检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yang, Yufeng Pandey, Ashutosh Wang, DeLiang Department of Computer Science and Engineering The Ohio State University United States Center for Cognitive and Brain Sciences The Ohio State University United States

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement algorithms. However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in noisy conditions compared to an ASR model trained on noisy speech directly. The divide between speech enhancement and ASR impedes the progress of robust ASR systems especially as speech enhancement has made big strides in recent years. In this work, we focus on eliminating this divide with an ARN (attentive recurrent network) based time-domain enhancement model. The proposed system fully decouples speech enhancement and an acoustic model trained only on clean speech. Results on the CHiME-2 corpus show that ARN enhanced speech translates to improved ASR results. The proposed system achieves 6.28% average word error rate, outperforming the previous best by 19.3% relatively. Copyright © 2022, The Authors. All rights reserved.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

IEEE International Conference on Big Data

作者： Krzysztof Hanzel Damian Grzechca Adam Ziebinski Lukas Chruszczyk Artur Janus Department of Telecommunications and Teleinformatics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Electronics Electrical Engineering and Microelectronics Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Department of Distributed Systems and Informatics Devices Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Student of Electrical Engineering Faculty of Electrical Engineering Silesian University of Technology Gliwice Poland

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested; however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV – so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PND-Net: plant nutrition deficiency and disease classification using graph convolutional network (vol 14, 15537, 2024)

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-17页

作者： Bera, Asish Bhattacharjee, Debotosh Krejcar, Ondrej Department of Computer Science and Information Systems BITS Pilani Pilani Campus Pilani Rajasthan 333031 India Department of Computer Science and Engineering Jadavpur University Kolkata West Bengal 700032 India Faculty of Informatics and Management University of Hradec Kralove Hradec Kralove Czech Republic Skoda Auto University Na Karmeli 1457 293 01 Mlada Boleslav Czech Republic Malaysia Japan International Institute of Technology (MJIIT) Universiti Teknologi Malaysia Kuala Lumpur Malaysia

Crop yield production could be enhanced for agricultural growth if various plant nutrition deficiencies, and diseases are identified and detected at early stages. Hence, continuous health monitoring of plant is very crucial for handling plant stress. The deep learning methods have proven its superior performances in the automated detection of plant diseases and nutrition deficiencies from visual symptoms in leaves. This article proposes a new deep learning method for plant nutrition deficiencies and disease classification using a graph convolutional network (GNN), added upon a base convolutional neural network (CNN). Sometimes, a global feature descriptor might fail to capture the vital region of a diseased leaf, which causes inaccurate classification of disease. To address this issue, regional feature learning is crucial for a holistic feature aggregation. In this work, region-based feature summarization at multi-scales is explored using spatial pyramidal pooling for discriminative feature representation. Furthermore, a GCN is developed to capacitate learning of finer details for classifying plant diseases and insufficiency of nutrients. The proposed method, calledPlantNutrition Deficiency andDiseaseNetwork (PND-Net), has been evaluated on two public datasets for nutrition deficiency, and two for disease classification using four backbone CNNs. The best classification performances of the proposed PND-Net are as follows: (a) 90.00% Banana and 90.54% Coffee nutrition deficiency; and (b) 96.18% Potato diseases and 84.30% on PlantDoc datasets using Xception backbone. Furthermore, additional experiments have been carried out for generalization, and the proposed method has achieved state-of-the-art performances on two public datasets, namely the Breast Cancer Histopathology Image Classification (BreakHis 40\(\times \): 95.50%, and BreakHis 100\(\times \): 96.79% accuracy) and Single cells in Pap smear images for cervical cancer classification (SIPaKMeD: 99.18% accuracy).

