检索结果-内蒙古大学图书馆

Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep learning Models: A Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jafari, Mahboobeh Shoeibi, Afshin Khodatars, Marjane Ghassemi, Navid Moridian, Parisa Delfan, Niloufar Alizadehsani, Roohallah Khosravi, Abbas Ling, Sai Ho Zhang, Yu-Dong Wang, Shui-Hua Gorriz, Juan M. Rokny, Hamid Alinejad Acharya, U. Rajendra Internship in BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Data Science and Computational Intelligence Institute University of Granada Spain Department of Medical Engineering Mashhad Branch Islamic Azad University Mashhad Iran Faculty of Computer Engineering Dept. of Artificial Intelligence Engineering K. N. Toosi University of Technology Tehran Iran Deakin University VIC3217 Australia Australia School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Department of Psychiatry University of Cambridge United Kingdom BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Data Science Hub The University of New South Wales SydneyNSW2052 Australia Research Centre Macquarie University Sydney2109 Australia Ngee Ann Polytechnic Singapore599489 Singapore Dept. of Biomedical Informatics and Medical Engineering Asia University Taichung Taiwan Dept. of Biomedical Engineering School of Science and Technology Singapore University of Social Sciences Singapore

In recent years, cardiovascular diseases (CVDs) have become one of the leading causes of mortality globally. CVDs appear with minor symptoms and progressively get worse. The majority of people experience symptoms such as exhaustion, shortness of breath, ankle swelling, fluid retention, and other symptoms when starting CVD. Coronary artery disease (CAD), arrhythmia, cardiomyopathy, congenital heart defect (CHD), mitral regurgitation, and angina are the most common CVDs. Clinical methods such as blood tests, electrocardiography (ECG) signals, and medical imaging are the most effective methods used for the detection of CVDs. Among the diagnostic methods, cardiac magnetic resonance imaging (CMR) is increasingly used to diagnose, monitor the disease, plan treatment and predict CVDs. Coupled with all the advantages of CMR data, CVDs diagnosis is challenging for physicians due to many slices of data, low contrast, etc. To address these issues, deep learning (DL) techniques have been employed to the diagnosis of CVDs using CMR data, and much research is currently being conducted in this field. This review provides an overview of the studies performed in CVDs detection using CMR images and DL techniques. The introduction section examined CVDs types, diagnostic methods, and the most important medical imaging techniques. In the following, investigations to detect CVDs using CMR images and the most significant DL methods are presented. Another section discussed the challenges in diagnosing CVDs from CMR data. Next, the discussion section discusses the results of this review, and future work in CVDs diagnosis from CMR images and DL techniques are outlined. The most important findings of this study are presented in the conclusion section. © 2022, CC BY-NC-ND.

关键词： Electrocardiography

Comparative Analysis of Five Local Search Operators on Visiting Constrained Multiple Traveling Salesmen Problem

学校读者我要写书评

暂无评论

Comparative Analysis of Five Local Search Operators on Visit...

IEEE Symposium Series on Computational intelligence (SSCI)

作者： Xin-Xin Liu Dong Liu Qiang Yang Xiao-Fang Liu Wei-Jie Yu Jun Zhang College of Computer and Information Engineering Henan Normal University Xinxiang China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang Henan China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China College of Artificial Intelligence Nankai University Tianjin China School of Information Management Sun Yat-sen University Guangzhou China Zhejiang Normal University Jinhua China Chaoyang University of Technology Taichung County Taiwan

ISBN: (纸本)9781728190495

Visiting constrained multiple traveling salesmen problem (VCMTSP) is an extension of the multiple traveling salesmen problem (MTSP). In this problem, each city is restricted to be only accessible to certain salesmen. Since the genetic algorithm (GA) has been widely utilized to solve the traveling salesman problem (TSP), this paper first adapts GA to solve VCMTSP. When solving TSP, local search (LS) methods are usually embedded into GA to refine the found solutions. Therefore, in this paper, we then embed five common LS operators, namely the single insertion method, the swap method, the two-optimization method (2-opt), the three-optimization method (3-opt), and the three-node permutation method (3-permute), into GA to investigate their influence on GA in solving VCMTSP. Extensive experiments on various VCMTSP instances show that LS operators can effectively help GA find more promising solutions. In particular, 2-opt brings the most benefit to GA to achieve promising performance in solving VCMTSP among the five LS operators. Except for 2-opt, the swap and 3-permute LS operators also bring considerable benefit to GA. With these investigations, it is expected that this paper could afford a basic guideline for new learners attempting to study VCMTSP.

