检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Xiancong Chen Weike Pan Zhong Ming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In this paper, we study a recent and important recommendation problem called heterogeneous one-class collaborative filtering (HOCCF), where we have two different types of one-class feedback, i.e., a set of browses and a set of purchases, for preference learning. Previous methods exploit the browses and purchases by extending some existing methods on modeling homogeneous one-class feedback in an integrative or sequential manner. However, an integrative method may be of high complexity in model training due to the expanded prediction rule, and a sequential method is of inconvenience in deployment because more than one parametric models have to be maintained. In this paper, we convert the HOCCF problem to an adaptive transfer learning task, where we first model browses via a factorization model from a perspective of the role of browser, and then adaptively refine the learned model parameters via purchases from a perspective of the dependent role of purchaser. Based on this conversion, we design a novel solution called role-based adaptive factorization (ROAF), and then derive two specific variants with pairwise preference learning and pointwise preference learning. Finally, we conduct extensive empirical studies on two large datasets, and find that our ROAF is a very promising solution in terms of recommendation accuracy, besides its convenience of one single parametric model in deployment.

关键词： Browsers Adaptation models Parametric statistics Training Bayes methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Sequence-Aware Factored Mixed Similarity Model for Next-Item Recommendation

Sequence-Aware Factored Mixed Similarity Model for Next-Item...

引用

International Conference on big data and Smart Computing (bigCOMP)

作者： Liulan Zhong Jing Lin Weike Pan Zhong Ming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen University College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Sequence-aware next-item recommendation has recently been studied because of the noteworthy usefulness of the sequential information integrated into recommendation algorithms. Following the development thread of sequential recommendation methods, especially the factored Markov chains segment, we propose a novel sequence-aware factored mixed similarity model (S-FMSM) based on a well-designed fusing similarity model with factored high-order Markov chains (i.e., Fossil). Unlike the baseline methods that model the general representation and the sequential representation in two divided factorization components, we use a factored mixed similarity model that unites the general similarity and the sequential relationship between two successive items for their sequential representation learning. Experiments on six datasets show that our newly introduced general similarity can notably improve the results of the recommended ranking lists. And a study on tuning the prior tradeoff parameter indicates the importance of the general similarity on different datasets.

关键词： Markov processes Linear programming Probability big data Collaboration Feeds Conferences

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on big data and Smart Computing (bigCOMP)

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

In this paper, we focus on a recently studied problem in recommendation called heterogeneous one-class collaborative filtering (HOCCF), which consists of different types of feedback, e.g., target feedback and auxiliary feedback. The main challenge of HOCCF is how to make good use of the large-scale and ambiguous auxiliary feedback to assist the task of learning users'true preferences. Inspired by a recent method that jointly learns the similarity among items associated with the target feedback and auxiliary feedback in a transfer learning manner, we further extend this method by learning additional similarity among users for better modeling users' preferences. Specifically, we jointly learn the item-based similarity and user-based similarity by leveraging the target feedback and auxiliary feedback, and then aggregate the dual similarity into one single prediction rule for estimating users' preferences, which is thus termed as dual similarity learning model (DSLM). Extensive empirical studies on three public datasets show that our DSLM with dual similarity is more effective in terms of recommendation accuracy, demonstrating that our method strikes a good balance between the item-based similarity and user-based similarity.

关键词： Collaboration IP networks Aggregates big data Predictive models Indexes Uncertainty

来源：评论

学校读者我要写书评

暂无评论

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

arXiv

引用

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Cross-Language Information Matching Technology Based on Term Extraction 14

Cross-Language Information Matching Technology Based on Term...

引用

14th IEEE International Conference on Intelligent Systems and Knowledge engineering, ISKE 2019

作者： Liu, Gang Zhang, Sennan Liu, Wangyang Cao, Yang Sun, Suyan Harbin Engineering University College of Computer Science and Technology Harbin China Cetc Big Data Research Institute Company Limited General Technology Research Center Guiyang China

ISBN: (纸本)9781728123486

Based on the analysis and summary of current achievements on terms extraction, this paper puts forward a method of term extraction based on multi feature fusion. This method firstly uses term word formation rules to filter words depending on the result of preprocessing, and then determines the boundaries of words according to information entropy. The paper introduces the concept of word co-occurrence according to the features of field terms, and uses bag of words model to align terms in both English and Chinese, and obtains the corresponding translation terms in one field. Finally, it establishes the link between Chinese and English by using the term alignment results in both English and Chinese retrieval model. This paper carries out repeated experiments on sets of policy documents. The experiments test and verify the availability of the method by the analysis and comparison between the method introduced in this paper and the traditional methods. © 2019 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation

