检索结果-内蒙古大学图书馆

Frontiers of Information Technology (FIT)

作者： Muhammad Umar Khan Sumair Aziz Khushbakht Iqtidar Raul Fernandez Rojas Department of Electronics Engineering University of Engineering and Technology Taxila Taxila Pakistan Department of Computer Software Engineering National University of Sciences and Technology Islamabad Pakistan Faculty of Science & Technology University of Canberra Canberra Australia

ISBN: (纸本)9798350345940

Preterm deliveries are an important cause of mortality and morbidity in newborns. Accurate and early prediction of a premature delivery can prove helpful in providing proper medication and treatment. Recording of electrical activity known as Electrohysterogram (EHG) from the abdominal surface of pregnant women corresponds to the uterus contractions. A new direction is open using EHG signals for the diagnosis of preterm births. In this research, we present a new method for the accurate classification of preterm and term EHG signals. The proposed method first filters a three-channel EHG signal using bandpass filters. Next, we combined the filtered three-channel EHG into one signal using an accumulation operation. The accumulated EHG signal was post-processed through variational mode decomposition (VMD). VMD algorithm splits the input signal into finite modes using center frequencies known as intrinsic mode functions (IMFs). An energy-based intelligent signal reconstruction approach is designed to combine IMFs having an energy level above the computed threshold. Next, the reconstructed EHG signals were split into continuous windows, and time, frequency, and Hjorth features were extracted. These features were fused to construct a distinct feature representation and were reduced using the ReliefF algorithm. We trained an artificial neural network (ANN) to obtain 98.8 % average accuracy using 10-fold cross-validation.

关键词： Band-pass filters Time-frequency analysis Artificial neural networks Filtering algorithms Feature extraction Signal reconstruction Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Automatic recommendation to appropriate log levels

Automatic recommendation to appropriate log levels

引用

作者： Kim, Taeyoung Kim, Suntae Park, Sooyong Park, YoungBeom Department of Software Engineering Chonbuk National University Korea Republic of Department of Computer Science & Engineering Sogang University Korea Republic of Department of Software Dankook University Korea Republic of

A log statement is one of the key tactics for a developer to record and monitor important run-time behaviors of our system in a development phase and a maintenance phase. It composes of a message for stating log contents, and a log level (eg, debug or warn) to denote the severity of a message and controlling its visibility at run time. In spite of its usefulness, a developer does not tend to deeply consider which log level is appropriate in writing source code, which causes the system to be unmaintainable. To address this issue, this paper proposes an automatic approach to validating the appropriateness of the log level in consideration of the semantic and syntactic features and recommending a proper alternative log level. We first build the semantic feature vector to quantify the semantic similarity among application log messages using the word vector space, and the syntactic feature vector to capture the application context that surrounds the log statement. Based on the feature vectors and machine learning techniques, the log level is automatically validated, and an alternative log level is recommended if the log level is invalid. For the evaluation, we collected 22 open-source projects from three application domains, and obtained the 77% of precision and 75% of recall in validating the log levels. Also, our approach showed 6% higher accuracy than that of the developer group who has 7 to 8 years of work experience, and 72% of the developers accepted our recommendation. © 2019 John Wiley & Sons, Ltd.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Classification of Alzheimer’s Disease Using Frontal Cortex Non-invasive fNIRS 8th

Multi-Class Classification of Alzheimer’s Disease Using Fro...

引用

8th International Conference on the Development of Biomedical engineering, BME8 2020

作者： Ho, Thi Kieu Khanh Kim, Minhee Garg, Harish Kim, Byeong C. Lee, Jang Jae Choi, Kyu Yeong Kim, Jae Gwan Lee, Kun Ho Song, Jong-In Gwak, Jeonghwan School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Department of Biomedical Science and Engineering Institute of Science and Technology Gwangju61005 Korea Republic of School of Mathematics Thapar Institute of Engineering and Technology Deemed University Patiala Punjab147004 India Department of Neurology Chonnam National University Medical School Gwangju61469 Korea Republic of Cohort Research Center Chosun University Gwangju61452 Korea Republic of Department of Biomedical Science Chosun University Gwangju61452 Korea Republic of Aging Neuroscience Research Group Korea Brain Research Institute Daegu41062 Korea Republic of Department of Software Korea National University of Transportation Chungju27469 Korea Republic of

