检索结果-内蒙古大学图书馆

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Liu, Fangxin Wang, Zongwu Xu, Peng Huang, Shiyuan Jiang, Li Department of Computer Science and Engineering Shanghai Jiao Tong University China Shanghai Qi Zhi Institute China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University China

ISBN: (纸本)9798400706356

Storing large-scale high-dimensional data, which is rapidly generated by both industry and academia, poses substantial challenges, primarily in terms of storage and maintenance costs. While data compression techniques offer a potential solution to these challenges, they must overcome two critical hurdles: 1) preserving data integrity within lossless bounds and 2) maintaining query performance on compressed *** address the above challenges, we propose a novel approach based on differential techniques that combine high-dimensional data compression with an efficient query engine. Specifically, Our methodology begins by employing vector quantization to transform high-dimensional vectors into compact integer sequences, known as quantization codes - -a classical and versatile compression method. Subsequently, we introduce DCQ, which builds upon the differential concept to perform lossless compression on quantization codes. DCQ organizes quantization codes into a tree structure and constructs a hierarchy of trees by analyzing the dissimilarity between two quantization codes. To minimize the impact on query performance, we have developed an adaptive reconstruction algorithm that partitions and reconstructs the original tree structure. This algorithm effectively balances the workload for searching each sub-tree, optimizing the compression-performance trade-off. Finally, we adopt a storage format based on multiple subtrees for rapid searching, thereby enabling differential storage to facilitate efficient queries. Extensive experiments on various large-scale real-world datasets show that DCQ achieves a compression ratio of up to 2.5 on the quantization codes and achieves > 50× performance improvement compared to the state-of-the-art general-purpose lossless compression techniques. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Healthcare Cost Patterns and Prediction: Investigating Personal Datasets Using Data Analytics 3rd

Healthcare Cost Patterns and Prediction: Investigating Perso...

引用

3rd International Conference on Signal and Data Processing, ICSDP 2023

作者： Islam, Md. Aminul Nag, Anindya Chandra, Pretam Mishra, Bhupesh Kumar Fahim, S. M. Firoz Ahmed Hoque, Md Mozammel School of Engineering Computing and Mathematics Oxford Brookes University Oxford United Kingdom College of Engineering and Physical Sciences University of Birmingham Birmingham United Kingdom Computer Science & Engineering Discipline Khulna University Khulna9208 Bangladesh Department of Computer Science & Engineering Adamas University Kolkata700126 India Centre of Excellence for Data Science AI and Modelling University of Hull Hull United Kingdom Department of Computer Science & Engineering American International University Dhaka Bangladesh Gannon University Erie United States

ISBN: (纸本)9789819795772

The present study introduces a health insurance prediction system that leverages machine learning methodologies. In contemporary times, there has been a notable increase in endeavors focused on tackling this matter, since the significance of health insurance as a research topic has markedly escalated following the occurrence of the pandemic. The dataset employed in this research comprises 1338 observations, 7 columns, and corresponds to individual medical expenditures in the United States which is available at the Kaggle platform. The dataset encompasses a variety of variables utilized in the prediction of insurance prices, including age, gender, BMI, smoking status, and number of children. The researchers utilized machine learning models including neural network, Xai, auto modeling to determine the correlation between pricing and the aforementioned attributes. The training process involved partitioning the dataset into a 80–20 ratio for training and evaluation respectively. As a consequence, the system achieved an accuracy rate of 97% by Gradient Boosting but we corrected it as 92% by Gradient Boosting Regressor by encoding and hyper tuning. Also, among predictive machine learning models, Random Forest had the best accuracy i.e., of 83.44%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

LLM Sensitivity Evaluation Framework for Clinical Diagnosis 31

LLM Sensitivity Evaluation Framework for Clinical Diagnosis

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yan, Chenwei Fu, Xiangling Xiong, Yuxuan Wang, Tianyi Hui, Siu Cheung Wu, Ji Liu, Xien School of Computer Science Beijing University of Posts and Telecommunications China Ministry of Education China Nanyang Technological University Singapore Department of Electronic Engineering Tsinghua University China College of AI Tsinghua University China

