检索结果-内蒙古大学图书馆

2023 IEEE Region 10 Symposium, TENSYMP 2023

作者： Furusawa, Tomoki Premachandra, Chinthaka Graduate School of Engineering and Science Shibaura Institute of Technology Electrical Engineering and Computer Science Tokyo Japan School of Engineering Shibaura Institute of Technology Department of Electronic Engineering Tokyo Japan

ISBN: (纸本)9781665482585

Unmanned aerial vehicles (UAVs) are being utilized for damage assessment in natural disasters and for search and rescue operations. Currently, the search for victims primarily relies on analyzing images captured by cameras mounted on UAVs. However, this approach has limitations when it comes to locating victims who are not within the camera's field of view. As a result, sound-based search methods are being considered. In this method, a voice message is transmitted to the disaster area through a speaker mounted on a UAV, and the presence of victims is confirmed by detecting their response using the onboard microphone of the UAV. Nevertheless, the UAV's microphone captures both the sound of the victim and the propeller rotation, posing a significant challenge in extracting the victim's voice from this combined audio. To address this issue, we propose a solution that involves generating spectrogram images of the sound mixture and the propeller sound, and extracting the human sound by subtracting them. We found that the conventional colormap was ineffective in emphasizing the human sound in the spectrogram images. To overcome this limitation, this paper introduces a new colormap based on the normal distribution. This colormap enhances human voices while attenuating propeller sounds by adjusting the mean and variance. Through the results of our experiments, we confirm that the proposed colormap effectively reduces propeller sound interference in the sound mixing and simultaneously emphasizes the voice of a disaster victim. By utilizing the proposed colormap, it becomes possible to visualize the victim's voice from the audio mixture acquired by the UAV's onboard microphone, enabling the identification of the victim. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Power-Measurement-Based Channel Autocorrelation Estimation for IRS-Assisted Wideband Communications

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 4647-4662页

作者： Sun, He Zhu, Lipeng Mei, Weidong Zhang, Rui National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications 611731 China The Chinese University of Hon g Kong School of Science and Engineering Shenzhen Research Institute of Big Data Guangdong Shenzhen518172 China

Channel state information (CSI) is essential to the performance optimization of intelligent reflecting surface (IRS)-aided wireless communication systems. However, the passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed practical challenges for efficient IRS channel estimation, especially in wideband communication systems with significant multi-path channel delay spread. To tackle the above challenge, we propose a novel neural network (NN)-empowered IRS channel estimation and passive reflection design framework for the wideband orthogonal frequency division multiplexing (OFDM) communication system based only on the user’s reference signal received power (RSRP) measurements with time-varying random IRS training reflections. As RSRP is readily accessible in existing communication systems, our proposed channel estimation method does not require additional pilot transmission in IRS-aided wideband communication systems. In particular, we show that the average received signal power over all OFDM subcarriers at the user terminal can be represented as the prediction of a single-layer NN composed of multiple subnetworks with the same structure, such that the autocorrelation matrix of the wideband IRS channel can be recovered as their weights via supervised learning. To exploit the potential sparsity of the channel autocorrelation matrix, a progressive training method is proposed by gradually increasing the number of subnetworks until a desired accuracy is achieved, thus reducing the training complexity. Based on the estimates of IRS channel autocorrelation matrix, the IRS passive reflection is then optimized to maximize the average channel power gain over all subcarriers. Numerical results indicate the effectiveness of the proposed IRS channel autocorrelation matrix estimation and passive reflection design under wideband channels, which can achieve significant performance improvement compared to the existing IRS re

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Volt-Var Control for Utility-scale Solar PV Plants to Replace SVCs 4

Volt-Var Control for Utility-scale Solar PV Plants to Replac...

