检索结果-内蒙古大学图书馆

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

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

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

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

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gao, Shihao Li, Caoshuo Mao, Cunli Zhang, Xulong Qu, Xiaoyang Jin, Taisong Wang, Jianzong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China Ping An Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350368741

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph's semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches. © 2025 IEEE.

关键词： Contrastive learning Graph representation Self-supervised learning

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

A Novel Grades Prediction Method for Undergraduate Students by Learning Explicit Conditional Distribution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4837-4848页

作者： Zhang, Na Liu, Ming Wang, Lin Liu, Shuangrong Sun, Runyuan Yang, Bo Zhu, Shenghui Li, Chengdong Yang, Cheng Cheng, Yuhu China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Shandong Key Laboratory of Intelligent Buildings Technology Jinan250101 China University of Jinan Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan250022 China Quan Cheng Laboratory Jinan250100 China Shandong Jianzhu University Shandong Key Laboratory of Intelligent Buildings Technology Jinan250101 China Shandong Jianzhu University School of Information and Electrical Engineering Jinan250101 China Ministry of Education Engineering Research Center of Intelligent Control for Underground Space Xuzhou221116 China

educational data mining (EDM) offers an effective solution to predict students' course grades in the next term. Conventional grade prediction methods can be viewed as regressing an expectation of the probability distribution of the student's grade, typically called single-value grade prediction. The reliable prediction outcomes of these methods depend on the complete input information related to students. However, next-term grade prediction often encounters the challenge of incomplete input information due to the inaccessibility of future data and the privacy of data. In this scenario, single-value grade prediction struggles to assess students' academic status, as it may not be represented and assessed by relying on a singular expectation value. This limitation increases the risk of misjudgment, and may lead to errors in educational decision-making. Considering the challenge of collecting complete input information, we shift from traditional single-value predictions to forecasting the explicit probability distribution of the course grade. The probability distribution of the grade can assess the students' academic status by providing probabilities corresponding to all possible grade values rather than relying solely on an expectation value, which offers the foundation to support the educators' decision-making. In this article, the course grade distribution prediction (CGDP) model is proposed, aiming to estimate an explicit conditional probability distribution of course grades in the next term. This model can identify at-risk students, offering comprehensive decision-making information for educators and students. To ensure precise distribution predictions, a calibration method is also employed to improve the alignment between predicted and actual probabilities. Experimental results verify the effectiveness of the proposed model in early grade warning for undergraduates, based on real university data. © 2020 IEEE.

关键词： Probability distributions

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：