ISBN: (纸本)9798891761964

Large language models (LLMs) have demonstrated impressive performance across various domains. However, for clinical diagnosis, higher expectations are required for LLM's reliability and sensitivity: thinking like physicians and remaining sensitive to key medical information that affects diagnostic reasoning, as subtle variations can lead to different diagnosis results. Yet, existing works focus mainly on investigating the sensitivity of LLMs to irrelevant context and overlook the importance of key information. In this paper, we investigate the sensitivity of LLMs, i.e. GPT-3.5, GPT-4, Gemini, Claude3 and LLaMA2-7b, to key medical information by introducing different perturbation strategies. The evaluation results highlight the limitations of current LLMs in remaining sensitive to key medical information for diagnostic decision-making. The evolution of LLMs must focus on improving their reliability, enhancing their ability to be sensitive to key information, and effectively utilizing this information. These improvements will enhance human trust in LLMs and facilitate their practical application in real-world scenarios. Our code and dataset are available at https://***/chenwei23333/DiagnosisQA. © 2025 Association for Computational Linguistics.

关键词： Medical informatics

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Security and Efficiency: Advanced Public Key Cryptographic Solutions for the Modern Era

Enhancing IoT Security and Efficiency: Advanced Public Key C...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Ramesh Sekaran Dhanalakshmi Ramasamy John Basha Mohamed Basha Kumaresan Maruthapillai S. Annamalai Manikandan Parasuraman Department of Computer Science and Engineering JAIN (Deemed-to-be University) Bangalore India Department of Computer Science and Engineering-AI Madanapalle Institute of Technology and Science Madanapalle India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

The landscape of the Internet of Things is evolving rapidly. The security and efficiency of data handling and device management are multifaceted and complex problems, which are only exacerbated by the huge volumes of data and the sprawling growth of IoT deployments. The goal of this paper is to outline innovative solutions to the most pressing issues in the field through the use of advanced cryptographic protocols and scalable management systems. The integrity and maintainability of IoT ecosystems face threats not only from quantum-capable attackers but also from vendor lock-in, which necessitates special attention. First, the Secure Data Retrieval Encryption system will be presented, which is based on the Learning with Errors assumptions, Self-Managed Public Key Infrastructure, Next-generation Hashed Elliptic Curve Protocol, and Dynamic Unclonable Physical Properties. In a single round of queries, SDRE enables forward security and efficient searches defined by authorized clients. This work presents a distinctive innovation. Initially, the search process was accelerated greatly, and the data being transmitted and decrypted was implemented based on secure computation. In addition, the Self-Managed Public Key Infrastructure protocol is a simple and standard-acquiescent answer for changing control between IoT service providers. SMS-PKI seeks to diminish this necessity of manual effort, especially in light of the massive upsurge in IoT deployments. SM-PKI also mechanizes the IoT PKI credentials updating and trusted domains process, allowing multiple domains to be run on one client apparatus. Tamarin is used to prove security and efficiency, which demonstrates the necessity of using SM-PKI to maintain desired security properties with the minimal cost and device overhead. Finally, a universal authentication scheme grounded on edge computing and involving Next-generation Hashed Elliptic Curve Protocol and Dynamic Unclonable Physical Properties will be shown. This approach

关键词： Technological innovation Elliptic curves Scalability Ecosystems Data retrieval Public key cryptography Encryption Internet of Things Security Next generation networking

来源：评论

学校读者我要写书评

暂无评论

Robust Face Recognition Using Histogram of Oriented Gradients and Auto-Associative Memory Network

Robust Face Recognition Using Histogram of Oriented Gradient...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Jay Kant Pratap Singh Yadav Zainual Abdin Jaffery Laxman Singh Electrical Engineering Department Jamia Millia Islamia (Central University) New Delhi India Computer Science & Engg.(AI&ML) Department KIET Group of Institutions Ghaziabad India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

