检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaowei Wang Jungang Han Ben Li Xiaoying Pan Hui Xu School of Computer Science Xi’an University of Posts and Telecommunications Xi’an China School of Computer Science Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligence Processing Xi’an China Life Singularity (Beijing) Technology Co. LTD Beijing Beijing China

ISBN: (纸本)9781665429825

Classifying diseases in electronic medical records into corresponding ICD codes requires not only a large amount of medical knowledge but also a large number of coders, which is time-consuming and labor-consuming. Therefore, automatic coding is of great significance. This paper aims to build a deep learning model for automatic ICD-10 coding from a batch of Chinese electronic medical records. The data enhancement, convolutional neural network, attention mechanism, and the gating residual network proposed by the author were used to code ICD code corresponding to the distribution of medical record information by supervised learning. The benchmark model and ablation model were tested on a data set of Chinese electronic medical records. The effectiveness of the proposed modules, such as feature aggregation, multi-head attention mechanism, dilated convolution, and gating residuals, was verified. In the automatic ICD coding task for 104 diseases, the accuracy of the proposed method is 91.71%, and the F1-Score is 92.11%. 1

关键词： Biological system modeling Supervised learning Neural networks Logic gates Encoding data models Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Deep learning for depression recognition with audiovisual cues: A review

arXiv

引用

arXiv 2021年

作者： He, Lang Niu, Mingyue Tiwari, Prayag Marttinen, Pekka Su, Rui Jiang, Jiewei Guo, Chenguang Wang, Hongyu Ding, Songtao Wang, Zhongmin Pan, Xiaoying Dang, Wei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Beijing100190 China Beijing100049 China Department of Computer Science Aalto University Espoo Finland School of Foreign Languages Northwest University Shaanxi Xi'an China School of Electronic Engineering Xi'an University of Posts and Telecommunications Xi'an China School of Electronics and Information Northwestern Polytechnical University Shaanxi Xi'an China Shaanxi Mental Health Center Shaanxi Xi'an710061 China

With the acceleration of the pace of work and life, people have to face more and more pressure, which increases the possibility of suffering from depression. However, many patients may fail to get a timely diagnosis due to the serious imbalance in the doctor-patient ratio in the world. Promisingly, physiological and psychological studies have indicated some differences in speech and facial expression between patients with depression and healthy individuals. Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection. To sort out and summarize these works, this review introduces the databases and describes objective markers for automatic depression estimation (ADE). Furthermore, we review the deep learning methods for automatic depression detection to extract the representation of depression from audio and video. Finally, this paper discusses challenges and promising directions related to automatic diagnosing of depression using deep learning technologies. © 2021, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

On the connectivity of highly dynamic wireless sensor networks in smart factory

On the connectivity of highly dynamic wireless sensor networ...

引用

2019 International Conference on networking and network Applications, NaNA 2019

作者： Gao, Cong Wang, Zhongmin Chen, Yanping School of Computer Science and Technology Xi'an China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China Xi'An University of Posts and Telecommunications Xi'an China

ISBN: (纸本)9781728126296

With the development of smart manufacturing in Industry 4.0, large amount of heterogeneous data are generated from multiple sources. Various data processing techniques can be applied to these data for the purpose of extracting potential information about the status of the manufacturing network. Thus, data are valuable to the analysis and adjustment of the manufacturing processes. Due to the diversity of products, assembly lines and manufacturing processes are highly dynamic. In view of the flexible deployment of wireless sensor networks, they have been widely deployed to conduct data collection. However, due to the limited radio range of a wireless sensor node, the connectivity of a highly dynamic wireless sensor network is a key issue. In this paper, we analyzed the connectivity in a wireless sensor network and accorded three types of connectivity. Then, we developed two network connectivity models from the perspective of one dimension and two dimensions. The degrees of connectivity for both two nodes and the network are elaborated. Finally, the relation between the number of sink nodes and the average degree of connectivity of the network is analyzed based on experimental results. © 2019 IEEE.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised learning for textbook question answering

TechRxiv

引用

TechRxiv 2021年

作者： Ma, Jie Chai, Qi Huang, Jingyue Liu, Jun You, Yang Zheng, Qinghua National Engineering Lab for Big Data Analytics School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The High Performance Computing for Artificial intelligence Lab Department of Computer Science National University of Singapore 117417 Singapore

