检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jemni, Sana Khamekhem Ammar, Sourour Souibgui, Mohamed Ali Kessentini, Yousri Cheddad, Abbas Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia Laboratory of Signals systems Artificial Intelligence and networks Sfax Tunisia Multimedia Information systems and Advanced Computing Laboratory Tunisia Computer Vision Center Computer Science Department Universitat Autònoma de Barcelona Spain Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated training data. However, in the case of historical manuscripts, there is a lack of annotated corpus for training. To handle the data scarcity issue, we investigate the merits of the self-supervised learning to extract useful representations of the input data without relying on human annotations and then using these representations in the downstream task. We propose ST-KeyS, a masked auto-encoder model based on vision transformers where the pretraining stage is based on the mask-and-predict paradigm, without the need of labeled data. In the fine-tuning stage, the pre-trained encoder is integrated into a siamese neural network model that is fine-tuned to improve feature embedding from the input images. We further improve the image representation using pyramidal histogram of characters (PHOC) embedding to create and exploit an intermediate representation of images based on text attributes. In an exhaustive experimental evaluation on three widely used benchmark datasets (Botany, Alvermann Konzilsprotokolle and George Washington), the proposed approach outperforms state-of-the-art methods trained on the same datasets. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Stress Prediction in Higher Education Students Using Psychometric Assessments and AOA-CNN-XGBoost Models

Stress Prediction in Higher Education Students Using Psychom...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Sarthak Sharma Suman Vij RVS Praveen S. Srinivasan Dharmendra Kumar Yadav Raj Kumar V S Management Shri Guru Ram Rai University Dehradun Uttarakhand India School of Management and Commerce Studies Shri Guru Ram Rai University Dehradun Uttarakhand India Digital Engineering and Assurance LTIMindtree Limited Hyderabad Telangana India Department of Advanced Computing Sciences AMET University Chennai Tamilnadu India University Department of Mathematics Lalit Narayan Mithila University Darbhanga Bihar India Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

research backs up the common perception that the years preceding up to college are the most difficult, showing that students report higher levels of discomfort and worse self-esteem during this switch. Positive personality qualities such as optimism, hope, and happiness were examined in this system along with 215 first-semester Israeli university students' ratings of functional impairment, psychological distress, and self-esteem. The three stages that make up this suggested method are data preprocessing, model training, and feature selection. In order to process data that would be infeasible to process without data preprocessing, the data can be adjusted to meet the specifications of each data mining technique. Beginning with different forms of feature classification or aggregation and progressing to individual activity levels, several levels of feature granularity were investigated in order to employ a feature selection technique. The proposed approach used an AOA-CNN-XGBoost for the whole model training phase. This novel method outperforms CNN and AOA with an average accuracy of 89.27%.

关键词： Training Accuracy Data preprocessing Psychology Human factors Switches Predictive models Feature extraction Prediction algorithms Data mining