关键词： Agriculture Cancer classification Convolutional neural network Graph convolutional network Nutrition deficiency Plant disease Spatial pyramid pooling

来源：评论

学校读者我要写书评

暂无评论

FreeTumor: Large-Scale Generative Tumor Synthesis in Computed Tomography Images for Improving Tumor Recognition

arXiv

引用

arXiv 2025年

作者： Wu, Linshan Zhuang, Jiaxin Zhou, Yanning He, Sunan Ma, Jiabo Luo, Luyang Wang, Xi Ni, Xuefeng Zhong, Xiaoling Wu, Mingxiang Zhao, Yinghua Duan, Xiaohui Vardhanabhuti, Varut Rajpurkar, Pranav Chen, Hao Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Tencent AI Lab Shenzhen China Department of Biomedical Informatics Harvard University Boston United States Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Radiology Shenzhen People’s Hospital Shenzhen China Department of Radiology The Third Affiliated Hospital of Southern Medical University Guangzhou China Department of Radiology Sun Yat-Sen Memorial Hospital Sun Yat-Sen University Guangzhou China Department of Diagnostic Radiology Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong Division of Life Science The Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong Shenzhen-Hong Kong Collaborative Innovation Research Institute The Hong Kong University of Science and Technology Shenzhen China

Tumor is a leading cause of death worldwide, with an estimated 10 million deaths attributed to tumor-related diseases every year. AI-driven tumor recognition unlocks new possibilities for more precise and intelligent tumor screening and diagnosis. However, the progress is heavily hampered by the scarcity of annotated datasets, which demands extensive annotation efforts by radiologists. To tackle this challenge, we introduce FreeTumor, an innovative Generative AI (GAI) framework to enable large-scale tumor synthesis for mitigating data scarcity. Specifically, FreeTumor effectively leverages a combination of limited labeled data and large-scale unlabeled data for tumor synthesis training. Unleashing the power of large-scale data, FreeTumor is capable of synthesizing a large number of realistic tumors on images for augmenting training datasets. To this end, we create the largest training dataset for tumor synthesis and recognition by curating 161,310 publicly available Computed Tomography (CT) volumes from 33 sources, with only 2.3% containing annotated tumors. To validate the fidelity of synthetic tumors, we engaged 13 board-certified radiologists in a Visual Turing Test to discern between synthetic and real tumors. Rigorous clinician evaluation validates the high quality of our synthetic tumors, as they achieved only 51.1% sensitivity and 60.8% accuracy in distinguishing our synthetic tumors from real ones. Through high-quality tumor synthesis, FreeTumor scales up the recognition training datasets by over 40 times, showcasing a notable superiority over state-of-the-art AI methods including various synthesis methods and foundation models. On average, FreeTumor improves the segmentation Dice scores by 6.7% and early tumor detection sensitivity by 16.4%. These findings indicate promising prospects of FreeTumor in clinical applications, potentially advancing tumor treatments and improving the survival rates of patients. Copyright © 2025, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

MRI Parameter Mapping via Gaussian Mixture VAE: Breaking the Assumption of Independent Pixels

arXiv

引用

arXiv 2024年

作者： Xu, Moucheng Zhou, Yukun Goodwin-Allcock, Tobias Firoozabadi, Kimia Jacob, Joseph Alexander, Daniel C. Slator, Paddy J. UCL Hawkes Institute United Kingdom UCL Satsuma Lab United Kingdom UCL Respiratory United Kingdom UCL Department of Computer Science United Kingdom UCL Medical School United Kingdom UCL Department of Medical Physics and Biomedical Engineering United Kingdom Cardiff University School of Computer Science and Informatics United Kingdom Cardiff University Brain Research Imaging Center United Kingdom

We introduce and demonstrate a new paradigm for quantitative parameter mapping in MRI. Parameter mapping techniques, such as diffusion MRI and quantitative MRI, have the potential to robustly and repeatably measure biologically-relevant tissue maps that strongly relate to underlying microstructure. Quantitative maps are calculated by fitting a model to multiple images, e.g. with least-squares or machine learning. However, the overwhelming majority of model fitting techniques assume that each voxel is independent, ignoring any co-dependencies in the data. This makes model fitting sensitive to voxelwise measurement noise, hampering reliability and repeatability. We propose a self-supervised deep variational approach that breaks the assumption of independent pixels, leveraging redundancies in the data to effectively perform data-driven regularisation of quantitative maps. We demonstrate that our approach outperforms current model fitting techniques in dMRI simulations and real data. Especially with a Gaussian mixture prior, our model enables sharper quantitative maps, revealing finer anatomical details that are not presented in the baselines. Our approach can hence support the clinical adoption of parameter mapping methods such as dMRI and qMRI. Our code is available at https://***/moucheng2017/MRI-GMM-VAE. © 2024, CC BY-NC-ND.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Develop learning methods imr (integrated material realistic) alternative mathematics learning during a pandemic 7

