检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 624-633页

作者： Ni, Shiwen Kao, Hung-Yu Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518000 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan

Recently, prompt-based learning has shown excellent performance on few-shot scenarios. Using frozen language models to tune trainable continuous prompt embeddings has become a popular and powerful methodology. For few-shot natural language understanding, even if we freeze the parameters of the pretrained language model, the learned pseudo-prompts might still be overfitted. In this article, we propose a novel masked Siamese prompt tuning (MSP-tuning) to improve few-shot natural language understanding. Concretely, MSP-tuning masks randomly out part of the prompt tokens to get a pair of masked Siamese prompts for each sample. Each training sample is then fed to the model twice with the masked Siamese prompts. Finally, MSP-tuning minimizes the Jensen-Shannon-divergence (JSD) between the two output probability distributions of the pretrained language model to regularize the model further. Experiment results on the few-shot GLUE benchmark and SuperGLUE benchmark show that MSP-tuning outperforms previous approaches. Numerically, our MSP-tuning achieves an average improvement of 1.79% (BERT-base) and 1.39% (BERT-large) of the GLUE benchmark and 1.90% (RoBERTa-base) and 1.71% (RoBERTa-large) of the SuperGLUE benchmark compared to state-of-the-art method P-tuning. Our method facilitates applying large pretrained language models in natural language understanding. © 2023 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Cognitive Computing-Based Mammographic Image Classification on an Internet of Medical

引用

computers, Materials & Continua 2022年第8期72卷 3945-3959页

作者： Romany F.Mansour Maha M.Althobaiti Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Recently,the Internet of Medical Things(IoMT)has become a research hotspot due to its various applicability in medical ***,the data analysis and management in IoMT remain challenging owing to the existence of a massive number of devices linked to the server environment,generating a massive quantity of healthcare *** such cases,cognitive computing can be employed that uses many intelligent technologies-machine learning(ML),deep learning(DL),artificial intelligence(AI),natural language processing(NLP)and others-to comprehend data ***,breast cancer(BC)has been found to be a major cause of mortality among ladies *** detection and classification of BC using digital mammograms can decrease the mortality *** paper presents a novel deep learning-enabled multi-objective mayfly optimization algorithm(DLMOMFO)for BC diagnosis and classification in the IoMT *** goal of this paper is to integrate deep learning(DL)and cognitive computing-based techniques for e-healthcare applications as a part of IoMT technology to detect and classify *** proposed DL-MOMFO algorithm involved Adaptive Weighted Mean Filter(AWMF)-based noise removal and contrast-limited adaptive histogram equalisation(CLAHE)-based contrast improvement techniques to improve the quality of the digital *** addition,a U-Net architecture-based segmentation method was utilised to detect diseased regions in the ***,a SqueezeNet-based feature extraction and a fuzzy support vector machine(FSVM)classifier were used in the presented *** enhance the diagnostic performance of the presented method,the MOMFO algorithm was used to effectively tune the parameters of the SqueezeNet and FSVM *** DL-MOMFO technique was tested on the MIAS database,and the experimental outcomes revealed that the DL-MOMFO technique outperformed existing techniques.

关键词： Cognitive computing breast cancer digital mammograms image processing internet of medical things smart healthcare

来源：评论

学校读者我要写书评

暂无评论

A proposed framework for crop yield prediction using hybrid feature selection approach and optimized machine learning

引用

Neural Computing and Applications 2024年第33期36卷 20723-20750页

作者： Abdel-salam, Mahmoud Kumar, Neeraj Mahajan, Shubham Faculty of Computer and Information Science Mansoura University Mansoura Egypt Department of CSE Thapar Institute of Engineering and Technology Deemed to Be University Patiala147004 India Delhi-NCR India