Textbook Question Answering (TQA) is the task of answering diagram and non-diagram questions given large multimodal contexts consisting of abundant text and diagrams. Deep text understandings and effective learning of diagram semantics are important for this task due to its specificity. In this paper, we propose a Weakly Supervised learning method for TQA (WSTQ), which regards the incompletely accurate results of essential intermediate procedures for this task as supervision to develop Text Matching (TM) and Relation Detection (RD) tasks and then employs the tasks to motivate itself to learn strong text comprehension and excellent diagram semantics respectively. Specifically, we apply the result of text retrieval to build positive as well as negative text pairs. In order to learn deep text understandings, we first pre-train the text understanding module of WSTQ on TM and then fine-tune it on TQA. We build positive as well as negative relation pairs by checking whether there is any overlap between the items/regions detected from diagrams using object detection. The RD task forces our method to learn the relationships between regions, which are crucial to express the diagram semantics. We train WSTQ on RD and TQA simultaneously, i.e., multitask learning, to obtain effective diagram semantics and then improve the TQA performance. Extensive experiments are carried out on CK12-QA and AI2D to verify the effectiveness of WSTQ. Experimental results show that our method achieves significant accuracy improvements of 5.02% and 4.12% on test splits of the above datasets respectively than the current state-of-the-art baseline. We have released our code on https://***/dr-majie/WSTQ. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Image Captioning Method Based on Generative Adversarial networks 21

An Efficient Image Captioning Method Based on Generative Adv...

引用

Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition

作者： Lin Zhenxian Feng Feirong Yang Xiaobao Ding Chen School of Science Xi'an University of Posts and Telecommunications China School of Telecommunication and Information Engineering Xi'an University of Posts and Telecommunications China School of Computer Science and Technology Northwestern Polytechnical UniversityChina. China and School of Computer Science and TechnologyXi'an University of Posts and Telecommunications China School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsChina China and Shaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'an University of Posts and Telecommunications China

ISBN: (纸本)9781450384087

Image captioning is usually based on the mainstream encoder-decoder framework, the accuracy of the encoders and the generation capability of the decoders directly affect the quality of image captions. But no matter how the encoders and the decoders are combined, the generated captions will only imitate the ground-truth captions, and its diversity is suppressed. To generate more accurate and diverse captions while exploring the impact of different encoder-decoder frameworks for the quality of the generated captions, we conducted an exploration of an efficient image captioning method based on GAN. Specifically, we use ResNet152, EfficientNet-B0, and EfficientNet-B2 as the encoders to extract image features, GRU or Transformer as the decoders to generate captions, respectively. Based on MS COCO2014 dataset, a large number of experiment results show that the EfficientNet-B2+GRU framework has best performance, training time is reduced, BLUE-4 score increases by 0.6, parameters reduce by 0.66 million, which can be used as an efficient encoder-decoder framework for generating diverse captions.

关键词： Decoder Encoder Generative Adversarial networks Image captioning

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Model Update Object Tracking Algorithm based on DenseNet Features

An Adaptive Model Update Object Tracking Algorithm based on ...

引用

International Conference on networking and network Applications (NaNA)

作者： Sugang Ma Lei Zhang Lei Pu Xiaobao Yang Zhiqiang Hou Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an shaanxi China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an shaanxi China School of Information and Navigation Air Force Engineering University Xi'an shaanxi China

ISBN: (数字)9781728189543

ISBN: (纸本)9781728189550

In order to further improve the ability to deal with complex scenes, a visual tracking algorithm based on DenseNet features and model adaptive updating is proposed. Aiming to improve the feature representation ability of correlation filtering algorithm, a more discriminative DenseNet model is used as feature extractor. Meanwhile, in order to improve the long-term tracking performance, an adaptive model update strategy is proposed. The average peak correlation energy (APCE) based on response map is used to judge and evaluate the tracking result and the model is updated only when the confidence is high. The experimental results show that the proposed algorithm achieves higher success rate and accuracy compared to the other five related algorithms, and improves the robustness of object tracking in complex scenes such as occlusion and deformation.

