检索结果-内蒙古大学图书馆

FusionGCNN: An IoT-Based Novel Spatiotemporal Graph Convolutional Network for ECG Arrhythmia Detection

IEEE Internet of Things Journal 2025年

作者： Iqbal, Saeed Zhong, Xiaopin Alhussein, Musaed Wu, Zongze Aurangzeb, Khursheed Liu, Weixiang Zhang, Yudong Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11543 Saudi Arabia Henan Polytechnic University School of Computer Science and Technology Henan Jiaozuo China

Electrocardiogram (ECG) arrhythmia identification is critical for early cardiovascular disease diagnosis and monitoring in Internet of Things (IoT) industry. Still, it is difficult due to complicated waveforms, individual variability, and the requirement for real-time analysis on resource-limited equipment. Traditional approaches sometimes fail to detect complicated spatial-temporal correlations in ECG data, limiting their efficiency in identifying arrhythmias. Furthermore, deploying these models in tinyML contexts, such as edge and IoT devices limited by large computational and memory needs, emphasizes the importance of lightweight, accurate models for real-time applications. Our suggested solution consists of three main components: SigNet, DualGCNN, and FusionGCNN. SigNet uses Separable Convolution layers to effectively extract local spatial features, making it ideal for IoT-based healthcare deployment. DualGCNN combines dual Graph Convolutional layers with spatial attention, allowing the model to capture local and global dependencies for better classification of arrhythmia. FusionGCNN combines the capabilities of GCN and SigNet with an effective feature fusion technique to improve feature representation while remaining computationally economical. Ablation tests show that FusionGCNN improves performance considerably, with greater accuracy (0.9641), lower training error (0.0004), and a higher F1 Score (0.9645) across a variety of ECG patterns. FusionGCNN, with its low training error, high stability, and computational economy, is well-suited to tinyML requirements, allowing implementation on edge and IoT devices for scalable, real-time ECG monitoring in healthcare. © 2014 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Renewable integration and energy reduction in multiple stage evaporator

Renewable integration and energy reduction in multiple stage...

引用

作者： Pati, Smitarani Kumar Sharma, Tarun Kumar Goyal, Kapil Prakash Verma, Om Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar144011 India Department of Computer Science and Engineering Shobhit University UP Saharanpur-247341 India Department of Industrial and Production Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar144011 India

Multiple Effect Evaporator (MEE) is an imperative part of the paper industry. It is used to process the waste byproduct named Black Liquor to enhance its solid concentration that may be further utilized to produce biomass-based energy. This process accounts very high energy consumption which leads to the energy intensiveness of this unit. A substantial amount of energy-saving may be accumulated by integrating various Energy Reduction Schemes (ERSs) with the MEE. Steam splitting, feed splitting, feed liquor preheating, thermo-vapor compressor, etc. are the well-known ERSs that may be incorporated with the MEE to reduce energy utilization. Hence, this study investigates the hybrid ERSs incorporated with MEE to observe their energy efficiency in an optimal manner. The prime focus of this investigation is to achieve enhanced energy efficiency in teams of maximum steam efficiency which is computed by formulating the nonlinear mathematical models of the MEE. To achieve the maximized energy efficiency, an optimization function has been developed under a constraint environment and solved by using metaheuristic-based approach named Flow Direction Algorithm. Another ERSs named flash tanks can also be integrated with this system to encourage waste heat re-utilization and ensures an increase in energy efficiency with constant steam consumption. This work also deals with the incorporation of the Linear Fresnel Reflector with ERSs integrated MEE which is capable of reducing the conventional energy load. The overall integrated MEE model achieves an energy-efficient and renewably operated MEE unit that may enhance the self-sustainability of the industry. © 2022

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Fully automatic Visual Attention Estimation Support System for A Safer Driving Experience 9

A Fully Automatic Visual Attention Estimation Support System...

引用

9th Scholar's Yearly Symposium of Technology, engineering and Mathematics, SYSTEM 2023

作者： Fiani, Francesca Russo, Samuele Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Department of Psychology Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

Drivers’ attention is a key element in safe driving and in avoiding possible accidents. In this paper, we present a new approach to the task of Visual Attention Estimation in drivers. The model we introduce consists of two branches, one which performs Gaze Point Detection to determine the exact point of focus of the driver, and the other which executes Object Detection to recognize all relevant elements on the road (e.g. vehicles, pedestrians, and traffic signs). The combination of the two outputs from the two branches allows us to determine whether the driver is attentive and, eventually, on which element of the road they are focusing. Two models are tested for the gaze detection task: the GazeCNN model and a model consisting of a CNN+Transformer. The performance of both models is evaluated and compared with other state-of-the-art models to choose the best approach for the task. Finally, the results of the Visual Attention Estimation performed on 3761 pairs of images (driver view and corresponding road view) from the DGAZE dataset are reported and analyzed. © 2023 Copyright for this paper by its authors.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain-Integrated Distributed Data Storage Model with Built-in Load Balancing 16

A Novel Blockchain-Integrated Distributed Data Storage Model...

