检索结果-内蒙古大学图书馆

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

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

Single Cell Ejection from Peripheral Blood Mononuclear Cells (PBMC) Into Oil-Coated 96-Well Plate 38

Single Cell Ejection from Peripheral Blood Mononuclear Cells...

引用

38th IEEE International Conference on Micro Electro Mechanical Systems, MEMS 2025

作者： Esfahani, Kianoush Sadeghian Neff, Baptiste Roy, Akash Sengupta, Anik Kim, Eun S. University of Southern California Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331508890

This paper presents a droplet-based technique for contactless and damage-free extraction of single or few cells from suspended mononuclear cells into a conventional 96-well plate for quantitative Polymeric Chain Reaction (qPCR). An acoustic droplet ejector is used to eject leukemia peripheral blood mononuclear cells (PBMC) suspended in an aqueous solution as a droplet into each well of a commercial 96-well plate with its U-bottom coated with oil. The ejected cell(s) with an aqueous solution are automatically encapsulated in the oil in the Ubottom, and thus the evaporation of the aqueous cell medium (of a few nL) is minimized, resulting in live cells for hours. © 2025 IEEE.

关键词： Ejectors (pumps)

来源：评论

学校读者我要写书评

暂无评论

Decoupled Double Synchronous Reference Frame Sequence Extraction Technique: A Compact Review on Applications in Microgrids 9

Decoupled Double Synchronous Reference Frame Sequence Extrac...

引用

9th International Conference on Technology and Energy Management, ICTEM 2024

作者： Mousavi, Mohammad Hossein Ahmadi, Mojtaba Moradi, Hassan Razi University Department of Computer and Electrical Engineering Kermanshah Iran

ISBN: (纸本)9798350329797

Unbalanced voltages and currents, harmonic distortions, and faulty conditions are inevitable in microgrids. Failure to balance network parameters, breakdowns in eliminating harmonic distortions, and malfunctioning operation of protection systems can cause irreversible damage to the network. One particularly effective way to combat these severe conditions is to isolate the positive and negative sequence components of systems under fault. The decoupled double synchronous reference frame (DDSRF) sequence extraction method is a potent and accurate technique that involves transforming the three-phase signals from the time domain into a rotating reference frame. By following the DDSRF configuration, the positive and negative sequence components become decoupled. This simplifies the control and management of these components. Hence, through an in-depth analysis of existing research and developments, this review highlights the key structures and applications associated with different DDSRF approaches within the microgrids. © 2024 IEEE.

关键词： Harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Voltage-Sag Origin Detection in Smart Grids for Enhanced Resiliency

Voltage-Sag Origin Detection in Smart Grids for Enhanced Res...

引用

2024 IEEE International Conference on Green Energy and Smart Systems, GESS 2024

作者： Mustafa, Ahmed M. Nassar, Mohammed E. Salama, M.M.A. University of Waterloo Department of Electrical and Computer Engineering Waterloo Canada

ISBN: (纸本)9798350379617

The prompt and precise identification of voltage-sags in smart grids is crucial to manage voltage-sag mitigation, system restoration, and recovery effectively while ensuring the security and resiliency of the grid. Given that faults are a primary cause of voltage-sag events, accurately detecting these faults can significantly speed up the mitigation and recovery process. However, as the adoption of Inverter-based Resources (IBRs) increases, traditional fault-detection schemes have become inadequate because they overly depend on evaluating fault currents, which are limited by these IBRs. This paper introduces a methodology for detecting and identifying the origin of voltage sags, enabling the determination of whether a fault is located upstream or downstream from the system's PCC. The simulation results show that the technique is faster and more efficient compared to existing methods in the literature. The proposed fault detection algorithm utilizes a voltage/current estimation technique in combination with Tellegen's theorem to pinpoint the accurate geographical location of the voltage-sag origin in Active Distribution Systems (ADSs). A case study is conducted on a modified IEEE 33-bus distribution network with a three-phase balanced 12.66 kV system, incorporating IBRs throughout the network, to evaluate the algorithm's effectiveness. © 2024 IEEE.

关键词： Power grids

来源：评论

学校读者我要写书评

暂无评论

Dynamic Control for Coverage Maximization in Mobile Sensor Networks 10

Dynamic Control for Coverage Maximization in Mobile Sensor N...

引用

10th IEEE International Symposium on Systems engineering, ISSE 2024

作者： Zamani, Najmeh Aghdam, Amir G. Concordia University Department of Electrical and Computer Engineering Montreal Canada

ISBN: (纸本)9798350353723

In this paper, a new distributed approach for maximizing coverage in a mobile sensor network is proposed. Some results from the multi-agent systems theory are used to generate a control signal composed of both the velocity consensus term and gradient vector to enhance coverage. It is shown that by selecting appropriate parameters, all sensors in the network move to appropriate positions to maximize coverage. The proposed approach is computationally more efficient than the existing results, while the sensors' energy consumption is also less than the methods reported in the literature. The stability and convergence of the proposed algorithm are proved using the modified LaSalle's invariance method. Simulations confirm the effectiveness of the control strategy. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Hot carrier extraction in plasmon integrated TiO2 anodes for enhanced photoelectrochemical activity

Hot carrier extraction in plasmon integrated TiO2 anodes for...

