检索结果-内蒙古大学图书馆

Deep learning based text detection using resnet for feature extraction

Multimedia Tools and Applications 2023年第30期82卷 46871-46903页

作者： Huang, Li-Kun Tseng, Hsiao-Ting Hsieh, Chen-Chiung Yang, Chih-Sin Institute of Bioinformatics and Structural Biology College of Life Science National Tsing Hua University No. 101 Sec. 2 Kuangfu Rd. East Dist. Hsinchu City300 Taiwan Department of Information Management National Central University No. 300 Zhongda Rd Zhongli District Taoyuan City320 Taiwan Department of Computer Science and Engineering Tatung University No. 40 Sec. 3 Jhongshan N. Rd Jhongshan District Taipei City104 Taiwan

Popular deep learning models for text segmentation include CTPN, EAST, and PixelLink. However, they are not very well capable of dealing with the images containing densely distributed characters, and those characters may be connected. For these problems, the ResNet with excellent sensitivity for feature extraction is used to replace those embedded convolution neural networks in the main structures of CTPN and EAST. The experimental results showed that a better feature extraction network could significantly improve the precision of text localization. Noteworthy, the results indicate that the accuracy of modified EAST with ResNet101 would be the highest with a deeper depth and larger width of ResNet. The accuracy of text segmentation on ICDAR 2015 is 83.4% which is 7% higher than the original PVANET-EAST. The text detection accuracy is 83.9% on the untrained scanned document. Also, it achieved an accuracy of 86.3% when applied to self-collected Chinese calligraphy. Those results demonstrated that text detection using ResNet is a better improvement for OCR applications. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Approximately Optimal Search on a Higher-dimensional Sliding Puzzle

arXiv

引用

arXiv 2024年

作者： Merleau, Nono S.C. O’Malley, Miguel Roldán, Érika Mukherjee, Sayan Center for Scalable Data Analytics and Artificial Intelligence Department of Computer Science Universität Leipzig Germany Max Planck Institute for Mathematics in the Sciences Germany Duke University Departments of Statistical Science Mathematics Computer Science and Biostatistics & Bioinformatics United States

Higher-dimensional sliding puzzles are constructed on the vertices of a d-dimensional hypercube, where 2d−l vertices are distinctly coloured. Rings with the same colours are initially set randomly on the vertices of the hypercube. The goal of the puzzle is to move each of the 2d − l rings to pre-defined target vertices on the cube. In this setting, the k-rule constraint represents a generalisation of edge collision for the movement of colours between vertices, allowing movement only when a hypercube face of dimension k containing a ring is completely free of other rings. Starting from an initial configuration, what is the minimum number of moves needed to make ring colours match the vertex colours? An algorithm that provides us with such a number is called God’s algorithm. When such an algorithm exists, it does not have a polynomial time complexity, at least in the case of the 15-puzzle corresponding to k = 1 in the cubical puzzle. This paper presents a comprehensive computational study of different scenarios of the higher-dimensional puzzle. A benchmark of three computational techniques, an exact algorithm (the A* search) and two approximately optimal search techniques (an evolutionary algorithm (EA) and reinforcement learning (RL)) is presented in this work. The experiments show that all three methods can successfully solve the puzzle of dimension three for different face dimensions and across various difficulty levels. When the dimension increases, the A* search fails, and RL and EA methods can still provide a generally acceptable solution, i.e. a distribution of a number of moves with a median value of less than 30. Overall, the EA method consistently requires less computational time, while failing in most cases to minimise the number of moves for the puzzle dimensions d = 4 and d = 5. © 2024, CC BY.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Pediatric Glucose Forecasting 4

