检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Hershey, Quincy Paffenroth, Randy Pathak, Harsh Data Science Worcester Polytechnic Institute Worcester United States Mathematical Sciences Computer Science and Data Science Worcester Polytechnic Institute Worcester United States

ISBN: (纸本)9798350345346

This paper explores the role of sparse parameteri-zations on Recurrent Neural Network (RNN) performance using anomaly detection tasks. The findings indicate sparsity plays a significant role in both improving training stability and overall performance of RNNs. Sparsity of the weight matrix is initially left to vary while the dimensions of the weight matrix remain fixed, causing total trainable weights to vary in response. The sparse RNN models demonstrate surprisingly low performance sensitivity to the resulting changes in total trainable weights. Building on these results, sparsity of the weight matrix is again left to vary with a fixed number of trainable weights and the dimensions of the weight matrix permitted to change with sparsity. By isolating the impact of sparse parameterizations, RNNs show improved training stability and overall performance. Moreover, the results indicate an optimal band of sparsity within which RNNs perform most efficiently across a difficult time-series task. Sparse RNN configurations are compared to LSTM models in anomaly detection tasks. Sparse RNN models demonstrate a strong performance advantage over LSTM models, even out-performing in scenarios where memory is crucial and LSTM models are expected to perform better. The results indicate the reputation of RNN training instability may be exacerbated by overparamaterization resulting from dense configurations. Several characteristics such as model depth and model sparsity are presented which significantly improve the stability and expressiveness of model performance across a wider array of hyperparameters while improving performance differentials at significantly reduced weight counts. Ultimately the paper finds the potential of RNNs to be better realized through sparse parameterizations. © 2023 IEEE.

关键词： recurrent neural networks RNN sparsity

来源：评论

学校读者我要写书评

暂无评论

Real-time updating of dynamic social networks for COVID-19 vaccination strategies

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第3期15卷 1981-1994页

作者： Cheng, Sibo Pain, Christopher C. Guo, Yi-Ke Arcucci, Rossella Data Science Instituite Department of Computing Imperial College London London United Kingdom Department of Earth Science and Engineering Imperial College London London United Kingdom

Vaccination strategy is crucial in fighting the COVID-19 pandemic. Since the supply is still limited in many countries, contact network-based interventions can be most powerful to set an efficient strategy by identifying high-risk individuals or communities. However, due to the high dimension, only partial and noisy network information can be available in practice, especially for dynamic systems where contact networks are highly time-variant. Furthermore, the numerous mutations of SARS-CoV-2 have a significant impact on the infectious probability, requiring real-time network updating algorithms. In this study, we propose a sequential network updating approach based on data assimilation techniques to combine different sources of temporal information. We then prioritise the individuals with high-degree or high-centrality, obtained from assimilated networks, for vaccination. The assimilation-based approach is compared with the standard method (based on partially observed networks) and a random selection strategy in terms of vaccination effectiveness in a SIR model. The numerical comparison is first carried out using real-world face-to-face dynamic networks collected in a high school, followed by sequential multi-layer networks generated relying on the Barabasi-Albert model emulating large-scale social networks with several communities. © The Author(s) 2023.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Skill Mount: Personalized Career Skills Development Using Machine Learning Algorithms 11

Skill Mount: Personalized Career Skills Development Using Ma...

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Krishnan, Akhil Joseph, James Nihal, N.N. Salva Fathima, S. Priya, C.V. Muthoot Institute of Technology and Science Department of Artificial Intelligence and Data Science Kerala Kochi India

