检索结果-内蒙古大学图书馆

International Conference on Engineering Education (ICEED)

作者： Katsuyuki Umezawa Makoto Nakazawa Michiko Nakano Shigeichi Hirasawa Department of Informatics Shonan Institute of Technology Kanagawa Japan Department of Industrial Information Science Junior College of Aizu Fukushima Japan Faculty of Education and Integrated Arts and Sciences Waseda University Tokyo Japan Data Science Center Waseda University Tokyo Japan

The advancement of AI in recent years has been remarkable, along with the widespread use of speech recognition functions. In addition, an increasing number of people are self-studying in their fields of interest. In a world considered a global society, many people in countries where English is not their first language are learning English. Therefore, in this study, the authors focus on self-study English learning. The pronunciation is assumed to be correct if the speech recognition feature correctly identifies the pronounced English words and sentences. It has been recognized that feedback plays a crucial role in English pronunciation practice. If the speech recognition function can be employed to provide feedback, it would alleviate the burden on teachers and enable students to practice pronunciation independently. In this research, the authors propose practicing pronunciation using each browser's built-in speech recognition features, including Google Chrome, iOS, and Microsoft Edge, and evaluating if one's English pronunciation is correctly recognized. Through a 7-day experiment, the authors clarify the speech recognition function suitable for self-studying English pronunciation. Through this experiment, it was observed that the speech recognition function on iOS (version 15.0) outperforms compared to Google Chrome (version 107.0.5304.63) and Microsoft Edge (version 107.0.1418.24) in accurately understanding speech, even when the pronunciation is incorrect. However, it became apparent that such highly accurate speech recognition capabilities may not be suitable for self-study pronunciation practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FUSENET: SELF-SUPERVISED DUAL-PATH NETWORK FOR MEDICAL IMAGE SEGMENTATION

arXiv

引用

arXiv 2023年

作者： Kazerouni, Amirhossein Karimijafarbigloo, Sanaz Azad, Reza Velichko, Yury Bagci, Ulas Merhof, Dorit School of Electrical Engineering Iran University of Science and Technology Iran Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Department of Radiology Northwestern University ChicagoIL United States Fraunhofer Institute for Digital Medicine MEVIS Germany

Semantic segmentation, a crucial task in computer vision, often relies on labor-intensive and costly annotated datasets for training. In response to this challenge, we introduce FuseNet, a dual-stream framework for self-supervised semantic segmentation that eliminates the need for manual annotation. FuseNet leverages the shared semantic dependencies between the original and augmented images to create a clustering space, effectively assigning pixels to semantically related clusters, and ultimately generating the segmentation map. Additionally, FuseNet incorporates a cross-modal fusion technique that extends the principles of CLIP by replacing textual data with augmented images. This approach enables the model to learn complex visual representations, enhancing robustness against variations similar to CLIP’s text invariance. To further improve edge alignment and spatial consistency between neighboring pixels, we introduce an edge refinement loss. This loss function considers edge information to enhance spatial coherence, facilitating the grouping of nearby pixels with similar visual features. Extensive experiments on skin lesion and lung segmentation datasets demonstrate the effectiveness of our method. Codebase. © 2023, CC BY.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Algorithm for Denoising Photoplethysmography Signals for Heart Rate Estimation from Wearables

arXiv

引用

arXiv 2023年

作者： Jain, Pranay Ding, Cheng Rudin, Cynthia Hu, Xiao Department of Computer Science Duke University United States Department of Biomedical Engineering Georgia Institute of Technology Emory University United States Center for Data Science Nell Hodgson Woodruff School of Nursing Associated Faculty of Biomedical Informatics School of Medicine Associated Faculty of Computer Science College of Arts and Sciences Emory University United States