引用

16th IEEE International Conference on Application of Information and Communication Technologies, AICT 2022

作者： Hammoud, Obadah Tarkhanov, Ivan A. National University of Science and Technology Department of Engineering Cybernetics Moscow Russia State Academic University for Humanities Federal Research Center 'Computer Science and Control' of Russian Academy of Sciences Russia

ISBN: (纸本)9781665451628

Most companies relay on centralized servers, which are considered as a fast and easy to deploy solution for file sharing, but they have many downsides, like security and trust issues, which can be solved using DLT (blockchain) solutions. However, DLT-based solutions have many challenges, such as nodes orchestration, adjusting reliability and double-spending, as well as load balancing. This research proposes a DLT (Distributed Ledger Technology) based model for files storage for companies using p2p networks, which takes into account both data reliability and storage space efficiency. More efficient data storage is achieved through the use of the Erasure coding technique. For load balancing, a set of algorithms that can be implemented in the form of a smart contract were proposed. The described model can become the basis of the IT infrastructure for trusted exchange of documents, technical and scientific information, games distributions, mobile applications, updates of scientific, regulatory and technical databases in b2b and b2c format © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DEGAN: A Deep Learning Model for SAR Image Segmentation in Aquacultural Raft Monitoring

DEGAN: A Deep Learning Model for SAR Image Segmentation in A...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Shuo Lian Jun Wang Min Han Jianchao Fan School of Computer Science and Engineering Chongqing Three Gorges University Wanzhou Chongqing China Department of Computer Science and Department of Data Science City University of Hong Kong Kowloon Hong Kong China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9798331508661

ISBN: (纸本)9798331508678

Offshore aquacultural raft information extraction from synthetic aperture radar (SAR) images is crucial for large-scale marine resource exploitation and environmental protection. In this paper, a deep learning model named Detail-Enhancing Generative Adversarial Network (DEGAN) is proposed for SAR image segmentation to monitor aquacultural rafts. DEGAN incorporates several key modules to enhance segmentation performance, including $f$ -divergence to improve the discrim-inator's ability to handle noisy data, and the Convolutional Block Attention Module (CBAM) for more effective spatial and channel attention. Within CBAM, multi-scale feature fusion is employed to capture both fine and coarse details across different resolutions. Additionally, the Simple, Parameter-Free Attention Module (SimAM) is introduced to enhance feature refinement by deriving neuron importance through an energy function. These modules, when integrated into the GAN framework, work together to improve noise suppression and detail preservation, critical for accurate segmentation in challenging SAR images. Experimental results demonstrate that DEGAN outperforms five baseline models in four performance metrics, making it highly effective for aquacultural raft monitoring in complex marine environments.

关键词： Deep learning Image segmentation Generative adversarial networks Feature extraction Radar polarimetry Noise measurement Spatial resolution Monitoring Synthetic aperture radar Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Awakened at CheckThat! 2022: Fake News Detection using BiLSTM and Sentence Transformer

Awakened at CheckThat! 2022: Fake News Detection using BiLST...

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Truică, Ciprian-Octavian Apostol, Elena-Simona Paschke, Adrian Department of Information Technology Uppsala University Lägerhyddsvägen 1 Uppsala75105 Sweden Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Splaiul Independentei 313 Bucharest060042 Romania Fraunhofer Institute for Open Communication Systems Berlin10589 Germany

In recent years, online social networks and online news venues have become some of the main news and event-related information spreading mediums. Although using these mediums has facilitated the speed of accessing information, it also created a new phenomenon used for propaganda and disinformation: fake news. As fake news has detrimental consequences to society, new technologies need to be developed in order to stop their harmful effects. In this paper, we propose two Bidirectional Long Short-Term Memory (BiLSTM) architectures with sentence transformers to solve two tasks: (1) a multi-class mono-lingual fake news detection task (i.e., mono-lingual task);and (2) a multi-class cross-lingual fake news detection task (i.e., cross-lingual task). For the mono-lingual task, we train and test a BiLSTM with BART sentence transformers model on an English dataset and obtain an accuracy of ∼ 0.53 and an F1-Score of ∼ 0.32. For the cross-lingual task, we train a BiLSTM with XLM sentence transformers model on an English dataset and test the model using transfer learning on a German dataset. For this task, we obtain an accuracy of ∼ 0.28 and an F1-Score of ∼ 0.19. © 2022 Copyright for this paper by its authors.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Dorsal Hand Vascular Imaging System

