检索结果-内蒙古大学图书馆

25th Conference on Computational Natural Language Learning, CoNLL 2021

作者： Chen, Shisong Gu, Binbin Qu, Jianfeng Li, Zhixu Liu, An Zhao, Lei Chen, Zhigang School of Computer Science and Technology Soochow University Suzhou China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China University of California Irvine United States IFLYTEK Research Suzhou China

ISBN: (纸本)9781955917056

Zero pronoun resolution aims at recognizing dropped pronouns and pointing out their anaphoric mentions, while non-zero coreference resolution targets at clustering mentions referring to the same entity. Existing efforts often deal with the two problems separately regardless of their close essential correlations. In this paper, we investigate the possibility of jointly solving zero pronoun resolution and coreference resolution via a novel end-to-end neural model. Specifically, we design a gap-masked self-attention model that encodes gaps and tokens in the same space, where gaps could capture valuable contextual information according to their surrounding tokens while tokens could maintain original sequential information without disturbance. Additionally, we also propose a two-stage interaction mechanism to make full use of the exclusive relationship between zero pronouns and mentions. Our empirical study conducted on the OntoNotes 5.0 Chinese dataset shows that our model could outperform corresponding state-of-the-art approaches on both tasks. © 2021 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Gait data Based on Deep Learning to Predict Multiple Balance Scale Scores

引用

IEEE Sensors Journal 2024年第1期24卷 920-930页

作者： Lin, Chueh-Ho Peng, Chih-Wei Lee, I-Jung Wu, Chi-Ming Lin, Bor-Shing Taipei Medical University International Ph.D. Program in Gerontology and Long-Term Care Taipei City110 Taiwan Taipei Medical University Research Center in Nursing Clinical Practice Wan Fang Hospital Taipei City110 Taiwan Taipei Medical University School of Biomedical Engineering College of Biomedical Engineering Taipei City110 Taiwan Taipei Medical University School of Gerontology and Long-Term Care College of Nursing Taipei City110 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237 Taiwan

Unbalanced walking is increasingly common among older adults;therefore, routinely assessing the balance of older adults is crucial. The traditional method of assessing balance uses scales, requires the supervision of a physical therapist (PT), and is time-consuming. The present study, therefore, proposes a deep learning (DL) model architecture that combines a convolutional neural network (CNN) and a long short-term memory (LSTM) network model to predict the scores of three scales, namely the Berg balance scale (BBS), timed up and go (TUG), and single-leg stance (SLS). The gait data of 15 m of walking were collected from seven inertial measurement units (IMUs) and input into the CNN-LSTM model for evaluation. The BBS and TUG only require the participants to wear two IMUs on the left and right thighs, respectively, for accurate predictions. The mean absolute errors (MAEs) of predicting the scores of the BBS and TUG are 1.2562 and 1.4016 s, respectively;however, the MAE of score predictions of SLS is higher than that of the BBS and TUG, indicating that gait data cannot be used for assessing SLS;moreover, participants only wear one IMU on the right calf for BBS and TUG evaluations, which yield MAEs of 1.4334 and 1.5229 s, respectively. The proposed system can quickly and accurately predict the scores of the BBS and TUG. The proposed model can assist PTs with making clinical decisions. © 2001-2012 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Optimizing Blood Bank Management with Cloud-Hosted Long Short-Term Memory Models for Inventory Forecasting and Utilization 3

Optimizing Blood Bank Management with Cloud-Hosted Long Shor...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Devi, R. Aiyshwariya Sree Southry, S. Rajanarayanan, S. Sekaran, S. Chandra Sivaraman, Audithan Srinivasan, S. R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem India Department of Computer Science and Engineering Tamil Nadu Salem India P.S.V College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Krishnagiri India Department of Information Technology Jafferpur New Delhi India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

This research presents an innovative method for blood bank management using Cloud-based Long Short-Term Memory (LSTM) models for precise inventory forecasting and optimization. The objective of this research is to increase blood bank efficiency by utilizing LSTM models to accurately estimate demand, optimize inventory levels, and enhance overall resource utilization. The system uses cloud computing to provide real-time demand forecasting, minimizing blood waste and assuring a reliable supply for healthcare requirements. LSTM models use historical data to identify long-term trends and variations in blood demand, facilitating accurate inventory forecasting. This predictive system optimizes the allocation process, resulting in improve resource utilization and increased operational efficiency. In compared to traditional techniques, the proposed system provides a more scalable and flexible solution by using cloud technology to provide continuous monitoring and dynamic modifications of inventory levels. It provides a robust framework for management of blood supply and enhancing patient care for improved resource management. Future enhancements may include broadening the system to incorporate real-time multi-source data integration and investigating hybrid machine learning models to better optimize demand forecasts. © 2025 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Image based Crop Monitoring Technologies in Protected Horticulture: A Review

arXiv

引用

arXiv 2024年

作者： Jayasuriya, Namal Guo, Yi Hu, Wen Ghannoum, Oula Hawkesbury Institute for the Environment Western Sydney University Hawkesbury Campus RichmondNSW2753 Australia Centre for Research in Mathematics and Data Science School of Computer Data and Mathematical Sciences Western Sydney University ParramattaNSW2150 Australia School of Computer Science and Engineering The University of New South Wales SydneyNSW2052 Australia