Smart watches and other wearable devices are equipped with photoplethysmography (PPG) sensors for monitoring heart rate and other aspects of cardiovascular health. However, PPG signals collected from such devices are susceptible to corruption from noise and motion artifacts, which cause errors in heart rate estimation. Typical denoising approaches filter or reconstruct the signal in ways that eliminate much of the morphological information, even from the clean parts of the signal that would be useful to preserve. In this work, we develop an algorithm for denoising PPG signals that reconstructs the corrupted parts of the signal, while preserving the clean parts of the PPG signal. Our novel framework relies on self-supervised training, where we leverage a large database of clean PPG signals to train a denoising autoencoder. As we show, our reconstructed signals provide better estimates of heart rate from PPG signals than the leading heart rate estimation methods. Further experiments show significant improvement in Heart Rate Variability (HRV) estimation from PPG signals using our algorithm. We conclude that our algorithm denoises PPG signals in a way that can improve downstream analysis of many different health metrics from wearable devices. Copyright © 2023, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Residual Networks Based Framework for Early Alzheimer’s Disease Classification and Diagnosis 6th

An Enhanced Residual Networks Based Framework for Early Alzh...

引用

6th International Conference on Communication, Devices and Networking, ICCDN 2022

作者： Awotunde, Joseph Bamidele Sur, Nath Samarendra Imoize, Agbotiname Lucky Misra, Sanjay Gaber, Tarek Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University East Sikkim Rangpo Majitar737136 India Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum44801 Germany Department of Applied Data Science Institute of Energy Technology Halden Norway Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt School of Science Engineering and Environment University of Salford ManchesterM5 4WT United Kingdom

ISBN: (纸本)9789819919826

Alzheimer's disease (AD) is a long-lasting, degenerative brain illness for which there is now no successful treatment. However, there are medications that can delay its growth and stop its tracks. Therefore, stopping and regulating the progression of AD depends greatly on its early diagnosis. Computer-aided diagnosis (CAD) in health care has become more and more dependent on deep learning technologies. This has help in early diagnosis and detection of various disease in health care. New techniques for the early diagnosis of neurocognitive abnormalities are now possible thanks to advancements in medical imaging and computational capacity in an effort to stop or slow down cognitive aging. Therefore, this study proposes a residual network (ResNet) type 50 for early diagnosis of AD. Convolutional neural networks (CNNs) are first used in the study for features extraction and then make the ultimate diagnosis using the ResNet-50. To create a better architecture, the problem of AD diagnosis will be addressed by utilizing and incorporating ResNet-50, which improves the current categorization problem's accuracy to its maximum. With a 98.8% accuracy rate, the proposed model using ResNet-50 produces encouraging findings for AD prediction. The study reveals that the model can effectively circumvent CNNs for the diagnostic issue with AD. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

ADOD: Adaptive Density Outlier Detection

ADOD: Adaptive Density Outlier Detection

引用

IEEE International Conference on data Mining (ICDM)

作者： Li Qian Jing Qian Xin Sun Wengang Guo Christian Böhm Institute of Informatics Ludwig Maximilian University of Munich Munich Germany Faculty of Computer Science University of Vienna Vienna Austria Carbon Neutral R&D Center China Railway Hi-Tech Industry Corporation Limited Beijing China Faculty of Data Science City University of Macau Macau China College of Electronic and Information Engineering Tongji University Shanghai China

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Outlier detection plays a dual role in data analysis: cleansing data to optimize the performance of downstream tasks and identifying potentially rare valuable events or patterns. Proximity-based methods, which are independent of data distribution assumptions, are plagued by parameter selection and performance challenges when handling data with varying densities. This study proposed a novel unsupervised algorithm named Adaptive Density Outlier Detection (ADOD) to address these challenges. The core innovation of ADOD involves two main aspects: adaptive neighborhood boundaries and density consistency scoring. First, instead of relying on a predefined fixed radius, ADOD employs perplexity to calculate the local scale of each data point. It then dynamically adjusts the neighborhood boundaries according to this scale to adapt to data with varying densities. Second, ADOD estimates local density using a mutual neighbor graph and combines the density differences between data points and their neighbors to compute outlier scores, effectively distinguishing outliers that significantly deviate from their surroundings. This study evaluated ADOD on one synthetic and 32 real datasets, and compared it with 14 classical and state-of-the-art algorithms from different categories. Extensive experimental results demonstrated the superior performance of ADOD, achieving the highest average accuracy across ROC, P@N, and AP metrics. This study promotes the development of outlier detection techniques and expands their potential for real-time applications.