Transfer Learning for Pediatric Glucose Forecasting

引用

4th Machine Learning for Health Symposium, ML4H 2024

作者： Ryser, Alain Feng, Chuhao Scheithauer, Tobias Pfister, Marc Burckhardt, Marie-Anne Bachmann, Sara Marx, Alexander Vogt, Julia E. Department of Computer Science ETH Zurich Zürich Switzerland Department of Statistics Research Center Trustworthy Data Science and Security of the University Alliance Ruhr TU Dortmund University Dortmund Germany Department of Biosystems Science and Engineering ETH Zurich Basel Switzerland Pediatric Pharmacology and Pharmacometrics University Children's Hospital Basel Basel Switzerland Department of Clinical Research University of Basel Basel Switzerland Pediatric Endocrinology and Diabetology University Children's Hospital Basel Basel Switzerland SIB Swiss Institute of Bioinformatics Ecublens Switzerland

Effective blood glucose forecasting is crucial for detecting events such as hypo- or hyperglycemia in people with diabetes, yet remains challenging in domains with only small, heterogeneous datasets, such as in the pediatric field. We present GluTFT, a novel transfer learning approach that allows leveraging models pretrained on publicly available adult diabetes datasets for pediatric glucose forecasting. We systematically evaluate multiple transfer learning strategies, including zero-shot prediction and fine-tuning across the entire dataset as well as specific subgroups of participants. Our extensive experiments reveal that GluTFT excels on the pretraining datasets and significantly outperforms baseline methods when fine-tuned. To validate the clinical relevance of our approach, we evaluate Parkes Error Grids, demonstrating the quality of GluTFT's blood glucose forecasts and its potential for enhancing clinical decision-making for pediatric diabetes. © 2024 A. Ryser, C. Feng, T. Scheithauer, M. Pfister, M.-A. Burckhardt, S. Bachmann, A. Marx & J.E. Vogt.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Fruit Segmentation via Transfer Learning

Few-Shot Fruit Segmentation via Transfer Learning

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jordan A. James Heather K. Manching Amanda M. Hulse-Kemp William J. Beksi Department of Computer Science and Engineering The University of Texas at Arlington Arlington TX USA Department of Crop and Soil Sciences North Carolina State University Raleigh NC USA Genomics and Bioinformatics Research Unit USDA Agricultural Research Service Raleigh NC USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Advancements in machine learning, computer vision, and robotics have paved the way for transformative solutions in various domains, particularly in agriculture. For example, accurate identification and segmentation of fruits from field images plays a crucial role in automating jobs such as harvesting, disease detection, and yield estimation. However, achieving robust and precise infield fruit segmentation remains a challenging task since large amounts of labeled data are required to handle variations in fruit size, shape, color, and occlusion. In this paper, we develop a few-shot semantic segmentation framework for infield fruits using transfer learning. Concretely, our work is aimed at addressing agricultural domains that lack publicly available labeled data. Motivated by similar success in urban scene parsing, we propose specialized pre-training using a public benchmark dataset for fruit transfer learning. By leveraging pre-trained neural networks, accurate semantic segmentation of fruit in the field is achieved with only a few labeled images. Furthermore, we show that models with pre-training learn to distinguish between fruit still on the trees and fruit that have fallen on the ground, and they can effectively transfer the knowledge to the target fruit dataset.

关键词： computer vision Accuracy Shape Image color analysis Semantic segmentation Transfer learning Neural networks

来源：评论

学校读者我要写书评

暂无评论

Extracting Stress-Related EEG Patterns from Pre-Sleep EEG for Forecasting Slow-Wave Sleep Deficiency

引用

IEEE Transactions on Neural Systems and Rehabilitation Engineering 2024年 32卷 1817-1827页

作者： Su, Cheng-Hua Ko, Li-Wei Jung, Tzyy-Ping Onton, Julie Tzou, Shey-Cherng Juang, Jia-Chi Hsu, Chung-Yao Institute of Bioinformatics and Systems Biology National Yang Ming Chiao Tung University Hsinchu300 Taiwan Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Kaohsiung Medical University Drug Development and Value Creation Research Center Department of Biomedical Science and Environmental Biology Kaohsiung807 Taiwan University of California San Diego Swartz Center for Computational Neuroscience La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan University of California San Diego Institute for Neural Computation La Jolla CA92093 United States National Yang Ming Chiao Tung University Department of Biological Science and Technology Hsinchu300 Taiwan Kaohsiung Medical University Hospital Sleep Disorders Center Department of Neurology Kaohsiung807 Taiwan Kaohsiung Medical University College of Medicine Department of Neurology Kaohsiung807 Taiwan

