检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Stephanie Eckman Barbara Plank Frauke Kreuter Social Data Science Center University of Maryland College Park MD Center for Information and Language Processing (CIS) LMU Munich Germany and Computer Science Department IT University of Copenhagen Denmark and Munich Center for Machine Learning (MCML) LMU Munich Germany Institute for Statistics and Munich Center for Machine Learning (MCML) LMU Munich Germany and Social Data Science Center and Joint Program in Survey Methodology University of Maryland College Park MD

Whether future AI models are fair, trustworthy, and aligned with the public's interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few AI/ML researchers are trained in data collection methods. Recent research in data-centric AI has show that higher quality training data leads to better performing models, making this the right moment to introduce AI/ML researchers to the field of survey methodology, the science of data collection. We summarize insights from the survey methodology literature and discuss how they can improve the quality of training and feedback data. We also suggest collaborative research ideas into how biases in data collection can be mitigated, making models more accurate and human-centric.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting Patch Correctness Checking via Combining Code-Edit Embeddings as Additional What-to-Change Information

Boosting Patch Correctness Checking via Combining Code-Edit ...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Chontipan Plengvittaya Zee Hen Tang Mi-Yen Yeh Chih-Ya Shen Social Networks and Human Centered Computing Taiwan International Graduate Program Taiwan Institute of Information Science Academia Sinica Taiwan Institute of Information Systems and Applications National Tsing Hua University Taiwan Data Science Degree Program National Taiwan University and Academia Sinica Taiwan

Patch Correctness Checking is the task of detecting automated-program-repair-generated patches that can pass the test suite but are still buggy. In this study, we investigated a new feature to improve the classification performance for automated patch correctness checking. Our approach involved leveraging code-change information at a finer granular level by embedding the code edits and combining them with existing code-change vectors. Through extensive experiments, the results revealed gains up to 3.4% and 3.2% on the Fl-score and AUC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dermatological Diagnostics: A Unified Deep Learning Framework for Skin Lesion and Cancer Classification

Dermatological Diagnostics: A Unified Deep Learning Framewor...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Vinod Kumar Isha Jain Durga Sritha Dongla Shivangi Rai Vani Rastogi Eva Kaushik Rohit Kaushik School of Engineering & Applied Science The George Washington University Washington D.C USA Computer Science & Engineering Department Dr. Akhilesh Das Gupta Institute of Technology and Management New Delhi India Computer Science & Engineering Department Gandhi Institute of Technology and Management Visakhapatnam Andhra Pradesh Data Scientist DXC Technology Noida India CS and Mathematics Department Data Analytics Program University of Illinois Springfield USA

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Skin pathologies encompass a spectrum of conditions, with malignancies such as melanoma representing a critical diagnostic urgency. This investigation delineates the deployment of Convolutional Neural Networks (CNNs) for the classification of dermatological anomalies, benchmarking CNN diagnostic fidelity against dermatological expert evaluations. The study underscores the efficacy of CNN classifiers in expediting the diagnostic workflow for various cutaneous disorders. Advocating for an automated diagnostic framework, the research introduces a CNN-based system aimed at reducing human diagnostic load, accelerating diagnostic timelines, and enhancing survival outcomes. Utilizing advanced image processing algorithms and deep learning architectures, the research presents an automated classification system for skin pathologies, addressing both benign and malignant presentations. The classification matrix includes nine dermatological conditions: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, nevus, seborrheic keratosis, squamous cell carcinoma, and vascular lesions. The objective is to engineer a CNN model with robust diagnostic performance across a diverse lesion dataset, ensuring accurate identification and categorization of dermatological conditions.

关键词： Deep learning Pathology Accuracy Melanoma Computer architecture Benchmark testing Skin Convolutional neural networks Lesions Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Push4Rec: Temporal and Contextual Trend-Aware Transformer Push Notification Recommender

