检索结果-内蒙古大学图书馆

4th International Conference on Advancement in electronics and communication engineering, AECE 2024

作者： Aadarsh, Nishchay Gupta, Shiv Narain Mohan, Jitendra Chaturvedi, Bhartendu Greater Noida Institute of Technology Department of Electronics and Communication Engineering Greater Noida India Jaypee Institute of Information Technology Department of Electronics and Communication Engineering Noida India

ISBN: (纸本)9798350364729

In this article a novel approach to design a sinusoidal oscillator using the versatile Extra-X second generation current conveyor, in conjunction with passive components, namely three resistors and two grounded capacitors is presented. The proposed oscillator configuration is tailored for integrated circuit implementation, offering a compact and efficient solution for various electronic applications. The proposed circuit can generate sinusoidal signal whose condition of oscillation and oscillation frequency can be independently controlled using grounded resistors. By utilizing PSPICE with 0.18 μm CMOS process parameters, the performance of the proposed oscillator is validating on computer simulations. The designed oscillator provides a stable oscillating frequency of 1.9 MHz, demonstrating high spectral purity in Fourier analysis, with a low power consumption of 2.4 mW, suitable for efficient applications. © 2024 IEEE.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

Subterranean Vegetable Sorting with YOLO Models and Flask Framework

Subterranean Vegetable Sorting with YOLO Models and Flask Fr...

引用

2025 International Conference on Control, Automation, and Instrumentation, IC2AI 2025

作者： Rakesh, M.D. Ronitha, R. Rudraswamy, S.B. JSS Science and Technology University Dept. of Electronics and Communication Engineering SJCE Mysuru India JSS Science and Technology University Dept. of Electronics and Communication Engineering Mysuru India

ISBN: (数字)9798331529604

ISBN: (纸本)9798331529604

The integration of advanced deep learning models, such as YOLOv5 and YOLOv8, into carrot cultivation significantly enhances post-harvest sorting systems, allowing for the effective differentiation between healthy and rotten carrots. This work streamlines the sorting process, ensuring that only high-quality produce reaches the market, thereby providing substantial advantages for traders. By automating this procedure, farmers can improve food safety, monitor shelf life, and enhance customer satisfaction, ultimately increasing productivity and profitability. The system employs convolutional neural networks (CNNs) to analyze visual data captured during harvest or post-harvest stages. These models are trained to identify distinguishing features of carrots, such as color changes, texture anomalies, and shape deformations, resulting in precision rates of 98.3% and 96.4% in identifying freshness with YOLOv8 and YOLOv5 respectively, and 96.5% and 93.6% in detecting rotten. Extensive training and evaluation have demonstrated notable improvements in performance metrics, validating the effectiveness of these models. As a prototype, we have developed a Flask web application for detecting whether carrots are rotten or fresh. This system significantly enhances productivity by allowing for quick and accurate assessment of carrot quality. The adoption of this AI-driven technology marks a transformative step toward optimizing resource management and maximizing crop value in modern agriculture. © 2025 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Hybrid attention residual deep convolution learning network for bio medical image analysis

引用

Journal of Intelligent and Fuzzy Systems 2025年第4期48卷 537-554页

作者： Sundar Raj, A. Naidu, Paruchuri Chandra Babu Sivakumar, S. Senthilkumar, S. Department of Biomedical Engineering E.G.S. Pillay Engineering College Tamilnadu Nagapattinam India Department of Electrical and Electronics Engineering BSA Crescent Institute of Science and Technology Vandalur Tamilnadu Chennai India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Tamilnadu Coimbatore India Department of Electronics and Communication Engineering E.G.S. Pillay Engineering College Tamilnadu Nagapattinam India

