检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Patil, Priyadarshini C. Ashwin, R.K. Kumar G, Arvind Bhaskar, M. Rajesh, N. Pda College of Engineering Department of Computer Science & Engineering Kalaburagi India H. K. E. Society's S. L. N. College of Engineering Department of Computer Science & Engineering Raichur India Ramaiah Institute of Technology Department of Electronics and Telecommunication Engineering Bengaluru India K L University Vadeeshwaram Department of Computer Science & Engineering Vijayawada India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350398465

Research into facial recognition has been one of the most intriguing and extensive areas of study for decades. Because of its importance in reading and conveying other people's emotions, the face often becomes the focal point of conversations. A facial recognition system's ability to identify an individual from a digital image or video is useful for a wide variety of security-related purposes, including surveillance, general identity verification, criminal-justice Systems, image database investigations, Smart Card applications, multi-media settings with adaptive human-computer interfaces, video indexing, gender classification, facial feature recognition, and tracking. While being less reliable than fingerprint and iris identification, face recognition has seen widespread adoption because of its contactless, non-invasive nature. light, emotion, and posture all have a role in making it harder to recognise a person's face. A computer model of face recognition is difficult to build because of the problem space's complexity and possible multidimensionality. Extensive attempts have been made to build accurate and reliable face recognition systems. The high dimensionality of a facial image is necessary for detecting minute variations in features, but this also means that the calculations required to classify the image take a long time. It's possible that lowering the image resolution will reduce the time needed for recognition processing. Facial recognition systems have been studied for quite some time, but there is always opportunity for improvement. These results show that current face recognition algorithms have matured to a considerable extent while operating in a constrained context. When put to the test in the real world, however, these technologies do not show a significant performance boost in all of the frequent cases faced by applications. Genetic face recognition is necessary when only the most cutting-edge method of facial identification will do. There are many

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Recognition of Face by Using Squeezenet Pre-Trained Network

A Novel Approach for Recognition of Face by Using Squeezenet...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Sangamesh, H. Viswanatha, M.V. Petli, Vishwanath Patil, Nagaraj B H. K. E. Society's S. L. N. College of Engineering Department of Electronics and Communication Engineering Raichur India Government Engineering College Department of Computer Science and Engineering Raichur India

ISBN: (纸本)9798350398465

A face recognition in current generation plays a vital role. day by day new techniques are emerging for face recognition. Now a days deep learning based face recognition techniques have become very popular due to the less recognition time and fast computation by using the sequence of layers and drop out is employed for training the deep neural network for some layers for reducing the over fitting of data in neural networks. leveraging ready-to-use pre-trained deep neural networks for specific applications, some of the layers are configured with transfer learning to perform face recognition tasks, significantly simpler and more accurate than previous techniques too. The squeezenet pre-trained convolutional neural network is used here by replacing two final layers with new layers adjusted to new data set. The Experimentation is performed on data sets such as ORl and Extended YAlE B. data is partitioned as training and validation datasets. 80% of image as training, 20% of image data is used as validating data. 97% of accuracy is achieved on training data and 92% of accuracy is obtained on validation data. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Urban Slum Mapping Using Homogeneous Urban Patches 3

Urban Slum Mapping Using Homogeneous Urban Patches

引用

3rd IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Prabhu, R. Priya, M. Sangeetha dayana, R. Suresh, M. School of Computing Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur Campus Chennai India Saveetha Engineering College Department of Computer Science and Engineering Thandalam Chennai India Jeppiaar Institute of Technology Department of Computer Science and Engineering Sriperumbudur Chennai India R.M.D. Engineering College Kavaraipettai Department of Mathematics Thiruvallur India

