检索结果-内蒙古大学图书馆

2nd International Conference on Power, Control and Computing Technologies, ICPC2T 2022

作者： Das, Samiran Kyal, Chirag Pratiher, Sawon JIS University JIS Institute of Advanced Studies and Research Kolkata India Tata Consultancy Services Bangalore India Indian Institute of Technology Kharagpur Department of Electrical Engineering Kharagpur India

ISBN: (纸本)9781665458580

Traditional clustering methods groups data points according to attributes such as similarity, continuity, neighbor-hood information, etc. overlooks the structural properties of the data. Consequently, prevalent clustering approaches to below-par performance in real-world applications. Unlike traditional clustering approaches, subspace clustering methods attempt to group datapoints keeping the inherent structure and rank-related properties of the data into account. Despite the rapid growth in deep learning-based approaches, very few works have utilized deep learning for the subspace clustering task. This work introduced an auto-encoder-based deep learning architecture consisting of a self-expressive layer for the deep subspace clustering task. We use smoothed L2, L0.5 and Frobenius norms instead of the actual measures for ease of optimization task. We also explored the efficacy of sparsity measures that characterize the self-representation coefficient matrix of the self-expressive layer. The experiments conducted on standard datasets suggest that the application of efficient sparsity measures improves the performance of the subspace clustering approach and results in superior performance compared to the previous deep subspace clustering approaches. © 2022 IEEE.

关键词： Deep learning Computers Clustering methods Power control Computer architecture Indexes Task analysis

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models

Hyperspectral Images for Crop Prediction using Machine and D...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： R. Mahalakshmi K. Kumutha M. Sakthivanitha R. Bagavathi Lakshmi Mohamed Sirajudeen Sankar Padmanabhan Department of Computer Applications-PG Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Computer Applications-PG Vels Institute of Science Technology Advanced Studies Chennai Tamil Nadu India Department of Computer Application Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Information Technology Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India PG and Research Department of Computer Science Nilgiri College of Arts and Science The Nilgiris Tami Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data.

关键词： Support vector machines Radio frequency Deep learning Recurrent neural networks Accuracy Crops Spatial databases Convolutional neural networks Reliability Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Localization through RGB-D Camera for the Quad-rotor

Localization through RGB-D Camera for the Quad-rotor

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Vidit Datt Prabhakar Vijay Kumar Pandey Anuj Kumar Sharma Tushar Sandhan Department of Mechatronics Centre for Advanced Studies AKTU Lucknow India Department of Electrical Engineering Indian Institute of Technology Kanpur India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper presents a thorough investigation into the implementation of a localization system using a RGB-D camera that prioritizes computational efficiency. The study focuses on utilizing the Oak D Pro depth camera, which includes an in-built Inertial Measurement Unit. Visual Odometry is used to estimate the camera pose which is lighter in computation than other algorithms like Simultaneous Localization and Mapping. The IMU is used to obtain the camera pose due to the presence of drift during the camera’s fast motion. The readings are fused together to get the correct camera pose by employing the Extended Kalman Filter for sensor fusion, achieving seamless integration of VO and IMU. This research explores the adaptation of Visual Inertial Odometry system for an autonomous Unmanned Aerial Vehicles applications, specifically for a quad-rotor/drone.

关键词： Location awareness Visualization Measurement units Simultaneous localization and mapping Inertial navigation Sensor fusion Cameras Kalman filters Odometry Visual odometry

来源：评论

学校读者我要写书评

暂无评论

Securing Smart Grid IoT System using A Robust RNN based Cyberattack Detection Framework