Push4Rec: Temporal and Contextual Trend-Aware Transformer Pu...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Chu-Chun Yu Ming-Yi Hong Chiok-Yew Ho Che Lin Graduate Institute of Communication Engineering National Taiwan University Taiwan Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Push notifications efficiently deliver real-time messages, boosting user engagement and website traffic. However, users often passively receive notifications without active interaction in recommendation contexts. Consequently, for precise recommendations, Click-Through Rate (CTR) prediction for push notifications requires addressing challenges such as user temporal and contextual preferences, the dynamic nature of user click behavior, and limited interactions between users and items. We propose Push4Rec, a novel push notification recommendation model designed explicitly for news articles. Push4Rec integrates pivotal learners to extract information adeptly. It assesses click behavior, captures preferences, and comprehends trends’ influence. A fusion function and gating network ensure versatile extraction of user click preferences. We assessed Push4Rec using a real-world push notification dataset from our partnering company. Push4Rec outperformed benchmark models, delivering state-of-the-art results across all evaluation metrics. Thus, we believe that Push4Rec, with its novel approach, sets a new standard in push notification services, driving forward the field of personalized recommendation systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Defect Detection of Wind Turbine Blade Using Virtual Reality and Deep Learning

A Novel Approach for Defect Detection of Wind Turbine Blade ...

引用

IISE Annual Conference and Expo 2023

作者： Rabbi, Md Fazle Emon, Solayman Hossain Nishat, Ehtesham Mahmud Tseng, Tzu-Liang Bill Ferdoushi, Atira Huang, Chun-Che Rahman, Md Fashiar Department of Industrial Manufacturing and Systems Engineering The University of Texas El PasoTX79968 United States Data Science Program The University of Texas at El Paso El PasoTX79968 United States Khulna9203 Bangladesh University of Rajshahi Rajshahi6205 Bangladesh National Chi Nan University Puli Taiwan

ISBN: (纸本)9781713877851

Wind turbines are subjected to continuous rotational stresses and unusual external forces such as storms, lightning, strikes by flying objects, etc., which may cause defects in turbine blades. Hence, it requires a periodical inspection to ensure proper functionality and avoid catastrophic failure. The task of inspection is challenging due to the remote location and inconvenient reachability by human inspection. Researchers used images with cropped defects from the wind turbine in the literature. They neglected possible background biases, which may hinder real-time and autonomous defect detection using aerial vehicles such as drones or others. To overcome such challenges, in this paper, we experiment with defect detection accuracy by having the defects with the background using a two-step deep-learning methodology. In the first step, we develop virtual models of wind turbines to synthesize the near-reality images for four types of common defects - cracks, leading edge erosion, bending, and light striking damage. The Unity® perception package is used to generate wind turbine blade defects images with variations in background, randomness, camera angle, and light effects. In the second step, a customized U-Net architecture is trained to classify and segment the defect in turbine blades. The outcomes of U-Net architecture have been thoroughly tested and compared with 5-fold validation datasets. The proposed methodology provides reasonable defect detection accuracy, making it suitable for autonomous and remote inspection through aerial vehicles. © IISE and Expo *** rights reserved.

关键词： Turbomachine blades

来源：评论

学校读者我要写书评

暂无评论

CVIT: CONTINUOUS VISION TRANSFORMER FOR OPERATOR LEARNING

arXiv

引用

arXiv 2024年

作者： Wang, Sifan Seidman, Jacob H. Sankaran, Shyam Wang, Hanwen Pappas, George J. Perdikaris, Paris Institution for Foundation of Data Science Yale University United States Graduate Program in Applied Mathematics and Computational Science University of Pennsylvania United States Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania United States Department of Electrical and Systems Engineering University of Pennsylvania United States

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision Transformer (CViT), a novel neural operator architecture that leverages advances in computer vision to address challenges in learning complex physical systems. CViT combines a vision transformer encoder, a novel grid-based coordinate embedding, and a query-wise cross-attention mechanism to effectively capture multi-scale dependencies. This design allows for flexible output representations and consistent evaluation at arbitrary resolutions. We demonstrate CViT’s effectiveness across a diverse range of partial differential equation (PDE) systems, including fluid dynamics, climate modeling, and reaction-diffusion processes. Our comprehensive experiments show that CViT achieves state-of-the-art performance on multiple benchmarks, often surpassing larger foundation models, even without extensive pretraining and roll-out fine-tuning. Taken together, CViT exhibits robust handling of discontinuous solutions, multi-scale features, and intricate spatio-temporal dynamics. Our contributions can be viewed as a significant step towards adapting advanced computer vision architectures for building more flexible and accurate machine learning models in the physical sciences. All data and code are publicly available at https://***/PredictiveIntelligenceLab/cvit. © 2024, CC BY-NC-SA.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contextual Caching for Mobile Edge Large Language Model Service

