检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Yao, Jiawei Mao, Yijie Chen, Mingzhe School of Information Science and Technology ShanghaiTech University Shanghai China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL United States

Reconfigurable intelligent surface (RIS) has been recognized as a promising solution for enhancing localization accuracy. Traditional RIS-based localization methods typically rely on prior channel knowledge, beam scanning, and pilot-based assistance. These approaches often result in substantial energy and computational overhead, and require real-time coordination between the base station (BS) and the RIS. In this work, we propose a novel multiple RISs aided localization approach to address these challenges. The proposed method first estimates the angle-of-directions (AoDs) between the RISs and the user using the conditional sample mean approach, and then uses the estimated multiple AoD pairs to determine the user’s position. This approach only requires measuring the received signal strength at the BS for a set of randomly generated phase shifts across all RISs, thereby eliminating the need for real-time RIS phase shift design or user-to-BS pilot transmissions. Numerical results show that the proposed localization approach improves localization accuracy while significantly reducing energy and signaling overhead compared to conventional methods. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Foot Pressure Analysis for Diabetic Care Using ANN 5

Cloud-Based Foot Pressure Analysis for Diabetic Care Using A...

引用

5th International Conference on data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Pradeepa, H. Amarnath, Raveendra N. Sivakumar, V.G. Thamizhamuthu, R. Manikandan, G. Bhuvaneswari, G. Thiagarajar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Madurai India Mphasis Campbell Dr MelissaTX United States Vidya Jyothi Institute of Technology Department of Electronics and Communication Engineering Telangana Hyderabad India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Campus-Chengalpattu Tamil Nadu Chennai India Rmk Engineering College Department of Artificial Intelligence and Data Science RSM Nagar Tamil Nadu Chennai India Saveetha Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350389609

It introduces a new method for caring for diabetic feet combines smart pressure monitoring for the feet with wearable gear that is cloud-based and uses artificial neural networks (ANNs). It is essential to recognize diabetic foot ulcers early and monitor them continuously to avoid complications. Wearable pressure sensors record data on the user's foot pressure in real time make up the proposed system. ANNs trained to detect patterns recommend a possible risk of ulceration by analyzing this data once it is transferred to a cloud-based platform. By using cloud-based architecture, healthcare practitioners can remotely monitor patients and intervene as necessary. Clinical trials show the technology improves diabetic foot care by detecting irregularities in pressure distribution and lowering the risk of ulcers and their sequel. Improved patient outcomes and decreased healthcare expenses are achieved via the preventive treatment of diabetic feet made possible by this system, which makes use of breakthroughs in wearable technology and artificial intelligence (AI). © 2024 IEEE.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

A Customize Battery Management Approach for Satellite

A Customize Battery Management Approach for Satellite

引用

International Carpathian Control Conference (ICCC)

作者： Muhammad Harris Hashmi Muhammad Affan Ritesh Tandon Department of Computer Science University of Alabama at Birmingham Birmingham United States Department of Computer Science Universitat Jaume I Castellon de la Plana Spain Department of Data Science Protective Life Birmingham United States

A low-cost and reliable battery management unit for a student satellite was designed under the Pakistan National Student Satellite program. Lithium-ion batteries were chosen as the secondary storage, and safety measures were incorporated to monitor, balance, and safeguard the cells. The main challenge was accurately measuring the voltage of individual cells, which was addressed using a resistive-divider network. Fast multiplexers and de-multiplexers were used to overcome the problem of insufficient I/O pins on the microcontroller. The design’s only limitation is the dissipation of heat due to dissipative resistors, but it is an optimal solution due to its cost-effectiveness and simplicity. This unique solution meets specific requirements, but more advanced and expensive designs are available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Involution-based efficient autoencoder for denoising histopathological images with enhanced hybrid feature extraction

引用

computers in Biology and Medicine 2025年 192卷 110174-110174页

作者： Islam, Md. Farhadul Reza, Md. Tanzim Manab, Meem Arafat Zabeen, Sarah Islam, Md. Fahim-Ul Shahriar, Md. Fahim Kaykobad, Mohammad Husna, Md. Golam Zel Asmaul Noor, Jannatun Research Group Department of Computer Science and Engineering United International University Dhaka Bangladesh Department of Computer Science and Engineering School of Data and Sciences BRAC University Dhaka Bangladesh Department of Mathematics and Natural Sciences School of Data and Sciences BRAC University Dhaka Bangladesh School of Law and Government Dublin City University Dublin Ireland National Institute of Cancer Research and Hospital Dhaka Bangladesh