Future food security is a major concern of the 21st century with the growing global population and climate changes. In addressing these challenges, protected cropping ensures food production year-round and increases crop production per land area by controlling environment conditions. Maintaining the growth and health of crops in these facilities is essential to ensure optimum food production. However, this is a laborious work and is currently done manually. Image-based nondestructive plant phenotyping is an emerging research area that reduces the skilled labour cost while enhancing the monitoring of crop growth, health, and identifying phenotype-genotype relations for plant breeding. With the proliferations of protected infrastructures and targeted plants, different technologies and sensor setups are needed for image-based crop monitoring. Conveyor-type plant-to-sensor systems, bench-top or gantry-based systems are commonly found in research facilities focussing on phenotyping of small, relatively short, or movable model plants. This review examines the literature on crop monitoring and phenotyping platforms in both field and protected facilities and explains different camera technologies and their ability to extract different plant traits. The review highlights the future research directions of image-based monitoring of commercial scale protected crops where crops can be relatively tall or vertically supported under semi controlled environments, which presents new challenges and is rarely covered in the literature. © 2024, CC BY.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

VSM: A Versatile Semi-supervised Model for Multi-modal Cell Instance Segmentation 36

VSM: A Versatile Semi-supervised Model for Multi-modal Cell ...

引用

Cell Segmentation Challenge in Multi-Modality High-Resolution Microscopy Images - 36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Cai, Xiaochen Cai, Hengxing Tu, Weiwei Xu, Kele Li, Wu-Jun National Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Nanjing University Nanjing China 4 Paradigm Inc. Beijing China School of Computer National University of Defense Technology Changsha China Center for Medical Big Data Nanjing Drum Tower Hospital Nanjing China

Cell instance segmentation is a fundamental task in analyzing microscopy images, with applications in computer-aided biomedical research. In recent years, deep learning techniques have been widely used in this field. However, existing methods exhibit inadequate generalization ability towards multi-modal cellular images and require a considerable amount of manually labeled data for training. To overcome these limitations, we present VSM, a versatile semi-supervised model for multi-modal cell instance segmentation. Our method delivers high accuracy and efficiency, as verified through comprehensive experiments. Additionally, VSM achieved a top-five ranking in the Weakly Supervised Cell Segmentation category of the multi-modal High-Resolution Microscopy competition. © 2023 SPIE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Image Description Generation Method Based on X-Linear Attention Mechanism 5

Image Description Generation Method Based on X-Linear Attent...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Qiao, Pingan Li, Yuan Shen, Ruixue Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an710121 China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781450396899

Aiming at the problem that existing image description models cannot model high-order multimodal feature interaction, this paper introduces the X-Linear attention mechanism, which uses bilinear pooling and ELU activation function to model high-order feature interaction between multimodal features. At the same time, the X-Linear attention mechanism uses spatial and channel attention mechanisms to enhance the expression ability of the model and the ability to generate image description sentences. The experimental results on the MSCOCO data set show that this method is effective and has a great improvement in each evaluation metric. © 2022 ACM.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Outlier Robust Multivariate Polynomial Regression 32

Outlier Robust Multivariate Polynomial Regression

引用

32nd Annual European Symposium on Algorithms, ESA 2024

作者： Arora, Vipul Bhattacharyya, Arnab Boban, Mathews Guruswami, Venkatesan Kelman, Esty School of Computing National University of Singapore Singapore Department of EECS Department of Mathematics University of California BerkeleyCA United States CSAIL Massachusetts Institute of Technology CambridgeMA United States Department of Computer Science Faculty of Computing & Data Sciences Boston University MA United States

ISBN: (纸本)9783959773386

We study the problem of robust multivariate polynomial regression: let p: Rn → R be an unknown n-variate polynomial of degree at most d in each variable. We are given as input a set of random samples (xi, yi) ∈ [−1, 1]n × R that are noisy versions of (xi, p(xi)). More precisely, each xi is sampled independently from some distribution χ on [−1, 1]n, and for each i independently, yi is arbitrary (i.e., an outlier) with probability at most ρ n log d), where the hidden constant depends on n, if χ is the n-dimensional Chebyshev distribution. The sample complexity is On(d2n log d), if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most O(σ), and the run-time depends on log(1/σ). In the setting where each xi and yi are known up to N bits of precision, the run-time's dependence on N is linear. We also show that our sample complexities are optimal in terms of dn. Furthermore, we show that it is possible to have the run-time be independent of 1/σ, at the cost of a higher sample complexity. © Vipul Arora, Arnab Bhattacharyya, Mathews Boban, Venkatesan Guruswami, and Esty Kelman;licensed under Creative Commons License CC-BY 4.0.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