来源：评论

学校读者我要写书评

暂无评论

BDHT: Generative AI Enables Causality Analysis for Mild Cognitive Impairment

arXiv

引用

arXiv 2023年

作者： Zuo, Qiankun Chen, Ling Shen, Yanyan Ng, Michael Kwok-Po Lei, Baiying Wang, Shuqiang The Hubei Key Laboratory of Digital Finance Innovation The School of Information Engineering China The Hubei Internet Finance Information Engineering Technology Research Center Hubei University of Economics Hubei Wuhan430205 China The School of Information Management Institute of Big Data and Digital Economy Hubei University of Economics Hubei Wuhan430205 China Department of Mathematics Hong Kong Baptist University Hong Kong The School of Biomedical Engineering Shenzhen University Shenzhen518060 China The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Effective connectivity estimation plays a crucial role in understanding the interactions and information flow between different brain regions. However, the functional time series used for estimating effective connectivity is derived from certain software, which may lead to large computing errors because of different parameter settings and degrade the ability to model complex causal relationships between brain regions. In this paper, a brain diffuser with hierarchical transformer (BDHT) is proposed to estimate effective connectivity for mild cognitive impairment (MCI) analysis. To our best knowledge, the proposed brain diffuser is the first generative model to apply diffusion models to the application of generating and analyzing multimodal brain networks. Specifically, the BDHT leverages structural connectivity to guide the reverse processes in an efficient way. It makes the denoising process more reliable and guarantees effective connectivity estimation accuracy. To improve denoising quality, the hierarchical denoising transformer is designed to learn multi-scale features in topological space. By stacking the multi-head attention and graph convolutional network, the graph convolutional transformer (GraphConformer) module is devised to enhance structure-function complementarity and improve the ability in noise estimation. Experimental evaluations of the denoising diffusion model demonstrate its effectiveness in estimating effective connectivity. The proposed model achieves superior performance in terms of accuracy and robustness compared to existing approaches. Moreover, the proposed model can identify altered directional connections and provide a comprehensive understanding of parthenogenesis for MCI treatment. Copyright © 2023, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Freezing dynamics of wetting droplet under a uniform electric field

arXiv

引用

arXiv 2024年

作者： Huang, Jiangxu Li, Hanqing Che, Jiaqi Chai, Zhenhua Wang, Lei Shi, Baochang School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan430074 China Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 China Marine Design & Research Institute of China China The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China School of Mathematics and Physics China University of Geosciences Wuhan430074 China

Electrofreezing is a powerful technique that employs the electric field to control and enhance the freezing process. In this work, a phase-field-based lattice Boltzmann (LB) method is developed to study the electrofreezing process of sessile droplet on a cooled substrate. The accuracy of the present LB method is first validated through performing some simulations of the three-phase Stefan problem, the droplet freezing on a cold wall, and the droplet deformation under a uniform electric field. Then it is used to investigate the effect of an electric field on the freezing of a wetting droplet on a cold substrate, and the numerical results show that the electric field has a significant influence on the freezing time of the droplet mainly through changing the morphology of the droplet. In particular, under the effect of the electric field, the freezing time is increased for the droplet with a prolate pattern, while the freezing time of the droplet with an oblate pattern is decreased. These numerical results bring some new insights on the electrofreezing and provide a valuable guidance for the precise regulation of droplet freezing. Copyright © 2024, The Authors. All rights reserved.

关键词： Wetting

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of Computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

St-Keys: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents

SSRN

引用

SSRN 2023年

作者： Jemni, Sana Khamekhem Ammar, Sourour Souibgui, Mohamed Ali Kessentini, Yousri Cheddad, Abbas Digital Research Center of Sfax B.P. 275 Sakiet Ezzit Sfax3021 Tunisia SM@RTS: Laboratory of Signals systeMs aRtificial Intelligence and neTworkS MIR@CL: Multimedia InfoRmation systems and Advanced Computing Laboratory Computer Vision Center Computer Science Department Universitat Aut`onoma de Barcelona Spain Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated training data. However, in the case of historical manuscripts, there is a lack of annotated corpus for training. To handle the data scarcity issue, we investigate the merits of the self-supervised learning to extract useful representations of the input data without relying on human annotations and then using these representations in the downstream task. We propose ST-KeyS, a masked auto-encoder model based on vision transformers where the pretraining stage is based on the mask-and-predict paradigm, without the need of labeled data. In the fine-tuning stage, the pre-trained encoder is integrated into a siamese neural network model that is fine-tuned to improve feature embedding from the input images. We further improve the image representation using pyramidal histogram of characters (PHOC) embedding to create and exploit an intermediate representation of images based on text attributes. In an exhaustive experimental evaluationon three widely used benchmark datasets (Botany, Alvermann Konzilsprotokolle and George Washington), the proposed approach outperforms state-of-the-art methods trained on the same datasets. © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach Featuring Graph-Based Algorithm for Cell Segmentation and Tracking

