检索结果-内蒙古大学图书馆

2024 International Conference on computer engineering, Network and Intelligent Multimedia, CENIM 2024

作者： Irhamsyah, Muhammad Roslidar Yunidar Al Lail Qadrillah, M. Nasaruddin Arnia, Fitri Munadi, Khairul Universitas Syiah Kuala Post Graduate Program in Engineering Banda Aceh2311 Indonesia Faculty of Engineering Department of Electrical and Computer Engineering 2311 Indonesia

ISBN: (纸本)9798350368802

Tuberculosis (TB) is an infectious disease that can attack the lungs and other organs. In the diagnosis of TB, the interpretation of X-ray radiological images requires special skills from medical specialists. However, the lack of experience of medical personnel and focus on X-ray examinations can be a challenge for radiologists because it has the potential to cause diagnostic errors in image interpretation. Therefore, we proposed a web-based application of real-time chest X-ray interpreter by integrating the deep learning model of Vision Transformer (ViT) to interpret chest X-ray images. The inference model was trained and tested on 652 normal and 652 tuberculosis X-ray images. The data preprocessing of Contrast Adaptive Histogram Equalization (CLAHE) was implemented to increase chest X-ray image contrast as well as inference model performance. The proposed real time system can inteprete the tested chest x-ray images with an accuracy of 95% and with simulation duration time of 4.7 seconds. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Autoencoder-Based Detection of False Data Injection Attacks Against Data Poisoning in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1287-1301页

作者： Takiddin, Abdulrahman Ismail, Muhammad Atat, Rachad Davis, Katherine R. Serpedin, Erchin Department of Electrical and Computer Engineering Texas A and M University College StationTX77843 United States Department of Computer Science Tennessee Tech University CookevilleTN38505 United States Department of Electrical and Computer Engineering Program Texas A and M University Qatar Doha23874 Qatar

Machine learning-based detection of false data injection attacks (FDIAs) in smart grids relies on labeled measurement data for training and testing. The majority of existing detectors are developed assuming that the adopted datasets for training have correct labeling information. However, such an assumption is not always valid as training data might include measurement samples that are incorrectly labeled as benign, namely, adversarial data poisoning samples, which have not been detected before. Neglecting such an aspect makes detectors susceptible to data poisoning. Our investigations revealed that detection rates (DRs) of existing detectors significantly deteriorate by up to 9-29% when subject to data poisoning in generalized and topology-specific settings. Thus, we propose a generalized graph neural network-based anomaly detector that is robust against FDIAs and data poisoning. It requires only benign datasets for training and employs an autoencoder with Chebyshev graph convolutional recurrent layers with attention mechanism to capture the spatial and temporal correlations within measurement data. The proposed convolutional recurrent graph autoencoder model is trained and tested on various topologies (from 14, 39, and 118-bus systems). Due to such factors, it yields stable generalized detection performance that is degraded by only 1.6-3.7% in DR against high levels of data poisoning and unseen FDIAs in unobserved topologies. Impact Statement-Artificial Intelligence (AI) systems are used in smart grids to detect cyberattacks. They can automatically detect malicious actions carried out bymalicious entities that falsifymeasurement data within power grids. Themajority of such systems are data-driven and rely on labeled data for model training and testing. However, datasets are not always correctly labeled since malicious entities might be carrying out cyberattacks without being detected, which leads to training on mislabeled datasets. Such actions might degrade the d

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Learning feature alignment and dual correlation for few‐shot image classification

引用

CAAI Transactions on Intelligence Technology 2024年第2期9卷 303-318页

作者： Xilang Huang Seon Han Choi Department of Electronic and Electrical Engineering Ewha Womans UniversitySeoulSouth Korea Graduate Program in Smart Factory Ewha Womans UniversitySeoulSouth Korea

Few‐shot image classification is the task of classifying novel classes using extremely limited labelled *** perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample *** FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment ***,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation ***,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation ***,a dual correlation module to learn the hard and soft correlations was developed by the *** module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled *** both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for *** results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.

关键词： image classification machine learning metric learning

来源：评论

学校读者我要写书评

暂无评论

Artificial visual perception neural system using a solution-processable MoS_(2)-based in-memory light sensor

引用

Light(Science & Applications) 2023年第8期12卷 1583-1594页

作者： Dayanand Kumar Lana Joharji Hanrui Li Ayman Rezk Ammar Nayfeh Nazek El-Atab Smart Advanced Memory Devices and Applications(SAMA)LaboratoryElectrical and Computer Engineering ProgramComputer Electrical Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Kingdom of Saudi Arabia Department of Electrical Engineering and Computer Science Khalifa UniversityAbu Dhabi 127788United Arab Emirates

