检索结果-内蒙古大学图书馆

IEEE India Conference (INDICON)

作者： Prashant Kumar Anand Kumar Department of Electronics and Communication Engineering National Institute of Technology Jamshedpur India School of Computer Science UPES Dehradun Uttarakhand

ISBN: (数字)9798350391282

ISBN: (纸本)9798350391299

Efficient underwater communication demands effective channel estimation and equalization techniques. Recent advancements in adaptive filtering algorithms have sparked significant interest in the realm of underwater acoustics (UWA) communication. In this work, we introduce and thoroughly analyze a novel reweighted $l_communication$ -norm normalized least mean square (NLMS) channel estimation algorithm tailored for sparse UWA channels. Unlike the conventional NLMS algorithm, which overlooks the inherent sparsity of the channel impulse response (CIR), our approach leverages this sparsity by employing an adaptive convex combination method that identifies sparse structures using a new $l_communication$ -norm NLMS and an adaptive filter based on NLMS principles. A detailed quantitative analysis of the reweighted $l_communication$ -norm NLMS algorithm is provided, along with the derivation of the excess mean square error (EMSE) expression. This analysis demonstrates that, under specific conditions, the proposed algorithm outperforms the traditional NLMS algorithm, as anticipated. To validate the efficacy of our approach, we present numerical studies based on both simulated channels and experimental channel data from shallow water in the 8.5 - 16.5 kHz acoustic band. The simulation results, particularly for scenarios with high sparsity levels, show that our proposed method offers superior performance compared to existing NLMS algorithms and reweighted $l_communication$ -norm LMS, in both Gaussian sparse channels and underwater sparse channels.

关键词： Underwater communication Statistical analysis Simulation Channel estimation Mean square error methods Minimization Underwater acoustics Channel impulse response Standards Convergence

来源：评论

学校读者我要写书评

暂无评论

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement Combining Structural Noise Reduction and Perceptual Quality

A Hybrid GAN-CNN Framework for Low-Light Image Enhancement C...

引用

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

作者： R. Gobinath R Boopathi Vijayalakshmi S D. Anu Disney P. Nirmala Priyadharshini K. Maheshwari Artificial intelligence and Data science E.G.S. Pillay Engineering College Nagapattinam Department of Electrical and Electronic Engineering Karpaga Vinayaga College of Engineering and Technology Tamilnadu Department of Electronics and communication Engineering Sona College of Technology Salem Tamilnadu Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai Department of Information Technology Adithya Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science Sir Issac Newton College of Engineering and Technology Nagapattinam

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Low light region is one of the difficult scenarios for surveillance system, especially noisy, low-quality images may lead to poor object detection and scene analysis. To tackle this problem, we introduce a hybrid GAN - CNN framework for low light image denoising and quality enhancement. We develop a framework that combines the strengths of Generative Adversarial Networks (GANs) for photorealistic image generation and Convolutional Neural Networks (CNNs) for robust noise reduction. First denoising and feature extraction is done by the CNN module, and the GAN part further refines the denoised output to improve the perceptual quality of the generated images. We train and validate the proposed model in standard low light image dataset and show superior PSNR, SSIM, and visual clarity compared to state of art methods. We show that the hybrid GAN-CNN model successfully trades between image denoising accuracy and visual realism, thereby providing a viable alternative for enhancing surveillance performance in lowlight conditions. Keywords: Image denoising, GAN-CNN hybrid, low-light enhancement, PSNR, SSIM, surveillance systems.

关键词： Visualization Accuracy Surveillance Noise reduction Noise Generative adversarial networks Feature extraction Convolutional neural networks Image enhancement Image denoising

来源：评论

学校读者我要写书评

暂无评论

Automation of Health Monitoring System for Elderly and COVID-19 Patients using IOT 8

Automation of Health Monitoring System for Elderly and COVID...