Facial recognition technology is based on a person's facial features. It is often the core of applications such as biometrics, access control, and forensics. However, due to environmental factors such as dust accumulation on the camera lens or equipment failure, the accuracy of the system is often questioned; especially when it comes to noise and partial occlusions in the test images. This paper proposes a new approach for automatic face recognition using histogram oriented gradient features of facial images with auto-associative memory in the form of a “Multi-Connection Hopfield Neural Network”. The method described here efficiently stores and retrieves facial patterns in noisy or partially occluded environments. In testing, this proposed approach achieved a recognition rate of 98.5% on the ORL dataset, outperforming these other state-of-the-art methods. Furthermore, this method maintains 95.0% accuracy even with 50% random noise and exhibits superior performance and robustness under partial occlusion and variable lighting conditions.

关键词： Histograms Accuracy Face recognition Noise Lighting Hopfield neural networks Robustness Computational efficiency Noise measurement Testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wind Turbine Reliability through Proactive High Speed Bearing Prognosis Based on Adaptive Threshold and Gated Recurrent Unit Networks 49

Enhancing Wind Turbine Reliability through Proactive High Sp...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Dhiman, Harsh S. Bhanushali, Dev Su, Chun-Lien Berghout, Tarek Amirat, Yassine Benbouzid, Mohamed Symbiosis Institute of Technology Department of Ai & Ml Pune India National Kaohsiung University of Science and Technology Department of Electrical Engineering Taiwan University of Batna 2 Laboratory of Automation and Manufacturing Engineering Algeria L@bISEN Department of Electrical Engineering Brest France University of Brest Umr Cnrs 6027 Irdl France

ISBN: (纸本)9798350331820

High-speed bearings play a vital role in the functionality of modern wind turbines. Accurately estimating impending failure and predicting the remaining useful life (RUL) of bearings brings significant benefits in scheduling maintenance strategies and preventing sudden turbine shutdowns. This paper discusses a reliability enhancement prognosis framework for high-speed wind turbine bearings based on a measured representative vibration signature. A health indicator is constructed using a sliding window adaptive threshold (SWAT) to map the degradation behavior of the bearings into RUL. The Gated recurrent unit (GRU)-based deep learning algorithm shows promising predictive performance in terms of mean absolute error (MAE) and relative accuracy (RA). © 2023 IEEE.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

SEED: Semantic Knowledge Transfer for Language Model Adaptation to Materials science

SEED: Semantic Knowledge Transfer for Language Model Adaptat...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Yeachan Park, Jun-Hyung Kim, SungHo Park, Juhyeong Kim, Sangyun Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761667

Materials science is an interdisciplinary field focused on studying and discovering materials around us. However, due to the vast space of materials, downstream datasets in this field are typically scarce and have limited coverage. This inherent limitation poses challenges when adapting pre-trained language models (PLMs) to materials science, as existing methods rely heavily on frequency information from these limited datasets. In this paper, we propose Semantic Knowledge Transfer (SEED), a novel vocabulary expansion method designed to adapt pre-trained language models (PLMs) for materials science. The core strategy of SEED is to transfer materials knowledge from lightweight embeddings into PLMs. To achieve this, we introduce knowledge bridge networks, which learn to transfer the latent knowledge embedded in materials-specific embeddings into representations compatible with PLMs. By expanding the embedding layer of PLMs with these transformed embeddings, the models can comprehensively understand the complex terminology associated with materials science. We conduct extensive experiments across a broad range of materials-related benchmarks. The comprehensive evaluation results convincingly demonstrate that SEED mitigates the limitations of previous adaptation methods, showcasing the efficacy of embedding knowledge transfer into PLMs. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Audio-Visual ASR with Unified Cross-Modal Attention 48

Robust Audio-Visual ASR with Unified Cross-Modal Attention

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Li, Jiahong Li, Chenda Wu, Yifei Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9781728163277