引用

4th International Conference on High Voltage engineering and Power Systems, ICHVEPS 2023

作者： Shimomukai, Ken Maeda, Haruka Fujita, Goro Shibaura Institute of Technology Functional Control Systems Graduate School of Engineering and Science Tokyo Japan Shibaura Institute of Technology Graduate School of Engineering and Science Department of Electrical Engineering and Computer Science Tokyo Japan Shibaura Institute of Technology Department of Electrical Engineering Tokyo Japan

ISBN: (纸本)9798350318678

One way to increase solar photovoltaic penetration in the grid is management of voltage fluctuations. This is because a photovoltaic plant cannot be interconnected to the grid if it causes voltage violations. Voltage violation is where voltage exceeds the acceptable range. Often, grid operators request photovoltaic plant owners to regulate voltage sufficiently with expensive and space-consuming static Var compensators. Unfortunately, this sometimes makes the project less feasible. This paper argues that there are better ways to regulate voltage. We ran a simulation with a 70 MWp photovoltaic plant as an addition to the grid. Without voltage regulation, voltage violations were found to be significant. This paper found that oversizing the inverter sufficiently would remove all voltage violations without deploying a static Var compensator. This is often a cheaper and space-saving solution for voltage management. This paper argues that economics and spatial efficiency of reactive power compensation devices is key to increasing photovoltaic penetration. © 2023 IEEE.

关键词： Reactive power

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Precision Agriculture: Weed and Cotton Crop Classification Using YOLO and Faster RCNN

Deep Learning Approaches for Precision Agriculture: Weed and...

引用

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Majeed, Asad Faridoon, Fatima Irfan, Muhammad Rashid, Ahmar Faculty of Computer Science and Engineering GIK Institute of Engineering Sciences and Technology Topi Pakistan Department of Electrical Engineering Sukkur IBA University Sukkur Pakistan

ISBN: (纸本)9798331504465

Weed infestation in cotton fields significantly challenges agricultural productivity by competing for essential nutrients and water resources. This study presents a comprehensive comparative analysis of two deep learning-based object detection models - YOLO and Faster R-CNN - for automated weed detection in cotton fields. We developed and annotated a custom dataset comprising field images captured under various environmental conditions, labelled in both COCO and YOLO formats using Label Studio. Performance evaluation revealed the YOLO model’s superior capabilities, achieving a mAP50 of 0.775, precision scores of 0.859 for cotton and 0.656 for weed detection, and recall rates of 0.849 and 0.543 for cotton and weed respectively on the test dataset. In comparison, Faster R-CNN showed lower performance with AP scores of 0.708 for cotton and 0.269 for weed detection, particularly struggling with objects of varying sizes. The YOLO model maintained consistent performance across both validation and test datasets, with validation metrics showing mAP50 of 0.982 and mAP50-95 of 0.829. These results establish YOLO’s effectiveness as a reliable tool for automated weed detection in cotton fields, offering a practical solution for precision agriculture applications. The developed model demonstrates the potential for integration into automated crop management systems, contributing to more efficient and targeted weed control strategies. © 2024 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Breast Mammogram Analysis and Classification Using Deep Convolution Neural Network

引用

computer Systems science & engineering 2022年第10期43卷 275-289页

作者： V.Ulagamuthalvi G.Kulanthaivel A.Balasundaram Arun Kumar Sivaraman Department of Computer Science and Engineering Sathyabama UniversityChennai600119India Department of Electrical Electronics and Communication EngineeringNITTTRChennai600113India Centre for Cyber Physical Systems School of Computer Science and EngineeringVellore Institute of Technology(VIT)Chennai600127India School of Computer Science and Engineering Vellore Institute of Technology(VIT)Chennai600127India

One of the fast-growing disease affecting women’s health seriously is breast *** is highly essential to identify and detect breast cancer in the earlier *** paper used a novel advanced methodology than machine learning algorithms such as Deep learning algorithms to classify breast cancer *** learning algorithms are fully automatic in learning,extracting,and classifying the features and are highly suitable for any image,from natural to medical *** methods focused on using various conventional and machine learning methods for processing natural and medical *** is inadequate for the image where the coarse structure matters *** of the input images are downscaled,where it is impossible to fetch all the hidden details to reach accuracy in *** deep learning algorithms are high efficiency,fully automatic,have more learning capability using more hidden layers,fetch as much as possible hidden information from the input images,and provide an accurate *** this paper uses AlexNet from a deep convolution neural network for classifying breast cancer in mammogram *** performance of the proposed convolution network structure is evaluated by comparing it with the existing algorithms.

