检索结果-内蒙古大学图书馆

Intelligent Control, Computing and Communications (IC3), International Conference on

作者： Jay Patil Suvarna Joshi Rahesha Mulla Kushal Yadav Department of Computer Science and Eng. MIT School of Computing MIT ADT University Pune India Department of Artificial Intelligence and Machine Learning Symbiosis Institute of Technology Symbiosis International (Deemed) University Pune India Department of Data Science Indian Institute of Technology Madras India

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

This paper introduces a cost-effective smart posture detection system aimed at promoting ergonomic sitting habits and preventing musculoskeletal disorders. The system integrates ultrasonic sensors for backrest proximity measurement and load cells for seat weight distribution analysis. By analyzing these inputs, it identifies posture irregularities and provides real-time feedback for corrective action. Testing results demonstrate the system's reliability, achieving a detection accuracy of 99% across users with varying body types and postures. The proposed hybrid approach ensures simplicity, affordability, and scalability, making it a viable solution for homes, workplaces, and schools. This research contributes to the growing field of smart health monitoring systems, offering a practical alternative to traditional posture correction methods.

关键词： Weight measurement Accuracy Ultrasonic variables measurement Ergonomics Real-time systems Acoustics Intelligent sensors Monitoring Wearable sensors Testing

来源：评论

学校读者我要写书评

暂无评论

AI- Powered Emotion Recognition: A Multimodal Approach to Analyzing Human Sentiment

AI- Powered Emotion Recognition: A Multimodal Approach to An...

引用

Visual Analytics and Data Visualization (ICVADV), International Conference on

作者： Shalma H Shreya Mukherjee Jainulabudeen S A K Borra Surya Thirumal Reddy Bhanu Budhati Nakka Shiva Krishna Department of Artificial Intelligence and Machine Learning Sphoorthy Engineering College Nadergul Hyderabad Department of Computer Science and Engineering College of Engineering and Technology Anna University Chennai Tamil Nadu India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

AI-Powered Emotion Recognition: A Multimodal Approach to Analyzing Human Sentiment, we develop an advanced emotion detection system using cutting-edge AI techniques. By leveraging attention-based models, the system effectively analyzes and integrates multiple modalities, including facial expressions, voice tone, and textual sentiment, to deliver an accurate and nuanced understanding of human emotions. Attention mechanisms allow the model to focus on the most significant features across these modalities, capturing tiny emotional cues that may otherwise be overlooked. This multimodal approach not only enhances the accuracy of emotion detection but also improves engagement analysis, making it particularly suited for applications in mental health, education, customer service, and human-robot interaction. Through this project, we aim to showcase the power of AI in providing a more empathetic and emotionally- aware interface, pushing the boundaries of intelligent systems in understanding complexhuman sentiment

关键词： Emotion recognition Accuracy Attention mechanisms Customer services Visual analytics Scalability Education Mental health Speech recognition Robustness

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Hybrid Smart Parking: Optimizing Parking Management Across Diverse Applications in Smart Cities

引用

Procedia Computer science 2025年 258卷 1524-1535页

作者： Shalini M.K. Hanumanthappa J. K.S. Santhosh Kumar S.P. Shiva Prakash Department of Computer Science Sheshadripuram college Bangalore karnataka and 560020 India Department of Studies in Computer Science Manasagangothri Campus University of Mysore Mysuru karnataka and 570006 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering Manasagangothri Campus University of Mysore Mysuru karnataka and 570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru karnataka and 570006 India

An Artificial Intelligence (AI) powered hybrid smart parking system optimizes parking allocation across various applications, including smart hospitals, colleges, offices, and shopping malls. The system uses AI and IoT technologies to enhance the user experience, streamline operations, and improve efficiency. It dynamically allocates parking spaces based on real-time demand, user preferences, and contextual factors. The system accurately predicts parking demand, optimizes space allocation and provides personalized recommendations, reducing congestion and waiting times. The hybrid smart parking algorithm combines machine learning techniques with domain-specific insights to prioritize parking allocation in diverse environments. The study emphasizes the importance of leveraging advanced technologies to address complex urban challenges, such as parking management, and aims to pave the way for sustainable, efficient, and user-centric parking solutions in smart cities. and Random Forest with an overall average score of 0.9400. Machine learning has become crucial for optimizing parking management systems, especially in densely populated cities. To address this challenge, advanced predictive models have been developed to anticipate parking duration based on slot availability, peak hours, and traffic conditions. The Random Forest model outperforms Logistic Regression, Random Forest, and K-Nearest Neighbors in predicting parking length, achieving high accuracy and performance metrics. It maintains user satisfaction and low operational costs, making it a recommended system for further implementation in parking management tasks. The classification report shows a respectable performance with 50% accuracy and a good recall for open slots. The optimization procedure was effective and did not reveal any notable areas for improvement. The optimized route (Slot2, Slot1, Slot3) provides an efficient parking sequence, with high accuracy (95%), good user satisfaction (90%) and suitabili

