检索结果-内蒙古大学图书馆

Transparent and Accurate COVID-19 Diagnosis:Integrating Explainable AI with Advanced Deep Learning in CT Imaging

computer Modeling in engineering & sciences 2024年第6期139卷 3101-3123页

作者： Mohammad Mehedi Hassan Salman A.AlQahtani Mabrook S.AlRakhami Ahmed Zohier Elhendi Department of Information Systems College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Science Technology and Innovation Department King Saud UniversityRiyadh11543Saudi Arabia

In the current landscape of the COVID-19 pandemic,the utilization of deep learning in medical imaging,especially in chest computed tomography(CT)scan analysis for virus detection,has become increasingly *** its potential,deep learning’s“black box”nature has been a major impediment to its broader acceptance in clinical environments,where transparency in decision-making is *** bridge this gap,our research integrates Explainable AI(XAI)techniques,specifically the Local Interpretable Model-Agnostic Explanations(LIME)method,with advanced deep learning *** integration forms a sophisticated and transparent framework for COVID-19 identification,enhancing the capability of standard Convolutional Neural Network(CNN)models through transfer learning and data *** approach leverages the refined DenseNet201 architecture for superior feature extraction and employs data augmentation strategies to foster robust model *** pivotal element of our methodology is the use of LIME,which demystifies the AI decision-making process,providing clinicians with clear,interpretable insights into the AI’s *** unique combination of an optimized Deep Neural Network(DNN)with LIME not only elevates the precision in detecting COVID-19 cases but also equips healthcare professionals with a deeper understanding of the diagnostic *** method,validated on the SARS-COV-2 CT-Scan dataset,demonstrates exceptional diagnostic accuracy,with performance metrics that reinforce its potential for seamless integration into modern healthcare *** innovative approach marks a significant advancement in creating explainable and trustworthy AI tools for medical decisionmaking in the ongoing battle against COVID-19.

关键词： Explainable AI COVID-19 CT images deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing stencil printing in PCB production using deep learning based approach for residue classification and optimization

引用

International Journal of Information Technology (Singapore) 2025年 1-11页

作者： Jain, Swati Patel, Ruhi Desai, Manad Verma, Jai Prakash Yoon, Sang Won Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India Department of Systems Science and Industrial Engineering State University of New York at Binghamton Binghamton NY United States

Surface-mount technology (SMT) is the technology used in the production of printed circuit boards (PCB) plays a vital role in PCB manufacturing for applications ranging from communication devices to medical systems. A significant challenge in the stencil printing process, a critical step in PCB production, is solder paste buildup in stencil apertures, contributing to 57%–71% of soldering defects. To address this issue, this study presents a convolutional neural network (CNN)-based framework for categorizing solder paste residue levels into three classes: low, moderate, and high. The methodology involves cropping and pre-processing images of stencil apertures, which are then fed into the CNN model for classification. To enhance model robustness and prevent overfitting, data augmentation techniques, including aperture rotation, are applied, effectively increasing the dataset size and promoting generalization. The model achieves a classification accuracy of 87% during testing, with precision and recall values provided for each residue class. This approach aims to optimize the stencil printing process by enabling accurate residue categorization and facilitating targeted cleaning cycles, ultimately reducing soldering defects and improving PCB production efficiency. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： CNN Deep learning Printed sensing board (PCB) Residue build-up Stencil printing Surface mount technology (SMT) SVM VGG16

来源：评论

学校读者我要写书评

暂无评论

Scheduling Bi-Objective Lot-Streaming Hybrid Flow Shops with Consistent Sublots via an Enhanced Artificial Bee Colony Algorithm

引用

Complex System Modeling and Simulation 2025年第1期5卷 46-67页

作者： Benxue Lu Kaizhou Gao Peiyong Duan Adam Slowik School of Computer Science Liaocheng UniversityLiaocheng 252000China Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China School of Information and Automation Engineering Qilu University of TechnologyJinan 250353China Department of Electronics and Computer Science Koszalin University of TechnologyKoszalin 75-453Poland

