检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

ANFIS and SA Based Approach to Prediction, Scheduling, and Performance Evaluation for Semiconductor Wafer Fabrication

引用

Chinese Journal of Electronics 2023年第1期22卷 25-30页

作者： Zhengcai Cao Huidan Zhao Yongji Wang College of Information Science and Technology Beijing University of Chemical Technology Beijing China State Key Laboratory of Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

In this paper, an optimized mechanism for Semiconductor wafer fabrication (SWF) by integrating the Adaptive neuro-fuzzy inference system (ANFIS) with Simulated annealing (SA) algorithm is proposed. In this approach, aiming to solve the rush order problem which significantly affect the cycle time and impact the Work in process (WIP) of lots due to the high priority, we build an ANFIS based prediction model which will be embedded into releasing to forecast product codes and quantities of the contingent rush orders. Then a scheduler based on SA algorithm is constructed, the coding of which represents a combination of scheduling policies, including lot releasing policies, dispatching rules, batching rules and settingup rules. When the SA finished its optimization process, an optimal scheduling policy is produced. By using the proposed approach, we will find that the system can be optimized to a large extent and give a better performance.

关键词： Semiconductor device modeling Job shop scheduling System performance Optimal scheduling Simulated annealing Predictive models Semiconductor device manufacture

来源：评论

学校读者我要写书评

暂无评论

Scale-Aware Cnn for Crowd Density Estimation and Crowd Behaviour Analysis

SSRN

引用

SSRN 2022年

作者： Sharma, Vipul Mir, Roohie Naaz Singh, Chandrapal Department of Computer Science Engineering and Information Technology Jaypee Uuiversity of Information Technology Waknaghat India Department of Computer Science and Engineering National Institute of Technology Srinagar India Xsyss Software Technologies Bengaluru India

Visual surveillance is a highly demanded system in various real-time applications for civil and military sectors. For huge gatherings such as rallies and stadiums, crowd monitoring becomes a tedious task. Moreover, crowd density estimation also plays an important role to improve the performance of crowd monitoring system. Several techniques have been presented for crowd counting or density estimation and crowd behaviour analysis. The crowd scenes contain noise, occlusion, cluttered environment which creates complexity to analyze the crowd behaviour. To overcome the challenges of crowd monitoring, we present a combined solution to perform the crowd density estimation and crowd behaviour analysis. The crowd density estimation is carried out by developing a new CNN based architecture which considers scale information and overcome the issues of scale *** order to deal with this issue of scale variation, we introduce a scale-aware attention module where multiple branches of self-attention module are concatenated to improve the scale variation realization. Further, we present the crowd behaviour analysis model which uses motion map and energy level distribution based features to detect the abnormal crowd behaviour. The comparative study shows the proposed approach achieves better performance © 2022, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

APPLE-MASNUM: Accelerating parallel processing for lightweight expansion of MASNUM on a single multi-GPU node

引用

Ocean Modelling 2025年 196卷

作者： Lou, Qi Wu, Changmao Dong, Changming Feng, Xingru Xia, Yuanyuan Liu, Li Xu, Zhengwei Gao, Xu Sun, Meng Yin, Xunqiang Institute of Software Chinese Academy of Sciences Beijing China School of Marine sciences Nanjing University of Information Science and Technology Nanjing China CAS Key Laboratory of Ocean Circulation and Waves Institute of Oceanology Chinese Academy of Sciences Qingdao China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China College of Computer and Information Engineering Henan Normal University Xinxiang China National Supercomputing Center in Zhengzhou Zhengzhou China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China First Institute of Oceanography Ministry of Natural Resources Qingdao China Ministry of Natural Resources Qingdao China

The Marine science and Numerical Modeling (MASNUM) system, developed for oceanic wave forecasting, play an important role in marine disaster prevention and maritime activities. However, its application is hampered by the requirement of large computing resources. To overcome these barriers, we have implemented an accelerating parallel processing for lightweight expansion of MASNUM (APPLE-MASNUM) on a single compute node with multiple GPUs. In initiating our approach, the mathematical-physics equations of the MASNUM system are thoroughly analyzed to pinpoint the primary computational bottlenecks. This study then transforms MASNUM from a multi-process MPI program into a preliminary GPU-compatible algorithms. Subsequently, the paper proposes an optimization strategy for two-dimensional four-point stencil computations. Following this, an optimization method for overlapping computation with communication is introduced. Finally, a refined data layout scheme tailored for GPUs is designed and implemented. Three numerical experiments with five-day wave forecasts demonstrated that compared to single-core MASNUM, the acceleration ratios of the framework presented in this study are 49.29-fold, 62.58-fold, and 65.74-fold, respectively. This considerable performance boost highlights the efficiency of the lightweight APPLE-MASNUM framework introduced in this research. This signifies the first implementation and optimization of the MASNUM model on a GPU-based heterogeneous platform. © 2025 Elsevier Ltd

