检索结果-内蒙古大学图书馆

International Conference on ent Computing and Control Systems (ICICCS)

作者： R. Praveen Kumar Pannala Ramya G.Sai Teja V.Rama Krishna Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

Emotion recognition in text is a crucial area within Natural Language Processing (NLP), serving diverse applications such as sentiment analysis, mental health assessment, and human-computer interaction. This study explores the use of Bidirectional Encoder Representations from Transformers (BERT) for this purpose, capitalizing on its bidirectional transformer architecture to grasp intricate contextual relationships in text. By fine tuning a pretrained BERT model on a dataset annotated with emotional categories like happiness, sadness, anger, surprise, and fear, the model achieves precise emotion classification. BERT's pre-trained linguistic knowledge and ability to interpret complex semantic and syntactic patterns provide a strong foundation for this task. Experimental results demonstrate that BERT surpasses traditional machine learning approaches, including Support Vector Machines (SVM) and logistic regression, in terms of accuracy, owing to its advanced contextual embeddings. Additionally, the model exhibits excellent generalization capabilities across diverse emotional expressions, highlighting its effectiveness for emotion-aware NLP applications. This project also leverages Streamlit to develop interactive web applications that integrate NLP-based emotion detection, showcasing its practicality and accessibility for real-world use cases.

关键词： Support vector machines Emotion recognition Sentiment analysis Semantics Bidirectional control Mental health Syntactics Transformers Encoding Tuning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical Imaging: Image Processing - From Augmenting Accuracy to Enhancing Efficiency 24

Deep Learning in Medical Imaging: Image Processing - From Au...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Lakshmi Vara Prasad, G. Murali, A. Bhaskar Reddy, Y.V. Marturi, Haribabu Paul, Valeru Vision Centre for Data Science AI and ML QIS College of Engineering and Technology Andhra Pradesh Ongole India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798400709586

Deep learning has transformed medical imaging by significantly improving accuracy and efficiency in image processing tasks such as disease detection, segmentation, and classification. This paper explores the role of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and other advanced architectures in enhancing image interpretation across various medical imaging modalities. By analyzing MRI, CT, and ultrasound data, this study demonstrates the efficacy of deep learning in automating critical diagnostic tasks, reducing human error, and improving patient outcomes. We propose a comprehensive framework for applying deep learning techniques in medical imaging, providing insights into future advancements in the field. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Medical Insurance Premiums

Predictive Analytics for Medical Insurance Premiums

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Muppidi Mahesh B. Sasi Priyatham G. SaiKumar K. Venkat Varshith Reddy Department of Computer Science and Engineering (AI & ML) Vignan Institute of Technology and Science

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

This paper enables a machine leaning method to project the health insurance costs, ever more crucial in view of growing medical expense complexity. Both payers and buyers are served by stable insurance price estimates. The authors used a sample set consisting of medical history, demographics, and other contributing parameters to construct model predictions by invoking multiple machine learning methods, from ensemble modeling and *** models were assessed with measures such as R-Squared and Mean Absolute Error, showing the methods were able to accurately predict insurance premiums. The innovation provides useful insights for insurance practitioners, with the potential to maximize pricing strategies, improve risk estimates, and enhances decision-making in the health insurance market. The research also highlights potential of the machine learning to forecast medical insurance premiums using personal attributes-gender, age, BMI number, dependents, smoking habits ,and geographical location are collected and prepared. The datasets have been separated into two groups: training and testing the Artificial Neural Network model is developed and trained on TensorFlow and Keras, and it produced a high R-Squared value indicating its precision. The study found significant factors that determine insurance premiums. Generally, the results indicate that machine learning has great potential in predicting healthcare expenditures. Through these predictive models, insurance firms may provide more customized insurance products, simplify the underwriting process, and enable customers to make well known decisions about their health plans. Finally, this study seeks to strengthen Utilization of information for making decisions in the insurance market, to the advantage of both providers and policyholders.

关键词： Training Pervasive computing Technological innovation Social networking (online) Insurance Machine learning Pricing Predictive models Predictive analytics Testing

来源：评论

学校读者我要写书评

暂无评论

Waste Product Identification to assist EPR using Object Detection 15

Waste Product Identification to assist EPR using Object Dete...

引用

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

作者： Anil Prasad, R. John, Ayain Gandiboina, Harika Jayadev, Gopika Frugal Scientific Pvt Ltd Bengaluru India Dayananda Sagar University School of Engineering Department of Computer Science and Engineering Bengaluru India Dayananda Sagar University School of Engineering Department of Ai & Ml Bengaluru India

ISBN: (纸本)9798350370249

With the increase in population, there has been a large increase in waste production. This has affected the environment and in turn have led to land pollution. To increase the recycling of products and increase the lifespan of raw materials, several countries of the world have implemented EPR policy. EPR requires collection of data related to the amount of non biodegradable waste generated by each company. With the recent technological advancements in machine vision, it has become possible to develop an infrastructure to easily collect such data in realtime using various object detection models like Yolo, SSD, RCNN and so on. This paper provides the details of a complete prototype that can help assist in the identification of non biodegradable waste products into their respective producers which can in turn help to implement the EPR policy and also elaborates on the model selection process for this application. The models that were used and compared in this paper includes CNN, Faster RCNN and Yolo v5 © 2024 IEEE.

