检索结果-内蒙古大学图书馆

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Chairat, Sawrawit Sae-Ang, Apichat Suvirat, Kerdkiat Ingviya, Thammasin Chaichulee, Sitthichok Prince of Songkla University Faculty of Medicine Department of Biomedical Sciences and Biomedical Engineering Songkhla Thailand Prince of Songkla University Division of Information Technology Faculty of Medicine Songkhla Thailand Prince of Songkla University Division of Digital Innovation and Data Analytics Faculty of Medicine Songkhla Thailand Prince of Songkla University Faculty of Medicine Department of Family Medicine and Preventive Medicine Songkhla Thailand

ISBN: (纸本)9798350371499

Prescribing medications is an essential part of patient care and requires precision and personalization in selection. Our study introduces a hierarchical medication recommendation system that aims to improve the prescribing process. We use FastText to embed medical contexts and employ a hierarchical attention-based model to manage the hierarchical structure of medication codes. The system takes input data from the current visit and the three previous visits to make recommendations. We trained and evaluated our model on 99,417 anonymized primary care outpatient visits. Our model achieved a mean average precision (mean AP) of 0.8724, 0.7419, 0.6805, and 0.6184 at the first, second, third, and fourth levels of the ATC system, respectively. We demonstrate that incorporating patient visit histories can improve predictions. Our results provide a solution to improve medication prescribing and suggest possible extensions for more comprehensive recommendations. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A DSSAT Model Approach for Yield Optimization: A Case Study of Mae Na Rua, Phayao, Thailand

A DSSAT Model Approach for Yield Optimization: A Case Study ...

引用

Geoinformatics for Spatial-Infrastructure Development in Earth and Allied Sciences (GIS-IDEAS)

作者： Pongsak Jindasee Sawarin Lerk-U-Suke Jirabhorn Chaiwongsai Krittika Kantawong Napa Rachata Prattana Deeprasertkul Geospatial Data Science School Of Information And Communication Technology University of Phayao Phayao Thailand School Of Information And Communication Technology University of Phayao Phayao Thailand Researcher in Technology and Information Research Section Digital and Technology Development Division Hydro-Informatics Institute (Public Organization) Bangkok Thailand

ISBN: (数字)9798331504243

ISBN: (纸本)9798331504250

Rice production in northern Thailand, particularly in the Mae Na Ruea Sub-district, has been significantly affected by climate change, with increasing temperatures and decreasing water availability leading to reduced yields. This study aims to determine the optimal rice planting periods to maximize yields under changing climatic conditions by using the Decision Support System for Agrotechnology Transfer (DSSAT) model. The research utilizes the CERES-Rice module within DSSAT to simulate rice growth and yields across 15 planting periods from mid-April to late July 2023. Weather, soil, and crop management data were input into the model to predict yields under various environmental conditions. The results indicate that mid-May (W5) is the optimal planting time, with a predicted yield of 4294 kg/ha, 41.95% higher than the average. In contrast, early May (W3) showed the lowest yield at 1889 kg/ha. The simulated yield for weeks (W9) and (W10) were 3,018 kg/ha and 2,987 kg/ha, respectively, which were only 0.23% and 1.26% lower than the average. This demonstrates the model's a high degree of precision. The study highlights the significant impact of planting time on yield outcomes, emphasizing the need for adaptive strategies to cope with climate variability. However, the model's limitations, including underestimation of early-season drought stress and lack of consideration for factors such as irrigation and pest pressures, suggest the need for further research to enhance prediction accuracy and address long-term environmental variability.