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

A Correlation And Order-Aware Rule Learning Method For Knowledge Graph Reasoning

A Correlation And Order-Aware Rule Learning Method For Knowl...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yuefeng He Yang He Xu Zheng Bei Hui Bin Tian Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu Naval University of Engineering Wuhan

Mining high-quality logical rules is crucial as they can provide beneficial interpretability for predictions. Recent methods that incorporate logical rules into learning tasks have been proven to yield high-quality logical rules successfully. However, existing methods either rely on the rule instances observed to support rule mining, or simply embed the rule head and the rule body to learn from them. Additionally, they can not fully utilize the rich semantic information contained in logical rules and overlook the intrinsic correlations between all relations within the domain. In this paper, we propose a model called Correlation and order-Aware Rule Learning (CARL) that captures deeper semantic information in rules by allowing relations to be co-aware of each other and paying attention to logical sequence sensitivity. CARL utilizes semantic consistency between the rule body and rule head as its learning objective, continuously introducing more semantic information and logically simplifying the rule body while considering logical sequence sensitivity. We explored the internal correlations between domain relations and used the thought of knowledge distillation to simplify modules so that relations in CARL can share or perceive each other’s information or state efficiently. Experiments on link prediction tasks have demonstrated that CARL can learn higher-quality rules and yield state-of-the-art results on four popular public datasets. https://***/burning5112/CARL

关键词：

来源：评论

学校读者我要写书评

暂无评论

M-CNN-RF: A hybrid deep learning model for accurate pediatric skeletal age estimation using hand bone radiographs

引用

Alexandria engineering Journal 2025年 129卷 289-301页

作者： Hazrat Bilal Yibin Tian Inam Ullah Sahil Garg Bong Jun Choi Mohammad Mehedi Hassan College of Mechatronics and Control Engineering Shenzhen University Shenzhen 518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen 518060 China Department of Computer Engineering Gachon University Seongnam 13120 Republic of Korea École de Technologie Supérieure Montreal QC H3C1K3 Canada Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India School of Computer Science and Engineering Soongsil University Seoul Republic of Korea Department of Information Systems College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia

Precise and accurate skeletal age estimation using medical imaging is a pivotal and challenging task in the healthcare sector, particularly for identifying potential bone growth issues in infants and newborns. Therefore, this study addresses the pervasive challenges associated with assessing bone abnormalities in pediatric patients, including injuries and infections. Given the importance of early and precise detection of skeletal development, a novel hybrid model is proposed that integrates a modified convolutional neural network (M-CNN) with a robust machine learning (ML) model, specifically random forest (RF), resulting in the M-CNN-RF framework. This model is designed to enhance pediatric bone health assessment by providing an effective method for skeletal age estimation. The M-CNN-RF model is tailored to accurately evaluate hand bone maturation, overcoming the inherent difficulties in skeletal age assessment. The model utilizes the bone age dataset from the Radiological Society of North America that includes 14,236 left-hand radiological images, focusing on the development of a robust model for a precise evaluation based on hand skeleton guidelines. In addition, to enhance the prediction and generalization of the model, data augmentation techniques were employed to increase the size of the dataset. The M-CNN-RF exhibits exceptional performance using numerous performance measures, achieving an accuracy of 97% and precision and recall exceeding 94%. In addition, the model reaches an F1 score of 97%, highlighting the ability of the model to ensure a balance between precision and recall. Furthermore, low mean absolute error (MAE) and mean square error (MSE) values of 0.0141 and 0.0327, respectively, were computed for the proposed model, which demonstrates its notable efficacy in predicting skeletal age. The findings of this study not only contribute valuable information for clinical applications but also underscore the potential of the adopted approach to address th

关键词： Machine learning Pediatric bone health assessment Bone X-ray images Modified-CNN model Hybrid M-CNN-RF model Skeletal age estimation

来源：评论

学校读者我要写书评

暂无评论

TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypes

TSEML: A task-specific embedding-based method for few-shot c...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ran Su Rui Shi Hui Cui Ping Xuan Chengyan Fang Xikang Feng Qiangguo Jin School of Computer Software College of Intelligence and Computing Tianjin University Tianjin China School of Software Northwestern Polytechnical University Shaanxi China Department of Computer Science and Information Technology La Trobe University Melbourne Australia Department of Computer Science School of Engineering Shantou University Guangdong China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Molecular subtyping of cancer is recognized as a critical and challenging upstream task for personalized therapy. Existing deep learning methods have achieved significant performance in this domain when abundant data samples are available. However, the acquisition of densely labeled samples for cancer molecular subtypes remains a significant challenge for conventional data-intensive deep learning approaches. In this work, we focus on the few-shot molecular subtype prediction problem in heterogeneous and small cancer datasets, aiming to enhance precise diagnosis and personalized treatment. We first construct a new few-shot dataset for cancer molecular subtype classification and auxiliary cancer classification, named TCGA Few-Shot, from existing publicly available datasets. To effectively leverage the relevant knowledge from both tasks, we introduce a task-specific embedding-based meta-learning framework (TSEML). TSEML leverages the synergistic strengths of a model-agnostic meta-learning (MAML) approach and a prototypical network (ProtoNet) to capture diverse and fine-grained features. Comparative experiments conducted on the TCGA FewShot dataset demonstrate that our TSEML framework achieves superior performance in addressing the problem of few-shot molecular subtype classification.