ISBN: (纸本)9798350361186

Slums (Informal Settlements) are the most dynamic areas whose geographical locations are inaccurate according to official statistics and maps because of the exponential expansion of urbanization strategies. As a result, a method has to be developed to distinguish between informal settlements and track their spatial patterns. This paper presents an integrated method for detecting slums from satellite images that employs homogeneous urban patches (HUP) and grey level co-occurrence matrix (GlCM)-based image segmentation. In order to extract meaningful spatial features, urban patches are segmented according to their homogeneity and GlCM analysis provides useful texture information about slum areas. The combination of both these GlCM and HUP features allows for the creation of a classification map that accurately identifies and maps slum areas. We utilized WorldView-2 (1.84m) satellite imagery of Madurai to test the effectiveness of proposed HUP approach. The validation process includes rigorous testing against ground truth data, with careful consideration given to the selection of training and testing datasets. The effectiveness of the proposed method is evaluated using metrics including overall accuracy, user accuracy, and producer accuracy Furthermore, the proposed algorithm outperformed existing GlCM-based approaches in terms of accuracy. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Synergistic Brain Tumor detection: Anisotropic diffusion, with SVM 3

Synergistic Brain Tumor Detection: Anisotropic Diffusion, wi...

引用

3rd IEEE delhi Section Flagship Conference, dElCON 2024

作者： Alphonsa, J. Kumari, V. Sheeja Roslin dayana, K. Saveetha School of Engineering Simats University Department of Computational Intelligence Chennai600025 India R.M.D Engineering College Department of Computer Science Chennai601206 India

ISBN: (纸本)9798331518592

Accurate finding of the tumors in MRI images is crucial for effective prevention and cure. Here, an innovative approach integrating anisotropic diffusion filtering, U-net-based segmentation, CNN feature extraction, and SVM classification is proposed and optimized by Bayesian techniques. The method starts with anisotropic diffusion filtering to improve image quality by dropping noise while conserving significant basic particulars. The tumor regions are segmented using the U-Net architecture, which is known for its robust performance in segmenting medical images due to its encoder-decoder structure and skip connections. Feature extraction is performed using a Convolutional Neural Network (CNN) that finds some complex patterns, and features associated with tumors. An SVM classifier is then used to distinguish between tumor and non-tumor regions based on these features. To further refine the model, Bayesian optimization is used to fine-tune the hyperparameters of the SVM and other components of the pipeline. The proposed method shows significant improvements in detection accuracy and robustness compared to conventional techniques. Bayesian optimization plays an important part in cultivating classification performance by systematically exploring and optimizing the hyperparameters. This integrated approach provides a powerful and reliable solution for brain tumor detection with great potential for clinical healthcare applications where precision and early diagnosis are critical. The results not only advance the current state of tumor detection but also provide a solid foundation for future research to optimize diagnostic methods. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

different Respiratory lung Sounds Prediction using deep learning

Different Respiratory Lung Sounds Prediction using Deep Lear...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Rajeshree Parsingbhai Vasava Hetal A. Joshiara Computer Engineering Department L D college of engineering Ahmedabad Gujarat India

The sounds produced by the lungs when breathing might provide important information to physicians. Based on the findings, a deep learning-based approach is recommended for the prediction of breathing-related lung sounds. The Proposed model was trained in lung sounds collected from people suffering from a broad variety of respiratory conditions. The research improves classifying lung sounds, by audio to image spectrogram features is taken and used to train a deep convolutional neural network. The proposed technique accurately predicts many different types of respiratory lung sounds, demonstrating the promise of deep learning in this domain. This research results have important implications for the development of automated diagnostic tools that might help doctors make correct diagnoses of respiratory disorders more quickly and accurately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing wireless sensor network longevity and security: A quad-leach approach

Enhancing wireless sensor network longevity and security: A ...

引用

2024 IEEE International Conference on Emerging Technologies in computer Science for Interdisciplinary Applications, ICETCS 2024

作者： lohith, J.J. Shreya, S. Hamsa Priya, J.l. B.M.S. College of Engineering Dept. of Computer Science and Engineering Bangalore India D.S.C.E. Dept. of Information Science and Engineering Bangalore India B.M.S. College of Engineering Dept. of Electronics and Telecommunications Bangalore India

