检索结果-内蒙古大学图书馆

7th International Conference on Intelligent computing and Signal Processing, ICSP 2022

作者： Yan, Jing Zhou, Shihua Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian China

ISBN: (纸本)9781665478571

Extraction summarization and abstraction summarization have advantages and disadvantages, so how to better combine these two ways has become a difficult problem. To address this challenge, this paper proposed a new fusion method. The major novelty lies in the design of the new method. Wherein our approach, first, use the text structure information and the idea of the K-means algorithm to divide the text into regions, and then the main part and the non-main parts are determined according to the distribution of the subject words. Next, apply information extraction on the main part and text generation on the non-main parts. Finally, the two parts of the summarization are merged according to the sequence of the text. Experimental results show that the quality of the summarization is better than that of extraction summarization and abstraction summarization. In addition, to make the method more targeted in Chinese text processing, the Cw2vec model based on Chinese stroke information is used in the encoding process, and the experiment proves that the quality of summarization can be further improved. © 2022 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Turn-on fluorescence detection of specific inorganic anions by Zr(Ⅳ)-MOF with amino-functional group

引用

Tungsten 2023年第2期5卷 217-224页

作者： Jing Dong Shi-Qing Wang Xiao-Yu Zhang Zi-Qing Huang Xiu-Du Zhang Wei-Yin Sun Coordination Chemistry Institute State Key Laboratory of Coordination ChemistrySchool of Chemistry and Chemical EngineeringNanjing National Laboratory of MicrostructuresCollaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China Scientific Research Institute Nanjing Tech UniversityNanjing 211816China College of Chemistry and Materials Science Key Laboratory of Functional Molecular Solids Ministry of EducationAnhui Laboratory of Molecule-Based MaterialsAnhui Key Laboratory of Functional Molecular SolidsAnhui Normal UniversityWuhu 241002China

Inorganic anions such as phosphates and carbonates are essential in the natural system and it is important for the detec-tion of such *** this work,the fluorescence sensing capacity of Zr(IV)framework with an amino-functional group,namely UiO-66-NH_(2),towards specific inorganic anions was investigated in aqueous *** results revealed that the fluorescence emission intensity of UiO-66-NH2 could be strongly enhanced by phosphate and carbonate anions including HPO_(4)^(2-),H_(2)PO_(4)^(-),PO_(4)^(3-),P_(2)O_(7)^(4-),HCO_(3)^(-)and CO_(3)^(2-),implying its sensing capacity towards phosphate and carbonate ***,fluorescence titration experiments exhibit that the emission intensity enhancement ratio depends linearly on the concentration of anions,suggesting the possibility of quantitative detection of these *** studies suggest that the sensing of UiO-66-NH,towards HPO_(4)^(2-)/PO_(4)^(3-)/P_(2)O_(4)^(-)/HCO_(3)^(-)/CO_(2)-could be ascribed to the collapse of the framework,while that for H_(2)PO_(4)-could be attributed to the adsorption of H,PO4-by UiO-66-NH2 with hydrogen bonding interactions between H,PO4-and the amino group of UiO-66-NH_(2) supported by the different fluorescence response of UiO-66 and UiO-66-NH,towards the anions.

关键词： Zr(IV)framework UiO-66-NH_(2) Anions Sensing Turn-on fluorescence

来源：评论

学校读者我要写书评

暂无评论

Memory-Guided Contrastive and Triplet Separation for Weakly-Supervised Disease Detection

Memory-Guided Contrastive and Triplet Separation for Weakly-...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： She, Jinwen Li, Qiong Ma, Andy J. Sun Yat-sen University Cancer Center Guangzhou China Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Ministry of Education Guangdong Province Key Laboratory of Information Security Technology Key Laboratory of Machine Intelligence and Advanced Computing China