关键词： Medical image processing deep learning convolution neural network breast cancer feature extraction classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging hierarchical semantic‐emotional memory in emotional conversation generation

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 824-835页

作者： Min Yang Zhenwei Wang Qiancheng Xu Chengming Li Ruifeng Xu Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhenChina School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaUSA School of Intelligent Systems Engineering Sun Yat‐Sen UniversityGuangzhouChina School of Computer Science Harbin Institute of Technology(Shenzhen)ShenzhenChina

Handling emotions in human‐computer dialogues has emerged as a challenging task which requires artificial intelligence systems to generate emotional responses by jointly perceiving the emotion involved in the input posts and incorporating it into the gener-ation of semantically coherent and emotionally reasonable ***,most previous works generate emotional responses solely from input posts,which do not take full advantage of the training corpus and suffer from generating generic *** this study,we introduce a hierarchical semantic‐emotional memory module for emotional conversation generation(called HSEMEC),which can learn abstract semantic conver-sation patterns and emotional information from the large training *** learnt semantic and emotional knowledge helps to enrich the post representation and assist the emotional conversation *** experiments on a large real‐world conversation corpus show that HSEMEC can outperform the strong baselines on both automatic and manual *** reproducibility,we release the code and data publicly at:https://***/siat‐nlp/HSEMEC‐code‐data.

关键词： deep learning emotional conversation generation semantic‐emotional memory

来源：评论

学校读者我要写书评

暂无评论

How do Software engineering Researchers Use GitHub? An Empirical Study of Artifacts & Impact 24

How do Software Engineering Researchers Use GitHub? An Empir...

引用

24th IEEE International Conference on Source Code Analysis and Manipulation, SCAM 2024

作者： Alrashedy, Kamel Binjahlan, Ahmed Georgia Institute of Technology School of Computer Science AtlantaGA United States Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA United States

ISBN: (纸本)9798331528508

Millions of developers share their code on open-source platforms like GitHub, which offer social coding opportunities such as distributed collaboration and popularity-based ranking. Software engineering researchers have joined in as well, hosting their research artifacts (tools, replication package & datasets) in repositories, an action often marked as part of the publication's contribution. Yet a decade after the first such paper-with-GitHub-link, little is known about the fate of such repositories in practice. Do research repositories ever gain the interest of the developer community, or other researchers? If so, how often and why (not)? Does effort invested on GitHub pay off with research impact? In short: we ask whether and how authors engage in social coding related to their research. We conduct a broad empirical investigation of repositories from published work, starting with ten thousand papers in top SE research venues, hand-Annotating their 3449 GitHub (and Zenodo) links, and studying 309 paper-related repositories in detail. We find a wide distribution in popularity and impact, some strongly correlated with publication venue. These were often heavily informed by the authors' investment in terms of timely responsiveness and upkeep, which was often remarkably subpar by GitHub's standards, if not absent altogether. Yet we also offer hope: popular repositories often go hand-in-hand with well-cited papers and achieve broad impact. Our findings suggest the need to rethink the research incentives and reward structure around research products requiring such sustained contributions. © 2024 IEEE.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Study on Screw Filtration System

Study on Screw Filtration System

引用

2023 IET International Conference on engineering Technologies and Applications, ICETA 2023

作者： Chuang, Ching-Chun Lin, Bo-Yu Department of Electrical Engineering National Kaohsiung University of Science and Technology Taiwan Department of Computer Science & Information Engineering National Formosa University Taiwan

