检索结果-内蒙古大学图书馆

7th International Conference on Image Information Processing, ICIIP 2023

作者： Sundas, Amit Singh, Gurpreet Badotra, Sumit Verma, Amit Kaur, Balwinder Lovely Professional University Department of Computer Science And Engineering Punjab Phagwara India Bennett University School of Computer Engineering And Technology Greater Noida India University Center For Research And Development Department of Computer Science And Engineering Chandigarh India

ISBN: (纸本)9798350371406

In the critical care unit, bedside monitors track patients' vital signs to help physicians make choices. With increased storage and analysis capability, huge datasets may be processed faster. Lately, physiological data have showed promise for identifying specific consequences and occurrences. At the critical care unit. Our method was aimed to Live bedside vital sign data may be automatically retrieved. Devices that can predict patient mechanical ventilation for more than 4 days in a pediatric critical care unit. 284 ICU patients had their vital signs and clinical history documented continuously from admission. 24 hours of artificial breathing in Boston Children's Hospital's pediatric medical-surgical critical care unit. They trained many machine learning models using subsets. Assess the likelihood of each person staying long. We examined our systems' capacity to anticipate outcomes for unknown persons. Adding vital sign data increased model performance to 90% (area under the curve) from >83% when using just vital sign data. static participant clinical data in electronic health records. For research group representative sample reliability, we employed this approach on 300 individually trained tests employing a variety of sets for training and hold-out validation. Other deep learning methods failed to forecast like ours. Gaining equivalent work outcomes prediction skills. We may be able to help create scalable ICU-based prediction systems that leverage real-time patient monitor data. © 2023 IEEE.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

GrCol-PPFL:User-Based Group Collaborative Federated Learning Privacy Protection Framework

引用

computers, Materials & Continua 2023年第1期74卷 1923-1939页

作者： Jieren Cheng Zhenhao Liu Yiming Shi Ping Luo Victor S.Sheng School of Compute Science and Technology Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China Department of Computer Science Texas Tech University TX79409USA

With the increasing number of smart devices and the development of machine learning technology,the value of users’personal data is becoming more and more *** on the premise of protecting users’personal privacy data,federated learning(FL)uses data stored on edge devices to realize training tasks by contributing training model parameters without revealing the original ***,since FL can still leak the user’s original data by exchanging gradient *** existing privacy protection strategy will increase the uplink time due to encryption *** is a huge challenge in terms of *** there are a large number of devices,the privacy protection cost of the system is *** on these issues,we propose a privacy-preserving scheme of user-based group collaborative federated learning(GrCol-PPFL).Our scheme primarily divides participants into several groups and each group communicates in a chained transmission *** groups work in parallel at the same *** server distributes a random parameter with the same dimension as the model parameter for each participant as a mask for the model *** use the public datasets of modified national institute of standards and technology database(MNIST)to test the model *** experimental results show that GrCol-PPFL not only ensures the accuracy of themodel,but also ensures the security of the user’s original data when users collude with each ***,through numerical experiments,we show that by changing the number of groups,we can find the optimal number of groups that reduces the uplink consumption time.

关键词： Federated learning privacy protection uplink consumption time

来源：评论

学校读者我要写书评

暂无评论

PBRL-TChain: A performance-enhanced permissioned blockchain for time-critical applications based on reinforcement learning

引用

Future Generation computer Systems 2024年 154卷 301-313页

作者： Zhang, Yiguang Lin, Junxiong Lu, Zhihui Duan, Qiang Huang, Shih-Chia School of Computer Science Fudan University Shanghai200433 China Information Sciences & Technology Department Pennsylvania State University AbingtonPA United States Shanghai Blockchain Engineering Research Center Shanghai China Department of Electronic Engineering National Taipei University of Technology Taiwan