关键词： Urban areas Optimization methods Evolutionary computation Traveling salesman problems Search problems Genetic algorithms Guidelines

Towards a computer-assisted assessment of imitation in children with autism spectrum disorder based on a fine-grained analysis

学校读者我要写书评

暂无评论

Humanities and Social Sciences Communications

Humanities and Social Sciences Communications 2025年第1期12卷 1-10页

作者： Rujing Zhang Jingying Chen Xiaodi Liu Guangshuai Wang Yanling Gan Faculty of Artificial Intelligence in Education National Engineering Research Center for E-Learning Central China Normal University Wuhan China School of Media and Technology Liaocheng University Liaocheng China School of Educational Science Kashi University Kashgar China School of Computer Science and Engineering Guangxi Normal University Guilin China

Imitation is considered a fundamental skill for learning in children with autism spectrum disorder (ASD). However, existing assessment methods usually provide a qualitative description of whether children imitate while ignoring individual variability in their imitation ability. Therefore, this study proposes a computer-assisted method for the refined assessment of imitation ability in children with ASD. First, 25 children with ASD and 25 age-matched typically developing (TD) children between 60 and 78 months old were recruited to imitate meaningful actions on objects and nonmeaningful gestures. In this process, several quantitative indicators were applied to quantify the children’s imitation ability based on a fine-grained analysis of their visual attention and motor execution patterns. Then, three classic machine-learning algorithms were employed to explore whether the indicators could efficiently classify children with imitation difficulties. The results indicated that the proposed indicators could provide a detailed description of individual differences in imitation impairment. Also, the high classification performance revealed that the proposed indicators could classify children with and without imitation difficulties. In addition, the findings contributed to research regarding the diagnostic evaluation of children with ASD.

关键词：

Method of Predicting of Trend in the Stock Exchange using ML and DL Algorithms

学校读者我要写书评

暂无评论

Method of Predicting of Trend in the Stock Exchange using ML...

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Gagan Deep Arora Mohammed Faez Hasan Kawerinder Singh Sidhu Vikas Tripathi Dipankar Misra T. Vijaya Kumar Department of Artificial Intelligence(AI) and Machine Learning (ML) Vardhaman College of Engineering Hyderabad Telangana Department of Finance and Banking Sciences Kerbala University Karbala Iraq UIM Uttaranchal University Dehradun Uttarakhand Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Nischintapur Budge Budge Budge Budge Institute of Technology Kolkata West Bengal India Department of Mechanical Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

Stock are the core of every investing portfolio and may be the most commonly used financial tool ever created for accumulating wealth. Now, almost everyone may invest in stocks due to developments in selling technologies that have open up the market. The ordinary user’s interest in the stock market has skyrocketed during the previous several decades. It is crucial to possess a highly precise forecast of a new direction in a sector with such volatile financial conditions as the share market. It is essential that there be a reliable projection of stock prices because of the economic downturn & declining profitability. With the use of ai technology, computer learning’s progressing algorithms are necessary to forecast an ou pas signal (AI). With MS Xls serving as the greatest statistical method in graph & tabular depiction of predictions outcomes, we will employ machine learning Model in our study with an emphasis on Regression Model (Lb), 3 Months Exponential Moving (3MMA), Exponentially Weighted moving (Aes), and Time-Series Forecasting. While implementing LR, we gathered data from Marketwatch for the stocks of Apple (AMZN), Apple (AAPL), and Youtube (Xom). We accurately forecasted the stock market’s direction for the next quarter and assessed accuracy in accordance with measures.

关键词： Video on demand Computational modeling Time series analysis Companies Share prices Predictive models Prediction algorithms

Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Hui Zhang, Qi Yi, Kun Shi, Kaize Niu, Zhendong Cao, Longbing The School of Medical Technology Beijing Institute of Technology Beijing100081 China The School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China The Department of Computer Science Tongji University Shanghai201804 China The Data Science and Machine Intelligence Lab University of Technology SydneyNSW2007 Australia The Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education China The DataX Research Centre School of Computing Macquarie University SydneyNSW2109 Australia

Due to the non-stationary nature, the distribution of real-world multivariate time series (MTS) changes over time, which is known as distribution drift. Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time. Existing methods address distribution drift via adapting to the latest arrived data or self-correcting per the meta knowledge derived from future data. Despite their great success in MTS forecasting, these methods hardly capture the intrinsic distribution changes, especially from a distributional perspective. Accordingly, we propose a novel framework temporal conditional variational autoencoder (TCVAE) to model the dynamic distributional dependencies over time between historical observations and future data in MTSs and infer the dependencies as a temporal conditional distribution to leverage latent variables. Specifically, a novel temporal Hawkes attention mechanism represents temporal factors subsequently fed into feed-forward networks to estimate the prior Gaussian distribution of latent variables. The representation of temporal factors further dynamically adjusts the structures of Transformer-based encoder and decoder to distribution changes by leveraging a gated attention mechanism. Moreover, we introduce conditional continuous normalization flow to transform the prior Gaussian to a complex and form-free distribution to facilitate flexible inference of the temporal conditional distribution. Extensive experiments conducted on six real-world MTS datasets demonstrate the TCVAE’s superior robustness and effectiveness over the state-of-the-art MTS forecasting baselines. We further illustrate the TCVAE applicability through multifaceted case studies and visualization in real-world *** Codes 68Txx Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

Enhanced dysarthria detection in cerebral palsy and ALS patients using WaveNet and CNN-BiLSTM models: A comparative study with model interpretability