关键词： CNN Extended Producer Responsibility (EPR) Faster RCNN Object Detection Techniques Waste Management YOLO

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Cyber Defense: Deep Q-Learning-Based Adversarial Detection and Prevention in Autonomous Vehicle Networks 4

Next-Generation Cyber Defense: Deep Q-Learning-Based Adversa...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Srivastava, Shubhi Bhargav, H.K. Gurani, Vijayakumar Chaturvedi, Arpana Gandhi, Ankita Dharangutti, Yogesh New Horizon College of Engineering Department of Information Science and Engineering Bangalore India Shridevi Institute of Engineering and Technology Department of Computer Science and Engineering Tumakuru India Karnatak University Department of Computer Science Dharwad India New Delhi Institute of Management Department of IT/AI/ML New Delhi India Parul Institute of Engineering and Technology Department of Computer science and Engineering Gujarat India Faculty of Law Pune India

ISBN: (纸本)9798350352931

This paper presents a novel ai-powered super-resolution technique for real-time video processing, which significantly enhances the visual quality of low-resolution video frames. The proposed framework employs a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) with Generative Adversarial Networks (GANs) to reconstruct high-resolution frames with minimal computational overhead. Experimental results on benchmark video datasets show that the proposed method achieves a peak signal-to-noise ratio (PSNR) of 34.56 dB and a structural similarity index (SSIM) of 0.94, outperforming state-of-the-art methods by 12.3% in PSNR and 8.7% in SSIM. Additionally, the system demonstrates an average processing speed of 30 frames per second (fps) on a GTX 1080Ti GPU, making it suitable for real-time applications. The qualitative and quantitative results validate the effectiveness of the proposed method in preserving fine details, reducing artifacts, and enhancing visual clarity in various real-time video processing scenarios. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Development and Implementation of a Virtual Reality Simulation for an Immersive College Environment Using the Unity Game Engine 3

Development and Implementation of a Virtual Reality Simulati...

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Lendalay, Ashwin Raj Pabba, Rupesh Katta, Sudheer Reddy Ahmed, Mohd Afnan Karthik, R.U. Prasad, Kowdodi Siva Hyderabad Institute of Technology and Management Computer Science with Ai & Ml Hyderabad India Hyderabad Institute of Technology and Management Mechanical Engineering Hyderabad India

ISBN: (纸本)9798350364569

Virtual Reality (VR) simulation has emerged as a transformative technology with applications spanning various fields such as education, healthcare, training, and entertainment. This research paper explores the advancements, methodologies, and impacts of VR simulation, providing a comprehensive review of current technologies and their *** paper details the development and implementation of a Virtual Reality (VR) walkthrough simulation of a college environment using the Unity game engine. The project aims to offer users an immersive and interactive experience that closely mirrors the sensation of navigating through a physical establishment. The simulation integrates lifelike visuals, intuitive navigation, and interactive elements to create a compelling virtual environment. Through this innovative approach, users can experience a realistic and engaging representation of the college, enhancing their understanding and exploration of the space. Traditional architectural models, typically rendered with pen-and-paper blueprints or clay models, often lack detailed visualization and feasibility for quick modifications. This research explores the advantages of utilizing Virtual Reality (VR) for visualizing architectural models of college environments with significantly enhanced detail, both exterior and interior. VR technology allows for the immediate identification and correction of errors, facilitating rapid and efficient updates. Unlike traditional methods, which require redrawing entire blueprints for minor changes, VR's layered structure permits individual modifications without impacting the whole model. Leveraging the Unity game engine, multiple architects can collaborate seamlessly, working together with clients to develop a satisfactory and detailed VR model of the building. This approach not only improves design accuracy but also enhances collaborative efforts, demonstrating the substantial benefits of VR in modern architectural practices. © 2024 IEEE

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Analysis on Detecting Cardiac Arrhythmia Using Advanced Technologies 8th

Analysis on Detecting Cardiac Arrhythmia Using Advanced Tech...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Radhika, N. Sujatha, D. School of Computer Science & Engineering MRUH Telangana Hyderabad India CSE-AI&ML Department MRCET Telangana Hyderabad India Department of Computational Intelligence MRCET Telangana Hyderabad India