Biomedical image analysis has progressed significantly with the integration of artificial intelligence, presenting new opportunities for early diagnosis and treatment of diseases with high mortality rates, such as skin cancer. This research work introduces a novel Hybrid Attention Residual Deep Convolution Learning (HARDCL) Model designed to enhance the accuracy of skin lesion classification, which is often challenging due to the subtle characteristics of lesions. The HARDCL Network employs an innovative hybrid attention mechanism within a residual learning framework, effectively distinguishing between benign and melanoma skin lesions with a high degree of precision. The encoder-decoder network segments the lesion from dermoscopic images, followed by feature extraction and classification, achieving a maximum accuracy of 97.11%, precision of 98.10%, recall of 98.81%, and an F1-score of 98.45%. This performance surpasses conventional deep learning algorithms such as AlexNet, InceptionV3, and ResNet18, demonstrating the effectiveness of the attention-based features in identifying critical lesion characteristics. However, despite its strengths, the HARDCL Network’s computational intensity and the need for a substantial dataset for optimal training highlight areas for further refinement. The proposed network advances the field of skin cancer diagnostics, offering a robust tool for medical professionals and setting a foundation for future enhancements in automated biomedical image analysis techniques. © 2025 – IOS Press. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Joint Transmit and Reflective Beamforming Design for Active IRS-Aided SWIPT Systems

引用

Chinese Journal of electronics 2024年第2期33卷 536-548页

作者： Weiping SHI Qingqing WU Di WU Feng SHU Jiangzhou WANG School of Electronic and Optical Engineering Nanjing University of Science and Technology Department of Electronic Engineering Shanghai Jiao Tong University School of Information and Communication Engineering Hainan University Department of Automation Shanghai Jiao Tong University School of Engineering University of Kent

To further improve the performance of passive intelligent reflecting surface(IRS)-assisted communication systems and mitigate the serious path loss due to “double-fading ” of IRS-assisted links, an active IRS-aided simultaneous wireless information and power transfer(SWIPT) system is investigated. This paper jointly optimizes the transmit beamforming at the base station(BS) and the phase shifts at the active IRS in order to maximize the power collected by the energy harvesting receiver under both perfect and imperfect channel state information(CSI)states, subject to the signal-to-interference-noise ratio constraint of the information decoding receiver, and the power constraints of the BS/IRS. Under perfect CSI, the alternating optimization algorithm is utilized for obtaining the transmit beamforming at the BS and the phase shifts at the active IRS. For each subproblem, we first transform nonconvex objective function and constraints into convex ones by performing a first-order Taylor expansion. Then, each subproblem is solved by using the interior point method. Given that obtaining perfect CSI is impractical, two robust beamforming designs are proposed for imperfect CSI case. Under the bounded CSI error model, we first transform the non-convex optimization problem into two semidefinite programming subproblems, and then solve each subproblem based on S-procedure and sequential rank-one constraint relaxation(SROCR) techniques. Under the stochastic CSI error model, the alternating optimization method is applied in an iterative manner based on Bernstein-type inequality and SROCR technique. Simulation results show that both robust and non-robust schemes for active IRS-assisted SWIPT systems can achieve extremely superior performance over conventional passive IRS-assisted systems under the same overall power budget.

关键词： Active intelligent reflecting surface Energy harvesting Perfect channel state information Imperfect channel state information Simultaneous wireless information and power transfer

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Clustering-Based (k, t)-Anonymity Algorithm for Graphs

引用

Chinese Journal of electronics 2025年第1期34卷 365-372页

作者： Yuanyuan Wang Xing Zhang Zhiguang Chu Wei Shi Xiang Li School of Electronics and Information Engineering Liaoning University of Technology Key Laboratory of Security for Network and Data in Industrial Internet of Liaoning Province Faculty of Information Technology Beijing University of Technology

As people become increasingly reliant on the Internet, securely storing and publishing private data has become an important issue. In real life, the release of graph data can lead to privacy breaches, which is a highly challenging problem. Although current research has addressed the issue of identity disclosure, there are still two challenges: First, the privacy protection for large-scale datasets is not yet comprehensive; Second, it is difficult to simultaneously protect the privacy of nodes, edges, and attributes in social networks. To address these issues, this paper proposes a(k,t)-graph anonymity algorithm based on enhanced clustering. The algorithm uses k-means++ clustering for k-anonymity and t-closeness to improve k-anonymity. We evaluate the privacy and efficiency of this method on two datasets and achieved good results. This research is of great significance for addressing the problem of privacy breaches that may arise from the publication of graph data.

