检索结果-内蒙古大学图书馆

2nd International Conference on Pervasive Computing Advances and applications, PerCAA 2024

作者： Vishal Dutt, Krishan Srivastava, Animesh Dutta, Neha Bali, Milan Deep Kaur Komal School of Computer Applications Lovely Professional University Punjab Jalandhar India Department of Computer Science & Engineering Graphic Era Hill University Dehradun India Department of Computer Science & Engineering Chandigarh University Chandigarh India Department of Computer Science & Engineering Chandigarh Group of Colleges Janjheri India

ISBN: (纸本)9781837242627

Key distribution in sensor nodes is one of most complex process to create a secure network. There are many innovations used for secure key distribution among the nodes. But main constraints come in computation, storage and mutual authentication using heavy communication protocols. problem exist in decision for generation and distribution of keys. Master nodes have large key pools, still problem exists in selection and distribution of key rings among large number of nodes in particular deployment areas. Dynamic deployment and revocation of keys is fundamental problem that exit in network. © The Institution of Engineering & Technology 2024.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Approach of Cluster-Based Topic Modeling for Effective Tweet Hashtag Recommendation

引用

SN computer science 2024年第7期5卷 951页

作者： Pattanayak, Pradipta Kumar Tripathy, Rudra M. Padhy, Sudarsan Research Scholar BPUT(Rourkela) Department of Computer Science and Engineering Silicon University Patia Odisha Bhubaneswar 751024 India School of Computer Science and Engineering XIM University Harirajpur Odisha Bhubaneswar 752050 India Institute of Mathematics and Applications Andharua Odisha Bhubaneswar 751029 India

Twitter has emerged as a significant source of data to be used for text summarization, Topic Modeling, document clustering, information retrieval, sentiment analysis, etc. Using hashtags, Twitter users may categorize their tweets as hashtags provide the essential meta-information in connecting tweets to the underlying themes. However, the majority of tweets do not have hashtags, which makes it challenging to search for a particular theme. The proposed model is designed to recommend appropriate hashtags for tweets by considering their categorization into sports, politics, health, or technology. In this paper, we proposed a novel heuristic for recommending hashtags of tweets. Taking 20,000 tweets, which includes 5000 tweets from each of the specified four topics along with their respective hashtags. These hashtags were manually assigned by a group of experts, which were subsequently excluded during the topic modeling process. The basic data-cleaning technique is applied to clean and tokenize the tweets. Then Word2Vec technique is used to vectorize the tokens which captured the semantic meaning of the words in the tweets and overcomes the data sparsity issues. The dimension of the data is reduced using Singular Value Decomposition (SVD) followed by t-SNE (t-distributed Stochastic Neighbor Embedding). The reduced data is divided into four clusters and a semi-supervised method is introduced to link these clusters to the aforementioned topics, which eventually helped to produce the hashtag for a list of tweets. On comparison of our results with existing techniques, it is observed that our model performance is better with respect to the metrics: precision, recall, and F1-score. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Gibbs sampling Dirichlet mixture model Linear Dirchlet allocation Singular value decomposition Topic modeling Word2Vec

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Object Detection in Underwater Environments

Deep Learning Techniques for Object Detection in Underwater ...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Praveen, R.V.S. Maindola, Meenakshi Anandhi, R.J. Thandra, Nagarjuna Bansal, Saloni Sharma, Vishal LTIMindtree Limited Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India New Horizon College of Engineering Department of Information Science Engineering Bangalore India MLR Institute of Technology Dept. Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India Lovely Professional University Phagwara India

ISBN: (纸本)9798331512965

The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. applications like marine research, environmental monitoring, and autonomous underwater vehicles (AUVs) are restricted in their effectiveness by traditional image processing techniques, which often struggle with these complexities. Recent years have seen the rise of deep learning techniques as a potent weapon in the fight against these obstacles. In order to accurately detect objects underwater, this paper investigates the use of deep learning models, specifically convolutional neural networks (CNNs). We explore cutting-edge models and methods like attention mechanisms, transfer learning, and hybrid deep learning architectures to improve detection performance in challenging underwater environments. Furthermore, we utilize data augmentation techniques and synthetic dataset generation to tackle the critical issue of limited labeled underwater datasets. From a detection accuracy and robustness perspective, the experimental results show that our suggested deep learning method is light years ahead of the competition. Marine exploration, autonomous underwater vehicle navigation, and underwater surveillance systems can all benefit from this study's new insights into how to better detect objects in real time while submerged. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Object Detection in Real-Time Surveillance Using Deep Learning-Based YOLO Framework

Object Detection in Real-Time Surveillance Using Deep Learni...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Kukreti, Sanjeev Praveen, R.V.S. Bansal, Saloni Raju, Hemanth Singh, Navdeep Begum, Rowsonara Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India LTIMindtree Limited Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Lovely Professional University Phagwara India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798331512965

