检索结果-内蒙古大学图书馆

12th IEEE International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2024

作者： Alsharif, Maram Rawat, Danda B. Department of Electrical Engineering & Computer Science WashingtonDC20059 United States

ISBN: (纸本)9798331510633

Security solutions based on machine learning enabled Intrusion detection systems (ML-IDS) have been popular for IoT edge device security. The cloud support has been considered to leverage heavy workloads off IoT edge devices such as learning, model fitting and updating. In this paper, we apply ML model optimization techniques as 3 distinct key roles of the cloud layer in Machine Learning as a Service (MaaS) architecture. In order to influence the performance of IoT edge devices, the optimization would require: a) device benchmarking that quantifies the available computing resources and network traffic for the edge device;b) feature weighing that determines the contribution of each extracted feature to the overall ML-IDS operation;and c) dimensionality reduction of important features in the training dataset. We examine feature importance and dimensionality reduction techniques on 3 public IDS datasets and present how they affect ML model performance. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

The Status of WBG Devices Towards Net-Zero Solutions 17

The Status of WBG Devices Towards Net-Zero Solutions

引用

17th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2024

作者： Ostling, Mikael KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Sweden

ISBN: (纸本)9798350361834

The world is facing a dramatic increase in the need for electricity and needs to battle the ever-increasing carbon dioxide emissions. New, more efficient, wide bandgap power electronics devices are developed to enable the urgent plans towards net-zero loss in electricity production, distribution and consumption. These devices will be very important pieces in the worldwide puzzle to enable fossil free electricity production, distribution and consumption. This paper discusses the status of wide bandgap device technology in the perspective of maturity of the devices for roll-out and implementation for industrial commercial use. © 2024 IEEE.

关键词： Power semiconductor devices

来源：评论

学校读者我要写书评

暂无评论

'Looking' into Attention Patterns in Extended Reality: An Eye Tracking-Based Study 23

'Looking' into Attention Patterns in Extended Reality: An Ey...

引用

23rd IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2024

作者： Qu, Zhehan Byrne, Ryleigh Gorlatova, Maria Duke University Department of Computer Science United States Duke University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798331516475

Virtual reality (VR) simulations have been adopted to provide controllable environments for running augmented reality (AR) experiments in diverse scenarios. However, insufficient research has explored the impact of AR applications on users, especially their attention patterns, and whether VR simulations accurately replicate these effects. In this work, we propose to analyze user attention patterns via eye tracking during XR usage. To represent applications that provide both helpful guidance and irrelevant information, we built a Sudoku Helper app that includes visual hints and potential distractions during the puzzle-solving period. We conducted two user studies with 19 different users each in AR and VR, in which we collected eye tracking data, conducted gaze-based analysis, and trained machine learning (ML) models to predict user attentional states and attention control ability. Our results show that the AR app had a statistically significant impact on enhancing attention by increasing the fixated proportion of time, while the VR app reduced fixated time and made the users less focused. Results indicate that there is a discrepancy between VR simulations and the AR experience. Our ML models achieve 99.3% and 96.3% accuracy in predicting user attention control ability in AR and VR, respectively. A noticeable performance drop when transferring models trained on one medium to the other further highlights the gap between the AR experience and the VR simulation of it. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

2-Step RACH and Unsourced Massive Random Access in Cell-Free User-Centric Networks 58

2-Step RACH and Unsourced Massive Random Access in Cell-Free...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Gkiouzepi, Eleni Çakmak, Burak Caire, Giuseppe Technische Universität Faculty of Electrical Engineering and Computer Science Berlin Germany

ISBN: (纸本)9798350354058

In this work we consider a scheme for unsourced random access (uRA) in cell free (CF) wireless networks, which is conceptually reminiscent of the 2-step RACH scheme defined in 3GPP for cellular networks. During the designated random access channel (RACH) slots, users engaged in random access transmit codewords drawn from a shared codebook. The distributed and CF nature of the network is adressed by partitioning the network coverage area into zones, referred to as 'locations,' and assigning a location-specific access codebook to each location. We use the recently proposed multisource Approximated Message Passing (AMP) algorithm for joint detection of the access codewords and channel estimation. In particular, AMP generates two outputs:a list of active codewords and an estimate of the corresponding channel vectors. The aforementioned outputs facilitate the formation of a user-centric cluster. The impact of random access users and the overall system performance are assessed based on the sum spectral efficiency for uplink (UL) and downlink (DL) of the data transmission slots, under limited random activity of the users. © 2024 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Beyond Human Vision: The Role of Large Vision Language Models in Microscope Image Analysis