关键词： Metalearning Deep learning Knowledge engineering Medical treatment Benchmark testing Bioinformatics Cancer

来源：评论

学校读者我要写书评

暂无评论

A Stylometric Dataset for Bengali Poems 22

A Stylometric Dataset for Bengali Poems

引用

Proceedings of the 2022 6th International Conference on Natural Language Processing and information Retrieval

作者： Mirza Kamrul Bashar Shuhan Rupasree Dey Sourav Saha Md Shafa Ul Anjum Tarannum Shaila Zaman Software Research and Engineering bKash Limited Bangladesh Computer Science Oregon State University United States of America Business Administration Shahjalal University of Science and Technology Bangladesh Engineering Progoti Systems Limited Bangladesh Computer & Information Science SUNY Polytechnic Institute United States of America

ISBN: (纸本)9781450397629

Poetry is a form of literature that conveys feelings using different styles, aesthetics, and rhythms. The Bengali language has an enriched collection of poems. Every poet has an individual style of expressing their thoughts and emotions. However, stylometric research in this branch of the Bengali language is still in its early stage of development. In this paper, we have presented a stylometric dataset, which has 6,070 poems of 137 poets stored in the textual format. To the best of our knowledge, this is the first stylometric dataset for Bengali poems which will add an extra dimension to the expanding research arena of the Bengali language. To explore the usability of this dataset, we developed poem genre classifiers using deep learning that can classify these poems. Performance analysis of some deep learning classifiers has been presented in addition to classification. The classifiers include GRU and CNN. Among these two, GRU showed better performance by 91.48 in terms of the F1-score. The dataset will be publicly available at https://***/shuhanmirza/Bengali-Poem-Dataset after publishing this article.

关键词： Bengali Poems Corpora Datasets Language Resources Natural Language Processing Stylometric Datasets

来源：评论

学校读者我要写书评

暂无评论

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

arXiv

引用

arXiv 2025年

作者： Li, Jiahe Zhang, Jiawei Bai, Xiao Zheng, Jin Zhou, Jun Gu, Lin School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Jiangxi Research Institute Beihang University China School of Information and Communication Technology Griffith University Australia RIKEN AIP Japan The University of Tokyo Japan

Despite exhibiting impressive performance in synthesizing lifelike personalized 3D talking heads, prevailing methods based on radiance fields suffer from high demands for training data and time for each new identity. This paper introduces InsTaG, a 3D talking head synthesis framework that allows a fast learning of realistic personalized 3D talking head from few training data. Built upon a lightweight 3DGS person-specific synthesizer with universal motion priors, InsTaG achieves high-quality and fast adaptation while preserving high-level personalization and efficiency. As preparation, we first propose an Identity-Free Pre-training strategy that enables the pre-training of the person-specific model and encourages the collection of universal motion priors from long-video data corpus. To fully exploit the universal motion priors to learn an unseen new identity, we then present a Motion-Aligned Adaptation strategy to adaptively align the target head to the pre-trained field, and constrain a robust dynamic head structure under few training data. Experiments demonstrate our outstanding performance and efficiency under various data scenarios to render high-quality personalized talking heads. Project page: https://***/InsTaG/ . Copyright © 2025, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Improved Dingo Optimization Algorithm for Human-robot Collaborative U-shaped Disassembly Line Balancing Problem

Improved Dingo Optimization Algorithm for Human-robot Collab...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jialong Li XiWang Guo Jiacun Wang ShuJin Qin Liang Qi Qi Kang Information and Control Engineering Liaoning Petrochemical University Fushun China Computer Science and Software Eng. Monmouth University Wes Long Branch New Jersey USA Economics and Management Shangqiu Normal University Shangqiu China Computer Science and Technology Shandong University of Science and Technology Qingdao China Electrical and Computer Engineering New Jersey Institute of Technology Newark USA

ISBN: (数字)9798350376739

ISBN: (纸本)9798350376746

There is increasing attention on remanufacturing, with the primary focus in the industry on recovering reusable products to generate profit. In the process of optimizing remanufacturing, addressing the balance issue in the operation of the disassembly line is crucial. Therefore, this study proposes the use of an improved Dingo Optimization Algorithm (IDOA) and designs a mathematical model for human-robot collaboration to explore how to achieve higher profits under these conditions. Finally, the improved IDOA is experimentally compared with the commercial optimization solver CPLEX and another intelligent optimization method—the Battle Royale Optimization (BRO). The results demonstrate that this method offers high quality and efficiency.

关键词： Industries Human-robot interaction Collaboration Mathematical models Social intelligence Optimization

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：