检索结果-内蒙古大学图书馆

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Priyadarsini, K. Karthik, S. Tamilarasi, R. Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India Srm Institute of Science and Technology Vadapalani Campus Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350367904

This review, titled 'Empowering Tomorrow's Cities: Navigating Power Challenges through Deep Learning Solutions,' explores the intersection of power management issues and the trans-formative potential of deep learning technologies. It addresses the growing challenges of energy consumption, grid reliability, and peak demand, emphasizing deep learning's vital role in optimizing power usage. The article provides a detailed overview of smart cities, highlighting the importance of efficient power management for their continued development. By presenting deep learning as a groundbreaking solution, it examines its applications in real-time monitoring, predictive analytics, and demand forecasting. Through case studies, the review showcases successful deep learning implementations in tackling specific power challenges. It also explores the integration of IoT with deep learning, emphasizing their synergy in advancing data-driven decision-making. Critical aspects like data security and privacy are discussed, ensuring a thoughtful approach to managing sensitive data for optimized power distribution. Looking ahead, the article envisions future trends and innovations, stressing the need for ongoing research to fully harness deep learning in addressing power challenges in smart cities. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Vision - Yolov8 Algorithm for Objects and Impediments Detection 2

Artificial Vision - Yolov8 Algorithm for Objects and Impedim...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Lakshmi, S. Jothi Sasirekha, S.P. Mekala, N. Reshma, R. Nair, V. Indu Bhagya, S.G. Nehru Institute of Technology Department of Information Technology Coimbatore India Karpagam Academy of Higher Education Department of Computer Science and Engineering Coimbatore India Coimbatore India SNS College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India Bapuji Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Davangere India

ISBN: (纸本)9798331534950

This paper presents an object detection method using YOLO technique (You Only Look Once) based deep learning algorithm to help visually impaired people in their daily life. A Cobotic Spectacle is a cutting-edge product designed specifically for visually impaired individuals. The system seamlessly integrates face motion recognition, object identification and text detection functionalities using YOLO Algorithm. The real time object detection method uses YOLO and convolution neural networks (CNN) for single forward propagation from end to end. The proposed system utilizes YOLOv8, a state-of-the-art real-time object detection algorithm, which is trained on the Common Object in Context (COCO) dataset to accurately identify objects in front of a person. With a high degree of accuracy, the system then conveys the identified object information through a synthesized voice output, thereby enhancing visual perception and providing an immersive *** face motion recognition module promotes improved social interaction, while object identification increases environmental awareness. This integrated solution combines edge processing and cloud-based analysis for portability, real-time processing, and computational efficiency. A Cobotic Spectacle empowers visually impaired individuals, providing a state-of-the-art smart spectacle system that enhances visual perception, promotes independence, and improves their overall quality of life. © 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

Ontology-Based Decision-Making Support in Real-Time Strategy Game 4

Ontology-Based Decision-Making Support in Real-Time Strategy...

引用

4th International Conference on Consumer Electronics and Computer engineering, ICCECE 2024

作者： Wang, Yaochu Yang, Jian Yang, Guoli School of Automation Science and Engineering South China University of Technology Guangzhou China Advanced Institute of Big Data Department of Big Data Intelligence Beijing China

ISBN: (纸本)9798350384062

Real-Time Strategy (RTS) games have attracted millions of players due to their characteristics of diverse scenes and flexible decision-making mechanisms. However, the mechanisms, contents, and operations of RTS games could be quite complex for beginners. The frustration and poor beginner experience caused by the high level of difficulty in getting started may lead novice players to give up on a specific RTS game due to a lack of sense of achievement. To address this issue and enhance the gaming experiences of beginners, this article proposes to assist beginners in familiarizing themselves with the mechanisms of the games and evaluating the opponents' abilities based on ontology. Firstly, an ontology will be built according to the properties of game units, which can provide beginners with a clear and comprehensive conceptual framework to understand game mechanisms and operations. Secondly, a knowledge-based reasoning method will be proposed to help beginners evaluate their opponents' abilities. Using a specific RTS game as a demonstration, the ontology is built and a reasoning example is proposed. By analyzing and reasoning about the abilities of their opponents' game units, this reasoning method can help beginners develop more effective strategies and tactics to enhance their experience in the game. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

