检索结果-内蒙古大学图书馆

9th International Workshop on Advanced Analytics and Learning on Temporal data, AALTD 2024

作者： O’Connor, Ciaran Prestwich, Steven Visentin, Andrea SFI CRT in Artificial Intelligence School of Computer Science & IT University College Cork Cork Ireland Insight Centre for Data Analytics School of Computer Science & IT University College Cork Cork Ireland

ISBN: (纸本)9783031770654

Integrating the erratic production of renewable energy into the electricity grid poses numerous challenges. One approach to stabilising market prices and reducing energy losses due to curtailments is the deployment of batteries. Efficient electricity arbitrage is crucial to make investments in storage systems financially viable;trading solutions to achieve this rely on price forecasting techniques. This study delves into the application of Conformal Prediction (CP) techniques, including Ensemble Batch Prediction Intervals (EnbPI) and Sequential Predictive Conformal Inference for Time Series (SPCI), for generating probabilistic forecasts in the Irish electricity market. Recent advancements in CP have addressed temporal considerations inherent in time series forecasting, eliminating the need for exchangeability assumptions. Our study demonstrates that despite potential efficiency trade-offs, CP methods consistently yield precise and reliable prediction intervals, ensuring comprehensive coverage. We assess the impact of CP on the financial results of a simulated trading algorithm. Monetary outcomes achieved with EnbPI and SPCI outperform those of both split CP and traditional quantile regression models, highlighting the practical superiority of CP in electricity price forecasting. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MedFILIP: Medical Fine-grained Language-Image Pre-training

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3587-3597页

作者： Liang, Xinjie Li, Xiangyu Li, Fanding Jiang, Jie Dong, Qing Wang, Wei Wang, Kuanquan Dong, Suyu Luo, Gongning Li, Shuo The School of Computer Science and Technology Harbin Institute of Technology Harbin China The Department of Thoracic Surgery at No. 4 Affiliated Hospital Harbin Medical University Harbin China The School of Computer Science and Technology Harbin Institute of Technology Shenzhen China The College of computer and control engineering Northeast Forestry University Harbin China The Computer Electrical and Mathematical Sciences & Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia The Department of Biomedical Engineering Department of Computer Data Science Case Western Reserve University ClevelandOH United States

Medical vision-language pretraining (VLP) that leverages naturally-paired medical image-report data is crucial for medical image analysis. However, existing methods struggle to accurately characterize associations between images and diseases, leading to inaccurate or incomplete diagnostic results. In this work, we propose MedFILIP, a fine-grained VLP model, introduces medical image-specific knowledge through contrastive learning, specifically: 1) An information extractor based on a large language model is proposed to decouple comprehensive disease details from reports, which excels in extracting disease deals through flexible prompt engineering, thereby effectively reducing text complexity while retaining rich information at a tiny cost. 2) A knowledge injector is proposed to construct relationships between categories and visual attributes, which help the model to make judgments based on image features, and fosters knowledge extrapolation to unfamiliar disease categories. 3) A semantic similarity matrix based on fine-grained annotations is proposed, providing smoother, information-richer labels, thus allowing fine-grained image-text alignment. 4) We validate MedFILIP on numerous datasets, e.g., RSNA-Pneumonia, NIH ChestXray14, VinBigdata, and COVID-19. For single-label, multi-label, and fine-grained classification, our model achieves state-of-the-art performance, the classification accuracy has increased by a maximum of 6.69%. © 2013 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An electron-transfer-tuning strategy at the graphene/metal interface for improving acidic water electrolysis in proton exchange membrane electrolyzers

引用

Journal of Energy Chemistry 2025年第4期103卷 344-352页

作者： Yue Xu Shuaidong Li Yingjian He Fumiya Shiokawa Samuel Jeong Aimi Asilah Haji Tajuddin Zeyu Xi Yoshikazu Ito Jingzi Zhang Zeyun Cai Xi Lin Kailong Hu School of Materials Science and Engineering and Institute of Materials Genome & Big Data Harbin Institute of Technology Institute of Applied Physics Graduate School of Pure and Applied Sciences University of Tsukuba Institute of Special Environments Physical Sciences Harbin Institute of Technology School of Computer Science and Technology Harbin Institute of Technology