Accurately predicting crop yield is essential for optimizing agricultural practices and ensuring food security. However, existing approaches often struggle to capture the complex interactions between various environmental factors and crop growth, leading to suboptimal predictions. Consequently, identifying the most important feature is vital when leveraging Support Vector Regressor (SVR) for crop yield prediction. In addition, the manual tuning of SVR hyperparameters may not always offer high accuracy. In this paper, we introduce a novel framework for predicting crop yields that address these challenges. Our framework integrates a new hybrid feature selection approach with an optimized SVR model to enhance prediction accuracy efficiently. The proposed framework comprises three phases: preprocessing, hybrid feature selection, and prediction phases. In preprocessing phase, data normalization is conducted, followed by an application of K-means clustering in conjunction with the correlation-based filter (CFS) to generate a reduced dataset. Subsequently, in the hybrid feature selection phase, a novel hybrid FMIG-RFE feature selection approach is proposed. Finally, the prediction phase introduces an improved variant of Crayfish Optimization Algorithm (COA), named ICOA, which is utilized to optimize the hyperparameters of SVR model thereby achieving superior prediction accuracy along with the novel hybrid feature selection approach. Several experiments are conducted to assess and evaluate the performance of the proposed framework. The results demonstrated the superior performance of the proposed framework over state-of-art approaches. Furthermore, experimental findings regarding the ICOA optimization algorithm affirm its efficacy in optimizing the hyperparameters of SVR model, thereby enhancing both prediction accuracy and computational efficiency, surpassing existing algorithms. © The Author(s) 2024.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

CA-DTS:A Distributed and Collaborative Task Scheduling Algorithm for Edge Computing Enabled Intelligent Road Network

引用

Journal of computer science & technology 2023年第5期38卷 1113-1131页

作者：胡世红罗渠元李光辉施巍松叶保留 Key Laboratory of Water Big Data Technology of Ministry of Water Resources Houhai UniversityNanjing 210098China School of Computer and Information Houhai UniversityNanjing 210098China School of Information Science and Technology Southwest Jiaotong UniversityChengdu 611756China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuci 214122China Department of Computer and Information Sciences University of DelawareNewarkDE 19716U.S.A National Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210093China

Edge computing enabled Intelligent Road Network(EC-IRN)provides powerful and convenient computing services for vehicles and roadside sensing *** continuous emergence of transportation applications has caused a huge burden on roadside units(RSUs)equipped with edge servers in the Intelligent Road Network(IRN).Collaborative task scheduling among RSUs is an effective way to solve this ***,it is challenging to achieve collaborative scheduling among different RSUs in a completely decentralized *** this paper,we first model the interactions involved in task scheduling among distributed RSUs as a Markov *** that multi-agent deep reinforcement learning(MADRL)is a promising approach for the Markov game in decision optimization,we propose a collaborative task scheduling algorithm based on MADRL for EC-IRN,named CA-DTS,aiming to minimize the long-term average delay of *** reduce the training costs caused by trial-and-error,CA-DTS specially designs a reward function and utilizes the distributed deployment and collective training architecture of counterfactual multi-agent policy gradient(COMA).To improve the stability of performance in large-scale environments,CA-DTS takes advantage of the action semantics network(ASN)to facilitate cooperation among multiple *** evaluation results of both the testbed and simulation demonstrate the effectiveness of our proposed *** with the baselines,CA-DTS can achieve convergence about 35%faster,and obtain average task delay that is lower by approximately 9.4%,9.8%,and 6.7%,in different scenarios with varying numbers of RSUs,service types,and task arrival rates,respectively.

关键词： edge computing deep reinforcement learning task scheduling vehicular edge computing

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Handling Class Imbalance on Medical Data 2

Hybrid Approach for Handling Class Imbalance on Medical Data

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Sujay, J.K. Surakshith, D.T. Uday, T.Y. Sneha, H.R. Annappa, B. Sushma, V. Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India National Institute of Technology Department of Computer Science and Engineering Karnataka Surathkal India

ISBN: (纸本)9798350373110

Class imbalance in medical X-ray image datasets poses a significant challenge for developing accurate machine-learning models. This paper presents a novel 'Integrated Strategy for Addressing Class Imbalance in Medical Image Datasets' aiming to tackle this issue systematically. The proposed approach combines weighted loss functions and an ensemble model comprising a pre-trained DenseNet architecture and a customized model. The methodology is applied to a representative medical image dataset, demonstrating its effectiveness in mitigating class imbalance issues. The findings reveal notable improvements in model performance, particularly in underrepresented classes. This research advances robust machine learning models in medical image analysis, with potential applications in medical imaging and illness diagnostics. The results underscore the necessity for hybrid approaches and highlight the efficacy of ensemble models and weighted loss in addressing class imbalance in medical imaging datasets. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Towards the Implementation of Traffic Engineering in SDN: A Practical Approach 1