ISBN: (纸本)9798350386226

Weakly-supervised disease detection has the great potential to alleviate the time-consuming and labor-intensive burden of manual annotations in instance level. While existing methods extract normality prototypes encoding normal patterns to improve the detection performance, they may fail to detect subtle anomalies without considering the diverse abnormal patterns. In this paper, we propose to recognize both normal and abnormal patterns for feature representation learning in disease detection based on a dual memory network. To learn discriminative memory banks and classifiers, dual memory loss is incorporated with a feature magnitude separation loss for model training. With the proposed contrastive feature separation loss and triplet feature separation loss, feature discriminability is further improved to obtain a more separable decision boundary. Additionally, we collect a large-scale CT dataset to evaluate lung tumor detection. Extensive experiments on the publicly available PANDA-MIL dataset and the collected LUNG-MIL dataset demonstrate the superiority of our proposed method compared to the state-of-the-art approaches for weakly-supervised disease detection. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Assessment of prediction model of the CPUE of neon flying squid with different sources of remote sensing data

引用

Acta Oceanologica Sinica 2023年第6期42卷 33-38页

作者： Liang Chang Yanli Yang Xinjun Chen Wei Yu Yangdong Li Guiping Feng Yang Zhang College of Marine Sciences Shanghai Ocean UniversityShanghai 201306China State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of OceanographyMinistry of Natural ResourcesHangzhou 310012China National Engineering Research Centre for Oceanic Fisheries Shanghai Ocean UniversityShanghai 201306China Key Laboratory of Sustainable Exploitation of Oceanic Fisheries Resources of Ministry of Education Shanghai Ocean UniversityShanghai 201306China Key Laboratory of Oceanic Fisheries Exploration Ministry of Agriculture and Rural AffairsShanghai 201306China Scientific Observing and Experimental Station of Oceanic Fishery Resources Ministry of Agriculture and Rural AffairsShanghai 201306China

Accurately building the relationship between the oceanographic environment and the distribution of neon flying squid(Ommastrephes bartramii)is very important to understand the potential habitat pattern of ***,when building the prediction model of *** with traditional oceanographic variables(e.g.,chlorophyll a concentration(Chl a)and sea surface temperature(SST))from space-borne observations,part of the important spectrum characteristics of the oceanic surface could be masked by using the satellite data products *** this study,the neglected remote sensing information(i.e.,spectral remote sensing reflectance(Rrs)and brightness temperature(BT))is firstly incorporated to build the prediction model of catch per unit effort(CPUE)of *** from July to December during 2014–2018 in the Northwest Pacific *** show that both the conventional oceanographic variables and the neglected remote sensing data are suitable for building the prediction model,whereas the overall root mean square error(RMSE)of the predicted CPUE of *** with the former is typically less accurate than that with the ***,the Rrs and BT could be a more suitable data source than the Chl a and SST to predict the distribution of ***,highlighting that the potential value of the neglected variables in understanding the habitat suitability of ***.

关键词： Ommastrephes bartramii CPUE prediction remote sensing Rrs BT.

来源：评论

学校读者我要写书评

暂无评论

Performance Verification of Smith Predictor Control Using IMC Scheme via Chemical Reaction Networks and DNA Strand Displacement Reaction 9

Performance Verification of Smith Predictor Control Using IM...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Yao, Jingwang Lv, Hui Xiao, Yijun Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China

ISBN: (纸本)9798350319804

Biochemical process control is often achieved through feedback control strategies for theoretical analysis and optimization of biochemical reaction processes. Here, the design improves the robustness of the biochemical process by taking advantage of the Smith prediction structure and internal mode control within the chemical reaction network theory framework to intervene against the time delays and perturbations present in the biochemical process. First, an IMC representation of Smith prediction is constructed using the presence of parameter rectification of the control method, and then an IMC-MSP control scheme is proposed. A first-order time-lag controlled object is established in the construction of the IMC-MSP control scheme. Besides, CRNs and kinetic representations are established based on the control structure to facilitate the evaluation of the control system performance. In this paper, CRNs representations of parabolic functions as signal inputs are defined for the first time and optimized for stepping signals to facilitate the design and study of biomolecular circuits. Notably, for the CRNs-based IMC-MSP control scheme, on the one hand, numerical simulation experiments are designed to verify the effectiveness of the whole scheme from multiple perspectives of time delays, external perturbations, and filter tuning parameters;on the other hand, using DNA strand displacement is reflected to verify the feasibility of the whole scheme. © 2023 IEEE.