Permissioned blockchains can provide high security and reliability for various Internet of Things (IoT) systems, such as smart healthcare and vehicular networks. However, the performance issues of permissioned blockchains have been a constraint for fully supporting time-critical tasks with tight requirements of low latency and high throughput. This paper proposes PBRL-TChain, a performance-enhanced permissioned blockchain for time-critical applications based on deep reinforcement learning (DRL). First, we propose a priority ordering mechanism to minimize latency and maximize reliability. Then, we design a fast retransmission mechanism to alleviate the impact of transaction conflicts on the latency performance. Finally, we propose a DRL-based dynamic adjustment method in PBRL-TChain to achieve better performance and reliability. Experiments show that our method outperforms existing methods. Compared with Fabric++ and Athena, it can reduce the latency of time-critical transactions by 10 times, achieving a level of 10 ms, significantly improving the system's performance and reliability. © 2023 Elsevier B.V.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Model for Bottles in a Manufacturing Unit 3

Anomaly Detection Model for Bottles in a Manufacturing Unit

引用

3rd International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2023

作者： Sreerama, Sai Lahari Shashank, H.R. Shashank, R.B. Shankar, T. Hemavathy, R. Ramakanth Kumar, P. RV College of Engineering Department of Computer Science and Engineering Bangalore India CCTV Research Center RV College of Engineering Bangalore India

ISBN: (纸本)9798350343632

Emphasizing the consistent production of defect-less bottles in a manufacturing unit is crucial to ensure product integrity and customer satisfaction. Nevertheless, anomalies during the manufacturing process can lead to defects that compromise the overall quality of the bottles produced. The presented approach introduces innovation in detecting three critical anomalies in bottle manufacturing units: dents on the bottle surface, skewed caps, and deformities resulting in non-straight bottles. In conclusion, a robust anomaly detection solution tailored for the bottle manufacturing industry is contributed. By leveraging computer vision and machine learning techniques, the approach efficiently detects dents, skewed caps, and deformities in real-time, thereby facilitating improved quality control and minimized production wastage. © 2023 IEEE.

关键词： Convolutional Neural Networks Hough Line Transformation You Look Only Once (YOLO v4)

来源：评论

学校读者我要写书评

暂无评论

MARM-HyLiWi: Mobility-Aware Rate Maximization in Link Aggregation Enabled Hybrid Li-Fi/Wi-Fi Networks 17

MARM-HyLiWi: Mobility-Aware Rate Maximization in Link Aggreg...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Paramita, Saswati Mondal, Rajorshi Bhattacharya, Arani Bohara, Vivek Ashok Srivastava, Anand Delhi Wirocomm Research Group Center of Excellence Li-Fi Department of Electronics and Communication Engineering New Delhi India IIIT Delhi Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798331531195

Light Fidelity (Li-Fi) offers high data rates in confined areas but is limited by susceptibility to signal blockages and constrained coverage. To address these limitations, Li-Fi is often integrated with Wi-Fi in a heterogeneous network (HetNet), leveraging Li-Fi's speed with Wi-Fi's broader coverage. However, hybrid networks introduce frequent handovers between Li-Fi and Wi-Fi access points (APs), especially for users near blind spots or with limited mobility. This paper proposes a link aggregation (LA) approach for a Li-Fi and Wi-Fi HetNet (LA-HLWN), where users receive data from both types of APs simultaneously, enhancing data rates and reducing handover frequency. To manage network load effectively, we develop an algorithm for dynamic data rate allocation, formulated as a multi-dimensional commodity flow problem that considers factors such as user requirements, AP signal quality, and backhaul conditions. Given the NP-hard nature of this problem, our solution models it initially as an integer linear programming (ILP) challenge and then applies a relaxed linear programming (LPP) approach with a rounding technique for real-time allocation. Additionally, to balance throughput and reduce the computational overhead, we implement a strategy to control handover frequency and load distribution across APs, achieving a 54% improvement in throughput. This approach demonstrates the potential of LA in enhancing user satisfaction and system performance in hybrid Li-Fi/Wi-Fi networks. © 2025 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Giant phonon-skyrmion coupling in ferromagnet/heavy metal heterostructures

引用

Physical Review B 2024年第6期110卷 064423-064423页

作者： Egor Savostin Vitaliy Lomakin Program in Materials Science and Engineering Center for Memory and Recording Research Department of Electrical and Computer Engineering