引用

7th International Conference on Inventive Systems and Control, ICISC 2023

作者： Prabu, U. Geetha, V. Department of Computer Science and Engineering Pondicherry Engineering College Puducherry India Department of Information Technology Pondicherry Engineering College Puducherry India

ISBN: (数字)9789819916245

ISBN: (纸本)9789819916238

The advancement of software-defined networks (SDNs) plays a major role in the next generation of networks. It has laid its root in the cloud, data center, and the Internet of things. SDN separates the data and control plane. Through this, it provides greater flexibility, cost-effective configuration, and improved functioning of advanced design of networks. Traffic engineering (TE) is one of the major strengths of software-defined networks. Its main goal is to manage the flows in the network, update topologies, analyze the traffic, and be fault tolerant. Apart from that, it performs load balancing, congestion control, traffic rerouting, and updating policies. This article is intended to provide a detailed description of the types of TE techniques, formulation of TE problems, different ways to implement TE in SDN, and different topologies to be considered for the performance evaluation of the algorithms. The overview of the above-mentioned things might be beneficial for beginners and future researchers to have a clear understanding and go ahead with the implementation of TE in SDN. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-enhanced loT and Wireless Sensor Networks for predictive analysis and maintenance in wind turbine systems

引用

International Journal of Intelligent Networks 2024年第1期5卷 133-144页

作者： Gong, Lei Chen, Yanhui Master Science and Technology of Computer Department PingDingShan Vocational and Technical College Henan Pingdingshan467002 China Master College of Tourism and Planning Pingdingshan University Henan Pingdingshan467002 China

Wind power (WP) represents a Renewable Energy Source (RES) that has noticed substantial development as people continuously search for green energy sources. Utilizing predominantly Predictive Maintenance (PM) of Wind Turbines (WT), this research analyzes the potential benefits that could be generated by Wind Energy (WE) through the use of the Internet of Things (IoT) and Wireless Sensor Networks (WSN). This research recommends an Internet of Things-WSN model for PM comprised of three distinct phases: the primary phase is the collection of data via sensors, the second phase is the transmission of that data through a connection to the Internet, and the final phase is the implementation of data analytics on that data in the context of cloud computing. For PM analytics, this work introduces a Predictive Maintenance Convolutional Long Short-Term Memory (PM-C-LSTM) model that combines the spatial pattern recognition capabilities of a Convolutional Neural Network with the sequential data prowess of LSTM networks. The PM-C-LSTM model combines CNN for recognizing spatial patterns and LSTM networks for analyzing sequential data in a way that doesn't affect the accuracy of WT-PM. A Failure Sample Generator model is also fused into the study to measure soft failure and hard failure factors and improve the predictive accuracy of the Machine Learning (ML) model. Data became available over 16 months while the model was applied to a Wind Farm (WF) positioned on the Qinghai-Tibet Plateau. It has been demonstrated that the PM-C-LSTM model possesses enhanced PM capabilities by comparing its efficiency to other standard models using a selection of performance metrics. The result of the test indicates that there is a probability that the hybrid IoT and ML will improve PM methods in WT, which will subsequently help improve the effectiveness and sustainability of WE generation. © 2024 The Authors

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Intelligent Irrigation Management: An IoT-Driven Approach with Real-Time Data Integration

Intelligent Irrigation Management: An IoT-Driven Approach wi...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Kanaga Priya, P. Prasanna Blessy, M. Suguna, R.K. Narmada, C. Devi, G. Ramesh Kalyan, G. KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India RVS Technical Campus Department of Computer Science and Engineering Coimbatore India SNS College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350319200