ISBN: (纸本)9789819786657

Essential features of the various cardiac diseases that affect the human heart are provided by the electrocardiogram (ECG). A significant portion of the diagnosis of heart illness comes from the categorization of arrhythmias. An arrhythmia is any alteration to the regular electrical impulse sequence. Conventional techniques for analyzing digital signals, machine learning, and the offshoots, including deep learning approaches are widely used for analyzing and classification of ECG signals and more importantly, for the timely diagnosis of cardiac disorders and arrhythmias. An extensive review of the literature regarding ECG analysis is presented in this document. Also address the computational barriers of machine learning techniques to wearable devices. The study started with a search for pertinent papers and then the gathered data was examined. Examining the assessed ECG features and the machine learning technique for identifying arrhythmias was the second step. The analysis shows that even though the MIT-BIH database requires a large amount of preprocessing work, it chose a sizable proportion of studies. We examine the substantial corpus of literature on pre-recorded ECG data, signal collection, ECG signal processing, and noise reduction, identifying ECG spectrographic states through function technology, classification of ECG signals, and relative perspectives among the examined modules. We reviewed the ultra-modern machine learning strategies for automated arrhythmia detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Convolutional Neural Network Using Hierarchical Particle Swarm Optimization for Sensor Based Human Activity Recognition

引用

SN computer science 2024年第5期5卷 447页

作者： Ankalaki, Shilpa Thippeswamy, M.N. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal Karnataka 576104 India Department of Computer Science and Engineering (AI & amp

Hyperparameter optimization poses a significant challenge when developing deep neural networks. Building a convolutional neural network (CNN) for implementation can be an arduous and time-intensive task. This work proposed an approach to optimize the hyperparameters of one dimensional (1D-CNN) to improve the accuracy of human activity recognition (HAR). The framework includes a parametric depiction of 1D-CNNs along with an optimization process for hyperparameters aimed at maximizing the model's performance. This work designed the method called OPTConvNet for hyperparameter optimization of 1D-CNN using Hierarchical Particle Swarm Optimization (H-PSO). The H-PSO algorithm is designed to optimize the architectural, layer and training parameters of 1D-CNN. The H-PSO optimizes the architecture of the 1D-CNN at initial level. Layer and training hyperparameters will be optimized at the next level. The proposed approach employs an exponential-like inertia weight to fine-tune the balance between exploration and exploitation of particles to prevent premature convergence to a local optimum solution in the PSO algorithm. The H-PSO- CNN is evaluated on publicly available sensor- human activity recognition (S-HAR) datasets namely, UCI-HAR, Daphnet Gait, Opportunity and PAMPA2 datasets. © The Author(s) 2024.

关键词： 1D-convolutional neural network Hierarchical particle swarm optimization Human activity recognition Hyperparameters OPTConvNet Optimization

来源：评论

学校读者我要写书评

暂无评论

ml based Text Summarization for Sentiment Analysis in Information Retrieval using Feature engineering 4

ML based Text Summarization for Sentiment Analysis in Inform...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Shirley, C.P. Berin Jeba Jingle, I. Venkatesan, R. Tamilarasan, R. Yashvanth Ram, R.V. Joyce Beryl Princess, P. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Dept. of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Dept. of Ai & Ml Coimbatore India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

Sentiment analysis plays a crucial role in understanding user preferences and opinions in the field of information retrieval. This research focuses on developing a system that combines text summarization and machine learning techniques to improve sentiment analysis accuracy. The proposed approach employs extractive and abstractive summarization techniques to reduce lengthy texts into concise summaries while preserving key information. Feature engineering is then applied to extract sentiment-related elements from the summary text, providing valuable insights for the SVM model. The SVM model, enhanced with feature engineering, is expected to effectively summarize text and accurately detect sentiments expressed in documents. This research contributes to the advancement of sentiment analysis techniques and provides valuable insights for decision-making and content development. © 2024 IEEE.

关键词： Support vector machines Measurement Sentiment analysis Accuracy Text summarization Machine learning Information retrieval Feature extraction Vectors Resilience

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Intelligent System for Social Distancing Compliance Using YOLOv5 and YOLOv6 with Euclidean Distance Metric

引用

SN computer science 2024年第8期5卷 1-19页

作者： Parkavi, A. Alex, Sini Anna Pushpalatha, M.N. Shukla, Prashant Kumar Pandey, Ankur Sharma, Sachin Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering (AI and ML) M S Ramaiah Institute of Technology Bangalore India Department of Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur 522302 India Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Manav Rachna International Institute of Research and Studies Faridabad India

The COVID-19 pandemic forced rigorous social distancing measures to be put in place to halt the virus’s spread;compliance was extremely difficult. In response, we have designed a highly advanced intelligent drone system that maintains and controls distance measures following social distance principles through advanced machine learning skills. This paper describes an intelligent monitoring and compliance system in public places using drone technology with a focus on social distance requirements. Boosting the efficiency of human detection in real-time video streams acquired by drones, our solution employs the You Only Look Once version 5 (YOLOv5) and YOLO version 6 (YOLOv6) object detection algorithms which are the most potent computer vision tools today. The distances between the recognized individuals are computed based on the Euclidean distance measurement to distinguish cases of nonadherence to social distance measures. Our technique integrates the recently developed deep learning models with aerial imagery and monitoring to make it easily scalable for population health surveillance. Thus, we prove impressively that the underlying inventive method works well in different environmental conditions and can potentially contribute to people’s safety in the event of a pandemic. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19 Drones Euclidean distance metric Social distancing YOLOv6

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：