关键词： Measurement Technological innovation Accuracy data analysis Sensitivity analysis Heuristic algorithms Memory management Nearest neighbor methods Real-time systems Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Bayes Optimal Estimation and Its Approximation Algorithm for Difference with and without Treatment under URLC Model

Bayes Optimal Estimation and Its Approximation Algorithm for...

引用

International Symposium on Information Theory and Its Applications, ISITA

作者： Taisuke Ishiwatari Shota Saito Yuta Nakahara Yuji Iikubo Toshiyasu Matsushima Department of Applied Mathematics Waseda University Tokyo Japan Faculty of Informatics Gunma University Gunma Japan Center for Data Science Waseda University Tokyo Japan

ISBN: (数字)9784885523410

ISBN: (纸本)9781665499071

In this paper, we propose the data generative model in which a target population is divided into several latent classes, and the probability distribution of responses within each latent class is the same under a given treatment. We call this model the Uniform Response Latent Class model (URLC model). Under the proposed model, we calculate Bayesian optimal decision and its approximation algorithm for the difference with and without the treatment for the entire population. We conduct experiments and confirm the following characteristics of the proposed algorithm: 1) our algorithm correctly estimates the true number of latent classes even if the number of latent classes is not known. 2) given the synthetic data generated from the proposed model, the mean square error is smaller than the conventional method. 3) when the class tendency is different, the mean square error is smaller than the conventional method. 4) given the synthetic data from SEM, our propose method works well.

关键词： Estimation Mean square error methods Approximation algorithms data models Probability distribution Bayes methods Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Multiple Teachers-Meticulous Student: A Domain Adaptive Meta-Knowledge Distillation Model for Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Nabavi, Shahabedin Hamedani, Kian Anvari Moghaddam, Mohsen Ebrahimi Abin, Ahmad Ali Frangi, Alejandro F. Faculty of Computer Science and Engineering Shahid Beheshti University Tehran Iran Division of Informatics Imaging and Data Sciences Schools of Computer Science and Health Sciences The University of Manchester Manchester United Kingdom Electrical Engineering and Cardiovascular Sciences Departments KU Leuven Leuven Belgium Alan Turing Institute London United Kingdom

Background: Image classification can be considered one of the key pillars of medical image analysis. Deep learning (DL) faces challenges that prevent its practical applications despite the remarkable improvement in medical image classification. The data distribution differences can lead to a drop in the efficiency of DL, known as the domain shift problem. Besides, requiring bulk annotated data for model training, the large size of models, and the privacy-preserving of patients are other challenges of using DL in medical image classification. This study presents a strategy that can address the mentioned issues simultaneously. Method: The proposed domain adaptive model based on knowledge distillation can classify images by receiving limited annotated data of different distributions. The designed multiple teachers-meticulous student model trains a student network that tries to solve the challenges by receiving the parameters of several teacher networks. The proposed model was evaluated using six available datasets of different distributions by defining the respiratory motion artefact detection task. Results: The results of extensive experiments using several datasets show the superiority of the proposed model in addressing the domain shift problem and lack of access to bulk annotated data. Besides, the privacy preservation of patients by receiving only the teacher network parameters instead of the original data and consolidating the knowledge of several DL models into a model with almost similar performance are other advantages of the proposed model. Conclusions: The proposed model can pave the way for practical clinical applications of deep classification methods by achieving the mentioned objectives simultaneously. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Statistical Distance-Guided Unsupervised Domain Adaptation for Automated Multi-Class Cardiovascular Magnetic Resonance Image Quality Assessment

arXiv

引用

arXiv 2024年

This study proposes an attention-based statistical distance-guided unsupervised domain adaptation model for multi-class cardiovascular magnetic resonance (CMR) image quality assessment. The proposed model consists of a feature extractor, a label predictor and a statistical distance estimator. An annotated dataset as the source set and an unlabeled dataset as the target set with different statistical distributions are considered inputs. The statistical distance estimator approximates the Wasserstein distance between the extracted feature vectors from the source and target data in a mini-batch. The label predictor predicts data labels of source data and uses a combinational loss function for training, which includes cross entropy and centre loss functions plus the estimated value of the distance estimator. Four datasets, including imaging and k-space data, were used to evaluate the proposed model in identifying four common CMR imaging artefacts: respiratory and cardiac motions, Gibbs ringing and Aliasing. The results of the extensive experiments showed that the proposed model, both in image and k-space analysis, has an acceptable performance in covering the domain shift between the source and target sets. The model explainability evaluations and the ablation studies confirmed the proper functioning and effectiveness of all the model's modules. The proposed model outperformed the previous studies regarding performance and the number of examined artefacts. The proposed model can be used for CMR post-imaging quality control or in large-scale cohort studies for image and k-space quality assessment due to the appropriate performance in domain shift coverage without a tedious data-labelling process. Copyright © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Paddy Diseases Multi-Class Classification using CNN Variants