ISBN: (纸本)9798350372502

Researchers have increasingly focused on Wireless Sensor Networks (WSNs) in recent years, recognizing their versatile applications. The primary focus within WSNs is enhancing network longevity for efficient resource utilization, coupled with a strong emphasis on security and authentication. This paper specifically delves into the implementation of Quad lEACH for homogeneous networks, aiming to substantially improve network lifetime, stability, and throughput. The proposed protocol achieves this by employing a cluster head selection process and integrating security and authentication measures between cluster heads in the Quad-lEACH routing protocol. The research addresses the integration of a security agent within WSNs using the NS-2 tool, contributing to enhanced authentication. The implementation is carried out through the simulation software NS 2, where the security agent is seamlessly combined with the WSN infrastructure. The objective of this research is to incorporate a reliable authentication and security agent into NS-2 in conjunction with the lEACH protocol, which is the standard for wireless sensors networks (WSNs). The efficacy of the suggested methodology will be validated through simulated outcomes. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

deep learning Models for Acoustic Monitoring of the Himalayan Monal and Other Elusive Bird 4

Deep Learning Models for Acoustic Monitoring of the Himalaya...

引用

4th International Conference on Sentiment Analysis and deep learning, ICSAdl 2025

作者： Nikshya, J. Ebens Raj, J. Relin Francis Krishnan, R. Santhana Rajkumar, G.Vinoth Settu, Imran Javeed Kavitha, S. Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India J. P. College of Engineering Department of Electronics and Communication Engineering Tenkasi India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India

ISBN: (纸本)9798331523923

Acoustic monitoring of rare and elusive bird species presents significant challenges due to the complexity of environmental noise and the variability in bird vocalizations. This study proposes a novel deep learning framework, BioAudio VisionNet (BAVNet), specifically designed for the acoustic identification and monitoring of the Himalayan Monal and other rare bird species. The performance of the proposed algorithm was evaluated against three established algorithms: Support Vector Machines with Acoustic Features (SVM-AF), Audio Spectrogram Transformer (ASF), and deep Belief Networks (dBN). Simulation experiments were conducted using metrics such as accuracy versus the number of epochs, processing time versus accuracy, and spectrogram classification accuracy versus spectrogram resolution. The results demonstrated that BAVNet achieved a notable improvement in classification accuracy, computational efficiency, and adaptability to varying spectrogram resolutions when compared to existing methods. These findings highlight the potential of BAVNet for real-time biodiversity monitoring in challenging environments. Future work can explore the integration of additional contextual data, such as environmental factors, to further enhance system performance. © 2025 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Au/SiC Microfluidic devices Fabricated by Rapid laser Cladding for Photocatalytic degradation of Water Pollutants

引用

ACS Sustainable Chemistry and engineering 2024年第11期12卷 4486-4496页

作者： Chang, Chun-Hao lin, Hsiu-Pen Chen, Chien-Wei lu, Yu-Cheng Hsiao, Fu-He Hsieh, Chi-Hsiang lin, Bo-Cheng Yu, Bang-Ying Ma, dai-liang Kuo, Hao-Chung Tu, Chang-Ching li, Bor-Ran Institute of Biomedical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electrical and Computer Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Centre for Emergent Functional Matter Science National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Department of Electrophysics College of Science National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Semiconductor Research Center Hon Hai Research Institute Taipei11492 Taiwan Department of Photonics Institute of Electro-Optical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Taisic Materials Corp. Taoyuan320 Taiwan Department of Electrical Engineering National Central University Taoyuan32001 Taiwan Medical Device Innovation and Translation R&D Center National Yang Ming Chiao Tung University Taipei112304 Taiwan