关键词： Artificial Intelligence Smart Parking: Smart city Machine learning Smart Applications

来源：评论

学校读者我要写书评

暂无评论

Terminal-based method for efficient inter-turn fault localization and severity assessment in transformer windings

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2025年 12卷

作者： Lakshmi Prasanna, K. Samal, Manoj Mondal, Mithun Working Integrated Learning Programmes Birla Institute of Technology and Science Pilani Telangana Hyderabad India Electrical & Electronics Engineering Department Birla Institute of Technology & Science Pilani Telangana Hyderabad India

Early detection of Inter-Turn Fault (ITF) in power transformers is crucial for preventing extensive damage to the windings. However the existing methods based on calculation of fault factors, machine learning methods, and statistical indices require additional terminals or internal tap points, extensive training data and high computational demands, and limited applicability due to non-standardization and specific frequency band selection. To overcome these limitations, this paper presents a novel, non-invasive method for identifying the location and severity of ITFs using only external terminal measurements. Our approach leverages a non-iterative subspace identification algorithm to estimate the pole-zero-gain model from the measured Driving Point Impedance (DPI) frequency response, Z_f(s), of a faulty transformer. By solving a matrix equation involving gain, K, series capacitance (C_s), and ground capacitance (C_g), we determine the faulty capacitance, C_f for each winding section. The fault location is then identified by correlating the measured and estimated DPIs, with the section exhibiting the maximum correlation being deemed the faulty disc and its corresponding C_f is the faulty capacitance. This approach accurately identifies the faulty disc and determines the extent of insulation damage caused by the ITF, as validated through simulation and experimental results on various winding types. It paves the way for a more efficient and reliable diagnostic solution. © 2025 The Authors

关键词： Capacitances Fault localization Frequency response analysis Inter-turn fault Power transformer Windings

来源：评论

学校读者我要写书评

暂无评论

IoT-based Efficient Waste Management on University Campus : Enhancing Monitoring and Optimization through Machine learning

引用

Procedia Computer science 2025年 258卷 4157-4168页

作者： Sumathi M. Hanumanthappa J. K.S. Santhosh Kumar S.P. Shiva Prakash Meghana J. Department of Studies in Computer Science Manasagangothri Campus University of Mysore Mysuru Karnataka 570006 India Department of Artificial Intelligence and Machine Learning Mysore University School of Engineering Manasagangothri Campus University of Mysore Mysuru Karnataka 570006 India Department of Information Science and Engineering & Computer Science and Business Systems JSS Science and Technology University Mysuru Karnataka 570006 India Department of Computer Science Mahajana Post Graduate Center Mysuru Karnataka 570016 India

The introduction of an IoT-based smart waste management system is proposed to optimize various aspects of university campus waste recycle management processes, such as garbage collection scheduling, waste type identification, and collection routes. This system utilizes advanced data analytics algorithms, wireless communication protocols, and sensors to measure and document variations in trash levels, enabling real-time monitoring of waste accumulation. Through this IoT-based infrastructure, university administrators and waste management staff gain fine-grained visibility and control over garbage collection processes. The implications for sustainability advocacy and environmental stewardship in academic environments are significant. By fostering a culture of environmental awareness and accountability, universities can instill ideals of conservation and resourcefulness in their student populations and staff. The proposed IoT-enabled waste bin system exemplifies the synergy between technological innovation and environmental responsibility, serving as a model for institutions worldwide. Collaboration among universities can leverage IoT technology to drive positive change, mitigate environmental degradation, and promote sustainable practices beyond campus boundaries. Efficient waste management is crucial for nurturing sustainability on college and university campuses, as evidenced by the urgent need for the collection and recycling of compost, general waste, and recyclables. Our models consistently achieve high performance, with perfect scores (1.000) across all split ratios, indicating flawless classification of waste types. Although the Artificial Neural Network (ANN) demonstrates slightly lower accuracy, ranging from 0.973 to 0.997 depending on data splits, it still performs well. As a result, Naive Bayes produces less accurate results, typically surpassing 0.93 but falling short of Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM)’s flawless