This work addresses bi-objective hybrid flow shop scheduling problems considering consistent sublots(Bi-HFSP_CS).The objectives are to minimize the makespan and total energy ***,the Bi-HFSP_CS is formalized,followed by the establishment of a mathematical ***,enhanced version of the artificial bee colony(ABC)algorithms is proposed for tackling the Bi-HFSP_***,fourteen local search operators are employed to search for better *** different Q-learning tactics are developed to embed into the ABC algorithm to guide the selection of operators throughout the iteration ***,the proposed tactics are assessed for their efficacy through a comparison of the ABC algorithm,its three variants,and three effective algorithms in resolving 95 instances of 35 different *** experimental results and analysis showcase that the enhanced ABC algorithm combined with Q-learning(QABC1)demonstrates as the top performer for solving concerned *** study introduces a novel approach to solve the Bi-HFSP_CS and illustrates its efficacy and superior competitive strength,offering beneficial perspectives for exploration and research in relevant domains.

关键词： hybrid flow shop scheduling Q-learning lot streaming local search

来源：评论

学校读者我要写书评

暂无评论

A Summary on Privacy and Security in Cloud Data using Various Approaches 4

A Summary on Privacy and Security in Cloud Data using Variou...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Jayaram, B. Sethukarasi, T. Sindhu, M. Jeyamohan, H. Rmk Engineering College Department of Computer Science and Business Systems 601206 India Rmk Engineering College Department of Computer Science and Engineering 601206 India Velammal Engineering College Department of Computer Science and Engineering Chennai600066 India

ISBN: (纸本)9798350300888

Nowadays online users are prone to lot of security related issues in protecting their data. In order to achieve this privacy preservation in cloud plays a major role. For this purpose various technologies related to cyber security was proposed according to application in which the security has to be implemented. Some of these techniques include machine learning, deep learning, federated learning natural language processing, block chain etc. This paper analyses various approaches proposed by researches. This paper is divided into 7 sections such as role of cyber security in privacy preservation, privacy preservation in cloud using cyber security, what is a hybrid model and how to build it to implement features of security, Malicious node deduction in wireless sensor network using cyber security, relation between cyber-security and block-chain, federated learning and differential privacy. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Secure Authentication and Authorization with MAC Address and Cryptography-Based Multi-Factor Algorithm 2

Secure Authentication and Authorization with MAC Address and...

引用

2nd International Conference on Informatics, ICI 2023

作者： Abualkas, Yaser M.A. Lalitha Bhaskari, D. Andhra University Visakhapatnam Department of Computer Science and Systems Engineering India

ISBN: (纸本)9798350343830

The aim of this paper is to propose an MFA (Multi-Factor Authentication) algorithm using MAC address that achieves authentication and authorization in a secure and efficient manner. At first aim to achieve authentication by algorithm involves a user registration process, generating a random MAC address, and storing user data in an encoded format using map charset. During the login process, a QR code is generated containing user details, and the MAC address is checked against the local MAC address stored in the user device. If the MAC addresses match, the user is granted access to the account. In case of a mismatch, an alert is sent to the user. This algorithm provides an additional layer of security and prevents unauthorized access to user accounts for the second aim to achieve authorization by The Cryptography algorithm by MAC address provides a high level of security and authorization. The algorithm involves converting the target device's MAC address and plain text to ASCII code, adding a random number, and applying the RSA algorithm. The output is then stored in an n*n matrix, which is reordered for added security. The encrypted text is then sent to the target device, ensuring secure communication. This algorithm prevents unauthorized access to sensitive information and provides an additional layer of security. This paper highlights the importance of cryptography in ensuring data security and proposes a new algorithm that provides a high level of security and authorization. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Multi-task System for Multiple Languages Translation Using Transformers 4th

Multi-task System for Multiple Languages Translation Using T...