The strong impact of the strain-induced Dzyaloshinskii-Moriya interaction (SIDMI) on the magnetization dynamics of skyrmions in nanomagnetic structures is demonstrated. The effects of SIDMI are characterized by skyrmion equations (SEs) of motion and magnetoelastic (ME) equations. The study is performed on a model system of MgO/CoFe/Pt stacked on a piezoelectric substrate. The results demonstrate a major nonlinear amplification in both the first- and higher-harmonic magnitudes of the skyrmion breathing mode due to SIDMI. Remarkably, this enhancement can trigger a skyrmion collapse, enabling its deletion with ultraweak strain-induced excitations. The SIDMI effect is shown to be much more significant than the conventional ME effect. These findings open different avenues for the efficient manipulation of nanomagnetic structures through strain.

关键词： Exchange interaction Magnetic interactions Magnetization dynamics Magnetoacoustic effect Micromagnetism Spin dynamics

来源：评论

学校读者我要写书评

暂无评论

Augmenting Internet of Medical Things Security:Deep Ensemble Integration and Methodological Fusion

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2185-2223页

作者： Hamad Naeem Amjad Alsirhani Faeiz MAlserhani Farhan Ullah Ondrej Krejcar Faculty of Informatics and Management Center for Basic and Applied ResearchUniversity of Hradec KraloveHradec Kralove50003Czech Republic Department of Computer Science College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Engineering&Networks College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Cybersecurity Center Prince Mohammad Bin Fahd UniversityAl JawharahKhobarDhahran34754Saudi Arabia

When it comes to smart healthcare business systems,network-based intrusion detection systems are crucial for protecting the system and its networks from malicious network *** protect IoMT devices and networks in healthcare and medical settings,our proposed model serves as a powerful tool for monitoring IoMT *** study presents a robust methodology for intrusion detection in Internet of Medical Things(IoMT)environments,integrating data augmentation,feature selection,and ensemble learning to effectively handle IoMT data *** rigorous preprocessing,including feature extraction,correlation removal,and Recursive Feature Elimi-nation(RFE),selected features are standardized and reshaped for deep learning *** using the BAT algorithm enhances dataset *** deep learning models,Transformer-based neural networks,self-attention Deep Convolutional Neural Networks(DCNNs),and Long Short-Term Memory(LSTM)networks,are trained to capture diverse data *** predictions form a meta-feature set for a subsequent meta-learner,which combines model *** classifiers validate meta-learner features for broad algorithm *** comprehensive method demonstrates high accuracy and robustness in IoMT intrusion *** were conducted using two datasets:the publicly available WUSTL-EHMS-2020 dataset,which contains two distinct categories,and the CICIoMT2024 dataset,encompassing sixteen *** results showcase the method’s exceptional performance,achieving optimal scores of 100%on the WUSTL-EHMS-2020 dataset and 99%on the CICIoMT2024.

关键词： Cyberattack ensemble learning feature selection intrusion detection smart cities machine learning BAT augmentation

来源：评论

学校读者我要写书评

暂无评论

A Composite Decomposition Method for Large-Scale Global Optimization

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6304-6319页

作者： Tian, Maojiang Chen, Minyang Du, Wei Tang, Yang Jin, Yaochu Yen, Gary G. Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China East China University of Science and Technology Engineering Research Center of Process System Engineering Ministry of Education Shanghai200237 China Westlake University School of Engineering Hangzhou310030 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74048 United States

Cooperative coevolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the grouping stage significantly impact the performance of the optimization process. While the general separability grouping (GSG) method has overcome the limitation of previous differential grouping (DG) methods by enabling the decomposition of nonadditively separable functions, it suffers from high computational complexity. To address this challenge, this article proposes a composite separability grouping (CSG) method, seamlessly integrating DG and GSG into a problem decomposition framework to utilize the strengths of both approaches. CSG introduces a step-by-step decomposition framework that accurately decomposes various problem types using fewer computational resources. By sequentially identifying additively, multiplicatively and generally separable variables, CSG progressively groups nonseparable variables by recursively considering the interactions between each nonseparable variable and the formed nonseparable groups. Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a nonseparable variable grouping method. These two methods are designed to effectively detect multiplicatively separable variables and efficiently group nonseparable variables, respectively. Extensive experimental results demonstrate that CSG achieves more accurate variable grouping with lower computational complexity compared to GSG and state-of-the-art DG-series designs. © 2024 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimized Home Appliance Scheduling Utilizing Reinforcement Learning for Enhanced Load Profile