Graphene encapsulation has been shown to be an effective technique for improving the corrosion resistance of non-noble metal catalysts for the acidic water *** key challenge lies in enhancing the electrocatalytic activity of graphene-encapsulated metals while maintaining their durability in acidic ***,an electron-transfer-tuning strategy is investigated at the graphene/NiMo interface,aiming to improve the hydrogen evolution reaction（HER） performance of graphene-encapsulated NiMo *** doping of Ti,a low electronegativity element,into NiMo substrate was confirmed to increase electron transfer from the metal core toward the *** electron-rich state on graphene facilitates the adsorption of positively charged protons on graphene,thereby enabling a Pt/C-comparable performance in 0.5 M H2SO4,with only a 3.8% degradation in performance over a 120-h continuous *** proton exchange membrane（PEM） water electrolyzer assembled by the N-doped grapheneencapsulated Ti-doped NiMo exhibits a smaller cell voltage to achieve a current density of 2.0 A cm-2,in comparison to the Pt/C based *** study proposes a novel electron-transfer-tuning strategy to improve the HER activity of graphene-encapsulated non-noble metal catalysts without sacrificing durability in acidic electrolytes.

关键词： Acidic media Graphene encapsulation Hydrogen evolution Interface Proton exchange membrane

来源：评论

学校读者我要写书评

暂无评论

data Analysis with Model Explainability for Air Quality and Pollution Prediction of Urban Areas in Edge Networks 12th

Data Analysis with Model Explainability for Air Quality an...

引用

12th International Conference on Big data and Artificial Intelligence, BDA 2024

作者： Singh, Akansha Chakraborty, Soumendu Adhikari, Mainak Department of Computer Science Indian Institute of Information Technology Lucknow Lucknow India School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram Thiruvananthapuram India

ISBN: (纸本)9783031818202

Air quality significantly impacts human health and economic conditions, making precise and timely assessment crucial in urban areas. Existing studies often fail to predict pollution accurately in smaller areas due to varying meteorological conditions. Most existing prototypes rely on standard ML models, trained with generic, publicly available datasets, which often lack local dynamics, adaptability, and synchronization. To address these challenges, in this paper, we propose a new Hybrid Edge-Cloud Air Quality Monitoring System. For initial model training a robust testbed is created by data Fusion of air quality data from diverse sources like Application Programming Interfaces and public datasets. The system trains and refines ML models in the cloud, identifies key features to reduce feature dimensions, and leverages local decision-making using site-specific data collected by sensors on edge devices. Sensors monitor local environmental parameters for real-time analysis and decision-making, ensuring accurate predictions for specific urban locations while optimizing performance and minimizing resource usage on edge devices. Explainable AI techniques improve transparency and confidence in decisions. The model is validated by simulating various ML models on the testbed, with and without feature extraction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Particle Swarm Optimization of U-net Parameters for Marine Aquaculture Image Segmentation 13

Adaptive Particle Swarm Optimization of U-net Parameters for...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Zhao, Jin Wang, Jun Han, Min Fan, Jianchao School of Computer Science and Engineering Chongqing Three Gorges University Chongqing China Department of Computer Science Department of Data Science City University of HongKong Hong Kong School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798331516147

Marine aquaculture image segmentation plays a crucial role in managing aquatic resources and environmental protection. Traditional deep learning models rely on manual parameter tuning for image segmentation, which limits their efficiency and accuracy. This paper proposes an adaptive Particle Swarm Optimization (PSO) algorithm to optimize the parameters of the U-net model automatically. The algorithm dynamically adjusts the PSO parameters based on the population’s entropy and clustering metrics and employs a hill-climbing algorithm to address the issue of the PSO easily falling into local optima, enhancing the algorithm’s adaptability. The proposed algorithm updates and iterates particles to automatically find suitable model parameters. The remote sensing data used in this experiment were from the Yellow Sea aquaculture area near Dalian, China, with a segmentation accuracy of 91.8%. This method improves segmentation accuracy, reduces the burden of manual parameter tuning, and provides an effective solution for optimizing deep learning models. © 2025 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Advancing Sentiment Analysis for Low-Resource Languages Using Fine-Tuned LLMs: A Case Study of Customer Reviews in Turkish Language

