检索结果-内蒙古大学图书馆

Towards Optimized Physical Activity: A Fusion of Graph Convolutional Networks and XGBoost for Exercise Analysis

Towards Optimized Physical Activity: A Fusion of Graph Convo...

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Kishan, V. Rajesh, M. Dhanush, B. Vincent, Rajiv School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai India

ISBN: (纸本)9798350378177

This research explores the implementation of the GCN-XGBoost with attention mechanism within the detection and correction of exercises through computer vision, utilizing the 2-dimensional pose coordinates from the MMFit [1] dataset. The objective is to enhance the precision and reliability of squat performance analysis, leveraging the robust, scalable machine learning capabilities of XGBoost. By processing and analyzing two-dimensional skeletal data, the study aims to identify key postural deviations and provide corrective feedback in realtime, potentially reducing the risk of injury and improving overall exercise effectiveness. Initial results demonstrate the model's capability to discern between correct and incorrect exercise forms with high accuracy, indicating the feasibility of applying advanced machine learning techniques to personal fitness and rehabilitation contexts. This paper details the methodology, from data preprocessing to model training and evaluation, highlighting the contributions to the fields of sports science and machine learning in physical activity monitoring. We have used MMFit dataset for the model that we have trained. We use the 2D coordinates of 18 of the 33 joints in the human body as the main features to categorize various exercises and forecast the accuracy of the poses identified by the Google's AI framework MediaPipe [2]. In this paper, we first classify an individual's exercises (squats, lunges, bicep curls, situps, pushups, triceps extensions, dumbbell rows, jumping jacks, dumbbell shoulder press, lateral shoulder raises) and check whether the pose associated with an exercise is correct. The final model trained has a 98% final validation accuracy. © 2024 IEEE.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Classification and Localization Model using DTCWT and ANN-BPN 5

Lung Cancer Classification and Localization Model using DTCW...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Siva Priya, M.S. Manivannan, KiranKumar Vivekanandan, M. Saranya, G. School of Computer Science and Engineering Vellore Institute of Technology Chennai campus India School of Electronics Engineering Vellore Institute of Technology Chennai campus India

ISBN: (纸本)9798350379945

Early and accurate lung cancer detection is crucial for improved patient outcomes. This research proposes a hybrid framework combining traditional image processing techniques and machine learning for enhanced lung cancer diagnosis. By leveraging CT images, the system employs DTCWT and GLCM for feature extraction, followed by ANN-BPN for classification. Fuzzy clustering is utilized for malignant tissue localization. The proposed approach demonstrates superior performance in terms of accuracy, precision, and F1-score compared to conventional methods. This hybrid model offers a promising tool for assisting radiologists in lung cancer diagnosis. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Navigating Uncontrolled Terrains: Integrating Heuristic Search-Based Path Planning Alogrithms 2

Navigating Uncontrolled Terrains: Integrating Heuristic Sear...

引用

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Maniar, Parshva Garg, Kushagra Veer Chopra, Nikkhil Krishnamoorthy, A. Vellore Institute of Technology School of Computer Science & Engineering Tamil Nadu India

ISBN: (纸本)9798350368109

If you are working on autonomous systems such as drones, robots, or self-driving cars that have to navigate through an unknown environment, you will at some point face the peculiar problem of path planning. In this study, the quality star algorithm is proposed, which has the advantages of a more compact and adaptable system that can solve path query problems more flexibly in the region that is known at any time. D Star, on the other hand, is able to adapt to the environment and is ideal for situations when the terrain is uncertain. To evaluate its performance, we consider it with respect to search space approximation, time complexity, completeness, and adaptability. The results show that this method is efficient for autonomous navigation over unknown terrain, proving the versatility and large-scale scalability of the proposed solution for a large number of autonomous robotic applications. Autonomous systems are fast becoming a crucial cornerstone of the future of many industries - bringing with them the benefits of both innovation and efficiency. But this opens up a whole host of new problems when it comes to traveling across uncontrolled environments. Classical algorithms, such as Dijkstra, perform fine on tidy, predictable terrain but can easily be outsmarted on rough landscapes. Above study: Navigating Uncontrolled Terrains: Integrating Heuristic Search-Based Path Planning Algorithms. The main idea is to design an algorithm that is capable of giving the best performance in any situation. In addition, the dynamic modifiability of the system also allows for agile and efficient response to unexpected hurdles! If successful, the study could also serve as an application-proof complement to theory and provide pragmatic insights for furthering the development of autonomous navigation technology. © 2024 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Quantum-Enhanced Spiking Neural Networks for Closed-Loop Neuromodulation Systems: A Theoretically Advanced Framework