In the ever-evolving landscape of agriculture, the need for precision and efficiency has never been more critical. This paper introduces a cutting-edge irrigation management system that leverages the power of the Internet of Things (IoT) and real-time data integration. Instead of traditional irrigation methods, this system adapts irrigation practices dynamically based on soil moisture and plant growth stages. Through a seamless synergy of wireless IoT sensors and web applications, this solution provides farmers with a robust platform to remotely monitor and control irrigation processes. Soil moisture data is collected and analyzed in real-time, ensuring that water is delivered precisely when and where it's needed. Beyond soil data, this system integrates external sources of information, including real-time weather data encompassing rainfall probability, temperature, and wind speed. This data fusion empowers farmers to make informed decisions and fine-tune their irrigation strategies from anywhere, at any time. The project's scalability is a hallmark, capable of serving the needs of small-scale farms as well as extensive agricultural operations, and adaptable to a wide variety of crops. By embracing technology, this IoT-driven irrigation management system represents a significant stride towards sustainable and efficient agriculture, promising not only resource conservation but also increased crop health and resilience. © 2023 IEEE.

关键词： IoT Irrigation Precision Agriculture Real-Time Data Integration Soil Moisture Monitoring Sustainable Farming Wireless Sensors

来源：评论

学校读者我要写书评

暂无评论

Decision-based framework to facilitate EDGE computing in smart health care

引用

Multimedia Tools and Applications 2024年第38期83卷 85849-85869页

作者： Singh, Simranjit Sajwan, Mohit Kukreja, Sonal Department of Information Technology Dr B R Ambedkar National Institute of Technology Jalandhar Punjab India Department of Information Technology Netaji Subhas University of Technology New Delhi India School of Computer Science Engineering and Technology Bennett University U.P. Greater Noida India

In the past few years, with the increase in population and health concerns, there has been a need for efficient health monitoring solutions that can help patients monitor their health consistently to be aware of any health risks at the initial stage. The advancement in sensing and smart technologies helps monitor human behaviors to predict health risks. In this work, a dynamic decision-based activity prediction system is proposed using Random Forest, SVM, Decision Trees, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) on an edge device. We train the models using features from the MHealth dataset, such as acceleration, rate of turn, and magnetic field, to predict activities such as standing, climbing, running, and jogging, collected from various sensors. Our framework dynamically selects between machine learning (ML) and deep learning (DL) algorithms based on real-time data size and edge device capabilities, ensuring optimal performance and resource utilization. The results for the proposed models are compared and analyzed. The experimental results indicate that among all machine learning methods, Random Forest achieves the highest overall accuracy at 98%, while in deep learning algorithms, both LSTM and GRU reach a maximum accuracy of 98%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Disease Diagnosis for Secure Internet of Medical Things

引用

computers, Materials & Continua 2022年第10期73卷 965-979页

作者： Sultan Ahmad Shakir Khan Mohamed Fahad Al.Ajmi Ashit Kumar Dutta L.Minh Dang Gyanendra Prasad Joshi Hyeonjoon Moon Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharj11942Saudi Arabia College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia College of Pharmacy King Saud UniversityRiyadh11451Saudi Arabia Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Saudi Arabia Department of Information Technology FPT UniversityHo Chi Minh CityVietnam Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea

In recent times,Internet of Medical Things(IoMT)gained much attention in medical services and healthcare management *** healthcare sector generates massive volumes of data like personal details,historical medical data,hospitalization records,and discharging records,IoMT devices too evolved with potentials to handle such high quantities of *** and security of the data,gathered by IoMT gadgets,are major issues while transmitting or saving it in *** advancements made in Artificial Intelligence(AI)and encryption techniques find a way to handle massive quantities of medical data and achieve *** this view,the current study presents a new Optimal Privacy Preserving and Deep Learning(DL)-based Disease Diagnosis(OPPDL-DD)in IoMT ***,the proposed model enables IoMT devices to collect patient data which is then preprocessed to optimize *** order to decrease the computational difficulty during diagnosis,Radix Tree structure is *** addition,ElGamal public key cryptosystem with Rat Swarm Optimizer(EIG-RSO)is applied to encrypt the *** the transmission of encrypted data to cloud,respective decryption process occurs and the actual data gets ***,a hybridized methodology combining Gated Recurrent Unit(GRU)with Convolution Neural Network(CNN)is exploited as a classification model to diagnose the *** sets of simulations were conducted to highlight the performance of the proposed model on benchmark *** experimental outcomes ensure that the proposed model is superior to existing methods under different measures.

关键词： Internet of medical things privacy security encryption radix tree deep learning

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：