引用

IEEE Access 2025年 13卷 77382-77394页

作者： Kiziltepe, Rukiye Savran Ezin, Ercan Yentur, Omer Basbrain, Arwa Karakus, Murat Ankara University Department of Software Engineering Ankara Turkey Harran University Department of Computer Engineering Şanliurfa Turkey Kron Technology Software Solutions-Data Security & Data Management İstanbul Turkey Department of Computer Science King Abdulaziz University Jeddah Saudi Arabia

This study investigates the application of advanced fine-tuned Large Language Models (LLMs) for Turkish Sentiment Analysis (SA), focusing on e-commerce product reviews. Our research utilizes four open-source Turkish SA datasets: Turkish Sentiment Analysis version 1 (TRSAv1), Vitamins and Supplements Customer Review (VSCR), Turkish Sentiment Analysis dataset (TSAD), and TR Customer Review (TRCR). While these datasets were initially labeled based on star ratings, we implemented a comprehensive relabeling process using state-of-the-art LLMs to enhance data quality. To ensure reliable annotations, we first conducted a comparative analysis of different LLMs using the Cohen's Kappa agreement metric, which led to the selection of ChatGPT-4o-mini as the best-performing model for dataset annotation. Our methodology then focuses on evaluating the SA capabilities of leading instruction-tuned LLMs through a comparative analysis of zero-shot models and Low-Rank Adaptation (LoRA) fine-tuned LlaMA-3.2-1B-IT and Gemma- 2-2B-IT models. Evaluations were conducted on both in-domain and out-domain test sets derived from the original star-ratings-based labels and the newly generated GPT labels. The results demonstrate that our finetuned models outperformed leading commercial LLMs by 6% in both in-domain and out-domain evaluations. Notably, models fine-tuned on GPT-generated labels achieved superior performance, with in-domain and outdomain F1-scores reaching 0.912 and 0.9184, respectively. These findings underscore the transformative potential of combining LLM relabeling with LoRA fine-tuning for optimizing SA, demonstrating robust performance across diverse datasets and domains. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A study on Electronic Health Records (EHR) in India: Security challenges, initiatives and blockchain integration 4th

A study on Electronic Health Records (EHR) in India: Securit...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Bhargava, Misha Mahi, Samarjit Rao, Vidya Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India

ISBN: (纸本)9781032911571

With its vast population and extensive healthcare requirements, India is moving toward digitalizing its health records. Safeguarding Electronic Health Records (EHRs) is crucial given the increase in security breaches and attacks, with India’s healthcare sector at the forefront. This study provides an overview of EHR security in India by exploring the EHR adoption rate in India and the barriers to its use. It focuses on the significant security challenges they bring, and the initiatives currently being implemented in India, such as the Ayushman Bharat Digital Mission (ABDM) and the recently released National Accreditation Board for Hospitals (NABH) Digital Health Standards. Integrating Blockchain in current EHR systems to resolve the observed challenges is then explored. The findings of this study show the urgency of integrating emerging technologies such as blockchain which have the potential for patient-controlled data sharing and data immutability possibly within the framework of the ABDM. This study aims to serve as a valuable resource for healthcare professionals, researchers and other regions seeking to understand and improve EHR security. © 2025 the Author(s).

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

SARA: A Sparsity-Aware Efficient Oblivious Aggregation Service for Federated Matrix Factorization 25th

SARA: A Sparsity-Aware Efficient Oblivious Aggregation Servi...