CLERC: An Intelligent Sign Language Translator for Improved Accessibility using Machine Learning 2

CLERC: An Intelligent Sign Language Translator for Improved ...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Vijayaganth, V. Santhosh Kumar, S. Davis, L. Pranava Darisan, S.V. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kpr Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350369960

Clerc's system is a modern smart language interpreter using advanced methods like artificial intelligence, imagery recognition, and natural languages translation. The Clergs System includes these are just some of tools used. The system is able to do this by turning gestures in sign language into verbal and written outputs smoothly thus helping people with hearing impairment to communicate easily in real time. In this research, an object recognition SSD MobileNets and FDN feature extraction models are used for accurate gesture detection. A machine-learning model can also be used to predict accurate translations. The efficacy of the Clerc system has been tested and validated to the utmost extent in different settings such as public places, schools, hospitals amongst others. This research seeks to explore possibilities of improving the system's precision, efficacy, scalability, and use with regards to the practical application. © 2023 IEEE.

关键词： Clerc system Computer vision FPN-lite feature extractor scalability SSD Mobile Net Object recognition model

来源：评论

学校读者我要写书评

暂无评论

Freshness Monitoring of Broccoli Using Intelligent Electronic Nose Systems for Sustainability in Food Supply Chains

Freshness Monitoring of Broccoli Using Intelligent Electroni...

引用

2024 International Conference on Smart Electronics and Communication Systems, ISENSE 2024

作者： Ebenezer, Brighty L. Sasithradevi, A. Baskar, Chanthini School of Electronics Engineering Vellore Institute of Technology Chennai India Vellore Institute of Technology Centre for Advanced Data Science Chennai India

ISBN: (纸本)9798331528126

Reducing food waste and enhancing sustainability in food supply chains have become increasingly critical in the global food industry. Broccoli, known for its nutrient richness, is particularly vulnerable to spoilage due to environmental factors, which results in considerable food loss. To address this issue, this paper proposes an innovative and sustainable approach to predicting broccoli freshness using an electronic nose (E-nose) system. The E-nose, equipped with gas sensors, detects volatile organic compounds (VOCs) emitted by broccoli during spoilage. The sensor data was first analyzed using unsupervised clustering algorithms such as K-Means, Gaussian Mixture Model (GMM), and Spectral Clustering, to group the broccoli samples based on freshness levels. Following this, advanced machine learning (ML) and deep learning (DL) techniques were applied to classify the samples into specific freshness categories: fresh, half-spoiled, and spoiled. K-means clustering combined with the Long Short-Term Memory (LSTM) model achieved an accuracy of 99.46%. Furthermore, hyperparameter tuning (HPT) was employed to optimize the performance of the LSTM models, improving classification accuracy to 100%. The results illustrate the effectiveness of integrating E-nose technology with AI-driven techniques for real-time, scalable freshness monitoring. This system offers a promising solution for reducing food waste and promoting sustainability in the management of perishable produce within food supply chains. © 2024 IEEE.