Securing Smart Grid IoT System using A Robust RNN based Cybe...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Asha A Karthika S P.C. Saranya Deepak Arumugam St. Joseph’s Institute of Technology OMR Chennai KIT-Kalaignarkarunanidhi Institute of Technology Coimbatore School of Management Studies Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Cybersecurity in smart grid IoT systems is now a concern of high priority, as the integration of connected devices increases, and these systems become more vulnerable to sophisticated cyberattacks. This paper proposes a new RNN+GRU-based cyberattack detection system to meet such security challenges in smart grid IoT networks. The proposed model is based on Recurrent Neural Networks (RNN) and Gated Recurrent Units (GRU) to efficiently capture temporal and contextual patterns of the attack data for improving detection accuracy of different types of cyber-attacks. Comparing the performance of our proposed model with other models like Support Vector Machines (SVM), Random Forest (RF), Convolutional Neural Network (CNN), Deep Neural Network (DNN), and Long Short-Term Memory (LSTM) network is shown. Experimental results show that the RNN+GRU-based model outperforms these approaches in some key performance metrics: accuracy, precision, recall, F1-score, and ROC-AUC, better than other compared methods by achieving superior attack detection rates. Moreover, correlation analysis is also included for both the existing DNN model and the proposed approach; thus, the effectiveness of the RNN+GRU model in adapting to various scenarios of cyberattacks is noted. In the final analysis, the RNN+GRU-based cyberattack detection system shows great promise in securing smart grid IoT networks and shows better performance compared to some of the existing techniques.

关键词： Support vector machines Radio frequency Adaptation models Analytical models Accuracy Data models Smart grids Convolutional neural networks Internet of Things Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Detection of Irregular Shapes Resembling Non-Uniform Gaps for UAV Navigation

Detection of Irregular Shapes Resembling Non-Uniform Gaps fo...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Shashi Kumar Singh Anuj Kumar Sharma Tushar Sandhan Department of Mechatronics Centre For Advanced Studies AKTU Lucknow India Department of Electrical Engineering Indian Institute of Technology Kanpur India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This research paper presents a novel approach for the detection and segmentation of non-uniform gaps to facilitate safe autonomous navigation of UAVs (Unmanned Aerial Vehicles) using the YOLOv8 deep learning model. The methodology comprises three key stages: data collection, annotation, and model training using the YOLOv8 architecture. Initially, the model is trained on regular shapes images such as lines, triangles, quadrilateral and hexagons which also resembles the many real-world scenarios to establish a foundational understanding before transitioning to non-uniform gaps. We solved the problem of data scarcity through synthetic to natural data training process. Non-uniform gaps, simulated to real-world, data is meticulously annotated to train the YOLOv8 model, ensuring robustness across diverse scenarios. A post-processing step is introduced to find the centroid of the segmentation mask of detected gaps, providing actionable guidance for UAV maneuvering with proper clearance. Experimental results demonstrate the efficacy of the proposed approach in accurately detecting and segmenting non-uniform gaps, showcasing its potential for real-world deployment in various applications. This research contributes to advancing UAVs navigation by providing a reliable solution for safe passage through complex environments.

关键词： Training Accuracy Navigation Shape Data collection Autonomous aerial vehicles Real-time systems Robustness Data models Drones

来源：评论

学校读者我要写书评

暂无评论

Study of the growth mechanism of a self‑assembled and ordered multi‑dimensional heterojunction at atomic resolution

引用

Frontiers of Optoelectronics 2023年第4期16卷 37-48页

作者： Zunyu Liu Chaoyu Zhao Shuangfeng Jia Weiwei Meng Pei Li Shuwen Yan Yongfa Cheng Jinshui Miao Lei Zhang Yihua Gao Jianbo Wang Luying Li Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China Ministry-of-Education Key Laboratory for the Green Preparation and Application of Functional Materials Hubei Collaborative Innovation Center for Advanced Organic Chemical MaterialsSchool of Materials Science and EngineeringHubei UniversityWuhan 430061China Center for Electron Microscopy MOE Key Laboratory of Artificial Micro-and Nano-Structures and the Institute for Advanced StudiesSchool of Physics and TechnologyWuhan UniversityWuhan 430072China State Key Laboratory of Infrared Physics Shanghai Institute of Technical PhysicsChinese Academy of SciencesShanghai 200083China