关键词： Data privacy Uncertainty Social networking (online) Publishing Heuristic algorithms Scalability Clustering algorithms Privacy breach Internet Protection

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Logic Despeckling in Non-Subsampled Contourlet Transformed Ultrasound Pictures

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 2755-2771页

作者： T.Manikandan S.Karthikeyan J.Jai Jaganath Babu G.Babu Department of Electronics and Communication Engineering Rajalakshmi Engineering CollegeChennai602105India Department of Electronics and Communication Engineering Velammal Institute of TechnologyChennai601204India Center for System Design Chennai Institute of TechnologyChennai600069India Department of Bio-Medical Engineering Easwari Engineering CollegeChennai600089India

Signal to noise ratio in ultrasound medical images captured through the digital camera is poorer,resulting in an inaccurate *** a result,it needs an efﬁcient despeckling method for ultrasound images in clinical practice and *** article proposes a novel adaptive fuzzyﬁlter based on the direc-tionality and translation invariant property of the Non-Sub sampled Contour-let Transform(NSCT).Since speckle-noise causes fuzziness in ultrasound images,fuzzy logic may be a straightforward technique to derive the output from the noisy ***ﬁltering method comprises detection andﬁltering ***,image regions classify at the detection stage by applying fuzzy inference to the directional difference obtained from the NSCT noisy ***,the system adaptively selects the better-suitedﬁlter for the speciﬁc image region,resulting in signiﬁcant speckle noise suppression and retention of detailed *** suggested approach uses a weighted averageﬁlter to distinguish between noise and edges at theﬁltering *** addition,we apply a structural similarity mea-sure as a tuning parameter depending on the kind of noise in the ultrasound *** proposed methodology shows that the proposed fuzzy adaptiveﬁlter effectively suppresses speckle noise while preserving edges and image detailed structures compared to existing approaches.

关键词： Image processing fuzzy logic directional differences classiﬁcation ultrasound technology

来源：评论

学校读者我要写书评

暂无评论

An AI-Enhanced IoT Model for Three-Way Authentication and Location Tracking in Secured Jewellery Boxes 5

An AI-Enhanced IoT Model for Three-Way Authentication and Lo...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Sundararajan, S. Darney, P.Ebby Rajan, K.Palanivel Fernando, A. Vegi Jothi, J.Nirmal Krishnan, R.Santhana SCAD College of Engineering and Technology Department of Mechanical Engineering Cheranmahadevi India RajaRajeswari College of Engineering Department of Electrical and Electronics Engineering Bangalore India PSNA College of Engineering and Technology Department of Electronics and Communication Engineering Dindigul India Karnataka Bengaluru India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India SCAD College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India

ISBN: (纸本)9798350395235

Securing valuable assets has become imperative in contemporary contexts, with a particular emphasis on safeguarding precious items such as jewellery. This research introduces a comprehensive solution for enhancing the security of jewellery boxes through a novel TripleFuse Recognition Algorithm (TFRA). TFRA integrates Convolutional Neural Networks (CNN) for Fingerprint Recognition, Support Vector Machines (SVM) for Barcode Recognition, and Recurrent Neural Networks (RNN) for OTP Authentication. The algorithm is coupled with an Internet of Things (IoT) model utilizing the Message Queuing Telemetry Transport (MQTT) protocol, facilitating efficient communication and data exchange between the jewellery box and the authentication components. To evaluate the effectiveness of TFRA, simulation analyses are conducted and compared with established algorithms in the field. The simulation metrics include accuracy, precision, recall, and F1-score. TFRA exhibits superior performance in achieving high accuracy rates, ensuring robust Fingerprint Recognition, Barcode Recognition, and OTP Authentication. Furthermore, the proposed model demonstrates enhanced efficiency in communication and data transfer through the MQTT protocol within the IoT framework. Comparative analyses with existing algorithms underscore TFRA's efficacy, particularly in achieving a harmonious synergy between diverse recognition tasks. The results indicate that TFRA not only surpasses its counterparts in terms of authentication accuracy but also offers an optimized solution for real-time location tracking within the secured jewellery box. This research contributes to the burgeoning field of IoT-based security applications, providing a comprehensive solution for safeguarding valuable assets. The proposed TFRA algorithm, integrated into an advanced IoT model, demonstrates promising results in the context of three-way authentication and location tracking for secured jewellery boxes. © 2024 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