The increasing proliferation of third-generation semiconductor silicon carbide (SiC) products has led to the emergence of SiC powder as an industrial byproduct. To reutilize the SiC efficiently, we propose a facile method for fabrication of photocatalytic plates from reclaimed SiC. Our approach involves affixing the SiC onto a glass surface with laser cladding, followed by sputter deposition of a gold film and laser annealing. The resulting nanogold-coated SiC plate exhibited enhanced photocatalytic activity due to the injection of hot electrons into the SiC via surface plasmon resonance. Unlike chemical reduction, which requires hours for the synthesis, purification, and isolation of Au/SiC, our approach accomplished this in just 30 min. When illuminated, the Au/SiC plate generated electron-hole pairs that formed radicals in the presence of water and oxygen, leading to the decomposition of methylene blue. Furthermore, the Au/SiC plate can be integrated into a microfluidic device for an enhanced degradation rate and efficiency. This research provides a simple and environmentally friendly approach to the production of photocatalytic plates from reclaimed SiC and contributes to sustainable development. © 2024 The Authors. Published by American Chemical Society.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Scaling Spherical Convolutional Neural Network with Weighted-leader Search based PId control Approach for a Four Wheeled Omnidirectional Mobile Robot 8

Scaling Spherical Convolutional Neural Network with Weighted...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Selvi, d.M. Kalai Veerabhadraswamy, K.M. Choudhary, Ankur Parikh, Swapnil Natrayan, l. Patil, Harshal R.M.D Engineering College Department of Computer Science and Engineering Chennai Tamil Nadu Tiruvallur601 206 India Government Engineering College Department of Electronics and Communication Engineering Mosalehosahalli Karnataka Hassan573 212 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Parul University Parul Institute of Engineering and Technology Department of Computer Science and Engineering Post Limda Gujarat Waghodia391760 India Saveetha School of Engineering Simats Department of Mechanical Engineering Tamil Nadu Chennai602105 India Iilm University School of Computer Science & Engineering Uttar Pradesh Greater Noida201 306 India

ISBN: (纸本)9798350376425

Over the past ten years, there has been a significant growth in the need for automation employing mobile robots. These days, mobile robots serve many purposes that humans cannot fulfil. One subset of these mobile robots, known as omnidirectional mobile robots, has drawn interest due to its superior mobility and ease of tracking complex trajectories compared to its differential type competitors. Nevertheless, these robots' complex dynamical model presents a number of difficulties for their control strategy. This research develops the modeling of an omnidirectional mobile robot on four wheels. Additionally, a scaling spherical convolutional neural network with weighted leader search (SSCNN-WlS) process is utilized to determine the optimal controller's weights, and an intelligent proportional integral derivative (PId) neural network control approach is built for trajectory-following jobs. The findings of the simulation investigation, which used MATlAB, verified that the suggested intelligent control strategy for trajectory tracking jobs is accurate. The introduced approach attains higher accuracy, as 95%. © 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

Unlocking Efficiency in Agricultural Supply Chains: A Secure and Transparent Approach through Blockchain Technology

Unlocking Efficiency in Agricultural Supply Chains: A Secure...

引用

2024 IEEE International Conference on Emerging Technologies in computer Science for Interdisciplinary Applications, ICETCS 2024

作者： lohith, J.J. Shreya, S. Hamsa Priya, J.l. B.M.S. College of Engineering Dept. of Computer Science and Engineering Bangalore India D.S.C.E Dept. of Information Science and Engineering Bangalore India B.M.S. College of Engineering Dept. of Electronics and Telecommunications Bangalore India

ISBN: (纸本)9798350372502

Supply Chain Management (SCM) involves orchestrating various processes that extend from acquiring raw materials to delivering finished products to end consumers. The key objectives of a proposed supply chain in agriculture, emphasizes information-driven processes, cost reduction, and customer impact. It creates a versatile system capable of managing the supply chain for diverse commodities within a country, while also addressing the crucial need for increased transparency and traceability in data throughout the chain of activities. In our proposed approach to agricultural supply chain management (SCM), the focus is on creating a secure, transparent, and traceable SCM. To achieve this, we leverage cutting-edge technologies like the Ethereum blockchain and the Interplanetary File System (IPFS). The resulting software is a decentralized Application (dApp) that orchestrates a series of activities within the agricultural industry, using cryptocurrencies to establish a seamless and efficient supply chain management system. This software platform is fortified by the secure algorithms of blockchain, providing an added layer of reliability. Additionally, our application incorporates transparency and traceability, ensuring user-friendly functionality and making it more accessible for users. © 2024 IEEE.

关键词： Blockchain

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：