Multi-dimensional heterojunction materials have attracted much attention due to their intriguing properties,such as high efciency,wide band gap regulation,low dimensional limitation,versatility and *** further improve the performance of materials,researchers have combined materials with various dimensions using a wide variety of ***,research on growth mechanism of such composite materials is still *** this paper,the growth mechanism of multidimensional heterojunction composite material is studied using quasi-two-dimensional(quasi-2D)antimonene and quasione-dimensional(quasi-1D)antimony sulfde as *** are synthesized by a simple thermal injection *** is observed that the consequent nanorods are oriented along six-fold symmetric directions on the nanoplate,forming ordered quasi-1D/quasi-2D *** transmission electron microscopy(TEM)characterizations confrm the chemical information and reveal orientational relationship between Sb2S3 nanorods and the Sb nanoplate as *** density functional theory calculations indicate that interfacial binding energy is the primary deciding factor for the self-assembly of ordered *** details may fll the gaps in the research on multi-dimensional composite materials with ordered structures,and promote their future versatile applications.

关键词： Multi-dimensional composite materials Ordered heterostructures-Self-assembly Growth mechanism

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation on sensitiveness WEDM parameters for12X18H10T – Stainless steel

引用

Materials Today: Proceedings 2023年 81卷 454-458页

作者： V.N. Aneesh K. Karunakaran Department of Mechanical Engineering School of Engineering Vels Institute of Science Technology and Advanced Studies (Deemed to be University) Vels University Chennai TN India

The unconventional machining processes are popular in machining the difficult to cut type complex contour/ profile. The key parameters are to be machined with care as they directly affects the function and non key dimensions are machined with other than consideration of functional aspect, like design, passage. That means accuracy is less important in those dimensions but finish is to be good. So the machining of engineering materials does not always require optimizing parameters based on multiple responses. This investigation focuses on the sensitiveness of Wire EDM of 12X18H10T - Stainless Steel and identifying the parameters contribution and establish mathematical model to predict values without trial. An austenitic alloy 12X18H10T - Stainless Steel exhibits its inherent mechanical properties even when it expose to extremely high temperature. Ithas potential application in aerospace engine components manufacturing. This investigation utilized the Taguchi L9 experiential Design with factors of Pulse off Time, Wire Tension, Pulse on Time, and Wire Feed Rate. This study aims to examine Maximize the rate of machining with Taguchi approach in the process of Wire EDM of 12X18H10T - Stainless Steel and establish a mathematical model to predict the highly influencing parameter(s) for desired rate of machining.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Diversity and Inclusion: Addressing Biases in HR Practices 5

Machine Learning for Diversity and Inclusion: Addressing Bia...

引用

5th IEEE International Conference on Recent Trends in Computer Science and technology, ICRTCST 2024

作者： Anitha Kumari, D. Shaikh, Irfan Abdul Karim Gangadharan, S. Narendra Kiran, P.B. Ramya, S.R. Nargunde, Amarja Satish Vels Institute of Science Technology and Advanced Studies Pallavaram TamilNadu Chennai India Bahrain Polytechnic Faculty of Business Bahrain St. Joseph's College of Engineering Department of Management Studies Chennai India Lovely Professional University Jalandhar-Delhi Mittal School of Business Punjab Phagwara India Karpagam College of Engineering School of Management Studies Tamilnadu Coimbatore India Bharati Vidyapeeth Institute of Management and Rural Development Administration Sangli Bharati Vidyapeeth Bhavan Rajwada Chowk Maharashtra Sangli India