A Novel Deep Learning Approach Featuring Graph-Based Algorit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Keliang Zhao Jovial Niyogisubizo Linxia Xiao Yi Pan Dongqing Wei Didi Rosiyadi Yanjie Wei Shenzhen Key Laboratory of Intelligent Bioinformatics and Center for High Performance Computing Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China College of Computer Science and Control Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory of Microbial Metabolism and School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai China Research Center for Artificial Intelligence and Cybersecurity National Research and Innovation Agency Bandung Indonesia

The precise segmentation and tracking of cells in microscopy image sequences play a pivotal role in biomedical research, facilitating the study of tissue, organ, and organism development. However, manual segmentation and tracking of cells is time-consuming and often require professional experiences. Besides, segmenting cells in the images with a low signal-to-noise ratio remains difficult. While deep learning (DL) has become a common method for cell segmentation, few DL- based methods address concurrent cell segmentation and tracking. In this paper, we propose a novel DL approach featuring graph-based tracking for cell segmentation and tracking in microscopy images. We combine Deeplabv3+ for semantic segmentation and ResNet50 for enhanced feature extraction, enabling comprehensive cell detection and instance segmentation. Post-processing, involving non-maxima suppression and outlier detection, refines predictions and produces final segmentation. The tracking method is based on the relative position of graph nodes to track segmented cells, encompassing cell division and apoptosis. We conduct our experiments on the induced pluripotent stem (iPS) cell datasets, and the results show that the segmentation and tracking performance of our method yields superior performance compared to the benchmark models. More specifically, our approach achieved DET values of 0.955 and 0.913, TRA values of 0.951 and 0.906, and SEG values of 0.690 and 0.665 on two iPS dataset videos, respectively. Additionally, the performance assessment encompasses four real microscopy datasets from the Cell Tracking Challenge (CTC). Our method greatly reduces the cost of manual labeling and labor-intensive costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regulating the Hydrophobic Part in Amphiphilic Triphenylamino-Diarylethene Fluorophores for Ultrasensitive and Portable Detection of Urinary Albumin

SSRN

引用

SSRN 2025年

作者： Qin, Tianyi Liao, Caiqiang Liang, Xianwen Du, Xinfeng Xiong, Haoyan Chen, Quan Lu, Cuizhen Zhang, Zhongyang Xu, Zhongyong Lv, Taoyuze Wang, Zhaohui Wang, Yalong Liu, Bin Zhu, Mingqiang State Key Laboratory of Digital Medical Engineering Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical Engineering Hainan University Hainan Sanya572025 China Department of Hepatobiliary and Pancreatic Surgery Hainan Affiliated Hospital of Hainan Medical University Hainan Province Haikou570311 China State Key Laboratory of Marine Resource Utilization in South China Sea Hainan University Haikou570228 China College of Material Science and Engineering Shenzhen University Shenzhen518060 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China

Sensitive and accurate detection of urinary albumin (u-ALB), preferably by user-friendly smartphone-based portable devices, is essential for the prevention and regular evaluation of chronic kidney disease (CKD). Here, we present a class of ionic aggregation-induced emission fluorogens (AIEgens) containing triphenylamine pyridinium skeleton and extended alkyl chains (TPA-Ps) as novel probes for u-ALB. Different from the previous studies focusing on regulating the number of ionic moieties, we for the first time investigated the effect of extending the hydrophobic tails on enhancing the sensitivity. Specifically, the TPA-P-C6 with one ionic moiety yet a n-hexyl chain exhibited the highest fluorescent increasing fold (> 3450) on responding to u-ALB, which has also been the highest degree among the reported ionic AIEgen-based u-ALB probes. Different stages of albuminuria (A1-A3) represented by varying u-ALB concentrations could be clearly revealed through fluorescence spectral signal readout. Additionally, the TPA-P-C6 exhibited a restored fluorescence at longer wavelength area in real urine samples, enabling fluorocolorimetric sensing and point-of-care testing by naked eyes. With the assistance of smartphones for signal capturing and analysis, portable devices based on test papers, 96-well plate, and 3D-printing technique have been constructed for the on-site detection of u-ALB. Compared with the commercial dye based u-ALB indicator (G250) and test papers, the multi-color sensing signals of our probe can clearly reveal the different stages of albuminuria and offer useful proofs for early diagnosis of CKD. © 2025, The Authors. All rights reserved.