引用

2024 Photonics North, PN 2024

作者： Chaulagain, Narendra Vahidzadeh, Ehsan Vrushabendrakumar, Damini Shankar, Karthik Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

ISBN: (纸本)9798350366365

Hybrid carbon nitride/titanium dioxide heterojunction photoanodes consisting of buried plasmonic Au nanoislands (AuNI) and/or decorated with Au nanoparticles (AuNP) exhibited remarkable photoelectrochemical (PEC) performance for water splitting in the visible-light regime due to successful harvesting of plasmonic hot carriers. In this work, we present distinct architectures for efficient harvesting of plasmonic hot carriers. © 2024 IEEE.

关键词： Heterojunctions

来源：评论

学校读者我要写书评

暂无评论

Advanced gate-level glitch modeling using ANNs 24

Advanced gate-level glitch modeling using ANNs

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Vagenas, Anastasis Garyfallou, Dimitrios Evmorfopoulos, Nestor Stamoulis, George Department of Electrical and Computer Engineering University of Thessaly Volos Greece

ISBN: (纸本)9798400706011

Multiple Input Switching (MIS) effects commonly induce undesired glitch pulses at the output of CMOS gates, potentially leading to circuit malfunction and significant power consumption. Thus, accurate and efficient glitch modeling is crucial for the design of high-performance, low-power, and reliable ICs. In this work, we present a new gate-level approach for modeling glitch effects under MIS. Unlike previous studies, we leverage efficient Machine Learning (ML) techniques to accurately estimate the glitch shape characteristics, propagation delay, and power consumption. To this end, we evaluate various ML engines and explore different Artificial Neural Network (ANN) architectures. Moreover, we introduce a seamless workflow to integrate our ANNs into existing standard cell libraries, striking an optimal balance between model size and accuracy in gate-level glitch modeling. Experimental evaluation on gates implemented in 7 nm FinFET technology demonstrates that the proposed models achieve an average error of 2.19% against SPICE simulation while maintaining a minimal memory footprint. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： SPICE

来源：评论

学校读者我要写书评

暂无评论

Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach 1

Empowering Persian LLMs for Instruction Following: A Novel D...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Mokhtarabadi, Hojjat Zamani, Ziba Maazallahi, Abbas Manshaei, Mohammad Hossein Department of Electrical and Computer Engineering Isfahan University of Technology Iran Department of Computer Engineering Shahid Bahonar University of Kerman Iran Department of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Computer Science Hunter College City University of New York NY United States

ISBN: (纸本)9798891762152

Instruction-tuned large language models have demonstrated remarkable capabilities in following human instructions across various domains. However, their proficiency remains notably deficient in many low-resource languages. To address this challenge, we begin by introducing FarsInstruct: a comprehensive instruction dataset designed to enhance the instruction-following ability of large language models specifically for the Persian language—a significant yet underrepresented language globally. FarsInstruct encompasses a wide range of task types and datasets, each containing a mix of straightforward to complex manual written instructions, as well as translations from the Public Pool of Prompts, ensuring a rich linguistic and cultural representation. Furthermore, we introduce Co-CoLA, a framework designed to enhance the multi-task adaptability of LoRA-tuned models. Through extensive experimental analyses, our study showcases the effectiveness of the FarsInstruct dataset coupled with training by the Co-CoLA framework, in improving the performance of large language models within the Persian context. As of the current writing, FarsInstruct comprises 197 templates across 21 distinct datasets, and we intend to update it consistently, thus augmenting its applicability. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Improving Transient Response of a Battery Energy Storage System with Minimized DC Capacitors

Improving Transient Response of a Battery Energy Storage Sys...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Mazloum, Neda Ali Khajehoddin, S. University of Alberta Electrical and Computer Engineering Department Edmonton Canada

ISBN: (纸本)9798350364446

Battery Energy Storage Systems (BESSs) are widely adopted in electric vehicles, aircraft, and residential units. Current market trends for low and medium-power BESSs require the achievement of maximum efficiency and power density to enhance cost-effectiveness and long-term energy savings. The DC-link capacitance of the charger-inverter system can be reduced through the application of advanced control systems. However, this reduction in the energy storage capacity can result in over/under voltage issues during sudden load changes. To address this, the control system must maintain the bus voltage within an acceptable range by ensuring rapid transient response and efficient energy transfer to the battery. To overcome this challenge, two nested control loops are proposed and designed in this paper which enhance the transient response and offer a systematic design approach. The paper covers discussions on system modeling, the control design methodology, as well as simulation and experimental results. The experimental results reveal that the proposed approach can significantly improve the bus voltage transients, compared with the conventional methods. © 2024 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Mean-Based Approach To Omnidirectional Pathfinding Algorithm Using Single Ultrasonic Sensor For Robotic Car

Mean-Based Approach To Omnidirectional Pathfinding Algorithm...

引用

2024 IEEE International Students' Conference on electrical, Electronics and computer Science, SCEECS 2024

作者： Tandon, Anvit Sah, Shubham Gawre, Suresh Kumar Iiit Bhopal Department of Computer Science and Engineering India Manit Bhopal Department of Electrical Engineering India

ISBN: (纸本)9798350348460

Our project centers around creating and practically testing a pathfinding algorithm using a single ultrasonic sensor on a test RC car. The algorithm consists of two phases: normal and intensive detection. This algorithm provides a reliable method for determining an obstacle-free path. The intensive detection method uses a servo motor for a broader field of view, thus creating an omnidirectional composite sensor with just one monodirectional sensor. It reduces the number of potential false positives for the ideal path by a mean-based approach. © 2024 IEEE.

关键词： Arduino UNO DC Motors H-W 130 Motor Shield Servo Motor Ultrasonic Sensor

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：