引用

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Swathi, Kanisetty Latha, S. Bhargavi Vadlamudi, Muniraju Naidu Alkhafaji, Mohammed Ayad Mohsen, Karrar Shareef Saikumar, K. Department of ECE A.P Visakhapatnam India Gokaraju Rangaraju Institute of Engineering and Technology Department of CSE Telangana Hyderabad500090 India VNR Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Hyderabad India National University of Science and Technology College of Engineering Technology Department of Medical Device Industry Engineering Dhi Qar Iraq Al-Ayen University Information and Communication Technology Research Group Scientific Research Center Thi-Qar Iraq Koneru Lakshmaiah Education Foundation Hyderabad Department of ECE Telangana 500075 India

ISBN: (纸本)9798350334012

The healthcare industry has been getting advanced scientifically and technologically through wireless-sensing devices. Automation of the healthcare system with the Internet of things has been implemented & attains accurate results. Due to the panic situation of COVID-19, this automation of health monitoring systems plays an important role in the medical sector. In this research work, an advanced IoT-based, fully automated health monitoring system has been implemented for elderly & COVID-19 patients. The proposed design is verified on the python 3.6.0 software tool. The Lack of early treatment may cause patients to get unexpected risk failure, including death. This research work monitors elderly & older COVID-19 patients monitorization remotely using IoT technologies, even in crucial conditions. Wearable IoT devices have saved healthcare workers time and effort, according to medical regulations. The following mechanism helps with early diagnosis, quarantine, and patient monitorization has been performed with 68% saving time. This investigation aims to keep physicians and researchers can be updated about elderly patients covid 19 health issues while protecting their safety and health. Temperature and pulse sensors are used to check primary patient information. If heart rate or body temperature exceeds a safe level, IOT warning devices can give an indication. The designed application has achieved a sensitivity of 98.53%, an accuracy of 98.63%, a throughput of 97.98%, and a monitoring rate of 98.21%. The employed application is very helpful to researchers and doctors for easy treatment & covid 19 prevention. The proposed IoT-based automated health monitoring application strives with present technology and better method. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Advanced Deep Learning Based Three-Stream Hybrid Model for Dynamic Hand Gesture Recognition

arXiv

引用

arXiv 2024年

作者： Rahim, Md Abdur Miah, Abu Saleh Musa Akash, Hemel Sharker Shin, Jungpil Hossain, Imran Hossain, Najmul Department of Computer Science and Engineering Pabna University of Science and Technology Rajapur Pabna6600 Bangladesh School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Fukushima9658580 Japan Department of Information and Communication Engineering Pabna University of Science and Technology Rajapur Pabna6600 Bangladesh Department of Electrical Electronic and Communication Engineering Pabna University of Science and Technology Rajapur Pabna6600 Bangladesh

In the modern context, hand gesture recognition has emerged as a focal point. This is due to its wide range of applications, which include comprehending sign language, factories, hands-free devices, and guiding robots. Many researchers have attempted to develop more effective techniques for recognizing these hand gestures. However, there are challenges like dataset limitations, variations in hand forms, external environments, and inconsistent lighting conditions. To address these challenges, we proposed a novel three-stream hybrid model that combines RGB pixel and skeleton-based features to recognize hand gestures. In the procedure, we preprocessed the dataset, including augmentation, to make rotation, translation, and scaling independent systems. We employed a three-stream hybrid model to extract the multi-feature fusion using the power of the deep learning module. In the first stream, we extracted the initial feature using the pre-trained Imagenet module and then enhanced this feature by using a multi-layer of the GRU and LSTM modules. In the second stream, we extracted the initial feature with the pre-trained ReseNet module and enhanced it with the various combinations of the GRU and LSTM modules. In the third stream, we extracted the hand pose key points using the media pipe and then enhanced them using the stacked LSTM to produce the hierarchical feature. After that, we concatenated the three features to produce the final. Finally, we employed a classification module to produce the probabilistic map to generate predicted output. We mainly produced a powerful feature vector by taking advantage of the pixel-based deep learning feature and pos-estimation-based stacked deep learning feature, including a pre-trained model with a scratched deep learning model for unequalled gesture detection capabilities. The design of the proposed system is intended to be useful in challenging industrial situations and to create efficient, contactless interfaces. We conducted extens

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Effective Location-based Recommendation Systems for Holiday using RBM Machine Learning Approach 3

Effective Location-based Recommendation Systems for Holiday ...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Jayaraman, Ramkumar Karthikeyan, C. Sahaya Anselin Nisha, A. Somasundaram, K. Naga Saranya, N. Vijendra Babu, D. Srm Institue of Science and Technology Department of Computing Technology Tamil Nadu Kattankulathur India Koneru Lakshmaiah Education Foundation Computer Science and Engineering Andhra Pradesh Vaddeswaram India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Institute of Information Technology Saveetha School of Engineering Simats Tamil Nadu Chennai India Meenakshi College of Engineering Departement of Mca Tamil Nadu Chennai India Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Vellore India