BERT-based Topic Modeling Approach for Malaria Research Publication

BERT-based Topic Modeling Approach for Malaria Research Publ...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Alam Ahmad Hidayat Rudi Nirwantono Arif Budiarto Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665473286

Malaria is a communicable disease with half of the global population at risk due to its high morbidity and mortality rates. A massive number of studies are dedicated to malaria research, so it plays a key role in formulating the proper prevention strategy and effective malaria treatment. With the overwhelming number of updated publications in the field, an unsupervised text mining approach such as topic modeling may provide an alternative method for the malaria researcher to keep pace with new insights. In this work, we collect metadata of malaria publications from the PubMed database to perform BERT-based topic modeling to find well-defined topics regarding malaria research. The method is largely based on the popular BERTopic pipeline. We compare the performance of three different language models to generate document embeddings from the data. The dimension reduction and the density-based clustering algorithm are used to cluster the embeddings. The topic representation is computed based on the semantic similarity of the class TF-IDF representation. The substance of the resulting topics is then manually annotated based on the top words of each topic. We demonstrate that by merging initial topics into larger topics using hierarchical clustering and manual content-based examination, the evaluated coherence measure can be further improved, thus enhancing the topic's interpretability. Our modeling result is able to extract ten major topics recurring in the malaria research publication published from 2017–2022. The result provides preliminary insight to understand the dynamics and patterns of malaria research over the years

关键词： Text mining Heuristic algorithms Multimedia systems Time series analysis Sociology Semantics Pipelines

来源：评论

学校读者我要写书评

暂无评论

Deep Hashing with Minimal-Distance-Separated Hash Centers

Deep Hashing with Minimal-Distance-Separated Hash Centers

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Liangdao Wang Yan Pan Cong Liu Hanjiang Lai Jian Yin Ye Liu School of Computer Science and Engineering Sun Yat-Sen University Big Data Department Lizhi Inc.

Deep hashing is an appealing approach for large-scale image retrieval. Most existing supervised deep hashing methods learn hash functions using pairwise or triple image similarities in randomly sampled mini-batches. They suffer from low training efficiency, insufficient coverage of data distribution, and pair imbalance problems. Recently, central similarity quantization (CSQ) attacks the above problems by using “hash centers” as a global similarity metric, which encourages the hash codes of similar images to approach their common hash center and distance themselves from other hash centers. Although achieving SOTA retrieval performance, CSQ falls short of a worst-case guarantee on the minimal distance between its constructed hash centers, i.e. the hash centers can be arbitrarily close. This paper presents an optimization method that finds hash centers with a constraint on the minimal distance between any pair of hash centers, which is non-trivial due to the non-convex nature of the problem. More importantly, we adopt the Gilbert-Varshamov bound from coding theory, which helps us to obtain a large minimal distance while ensuring the empirical feasibility of our optimization approach. With these clearly-separated hash centers, each is assigned to one image class, we propose several effective loss functions to train deep hashing networks. Extensive experiments on three datasets for image retrieval demonstrate that the proposed method achieves superior retrieval performance over the state-of-the-art deep hashing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Genetic Algorithm Based on Deep Q-learning in Optimization of Remote Sensing data Discretization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Chen, Qiong Ding, Weiping Hainan Medical University Hainan Academy of Medical Sciences School of Biomedical Information and Engineering Haikou571199 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science Macau999078 China

Feature discretization can improve the processing efficiency of remote sensing big data. However, the distribution of target attribute values is often difficult to ascertain, and there are complex correlations between features, making it extremely difficult to obtain an optimal discretization scheme for remote sensing data. Although feature discretization methods based on evolutionary models can achieve some considerable results, it is difficult to formulate appropriate strategies without prior knowledge as guidance, which makes searching in multidimensional space inefficient and prone to falling into local optima. Therefore, we propose a genetic algorithm based on deep Q-learning (DQLGA) to optimize the discretization scheme of remote sensing data. First, we design a state set in the crossover and mutation stages by balancing the global and local search capabilities of genetic operators to obtain an accurate mapping of states in high-dimensional feature space. Then, we simulate the variation pattern of the optimal discretization scheme by analyzing the distribution of all individuals in the population during the evolution process to construct a reasonable adaptive reward function in reinforcement learning model. Finally, we introduce a pair of deep Q-networks with the same structure by treating the calculation of Q-values as a function fitting problem to fulfil an efficient updating of massive Q-values in state transition. We compare DQLGA with state-of-the-art feature discretization methods on remote sensing data. The experimental results indicate that DQLGA significantly improves the search efficiency of feature discretization methods based on evolutionary models, achieving higher classification accuracy while further reducing the number of breakpoints. © 2024 IEEE.

关键词： Contrastive Learning

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：