The continual growth of the computer vision and artificial intelligence fields overtime have provided the basis for more efficient and accurate surveillance. This paper examines the use of YOLO, a deep learning model that is used in the detection of objects, for use in real-time surveillance systems. The added benefits of identifying and labeling multiple objects in a single pass forward makes YOLO ideal for real-time surveillance. Unlike other approaches to object detection such as region-based methods or methods with multiple stages of detection, YOLO cast object detection as a regression problem where boxes and class probabilities are predicted jointly. This leads to a far improved performance when compared with their slower counterparts without the sacrifice of precision. In this work, the YOLO model is finetuned on a large database of surveillance videos to improve object detection at low lighting and in the presence of occlusion and crowding. The developed system has a high detection speed and accuracy;the application areas will include uses such as security inspection, traffic regulation, and anomaly detection. This is done to affirm that using YOLO is more efficient and faster than the other object detection algorithms in real-time surveillance tasks. The results indicate directions for further improvements to guarantee public safety and improve efficient surveillance systems. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Predicting the Emergence of Hyperglycaemia through the Application of Machine Learning Methodologies 5

Predicting the Emergence of Hyperglycaemia through the Appli...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Pattnayak, Parthasarathi Patnaik, Sanghamitra Gourisaria, Mahendra Kumar Singh, Satyendr Goje, Nitin S. Patra, Sudhansu Shekhar KIIT Deemed to be University School of Computer Applications Bhubaneswar India KIIT Deemed to be University School of Law Bhubaneswar India KIIT Deemed to be University School of Computer Engineering Bhubaneswar India BML Munjal University Computer Science & Engg Department Gurugram India Webster University Computer and Information Sciences Department Tashkent Uzbekistan

ISBN: (纸本)9798350367171

Hyperglycaemia is a lifelong digestive condition that causes excessive blood sugar levels. Early detection along with treatment can avoid or prolong the problems in their beginning. Earlier studies have used machine learning to predict pathology. This study suggests that an artificially intelligent neural network could be a beneficial tool for managing and preventing diabetes. Hyperglycaemia can lead to both acute and chronic consequences, including fatalities. Chronic problems can lead to various impairments and organ deterioration. Failure to provide comprehensive remedies and preventions for diabetes patients can result in increased medical costs and a reduction in society's overall quality of life. Eight subject parameters were examined in this study: age, body mass index, plasma glucose level, insulin level, diastolic blood pressure, sebum thickness, pregnancies' number, and diabetes pedigree function. This study used to build neural network models and assess their accuracy in predicting diabetes. Results showed that some models performed better than others. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

IoT Based Smart Home Using Virtual Key 1

IoT Based Smart Home Using Virtual Key

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Edna Elizabeth, N. Jeffrey Isaac, S. Janit, Sophia Sri Sivasubramaniya Nadar College of Engineering Kalavakkam Department of Electronics and Communication Chennai India Hindustan Institute of Technology and Science Department of Computer Applications Chennai India

ISBN: (纸本)9798350367003

In this comprehensive documentation, we embark on an enlightening journey into the dynamic realm of Internet of Things (IoT) home automation. From the seamless integration of smart devices to the complex orchestration of automated processes, IoT home automation redefines the very essence of domesticity. We explore the landscape of cutting-edge advancements, delving into the intricate interplay of sensors, actuators and connectivity protocols that underpin the functionality of smart homes. Furthermore, we delve into the practical applications of IoT in various aspects of home management. This includes optimizing the energy efficiency, monitoring the environment, controlling personalized comfort and enhancing security measures. As we navigate through real-world case studies and exemplary implementations, we gain invaluable insights into the practical challenges and opportunities inherent in deploying IoT solutions within residential settings. In our proposed work, we have developed a prototype for a smart IoT-based smart home to control and monitor various systems such as light, lamp, socket and fan using ESP32 controller. The various controls are performed through relays. The data are sent to the firebase cloud through Wi-Fi and stored in the cloud. Later, the appliances are switched ON/OFF through virtual key using mobile APP. By using virtual keys, we address pertinent ethical and privacy considerations, shedding light on the importance of responsible data stewardship and robust cybersecurity measures. These are crucial in safeguarding the integrity of smart home ecosystems. By combining theoretical frameworks with empirical observations, we aim to provide a comprehensive understanding of IoT home automation. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Enhanced Monitoring and Security Measures with Video Analysis

Enhanced Monitoring and Security Measures with Video Analysi...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Jyothi, V. Esther Rakesh, G. Aruna, Vipparla Gorintla, Shobana Ayyappa, Yalanati Naidu, U. Ganesh Velagapudi Ramakrishna Siddhartha Engineering College Deemed to be University Department of Computer Applications A.P. Vijayawada India Department of Computer Science and Engineering Pothavarapadu A.P India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Avadi India B V Raju Institute of Technology Telangana Narsapur India