关键词： Decision support systems Adaptation models Irrigation Climate variability Predictive models Soil data models Reliability Stress Meteorology

来源：评论

学校读者我要写书评

暂无评论

Incentive Mechanism Design for Federated Learning With Dynamic Network Pricing

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ding, Ningning Gao, Lin Huang, Jianwei Data Science and Analytics Thrust Internet of Things Thrust Information Hub Guangzhou China Harbin Institute of Technology School of Electronics and Information Engineering Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Shenzhen China The Chinese University of Hong Kong School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen Shenzhen518172 China

Federated learning protects users' data privacy by sharing users' local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users' contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users' private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under three interaction structures of the participants. We show that the coordinated structure is better than the two uncoordinated structures, as it avoids the selfish behaviors of the network operator and the server;the vertically uncoordinated structure is better than the horizontally uncoordinated structure, as it avoids the interests misalignment between the server and the network operator. We also propose multi-period network pricing to reduce the implementation complexity of dynamic pricing. Numerical results based on real-world datasets show that our proposed mechanisms decrease the server's cost by up to 24.87% and increase the network operator's profit by up to 1245.25%, compared with the state-of-the-art benchmarks. © 2025 IEEE. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Performance of Machine Learning Models Using Satellite dataset for Classification of Various Crop Types

Assessing the Performance of Machine Learning Models Using S...

引用

Geoinformatics for Spatial-Infrastructure Development in Earth and Allied Sciences (GIS-IDEAS)

作者： Montree Pinkaeo Phaisarn Jeefoo Jirabhorn Chaiwongsai Surachai Chantee Pornthep Rojanavasu Prattana Deeprasertkul Geospatial Data Science School Of Information And Communication Technology University of Phayao Phayao Thailand Geographic Information Science School of Information and Communication Technology University of Phayao Phayao Thailand School of Information and Communication Technology University of Phayao Phayao Thailand Technology and Digital Division Hydro-Informatics Institute (Public Organization) Bangkok Thailand Researcher in Technology and Information Research Section Digital and Technology Development Division Hydro-Informatics Institute (Public Organization) Bangkok Thailand

ISBN: (数字)9798331504243

ISBN: (纸本)9798331504250

This paper aims to evaluate machine learning (ML) models' performance, named Random Forest (RF), Gradient Boosting (GB), Artificial Neural Network (ANN), and Support Vector Machine (SVM) for classifying different crop types using images from the Sentinel 2 satellite. The result shows that RF demonstrated the highest values across all criteria, outperforming the other models with an overall accuracy of 0.7365 (+ 0.010). With an accuracy of 0.7183 (+0.016) overall, GB trailed closely behind. The two models demonstrated robust performance, as evidenced by their respective F1-scores of 0.7344 and 0.7161, which suggest a well-balanced compromise between recall and precision. With total accuracies of 0.5429 (+ 0.0024) and 0.5169 (+ 0.017), respectively, the ANN and SVM algorithms performed comparably worse. In comparison to ensemble techniques like RF and GB, this shows that these models might not be as effective for this specific classification problem. The findings of this study can inform decision-making in the selection of ML algorithms for various applications, such as spatial water management, specifically in agriculture and irrigation, agricultural land management, and planning to mitigate the impact of natural disasters in the agricultural sector.

关键词： Support vector machines Radio frequency Accuracy Satellites Image resolution Crops Artificial neural networks Satellite images Classification algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Question Answering Systems: Complexity of judging a natural language

arXiv

引用

arXiv 2022年

作者： Farea, Amer Yang, Zhen Duong, Kien Perera, Nadeesha Emmert-Streib, Frank Predictive Society and Data Analytics Lab Faculty of Information Technology and Communication Sciences Tampere University Finland

Question answering (QA) systems are among the most important and rapidly developing research topics in natural language processing (NLP). A reason, therefore, is that a QA system allows humans to interact more naturally with a machine, e.g., via a virtual assistant or search engine. In the last decades, many QA systems have been proposed to address the requirements of different question-answering tasks. Furthermore, many error scores have been introduced, e.g., based on n-gram matching, word embeddings, or contextual embeddings to measure the performance of a QA system. This survey attempts to provide a systematic overview of the general framework of QA, QA paradigms, benchmark datasets, and assessment techniques for a quantitative evaluation of QA systems. The latter is particularly important because not only is the construction of a QA system complex but also its evaluation. We hypothesize that a reason, therefore, is that the quantitative formalization of human judgment is an open problem. © 2022, CC BY.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Research on Photovoltaic Power Prediction Method for Power Grid Safety 5

Research on Photovoltaic Power Prediction Method for Power G...