Beyond Human Vision: The Role of Large Vision Language Model...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Verma, Prateek Van, Minh-Hao Wu, Xintao University of Arkansas Department of Electrical Engineering and Computer Science Fayetteville United States

ISBN: (纸本)9798350362480

Vision language models (VLMs) such as LLaVA, ChatGPT-4, and Gemini have recently emerged and gained the spotlight for their ability to comprehend the dual modality of image and textual data showing impressive performance on tasks such as natural image captioning, visual question answering, and spatial reasoning. Additionally, a universal segmentation model by Meta AI, Segment Anything Model (SAM) shows unprecedented performance at isolating objects from unforeseen images. Because medical experts, biologists, and materials scientists routinely examine microscopy or medical images in conjunction with textual information in the form of captions, literature, or reports, and draw conclusions of great importance and merit, it is essential to evaluate their performance on these images. In this study, we charge ChatGPT, LLaVA, Gemini, and SAM quantitatively with classification, segmentation and counting tasks. We observed that ChatGPT and Gemini were impressively able to comprehend the visual features in microscopy images, while SAM was quite capable at isolating artifacts in a general sense. However, the performance was not close to that of a domain expert - the models were readily encumbered by the introduction of impurities, defects, object overlaps and diversity present in the images. © 2024 IEEE.

关键词： biology electron microscopy images materials science vision language models zero-shot evaluation

来源：评论

学校读者我要写书评

暂无评论

Current Trends, Challenges and Techniques in XAI Field;A Tertiary Study of XAI Research 47

Current Trends, Challenges and Techniques in XAI Field;A Ter...

引用

47th ICT and Electronics Convention, MIPRO 2024

作者： Brdnik, Saša Šumak, Boštjan University Of Maribor Institute Of Informatics Faculty Of Electrical Engineering And Computer Science Slovenia

ISBN: (纸本)9798350382495

This tertiary systematic literature review examines 29 systematic literature reviews and surveys in Explainable Artificial Intelligence (XAI) to uncover trends, limitations, and future directions. The study explores current explanation techniques, providing insights for researchers, practitioners, and policymakers interested in enhancing AI transparency. Notably, the increasing number of systematic literature reviews (SLRs) in XAI publications indicates a growing interest in the field. The review offers an annotated catalogue for human-computer interaction-focused XAI stakeholders, emphasising practitioner guidelines. Automated searches across ACM, IEEE, and science Direct databases identified SLRs published between 2019 and May 2023, covering diverse application domains and topics. While adhering to methodological guidelines, the SLRs often lack primary study quality assessments. The review highlights ongoing challenges and future opportunities related to XAI evaluation standardisation, its impact on users, and interdisciplinary research on ethics and GDPR aspects. The 29 SLRs, analysing over two thousand papers, include five directly relevant to practitioners. Additionally, references from the SLRs were analysed to compile a list of frequently cited papers, serving as recommended foundational readings for newcomers to the field. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Advancing Medical Imaging: High-Performance Brain Tumor Detection and Classification Using Deep Learning and Grad CAM Visualization

Advancing Medical Imaging: High-Performance Brain Tumor Dete...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Asif, Mikdad Mohammad Nawar, Sadia Uddin, Altaf Hosen, Md.Hamid Amran, Mohammed Hasan, Muhammad Asif East Delta University Computer Science and Engineering Chittagong Bangladesh Bangladesh University of Engineering and Technology Electrical and Electronic Engineering Dhaka Bangladesh Griffith University Computer Science and Engineering Australia

ISBN: (纸本)9798331529765

An essential component of the diagnostic and treatment process is identifying brain tumors early in their onslaught. Traditional approaches struggle with processing sequential data and face limitations in maintaining computational efficiency with large-scale data. The pre-trained model has the advantage of eliminating computational complexity and processing the data very well. This research intends to improve the overall accuracy and robustness of the brain tumor detection and classification system, which is an amalgamate of several CNN-based pre-trained models for classification and two well-known detection models, Mask RCNN and YOLOv8, for tumor detection. The ResNet50 model delivers remarkable results, with an accuracy of 98.21% and precision of 97.32%. On top of that, it has a recall of 97.09% and an F1 score of 97.01%. The detection approach successfully pinpoints the tumor and offers a confidence score for detected regions exceeding 0.8. It also makes a highly accurate distinction between positive and negative tumors. The findings showcase significant benefits for medical imaging, offering enhanced interpretable results through the use of Grad CAM as the optimal classifier. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Convolutional Neural Network Hardware IP for Epilepsy Detection 17

An Efficient Convolutional Neural Network Hardware IP for Ep...