ISBN: (纸本)9781839539848

This research focuses on developing a screw detection system using Yolo series object detection models and the OpenCV module. The plan uses a camera to detect and identify different types of screws on various production lines in real time. The Yolo series object detection models allow training custom objects to see corresponding screws. The performance of three models, yolov5s, yolov7-tiny, and yolov8n, is compared based on precision, recall, mAP, and loss to determine suitability. The study used four types of screws, namely screw_1, screw_2, screw_3, and screw_4, as examples of screw detection. Over 1000 images were collected for each type of screw, resulting in 5208 images used for training. In terms of screw detection, a GUI was developed using Python modules to control the detection system. The system provides visual confirmation of recognized screw patterns and displays errors if incorrect screws are detected. The experimental results indicate that in terms of precision, yolov7-tiny achieves the highest score among the Yolo models, followed by yolov8n and yolov5s. Regarding mAP, both yolov5s and yolov8n demonstrate high scores, while yolov7-tiny's mAP falls between 0.5 and 0.6, relatively lower than the other two models. In terms of loss, yolov7-tiny and yolov5s exhibit lower loss values, indicating better prediction results, while yolov8n has a higher loss, leading to poorer recognition performance. Regarding speed, yolov5s performs at 2.6ms, yolov7-tiny at 0.38ms, and yolov8n at 4.2ms. © The Institution of engineering & technology 2023.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache 41

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cach...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Zirui Yuan, Jiayi Jin, Hongye Zhong, Shaochen Xu, Zhaozhuo Braverman, Vladimir Chen, Beidi Hu, Xia Department of Computer Science Rice University United States Department of Computer Science Texas A&M University United States Department of Computer Science Stevens Institute of Technology United States Department of Electrical and Computer Engineering Carnegie Mellon University United States

Efficiently serving large language models (LLMs) requires batching many requests together to reduce the cost per request. Yet, the key-value (KV) cache, which stores attention keys and values to avoid re-computations, significantly increases memory demands and becomes the new bottleneck in speed and memory usage. This memory demand increases with larger batch sizes and longer context lengths. Additionally, the inference speed is limited by the size of KV cache, as the GPU's SRAM must load the entire KV cache from the main GPU memory for each token generated, causing the computational core to be idle during this process. A straightforward and effective solution to reduce KV cache size is quantization, which decreases the total bytes taken by KV cache. However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization. To fill the gap, we conducted a comprehensive study on the element distribution in KV cache of popular LLMs. Our findings indicate that the key cache should be quantized per-channel, i.e., group elements along the channel dimension and quantize them together. In contrast, the value cache should be quantized per-token. From this analysis, we developed a tuning-free 2bit KV cache quantization algorithm, named KIVI. With the hardware-friendly implementation, KIVI can enable Llama (Llama-2), Falcon, and Mistral models to maintain almost the same quality while using 2.6× less peak memory usage (including the model weight). This reduction in memory usage enables up to 4× larger batch size, bringing 2.35× ∼ 3.47× throughput on real LLM inference workload. The source code is available at https://***/jy-yuan/KIVI. Copyright 2024 by the author(s)

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach on Advanced Fruit Disease Identification Using RCNN

A Novel Approach on Advanced Fruit Disease Identification Us...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Kumar, R. Boopathi, P. Rajan, M. Sundar Bangalore India Shri Nehru College of Arts and Science Department of Computer Science Tamil Nadu Coimbatore India Arba Minch Institute of Technology Arba Minch University Faculty of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798331509828

The early diagnosis of diseases in fruits holds immense importance for agricultural industries, as it directly impacts production quality and quantity. This study introduces a novel approach utilizing Recursive Convolutional Neural Network (RCNN) for automated citrus plant disease detection. Through a comprehensive methodology involving data collection, image pre-processing, segmentation, feature extraction using Linear Principal Component Analysis (LPCA), and classification, the proposed RCNN algorithm showcases promising results. Experimental evaluation demonstrates the efficacy of the RCNN-based approach, with precision averaging at 0.929, recall at 0.946, accuracy at 0.945, F-measure at 0.943, and minimal time complexity. Compared to traditional manual inspection methods, RCNN offers a more accurate and efficient solution, significantly reducing the burden on farmers and experts while enhancing fruit disease detection capabilities. Overall, the proposed RCNN-based approach presents a significant advancement in fruit disease identification, offering precise and timely detection to mitigate agricultural losses. With its superior performance metrics and streamlined process, RCNN stands as a promising tool for revolutionizing fruit disease diagnosis and improving agricultural productivity. © 2025 IEEE.

关键词： Convolutional neural networks

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：