Innovations in Communications, electrical and computer engineering, ICICEC 2024

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Surendran, R. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Automated speech recognition (ASR) systems struggle with Bengali, which is the fifth most spoken language. Bengali has a varied morphology, many dialects, and limited high-quality annotated voice data. Traditional voice recognition techniques work well however struggle with Bengali phonetics and syntax. This method eliminates the need for large amounts of tagged data and the difficulties of differentiating sounds in different languages, both issues are addressed by this procedure. The research in this paper offers an Intellectual Bengali Speech Recognition System using Deep Learning Techniques (IBSRS-DLT). The model in this system uses transformer architecture and attention processes to manage Bengali speech pattern long-range dependencies. The IBSRS-DLT outperforms standard models in recognition accuracy using a pre-trained transformer model modified for phonetic and lexical correctness and fine-tuned on Bengali datasets. After training on a vast Bengali speech corpus, real-world datasets and rigorous simulations confirm the system. IBSRS-DLT can be used for automatic transcription, voice-controlled devices, and Bengali virtual assistants, such applications are efficient and accessible. The simulation showed a considerable boost in recognition speed and a decrease in keyword mistakes compared to current methods. This paper shows that deep learning can solve linguistic issues in ASR systems, enabling scalable regional language detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?

arXiv

引用

arXiv 2024年

作者： Sadeghi, Pouya Abaskohi, Amirhossein Yaghoobzadeh, Yadollah Department of Electrical and Computer Engineering University of Tehran Iran Department of Computer Science University of British Columbia Canada Tehran Institute for Advanced Studies Khatam University Tehran Iran

Inspired by human cognition, Jiang et al. (2023c) create a benchmark for assessing LLMs' lateral thinking-thinking outside the box. Building upon this benchmark, we investigate how different prompting methods enhance LLMs' performance on this task to reveal their inherent power for outside-the-box thinking ability. Through participating in SemEval-2024, task 9, Sentence Puzzle sub-task, we explore prompt engineering methods: chain of thoughts (CoT) and direct prompting, enhancing with informative descriptions, and employing contextualizing prompts using a retrieval augmented generation (RAG) pipeline. Our experiments involve three LLMs including GPT-3.5, GPT-4, and Zephyr-7B-β. We generate a dataset of thinking paths between riddles and options using GPT-4, validated by humans for quality. Findings indicate that compressed informative prompts enhance performance. Dynamic in-context learning enhances model performance significantly. Furthermore, fine-tuning Zephyr on our dataset enhances performance across other commonsense datasets, underscoring the value of innovative thinking. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Robust Tweets Classification Using Arithmetic Optimization with Deep Learning for Sustainable Urban Living

引用

SN computer Science 2024年第5期5卷 549页

作者： Hamza, Manar Ahmed Hashim, Aisha Hassan Abdalla Motwakel, Abdelwahed Elhameed, Elmouez Samir Abd Osman, Mohammed Kumar, Arun Singla, Chinu Munjal, Muskaan Department of Electrical and Computer Engineering International Islamic University Malaysia Kuala Lumpur 53100 Malaysia Department of Computer and Self Development Preparatory Year Deanship Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Management Information Systems College of Business Administration in Hawtat bani Tamim Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia Department of Computer Science College of Post-Graduated Studies University of Science and Technology Omdurman Sudan Department of Information System Faculty of Computer Science and Information Technology Omdurman Islamic University Omdurman Sudan Department of Electronics and Communication Engineering New Horizon College of engineering Bengaluru India Computer Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

Natural Language Processing (NLP) with Deep Learning (DL) for Tweets Classification includes use of advanced neural network designs to analyse and classify Twitter messages. DL techniques like recurrent neural network (RNN) or transformer-based frameworks like BERT are used to mechanically learn difficult linguistic patterns and contextual info from tweet data. These techniques able to capture subtleties of language with sarcasm, sentiment, and context-specific meanings and making them suitable for tasks like sentiment analysis or topic classification in realm of social media. Leveraging deep symbols learned from great amounts of textual data, these NLP techniques permit precise and nuanced classification of tweets, donating to enhanced information retrieval, sentiment tracking, and trend analysis in dynamic and fast-paced world of social media communication. In this view, this research develops an arithmetic optimization algorithm with deep learning based tweets classification (AOADL-TC) approach for sustainable living. The goal of the AOADL-TC technique is to identify and discriminate different kinds of sentiments that exist in the tweet data. At the initial stage, the AOADL-TC model pre-processes tweet data to convert uniform data into a useful format. For sentiment detection, the AOADL-TC technique applies a parallel bidirectional gated recurrent unit (BiGRU) model. At last, tuning of parameters related to parallel BiGRU model performed by AOA. An wide set of tests carried out to illustrate better performance of AOADL-TC model. The experimental outcomes portrayed that AOADL-TC technique demonstrates the supremacy of the AOADL-TC technique in terms of different evaluation metrics. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Machine learning Natural language processing Sentiment analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Exploring Convolution Neural Networks for Image Classification in Medical Imaging 2

Exploring Convolution Neural Networks for Image Classificati...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, electrical and Electronics, ICIITCEE 2024

