检索结果-内蒙古大学图书馆

Optimized COVID-19 detection using sparse deep learning models from multimodal imaging data

Multimedia Tools and Applications 2025年第13期84卷 11451-11474页

作者： Moradi, MohammadMahdi Hassanzadeh, Alireza Haghanifar, Arman Ko, Seok Bum Faculty of Computer Science and Software Engineering Concordia University MontrealQC Canada Faculty of Electrical Engineering Shahid Beheshti University Tehran Tehran Iran Department of Electrical & Computer Engineering University of Saskatchewan SaskatoonSK Canada

This paper explores the global spread of the COVID-19 virus since 2019, impacting 219 countries worldwide. Despite the absence of a definitive cure, the utilization of artificial intelligence (AI) methods for disease diagnosis has demonstrated commendable effectiveness in promptly diagnosing patients and curbing infection transmission. The study introduces a deep learning-based model tailored for COVID-19 detection, leveraging three prevalent medical imaging modalities: computed tomography (CT), chest X-ray (CXR), and Ultrasound. Various deep Transfer Learning Convolutional Neural Network-based (CNN) models have undergone assessment for each imaging modality. For each imaging modality, this study has selected the two most accurate models based on evaluation metrics such as accuracy and loss. Additionally, efforts have been made to prune unnecessary weights from these models to obtain more efficient and sparse models. By fusing these pruned models, enhanced performance has been achieved. The models have undergone rigorous training and testing using publicly available real-world medical datasets, focusing on classifying these datasets into three distinct categories: Normal, COVID-19 Pneumonia, and non-COVID-19 Pneumonia. The primary objective is to develop an optimized and swift model through strategies like Transfer Learning, Ensemble Learning, and reducing network complexity, making it easier for storage and transfer. The results of the trained network on test data exhibit promising outcomes. The accuracy of these models on the CT scan, X-ray, and ultrasound datasets stands at 99.4%, 98.9%, and 99.3%, respectively. Moreover, these models’ sizes have been substantially reduced and optimized by 51.93%, 38.00%, and 69.07%, respectively. This study proposes a computer-aided-coronavirus-detection system based on three standard medical imaging techniques. The intention is to assist radiologists in accurately and swiftly diagnosing the disease, especially during the screen

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Arabic Abstractive Summarization Using the Multilingual T5 Model 6

Arabic Abstractive Summarization Using the Multilingual T5 M...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Karim, Abdelrhman A. Usama, Mohammed Ibrahim, Manar A. Hatem, Youssef Wael, Waleed Mazrua, Ahmad T. El-Monayer, Ghada K. Elbanhawy, Magy Foad, Khaled Moawad, Ibrahim F. Artificial Intelligence Engineering Department Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Computer Engineering Department Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Artificial Intelligence Science Department Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Computer and System Department Faculty of Engineering Portsaid University Egypt Faculty of Computers and Artificial Intelligence Benha University Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt

ISBN: (纸本)9798350373875

Natural language processing (NLP) is a branch of artificial intelligence (Al) that enables computers to comprehend, generate, and manipulate human language. Natural language processing can interrogate the data with natural language text or voice. Abstractive Text Summarization is based on the Natural Language Processing technique that tries to provide new and more concise textual summaries for huge texts. Artificial intelligence and deep learning techniques are used in abstractive summarization to examine the text's essential information and create a new summary that conveys the content more concisely and accurately. This type of summary differs from normal extractive summarizing in that it can generate new summaries beyond simply extracting key lines from the source text. This study presents an abstractive Arabic summarization based on the Multilingual TS (MTS) model AASMTS to address these concerns. This technique is based on deep neural networks and models like transformers, which have changed the ability to summarize text. This research has explored the various types of summarizations and highlighted the significance of two prominent techniques: abstractive and extractive summarization. This research describes a complete process for developing an Arabic abstractive summarization model using the MTS architecture. Experiments on different datasets show that this model achieves state-of-the-art results across MTS. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Insights from Vast Data: An Overview of Deep Learning Techniques for Big Data 4

Exploring Deep Insights from Vast Data: An Overview of Deep ...

引用

4th International Conference on Electrical engineering and computer science, ICECOS 2024

作者： Baez Hasan, Sarhad Kareem, Shahab Wahhab Ameen, Didar Dlshad Hamad Soran University Faculty of Science Computer Science Department Soran Iraq Erbil Polytechnic University College of Engineering Knowledge University Department of Information System Engineering Department of Computer Engineering Erbil Iraq