An mmWave Dual-Band Integrated Substrate Gap Waveguide Single Cavity Filter with Frequency Selectivity

引用

China communications 2024年第1期21卷 188-199页

作者： Qiuhua Lin Dongya Shen Lihui Wang Zhiyong Luo School of Electronics and Communication Engineering Sun Yat-sen UniversityShenzhen 518107China School of Information Science and Engineering Yunnan UniversityKunming 650091China Pengcheng Laboratory Shenzhen 518107China Shenzhen Key Laboratory of Navigation and Communication Integration Shenzhen 518107China

A novel dual-band ISGW cavity filter with enhanced frequency selectivity is proposed in this paper by utilizing a multi-mode coupling *** cavity is designed to control the number of modes,and then the ports are determined by analyzing the coupling relationship between these selected *** synthesizing the coupling matrix of the filter,a nonresonating node(NRN)structure is introduced to flexibly tune the frequency of modes,which gets a dualband and quad-band filtering response from a tri-band filter no the ***,a frequency selective surface(FSS)has been newly designed as the upper surface of the cavity,which significantly improves the bad out-of-band suppression and frequency selectivity that often exists in most traditional cavity filter designs and *** results show that its two center frequencies are f01=27.50 GHz and f02=32.92GHz,*** with the dual-band filter that there is no the FSS metasurface,the out-of-band suppression level is improved from measured 5 dB to18 dB,and its finite transmission zero(FTZ)numbers is increased from measured 1 to 4 between the two designed *** with the tri-band and quadband filter,its passband bandwidth is expanded from measured 1.17%,1.14%,and 1.13% or 1.31%,1.50%,0.56%,and 0.57% to 1.71% and 1.87%.In addition,the filter has compact,small,and lightweight characteristics.

关键词： coupling topology frequency selectivity non-resonating node(NRN) out-of-band suppression single ISGW cavity filter

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of 3GPP-Standard Driven Polar Coded Modulation for 5G

Performance Evaluation of 3GPP-Standard Driven Polar Coded M...

引用

2024 IEEE Wireless Antenna and Microwave Symposium, WAMS 2024

作者： Mazumder, Lopamudra Ghosal, Sandip Indian Institute of Technology Kharagpur Electronics and Electrical Communication Engineering Kharagpur721302 India National Institute of Technology Rourkela Electronics and Communication Engineering Rourkela769008 India

ISBN: (纸本)9798350358926

This work provides a comparative study of the 5G new radio (NR) polar coding with different symbol modulation techniques and different delay profiles of NLOS channel. It has been observed that for the same remaining configurations, the block error rate and the block length error rate performances require higher amount of bit to noise ratio in 16-QAM modulation compared to the BPSK and QPSK modulation in both uplink and downlink transmission scenarios. In the next section, the impact of modulation on the signal received in a physical downlink control channel have been studied for different tapped delay profiles. The reported analyses carried out using the 3GPP guideline based 5G new radio model blocks of MATLAB 5G Toolbox can be further utilized for designing standard based 5G waveforms in different practical scenarios. © 2024 IEEE.

关键词： Bit error rate

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：