关键词： Chemical reaction networks (CRNs) DNA strand displacement (DSD) Internal model control (IMC control) Smith predictor

来源：评论

学校读者我要写书评

暂无评论

A Feature Distribution Smoothing Network Based on Gaussian Distribution for QoS Prediction

A Feature Distribution Smoothing Network Based on Gaussian D...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Lu, Tongxin Zhang, Xiaohong Wang, Ziliang Yan, Meng Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China Chongqing University School of Big Data and Software Engineering Chongqing China

ISBN: (纸本)9798350304855

With the increasing number of services and their homogenization, the use of Quality of Service (QoS) for recommendations has become necessary. However, existing QoS prediction solutions have limitations in solving the noise and label imbalance problems of dataset, which greatly limit the improvement of QoS prediction accuracy. In this paper, we propose FSNet that contains a feature distribution smoothing module and an improved W-Huber loss function. The feature distribution smoothing module mitigates the effect of noise problem by fitting potential Gaussian distribution of known features with a supervised feedforward neural network. W-Huber loss function mitigates the impact of label imbalance problem on QoS prediction by reweighting the two components of Huber loss function. We conduct extensive experiments on real large-scale QoS dataset, and the results demonstrate that the proposed FSNet method outperforms existing QoS prediction methods. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Incorporating dynamic attention gating mechanism and pre-trained embedding for Chinese clinical named entity recognition

Incorporating dynamic attention gating mechanism and pre-tra...

引用

2023 International Conference on Biomimetic Intelligence and Robotics

作者： Qiu, Zhenming Pan, Anyu Qi, Lin College of Medicine and Biological Information Engineering Northeastern University Shenyang110169 China Engineering Research Center of Medical Imaging and Intelligent Analysis Ministry of Education Shenyang110169 China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang110169 China

Clinical Named Entity Recognition (CNER) serves as a cornerstone in clinical research and healthcare informatics, with its primary goal being the discernment and categorization of clinical terminologies present within Electronic Medical Records (EMRs). While deep learning has significantly improved CNER’s performance, these models still face challenges in identifying rare or unseen entities. Our study unveils an innovative DAGM-BiLSTM-CRF model that seamlessly integrates data-driven deep learning strategies with human knowledge to surmount this limitation. The distinctive features of this model lie in its integration of a pre-trained character embedding layer, adept at encapsulating nuanced semantic variations at the granularity of individual characters. Furthermore, it incorporates a bidirectional Long Short-Term Memory (BiLSTM) layer, proficient in deriving contextually relevant information by traversing the sequence from both endpoints. The most noteworthy aspect of our model is the inclusion of a Dynamic Attention Gating Mechanism (DAGM) that dynamically recalibrates attention weights based on the traits of the input sequence and a Conditional Random Fields (CRF) layer that considers interdependencies among output labels within a sequence. The evaluation was carried out on the CCKS-2017 CNER benchmark dataset to underscore the superiority of our model over existing cutting-edge methods, thereby validating its proficiency in deciphering the intricacies of Chinese electronic medical records. © 2023 The Authors. Published by Elsevier B.V.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Domain Adaptation Model Based on Multi-Level Joint Alignment for Multi-Modal Cardiac Image Segmentation

An Unsupervised Domain Adaptation Model Based on Multi-Level...

引用

2023 International Conference on Biomimetic Intelligence and Robotics

作者： Li, Jiapeng Lv, Yimou Xu, Lisheng Qi, Lin College of Medicine and Biological Information Engineering Northeastern University Shenyang110169 China Engineering Research Center of Medical Imaging and Intelligent Analysis Ministry of Education Shenyang110169 China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang110169 China