关键词： Electronic nose

来源：评论

学校读者我要写书评

暂无评论

A Survey of LLM datasets:From Autoregressive Model to AI Chatbot

引用

Journal of Computer science & Technology 2024年第3期39卷 542-566页

作者：杜非马新建杨婧如柳熠罗超然王学斌姜海鸥景翔 National Key Laboratory of Data Space Technology and System Beijing 100195China Advanced Institute of Big Data Beijing 100195China Fu Foundation School of Engineering and Applied Science Columbia UniversityNY 10027U.S.A. School of Software and Microelectronics Peking UniversityBeijing 100091China CCF IEEE

Since OpenAI opened access to ChatGPT,large language models(LLMs)become an increasingly popular topic attracting researchers’attention from abundant ***,public researchers meet some problems when developing LLMs given that most of the LLMs are produced by industries and the training details are typically *** datasets are an important setup of LLMs,this paper does a holistic survey on the training datasets used in both the pre-train and fine-tune *** paper first summarizes 16 pre-train datasets and 16 fine-tune datasets used in the state-of-the-art ***,based on the properties of the pre-train and fine-tune processes,it comments on pre-train datasets from quality,quantity,and relation with models,and comments on fine-tune datasets from quality,quantity,and *** study then critically figures out the problems and research trends that exist in current LLM *** study helps public researchers train and investigate LLMs by visual cases and provides useful comments to the research community regarding data *** the best of our knowledge,this paper is the first to summarize and discuss datasets used in both autoregressive and chat *** survey offers insights and suggestions to researchers and LLM developers as they build their models,and contributes to the LLM study by pointing out the existing problems of LLM studies from the perspective of data.

关键词： large language model(LLM) autoregressive model AI chatbot natural language processing(NLP)corpora OpenAI

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Inference of a Proposed, Improved and Efficient W Model for Software Testing 15

Evaluation and Inference of a Proposed, Improved and Efficie...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Velan, Senthil S. Velan, Sivaranjani Senthil Rubini, P. Sudhakar, K. Information Science and Engineering CMR Institute of Technology Bengaluru India Computer Science and Engineering MVJ College of Engineering Bengaluru India School of Engineering and Technology CMR University Bengaluru India Artificial Intelligence and Data Science NITTE Meenakshi Institute of Technology Bengaluru India

ISBN: (纸本)9798350370249

Software Testing is an important and measured/outcome-oriented field that requires an in-depth analysis for developing new methodologies. This enables the development of high-quality end product resulting in fewer maintenance schedules. Several models have been proposed by research teams of different companies leading to improved development and testing schedules. Even with the availability of these models, a significant allocation of the budget has been dedicated purely on the maintenance of software developed by the IT industry. In order to address this need for improved process models of testing, a new exclusive and efficient W model has been proposed and explained in this paper. This model can improve the quality of end product, namely the high-quality software and further reduce the cost involved for the maintenance. Based on the quantitative measurement the proposed W software testing model, it was found the small scale software developed by adopting this method produces high-quality software with 50% less errors/faults compared to development using classical life cycle model. ©2024 IEEE.

关键词： Computer software selection and evaluation

来源：评论

学校读者我要写书评

暂无评论

Hybrid RNN Based Text Classification Model for Unstructured data

引用

SN Computer science 2024年第6期5卷 726页

作者： Sunagar, Pramod Sowmya, B.J. Pruthviraja, Dayananda Supreeth, S. Mathew, Jimpson Rohith, S. Shruthi, G. Cloudthat Technologies Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education School of Computer Science and Engineering REVA University Department of Computer Science and Engineering Indian Institute of Technology Patna Department of ECE Nagarjuna College of Engineering and Technology

The volume of social media posts is on the rise as the number of social media users expands. It is imperative that these data be analyzed using cutting-edge algorithms. This goal is handled by the many techniques used in text categorization. There are a variety of text categorization techniques available, ranging from machine learning to deep learning. Numerical crunching has become easier with less processing time since the emergence of high-end computer facilities. This has led to the development of sophisticated network architectures that can be trained to achieve higher precision and recall. The performance of neural network models which was evaluated by the F1 score is affected by cumulative performance in precision and recall. The current study intends to analyze and compare the performance of the neural network proposed, A Hybrid RNN model that has two layers of BiLSTM and two layers of GRU to that of previous hybrid models. GloVE dataset is used to train the models and their accuracy, precision, recall, and F1 score are used to assess performance. Except for the RNN + GRU model, the RNN + BILSTM + GRU model has a precision of 0.767, a recall of 0.759, and an F1-score of 0.7585. This hybrid model outperforms the others. © The Author(s) 2024.

