检索结果-内蒙古大学图书馆

Unmasking Frame Duplication: Comprehensive Approach to Detection in Digital Video Using Machine Learning Algorithms and Signal Processing Techniques

Unmasking Frame Duplication: Comprehensive Approach to Detec...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing systems, ADICS 2024

作者： Praddipraj, N.N. Praveen Kumar, B. Sreeji, S. Sathyabama Institute Of Science And Technology Dept. Of Computer Science And Engineering Tamilnadu Chennai600119 India

ISBN: (纸本)9798350364828

Our research proposes a comprehensive approach to identify duplicate frames in digital videos. It integrates machine learning and signal processing techniques for effective identification. The process begins with pre-processing, enhancing video quality through temporal filtering and noise reduction. Next, feature extraction captures statistical and structural information from each frame. Deep neural networks and other machine learning methods are used to classify frames as original or duplicated using these features. To enhance detection accuracy, signal processing methods like block-based and key point-based approaches are applied. Block-based methods divide frames into segments for region comparison, while key point-based methods identify and match key points between frames. Our method's effectiveness and robustness are demonstrated through experiments on various digital videos. This combination of machine learning and signal processing offers a comprehensive solution to uncover frame duplication, ensuring video content's integrity and authenticity. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Adaptive Video Streaming for Resource-Constrained UAVs through Dynamic Region-of-Interest Tile Swapping 10

Enhanced Adaptive Video Streaming for Resource-Constrained U...

引用

10th International Conference on Applied system Innovation, ICASI 2024

作者： Hsu, Tz-Heng Ju, Rui-Han Horng, Gwo-Jiun Southern Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350394924

Real-time video transmission via unmanned aerial vehicles (UAVs) is significantly impacted by latency issues. Using Region of Interest (ROI) tile segmentation methods, video streaming techniques can dynamically adjust the encoding bitrate, assign various priorities to distinct video tiles, and specify different quality quantization factors. High-efficiency video tile encoding techniques, combined with ROI-based streaming methods, can meet various Quality of Service (QoS) criteria. However, dynamically assigning quantization factors for different tiles has the disadvantage of increasing the encoding system's complexity. This study presents a method to dynamically swap ROI tiles to lower the complexity of the encoding system, making it suitable for UAVs with limited computational capacities. By adopting the proposed adaptive video streaming transmission method with tile-swapping strategy, it is feasible to enhance the visual quality in critical areas for resource-constrained UAV devices. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

LiDAR-Based Elderly Fall Detection system for Indoor Environments Using Neural Network Algorithms 4

LiDAR-Based Elderly Fall Detection System for Indoor Environ...

引用

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

作者： Vignesh, Puthucode Ganesh Nithin Kumar, S. Senthil Kumar, T. Jeyakumar, G. Amrita School of Computing Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798331523923

Fall detection systems are critical in elderly care and healthcare monitoring, but traditional camera-based solutions raise significant privacy concerns. This research presents a novel approach utilizing LiDAR (Light Detection and Ranging) sensors for fall detection in indoor environments, addressing privacy issues while maintaining high accuracy. We introduce LiFall, a new dataset captured using a Velodyne VLP 16 Puck LiDAR sensor, comprising 12 scenes and over 500 frames simulating various fall scenarios (including back falls, bed falls, and walking falls), contributing to the scarcity of LiDAR-based fall detection datasets. Our methodology employs two advanced deep learning architectures: Annularly Convolutional Neural Networks (ACNN) and Dynamic Graph Convolutional Neural Networks (DGCNN). Evaluating these models on both the ModelNet40 dataset and our custom LiFall dataset, results show DGCNN outperforms ACNN, achieving an accuracy of 84% on the ModelNet40 dataset with a 70:30 train-test split. On the LiFall dataset, despite challenges with dataset imbalance and achieving lower detection accuracy even after data augmentation, our approach demonstrates the potential of LiDAR-based fall detection systems. Compared to other fall detection methods, our LiDAR-based system offers significant advantages beyond privacy preservation, such as robust performance in low-light conditions and the ability to capture detailed 3D spatial information. While our current implementation is limited to laboratory settings, future work will focus on real-world deployments and further addressing dataset imbalance issues to enhance overall system performance. This research contributes to the field by providing a privacy-preserving, high-performance alternative to camera-based fall detection systems, paving the way for more acceptable monitoring solutions in sensitive indoor environments. © 2025 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

TotCareBot: A Comprehensive Approach Towards Enhancing Early Childhood Education through Robotics 5

TotCareBot: A Comprehensive Approach Towards Enhancing Early...