Sleep is vital to our daily activity. Lack of proper sleep can impair functionality and overall health. While stress is known for its detrimental impact on sleep quality, the precise effect of pre-sleep stress on subsequent sleep structure remains unknown. This study introduced a novel approach to study the pre-sleep stress effect on sleep structure, specifically slow-wave sleep (SWS) deficiency. To achieve this, we selected forehead resting EEG immediately before and upon sleep onset to extract stress-related neurological markers through power spectra and entropy analysis. These markers include beta/delta correlation, alpha asymmetry, fuzzy entropy (FuzzEn) and spectral entropy (SpEn). Fifteen subjects were included in this study. Our results showed that subjects lacking SWS often exhibited signs of stress in EEG, such as an increased beta/delta correlation, higher alpha asymmetry, and increased FuzzEn in frontal EEG. Conversely, individuals with ample SWS displayed a weak beta/delta correlation and reduced FuzzEn. Finally, we employed several supervised learning models and found that the selected neurological markers can predict subsequent SWS deficiency. Our investigation demonstrated that the classifiers could effectively predict varying levels of slow-wave sleep (SWS) from pre-sleep EEG segments, achieving a mean balanced accuracy surpassing 0.75. The SMOTE-Tomek resampling method could improve the performance to 0.77. This study suggests that stress-related neurological markers derived from pre-sleep EEG can effectively predict SWS deficiency. Such information can be integrated with existing sleep-improving techniques to provide a personalized sleep forecasting and improvement solution. © 2001-2011 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Dissection of a rapidly evolving wheat resistance gene cluster by long-read genome sequencing accelerated the cloning of Pm69

引用

Plant Communications 2024年第1期5卷 69-83页

作者： Yinghui Li Zhen-Zhen Wei Hanan Sela Liubov Govta Valentyna Klymiuk Rajib Roychowdhury Harmeet Singh Chawla Jennifer Ens Krystalee Wiebe Valeria Bocharova Roi Ben-David Prerna B.Pawar Yuqi Zhang Samidha Jaiwar Istvan Molnar Jaroslav Dolezel Gitta Coaker Curtis J.Pozniak Tzion Fahima Institute of Evolution University of HaifaMt.CarmelHaifa 3498838Israel The Department of Evolutionary and Environmental Biology University of HaifaMt.CarmelHaifa 3498838Israel The Institute of Plant Protection Sichuan Academy of Agricultural SciencesChengdu 610066China Crop Development Centre and Department of Plant Sciences University of Saskatchewan51 Campus DriveSaskatoonSK S7N 5A8Canada Department of Vegetables and Field Crops Institute of Plant SciencesAgricultural Research Organization(ARO)–Volcani CenterRishon Lezion 7505101Israel Department of Crop Genomics and Bioinformatics China Agricultural UniversityBeijing 100094China Institute of Experimental Botany of the Czech Academy of Sciences Centre of the Region Hana´for Biotechnological and Agricultural ResearchSlechtitelu 3177900 OlomoucCzech Republic Plant Pathology Department University of CaliforniaDavisDavisCA 95616USA Present address:Department of Plant Science University of ManitobaWinnipegMB R3T 2N2Canada Present address:Agricultural Institute Centre for Agricultural ResearchELKHMartonvasar 2462Hungary

Gene cloning in repeat-rich polyploid genomes remains ***,we describe a strategy for overcoming major bottlenecks in cloning of the powdery mildew resistance gene(R-gene)Pm69 derived from tetraploid wild emmer wheat.A conventional positional cloning approach was not effective owing to suppressed *** sorting was compromised by insufficient purity.A Pm69 physical map,constructed by assembling Oxford Nanopore Technology(ONT)long-read genome sequences,revealed a rapidly evolving nucleotide-binding leucine-rich repeat(NLR)R-gene cluster with structural variations.A single candidate NLR was identified by anchoring RNA sequencing reads from susceptible mutants to ONT contigs and was validated by virus-induced gene ***69 is likely a newly evolved NLR and was discovered in only one location across the wild emmer wheat distribution range in ***69 was successfully introgressed into cultivated wheat,and a diagnostic molecular marker was used to accelerate its deployment and pyramiding with other R-genes.