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Zheng, Yifeng Xiong, Tianchen Ouyang, Huajie Wang, Songlei Hua, Zhongyun Gao, Yansong School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Data61 CSIRO Sydney Australia

ISBN: (纸本)9789819605668

Federated matrix factorization (FedMF) has recently emerged as a privacy-friendly paradigm which runs matrix factorization (MF) in a federated learning (FL) setting and enables users to keep their individual rating data local in the training process. In FedMF, users only need to share out item gradients for aggregation. However, prior work has shown that the item gradients, if directly exposed, can still leak users’ rating data. Meanwhile, the rating data are typically sparse and simply uploading the gradients of rated items will leak which and how many items a user rates. In light of the above, in this paper, we present SARA, a new sparsity-aware efficient oblivious aggregation service for FedMF. SARA protects the confidentiality of item gradients as well as hides which and how many items a user rates, through a custom sparsity-aware design that delicately builds on differential privacy and lightweight cryptography. Extensive experiments over real-world datasets demonstrate that SARA is utility-preserving and can bring the users significant savings (up to 98.28%) in the number of transmitted item gradients, compared to the baseline of fully transmitting gradients for all possible items. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Targeted Universal Adversarial Attack Based on Fourier Transform 2nd

Targeted Universal Adversarial Attack Based on Fourier Tran...

引用

2nd International Conference on data Security and Privacy Protection, DSPP 2024

作者： Sun, Yancheng Chen, Yuling Liu, Ziyang Dou, Hui Tan, Chaoyue The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9789819785391

The existence of adversarial example reveals the fragility in neural networks, and the exploration of their theoretical origins increases the interpretability of deep learning, enhances researchers’ understanding of neural networks, and contributes to the development of next-generation artificial intelligence, which has attracted widespread research in various fields. The targeted adversarial attack problem based on sample features faces two problems: on the one hand, the difference in the model’s attention to different features in the example;On the other hand, the bias that occurs in adversarial attacks can have an impact on targeted attacks. The mechanism of the human eye relies more on the shape information of the image. However, in the past, artificial intelligence models based on convolutional neural networks often relied on the texture features of image examples to make decisions. At present, general optimize adversarial attack algorithms do not distinguish different types of features based on different parts of the image, but only process the entire example in a general manner, making it difficult to effectively utilize the effective features in the example, resulting in poor algorithm performance and interpretability. This article optimizes the adversarial attack algorithm based on optimization iteration, as follows: Firstly, different types of information in adversarial examples are studied, and fourier transform technology is used to process the attacked original image and obtain its low-frequency information. The obtained low-frequency examples are randomly cropped to obtain some feature examples. Then, the clustering effect was studied when the examples were attacked without targets, and an inter-class smoothing loss was designed to improve the success rate of target attacks. This Rebalance Universal Feature Method (RFM) is based on fourier low pass filtering and inter-class smoothing, which effectively improves the ability of optimization iteration bas

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SAMFNet: Scene-aware sampling and multi-stage fusion for multimodal 3D object detection

引用

Alexandria Engineering Journal 2025年 126卷 90-104页

作者： Wang, Baotong Xia, Chenxing Gao, Xiuju Ge, Bin Li, Kuan-Ching Fang, Xianjin Zhang, Yan Yang, Yuan College of Computer Science and Engineering Anhui University of Science and Technology Huainan232001 China College of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China Department of Computer Science and Information Engineering Providence University Taichung43301 China The School of Electronics and Information Engineering Anhui University Hefei230039 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

Recently, multimodal 3D object detection (M3OD) that fuses the complementary information from LiDAR data and RGB images has gained significant attention. However, the inherent structural differences between point clouds and images pose fusion challenges, significantly hindering the exploration of correlations within multimodal data. To address this issue, this paper introduces an enhanced multimodal 3D object detection framework (SAMFNet), which leverages virtual point clouds generated from depth completion. Specifically, we design a scene-aware sampling module (SASM) that employs tailored sampling strategies for different bins based on the density distribution of point clouds. This effectively alleviates the detection bias problem while ensuring the key information of virtual points, significantly reducing the computational cost. In addition, we introduce a multi-stage feature fusion module (MSFFM) that embeds point-level and regional-adaptive feature fusion strategies to generate more informative multimodal features by fusing features with different granularities. To further improve the accuracy of model detection, we also introduce a confidence prediction branch unit (CPBU), which improves the detection accuracy by predicting the confidence of feature classification in the intermediate stage. Extensive experiments on the challenging KITTI dataset demonstrate the validity of our model. © 2025 The Authors

关键词： Image fusion

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：