关键词： Bidirectional long-short-term memory (BiLSTM) Gated recurrent units (GRU) Recurrent neural networks (RNN) Region-based convolutional neural networks (RCNN) Text classification

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Dementia Disorder Detection Using an Improved Eliminate Particle Swarm Optimization (IEPSO) Based on Convolutional Neural Networks

引用

SN Computer science 2024年第6期5卷 695页

作者： Duraipandian, Kavitha Ambigapathy, Murugan Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Campus Tamil Nadu Chennai India Department of Data Science and Business Systems SRM Institute of Science and Technology SRM Nagar Tamil Nadu Kattankulathur Chennai India

Dementia is an un-repairable and continuous disease that affects a person's mental health. Symptoms of Dementia may vary from one person to another, there are no effective treatments for detecting Dementia. Machine learning algorithm has proven to be effectively used by many researchers in assisting optimal detection of Dementia. So, this research introduces an improved eliminate particle swarm optimization (IEPSO) based Convolutional Neural Network (IEPSO-CNN) for diagnosing Dementia without causing severe effects effectively. IEPSO is used to find suitable parameters while training the model to improve Dementia detection accuracy. This IEPSO is used for tuning the parameter of the two-level Visual Geometry Group 16 (VGG 16) model. The integration of IEPSO and two hierarchical layers of VGG 16 increases the model's Dementia detection performance. The IEPSO-CNN model performance is evaluated using 6400 Dementia and non-Dementia images. The performance analysis shows that the IEPSO-CNN obtained a maximum accuracy of 99% for detecting the dementia stages. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural network Deep learning Dementia detection Improved eliminate particle swarm optimization VGG 16

来源：评论

学校读者我要写书评

暂无评论

Advancing Alzheimer's Diagnosis Through Transfer Learning with Deep MRI Analysis

Advancing Alzheimer's Diagnosis Through Transfer Learning wi...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Adityasai, B. Babu, Nirmal Varghese Karunya Institute Of Technology And Sciences Division Of Computer Science And Engineering Coimbatore India Karunya Institute Of Technology And Sciences Division Of Data Science And Cyber Security Coimbatore India

ISBN: (纸本)9798350371567

Alzheimer's disease (AD) poses a significant health-care challenge, necessitating early and accurate diagnosis for effective management. This study presents a novel approach aimed at enhancing AD diagnosis through the integration of transfer learning, deep learning techniques, and meticulous data preprocessing methodologies. Leveraging a rich dataset from the Open Access Series of Imaging Studies (OASIS), comprising MRI scans from both healthy individuals and those with AD, the proposed method seeks to identify subtle abnormalities indicative of the disease. The methodology encompasses several key steps. Initially, MRI data undergoes rigorous cleaning and standardization using histogram equalization to ensure compatibility and remove irrelevant information. Subsequently, a two-step feature extraction process involving an autoencoder neural network is employed to identify significant AD-related features. These features are then combined with other relevant data to provide a comprehensive understanding of the disease. To optimize model efficiency, three algorithms iteratively refine the feature set, focusing on the most informative features associated with AD. Finally, a pretrained deep learning model, VGG19, is fine-tuned using the AD-specific dataset. Results demonstrate a significant improvement in diagnostic accuracy post-hyperparameter tuning, with accuracy increasing from 76.5% to 89.5%. The enhanced model performance across various metrics underscores the potential of the proposed approach to revolutionize AD diagnosis, offering promise for earlier detection and more accurate prognostication. This research contributes to advancing the field of neuroimaging-based diagnostic techniques for neurodegenerative diseases like Alzheimer's. © 2024 IEEE.

关键词： Magnetic resonance imaging

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：