检索结果-内蒙古大学图书馆

Background initialization in video data using singular value decomposition and robust principal component analysis

International Journal of Computers and Applications 2023年第9期45卷 600-609页

作者： Gowda, Vishruth B. Gopalakrishna, M.T. Megha, J. Mohankumar, Shilpa Department of Information Science and Engineering SJB Institute of Technology Bengaluru India Department of Artificial Intelligence and Machine Learning SJB Institute of Technology Bengaluru India Department of Artificial Intelligence and Machine Learning Ramaiah Institute of Technology Bengaluru India

Background initialization is used in video processing applications to extract a scene without the foreground scene. In recent times, the issue of background initialization has gained researchers’ attention in different fields such as video surveillance, video segmentation, computational photography, and so on. The initialization of the background is affected due to different complex dissimilarities such as shadow, intermittent movement, illumination, camera jitter, and clutter. To overcome the aforementioned issues, this paper proposes a decomposition using the combination of the Singular Value Decomposition (SVD) and Robust Principal Component Analysis (RPCA) for Singular Spectrum Analysis (SSA) to perform an effective background initialization. The incorporation of RPCA in SVD is used to overcome the issues related to non-Gaussian noise and it also uses an effective structural knowledge of the video input i.e. sparse and low rank matrix which improves the Peak-Signal-to-Noise-Ratio (PSNR) of the background image. The SBI dataset was used to analyze the performances of SSA-SVDRPCA. The SSA-SVDRPCA is analyzed using MultiScale Structural Similarity Index (MSSSIM), Average gray-level error (AGE), Percentage of clustered error pixels (pCEPS), Percentage of error pixels (pEPs), and PSNR. The existing approaches such as Background Initialization Singular Spectrum Analysis (BISSA) and Quaternion-based Dynamic Mode Decomposition (Q-DMD) are used to compare with the SSA-SVDRPCA method. The PSNR of the SSA-SVDRPCA for Board class is 30.39 dB which is higher than the BISSA and Q-DMD. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Identification of Potholes and Speed Bumps Using SSD and YOLO 15th

Identification of Potholes and Speed Bumps Using SSD and YOL...

引用

15th International Conference on Intelligent Computing and Networking, IC-ICN 2024

作者： Chandak, Payal Chaurasia, Shivamkumar Patil, Megharani Department of Artificial Intelligence and Machine Learning Thakur College of Engineering and Technology Mumbai India

ISBN: (纸本)9789819786305

Using SSD and YOLO to efficiently detect potholes and speed bumps is the main goal of this project, which aims to improve road safety and construction quality. Hazard priority is emphasized and the limitations of the manual method are addressed. YOLO and SSD architectures are used, trained, and optimized on a variety of datasets with different road appearances and conditions. To improve model capabilities, data augmentation approaches are used. The study explores techniques for processing data quickly through optimization. Accuracy, recall, and efficacy are measured by gathering large amounts of data, training models, and assessing results on different test sets. Extensive analysis between YOLOv4 and SSD-MobileNet demonstrates clear differences in performance. YOLOv4 achieves an overall improved object detection proficiency of 85.48, a superior mAP@0.5 score. By comparison, SSD-MobileNet demonstrates unique metric strengths in precision (0.42), recall (0.81), and F1 score (0.82). In particular, SSD-MobileNet significantly outperforms YOLOv4 (52.51 ms) in inference time (7 ms), demonstrating its effectiveness in real-time applications. The study suggests using SSD-MobileNet because of its excellent F1 score, repeatability, and precision for real-time applications. Because of its quick inference time, this model is a great fit for high-stakes situations where accurate and timely object identification is necessary, such as security systems, drones, and autonomous cars. It also balances performance measurements with practicality. Novelty: By utilizing cutting-edge computer vision techniques, this study creatively combines SSD and YOLO to produce a safer and more effective method of infrastructure management and road danger monitoring. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Determining the Underlying Factors of Chronic Liver Disease through Factor Analysis 2

Determining the Underlying Factors of Chronic Liver Disease ...