ISBN: (纸本)9798350351378

As organizations strive to foster diverse and inclusive workplaces, the role of technology, particularly machine learning, becomes crucial in addressing biases inherent in Human Resources (HR) practices. This research explores the application of machine learning algorithms to mitigate biases in recruitment, performance evaluation, and talent management processes, ultimately promoting diversity and inclusion. Biases, whether conscious or unconscious, can affect decision-making at various stages, leading to underrepresentation and disparities within the workforce. Recognizing the need for innovative solutions, this paper advocates for the integration of machine learning techniques to augment HR processes. By leveraging advanced algorithms, organizations can develop unbiased job descriptions, eliminate resume screening biases, and create diverse candidate shortlists. Machine learning models can provide objective insights by analyzing performance metrics, removing subjective biases, and fostering a more equitable assessment of employees. Talent management, the focus of the fourth section, is critical for the retention and development of a diverse workforce. Machine learning algorithms can assist in identifying high-potential employees based on merit, skills, and contributions, thus promoting a fair and inclusive talent pipeline. Addressing concerns related to algorithmic biases, the research suggests guidelines for responsible ML implementation to ensure that technology aligns with organizational values and legal requirements. In conclusion, this research underscores the transformative potential of machine learning in creating more equitable and inclusive workplaces. By addressing biases in HR practices, organizations can harness the power of technology to build diverse teams, foster innovation, and promote a culture of inclusion. However, it also emphasizes the need for ongoing research, collaboration, and ethical considerations to maximize the positive impact of machi

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Smart Electronic Arm Module using Arduino Applications

Smart Electronic Arm Module using Arduino Applications

引用

2022 IEEE International Conference on Current Development in engineering and technology, CCET 2022

作者： Kanna, R. Kishore Hema, L.K. Ramya, V. Subha Kripa, N. Gomalavalli, R. Ambikapathy, A. Vels Institute of Science Technology Advanced Studies Department of Biomedical Engineering Chennai India Department of Biomedical Engineering Chennai India Bharath Institute of Higher Education and Research Department of Biomedical Engineering Chennai India Siddharth Institute of Engineering and Technology Department of Electronics and Communication Engineering Andhra Pradesh India Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9781665454155

Automation is often employed in today's society to assist people in doing their jobs and improve work efficiency. One kind of automation device that is often employed to assist humans in doing their jobs is the robot. Robots play a variety of functions in human life and are used to make a variety of human tasks easier. Robots are often used because they can make tasks simpler and more productively do them. Robots are used in many different ways to assist people in their work, including drones, welding robots, and agricultural robots. One sort of robot that we come across often is a robot arm, which performs duties comparable to those of a human arm. The robot may be controlled in its application utilizing a variety of techniques, some of which directly use a cable connection and others which utilize a wireless technique. Additionally, a controller-the robot's brain-is required to operate a robot. In order to operate the robot arm via Bluetooth, this research will create a controller based on Arduino, one of the most popular microcontroller boards for use in education, hobbies, and the workplace. The identification of the programme and data collection from various sources, such as a journal or discussion forum, are the first steps in the methodology used in this study. Next, the systems schematic design of the hardware used in this research is done, and then the Arduino programme and smartphone app are added. The select and place activity may be carried out wirelessly utilizing a Bluetooth connection by the Arduino software and the simple Android applications created using App Inventor. © 2022 IEEE.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

AI-Integrated Sensor Data Analytics for Real-Time Decision-Making in Wireless Sensor Networks 2

AI-Integrated Sensor Data Analytics for Real-Time Decision-M...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Wasim Haidar, S.K. Wilfred Blessing, N.R. Chaubey, Sudhakar Kumar Mehmood, Zahid Kavitha, S.J. Sutherlin Subitha, G. College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Oman Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai India Stella Mary's College of Engineering Department of Computer Science and Engineering Aruthenganvilai India

ISBN: (纸本)9798331505745

The study compares the performance of Wireless Sensor Networks (WSNs) with 20, 30, 40, and 50 nodes in real-time AI-enhanced sensor analytics using the AODV routing protocol. All configurations showed a consistent Packet Delivery Ratio (PDR) of 100%. However, the end-to-end delay increased slightly from 0.2 sec (20 nodes) to 0.3 sec (30, 40, 50 nodes), indicating that larger networks result in longer paths. Throughput decreased from 2560 bps at 20 nodes to 1706.67 bps in larger configurations, probable due to network congestion. Energy efficiency also decreased as the number of nodes increased, suggesting higher energy consumption per transmission. © 2025 IEEE.

关键词： Sensor nodes

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：