关键词： Portable equipment

来源：评论

学校读者我要写书评

暂无评论

Development of an interpretable QSPR model to predict the octanol-water partition coefficient based on three artificial intelligence algorithms

引用

Green Chemical engineering 2025年第2期 193-199页

作者： Ao Yang Shirui Sun Lu Qi Zong Yang Kong Jaka Sunarso Weifeng Shen College of Safety Science and Engineering Chongqing University of Science and Technology Beijing Institute of Technology Chongqing Innovation Center School of Chemistry and Chemical Engineering Chongqing University School of Chemistry and Chemical Engineering Yangtze Normal University Jiangsu Key Laboratory of Advanced Catalytic Materials and Technology School of Petrochemical EngineeringChangzhou University School of Engineering and Technology Sunway University Research Centre for Sustainable Technologies Faculty of EngineeringComputing and ScienceSwinburne University of Technology

This study aims to significantly improve existing quantitative structure-property relationship（QSPR） models for predicting the octanol-water partition coefficient(KOW). This is because accurate predictions of KOWare crucial for assessing the environmental behavior and bioaccumulation potential of chemicals. Previous models have reported determination coefficient（R2） values between 0.9451 and 0.9681, and this research seeks to exceed these benchmarks. Three machine learning（ML） models are explored, r.e., feed-forward neural networks（FNN）,extreme gradient boosting（XGBoost）, and random forest（RF）. Using a dataset of 14,610 solvents（14,580 after data cleaning） and 21 molecular descriptors derived from SMILES representations, we rigorously evaluate these models based on R2, mean absolute error（MAE）, root mean squared error（RMSE）, and mean relative error（MRE）.Notably, the best model developed, the XGBoost-based QSPR, demonstrated exceptional performance, exhibiting an impressive R2value of 0.9772, surpassing benchmarks set by prior research models. Additionally, shapley additive explanation（SHAP） analysis is also employed for model interpretation, and it is revealed that the top five influential input features include SMR＿VSA8, SMR＿VSA3, Kappa2, Heavy Atom Count, and fr＿furan. This study not only sets a new benchmark for KOWprediction accuracy but also enhances the interpretability of QSPR models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Oxide transistors: Unconventional architectures and their applications 12

Oxide transistors: Unconventional architectures and their ap...

引用

Oxide-Based Materials and Devices XII 2021

作者： Bestelink, Eva Niang, Kham M. Mudiyanselage, Indrachapa Rajapakshe Bairaktaris, Georgios Frohlich, David M. Sporea, Radu A. Advanced Technology Institute University of Surrey GuildfordGU2 7XH United Kingdom Electrical Engineering Division Department of Engineering Cambridge University CambridgeCB3 0FA United Kingdom Digital World Research Centre University of Surrey GuildfordGU2 7XH United Kingdom

ISBN: (数字)9781510642102

ISBN: (纸本)9781510642096

Thin-film transistors deliberately comprising rectifying source contacts have attractive properties for sensor and driver circuits: High performance uniformity and geometrical tolerance;superior saturation;and high intrinsic gain. The paper reviews the source-gated and multimodal thin-film transistor configurations, and presents their proposed applications to ultra-compact sensing and data processing circuits. Source-gated transistors with nanoscale tunneling contacts offer an alternative to the Schottky-contact fabrication route, which presents processing challenges. Emerging multimodal transistors overcome limitations of traditional contact-controlled devices and add to the list of useful properties: High gain or constant transconductance by design;immunity to drain voltage variations in floating gate configuration;and a significantly faster response time than source-gated transistors. These devices form the foundation for the design of compact, yet extremely versatile, thin-film circuits for sensing, signal conditioning and signal conversion. Finally, a vision is presented in which the properties of these circuits will be essential to convey seamless user interactivity to physical objects, transforming them into intuitive user interfaces beyond traditional displays screens. © 2021 SPIE. All rights reserved.

关键词： Thin film transistors

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：