ISBN: (纸本)9781665462167

Application developers and researchers took many steps in finding out proper tourism recommendations for various seasons. With the faster development in the travel department through modern technologies, it has gotten fundamental to present headways and upgrades in the administrations given to the sightseers, to ensure their ease of travel and satisfaction. Over the years, there has been no optimal system providing all the necessities required by a tourist. Based on the holidata recommendation, proposed system makes to decrease the time spent on the planning period and it helps to increase the deployment of process to be more effective. Regarding the customer preferences, the customer details and their location are shared and there are some other information available based on the users are, their destination trip, dates for the travel, budget and there are other user attractive aspects as it helps to have the effective trip. Based on the above things, the travel can be planned for the trip entirely. This system uses RBM to predict the user ratings and recommend the best attraction. An attempt has been made to reduce the MAE in RBM prediction. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A 24-32 GHz Single-Chip Harmonic Balance Power Amplifier for 5G MW Application

A 24-32 GHz Single-Chip Harmonic Balance Power Amplifier for...

引用

engineering and Technology (PICET), Parul International Conference on

作者： Rajesh Kumar Binod Kumar Kanaujia Tosif Abdul Gaffar Babu Devesh Tiwari Department of Computer Science Engineering Galgotias College of Engineering &Technology Greater Noida India Department of Electronics Communication of Engineering National Institute of Technology Jalandhar Jawaharlal Nehru University New Delhi India Department of Electronics & Communication of Engineering PIET Parul University Vadodara Gujarat India Department of Computer Science Engineering Graphic Science and Engineering Graphic Era Era Hill University Dehradun Uttarakhand India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

This article introduces the CM output-matching networks in the Balance architecture and discusses the theory and design process of a broadband RF-input Class-F PA balanced power amplifier. The harmonic balance network ensures the operation of second and third-harmonic and determines output impedance for wideband response. The input MN is considered a band-pass filter. The reactance is taken from IMN. It stabilized the operation of the design. The suggested HBPA's results show an output power of up to 30. 6 dBm, more peak power-added efficiency (PAE) of 68.5 % at 27 GHz, and a small signal gain of less than 12 dB. Over the 24–30 GHz range, saturated output power (Psat) and uniform gain are both reached with variations of less than 0.8 dB.

关键词： Broadband amplifiers Power amplifiers computer architecture Harmonic analysis Impedance Power harmonic filters Power generation Gain Wideband Optimization

来源：评论

学校读者我要写书评

暂无评论

Micro-Expression Recognition Based On 3DCNN Combined With GRU and New Attention Mechanism

Micro-Expression Recognition Based On 3DCNN Combined With GR...

引用

IEEE International Conference on Image Processing

作者： Chun-Ting Fang Tsung-Jung Liu Kuan-Hsien Liu Department of Electrical Engineering and Graduate Institute of Communication Engineering National Chung Hsing University Taichung Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Micro-expressions, as a form of non-verbal emotional expressions, play a key role in interpersonal interaction. However, they are also quite challenging and not easy to analyze. In this paper, we propose a dual-branch shallow 3DCNN architecture that combines Gated Recurrent Unit (GRU) and enhances the Channel Attention Module (CAM) in Convolutional Block Attention Module (CBAM) to make it more suitable for recognizing micro facial expressions. Experiments show that the proposed method can achieve good results with a relatively simple architecture. The source code and pre-trained models are available at https://***/dannyFan-0201/ICIP_2024.

关键词： Convolutional codes Gold Attention mechanisms Image recognition Source coding Face recognition Logic gates

来源：评论

学校读者我要写书评

暂无评论

A Novel Fast Path Planning Approach for Mobile Devices using Hybrid Quantum Ant Colony Optimization Algorithm

arXiv

引用

arXiv 2023年

作者： Sarkar, Mayukh Pradhan, Jitesh Singh, Anil Kumar Nenavath, Hathiram Department of Computer Science and Engineering National Institute of Technology Jamshedpur India Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad India Department of Electronics and Communication Engineering National Institute of Technology Jamshedpur India