ISBN: (纸本)9798331509828

In modern surveillance, activities have increasingly become dependent on the continuous observation offered by CCTV systems. Still, with massive amounts of video data generated in a minute, sifting through this information manually to pick up any anomalies would be extremely burdensome and nearly impossible without significant human labor and vigilant watchfulness. CNN and CLIP models changed everything with regards to the working of surveillance systems. It makes use of CNN's capability for video frame processing and analysis to detect and classify these activities in the frames as either normal or suspicious. At the same time, it improves this by adding the CLIP model's capability of understanding textual descriptions and visual content together for better nuance detection in suspicious activities. This methodology transforms video surveillance by breaking video streams into frames and analyzing the behavior and interactions of persons in those frames. The synergy of CNN and CLIP models not only ensures real-time, efficient, and accurate surveillance but also minimizes dependency on extensive manual labor for monitoring. This paper aims to provide a contribution toward developing better security infrastructures in public spaces, transportation hubs, and private facilities. The introduction of this anomaly-detection mechanism can hugely improve the capability of implemented surveillance systems with a proactive response based on real-time detection and response capabilities against suspicious activities. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Management for Electric Vehicles: Fuzzy Logic and Neural Network Integration 10

Intelligent Energy Management for Electric Vehicles: Fuzzy L...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Thirumalaikumari, T. Princy, D. Lita Uma, S. Sadaieswaran, R. Malathi, P. Legapriyadharshini, N. Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Science Tamil Nadu Chennai India Meenakshi College of Engineering Department of Master of Computer Applications Tamil Nadu Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science Engineering Tamil Nadu Mahabalipuram India Tagore College of arts and science Department of Computer Applications Chennai Chromepet India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Data Analytics Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Application Tamil Nadu Chennai India

ISBN: (纸本)9798350384369

This study suggests a novel methodology for intelligent energy management in electric vehicles (EVs) through the integration of neural networks and fuzzy logic. Achieving enhanced energy efficiency for electric vehicles is a critical concern that is tackled in this research through the integration of neural networks' decision-making and pattern recognition functionalities with fuzzy logic's adaptability and learning capabilities. The proposed method seeks to optimize energy consumption, enhance overall performance, and extend driving range. The integrated system is subjected to rigorous testing using a meticulously planned experimental setup and simulation environment, which enables it to surpass the performance of more conventional approaches to energy management. The results emphasize the potential of the novel methodology to improve environmentally sustainable transportation options and propel the development of electric vehicle technology. This study not only offers valuable insights into efficient energy management but also establishes the groundwork for subsequent developments in the domain. © 2024 IEEE.

关键词： Electric Mobility Electric Vehicles Energy Management Intelligent Systems Neural Networks Smart Grid

来源：评论

学校读者我要写书评

暂无评论

Adult Obesity Prediction with Ensemble Classification Techniques - A Deep Learning Strategy 2

Adult Obesity Prediction with Ensemble Classification Techni...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Karthikeyan, S. Muthukumaravel, A. Department of Computer Applications Bharath Institute of Higher Education and Research Chennai India Department of Arts and Science Bharath Institute of Higher Education and Research Chennai India

ISBN: (纸本)9798331504960

The development of precise prediction models for early intervention is of the utmost importance due to the significant public health issue of the increasing prevalence of adult obesity. The study introduces an innovative approach for adult obesity prediction using deep learning and ensemble classification techniques. The current proposed approach is trying to overcome previous approaches in terms of robustness and accuracy. Normally, the proposed method is improving the prediction in performance by collecting various classifiers into one framework based on deep learning. Several classifiers are considered here, such as decision trees, SVMs, k-nearest neighbors. The system employs dynamic weighting modification scheme that optimizes input from every classifier within the training phase. On such a large dataset, experiments indicate that the proposed model is much more reliable and accurate compared to standard single-model methods for adult obesity prediction. These results showed that public health professionals may benefit from the ensemble learning that improves obesity prediction with a potential accuracy of 86.7% in monitoring populations and responding promptly, when necessary. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

PODX: A Comprehensive Framework for Detecting Prohibited Items in Security X-Rays 9

PODX: A Comprehensive Framework for Detecting Prohibited Ite...

引用

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

作者： Shivane, Ashwini S. Bhoite, Sachin Indira College Of Commerce & Science Tathawade Pune India Dr. Vishwanath Karad Mit World Peace University Department Of Computer Science & Applications Pune India

ISBN: (纸本)9798350377972

The increasing need for accurate and reliable detection of prohibited items such as guns, knives, and pliers in X-ray security images underscores the importance of advanced frameworks to enhance security screening processes. This study introduces Prohibited Object Detection in X-rays (PODX), a comprehensive two-stage framework aimed at improving detection capabilities through advanced feature extraction and classification techniques. The framework employs a two-stage approach: in the first stage, three convolutional neural network (CNN) architectures-ResNet, GoogLeNet, and DenseNet-are utilized to extract features, which are further refined using LASSO (Least Absolute Shrinkage and Selection Operator) regression to select the most significant features for classification. In the second stage, multiple machine learning algorithms, including Random Forests, Gradient Boosting, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN), are implemented to classify prohibited items based on the refined features. The performance of these algorithms is evaluated using metrics such as train accuracy and test accuracy, providing a comprehensive assessment of their strengths and weaknesses. The PODX framework not only enhances the accuracy and reliability of detecting prohibited items in security applications but also offers valuable insights into the comparative effectiveness of various classification techniques in X-ray image analysis. © 2024 IEEE.

关键词： Random forests

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：