Noise in histopathology images from hardware limitations, preparation artifacts, and environmental factors complicates disease analysis and increases risks. With growing workloads and the complexity of histopathology images, developing efficient and precise histopathology image analysis methods is essential. However, many denoising models struggle to extract spatial features and are computationally expensive, primarily due to the limited capacity of convolutions to capture visual patterns across spatial locations, and tend to occupy the largest share of computational costs. In histopathology, many spatial features, such as anomalies or microorganisms, located sparsely across an image, are crucial for the final diagnosis, and many denoising processes often either blur them or introduce artifacts. In this study, we propose a lightweight autoencoder (43.11 kilobytes) for denoising histopathology images by fusing a single involution layer within a small convolution model, resulting in better denoising performance in a hybrid model, which has both channel-specific and location-specific feature extraction capabilities. Building upon the idea of a shallow autoencoder, our model results in much lower memory and compute overhead requirements, while also not avoiding the generation of artifacts. On Malaria Blood Smear and CRC datasets, SSIM Loss and Peak-Signal-to-Noise-Ratio were used for performance evaluation, with lower SSIM Loss (0.058 and 0.34) in denoising images with an added Gaussian noise of 0.3. Our proposed autoencoder, with low weight parameters of 11,037 and 81,630,000 floating point operations (FLOPs), is over 20 times less computationally expensive than Xception, the second-best performing model, establishing ours as the most efficient denoising autoencoder for histopathology images. © 2025 Elsevier Ltd

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Deep Active Audio Feature Learning in Resource-Constrained Environments

arXiv

引用

arXiv 2023年

作者： Mohaimenuzzaman, Md Bergmeir, Christoph Meyer, Bernd The Department of Data Science and AI Monash University ClaytonVIC3800 Australia The Data Science and Computational Intelligence Andalusian Institute DaSCI Andalucía Spain The Department of Computer Science and AI University of Granada Granada18071 Spain

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To effectively identify both new and current classes, DNN models must continue to learn new features from a modest amount of fresh data. Active Learning (AL) is an approach that can help with this learning while requiring little labelling effort. Nevertheless, the use of fixed feature extraction approaches limits feature quality, resulting in underutilization of the benefits of AL. We describe an AL framework that addresses this issue by incorporating feature extraction into the AL loop and refining the feature extractor after each round of manual annotation. In addition, we use raw audio processing rather than spectrograms, which is a novel approach. Experiments reveal that the proposed AL framework requires 14.3%, 66.7%, and 47.4% less labelling effort on benchmark audio datasets ESC-50, UrbanSound8k, and InsectWingBeat, respectively, for a large DNN model and similar savings on a microcontroller-based counterpart. Furthermore, we showcase the practical relevance of our study by incorporating data from conservation biology projects. All codes are publicly available on GitHub. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Cross-lingual Representation for Semantic Retrieval with Code-switching

arXiv

引用

arXiv 2024年

作者： Maimaiti, Mieradilijiang Zheng, Yuanhang Zhang, Ji Huang, Fei Zhang, Yue Luo, Wenpei Huang, Kaiyu Alibaba DAMO Academy China Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Westlake University Hangzhou China Department of Computer Science and Technology Dalian University of Technology Dalian China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China

Semantic Retrieval (SR) has become an indispensable part of the FAQ system in the task-oriented question-answering (QA) dialogue scenario. The demands for a cross-lingual smart-customer-service system for an e-commerce platform or some particular business conditions have been increasing recently. Most previous studies exploit cross-lingual pre-trained models (PTMs) for multi-lingual knowledge retrieval directly, while some others also leverage the continual pre-training before fine-tuning PTMs on the downstream tasks. However, no matter which schema is used, the previous work ignores to inform PTMs of some features of the downstream task, i.e. train their PTMs without providing any signals related to SR. To this end, in this work, we propose an Alternative Cross-lingual PTM for SR via code-switching. We are the first to utilize the code-switching approach for cross-lingual SR. Besides, we introduce the novel code-switched continual pre-training instead of directly using the PTMs on the SR tasks. The experimental results show that our proposed approach consistently outperforms the previous SOTA methods on SR and semantic textual similarity (STS) tasks with three business corpora and four open datasets in 20+ languages. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SWITCHING GRAPHS AND HADAMARD MATRICES

arXiv

引用

arXiv 2024年

作者： Abiad, Aida Peters, Louka Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Mathematics and Data Science Vrije Universiteit Brussels Belgium Department of Mathematics: Analysis Logic and Discrete Mathematics Ghent University Belgium

Local operations of combinatorial structures (graphs, Hadamard matrices, codes, designs) that maintain the basic parameters unaltered, have been widely used in the literature under the name of switching. We show an equivalence between two switching methods to construct inequivalent Hadamard matrices, which were proposed by Orrick [SIAM Journal on Discrete Mathematics, 2008], and the switching method for constructing cospectral graphs which was introduced by Godsil and McKay [Aequationes Mathematicae, 1982]. © 2024, CC BY.