Optoelectronic devices are advantageous in in-memory light sensing for visual information processing,recognition,and storage in an energy-efficient ***,in-memory light sensors have been proposed to improve the energy,area,and time efficiencies of neuromorphic computing *** study is primarily focused on the development of a single sensing-storage-processing node based on a two-terminal solution-processable MoS2 metal-oxide-semiconductor(MOS)charge-trapping memory structure—the basic structure for charge-coupled devices(CCD)—and showing its suitability for in-memory light sensing and artificial visual *** memory window of the device increased from 2.8 V to more than 6V when the device was irradiated with optical lights of different wavelengths during the program ***,the charge retention capability of the device at a high temperature(100 ℃)was enhanced from 36 to 64%when exposed to a light wavelength of 400 *** larger shift in the threshold voltage with an increasing operating voltage confirmed that more charges were trapped at the Al_(2)O_(3)/MoS_(2) interface and in the MoS_(2) layer.A small convolutional neural network was proposed to measure the optical sensing and electrical programming abilities of the *** array simulation received optical images transmitted using a blue light wavelength and performed inference computation to process and recognize the images with 91%*** study is a significant step toward the development of optoelectronic MOS memory devices for neuromorphic visual perception,adaptive parallel processing networks for in-memory light sensing,and smart CCD cameras with artificial visual perception capabilities.

关键词： visual neural process

来源：评论

学校读者我要写书评

暂无评论

High Efficient Delta-Sigma Modulator Utilizing Multi-Stage Noise Shaping Structure

引用

Journal of Lightwave Technology 2024年第8期42卷 2693-2701页

作者： Jian, Yin-He Wei, Tzu-Chieh Chow, Chi-Wai National Yang Ming Chiao Tung University Department of Photonics Graduate Institute of Electro-Optical Engineering College of Electrical and Computer Engineering Hsinchu30010 Taiwan

Recently, several Delta-Sigma modulators (DSMs) with ultra-high quadrature-amplitude-modulation (QAM) order larger than one million, e.g., 1048576 and 4194304 QAM are reported. As different DSM works were implemented with different oversampling rates (OSRs), and pursuing a higher DSM QAM order seems to deviate from its original idea to achieve high spectral efficiency. Up to the authors' knowledges, there is still no comprehensive comparison of the intrinsic efficiencies of different DSM works. In this work, we first summarize the recent DSM works and compare their efficiencies. We also propose and demonstrate a 1-bit DSM and a 2-bit multi-stage noise shaping (MASH) DSM for the baseband-over-fiber system. The modified 1-bit DSM can achieve record efficiencies of 0.589 and 0.665 under the hard-decision (HD) and the 25% soft-decision (SD) forward error correction (FEC) requirements, respectively. The 2-bit MASH DSM can also achieve record efficiencies of 1.025 (HD) and 1.150 (SD) respectively. © 1983-2012 IEEE.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis of Incommensurate Fractional-Order Systems with Multiple Time Delays 10

Stability Analysis of Incommensurate Fractional-Order System...

引用

10th International Conference on Control, Instrumentation and Automation, ICCIA 2024

作者： Tavazoei, Mohammad Graduate University of Advanced Technology Department of Electrical and Computer Engineering Kerman Iran

ISBN: (纸本)9798331509972

This paper explores the stability of incommensurate fractional-order models. Building on previous work that introduced a method for assessing stability and calculating delay margins for single delay models, this study extends the analysis to models with multiple delay parameters. The proposed method assumes all delayed signals within the model act as disturbances. By employing the generalized smallgain theorem, stability conditions are established. These conditions rely on the H∞ norm and frequency analysis, resulting in final outcomes that depend on the fractional orders of the model. Importantly, the derived stability condition is independent of the delay parameter values. © 2024 IEEE.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

An Ensemble-Based Classifier to Determine the Harmonic Contribution Responsibility Between Utility’s Grid and Microgrids

引用

IEEE Access 2025年 13卷 85873-85881页

作者： Mella, Matheus C. Fernandes, Ricardo A.S Barbosa, Daniel Federal University of São Carlos Graduate Program in Electrical Engineering São Carlos Brazil University of São Paulo São Carlos School of Engineering Department of Electrical and Computer Engineering São Carlos Brazil Federal University of Bahia Department of Electrical Engineering Salvador Brazil

The integration of nonlinear loads and distributed energy resources in microgrids (MG) has increased the levels of harmonic distortions in distribution feeders. Identifying the responsibility for the harmonic distortions measured at the MG’s point of common coupling (PCC) is essential for managing the power quality. For this purpose, the present paper aims to determine whether the responsibility predominates from the utility’s grid or the MG itself. Thus, an ensemble-based approach was proposed, comparing the behaviour of Random Forest and XGBoost classifiers to identify the side with the predominant harmonic contribution. In order to validate the proposed approach, scenarios were simulated in the IEEE 34-node test feeder using the ATP/ATPDraw software, considering the harmonic sources located at different nodes of the feeder. Three-phase voltage and current signals were acquired at MG’s PCC to train and validate the ensembles. However, a feature extraction stage was performed to obtain time and frequency features used as inputs to the predictive models. The results demonstrated that the proposed approach effectively identified the contribution side, achieving an average F1-score above 99% for both ensembles, representing a feasible solution for determining the harmonic distortion responsibilities at the MG’s PCC. © 2013 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