With IoT systems' increasing scale and complexity, maintenance of a large number of nodes using stationary devices is becoming increasingly difficult. Hence, mobile devices are being employed that can traverse through a set of target locations and provide the necessary services. In order to reduce energy consumption and time requirements, the devices are required to traverse following a Hamiltonian path. This problem can be formulated as a Travelling Salesman Problem (TSP), an NP-hard problem. Moreover, in emergency services, the devices must traverse in real-time, demanding speedy path planning from the TSP instance. Among the well-known optimization techniques for solving the TSP problem, Ant Colony Optimization has a good stronghold in providing good approximate solutions. Moreover, ACO not only provides near-optimal solutions for TSP instances but can also output optimal or near-optimal solutions for many other demanding hard optimization problems. However, to have a fast solution, the next node selection, which needs to consider all the neighbors for each selection, becomes a bottleneck in the path formation step. Moreover, classical computers are constrained to generate only pseudorandom numbers. Both these problems can be solved using quantum computing techniques, i.e., the next node can be selected with proper randomization, respecting the provided set of probabilities in just a single execution and single measurement of a quantum circuit. Simulation results of the proposed Hybrid Quantum Ant Colony Optimization algorithm on several TSP instances have shown promising results, thus expecting the proposed work to be important in implementing real-time path planning in quantum-enabled mobile devices. © 2023, CC BY.

关键词： Traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Diabetes Prediction Using Machine Learning Algorithms 8

Diabetes Prediction Using Machine Learning Algorithms

引用

8th International Conference on Advanced Computing and communication Systems, ICACCS 2022

作者： Jana, S. Bharanidharan, N. ShanmukhaNagasai, P. Saravan Kumar, K. Mani Nageshwar, V. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Dayananda Sagar University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665408165

Diabetes patients with poor control is a kind of diabetes that affects the body's metabolism characterized by an abnormal rise in blood sugar levels due to insulin deficiency, tissue insulin sensitivity, or both. In the sphere of medicine, the diabetes system is quite beneficial. Diabetes prevention is critical, and utmost caution should be exercised to avoid it. Diabetes has now become a frequent condition affecting People of different ages, from toddlers to senior citizens. It is possible to control diabetes if it is detected early enough. Machine learning algorithms are utilized in the health-care system to carry out this analytical method. In order to conduct medical diagnostics, to analyze vast amounts of medical data and build machine learning models, methods of machine learning are utilized. The application of machine learning Models are created using data received from patients, users can improve their prediction results. To achieve this goal, we'll employ a variety of machine learning techniques to perform early diabetes prediction in a human body or a patient faster and more accurately. Techniques for machine learning, by constructing models from datasets obtained from patients, we can improve your prediction results. This model will predict diabetes using a dataset, we used Machine Learning Classification and ensemble techniques. K-nearest neighbor, Decision Tree and Random Forest are the three types of method. When compared to other models, the accuracy of each model is varied. It reveals that the model is capable of accurately predicting diabetes with a high level of accuracy. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Modelling and Performance Analysis of Physical and Electrical Properties of BaZrS3 Chalcogenide Perovskite Solar Cells

Modelling and Performance Analysis of Physical and Electrica...

引用

International Conference on Numerical Simulation of Optoelectronic Devices, (NUSOD)

作者： Devansh Gahlawat Jaspinder Kaur Rikmantra Basu Ajay Kumar Sharma Uma Rani Department of Electronics and Communication Engineering National Institute of Technology Delhi New Delhi India Department of Computer Science and Engineering National Institute of Technology Delhi New Delhi India Department of Computer Science and Engineering Dr. Akhilesh Das Gupta Institute of Professional Studies New Delhi India

ISBN: (数字)9798350390537

ISBN: (纸本)9798350390544

This study explores the application and utility of BaZrS3-based perovskite solar cells (PSCs) for thin-film photovoltaic applications. The proposed device exhibited stable current up to 1.1 eV and maintained over 65% quantum efficiency across a broad spectrum. The Mott-Schottky analysis indicated a bandgap of approximately 1.7 eV. Nyquist and Bode plots confirmed robust impedance behaviour. The device displayed $\mathbf{V}_{\text{oc}}=1.33\ \mathrm{V}, \mathbf{J}_{\mathbf{sc}}$ = 16.56 mA/cm2, FF = 83.97%, and Efficiency = 18.58%. BaZrS3's exceptional optical and electrical properties, coupled with environmental stability, position it as a promising material for advanced PSCs.

关键词： Photovoltaic systems Chalcogenides Photonic band gap Photovoltaic cells Perovskites Stability analysis Numerical models Performance analysis Impedance Standards

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：