学校读者我要写书评

暂无评论

Biomedical Signal Processing and Control 2025年 110卷

作者： Esraa Hassan Abeer Saber Tarek Abd El-Hafeez T. Medhat Mahmoud Y. Shams Department of Machine Learning and Information Retrieval Faculty of Artificial Intelligence Kafrelsheikh University Kafr El-Sheikh 33516 Egypt Information Technology Dept. Faculty of Computers and Artificial Intelligence Damietta University Damietta 34517 Egypt Computer Science Unit Deraya University El-Minia 61765 Egypt Department of Computer Science Faculty of Science Minia University El-Minia 61519 Egypt Department of Electrical Engineering Faculty of Engineering Kafrelsheikh University Kafr El-Sheikh 33516 Egypt

Dysarthria, a motor speech disorder commonly associated with neurological conditions such as cerebral palsy and ALS, poses significant challenges for early diagnosis and intervention. Traditional diagnostic methods often rely on subjective assessments, leading to delays in effective treatment. Recent advances in machine learning and deep learning offer promising avenues for automated dysarthria detection, enabling faster and more reliable assessments. However, these approaches often face challenges in handling diverse languages and operating efficiently on resource-constrained devices. In this study, we leverage the TORGO database with cerebral palsy, ALS, or control subjects, along with a Russian-voice dataset, to explore automated dysarthria classification. We evaluate the performance of machine learning models, including Random Forest Classifier and XGBClassifier, in comparison with state-of-the-art deep learning architectures such as CNN-LSTM. Building upon these findings, we suggest an enhanced WaveNet-based model specifically optimized to capture the temporal characteristics of audio signals across large and diverse datasets. To address real-world challenges, we introduce a Real-Time Adaptation Framework, enabling efficient and accurate dysarthria detection even on resource-constrained devices. Additionally, explainability enhancements using SHAP values and Grad-CAM techniques are integrated, providing insights into the model’s decision-making process and improving its reliability for clinical applications. The suggested WaveNet-based model demonstrates exceptional performance, achieving precision, recall, and F-score values of 0.92040, 0.91979, and 0.91965, respectively, alongside a Matthews Correlation Coefficient (MCC) of 0.89320, outperforming other models. These results highlight the potential of our approach for rapid and reliable dysarthria detection, particularly in multilingual and resource-limited settings. By combining explainability and real-time c

关键词：

Improved decision making with similarity based machine learning: Applications in chemistry

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lemm, Dominik von Rudorff, Guido Falk von Lilienfeld, O. Anatole University of Vienna Faculty of Physics Kolingasse 14-16 ViennaAT-1090 Austria University of Vienna Vienna Doctoral School in Physics Boltzmanngasse 5 ViennaAT-1090 Austria Departments of Chemistry Materials Science and Engineering and Physics University of Toronto St. George Campus TorontoON Canada Vector Institute for Artificial Intelligence TorontoONM5S 1M1 Canada Machine Learning Group Technische Universität Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

Despite the fundamental progress in autonomous molecular and materials discovery, data scarcity throughout chemical compound space still severely hampers the use of modern ready-made machine learning models as they rely heavily on the paradigm,’the bigger the data the better’. Presenting similarity based machine learning (SML), we show an approach to select data and train a model on-the-fly for specific queries, enabling decision making in data scarce scenarios in chemistry. By solely relying on query and training data proximity to choose training points, only a fraction of data is necessary to converge to competitive performance. After introducing SML for the harmonic oscillator and the Rosenbrock function, we describe applications to scarce data scenarios in chemistry which include quantum mechanics based molecular design and organic synthesis planning. Finally, we derive a relationship between the intrinsic dimensionality and volume of feature space, governing the overall model accuracy. © 2022, CC BY.

关键词： Decision making

Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Muchacho, Rafael I Cabral Laha, Riddhiman Pokorny, Florian T. Figueredo, Luis F.C. Chakraborty, Nilanjan Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden Munich Institute of Robotics and Machine Intelligence TUM Germany School of Computer Science University of Nottingham United Kingdom Department of Mechanical Engineering Stony Brook University NY United States

Safety-critical whole-body robot control demands reactive methods that ensure collision avoidance in real-time. Complementarity constraints and control barrier functions (CBF) have emerged as core tools for ensuring such safety constraints, and each represents a well-developed field. Despite addressing similar problems, their connection remains largely unexplored. This paper bridges this gap by formally proving the equivalence between these two methodologies for sampled-data, first-order systems, considering both single and multiple constraint scenarios. By demonstrating this equivalence, we provide a unified perspective on these techniques. This unification has theoretical and practical implications, facilitating the cross-application of robustness guarantees and algorithmic improvements between complementarity and CBF frameworks. We discuss these synergistic benefits and motivate future work in the comparison of the methods in more general cases. Copyright © 2025, The Authors. All rights reserved.

关键词： Optimal control systems

Unsupervised hashing with contrastive information bottleneck

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qiu, Zexuan Su, Qinliang Ou, Zijing Yu, Jianxing Chen, Changyou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China CSE Department SUNY at Buffalo Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines. © 2021, CC BY.

关键词： Semantics