arXiv

引用

arXiv 2024年

作者： Li, Cheng-Yi Chang, Kao-Jung Yang, Cheng-Fu Wu, Hsin-Yu Chen, Wenting Bansal, Hritik Chen, Ling Yang, Yi-Ping Chen, Yu-Chun Chen, Shih-Pin Lirng, Jiing-Feng Chang, Kai-Wei Chiou, Shih-Hwa Department of Computer Science University of California Los Angeles United States Department of Medical Research Taipei Veterans General Hospital Taiwan School of Medicine College of Medicine National Yang Ming Chiao Tung University Taiwan Institute of Clinical Medicine National Yang Ming Chiao Tung University Taiwan Big Data Center Taipei Veterans General Hospital Taiwan Department of Ophthalmology Taipei Veterans General Hospital Taiwan Department of Electrical Engineering City University of Hong Kong Hong Kong Institute of Hospital and Health Care Administration National Yang Ming Chiao Tung University Taiwan Department of Family Medicine Taipei Veterans General Hospital Taiwan Department of Neurology Neurological Institute Taipei Veterans General Hospital Taiwan Department of Radiology School of Medicine National Yang Ming Chiao Tung University Taiwan College of Medicine National Yang Ming Chiao Tung University Taiwan

Multi-modal large language models (MLLMs) have been given free rein to explore exciting medical applications with a primary focus on radiology report generation. Nevertheless, the preliminary MLLM successful attempts in 2D medical image-text pair captioning are incompetent to reflect the real-world diagnostic challenge in the volumetric 3D anatomy. Toward deploying MLLM for more applicable diagnostic context, we noticed that the (1) scarcity of 3D image training dataset, (2) the direct use of undifferentiated foundation MLLMs, and (3) the lack of pertinent caption evaluation metrics were independent domain-specific constraints that integratively hobbles the iteration of next-generation medical MLLM research. In this regard, this study collected a 3D-BrainCT dataset (18,885 text-scan pairs) and applied clinical visual instruction tuning (CVIT) to train volumetric anatomy-sensible BrainGPT models to generate radiology-adherent 3D brain CT reports. Statistically, our BrainGPT model scored BLEU-1 = 44.35, BLEU-4 = 20.38, METEOR = 30.13, ROUGE-L = 47.6, and CIDEr-R = 211.77 during internal testing and demonstrated an accuracy of 0.91 in captioning midline shifts on the external validation CQ500 dataset. By further inspecting the captioned report, we reported that the traditional metrics appeared to measure only the surface text similarity and failed to gauge the information density of the diagnostic purpose. To close this gap, we proposed a novel Feature-Oriented Radiology Task Evaluation (FORTE) to estimate the clinical relevance (lesion feature and landmarks) of the report. Notably, the BrainGPT model scored an average FORTE 0.71 F1-score (degree=0.661;landmark=0.706;feature=0.693, and impression=0.779). To demonstrate that BrainGPT models possess objective readiness to generate human-like radiology reports, we conducted a Turing test that enrolled 11 physician evaluators, and around 74% of the BrainGPT-generated captions were indistinguishable from those written by hu

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

A Mobile Cloud-Based eHealth Scheme

引用

computers, Materials & Continua 2020年第4期63卷 31-39页

作者： Yihe Liu Aaqif Afzaal Abbasi Atefeh Aghaei Almas Abbasi Amir Mosavi Shahaboddin Shamshirband Mohammed A.A.Al-qaness Data Recovery Key Laboratory of Sichuan Province College of Computer Science and AINeijiang Normal UniversityNeijiang641100China Department of Software Engineering Foundation UniversityIslamabad44000Pakistan Department of Communication Faculty of Social SciencesUniversity of TehranTehran***Iran Department of Computer Science International Islamic UniversityIslamabad46000Pakistan Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam Kalman Kando Faculty of Electrical Engineering Obuda UniversityBudapest1034Hungary School of the Built Environment Oxford Brookes UniversityOxfordOX30BPUK Department for Management of Science and Technology Development Ton Duc Thang UniversityHo Chi Minh CityVietnam Faculty of Information Technology Ton Duc Thang UniversityHo Chi Minh CityVietnam School of Computer Science Wuhan UniversityWuhan430072China

Mobile cloud computing is an emerging field that is gaining popularity across borders at a rapid ***,the field of health informatics is also considered as an extremely important *** work observes the collaboration between these two fields to solve the traditional problem of extracting Electrocardiogram signals from trace reports and then performing *** developed system has two front ends,the first dedicated for the user to perform the photographing of the trace *** the photographing is complete,mobile computing is used to extract the *** the signal is extracted,it is uploaded into the server and further analysis is performed on the signal in the *** this is done,the second interface,intended for the use of the physician,can download and view the trace from the *** data is securely held using a password-based authentication *** system presented here is one of the first attempts at delivering the total solution,and after further upgrades,it will be possible to deploy the system in a commercial setting.