Dorsal Hand Vascular Imaging System

引用

2024 IEEE Ural-Siberian Conference on Biomedical engineering, Radioelectronics and Information Technology, USBEREIT 2024

作者： Mizinov, Pavel V. Konnova, Natalia S. Kravchenko, Oleg V. Egorov, Dobroslav P. Osipenko, Gavriil V. Bauman Moscow State Technical University Department Of Information Security Moscow Russia Computer Science And Control Of Ras Federal Research Center Moscow Russia Kotel'nikov Institute Of Radio Engineering And Electronics Of Ras Moscow Russia Moscow Aviation Institute Moscow Russia

ISBN: (纸本)9798350362893

Biometric identification methods using vascular modalities (vein pattern of the finger, wrist, ventral and dorsal part of the metacarpal) use near infrared (NIR) illumination to obtain an image of the vein pattern. The 'classic' attack scenario for this type of biometric system involves the use of a photograph of the user's vein pattern, printed on ordinary office paper and obtained under NIR illumination, as a presentation attack tool. This attack scenario has been well studied by researchers and there are several reliable ways to detect such an attack. New biometric attack vectors on these systems involve the use of attack tools created using NIR reflective compounds. In order to develop effective methods to detect and counter this type of attack, it is necessary to study the characteristics of the attack tool in each of the 750-950 nm NIR sub-bands of the venous channel imaging band. In this paper, the authors present the stages of creating a hardware tool for obtaining an image of the vascular pattern to solve the problem at hand. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Study of Two Types of Introductory Exercise Problems for Network Programming Learning with Python 23

A Study of Two Types of Introductory Exercise Problems for N...

引用

11th International Conference on computer and Communications Management, ICCCM 2023

作者： Lu, Xiqin Funabiki, Nobuo Ueda, Kiyoshi Kao, Wen-Chung Department of Information and Communication Systems Distributed System Design Lab. Okayama University Okayama Japan Department of Computer Science Control Software Lab. Nihon University Koriyama Japan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

ISBN: (纸本)9798400707735

Network programming is the act of writing computer codes for communications between programs or processes in different computers across networks. It is crucial for applications and services using networks, including e-commerce, gaming, and social media. However, university courses of educating it are very limited. As a result, it has become important to develop and offer IT tools to support self-studies of network programming by novices. In this paper, we present a study of two types of introductory exercise problems, namely, Grammar-concept Understanding Problem (GUP) and Comment Insertion Problem (CIP), for self-studies of five basic network protocols of TCP/IP, ARP, SMTP, POP3, and SSH with Python. A GUP instance requests to answer the keyword such as a library function in the given source code that corresponds to the grammar concept described in the question. A CIP instance requests to insert the comment at each blank of the code. String matching is adopted to mark any answer at the browser-based answer interface. Through solving them, it is expected to understand the meaning of important words and the code structure for network programming. As preliminary evaluations, we generated six GUP and CIP instances respectively, and assigned them to 10 students in Okayama University, Japan. The results confirmed that the proposal is proper for novices to learn network programming with Python. © 2023 ACM.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Quantum Circuit engineering for Correcting Coherent Noise

TechRxiv

引用

TechRxiv 2023年

作者： Ahsan, Muhammad Zilqurnain Naqvi, Syed Abbas Anwer, Haider Department of Mechatronics and Control Engineering University of Engineering and Technology Lahore Pakistan Department of Computer Science Namal University Mianwali Pakistan

Crosstalk and several forms of coherent noise are invisible when qubit or a gate is calibrated or benchmarked in isolation. These are unlocked during the execution of full quantum circuit applying entangling gates to several qubits simultaneously. Unitary crosstalk noise, such as unwanted ZZ coupling, limits the state fidelity during the execution of cross-resonance CNOT gates in the superconductor quantum computers. This work presents (1) method of tracing coherent errors by exploiting their sensitivity to the arrangement of CNOT gates in the circuit and (2) correction scheme that modifies original circuit by inserting carefully chosen compensating gates (single- or two-qubit) to possibly undo coherent errors. On two vastly different types of IBMQ processors offering quantum volume 8 upto 32, our experimental results show up to 25% reduction in the infidelity of [[7, 1, 3]] code |+i state (clifford circuits) and 5- to 15-qubit W-states (non-clifford circuits). Our experimental circuits aggressively deploy forced commutation of CNOT gates to obtain low noise state-preparation circuits. Encoded state initialized with fewer errors, marks an important step towards successful demonstration of fault-tolerant quantum computers. © 2023, CC BY.

关键词： Crosstalk

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：