Develop learning methods imr (integrated material realistic)...

引用

7th International Conference on Mathematics, science, and Education 2020, ICMSE 2020

作者： Rusmana, I.M. Zainuri Wardono Nulhakim, A.L. Doctoral Program Universitas Negeri Semarang Indonesia Department of Mathematic Education Faculty of Mathematics and Natural Science Universitas Indraprasta Pgri Jakarta Indonesia Department of Mathematic Education Faculty of Mathematics and Natural Science Universitas Negeri Semarang Indonesia Department of Informatics Engineering Faculty of Engineering and Computer Science Universitas Indraprasta Pgri Jakarta Indonesia

The learning methods used by teachers in schools in Serang City are very ineffective, especially during the pandemic. This is because not integrated content of material in one subject with other subjects. Never mind between subjects, sometimes the material is not well integrated. The purpose of this study is to provide an alternative learning method during a pandemic, namely a method that integrates material with the realities of life which is abbreviated as IMR (Integrated Realistic Material). The method in this research is Research and Development (RnD) with the ADDIE model. In making this learning method according to the stages from the ADDIE study. The results of this study are in the form of learning methods that are integrated with the realities of life during the pandemic. © Published under licence by IOP Publishing Ltd.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

ESCAPED: Efficient Secure and Private Dot Product Framework for Kernel-based Machine Learning Algorithms with Applications in Healthcare 35

ESCAPED: Efficient Secure and Private Dot Product Framework ...

引用

35th AAAI Conference on Artificial Intelligence, AAAI 2021

作者： Ünal, Ali Burak Akgün, Mete Pfeifer, Nico Methods in Medical Informatics Department of Computer Science University of Tuebingen Germany Translational Bioinformatics University Hospital Tuebingen Tuebingen Germany Statistical Learning in Computational Biology Max Planck Institute for Informatics Saarbrücken Germany

ISBN: (纸本)9781713835974

Training sophisticated machine learning models usually requires many training samples. Especially in healthcare settings these samples can be very expensive, meaning that one institution alone usually does not have enough. Merging privacy-sensitive data from different sources is usually restricted by data security and data protection measures. This can lead to approaches that reduce data quality by putting noise onto the variables (e.g., in Ε-differential privacy) or omitting certain values (e.g., for k-anonymity). Other measures based on cryptographic methods can lead to very time-consuming computations, which is especially problematic for larger multi-omics data. We address this problem by introducing ESCAPED, which stands for Efficient SeCure And PrivatE Dot product framework. ESCAPED enables the computation of the dot product of vectors from multiple sources on a third-party, which later trains kernel-based machine learning algorithms, while neither sacrificing privacy nor adding noise. We have evaluated our framework on drug resistance prediction for HIV-infected people and multi-omics dimensionality reduction and clustering problems in precision medicine. In terms of execution time, our framework significantly outperforms the best-fitting existing approaches without sacrificing the performance of the algorithm. Even though we only present the benefit for kernel-based algorithms, our framework can open up new research opportunities for further machine learning models that require the dot product of vectors from multiple sources. Copyright © 2021, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Regression Analysis of Humidity and Temperature on Chicken Lifespan

Regression Analysis of Humidity and Temperature on Chicken L...