引用

4th International Conference on Advances in Distributed Computing and Machine Learning, ICADCML 2023

作者： Nunna, Bhargava Satya Department of Computer Science and Systems Engineering Andhra University Vishakapatnam India

ISBN: (纸本)9789819912025

In this work, we explore the problem of the multi-task Neural Machine Translation (NMT) model which can simultaneously translate given sentences from multiple source languages to a single target language. Our solution is supported by a recently proposed transformer model, where we extended the neural machine translation to a multi-task system that shares the common target language translation and separates the modeling of different source language representations. The multi-task system could be helpful in scenarios where insufficient data or imbalanced data exists. As the multi task system shares the parameters of different language pairs, the language pair with inadequate data could utilize the resources from data-abundant language pairs and can improve the translation quality. Our approach is also considerably faster learning when compared to separately trained NMTs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

A Weighted Optimal Scheduling Scheme for Congestion Control in Cloud Data Center Networks

引用

IEEE Transactions on Services Computing 2023年第4期16卷 1-9页

作者： Li Y. Jian S. Hsieh S. Chung W. Zomaya A.Y. Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Department of Computer Science and Information Systems The University of Sydney Australia

Cloud services are experiencing a remarkable increase in the number of users and the resource required over the past few years. Thus, it has become a great challenge for the internet vendors to make a robust framework to serve the customers with low cost and delay. Congestion control is one of the essential topics of routing algorithms in cloud data center networks. In this paper, we propose a weighted optimal scheduling scheme WSPR for congestion control in cloud data center networks which prevents the congestion in advance with the global view so that it can make good use of vacant network resources. We choose BCube as our network model and modify the network topology to fit software-defined networks so as to have a full view of the topology. First, we design the SP graph which contains all shortest paths between a source server and a destination server. Second, we propose WSPR to allocate the most appropriate path to each flow for congestion control. We implement a system to simulate a data center, and evaluate our proposed scheme WSPR by comparing WSPR with other classical methods. The experimental results demonstrate that our proposed scheme WSPR has the best performance in terms of the maximum delay, average delay, and throughput among all compared methods. IEEE

关键词： Cloud computing Cloud data center networks congestion control Data centers Network topology Optical switches Routing Servers software-defined networks Topology

来源：评论

学校读者我要写书评

暂无评论

Security Metrics and Authentication-based RouTing (SMART) Protocol for Vehicular IoT Networks

引用

SN computer science 2024年第2期5卷 1-14页

作者： Kumar, Rakesh Singh, Sunil K. Lobiyal, D.K. Kumar, Sudhakar Jawla, Shashi Department of Applied Computational Sciences & Engineering GLBITM Greater Uttar Pradesh Noida India Department of Computer Science & Engineering CCET Panjab University Chandigarh India School of Computer & Systems Sciences Jawaharlal Nehru University New Delhi India Department of Computer Science & Engineering SVIET Mohali India

Routing protocols, responsible for determining optimal paths, fall into two main categories: reactive and proactive protocols. In the realm of reactive routing protocols, exemplified by Ad hoc On-demand Distance Vector (AODV), routes are created only when there is an actual data transmission requirement. In contrast, proactive routing protocols maintain pre-computed paths to all potential destinations, resulting in reduced resource utilization within reactive protocols and continuous route maintenance within proactive ones. Reactive routing protocols are resource efficient as they establish routes as needed, while proactive counterparts maintain routing tables for all possible destinations, ensuring constant route availability regardless of data transmission demands. This paper primarily concentrates on the reactive routing protocol category, focusing on real-time path optimization and routing information updates. In the context of Vehicular Internet of Things (VIoT) networks, where malicious entities might attempt to flood, mislead, or impersonate routing packets, it is imperative to ensure robust security measures within the routing protocol. Unfortunately, secure routing protocols in VIoT networks, including AODV, SAODV, and SGHRP, often exhibit inefficiencies and impose a high overhead. To address these challenges, this research paper introduces the Security Metrics and Authentication-based RouTing (SMART) protocol for VIoT networks, with a focus on enhancing security while minimizing overhead. The SMART protocol utilizes the Merkle tree for hash (digest) generation, which is then encrypted using Elliptic Curve Cryptography (ECC) to reduce overhead. This proposed protocol enhances security by authenticating the source and incorporating security metrics into the routing information. To assess the performance of the SMART protocol, simulations were conducted using Network Simulator-2 (NS₂). The results demonstrated an improved packet delivery ratio, red