Optimized Home Appliance Scheduling Utilizing Reinforcement ...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Hassan, Eslam Al Abughali, Ahmed Alansari, Mohamad Muhaidat, Sami Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Khalifa University 6G Research Center Department of Computer Science Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350376715

With the recent multiple increases in the fuel prices, and as most of electricity generation are fossil-fuelled, utilities were obliged to raise the electricity tariffs accordingly. Subsequently, individuals are compelled to reduce their energy usage to cut the daily energy bills. One approach to address this challenge is to enhance the overall efficiency of electrical systems by shifting peak demand periods, rather than relying on expanding the transmission network to correspond to peak demand indirectly. With the smart grid and deploying bi-directional smart meters, it is probable to perform load control using innovative Home Energy Management (HEM) systems with demand responseenabled appliances. A HEM system utilizes automated control and monitoring capabilities for household appliances, enabling it to make decisions regarding load shedding and shifting according to a predefined set of preferences. This in turn helps alleviate power system stress conditions and shift the peak demand. This study aims to develop two intelligent HEM systems with responseenabled appliances considering Reinforcement Learning (RL) as the main controlling algorithm and Time-of-Use (ToU) electricity price. The objective of the first controller is to minimize the power consumption while the second controller aims to enhance the load profile. The proposed RL-based intelligent HEM systems achieved 8.3% reduction and 1.25% for the minimization and load enhancement cases, respectively, achieving flexible appliance usage schedules that will minimize consumer energy bill without user lifestyle disruptions. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Diagnosis Using Sparrow Search Algorithm Based Deep Learning Model

引用

computer Systems science & engineering 2023年第2期44卷 1793-1806页

作者： G.Ignisha Rajathi R.Ramesh Kumar D.Ravikumar T.Joel Seifedine Kadry Chang-Won Jeong Yunyoung Nam Department of Computer Science and Business Systems Sri Krishna College of Engineering and TechnologyCoimbatore641008India Department of Information Technology Sri Krishna College of TechnologyCoimbatore641008India Department of Electronics and Communication Engineering Kings Engineering CollegeChennai602117India Department of Electronics and Communication Engineering R.M.K.Engineering CollegeChennai601206India Deparmtent of Applied Data Science Noroff University CollegeKristiansandNorway Medical Convergence Research Center Wonkwang UniversityIksanKorea Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea

Recently,Internet of Medical Things(IoMT)has gained considerable attention to provide improved healthcare services to *** earlier diag-nosis of brain tumor(BT)using medical imaging becomes an essential task,auto-mated IoMT and cloud enabled BT diagnosis model can be devised using recent deep learning *** this motivation,this paper introduces a novel IoMT and cloud enabled BT diagnosis model,named *** IoMTC-HDBT model comprises the data acquisition process by the use of IoMT devices which captures the magnetic resonance imaging(MRI)brain images and transmit them to the cloud ***,adaptive windowﬁltering(AWF)based image preprocessing is used to remove *** addition,the cloud server executes the disease diagnosis model which includes the sparrow search algorithm(SSA)with GoogleNet(SSA-GN)*** IoMTC-HDBT model applies functional link neural network(FLNN),which has the ability to detect and classify the MRI brain images as normal or ***ﬁnds useful to generate the reports instantly for patients located in remote *** validation of the IoMTC-HDBT model takes place against BRATS2015 Challenge dataset and the experimental analysis is car-ried out interms of sensitivity,accuracy,and speciﬁ*** experimentation out-come pointed out the betterment of the proposed model with the accuracy of 0.984.

关键词： Internet of medical things healthcare brain tumor disease classiﬁcation deep learning metaheuristics

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：