引用

2nd International Conference on artificial intelligence and machine learning Applications, AIMLA 2024

作者： Balaji, V.S. Mahi, A.R. Aashif, M. Manju, M. Indira Priya, P. Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (数字)9798350349221

ISBN: (纸本)9798350349221

Chronic liver disease is a significant health concern, necessitating a comprehensive understanding of its underlying causes. The work aims to identify the key factors contributing to chronic liver disease using Factor Analysis, a statistical technique that explores the inter-relationships among a set of variables. The dataset, comprising various biochemical parameters and demographic details, is subjected to rigorous preprocessing, including imputation and standardisation. The suitability of data is determined using KMO measure value. The factors are represented by combinations of things that include the biochemical parameters protein, aminotransferase, globulin, phosphatase and *** research provides valuable insights, potentially aiding in early diagnosis and effective treatment strategies for chronic liver disease. This research underscores the utility of Factor Analysis in medical research, particularly in understanding complex diseases like chronic liver disease. The overview of Factor Analysis would include the loadings of each factor for each variable on each factor, which indicate how much each variable contributes to each factor and further help to identify which variables are most strongly associated with each underlying factor. The communalities and specific variances of the factors are *** could potentially aid in early diagnosis and effective treatment strategies for chronic liver disease. The complex relationship among various attributes of the dataset is examined thereby providing the contribution of a vital parameter to liver disease. © 2024 IEEE.

关键词： Factor analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Operational Efficiency and Security in Multi-Sectioned Businesses with Edge AI through Real-Time Analytics

Enhancing Operational Efficiency and Security in Multi-Secti...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Vijay, K. Jeyanth, V. Kamalesh, S. Dheva Prasath, D. Rajalakshmi Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (数字)9798331522988

ISBN: (纸本)9798331522988

The goal of this project is to disrupt the way businesses monitor their operations by integrating IoT and machine learning to gain a deeper understanding of customer behavior and improve operational efficiency. Traditional surveillance systems create lots of data to store and analyze, but they do not provide actionable intelligence. CCTV cameras and edge devices strategically placed throughout a facility capture real-time footage, identify visitor movement patterns, and represent critical heat zones on a heat map. This data-driven process enhances resource allocation, enhances customer experience, and enables proactive improvements in operational workflow. Edge devices enable real-time anomaly detection, such as theft or staff sitting, without compromising privacy, as the device retains all information and performs all processing locally. Our next-gen solution provides businesses with an all-inclusive monitoring system that solves today's most pressing security and operational issues, ultimately delivering better business results. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Hybrid machine learning for Personalized Ayurvedic Drug Recommendation via Prakriti Assessment 1

Hybrid Machine Learning for Personalized Ayurvedic Drug Reco...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Mathew, Jimsha K Pandi, J Maruthu Kumar, V Harish Charan, Vadagam V Sri Vishnu Bindu, S.M. Bhoomika, H. New Horizon College of Engineering Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798331518943

Ayurveda, an ancient system of medicine, emphasizes personalized treatment based on individual body constitutions, known as Prakriti. In this paper, we present a hybrid machine learning approach for recommending Ayurvedic drugs, integrating traditional Prakriti assessment with modern symptom-based analysis. Using clustering and classification algorithms, the system analyzes patient symptoms and body constitution to generate personalized drug recommendations. This method avoids the computational complexity of deep learning, providing an interpretable, efficient, and scalable solution. Experimental results demonstrate the system's accuracy in identifying Dosha imbalances and its effectiveness in recommending appropriate treatments. © 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

Emotion Trajectories in Cinematic Narratives: A Transformer-Based Analysis 1

Emotion Trajectories in Cinematic Narratives: A Transformer-...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Sudabathula, Vijay Sai Kumar Naik, Banoth Krishna Mohan Ismail, Shifa Mattaparty, Sri Harsh Arora, Gagan Deep Yadav, Guda Sravan Vardhaman College of Engineering Department of Artificial Intelligence & Machine Learning Hyderabad India

ISBN: (纸本)9798350352931

This paper introduces a novel method for analyzing movie dialogues to predict characters' primary emotions and the overall emotional tone of a film. Using natural language processing, we assess dialogues across emotional dimensions such as happiness, sadness, anger, fear, and more. Our approach involves collecting and preprocessing movie scripts, followed by building emotion classification models. By examining the context, sentiment, and linguistic features of dialogues, we predict character emotions and aggregate them to map the emotional trajectory of the movie. Diverging from traditional rating prediction models, our method aligns emotional experiences from movie scripts with reviewer feedback for improved accuracy. We also propose a sentimentbased movie recommender system that matches users' emotions with film sentiments, offering a unique alternative to existing recommendation systems. Through extensive evaluation, our approach contributes to affective computing and provides deeper insights into the emotional structure of cinematic narratives. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence and machine learning in Telemedicine: Transforming Remote Healthcare

Artificial Intelligence and Machine Learning in Telemedicine...