A novel IoT-based arrhythmia detection system with ECG signals using a hybrid convolutional neural network and neural architecture search network

引用

International Journal of Applied Decision Sciences 2024年第5期17卷 636-656页

作者： Şentürk, Ümit Gülen, Ceren Polat, Kemal Department of Computer Engineering Faculty of Engineering Abant Izzet Baysal University Bolu Turkey Department of Computer Engineering Education of Graduate Institute Abant Izzet Baysal University Bolu Turkey Department of Electrical and Electronics Engineering Bolu Abant Izzet Baysal University Bolu Turkey

Electrocardiogram (ECG) signals are the most common tool to evaluate the heart’s function in cardiovascular diagnosis. Irregular heartbeats (arrhythmia) found in the ECG play an essential role in diagnosing cardiovascular diseases (CVD). In this paper, we proposed an arrhythmia classification method with the neural architecture search network (NASNet) model, an optimised version of the convolutional neural networks (2D-CNN) model, which performs very well in visual information analysis classification. We aimed to use the arrhythmia classification problem in IoT and mobile devices with the NASNet model with low parameter numbers and processing capacity without performance loss. 2D input data have been obtained by converting the classified heart rate signals in the datasets into image files. The 2D data obtained have been classified by machine learning, CNN, and NASNet models. As a result of classification, 2D CNN accuracy was 97.51%, and the NASNet model was 96.89% accuracy. As a result of arrhythmia classification, the accuracy rates of the NASNet and the 2D CNN models were close. In conclusion, the proposed IoT-based arrhythmia detection system with ECG signals using a hybrid CNN and NASNet is a promising tool for the early detection of arrhythmias. Furthermore, it could help to reduce the mortality associated with these potentially fatal conditions. © 2024 Inderscience Enterprises Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Expanded Latent Space Autoencoder for Land Cover Classification of Remote Sensing Images from EuroSAT 16

An Expanded Latent Space Autoencoder for Land Cover Classifi...

引用

16th Brazilian Symposium on Robotics and 15th Workshop on Robotics in Education, SBR-WRE 2024

作者： Vilar Oliveira, Emerson Garcia Gonçalves, Luiz Marcos Graduate Program in Electrical and Computer Engineering Universidade Federal do Rio Grande do Norte Natal Brazil

ISBN: (纸本)9798350391084

Image classification has been instrumental in the interpretation and labeling of images in the field of remote sensing, computer vision, and in robotics applications. Machine learning and artificial intelligence algorithms, particularly artificial neural networks, are extensively utilized for this purpose. In this work we propose the Expanded Latent Space Autoencoder (ELSA) with a case use application to classify land cover data. The main idea on the ELSA network structure is to utilize the latent spaces of multiple internal autoencoders in order to create an expanded latent space. This expanded latent space extracts more information from the input data, and serves as input features for a more simpler classifier network. In order to evaluate the proposed network’s ability to extract features and classify complex and multispectral images we employed it to the EuroSAT dataset. The results demonstrate a remarkable capacity for feature extraction using the ELSA network, with lower complexity, trained with a reduced number of images. The classifier network achieved a final accuracy of 98.7%, matching or exceeding the performance of more complex state-of-the-art models. ©2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Quality Analytics for Latin American and Brazilian Robotics Symposiums 16

Quality Analytics for Latin American and Brazilian Robotics ...

引用

16th Brazilian Symposium on Robotics and 15th Workshop on Robotics in Education, SBR-WRE 2024

作者： Garcia Gonçalves, Luiz Marcos Electrical and Computer Engineering Graduate Program Universidade Federal do Rio Grande do Norte Natal Brazil

ISBN: (纸本)9798350391084

We bring historical findings related to the most important Latin American and Brazilian Robotics Symposiums including their quality analytics regarding all papers published since their creation. For this quality analysis, we first provide a little of history and then we apply a methodology based on a systematic mapping of the literature using Scopus (from Elsevier) and Web of Science. The quality analysis includes variables as citations metrics, and also other historical variables as participation per countries, per states, per universities, and contributed areas among others. We use metadata and tools available in the most commonly used digital libraries, for a fair comparison. To the end, with basis on the results of our methodological approach, we point out that the community has followed the right path for establishing a high quality event, mainly regarding the decision of publication of the proceedings at IEEE Xplore, and recently in the Brazilian computer Society Library (Sol-SBC), all together. Also, our analysis corroborate to verify the modi operandi that have been used in the events execution, including joining in the Workshop of Robotics in Education (WRE) and the competitions (RCB, OBR, MNR, CBR, LARC). Besides happening jointly, each event keeps their original event structure and characteristics. ©2024 IEEE.

关键词： Taxonomies

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：