关键词： cluster resistance Israel

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Early Prediction of Parkinson's Disease for Sustainable Healthcare 1st

Machine Learning Based Early Prediction of Parkinson's Disea...

引用

1st International Conference on Sustainable Development through Machine Learning, Artificial Intelligence, and IoT, ICSD 2023

作者： Chauhan, Ritu Mehta, Khushi Alankar, Bhavya Kaur, Harleen Artificial Intelligence and IoT Lab Center for Computational Biology and Bioinformatics Amity University UP Noida India Amity Institute of Information Technology Amity University UP Mumbai India Department of Computer Science and Engineering School of Engineering Sciences and Technology Jamia Hamdard New Delhi India

ISBN: (纸本)9783031470547

The healthcare sector and technology are working hand-in-hand, which has led researchers to focus on Parkinson's disease. In a world where medical science and technology intertwined, there was a group of researchers determined to unravel the mysteries of Parkinson's disease. Medical science with machine learning algorithms, aimed to develop a robust prediction model for diagnosing this complex neurological disorder. The researchers explored various algorithms including Xgboost, Naive Bayes, Tree Classifier, KNN model, SVC model, Logistic Model, Random Forest, AdaBoost, and Gradient Boosting, using a diverse dataset encompassing clinical measurements, genetic information, and demographic factors. The researchers utilized various machine learning algorithms to uncover patterns and correlations, shed light on relationships, make accurate predictions, foster insights, differentiate Parkinson's disease, understand odds and probabilities, tackle uncertainty, and improve accuracy. By combining these algorithms, they constructed a prediction model for the accurate diagnosis of Parkinson's disease, bringing us closer to unraveling its mysteries. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Characterizing RNA Pseudouridylation by Convolutional Neural Networks

引用

genomics, Proteomics & bioinformatics 2021年第5期19卷 815-833页

作者： Xuan He Sai Zhang Yanqing Zhang Zhixin Lei Tao Jiang Jianyang Zeng Institute for Interdisciplinary Information Sciences Tsinghua UniversityBeijing 100084China Peking-Tsinghua Center for Life Sciences Peking UniversityBeijing 100871China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijing 100871China Department of Computer Science and Engineering University of CaliforniaRiversideCA 92521USA MOE Key Lab of Bioinformatics and Bioinformatics Division BNRIST/Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Institute of Integrative Genome Biology University of CaliforniaRiversideCA 92521USA MOE Key Laboratory of Bioinformatics Tsinghua UniversityBeijing 100084China

Pseudouridine(Ψ)is the most prevalent post-transcriptional RNA modification and is widespread in small cellular RNAs and m ***,the functions,mechanisms,and precise distribution ofΨs(especially in m RNAs)still remain largely *** landscape ofΨs across the transcriptome has not yet been fully ***,we present a highly effective model based on a convolutional neural network(CNN),called Pseudo Uridy Lation Site Estimator(PULSE),to analyze large-scale profiling data ofΨsites and characterize the contextual sequence features of ***,consisting of two alternatively-stacked convolution and pooling layers followed by a fully-connected neural network,can automatically learn the hidden patterns of pseudouridylation from the local sequence *** validation tests demonstrated that PULSE can outperform other state-of-the-art prediction methods and achieve high prediction accuracy,thus enabling us to further characterize the transcriptome-wide landscape ofΨ*** further showed that the prediction results derived from PULSE can provide novel insights into understanding the functional roles of pseudouridylation,such as the regulations of RNA secondary structure,codon usage,translation,and RNA stability,and the connection to single nucleotide *** source code and final model for PULSE are available at https://***/mlcb-thu/PULSE.