Quantum-Enhanced Spiking Neural Networks for Closed-Loop Neu...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Ashar, Vallari Bansal, Sarthak Pandiyaraju, V. School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Chennai India

ISBN: (纸本)9798331543617

Over one billion people worldwide are affected with neurological disorders and their economic impact is approximately $800 billion annually, which constitutes major medical challenge. Using neuromodulation systems currently available suffers from sensitivity, reaction time as well as energy consumption. The proposal in this research is to address these major issues in closed loop neuromodulation by using a Quantum enhanced Spiking Neural Network (QESNN) architecture. This paper represents the interfacing of two major fields: quantum sensing and neuromorphic computing. The QESNN architecture comprises three core components: This is implemented as an array of quantum sensors, a quantum classical hybrid interface, and a spiking neural network (SNN). Taking advantage of quantum superposition and entanglement principles, the quantum sensor array noninvasively images neural activity at the level of single action potentials using NV centers. These sensors work at ambient temperatures, which is unlike superconducting devices. For processing with neuromorphic processing, quantum-classical hybrid converts quantum sensor data into classical signals with advanced signal process such as quantum state estimation and noise reduction. By modeling biological neurons with leaky integrate and fire neurons, the SNN serves as a low power, timed neural dynamics modulation component that emulates biological event driven behavior. A key innovation in our architecture is adaptive thresholding, which dynamically adjusts detection thresholds based on signal distributions, improving sensitivity and reducing false positives by 45.6%. The system also achieves 20-30% higher power efficiency through techniques like adaptive sensor frequency control and low-power processing. Simulation results that show how the QESNN performs better than classical systems with less false positives and greater energy efficiency are presented. A new platform is demonstrated that integrates quantum sensing with neurom

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

iLIAC: An approach of identifying dissimilar groups on unstructured numerical image dataset using improved agglomerative clustering technique

引用

Multimedia Tools and Applications 2024年第39期83卷 86359-86381页

作者： S, Sreedhar Kumar Ahmed, Syed Thouheed Fathima, Afifa Salsabil Mathivanan, Sandeep Kumar Jayagopal, Prabhu Saif, Abdu Gupta, Sachin Kumar Sinha, Garima Department of Computer Science and Engineering School of Engineering and Technology CMR University Karnataka Bengaluru India Department of Electrical Engineering Indian Institute of Technology Hyderabad Telangana Kandi India School of Computer Science and Engineering REVA University Bangalore India School of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida203201 India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Communication and Computer Engineering Faculty of Engineering and IT Taiz University Taiz Yemen Katra India Department of Computer Science Engineering Jain University Bangalore India

Unstructured Numerical Image Dataset Separation (UNIDS) method employing an enhanced unsupervised clustering technique. The objective is to delineate an optimal number of distinct groups within the input grayscale (G-S) image content, utilizing the improved limited iteration agglomerative clustering (iLIAC) clustering technique for the separation and enhancement of picture elements. The UNIDS method is structured into two primary stages: partitioning and validation. In the partitioning stage, the UNIDS method identifies an appropriate number of discrete clusters within the grayscale image using the iLIAC technique, eliminating the need for predetermined procedures. Subsequently, the method evaluates the similarity and deviation among data elements within the same group in the resultant image dataset. Additionally, it assesses the proximity and inters severance among clusters in the outcome of the image dataset through the partitioning process. Empirical results indicate that the UNIDS system excels in the spontaneous identification of an optimal number of discrete clusters within the input G-S image. The system demonstrates superior thickness, reduced deviation among data elements within the same cluster, increased inter-separation, and diminished inter-closeness between cluster elements. Furthermore, empirical analysis establishes the superior performance of the UNIDS approach compared to existing clustering techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Advancing Virtual Reality Interaction through Real-Time Hand Gesture Recognition for Immersive Experiences 3