Unsupervised Domain Adaptation has greatly boosted the performance of multi-modal medical segmentation when there are only source domain labels and no labels in the target domain. Many previous work relies on Convolutional Neural Networks for distribution or instance alignment, however, the receptive field of CNN makes it overly concerned with texture and local semantic information of images, while losing the global style information and semantic information and lacking relationships between local and global semantics. In order to address these issues, we propose a two-stage, multi-level framework for unsupervised domain adaptation, which consists of an image translation network and a Transformer-based domain adaptation segmentation network, jointly aligning the data distribution in the source and target domains from the image, feature and output level through adversarial learning. Experimental results indicate that our method can achieve satisfactory results and outperform other state-of-the-art medical image segmentation methods. © 2023 The Authors. Published by Elsevier B.V.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Preparation of gradient porous polymer membranes with multifunctionality

RSC Applied Polymers

引用

RSC Applied Polymers 2024年第5期2卷 816-820页

作者： Ji, Weigang Li, Xiaohu Xi, Qi Song, Mengyuan Wu, Xue Song, Pengfei College of Chemistry and Chemical Engineering Key Laboratory of Eco-functional Polymer Materials of the Ministry of Education Key Laboratory of Eco-environmental Polymer Materials of Gansu Province Gansu International Scientific and Technological Cooperation Base of Water-Retention Chemical Functional Materials Northwest Normal University Lanzhou 730070 China

Porous membranes have attracted considerable attention in materials science. It is crucial to develop a simple strategy for multifunctional porous membranes with broad applications. Herein, gradient porous membranes were prepared from a poly(ionic liquid) (PIL) of poly[3-cyanomethyl-1-vinylimidazolium bis(trifluoromethane-sulfonyl)imide] and the natural small molecule of α-thioctic acid (TA) using a combination of solution mixing, ring-opening polymerization (ROP) and post-processing. The resulting membranes of PIL/PTA with gradient pores were confirmed by FT-IR, NMR, Raman, and SEM characterizations. Interestingly, PIL/PTA porous membranes are stimulus-responsive materials with self-healing and UV-blocking properties. It is demonstrated that polymer membranes with solvent-stimulated responsiveness depend mainly on their gradient pore structure, which can be used as a highly sensitive solvent sensor. In addition, self-healing and UV-blocking properties have been developed by combining typical features of PIL and PTA into porous membranes. This work is beneficial for the rational design of multifunctional porous membrane materials to meet existing applications. © 2024 RSC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical fiber integrated photoelectrochemical sensing patch: towards non-invasive blood glucose detection

引用

IEEE Sensors Journal 2025年第11期25卷 18741-18749页

作者： Wen, Xingyue Ge, Zhongxuan Ma, Minghua Yang, Xinghua Wang, Shengjia Tian, Fengjun Liu, Zhihai Zhang, Yu Teng, Pingping Gao, Shuai Zhu, Zheng Zhang, Yang Jones, Adam Zhang, Bo Sivanathan, Sivagunalan Li, Kang Harbin Engineering University Key Laboratory of In-Fiber Integrated Optics Ministry of Education College of Science Harbin150001 China Department of Anesthesiology First Hospital of Harbin Harbin150000 China University of South Wales Faculty of Computing Engineering & Science CF37 1DL United Kingdom Henan Academy of Special Optics Ltd Xinxiang453000 China

In recent years, non-invasive blood glucose detection has received increasing attention. Among them, sweat glucose detection is expected to become an alternative to blood glucose detection due to advantages such as its samples easily to obtain. This study was proposed and preliminarily verified a prototype of photoelectrochemical sensing patch based on an optical fiber modified by ITO/ZnO/polydopamine/glucose oxidase and printed electrode, enabling close contact with human skin. In this innovative design, the optical fiber to serve both as a light transmission medium and a working electrode, while the printed electrode functions as the counter electrode and reference electrode. The electrode materials were characterized by SEM, EDS, XRD and XPS, and the reaction kinetics of the optical fiber electrode studied through SWV, EIS, and Mott-Schottky analysis. A linear relationship was established between the photocurrent and the logarithm of glucose concentration in the concentration range from 10 μM to 1 mM, with a detection limit of 3.5 μM, and a response time of less than 1 s. In addition, the specificity and stability of the sensing patch were evaluated, and an attempt was made to detect real sweat glucose in situ. This work presents a novel prototype for the development of wearable sensors, with promising applications in biochemical analysis and health monitoring. © 2001-2012 IEEE.

关键词： Glucose sensors

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：