关键词： Artificial Intelligence Smart Parking: Smart city Machine learning Smart Applications

来源：评论

学校读者我要写书评

暂无评论

Precision Land Use and Land Cover Mapping with a High-Accuracy Time Series LSTM Model

Precision Land Use and Land Cover Mapping with a High-Accura...

引用

IEEE Students' Conference on Electrical, Electronics and Computer science (SCEECS)

作者： Adla Aryan Prakash RV Srinivas Aluvala Venigalla Shashank Chowdary Department of Artificial Intelligence & Machine Learning Ardhaman College of Engineering Hyderabad Telangana India Department of Computer Science & Artificial Intelligence SR University Warangal Telangana India Department of Computer Science and Engineering (Data Science) Rajeev Gandhi Memorial College of Engineering and Technology Nandyal India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

This paper introduces a machine-learning-based LULC classifying model developed with a time series data set, trained on a diverse set of agriculture and non-agricultural classes. It used a strong generalization capability employing an LSTM architecture; that is, it achieved accuracy of 90.04% in training and also validation accuracy of 90.55%. The ultimate accuracy was obtained at the minimal loss of 0.1909 at the accuracy of 95.58%, thereby validating its usability for LULC pattern classification. This model has a wide-range of potential application in environmental monitoring and resource management. Future work involves introducing more variables into the dataset, the inclusion of other environmental factors, and fine-tuning of the model towards more general applications in geospatial applications. Thus, this work advances the current state of remote sensing and LULC classification to present an effective tool in sustainable land management.

关键词： Deep learning Accuracy Image processing Time series analysis Land surface Spatial databases Environmental monitoring Resource management Remote sensing Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Observing black hole phase transitions in extended phase space and holographic thermodynamics approaches from optical features

引用

European Physical Journal C 2025年第5期85卷 484-484页

作者： Promsiri, Chatchai Horinouchi, Weerawit Hirunsirisawat, Ekapong Faculty of Science King Mongkut’s University of Technology Thonburi Bangkok10140 Thailand High Energy Physics Research Unit Department of Physics Faculty of Science Chulalongkorn University Bangkok10330 Thailand Learning Institute King Mongkut’s University of Technology Thonburi Bangkok10140 Thailand

The phase transitions of charged Anti-de Sitter (AdS) black holes are characterized by studying null geodesics in the vicinity of the critical curve of photon trajectories around black holes as well as their optical appearance as the black hole images. In the present work, the critical parameters including the orbital half-period τ, the angular Lyapunov exponent λL, and the temporal Lyapunov exponent γL are employed to characterize black hole phase transitions within both the extended phase space and holographic thermodynamics frameworks. Under certain conditions, we observe multi-valued function behaviors of these parameters as functions of bulk pressure and temperature in the respective approaches. We propose that τ,λL, and γL can serve as order parameters due to their discontinuous changes at first-order phase transitions. To validate this, we provide detailed analytical calculations demonstrating that these optical critical parameters follow scaling behavior near the critical phase transition point. Notably, the critical exponents for these parameters are found to be 1/2, consistent with those of the van der Waals fluid. Our findings suggest that static and distant observers can study black hole thermodynamics by analyzing the images of regions around the black holes. © The Author(s) 2025.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation System Using Hybrid Based Method

Movie Recommendation System Using Hybrid Based Method

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Kamble, Khushi Bhadarge, Pradnyanand Bhakte, Shreejit Kulkarni, Omkaresh Kadam, Rutuja Pinjarkar, Latika Vishwakarma Institute of Information Technology Computer Science and Engineering - Artificial Intelligence and Machine Learning Department Pune India Maharashtra Pune India Nagpur Campus Pune India