Advancing Virtual Reality Interaction through Real-Time Hand...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Singh, Vinayak Kumar Kalinathan, Lekshmi Marimuthu, Marimuthu Vadivel, Sengazhani Murugesan Palani, Saravanan Vellore Institute of Technology School of Computer Science and Engineering Chennai India VIT Business School Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350372120

Virtual Reality technology offers immersive experiences, but reliance on handheld controllers can limit immersion. This study explores real-time hand gesture recognition to enhance natural interaction in VR environments. Motivated by VR's diverse applications in gaming, education, and training, it seeks to improve engagement and realism. The study provides an overview of current hand gesture recognition techniques, including computer vision and deep learning methods. Understanding the state of real-time gesture recognition informs future research and development in VR interaction. It enables researchers, developers, and practitioners to make informed decisions about integrating and enhancing gesture recognition technologies in various VR applications © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Secure Communication in Wireless Sensor Networks: Quantum Key Distribution with KIRSAN Gate 5

Enhanced Secure Communication in Wireless Sensor Networks: Q...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Manivannan, Kirankumar Vivekanandan, M. Saranya, G. Kumaran, K. School of Electronics Engineering Vellore Institute of Technology Chennai campus India School of Computer Science and Engineering Vellore Institute of Technology Chennai campus India

ISBN: (纸本)9798350379945

Sensor nodes are integral to wireless sensor networks (WSNs) but their deployment across various locations exposes their communications to potential monitoring. Key challenges include message protection and node identification, necessitating efficient mechanisms for key distribution and management, especially in large-scale networks. Quantum cryptography, specifically quantum key distribution (QKD), offers a method to securely establish keys over short distances, leveraging principles like garbage output reduction and quantum communication for enhanced security. To address these issues, reversible logic gates, such as the newly developed © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Predicting Land Cover Changes with Convolutional LSTM Networks: A Case Study of Chatham, Massachusetts

Predicting Land Cover Changes with Convolutional LSTM Networ...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Kavitha, J.C. Subitha, D. Bhandari, Divyansh Jaluka, Devesh Kumar Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India Vellore Institute of Technology School of Electronics and Engineering Chennai600127 India

ISBN: (纸本)9798331533311

Land use and land cover changes has become crucial for natural resource management and monitoring, particularly in urban planning. Remote sensing and geographical information systems analyze the changes in land use and land cover, promoting sustainability. Remote sensing images are the major data sources for land cover classification. High spatial resolution images enable more precise analysis and identification of land cover data types. However, better spatial resolution creates new challenges to the existing classification and prediction methods. This research work outlines a new model that integrates the Convolutional Neural Networks and Long Short-Term Memory network model for the prediction of dynamic changes in land cover patterns from historic satellite images. The proposed model is constructed for Chatham, Massachusetts, prediction from Google Earth timelapse imagery taken over 39 years to compile a sequence of 39 annual satellite images. The images are preprocessed to 256 × 256 pixels and image normalization ensured efficient data handling. The proposed model predicted land cover over the next three years and demonstrated the model's capacity to capture both geographical and temporal patterns in the data. Evaluation of metrics, such as the training and validation loss, showed good performance by the model. Despite some limitations in image resolution and iterative prediction, the findings show that CNN-LSTM models could be very useful for land cover forecasting, providing important guidelines for future study and practical applications in the context of environmental management. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

NeutroAlgebra of Idempotents in Group Rings

引用

Neutrosophic Sets and Systems 2022年 50卷 156-177页

作者： Kandasamy, Vasantha Kandasamy, Ilanthenral School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

In this paper, the authors study the new concept of NeutroAlgebra of idempotents in group rings. It is assumed that RG is the group ring of a group G over the ring R. R should be a commutative ring with unit 1. G can be a finite or an infinite order group which can be commutative or non-commutative. We obtain conditions under which the idempotents of the group rings ZG, ZnG, and QG form a NeutroAlgebra under the operations + or ×. Some collection of idempotents in these group rings form an AntiAlgebra. We propose some open problems which has resulted from this study. © 2022

关键词： AntiAlgebra group ring NeutroAlgebra NeutrosubAlgebra Partial Algebra Symmetric group

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：