ISBN: (纸本)9798350368253

Big data has emerged very fast, and this has brought both opportunities and problems that are related to the application of deep learning. This paper explores how deep learning can be implemented using big data and in particular the Apache Mahout library. Unlike most other machine learning tools, Mahout can perform distributed computation, especially while using the MapReduce frameworks including Apache Hadoop and Apache Spark. However, this study does not only focus on the explanation of the need for Mahout's integration and employment but also carries out a high-fidelity argument on how deep learning algorithms can be incorporated in the Mahout framework to optimize the manipulation of large and complicated datasets. Mahout-based contributions include the comparative analysis of key deep learning paradigms including distributed processing, parallel processing and transfer learning. This paper also includes examples of the Mahout deep learning integration use and its application in real contexts. This article describes the challenges that currently organizations face in handling big data and indeed, the potential threats these challenges pose to the success of deep learning techniques when used in organizations' big data processing and analysis. © 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

Orbit-Orbit Interaction in Spatiotemporal Optical Vortex

引用

engineering 2025年第2期45卷 44-51页

作者： Jian Chen Jie Zhao Xi Shen Dewei Mo Cheng-Wei Qiu Qiwen Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore

While spin-orbit interaction has been extensively studied,few investigations have reported on the interaction between orbital angular momenta(OAMs).In this work,we study a new type of orbit-orbit coupling between the longitudinal OAM and the transverse OAM carried by a three-dimensional(3D)spatiotemporal optical vortex(STOV)in the process of tight *** 3D STOV possesses orthogonal OAMs in the x-y,t-x,and y-t planes,and is preconditioned to overcome the spatiotemporal astigmatism effect.x,y,and t are the axes in the spatiotemporal *** corresponding focused wavepacket is calculated by employing the Debye diffraction theory,showing that a phase singularity ring is generated by the interactions among the transverse and longitudinal vortices in the highly confined *** Fourier-transform decomposition of the Debye integral is employed to analyze the mechanism of the orbit-orbit *** is the first revelation of coupling between the longitudinal OAM and the transverse OAM,paving the way for potential applications in optical trapping,laser machining,nonlinear light-matter interactions,and more.

关键词： Spatiotemporal optical vortex Orbital angular momentum Momentum interaction Highly confined wavepacket Diffraction

来源：评论

学校读者我要写书评

暂无评论

Automatic Transportation Mode Classification Using a Deep Reinforcement Learning Approach With Smartphone Sensors

引用

IEEE Access 2024年 12卷 514-533页

作者： Taherinavid, Siavash Moravvej, Seyed Vahid Chen, Yen-Lin Yang, Jing Ku, Chin Soon Yee, Por Lip Iran University of Science and Technology School of Civil Engineering Tehran13114-16846 Iran Isfahan University of Technology Department of Electrical and Computer Engineering Isfahan84156-83111 Iran National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Malaya Faculty of Computer Science and Information Technology Department of Computer System and Technology Kuala Lumpur50603 Malaysia Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

The increasing dependence on smartphones with advanced sensors has highlighted the imperative of precise transportation mode classification, pivotal for domains like health monitoring and urban planning. This research is motivated by the pressing demand to enhance transportation mode classification, leveraging the potential of smartphone sensors, notably the accelerometer, magnetometer, and gyroscope. In response to this challenge, we present a novel automated classification model rooted in deep reinforcement learning. Our model stands out for its innovative approach of harnessing enhanced features through artificial neural networks (ANNs) and visualizing the classification task as a structured series of decision-making events. Our model adopts an improved differential evolution (DE) algorithm for initializing weights, coupled with a specialized agent-environment relationship. Every correct classification earns the agent a reward, with additional emphasis on the accurate categorization of less frequent modes through a distinct reward strategy. The Upper Confidence Bound (UCB) technique is used for action selection, promoting deep-seated knowledge, and minimizing reliance on chance. A notable innovation in our work is the introduction of a cluster-centric mutation operation within the DE algorithm. This operation strategically identifies optimal clusters in the current DE population and forges potential solutions using a pioneering update mechanism. When assessed on the extensive HTC dataset, which includes 8311 hours of data gathered from 224 participants over two years. Noteworthy results spotlight an accuracy of 0.88±0.03 and an F-measure of 0.87±0.02, underscoring the efficacy of our approach for large-scale transportation mode classification tasks. This work introduces an innovative strategy in the realm of transportation mode classification, emphasizing both precision and reliability, addressing the pressing need for enhanced classification mechanisms in an eve

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Battery Monitoring system on IoT-Based Smart Micro Grid 4

Battery Monitoring System on IoT-Based Smart Micro Grid

引用

4th International Conference on Electronic and Electrical engineering and Intelligent system, ICE3IS 2024

作者： Iksan, Nur Widodo, Djoko Adi Djuniadi, Djuniadi Putri, Riana Defi Mahadji Suryanto, Agus Udayanti, Erika Devi Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Indonesia Universitas Dian Nuswantoro Faculty of Computer Science Department of Information System Indonesia

ISBN: (纸本)9798350378368

The use of batteries as an energy storage medium has a very important role in the installation of renewable energy power plants, such as photovoltaics to overcome intermittency in photovoltaics and to maintain stable power quality. In this study, the installation of solar plants that was used as the research object was a smart micro grid that integrates photovoltaic electrical energy sources with the Utility electricity network for residential scale. The battery monitoring system is used to manage the performance of existing batteries on the electricity grid through analysis of the battery's electrical values such as current, voltage, power and energy, so that it can function optimally in storing electrical energy and supplying electricity to users. Internet of things (IoT) technology is used to provide easy transfer of data obtained through the process of data acquisition to data visualization provided to be accessed by users in real time. This research aims to develop an IoT-based battery monitoring system. The development carried out focuses on the data acquisition process, the data transfer process using IoT technology, the process of analyzing and visualizing data on the IoT cloud and remote access to users. © 2024 IEEE.