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

database Design for Pre-Eclampsia Case Administration

Database Design for Pre-Eclampsia Case Administration

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Faisal Asadi Gregorius Natanael Elwirehardja Joko Pebrianto Trinugroho Reza Rahutomo Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

The Ministry of Health of Indonesia has referred to pre-eclampsia as one of the most severe diseases affecting women. As an urgency, it is crucial to administrate pre-eclampsia cases for disease prevention as a long-term national healthcare strategy. Regarding health science, case data was significant in developing research and innovation. However, the main problem regarding pre-eclampsia case administration is data handling, recording, and management incompetence. Hence, this research proposed a conceptual design of a database for pre-eclampsia case administration. The proposed design covered conceptual, logical, and physical design. We elaborate the concept into three concepts of pre-eclampsia disease: pre-treatment, treatment, and post-treatment. This study proposed a solution to gain more data and study pre-eclampsia disease in Indonesia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Implementations in Childhood Stunting Research: A Systematic Literature Review

Machine Learning Implementations in Childhood Stunting Resea...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Reza Rahutomo Gregorius Natanael Elwirehardja Mahmud Isnan Faisal Asadi Bens Pardamean Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

Childhood stunting is a condition anticipated to affect the growth potential of children under the age of five. With numerous stunting researches that have been conducted, stunting datasets are now widely available to facilitate stunting research. This provides an opportunity to implement machine learning (ML) principles to produce a broader insight or a novel technique in stunting prediction. A systematic literature review is necessary to discover the landscape of machine learning implementation in the application domain as a preliminary study for creating an effective research roadmap. This paper presents a systematic literature review (SLR) of 22 curated manuscripts that focuses on identifying the ML models applied in stunting research, as well as the datasets used in such studies that were published during 2017–2022. The SLR process found that ML principles have been applied in stunting research since 2017, and the diversity of ML implementation has become more varied in 2021–2022. In terms of ML models, XGBoost and Random Forest are recognized as the two most utilized models, and stunting prediction is the most common ML implementation. The majority of stunting research utilizing ML has been conducted in Indonesia. Although national survey data has been the most commonly utilized dataset in stunting research, researchers in Indonesia have shown a preference for utilizing data from regional or independent surveys. This study will be followed by developing a classifier model for stunted children using XGBoost and Random Forest algorithms. The model will be trained on a dataset generated from StuntingDB.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process 25

From RAG to QA-RAG: Integrating Generative AI for Pharmaceut...

引用

40th Annual ACM Symposium on Applied Computing, SAC 2025

作者： Kim, Jaewoong Hur, Minseok Min, Moohong Department of Applied Data Science Sungkyunkwan University Seoul Korea Republic of Department of Immersive Media Engineering/Convergence Program for Social Innovation Sungkyunkwan University Seoul Korea Republic of Department of Computer Education/Convergence Program for Social Innovation Sungkyunkwan University Seoul Korea Republic of

ISBN: (纸本)9798400706295

Regulatory compliance in the pharmaceutical industry involves navigating complex and voluminous guidelines, often requiring significant amounts of human resources. Recent advancements in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) methods provide promising enhancements to data processing and knowledge management, potentially easing these burdens. However, despite these advancements, conventional Retrieval-Augmented Generation (RAG) methods fall short in this domain due to inherent structural problems. To address these challenges, we introduce the Question and Answer Retrieval Augmented Generation (QA-RAG) framework. This framework enhances the conventional RAG framework. It integrates a dual-track retrieval mechanism tailored to the specific and dynamic nature of pharmaceutical regulations. It utilizes not only the original query but also the answers generated by a fine-tuned LLM, thus providing a more robust foundation for document retrieval. Our experiments demonstrate that QA-RAG outperforms conventional methods in various evaluation metrics including precision, recall, and F1-score. These results underscore QA-RAG's capability to enhance both the accuracy and efficiency of regulatory compliance processes in the pharmaceutical industry. This paper details the structure and efficacy of QA-RAG, emphasizing its potential to revolutionize the regulatory compliance process in the pharmaceutical industry and beyond. Copyright © 2025 held by the owner/author(s).

关键词： data integration

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：