关键词： Hadamard matrices

来源：评论

学校读者我要写书评

暂无评论

Testing Approach for IoT System (Case Study: Air Quality Monitoring System)

Testing Approach for IoT System (Case Study: Air Quality Mon...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Theresia Herlina Rochadiani Haryono Soeparno Ford Lumban Gaol Yulyani Arifin Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Informatics Department Pradita University Tangerang Indonesia

The Internet of Things (IoT) was evaluated as part of this study. The IoT system in this study is the air quality monitoring system. The system consists of three layers, three end devices with air quality monitoring sensors as the perception layer, the LoRaWAN network as the network layer, and the monitoring website as the presentation layer. Before being made available to the public, IoT hardware and software must undergo testing. For IoT systems, there are no established standards or quality criteria. This study's goal is to evaluate the methodology for an air quality monitoring system. Website speed is measured using Pingdom tools. The website received a performance grade of B. Pingdom offers advice for enhancing website performance. Sucuri is utilized as a security test tool to evaluate the website's security, and consequently, no malware was discovered. The latency and data dependability are monitored to assess the system's performance fully. The outcome demonstrates that all system components consistently and accurately receive data with a latency of less than 1 s.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Recognition using YOLO based Deep Learning Classifier 1

Facial Emotion Recognition using YOLO based Deep Learning Cl...

引用

1st International Conference on Electronics, Communication and Signal Processing, ICECSP 2024

作者： Vanamoju, Sri Vaibhav Mohan Dev Vineetha, Moturi Veda Tekchandani, Hitesh Joshi, Pallavi Shukla, Praveen Kumar Khanna, Anita Electronics and Communication Koneru Lakshmaiah Education Foundation Hyderabad India Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Hyderabad India Amrita Vishwa Vidyapeetham Mysuru Department of Computer Science Mysuru India School of Computing and Intelligent Systems Manipal University Jaipur Jaipur India Electrical Engineering Guru Ghasidas Vishwavidyalaya Bilaspur Bilaspur India

ISBN: (纸本)9798350364590

Understanding facial expressions is key to successful communication. It's like decoding a secret language that helps us know if someone is happy, sad, angry, surprised, or something else altogether. Harnessing facial emotion recognition (FER) in machines holds the potential to revolutionize human-computer interaction, improve customer service experiences and provide invaluable support in medical diagnosis. Machines can comprehend human's needs more effectively by reading the emotions from their facial expression and therefore this results in a more natural conversation between them and the machine. Various machine and deep learning methodologies have been implemented for FER. In this research work, the authors propose the state-of-the-art YOLO (You Only Look Once) based deep learning classifier for FER. The YOLO algorithm is a single-shot approach that efficiently classifies objects in a single pass. It achieves this by using a single neural network to predict bounding boxes and target class probabilities by utilizing the entire image as input. YOLOv8 is a recent iteration of the YOLO object detection algorithm is popular for its speed and accuracy which offers improvements over prior versions, making it a suitable choice for real-time intended task of FER. With the proposed classifier, the authors achieved test accuracy of 72.56% on the FER-2013 dataset in a seven-class FER task. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning Arabic printed document knowledge extraction 5

Deep learning Arabic printed document knowledge extraction

引用

5th International Conference on Future Networks and Distributed Systems: The Premier Conference on Smart Next Generation Networking Technologies, ICFNDS 2021

作者： Alghamdi, Taghreed Snoussi, Samia Hsairi, Lobna Department of Computer Science College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Data Science Department University of Jeddah Saudi Arabia University of Tunis ElManar University Tunisia

ISBN: (纸本)9781450387347

This paper presents how to utilize deep learning to extract knowledge from Arabic printed document images. The fundamental goal of deep learning is automatically extracting significant features from images, eliminating the need for a classic feature extraction method. We describe how to extract high-quality and coherent knowledge from Arabic printed document images using deep learning. This system is constructed on keywords used to classify Arabic document images according to these keywords. We used A questionnaire to choose valuable words according to historical, scientific, or religious documents. The evaluation of the proposed system is applied to Arabic printed document images to extract keywords. The accuracy of the proposed deep learning extraction approach is hugely affected by image preprocessing and image quality. The proposed system has a higher level of accuracy while extracting keywords. We achieve a 3.78% character error rate in the proposed system and a 15.46% word error rate. © 2021 ACM.

关键词： Extraction

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：