关键词： Cloud computing electrocardiograms health-care signal analysis signal processing

来源：评论

学校读者我要写书评

暂无评论

Non-Orthogonal Superimposed Pilot for Goodput Enhancement in Digital Semantic Communication

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Zou, Jian Xiao, Jian Shen, Han Xie, Wenwu Meng, Fanyang Yang, Liang Liang, Yongsheng Shenzhen University College of Applied Technology Shenzhen518060 China Central China Normal University College of Physical Science and Technology Department of Electronics and Information Engineering Wuhan430079 China Harbin Institute of Technology School of Electronics and Information Engineering Shenzhen518055 China Pengcheng Laboratory Research Center of Networks and Communications Shenzhen518060 China Hunan Institute of Science and Technology School of Information Science and Engineering Yueyang414006 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Jishou University School of Communication and Electronic Engineering Jishou416000 China Shenzhen Technology University College of Big Data and Internet Shenzhen518118 China Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China

A novel digital semantic communication (D-SemCom) framework is proposed to enhance the adaptability and goodput of multi-user-multiple-input multiple-output (MU-MIMO) orthogonal frequency division multiplexing (OFDM) systems by integrating the non-orthogonal superposition pilot (NOSIP) scheme. However, this introduces challenges, such as inter-user interference, which limit the performance of traditional signal processing methods. To address these challenges, we propose SANet, which realizes the nonlinear mapping of received signals to log-likelihood ratios. SANet leverages a common subspace and a multi-head self-attention mechanism to effectively suppress interference and optimize signal decoding performance. Additionally, SANet addresses the coupling between the semantic encoder-decoder and the channel environment, reducing the dependency on channel variations and enabling the system to adapt more flexibly to different channel and data scenarios. We also introduce an adaptive data augmentation strategy that dynamically adjusts the data representation based on channel conditions, further enhancing the reliability and performance of D-SemCom. Numerical results show that: 1) SANet improves the goodput of D-SemCom by 7.01% compared to traditional approaches;2) the goodput of D-SemCom is improved by 37.15% with the NOSIP scheme compared to the orthogonal pilot scheme;and 3) the effectiveness of the adaptive data augmentation strategy in enhancing D-SemCom performance is validated. © 2025 IEEE.

关键词： Frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

A short-term output power prediction model of wind power based on deep learning of grouped time series

引用

European Journal of Electrical engineering 2020年第1期22卷 29-38页

作者： Wang, Yongsheng Gao, Jing Xu, Zhiwei Li, Leixiao College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot010018 China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application for Agriculture and Animal Husbandry Hohhot010018 China College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service Hohhot010080 China Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China

The output power prediction of wind power plants is an important guarantee to improve the utilization rate of wind energy and reduce wind curtailment. However, due to the strong randomness of wind energy, the ultra-short-term prediction accuracy of wind power output is poor. In view of the problem above, a prediction model based on deep learning of grouped time series (LW-CLSTM) was proposed in this paper. Based on this model, the authors attempted to explore a prediction method of wind power output. For this, first the multivariate data of wind power was fused, cleaned, dimension-reduced, and standardized, and the time period characteristics of the output power itself were extracted. Afterwards, it proposes a time sliding window (TSW) algorithm, and constructs a neural network input data set. Then a deep neural network prediction model combining the Convolutional Neutral Network (CNN) and Long-Short Term Memory (LSTM) was established, and the regression evaluation criteria for output power forecast accuracy in wind power production were designed, to compare the proposed model with four other prediction models. Finally, the experiments on the TensorFlow platform using real data show that this model has better prediction accuracy than the other four models, reaching a prediction accuracy rate of 92.5%, which verified the effectiveness of this prediction method. © 2020 International Information and engineering Technology Association. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Adaptive layer-wise personalized federated learning via dual delay update in future communication networks

引用

computer Communications 2025年 239卷

作者： Xu, Haowen Mao, Yingchi Chen, Si Rong, Yi Muazu, Tasiu He, Xiaoming College of Computer Science And Software Engineering Hohai University No. 8 Focheng West Road Jiangning District Nanjing211100 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing210098 China China Huaneng Group Co. Ltd Beijing100000 China College of Internet of Things Nanjing University of Posts and Telecommunications Nanjing210003 China

The future communication networks refers to large-scale mass-connected networks consisting of billions of cloud, edge, and end devices, which are expected to support the ever-growing communication demands. In the future communication networks, billions of end devices generate massive amount of data that needs to be processed and analyzed (e.g., model training). Artificial Intelligence of Things (AIoT) is a groundbreaking technology that leverages artificial intelligence models to process and analyze data generated by a large number of internet of things devices. As an emerging AIoT method, personalized Federated Learning (pFL) has emerged prominently in distributed model training using massive data from the future communication networks. However, it is challenging to accomplish high-performance and communication-efficient model training by existing pFL methods in the future communication networks, due to the following limitations. a) Dynamic role differences in each layer of a multi-layer model are neglected, leading to poor accuracy in customized models deployed on end devices. b) Owing to numerous end devices in the future communication networks, the communication frequency between a cloud server and end devices is extremely high in each communication round, resulting in expensive communication cost. To solve these two limitations, this paper presents a novel pFL framework for distributed model training in the future communication networks, called Adaptive Layer-wise personalized Federated Learning via Dual Delay Update (ALpFLDDU). First, in end devices, a layer-wise aggregation scheme based on an adaptive weight calculation mechanism is designed to capture the dynamic role differences of model layers. Second, in each communication round, we develop a dual delay update strategy to reduce communication frequency between a cloud server and end devices while ensuring model performance. Simulation experiments on text and image classification datasets are conducted. Th

关键词： Internet of things

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：