关键词： Battery IoT Monitoring Smart Micro Grid

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

science China(Information sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

Reconstruction Attacks in Template-Based ECG Biometric Recognition systems

引用

IEEE Internet of Things Journal 2024年第8期11卷 14971-14984页

作者： Lee, Song-Hong Nien, Cing-Ping Wu, Shun-Chi Swindlehurst, A. Lee National Tsing Hua University Department of Engineering and System Science Hsinchu30013 Taiwan University of California Department of Electrical Engineering and Computer Science IrvineCA92697 United States

The success of Internet of Things (IoT) services will be determined by how the security of the IoT devices and the networks to which they are connected can be guaranteed. Integrating biometric recognition technology into IoT systems has gained popularity as a means of accomplishing this objective. Electrocardiograms (ECGs) have become a promising biometric tool for security because their intrinsic and dynamic nature makes them difficult to steal and forge for replay attacks. However, as with other biometric-based security approaches, attacks on ECG biometric systems have been developed. This study examines the vulnerability of template-based ECG biometric systems to reconstruction attacks. These attacks involve exposing the biometric templates of registered subjects in a hacked database and attempting to reconstruct their ECGs to spoof the system. Both deep learning models and 'heuristic' approaches are used to perform this task, depending on the intruder's level of knowledge of the template construction. Several reconstruction attack strategies are proposed and evaluated for fiducial- and PCA-based systems using ECGs from the Physikalisch-Technische Bundesanstalt database of 285 subjects. The experimental results demonstrate a reconstruction similarity of at least 0.93 and an increase in the false-positive identification-error rate of more than 73%. © 2014 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Large circuit models: opportunities and challenges

引用

science China(Information sciences) 2024年第10期67卷 25-66页

作者： Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y.YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU Huawei Noah’s Ark Lab School of Integrated Circuits Peking University Faculty of Electrical Engineering and Computer Science Ningbo University Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Department of Computer Science and Engineering The Chinese University of Hong Kong School of Integrated Circuits Southeast University Huawei HiSilicon Peng Cheng Laboratory School of Computer Science Peking University School of Microelectronics State Key Laboratory of Integrated Chips and System Fudan University School of Artificial Intelligence Shanghai Jiao Tong University

Within the electronic design automation(EDA) domain, artificial intelligence(AI)-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an “AI4EDA” approach falls short of achieving a holistic design synthesis and understanding,overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This study argues for a paradigm shift from AI4EDA towards AI-rooted EDA from the ground up, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, register-transfer level(RTL) designs, circuit netlists,and physical layouts. We champion the creation of large circuit models(LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-rooted philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound “shift-left” in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design-tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area(PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

关键词： AI-rooted EDA large circuit models (LCMs) multimodal circuit representation learning circuit optimization

来源：评论

学校读者我要写书评

暂无评论

Number Plate Recognition Using OpenCV 6

Number Plate Recognition Using OpenCV

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Roopa Chandrika, R. Vanitha, K. Thahaseen, Aafiya Chandramma, R. Neerugatti, Vikram Mahesh, T.R. Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Al-Ameen Engineering College Department of Computer Science and Engineering Erode India Bangalore India Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350306613

The advancement of automated number plate recognition (ANPR) systems has garnered noteworthy attention in recent times owing to their diverse applications across multiple domains, including traffic management, parking management, and law enforcement. This paper presents an innovative ANPR method using OpenCV, an open-source computer vision library. Developing ANPR systems is a great fit for OpenCV since it offers a flexible platform for image processing and computer vision tasks. The suggested method effectively detects and recognizes number plates from images and video streams by utilizing OpenCV's capabilities for feature extraction, image preprocessing, and machine learning. Character segmentation, optical character recognitlon (OCR), and licence plate localization are important stages in the process. The ANPR system's accuracy and effectiveness are increased by using these strategies. A variety of real-world datasets, including different lighting conditions, camera angles, and vehicle types, are used in extensive experiments to assess the system's performance. The outcomes show how well the OpenCV-based ANPR system performs in tasks requiring license plate recognition, attaining high accuracy and resilience. Additionally, covered in the paper are possible uses for the ANPR system in security systems, vehicle tracking, and traffic monitoring. To make sure the system is workable in a variety of situations, scalability and real-time implementation are also taken into account. © 2024 IEEE.

关键词： machine learning number plate OpenCV recognition

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：