引用

machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： Shrikant Khadse Prateek Verma Vivek Lande Faculty of Engineering and Technology Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research (Deemed to be University) Wardha India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The concept of telemedicine developed before the upsurge of popularisation of telehealth services, particularly with the support of artificial intelligence and machine learning. This review aims to deeply analyse how these technologies integrate and change telemedicine, improve the diagnostics of diseases, help in the treatment process, and provide more accessible healthcare. Predictive analytics, natural language processing, and tele-therapy monitoring are examples of the ML and A.I. technologies used in patient care management. This is the time of more intelligent and more effective remote care services with the help of several innovative technologies and phenomena like A.I. health chatbots and intelligent treatment algorithms. However, several factors limit its development, including data privacy, legal issues, and users' access to technologies. Directions for further development and continuous healthcare improvement include integrating advanced 5G communication systems and wearables and exploiting blockchain technology for data interchange. These developments create prospects to eliminate current impediments and enhance the provision of healthcare services worldwide. This scope consists of mechanisms for the best present data, emphasizing growth areas of new technologies, especially artificial intelligence and machine learning, that transform healthcare systems.

关键词： Data privacy Shape Reviews Telemedicine Medical services machine learning Transforms Prediction algorithms Predictive analytics Wearable devices

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence and machine learning in Telemedicine: Transforming Remote Healthcare 2

Artificial Intelligence and Machine Learning in Telemedicine...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Khadse, Shrikant Verma, Prateek Lande, Vivek Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research Deemed to be University Faculty of Engineering and Technology Wardha India Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research Deemed to be University Wardha India

ISBN: (纸本)9798331505745

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Developing an AI-Based Library Assistant: Enhancing Book Retrieval with Natural Language Processing and machine learning 2

Developing an AI-Based Library Assistant: Enhancing Book Ret...

引用

2nd International Conference on Computational intelligence, Communication Technology and Networking, CICTN 2025

作者： Kailash Varma, Nadimpalli Madana Aryan, Adla Dhanush, Pagilla Manikanta, Rangisetti Chandhu, Nalla Arora, Gagan Deep Department of Artificial Intelligence & Machine Learning Vardhaman College of Engineering Telangana Hyderabad501218 India

ISBN: (纸本)9798331530389

The current college library system is hindered by inefficiencies in book searching, availability updates, identity verification, and checkout processes, resulting in delays and errors that negatively impact student experiences. This research paper presents an Al-based librarian system designed to address these challenges through automation and digital transformation. Leveraging a Large Language Model (LLM), the proposed system facilitates personalized interactions between students and library resources. Upon student verification, the AI librarian provides real-time information on book availability, location, and tailored recommendations, significantly reducing the time spent on manual searches. The streamlined checkout process allows for automated book issuance and instant confirmation notifications, minimizing human error and enhancing record- keeping. This innovative solution not only improves operational efficiency but also enriches the user experience by offering a user-friendly interface and timely assistance. Future enhancements, such as voice integration and mobile application support, are suggested to further modernize library services. This research underscores the potential of AI technologies to revolutionize library management and improve service delivery in academic settings. © 2025 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Visionary Cardioscan: Heart Risk Detection through Retinal Imaging 3

Visionary Cardioscan: Heart Risk Detection through Retinal I...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Arun Kumar, S. Dharshini, B. Hemanth, M. Vignesh, S. Saratha, M. Department of Artificial Intelligence and Machine Learning M.Kumarasamy College of Engineering Karur India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

Heart attacks and hypertension are two cardiovascular disease risk factors that have a major impact on the microvascular system's structure and function. Fundus camera images can detect abnormalities in retinal blood vessels that indicate vascular injury. Using machine learning techniques, preclinical signs of damage, which may not be visible to an observer, can be detected. It proposes a system that uses retinal images to predict heart attack risk. The model leverages vessel segmentation to extract morphological details of retinal blood vessels. The results can assist in identifying heart disease early, especially in young patients. © 2025 IEEE.

关键词： Ophthalmology

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：