ISBN: (纸本)9798350379136

In today's rapidly changing job market, achieving career goals requires a strategic approach to skill development. Skill Mount is an intuitive web application designed to guide individuals through their career journeys, aiding in both planning and attainment of objectives through personalized technology-driven methods. Given the constant evolution of job roles and the competitive landscape, continuous skill enhancement is imperative for career advancement, making Skill Mount an indispensable tool. Serving as a personalized coach, it tailors daily skill acquisition plans, monitors progress, and suggests suitable job roles based on individual preferences. Leveraging artificial intelligence (AI), including Natural Language Processing (NLP) and Machine Learning (ML), Skill Mount analyzes user data to provide customized skill suggestions and job descriptions. The proposed system uses Recommendation Systems to propose relevant learning resources and utilizes an ensemble method (random forest algorithm) for job recommendations, As a result system acquired higher accuracy rates. With a focus on user experience (UX), Skill Mount ensures seamless interaction through its intuitive interface and automated features driven by AI. By simplifying the career journey and empowering individuals to adapt to the competitive job market, Skill Mount plays a pivotal role in facilitating career growth and success. © 2024 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Markov Property Checking methods for time series data 2

Markov Property Checking methods for time series data

引用

2nd International Conference on Big data, Computational Intelligence, and Applications, BDCIA 2024

作者： Chen, Xinran Fang, Huan College of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

ISBN: (纸本)9781510689053

In applicable scenarios, data used for forecasting and decision-making is usually expected to exhibit characteristics like time stationarity and the Markov property, and etc. However, industrial applications often skip verifying whether the data meets these requirements, aiming to save time and effort, which may lead to inaccurate results. This paper explores the Markov property checking method from statistical and information-theoretic perspectives, and utilizes two types of time series data, named AAPL stock prices data and BPIC2012 event logs, respectively, to validate the effectiveness of proposed checking method. Experimental results show that datasets that conforming to the Markov property tend to perform better in predictive tasks. © 2025 SPIE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

EEG-based Incongruency Decoding in AR with sLDA, SVM, and EEGNet

引用

Current Directions in Biomedical Engineering 2024年第3期10卷 21-24页

作者： Wimmer, Michael Veas, Eduardo E. Müller-Putz, Gernot R. Know-Center Graz Austria Institute of Neural Engineering Graz Austria Institute of Interactive Systems and Data Science Graz Austria

Augmented reality (AR) technologies enhance a user’s physical environment by providing contextual information about their surroundings. This information might appear incongruent to users, either due to their current mental context or factual errors in the data. This paper explores the feasibility of incongruency decoding using electroencephalographic (EEG) signals from 19 participants acquired during an interactive AR task. Previous studies on single-trial N400 decoding for brain-computer interfaces using EEG data are limited. Therefore, we implemented commonly used classification approaches and assessed their decoding performance compared to the convolutional neural network EEGNet. We found that the investigated approaches offer comparable accuracies ranging from 63.3% to 64.8%. Successful decoding of incongruency effects can foster more contextually appropriate interactions within AR environments. © 2024 The Author(s), published by De Gruyter.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

OpenRAG: Open-source Retrieval-Augmented Generation Architecture for Personalized Learning 4

OpenRAG: Open-source Retrieval-Augmented Generation Architec...

引用

4th International Conference on Artificial Intelligence, Robotics, and Communication, ICAIRC 2024

作者： Shan, Richard North Carolina School of Science and Mathematics Department of Data Science DurhamNC United States

ISBN: (纸本)9798331531225

This paper introduces OpenRAG, an open-source Retrieval-Augmented Generation (RAG) system architecture designed to enhance GenAI applications in personalized learning. The architecture is modular with loosely coupled components: Generator, User Interface, Indexing subsystem, Retriever, and Orchestration module. The research applies cutting-edge design patterns for retrieval, generation, indexing, storage, user interactions, and performance optimization, whereas the data flow and processing pipeline are seamlessly integrated for customization and adaptability. A case study demonstrates a proof-of-concept implementation of OpenRAG used in an online learning platform, resulting in significant increases in learner engagement and education efficiency. Key design concerns such as computational efficiency, content accuracy, learning styles, and user experience are discussed along with their solutions. © 2024 IEEE.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Ensemble Based Precautionary Detection of Parkinson's Disease from Voice Signal 1