关键词： Adaptation models Visualization Correlation Target tracking Feature extraction Object tracking Strain

来源：评论

学校读者我要写书评

暂无评论

Edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers

引用

Cleaner Engineering and Technology 2025年 27卷

作者： Shuaiyin Ma Yichun Cao Yang Liu School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an 710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an 710121 China Shaanxi Union Research Centre of University and Enterprise for 5G+ Industrial Internet Communication Terminal Technology Xi'an University of Posts and Telecommunications Xi'an 710121 China Department of Management and Engineering Linköping University SE-581 83 Linköping Sweden Industrial Engineering and Management University of Oulu 90570 Oulu Finland

Within the context of cleaner production, enhancing energy efficiency and sustainability has emerged as a central focus in supercomputing center development. To address the challenges in predicting energy consumption, this study proposes an architecture of edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers. This architecture combines time-series generative adversarial network (TimeGAN) for data augmentation with the neural basis expansion analysis for time series (N-BEATS) for prediction, providing a robust solution for accurate energy consumption prediction. TimeGAN enhances the training dataset by generating high-quality synthetic time-series data, effectively mitigating issues of data sparsity and imbalance. N-BEATS, with its modular architecture and strong adaptability to temporal data, ensures precise predictions by capturing both global trends and local variations in energy usage. Experimental results demonstrate the effectiveness of the proposed architecture, exhibiting superior performance across key metrics when compared to traditional models. Specifically, the RMSE of TimeGAN-N-BEATS reduced by more than 8 %, the MSE decreased by over 18 %, and the R 2 reached 97.31 %, outperforming baseline models such as long short-term memory and gated recurrent unit, and their attention-enhanced variants. This study highlights the potential of integrating generative and predictive models to optimize energy efficiency in liquid cooling systems, offering valuable insights for sustainable supercomputing operations.

关键词： Edge computing Liquid cooling system N-BEATS Supercomputing centers TimeGAN

来源：评论

学校读者我要写书评

暂无评论

XTQA: Span-Level Explanations for Textbook Question Answering

arXiv

引用

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks

来源：评论

学校读者我要写书评

暂无评论

Distance variety preserving hashing for large-scale retrieval

Distance variety preserving hashing for large-scale retrieva...

引用

作者： Zhai, Sheping School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an710121 China

Hashing techniques have been seen huge adoption in large-scale retrieval owing to the computational and storage efficiencies of binary codes. However, the binary codes might not preserve the semantic similarity powerfully and lead to poor accuracy. To evade binary limitation but remain hashing superiority, this paper introduces a novel asymmetric hashing framework for distance variety preserving, which yields preferable performance via real-valued query and multi-valued database with shorter code length. Concretely, a binary sparse representation is proposed for multivalued database encoding to make computation and storage complexity tolerable. By exploiting the supervised information, we learn a projective matrix that project data onto a sub-space in which the similarity between realvalued query and multi-valued database can be measured. Due to the discrete constraints, for different discrete variables, we present different meticulous discrete solutions for their sub-problems. Exhaustive experiments on three multilabel datasets demonstrate our approach outperforms most state-of-the-art hashing methods. © 2018 John Wiley & Sons, Ltd.

关键词： database systems

来源：评论

学校读者我要写书评

暂无评论

Edge-cloud cooperation driven surface roughness classification method for selective laser melting

引用

Advanced Engineering Informatics 2025年 66卷

作者： Ma, Shuaiyin Huang, Yuming Liu, Yang Yan, Zhiqiang Lv, Jingxiang Cai, Wei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an710121 China Shaanxi Union Research Centre of University and Enterprise for 5G+ Industrial Internet Communication Terminal Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Department of Management and Engineering Linköping University LinköpingSE-581 83 Sweden Industrial Engineering and Management University of Oulu Oulu90570 Finland Key Laboratory of Road Construction Technology and Equipment of MOE Chang'an University Xi'an710064 China College of Engineering and Technology Southwest University Chongqing400715 China

Additive manufacturing (AM) technology is extensively utilized in aerospace and industrial manufacturing. However, parts built using AM are susceptible to spheroidization, porosity, cracks, and poor surface quality, making it difficult to establish an actionable product quality degree. Hence, developing a reasonable method to equate product quality with a new degree and further analyzing the product quality based on these standards has proven effective for enhancing part quality in AM. To achieve this goal, this paper proposes a surface roughness classification method that utilizes surface roughness analysis and sample enhancement. This method leverages edge cloud cooperation to efficiently analyze and integrate data from different sensors, enabling real-time monitoring and adjustment of the manufacturing process. Subsequently, the quality degree analysis system was developed utilizing matter-element extension cloud model. Furthermore, a bidirectional-gated recurrent unit (Bi-GRU) based model for quality classification and recognition has been established, with Wasserstein generative adversarial network (WGAN) employed for sample enhancement to address the issue of imbalanced column classification and to enhance the accuracy of both classification and recognition. Finally, the results obtained from this case study demonstrate through comparative experiments that the proposed method for classifying surface roughness can accurately identify 98% of prepared samples. © 2025 The Authors

关键词： Inspection

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：