引用

5th International Conference on communications, information System and Computer Engineering, CISCE 2023

作者： Guo, Mingkang Ji, Wenxuan Gu, Bingling Li, Peiyuan Tian, Lin Information & Communication Company of State Grid Gansu Electric Power Company Dept. Digital Business Division Lanzhou China Lanzhou University of Technology Dept. School of Computer & Communication Lanzhou China SGTI-UNI Cloud Data Technology Co. Ltd. Dept. Engineering O&M Department Lanzhou China

ISBN: (纸本)9798350326796

When integrating large-scale photovoltaic systems with the power grid, variability and intermittency of photovoltaic power may potentially endanger the secure and stable operation of the power system as well as its scheduling management. So a new photovoltaic power prediction method using logistic chaotic mapping (LCM) improving atomic search optimization algorithm (ASO) to optimize back propagation neural network (LCM-ASO-BPNN) is proposed to solve this problem. The ASO algorithm is used to solve the defect that BPNN is likely to be trapped in a local optimum, and the initial population of the ASO algorithm is optimized by introducing logistic chaotic mapping, subsequently, the model's predictive accuracy is greatly enhanced. The experimental results demonstrate a significant improvement in the prediction accuracy of the proposed model when compared with the traditional prediction model. © 2023 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

An Optimization Algorithm of Charging Station Siting to Balance Pressure & Safety of Power Grid 5

An Optimization Algorithm of Charging Station Siting to Bala...

引用

5th International Conference on communications, information System and Computer Engineering, CISCE 2023

作者： Li, Bokai Quan, Wei Ma, Dongdong Xin, Junwei Ning, Jing Information & Communication Company of State Grid Gansu Electric Power Company Dept. Digital Business Division Lanzhou China Lanzhou University of Technology Dept. School of Computer & Communication Lanzhou China SGTI-UNI Cloud Data Technology Co. Ltd. Dept. Engineering O&M Department Lanzhou China

ISBN: (纸本)9798350326796

A reasonable charging station layout can not only alleviate the difficult problem of electric vehicle (EV) charging, but also balance the grid pressure and ensure the safety of electricity consumption. In this paper, the sparrow search algorithm (SSA) is used to optimize the charging station siting process and obtain suitable charging station siting results. This can meet the needs of customers, lower the cost of building charging stations, and have the least negative effects on the electrical system. The experiment results show the SSA has the best capacity to search globally and the fastest convergence speed compared with the genetic algorithm (GA) and moth-flame optimization algorithm (MFO). © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

AUTODEEPSLICE: A data Driven Network Slicing Technique of 5G network using Automatic Deep Learning

AUTODEEPSLICE: A Data Driven Network Slicing Technique of 5G...

引用

2022 IEEE GLOBECOM Workshops, GC Wkshps 2022

作者： Chowdhury, Deepraj Das, Rupanjan Rana, Risav Dwivedi, Ashutosh Dhar Chatterjee, Pushpita Mukkamala, Raghava Rao International Institute of Information Technology Department of Electronics and Communication Naya Raipur India Copenhagen Business School Centre for Business Data Analytics Department of Digitization Frederiksberg Denmark Tennessee State University Department of Computer Science Nashville United States

ISBN: (纸本)9781665459754

With the advancement of mobile networks, and the revolution of mobile communication from 1G to 5G, human dependency has increased, so it has become the most priority to provide an efficient and highly reliable network. The 5G networks need high capacity and high-speed data transfer, with the least latency and increased security. 5G service providers are trying to find a programmable solution that can handle a huge number of independent service users on the same physical infrastructure. Network slicing is used to provide end-to-end network resource allocation. To accelerate the 5G network performance, Artificial Intelligence (AI) powered data-driven based decisions will be used for future communication. In this proposed work, Automatic deep learning has been implemented, where the hyperparameter will automatically select the algorithm and tune the hyperparameter. The proposed model AUTODEEPSLICE efficiently makes intelligent decisions and will choose the best network slice at the time of network breakdown. © 2022 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Security Algorithm Using Machine Learning 10