Ensemble Based Precautionary Detection of Parkinson's Diseas...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Bhanusree, Yalamanchili Adhvy, Vodnala Sharan Affan, Mohammed Shaji Praneetha, Kanvapuri Sai Sahithi, Katikireddy Sai Computer Science - Data Science VNR Vignana Jyothi Institute of Engineering & Technology Hyderabad India

ISBN: (纸本)9798331518943

Parkinson's Disease is a neurological progressive disorder that affects the nervous system of a human being, which effects the parts of the body. Tremors, imbalance, slowed movement, stiffness, difficulty in walking and talking etc. are observed. The reasons being, brain disorder, injuries, toxins certain drugs etc. The disease has no cure however treatment can be offered for relief from symptoms. However early detection can cure the disease in the first stages and extend the life span of the patient. This paper proposes a Ensembled learning model for early detection of Parkinsons disease through voice features. Random forest ensemble models have outperformed the Machine learning and Neural Network models in detecting disease from voice. An accuracy of 94.8% is achieved with this model with proper preprocessing techniques and training. As a future work the proposed model's software prototype can be released for mobile application for cost effective early detection of Parkinsons Disease. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural Computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Designing a data science simulation with MERIT S: A Primer

arXiv

引用

arXiv 2024年

作者： Elliott, Corrine F. Duncan, James Tang, Tiffany M. Behr, Merle Kumbier, Karl Yu, Bin Department of Statistics University of California BerkeleyCA United States Graduate Group in Biostatistics University of California BerkeleyCA United States Department of Statistics University of Michigan MI United States Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Department of Pharmaceutical Chemistry University of California San FranciscoCA United States

Simulations play a crucial role in the modern scientific process. Yet despite (or due to) their ubiquity, the data science community shares neither a comprehensive definition for a "high-quality" study nor a consolidated guide to designing one. Inspired by the Predictability-Computability-Stability (PCS) framework for 'veridical' data science, we propose six MERIT S that a data science simulation should satisfy. Modularity and Efficiency support the Computability of a study, encouraging clean and flexible implementation. Realism and Stability address the conceptualization of the research problem: How well does a study Predict reality, such that its conclusions generalize to new data/contexts? Finally, Intuitiveness and T ransparency encourage good communication and trustworthiness of study design and results. Drawing an analogy between simulation and cooking, we moreover offer (a) a conceptual framework for thinking about the anatomy of a simulation 'recipe';(b) a baker's dozen in guidelines to aid the data science practitioner in designing one;and (c) a case study deconstructing a simulation through the lens of our framework to demonstrate its practical utility. By contributing this "PCS primer" for high-quality data science simulation, we seek to distill and enrich the best practices of simulation across disciplines into a cohesive recipe for trustworthy, veridical data science. © 2024, CC BY.

关键词： Computability and decidability

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation on Point Clouds via High-Order Geometric Structure Modeling

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6121-6133页

作者： Cheng, Jiang-Xing Lin, Huibin Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangdong Guangzhou510006 China

Point clouds can capture the precise geometric information of objects and scenes, which are an important source of 3-D data and one of the most popular 3-D geometric data structures for cognitions in many real-world applications like automatic driving and remote sensing. However, due to the influence of sensors and varieties of objects, the point clouds obtained by different devices may suffer obvious geometric changes, resulting in domain gaps that are prone to the neural networks trained in one domain failing to preserve the performance in other domains. To alleviate the above problem, this article proposes an unsupervised domain adaptation framework, named HO-GSM, as the first attempt to model high-order geometric structures of point clouds. First, we construct multiple self-supervised tasks to learn the invariant semantic and geometric features of the source and target domains, especially to capture the feature invariance of high-order geometric structures of point clouds. Second, the discriminative feature space of target domain is acquired by using contrastive learning to refine domain alignment to specific class level. Experiments on the PointDA-10 and GraspNetPC-10 collection of datasets show that the proposed HO-GSM can significantly outperform the state-of-the-art counterparts. © 2020 IEEE.

关键词： Self-supervised 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：