作者： Vishwa Priya, V. Chattu, Padmini Sivasankari, K. Pisal, Dnyaneshwar Tukaram Renuka Sai, Bantupalli Suganthi, D. Vels Institute Science Technology and Advanced Studies Department of Cs Tamilnadu Chennai India Ace Engineering College India Sri Sai Ram Institute of Technology Department of Ece Tamilnadu Chennai India SVPMs Institute of Management Baramati Pune Maharashtra Malegaon India Raghu Engineering College Computer Science and Engineering Visakhapatnam India Saveetha College of Liberal Arts and Sciences Simats Department of Computer Science Thandalam Chennai India

ISBN: (纸本)9798350306415

Modern healthcare relies on medical imaging to diagnose and cure diseases. Convolution Neural Networks (CNNs) have excelled at image categorization, and their use in medical imaging could change illness diagnosis. This study examines CNN's medical picture categorization performance. This study used X-rays, CT scans, MRIs, and histopathology slides. Traditional CNNs, transfer learning models, and bespoke networks were constructed and trained. The training data included lung ailments, cancer detection, bone fractures, and neurological disorders. Our investigations showed that CNNs can extract complex characteristics from medical photos, improving classification accuracy. Transfer learning, where pre-trained models were fine-tuned on medical data, performed well with 94.8% accuracy. We used cutting-edge data augmentation and attention strategies to improve model generalization and interpretability. In addition to high classification accuracy, we studied model explainability using gradient-based methods and visualization to highlight medical picture regions of relevance that influenced model predictions. Building trust with medical practitioners and understanding deep learning model decision-making requires interpretability. In clinical settings, CNN deployment raises ethical and practical issues such as data privacy, model robustness, and regulatory compliance. According to our research, CNNs may increase medical picture classification accuracy and speed. X-rays had the best accuracy at 95.2%, followed by CT scans at 92.7% and MRIs at 94.1%. Histopathological slides exhibited 88.6% accuracy;however, this shows that CNNs can diagnose diseases from microscopic images. © 2024 IEEE.

关键词： Convolutional Neural Networks Image Classification Medical Data Analysis Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced advanced Image Processing Techniques for Plant Disease Detection and Management 9

IoT-Enhanced Advanced Image Processing Techniques for Plant ...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Bajpai, Chhavi Gaur, Manish Saravanan, B. Raja, G.V. Malikl, Neeru Sucharitha, M. Centre for Advanced Studies Department of Computer Science & Engineering Uttar Pradesh Lucknow India Institute of Engineering and Technology Department of Computer Science & Engineering Uttar Pradesh Lucknow India Sri Eshwar College of Engineering Department of Cse Kondampatti Kinathukadavu Tamil Nadu Coimbatore India Sri Sairam College of Engineering Department of Ece Karnataka Bangalore India Pimpri Chinchwad University Department of Engineering and Technology Maharashtra India Andhra Pradesh Amaravati India

ISBN: (纸本)9798350377972

Plant diseases often lead to significant agricultural losses, causing economic difficulties and food shortages. Conventional detection approaches are inefficient, challenging, and must have expert engagement, resulting in decreasing scalability. Recent developments, including machine learning and IoT-integrated systems, have enhanced real-time monitoring;However, they encounter obstacles such as restricted generalization to varied environmental circumstances, data imbalance, and insufficient adaptability to uncharacteristic diseases. This research tackles these issues by introducing an IoT-Enhanced Convolutional Neural Network (CNN) integrated with a One-Class Support Vector Machine (SVM). The model utilizes IoT for real-time data collection, CNN for effective feature extraction, and One-Class SVM for anomaly identification. Experimental results indicate the system's exceptional performance, attaining 95.6% accuracy, a 3.4% lower rate of false positives, and 97.2% precision, offering a scalable, automated solution for early disease detection, minimizing crop losses, and enhancing agricultural sustainability. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Parameter Estimation of CAPN Model for Li-ion Battery

Optimal Parameter Estimation of CAPN Model for Li-ion Batter...

引用

2023 International Conference on computer, Electronics and electrical engineering and their Applications, IC2E3 2023

作者： Bharti, Soumya Saini, Vikash Kumar Kumar Yadav, Anshul Kumar, Rajesh Al-Sumaiti, Ameena S. Malaviya National Institute of Technology Department of Electrical Engineering Jaipur India Malaviya National Institute of Technology Center for Energy and Environment Jaipur India Swami Keshvanand Institute of Technology Department of Electrical Engineering Jaipur India Khalifa University Advanced Power and Energy Center Electrical Engineering and Computer Science United Arab Emirates

ISBN: (纸本)9798350338003

Recent developments in battery technology and the reduction of battery costs have resulted in battery energy storage systems (BESS) becoming more economically viable for various power sectors and automobile applications. The degradation of BESS when used in conjunction with photovoltaics (PV) and electric vehicles (EVs) brings new challenges in both technical and economic analysis. Consequently, to ensure the reliability and safety of an energy storage system, modeling battery degradation is critical in order to maintain and replace batteries before potential issues arise. This paper presents a hybrid optimal parameter estimation technique for a combination-factor-based semi-empirical approach to evaluate the state of health (SOH) of Li-ion batteries. The parameters of the proposed model are determined using the SCA optimization algorithm, and the numerical results are confirmed by placing them side-by-side with other heuristic algorithms such as GWO, DE, HHO, and GA. The proposed model outperformed the traditional model with a SOH value of 0.9591 as compared to the previous SOH obtained 0.9467 by the traditional model. © 2023 IEEE.

关键词： Lithium-ion batteries

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：