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Chougala, Manjula R Sushma, B. Bhayyar, Akshata S Bhandarkar, Abhay Pavithra, P.N. Ramaiah Institute of Technology Dept. of Computer Science and Engineering Bangalore India Ramaiah Institute of Technology Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798331528539

Robots have emerged as versatile tools with significant potential to enhance teaching and learning environments, including classrooms, laboratories, play homes, crèches, and even at home. Their engaging nature can captivate young children, boosting motivation and interest. This paper proposes a methodology for an Educational Robot (ER) designed for play homes. The ER is capable of moving around the classroom, monitoring children, analyzing their emotions, responding appropriately, and alerting the teacher when necessary. The proposed system aims to leverage the positive impact of expressive behaviors in robots, such as storytelling and pampering. Our findings indicate that expressive robot narration is as effective as that of a human displaying similar behaviors and even surpasses a static, inexpressive human narrator. Furthermore, the robot excels in conveying educational content, although its limited emotional expression slightly reduces its effectiveness in narrating emotionally rich stories. This research underscores the potential of ERs to create dynamic and interactive learning experiences for young children, fostering both their cognitive and emotional development. © 2024 IEEE.

关键词： Educational robots

来源：评论

学校读者我要写书评

暂无评论

Optimizing Web Server Performance: A Comparative Analysis of Central Manager and Round Robin Load Balancing Algorithms 4

Optimizing Web Server Performance: A Comparative Analysis of...

引用

4th International Conference on Electrical engineering and computer science, ICECOS 2024

作者： Permana Arrasyid, Fahmi Stiawan, Deris Afifah, Nurul Heryanto, Ahmad Azhar, Iman Saladin B. Bardadi, Ali Yudho Suprapto, Bhakti Pahendra Anto Saputra, Iwan Sriwijaya University COMNETS Rerearch Group Faculty of Camp. Science Palembang Indonesia Sriwijaya University Faculty of Comp. Science Computer Engineering Dept. Palembang Indonesia Sriwijaya University Faculty of Comp. Science Information System Dept. Palembang Indonesia Sriwijaya University Faculty of Engineering Electrical Engineering Dept. Palembang Indonesia

ISBN: (纸本)9798350368253

Central manager algorithm has a lower average throughput compared to the round robin algorithm. This is evidenced by a significant decrease in throughput values during measurements. Central manager algorithm provides a faster average response time than round robin algorithm, despite experiencing an increase in response time values over time. Central manager algorithm shows a higher request loss rate and many requests are not served. Under normal performance conditions, both algorithms yield the same average request loss rate, achieving stable values without failed requests. The central manager algorithm ensures relatively balanced resource availability, including CPU and memory usage, across each slave web server compared to the round robin algorithm. The results show that increasing the number of clients and client requests during system testing to better observe server resource availability and load distribution performance. For future research, it is recommended to increase the number of clients in the system testing to enhance server load and to introduce client request actions on the web server to further highlight resource availability on each web server. © 2024 IEEE.

关键词： Response time (computer systems)

来源：评论

学校读者我要写书评

暂无评论

Real-Time Network Monitoring: A Big Data Approach 14

Real-Time Network Monitoring: A Big Data Approach

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Jaswanth, Kunisetty Sruthi, S. Ramachandrula, Pranav Saravanan, S. Amrita School of Computing Dept. of Computer Science Engineering Bengaluru India Amrita School of Computing Dept. of Computer Science Engineering Chennai India

ISBN: (纸本)9798350335095

Real-time network monitoring is a critical requirement for tracking user activities and ensuring optimal network performance. In this paper, we propose a big data approach to real-time network monitoring that leverages the capabilities of Apache Spark, MongoDB, and Apache Kafka with Python. Our approach utilizes distributed stream processing of network data, enabling real-time analytics for user activity monitoring and network performance optimization. Our approach demonstrates the effectiveness of our system through experiments with real network traffic data, showing how it can identify and track user activities in real-time. Our system can be used by network administrators and IT professionals to optimize network performance, improve user experience, and enhance security through real-time monitoring and analysis of user activity data. This approach can also be opted as a feature in SDNs. © 2023 IEEE.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Fake Product Identification system 5

Fake Product Identification System

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Rajalakshmi, B. Jayashree, Ms. Dharan, Anushka Jain, Jainam Chavan, Shivswami Dept. of CSE New Horizon College of Engineering Bengaluru India Dept. Computer Science and Engineering New Horizon College of Engineering Bengaluru India