关键词： Pseudouridylation Convolution neural network Sequence motif Translation RNA stability

来源：评论

学校读者我要写书评

暂无评论

Internet of Things Enabled Gas Leakage Detection Over Industrial Areas using Powerful MQ Series Sensor and Controller 7

Internet of Things Enabled Gas Leakage Detection Over Indust...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Jalinder Jadhav, Rahul Radhakrishnan, P. Arun Jadhav, Dattatraya Ashreetha, B. Divya, J. Mukherjee, Saptarshi Yashwantrao Mohite Institute of Management Karad India Tagore Engineering College Electronics & Communication Engineering India Keystone School of Engineering Electronic And Telecommunication Department Pune India Mohan Babu University School of Engineering Department of Electronics And Communication Engineering Andhra Pradesh Tirupati India R.M.K.Enginnering College Dept of Computer Science And Design India GIAR Goldsmith Institute of Advanced Research Department of Mtech Bioinformatics West Bengal Kolkata India

ISBN: (纸本)9798350359299

This work presents a comprehensive overview of an Internet of Things (IoT)-enabled gas leakage detection system deployed in industrial areas using powerful MQ series gas sensors and controllers. The primary objective is to enhance safety measures by providing real-time monitoring and rapid response capabilities to potential gas leaks. The system incorporates MQ2, MQ7, and MQ135 gas sensors strategically placed in different zones within the industrial facility, capable of detecting a wide range of gases. These sensors continuously collect data, which is then transmitted to a centralized controller for analysis and decision-making. The system's architecture allows for remote accessibility, enabling authorized personnel to monitor sensor readings and take timely actions from anywhere with an internet connection. The MQ series gas sensors provide accurate and dynamic measurements of gas concentrations, including flammable hydrocarbons, toxic substances, and other hazardous gases. The system's integration with existing safety systems ensures a holistic approach to hazard prevention, allowing for coordinated responses with alarms, emergency shutdown systems, and ventilation controls. Key features of the system include scalability, cost-efficiency, and seamless integration with industrial processes. The scalability allows for the expansion of sensor networks to adapt to evolving industrial environments. The cost-efficiency is realized through the prevention of potential damage and operational downtime. Furthermore, the system integrates seamlessly with existing safety and automation systems, creating a unified safety infrastructure. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Learning Task-Aware Effective Brain Connectivity for fMRI Analysis with Graph Neural Networks (Extended Abstract)

Learning Task-Aware Effective Brain Connectivity for fMRI An...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Yu, Yue Kan, Xuan Cui, Hejie Xu, Ran Zheng, Yujia Song, Xiangchen Zhu, Yanqiao Zhang, Kun Nabi, Razieh Guo, Ying Zhang, Chao Yang, Carl Georgia Institute of Technology College of Computing United States Emory University Department of Computer Science United States Carnegie Mellon University Department of Philosophy United States Carnegie Mellon University Machine Learning United States University of California Department of Computer Science Los Angeles United States Emory University Biostatistics and Bioinformatics United States

ISBN: (纸本)9781665480451

Functional magnetic resonance imaging (fMRI) has become one of the most common imaging modalities for brain function analysis. Recently, graph neural networks (GNN) have been adopted for fMRI analysis with superior performance. Unfortunately, traditional functional brain networks are mainly constructed based on similarities among region of interests (ROI), which are noisy and agnostic to the downstream prediction tasks and can lead to inferior results for GNN-based models. To better adapt GNNs for fMRI analysis, we propose TBDS, an end-to-end framework based on Task-aware Brain connectivity DAG (short for Directed Acyclic Graph) Structure generation for fMRI analysis. The key component of TBDS is the brain network generator which adopts a DAG learning approach to transform the raw time-series into task-aware brain connectivities. Besides, we design an additional contrastive regularization to inject task-specific knowledge during the brain network generation process. Comprehensive experiments on two fMRI datasets, namely Adolescent Brain Cognitive Development (ABCD) and Philadelphia Neuroimaging Cohort (PNC) datasets demonstrate the efficacy of TBDS. In addition, the generated brain networks also highlight the prediction-related brain regions and thus provide unique interpretations of the prediction results. Our implementation will be published upon acceptance. © 2022 IEEE.

关键词： Forecasting

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：