关键词： AODV Authentication ECC Hash digest Merkle Tree OBU Routing Protocol SAODV VIoT Networks

来源：评论

学校读者我要写书评

暂无评论

Continuous-Time Prediction of Industrial Paste Thickener System With Differential ODE-Net

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 686-698页

作者： Zhaolin Yuan Xiaorui Li Di Wu Xiaojuan Ban Nai-Qi Wu Hong-Ning Dai Hao Wang the Beijing Advanced Innovation Center for Materials Genome Engineering Institute of Artificial IntelligenceBeijing Key Laboratory of Knowledge Engineering for Materials ScienceSchool of Computer and Communication EngineeringUniversity of Science and Technology Beijing the Department of ICT and Natural Science Norwegian University of Science and Technology IEEE the Institute of Systems Engineering and Collaborative Laboratory for Intelligent Science and SystemsMacao University of Science and Technology the Department of Computing and Decision Sciences Lingnan University the Department of Computer Science Norwegian University of Science and Technology

It is crucial to predict the outputs of a thickening system,including the underflow concentration(UC)and mud pressure,for optimal control of the *** proliferation of industrial sensors and the availability of thickening-system data make this ***,the unique properties of thickening systems,such as the non-linearities,long-time delays,partially observed data,and continuous time evolution pose challenges on building data-driven predictive *** address the above challenges,we establish an integrated,deep-learning,continuous time network structure that consists of a sequential encoder,a state decoder,and a derivative module to learn the deterministic state space model from thickening *** a case study,we examine our methods with a tailing thickener manufactured by the FLSmidth installed with massive sensors and obtain extensive experimental *** results demonstrate that the proposed continuous-time model with the sequential encoder achieves better prediction performances than the existing discrete-time models and reduces the negative effects from long time delays by extracting features from historical system *** proposed method also demonstrates outstanding performances for both short and long term prediction tasks with the two proposed derivative types.

关键词： Industrial 24 paste thickener ordinary differential equation(ODE)-net recurrent neural network time series prediction

来源：评论

学校读者我要写书评

暂无评论

Traffic and Pollution Control Using IoT-Enabled Smart Routing Algorithm 2

Traffic and Pollution Control Using IoT-Enabled Smart Routin...

引用

2nd International Conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Hammed, S Shahul Preethi, C. Haripriya, K. Pavalarajan, S. Gowtham, M.R. Krithick, N. Akshaay PSNA College of Engineering and Technology Department of Computer Science and Business Systems Dindigul India

ISBN: (纸本)9798331505745

Urbanization has led to increased traffic congestion and air pollution, primarily from vehicle emissions, posing risks to public health and the environment. Existing traffic management systems are inefficient in integrating real-time pollution data, leading to reactive control measures. This project proposes an IoT-based smart traffic management system that integrates real-time air quality monitoring with dynamic traffic control. IoT sensors collect pollution and vehicle data, which is processed using cloud computing and machine learning to optimize traffic flow and reduce emissions. AI techniques provide transparency, helping city authorities understand and trust the system's decisions. The system also offers predictive analytics for proactive pollution management and a user-friendly dashboard for real-time visualization. The solution aims to reduce urban emissions, and enhance traffic efficiency, offering a sustainable approach for modern cities. © 2025 IEEE.

关键词： Traffic congestion

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：