引用

17th IEEE International Conference on Solid-State and Integrated Circuit Technology, ICSICT 2024

作者： Gong, Yi Zhang, Yuejun Tu, Jiangtao Zou, Rongxin Wen, Liang Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China

ISBN: (纸本)9798350361834

Epilepsy is a common neurological disease which is sudden and unpredictable. In response to the current problems of low efficiency and high false detection rate in epilepsy detection, this paper proposes an efficient convolutional neural network (CNN) hardware intellectual property (IP) design scheme for epilepsy detection. According to the epilepsy pathology, the oversampling technique is used to solve the sample imbalance. Filters out the noise by using band-pass filters, and improves the model by using Z-score normalization. Then, the structure of convolutional neural network is optimized to build an end-to-end network model and train the corresponding weights as well as biases. A single convolutional kernel is used to lighten the network model and reduce the parameters. The 22-channel EEG data are processed in a parallelized manner to fully extract the correlation between the channels. The 3-layer convolutional and max pooling module is designed by combining with pipelining technique. Validated on the CHB-MIT dataset, the epilepsy detection accuracy is reached 97.45%. Under TSMC 65 nm process, the IP core area is measured as 1.625 mm 2 , power consumption is measured as 4.225 mW, single detection delay is 0.01935 ms, and single detection energy consumption is 0.237 μJ/class. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Planar Reflection-less Lens Based on Miniaturized-element Frequency Selective Surfaces for Automotive Radar Applications

Planar Reflection-less Lens Based on Miniaturized-element Fr...

引用

2024 United States National Committee of URSI National Radio science Meeting, USNC-URSI NRSM 2024

作者： Hafezi, Ehsan Sarabandi, Kamal Electrical Engineering and Computer Science University of Michigan Ann Arbor United States

ISBN: (纸本)9781946815194

A novel, planar and reflection-less lens antenna for automotive radar band (77-81 GHz) based on miniaturized-element frequency selective surfaces is designed, fabricated, and tested. This lens is designed to provide a narrow beam (2.53°) and high gain (35.6 dBi) while showing a very low reflection coefficient (-28 dB at resonance) measured at its feed. This lens is a key component in the future automotive radar-on-chip applications. The phase compensation for the lens is accomplished locally with phase delays through distributed 2-pole spatial filters that make use of only shunt elements. This lens includes three MEFSS-gold patterned layers and two layers of fused silica substrate. The lens is developed using microfabrication technology with feature size accuracy at the order of 0.1 μm, and has an F/D = 1.4 and is fed by a dual-polarized horn antenna. The fabricated 10-cm lens is only 1.05 mm thick and weighs 19 g and shows much improvement in the reflection coefficient from 77-81 GHz when compared with a typical dielectric lens of the same diameter and F/D. © 2024 IEEE. All rights reserved.

关键词： lens antennas radar-on-chip

来源：评论

学校读者我要写书评

暂无评论

Joint fuzzy background and adaptive foreground model for moving target detection

引用

Frontiers of computer science 2024年第2期18卷 93-106页

作者： Dawei ZHANG Peng WANG Yongfeng DONG Linhao LI Xin LI School of Artificial Intelligence Hebei University of TechnologyTianjin 300401China Lane Department of Computer Science and Electrical Engineering West Virginia UniversityMorgantownWV 26506-6109USA

Moving target detection is one of the most basic tasks in computer *** conventional wisdom,the problem is solved by iterative optimization under either Matrix Decomposition(MD)or Matrix Factorization(MF)*** utilizes foreground information to facilitate background *** uses noise-based weights to fine-tune the *** both noise and foreground information contribute to the recovery of the *** jointly exploit their advantages,inspired by two framework complementary characteristics,we propose to simultaneously exploit the advantages of these two optimizing approaches in a unified framework called Joint Matrix Decomposition and Factorization(JMDF).To improve background extraction,a fuzzy factorization is *** fuzzy membership of the background/foreground association is calculated during the factorization process to distinguish their contributions of both to background *** describe the spatio-temporal continuity of foreground more accurately,we propose to incorporate the first order temporal difference into the group sparsity constraint *** temporal constraint is adjusted *** foreground and the background are jointly estimated through an effective alternate optimization process,and the noise can be modeled with the specific probability *** experimental results of vast real videos illustrate the effectiveness of our *** with the current state-of-the-art technology,our method can usually form the clearer background and extract the more accurate ***-noise experiments show the noise robustness of our method.

关键词： matrixdecomposition matrix factorization generalized sparsity noise modeling

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：