Enhancing Network Security Algorithm Using Machine Learning

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering, UPCON 2023

作者： Satav, Sandip D Patel, Hiteshkumar Gunvantbhai Walke, Suchita Megala, R. Patel, Charushila Axay Pavithra, G. Information Technology JSPM's Jayawantrao Sawant Coe Pune411028 India Quality Engineering - Data Tiger Analytics Tamil Nadu Chennai India Mumbai University Pillaicollege of Engineering and Technology Department of Computer Engineering India Sri Eshwar College of Engineering Department of Computer and Communication Engineering Tamilnadu Coimbatore641202 India Department of Electrical Engineering Gujarat Surat India Dayananda Sagar College of Engineering Electronics & Communication Engineering Karnataka Bangalore560111 India

ISBN: (纸本)9798350382471

In light of the increasing sophistication of cyber threats in today's linked world, network security is of paramount importance. Monitoring network traffic and detecting suspicious activity is where intrusion detection systems (IDS) shine, playing a crucial role in identifying and managing these threats. There has been a rise in the use of machine learning methods to improve IDS performance. In order to improve network safety, a new hybrid method is proposed in this study, which combines Random Forest (RF) with Support Vector Machine (SVM) to perform intrusion detection. The proposed hybrid RF and SVM approach draws on the best features of both models to enhance intrusion detection precision and reliability. As an ensemble learning technique, Random Forest excels at both feature selection and handling big datasets. Conversely, Support Vector Machine has earned acclaim for its prowess in binary classification problems and its ability to locate complicated decision boundaries. We want to improve upon intrusion detection by integrating these two techniques, which have complimentary characteristics. The first step in this study is to compile a large dataset of legitimate and malicious network traffic. A preprocessing pipeline is built up to guarantee the quality of the data, and feature engineering techniques are used to extract useful information from the dataset. This preprocessed dataset is then used to train a hybrid RF and SVM algorithm using labelled data containing known intrusion cases. Extensive tests and comparisons to other intrusion detection methods are used to assess the performance of the proposed algorithm. The efficiency of the hybrid RF and SVM algorithm in identifying network intrusions is evaluated using performance measures like as accuracy, precision, recall, F1-score, and area under the Receiver Operating Characteristic (ROC-AUC) curve. This research shows that a system that combines RF and SVM for intrusion detection may beat both conventional me

关键词： etc Hybrid Algorithm i Intrusion Detection System (IDS) Machine Learning Network Security Random Forest (RF) Support Vector Machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments

Continual Learning for Adaptable Car-Following in Dynamic Tr...

引用

International Conference on Intelligent Transportation

作者： Xianda Chen PakHin Tiu Xu Han Junjie Chen Yuanfei Wu Xinhu Zheng Meixin Zhu Intelligent Transportation Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Data Science and Analytics Thrust Information Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Guangdong Provincial Key Lab of Integrated Communication Sensing and Computation for Ubiquitous Internet of Things

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments. Traditional learning-based models often suffer from performance degradation when encountering unseen traffic patterns due to a lack of continual learning capabilities. This paper proposes a novel car-following model based on continual learning that addresses this limitation. Our framework incorporates Elastic Weight Consolidation (EWC) and Memory Aware Synapses (MAS) techniques to mitigate catastrophic forgetting and enable the model to learn incrementally from new traffic data streams. We evaluate the performance of the proposed model on the Waymo and Lyft datasets which encompass various traffic scenarios. The results demonstrate that the continual learning techniques significantly outperform the baseline model, achieving 0 % collision rates across all traffic conditions. This research contributes to the advancement of autonomous driving technology by fostering the development of more robust and adaptable car-following models.

关键词： Continuing education Training Adaptation models Traffic control Trajectory Safety Autonomous vehicles Synapses Streams Intelligent transportation systems

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：