Paddy Diseases Multi-Class Classification using CNN Variants

引用

Information Technology (ACIT)

作者： Danial Izzat Anwar Bin Abdul Aziz Marina Yusoff Nurain Ibrahim Raed Alazaidah College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Malaysia Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan

Agriculture is critical to ensuring and securing food supply for human consumption. Paddy crops are an agricultural practice that produces one of the highest food yields in agriculture. Paddy diseases must now be detected and diagnosed as soon as possible rather than later. Farmers currently use the naked eye to observe suspected infected paddies. The suspected infected paddy will then be sampled and sent to the laboratory for further examination. These methods are highly inefficient, time-consuming, and error prone. Most paddy farmers lack the knowledge to make an informed and accurate diagnosis of which paddies are infected by which diseases. This paper explores using deep learning algorithms to detect and classify various paddy diseases automatically. This method will take an image of paddy leaves and classify it based on the disease category indicated by the idea. The PaddyDoctor dataset from the Kaggle website was used to train and test the deep-learning models. Convolutional Neural Network (CNN) and Transfer Learning models, including MobileNet, MobileNetv2, and InceptionV3, have been constructed. The results of an experiment involving different dataset split ratios, learning rates, and batch sizes. CNN with MobileNetV2 outperformed CNN with MobileNetV1 and CNN with InceptionV3 by 98.05 percent, 80.08 percent, and 83.98 percent, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Echo-E3Net: Efficient Endo-Epi Spatio-Temporal Network for Ejection Fraction Estimation

arXiv

引用

arXiv 2025年

作者： Heidari, Moein Bozorgpour, Afshin Zarif-Fakharnia, AmirHossein Merhof, Dorit Hacihaliloglu, Ilker School of Biomedical Engineering University of British Columbia VancouverBC Canada Faculty of Informatics and Data Science University of Regensburg Regensburg Germany School of Electrical Engineering Iran University of Science and Technology Tehran Iran Department of Radiology University of British Columbia VancouverBC Canada Department of Medicine University of British Columbia VancouverBC Canada

Left ventricular ejection fraction (LVEF) is a critical metric for assessing cardiac function, widely used in diagnosing heart failure and guiding clinical decisions. Despite its importance, conventional LVEF estimation remains time-consuming and operator-dependent. Recent deep learning advancements have enhanced automation, yet many existing models are computationally demanding, hindering their feasibility for real-time clinical applications. Additionally, the interplay between spatial and temporal features is crucial for accurate estimation but is often overlooked. In this work, we propose Echo-E3Net, an efficient Endo-Epi spatio-temporal network tailored for LVEF estimation. Our method introduces the Endo-Epi Cardial Border Detector (E2CBD) module, which enhances feature extraction by leveraging spatial and temporal landmark cues. Complementing this, the Endo-Epi Feature Aggregator (E2FA) distills statistical descriptors from backbone feature maps, refining the final EF prediction. These modules, along with a multi-component loss function tailored to align with the clinical definition of EF, collectively enhance spatial-temporal representation learning, ensuring robust and efficient EF estimation. We evaluate Echo-E3Net on the EchoNet-Dynamic dataset, achieving a RMSE of 5.15 and an R2 score of 0.82, setting a new benchmark in efficiency with 6.8 million parameters and only 8.49G Flops. Our model operates without pre-training, data augmentation, or ensemble methods, making it well-suited for real-time point-of-care ultrasound (PoCUS) applications. Our Code is publicly available on GitHub. © 2025, CC BY-NC-SA.

关键词：

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：