引用

Agrosystem Engineering, Technology & Applications (AGRETA), IEEE International Conference on

作者： Sittilin Salleh Razak Mohd Ali Lee Nurul Rawaida Ain Burhani Kennedy Juani Farah Hasanah Ab Jaid Electrical and Electronics Engineering Faculty of Engineering Universiti Malaysia Sabah Kota Kinabalu Sabah Malaysia Mechanical Engineering Faculty of Mechanical Engineering Universiti Teknologi Malaysia Johor Malaysia Department of Veterinary Services Sabah Malaysia Computer Science (Data Science) Faculty of Computing & Informatics Universiti Malaysia Sabah

ISBN: (数字)9798350373660

ISBN: (纸本)9798350373677

This study presents a comprehensive analysis of the effects of humidity and temperature variations on the lifespan of Ross broiler chickens at two different locations over two 35-day experimental periods. The study initially included a group of 20 chickens, followed by another group of 41 chickens. Through rigorous regression analysis, the research evaluates the correlation between environmental variables and chicken lifespan, using a multi-sensor system integrated with IoT technology to monitor temperature and humidity values in poultry farms. The results presented in significant MSE and R 2 values for Batch 2 using correlation matrix and polynomial regression provide valuable insights for optimizing poultry management practices.

关键词： Temperature sensors Temperature measurement Correlation Humidity Polynomials Regression analysis Monitoring

来源：评论

学校读者我要写书评

暂无评论

Empowering Smart Education through computer Vision and the Internet of Everything (IoE) in Intelligent Smart School Transportation 10

Empowering Smart Education through Computer Vision and the I...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Hermanus, Davy Ronald Supangkat, Suhono Harso Hidayat, Fadhil Sasmoko Indrianti, Yasinta Bina Nusantara University Research Interest Group in Educational Technology Computer Science Department Bandung Indonesia School of Electric and Informatic Institut Teknologi Bandung Bandung Indonesia School of Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Research Interest Group in Educational Technology Bina Nusantara University Faculty of Humanities Primary Teacher Education Department Jakarta Indonesia Universitas Agung Podomoro Entrepreneurship Department Jakarta Indonesia

ISBN: (纸本)9798350339543

This paper presents an innovative intelligent school transportation system designed for a smart town within a larger smart city framework. By harnessing the power of computer vision, the Internet of Everything (IoE), and advanced surveillance technologies, the system offers enhanced safety and convenience for students, parents, schools, public transportation, drivers, law enforcement, and the government. The research methodology incorporates qualitative research methods to capture valuable insights from stakeholders and inform the design architecture of the system. The case study focuses on Kota Baru Parahyangan City, where Cahaya Bangsa Classical School serves as an exemplary institution. Through the integration of computer vision techniques, such as facial recognition and object detection, the system enables real-time monitoring and tracking of students during their transportation journey. The IoE integration ensures seamless connectivity, enabling efficient communication and data exchange among surveillance cameras, central monitoring systems, and IoT-enabled vehicles. The proposed intelligent school transportation system offers not only improved safety but also optimized traffic management and resource allocation. The findings of this study contribute to the broader field of smart city development, specifically in the context of intelligent transportation systems. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CoRAL: a Context-aware Croatian Abusive Language Dataset

arXiv

引用

arXiv 2022年

作者： Shekhar, Ravi Karan, Mladen Purver, Matthew Cognitive Science Research Group School of Electronic Engineering & Computer Science Queen Mary University of London United Kingdom Department of Knowledge Technologies Jožef Stefan Institute Ljubljana Slovenia

In light of unprecedented increases in the popularity of the internet and social media, comment moderation has never been a more relevant task. Semi-automated comment moderation systems greatly aid human moderators by either automatically classifying the examples or allowing the moderators to prioritize which comments to consider first. However, the concept of inappropriate content is often subjective, and such content can be conveyed in many subtle and indirect ways. In this work, we propose CoRAL - a language and culturally aware Croatian Abusive dataset covering phenomena of implicitness and reliance on local and global context. We show experimentally that current models degrade when comments are not explicit and further degrade when language skill and context knowledge are required to interpret the comment. © 2022, CC BY-NC-ND.

关键词： Moderators

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：