ISBN: (纸本)9798350361155

The largest issue facing the retail industry today is product counterfeiting. Products that are counterfeit are just poor copies of authentic brands. Various techniques have been implemented to fight product counterfeiting, including RFID tags, machine learning, artificial intelligence, QR code-base systems, and many more. However, these techniques have drawbacks as well. For example, a QR code can be used to distinguish a real product from a fake one, artificial intelligence and machine learning require a lot of processing power to perform tasks, and numerous other techniques have been adopted but no workable solution has yet been created. With the aid of blockchain technology, we have attempted to enhance the detection of counterfeit goods in this *** approach involves using a QR code to store the product supply chain at each stage of the product's transaction with a new party. One of the key benefits of blockchain is that once data is recorded in the system, it cannot be changed by anybody, making our data more secure and protected from outside parties. This makes blockchain useful for storing product supply chains since it creates a decentralized system. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A User-manageable Credential system based on Blockchain

引用

Transactions of the Korean Institute of Electrical Engineers 2022年第1期71卷 210-217页

作者： Hong, Seongho Kim, Heeyoul Dept. of Computer Science Engineering Kyonggi University Korea Republic of

Credentials are one of the most important things to prove oneself in modern society. As the world goes digital, credentials change its form from paper to digital. However, digital data are easy to be forged and to be duplicated. To make digital data secure, cryptographic digital signature is the key technology ensuring its authenticity and integrity. And it is an inevitable choice for secure credential management systems. Recently blockchain has been raised as another key technology to guarantee data transparency. It is a decentralized and public ledger of transactions that anyone can participate and execute programs called smart contract. In this paper, we propose a credential management system based on Ethereum blockchain. This system provides users with a means both to manage their credentials by themselves and to prove their credentials without the issuer. We implemented its prototype on Ethereum, and analyzed the proposed system compared to previous systems. © 2022 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Alzheimer's Disease Detection Using Deep Learning Techniques 12

EEG-Based Alzheimer's Disease Detection Using Deep Learning ...

引用

12th IEEE Region 10 Humanitarian Technology Conference, R10-HTC 2024

作者： Ancy, S.A. Panachakel, Jerrin Thomas College of Engineering Dept. of Computer Science and Engineering Trivandrum India College of Engineering Dept. of Electronics and Comm. Engg. Trivandrum India

ISBN: (纸本)9798350340204

Alzheimer's disease (AD) is a neurological condition characterized by the degeneration of neuron cells, leading to cognitive impairment. This project investigates the effectiveness of EEG-based features for detecting Alzheimer's Disease using deep learning techniques. The dataset comprises EEG recordings from healthy controls, Frontotemporal Dementia (FTD) patients, and patients diagnosed with AD. Data preprocessing involved segmenting the EEG signals into fixed-length epochs and filtering the baseline EEG into alpha, beta, and theta frequency bands. Features such as Mean Phase Coherence (MPC), Differential Entropy (DE), and Mean Squared Coherence (MSC) were computed pairwise for each epoch and frequency band. A feature matrix was constructed for each subject by stacking these features, which were then converted into images and used as input data for a ResNet50-based pre-trained model. The model was tested in leave-one-out cross-validation setting and achieved results comparable to the state-of-the-art in distinguishing between EEG recordings from healthy and AD-affected subjects. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Stroke Disease Using Machine Learning Algorithms 7

Classification and Prediction of Stroke Disease Using Machin...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Lahari, Podutur Kumar, Akarsh Nandini, D. Usha Praveena, M. D. Anto Selvan, Mercy Paul Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350372816

Using text mining tools and machine learning algorithms, the paper presents a prototype for classifying strokes. The significance of machine learning extends across various domains, including surveillance, medicine, and data management, where appropriately trained algorithms prove invaluable. The study incorporates data mining techniques, offering a comprehensive understanding of information tracking from both semantic and syntactic perspectives. By analyzing medical case sheets, the proposed approach extracts symptoms and trains the system based on that information. A total of 507 case sheets are collected at "Sugam Multispecialty Hospital"in "Kumbakonam", Tamil Nadu, India, during the data collection phase. A tagging and maximum entropy approach was used to mine these case sheets. Stroke classification relies heavily on the suggested stemmer for distinguishing between common and special features. To handle the data that has been processed, support vector machines, XG Boost algorithms, SGD algorithms, decision trees, and random forests were used as machine learning algorithms. Random Forest demonstrated the highest accuracy among stroke classification algorithms evaluated. This integration of text mining and machine learning offers a promising framework for enhancing stroke classification based on patients' symptoms extracted from medical case sheets. The synergy between these technologies provides a robust methodology that can contribute significantly to improving the efficiency and accuracy of stroke diagnosis and classification in a medical. © 2024 IEEE.

关键词： Semantics

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：