ISBN: (纸本)9798331542375

The rise of digital platforms has increased user engagement and satisfaction through personalized recommendation systems. The research paper presents a hybrid approach to movie recommendation, which uses content-based filtering and collaborative filtering techniques to mitigate the cold start problem, data sparsity, and scalability issues. The proposed system will utilize methodologies from machine learning, such as cosine similarity and vectorization, and the K-Nearest Neighbors (KNN) algorithm, for recommending movies based on their precise and personalized values. The dataset TMDB5000 will then be used for two datasets involving movie features, cast, and crew information while preprocessing techniques in cleaning, feature extraction, and merging are undertaken to ensure robust foundation for the model building. The hybrid model uses the bag-of-words technique to vectorize and compute cosine similarity to determine movies' relationships in a multidimensional space. The KNN algorithm then refines the collaborative filtering process by the clustering of user preferences and makes recommendations using nearest-neighbor analysis. Our current approach overcomes these weaknesses by combining both content-based and collaborative methods, resulting in a system which handles diverse user preferences while maintaining high recommendation accuracy. As the evaluation of precision, recall, F1-score, and mean squared errors further validates that this system performance is good and also scalable and efficient for processing large datasets for which it explains some practical aspects related to implementation in real time. The future work includes deep learning models like neural collaborative filtering to further improve semantic understanding and recommendation accuracy. This paper addresses the current system's limitations by proposing a novel, efficient, and user-centric hybrid approach, which can be extended to other domains, such as e-commerce, music, and book recommendati

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Prognostication in Colorectal Cancer with Integrated Machine learning for Improved Survival Prediction

Enhancing Prognostication in Colorectal Cancer with Integrat...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： R Velmurugan K Suresh T Thilagaraj Meenakshi Sharma D. Saranya Department of Computer Science (PG) Kristu Jayanti College Autonomous Bangalore India Department of Computer Science Christ (Deemed to be University) Bangalore India Department of Artificial Intelligence and Machine Learning Moodlakatte Institute of Technology Kundapura Karnataka India Computer Science and Engineering Global Group of Institutes Amritsar Punjab Department of Information Technology Sri Eshwar College of Engineering Coimbatore

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Machine learning methods are recently used to predict patient survival in colorectal cancer using such models as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), VGG16, and Support Vector Machines (SVM). Taking advantage of a combination of CT, MRI scan images, and clinical records with drug recommendations, the study also checks to see how these models compare for distinguishing between patients in terms of their illness course-whether they are going to get better or worse over time. The results reveal VGG16 has better accuracy than CNN, RNN and SVM; as the highest-performing model tested, it also demonstrates superior precision, recall and F1-score. The research findings also validate these proposed models as they compare favorably with existing literature. This presents a promising proposition: a new, revolutionary approach to using artificial intelligence to boost prognostic accuracy.

关键词： Support vector machines Drugs Recurrent neural networks Accuracy Magnetic resonance imaging Computed tomography Machine learning Colorectal cancer Predictive models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Smart Emergency Management System Using Raspberry Pi Pico, GPS and GSM Modules 4

Smart Emergency Management System Using Raspberry Pi Pico, G...

引用

4th International Conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Govinda Rajulu, G. Sharmila, L. Venkatesan, D. Soumya, E. Prakash, Sargu Chandra Priyanka, Ms. P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Avadi Department of Computer Science and Engineering Tamil Nadu Chennai India St. Martin's Engineeringollege Dept. of Artificial Intelligence and Machine Learning Telangana Dhulapally Secunderabad India St. Martin's Engineeringollege Deptarment of Cse Telangana Dhulapally Secunderabad India Telangana Dhulapally Secunderabad India

ISBN: (纸本)9798331523923

This paper proposes a GSM-based children's rescue system designed for earthquake emergencies, emphasizing cost-effectiveness and simplicity while ensuring rapid child rescue. The system operates in three key stages: data acquisition, classification, and alert notification. Sensors collect temperature, pH, and heart rate data, which are then digitized and classified to assess the child's condition. If abnormal values are detected, an alert notification is sent via GSM to parents and rescue teams, providing real-time location data through GPS. The hardware implementation, based on Raspberry Pi, converts analog sensor signals into digital data for processing. The system's efficacy is validated through various scenarios, demonstrating its ability to detect critical conditions and promptly trigger alerts, enhancing child safety during disasters. © 2025 IEEE.

关键词： Earthquakes

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：