Audio-visual speech recognition (AVSR) takes advantage of noise-invariant visual information to improve the robustness of automatic speech recognition (ASR) systems. While previous works mainly focused on the clean condition, we believe the visual modality is more effective in noisy environments. The challenges arise from the difficulty of adaptive fusion of audio-visual information and the possible interferences inside the training data. In this paper, we present a new audio-visual speech recognition model with a unified cross-modal attention mechanism. In particular, the auxiliary visual evidence is combined with the acoustic feature along the temporal dimension in the unified space before the deep encoding network. This method provides a flexible cross-modal context and requires no forced alignment such that the model can learn to leverage the audio-visual information in relevant frames. In experiments, the proposed model is demonstrated to be robust to the potential absence of the visual modality or misalignment in audio-visual frames. On the large-scale audio-visual dataset LRS3, our new model further reduces the state-of-The-Art WER for clean utterances and significantly improves the performance under noisy conditions. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Implementing Machine Learning-based Autonomic Cyber Defense for IoT-enabled Healthcare Devices

引用

Journal of Artificial Intelligence and Technology 2023年第4期3卷 162-172页

作者： M.Manimaran Murali Dhar Roger Norabuena-Figueroa R.Mahaveerakannan S.Saraswathi K.Selvakumarasamy Department of Computer Science and Engineering(AI&ML) School of ComputingMohan Babu UniversityTirupatiAndhra PradeshIndia Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology AvadiChennaiTNIndia Universidad Privada San Juan Bautista LimaPerú Saveetha School of Engineering Saveetha Institute of Medical and Technical SciencesChennaiTNIndia

Smart homes present a serious challenge for the aged and those with mobility issues due to the environment’s inherent *** people have the propensity to fall over when bending over in these ***,they show two time-based reasoning models to identify incidents of potentially fatal falls that have not been accounted for(CM-I and CM-II).The ubiquitous use of IoT altimeter watches among the elderly provides a wealth of data that can be used by these algorithms to predict the likelihood of a fall based on categorization *** compared actual and simulated data involving missteps,mishaps,and crashes to gauge the programmers’*** suggest that using such logic models to help healthcare providers determine if senior people living in smart homes have fallen is a potential field for future *** CM-II model had the highest prediction accuracy of any model identified in the literature,at 0.98 when compared to the test *** the number of devices linked to the IoT can be quickly extended in contrast to the number of devices connected to conventional computers,the number of hacks aimed at the IoT has grown *** is no way to fix the issue that hacked IoT devices create until they figure out how to track down the source of the *** a deeper understanding of the technologies,protocols,and architecture of IoT systems,as well as the potential consequences of using infected IoT devices,is the overarching goal of this *** are many Internet of Things(IoT)systems vulnerable to cybercriminal manipulation,so this study also explores a range of machine learning and deep learning-based methods that can be used to detect such compromise.

关键词： cyber defense healthcare devices Internet of Things(IoT) machine learning

来源：评论

学校读者我要写书评

暂无评论

MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials science

MELT: Materials-aware Continued Pre-training for Language Mo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Junho Kim, Yeachan Park, Jun-Hyung Oh, Yerim Kim, Suho Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761681

We introduce a novel continued pre-training method, MELT (Materials-aware continued pretraining), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science. Unlike previous adaptation strategies that solely focus on constructing domain-specific corpus, MELT comprehensively considers both the corpus and the training strategy, given that materials science corpus has distinct characteristics from other domains. To this end, we first construct a comprehensive materials knowledge base from the scientific corpus by building semantic graphs. Leveraging this extracted knowledge, we integrate a curriculum into the adaptation process that begins with familiar and generalized concepts and progressively moves toward more specialized terms. We conduct extensive experiments across diverse benchmarks to verify the effectiveness and generality of MELT. A comprehensive evaluation convincingly supports the strength of MELT, demonstrating superior performance compared to existing continued pretraining methods. In-depth analysis of MELT also shows that MELT enables PLMs to effectively represent materials entities compared to the existing adaptation methods, thereby highlighting its broad applicability across a wide spectrum of materials science. © 2024 Association for Computational Linguistics.

关键词： Semantics

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：