ISBN: (纸本)9783030755058

Early and accurate diagnosis of Alzheimer’s disease (AD) is especially important for neurodegenerative disorders allowing patients, who exhibit different patterns of severity and progression risks, to take prevention and treatments before brain damages are shaped. Functional Near-Infrared Spectroscopy (fNIRS), as a clinical test, can be employed in an ecological setting to support AD diagnosis at early stages. In this study, we aimed to comprehensively study the hemodynamic response patterns among four subject groups from 140 participants by visualizing the 4-class distributions based on t-SNE visualization techniques and showing the fNIRS topographic mapping to have a pictorial representation on the surface of the prefrontal cortex region. We demonstrated that the changes in hemodynamic concentrations of oxygenated hemoglobin (HbO) and deoxygenated hemoglobin (Hb) from healthy controls to three stages of AD did exist during four stages of our experimental protocols. Results also revealed that various machine learning techniques were capable of both analyzing AD patterns and its related features and classifying multiple pathophysiologic mechanisms with the highest accuracies of 74.39 ± 4.7% and 84.91 ± 4.01% corresponding to raw and SMOTE-based features, respectively. These findings demonstrate the feasibility of fNIRS-based approaches to investigate the stages of AD progression. © 2022, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Modeling the One Class of Radionuclide Migration Processes in Soils under Non-Isothermal Conditions Using Perturbation Theory Methods

Modeling the One Class of Radionuclide Migration Processes i...

引用

International Conference on Advanced computer Information Technologies (ACIT)

作者： Andrii Bomba Oksana Ostapchuk Roman Vovk Miroslav Kopnický Department of Computer Science and Applied Mathematics National University of Water and Environmental Engineering Rivne Ukraine Department of Software Engineering Ivano-Frankivsk National Technical University of Oil and Gas Ivano-Frankivsk Ukraine Department of Catholic Theology Catholic University in Ružomberok Spišská Kapitula Slovakia

Based on the synthesis of complex analysis methods, perturbation theory, and characteristics, a new approach has been developed for accounting for osmosis and temperature in predicting the migration processes of radionuclides under non-isothermal conditions in quasi-ideal porous media (in curved regions) bounded by streamlines and equipotential lines. The solution to the corresponding degenerate problem was obtained based on the developed method of nonlinear inversion of boundary value problem solutions into quasi-conformal mappings. An algorithm for calculating a uniformly dynamic grid, streamlines, and speed of ideal filtration field was constructed. With the developed method of characteristics, formulas for the approximate solution of diffusion-convection mass transfer problems in perturbed osmosis and heat filtration fields were obtained.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Message from program committee

2021 International Conference on Code Quality, ICCQ 2021

引用

2021 International Conference on Code Quality, ICCQ 2021 2021年 5-5页

作者： Zykov, Sergey V. Software Engineering Department Computer Science Faculty Hse University Moscow Russia

来源：评论

学校读者我要写书评

暂无评论

Sexism Discovery using CNN, Word Embeddings, NLP and Data Augmentation

Sexism Discovery using CNN, Word Embeddings, NLP and Data Au...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Jaouhar Fattahi Feriel Sghaier Mohamed Mejri Ridha Ghayoula Sahbi Bahroun Marwa Ziadia Department of Computer Science and Software Engineering Laval University Quebec Canada DArS DGSSI MCN Québec Canada Carthage National Engineering School Carthage University Tunis Tunisia Faculty of Engineering University of Moncton New Brunswick Canada Institut Supérieur d’Informatique Tunis El-Manar University Tunis Tunisia

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

The pervasive issue of online sexism continues to pose significant challenges, fostering environments characterized by toxicity and perpetuating harmful societal norms. In response, this paper presents an approach for the discovery of sexist statements employing convolutional neural networks (CNNs), Word Embeddings, and data augmentation techniques. Through the fusion of CNNs’ capacity for hierarchical feature extraction with the semantic representations afforded by Word Embeddings, our method achieves exemplary discrimination performance. Additionally, the incorporation of data augmentation enriches the training dataset, thereby augmenting model generalization and resilience. Empirical evaluation on a larger dataset of statements demonstrates the efficacy of our approach, surpassing many baseline approaches in terms of discovery accuracy, precision, recall and F1-score.

关键词： Training Adaptation models Toxicology Semantics Training data Data augmentation Natural language processing Data models Convolutional neural networks Resilience

来源：评论

学校读者我要写书评

暂无评论

A Framework for Autonomous Vehicle Testing Using Semantic Models

A Framework for Autonomous Vehicle Testing Using Semantic Mo...

引用

IEEE International Conference on Artificial Intelligence Testing (AITest)

作者： Yejun He Muslim Razi Jerry Gao Chuanqi Tao Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Computer Engineering Department and Applied Data Science Department San Jose State University San Jose USA

With the rapid development of big data and artificial intelligence, autonomous vehicles (AV) have achieved great success in diverse application domains. Although the current development of autonomous driving technology has been greatly improved, the accident rate of driverless vehicles still rises. Therefore, how to ensure the quality of AVs using different testing technologies has become an important issue. Traditional testing approaches such as decision tables and state charts struggle with diversified test inputs. Hence, there is a strong demand for new test models for AV testing. In this paper, we present a model-based testing framework that utilizes semantic trees and 3-dimensional (3D) test tables to model driving scenarios into individual test cases. Using the proposed framework, we generate fine-grained examples corresponding to the real world. Also, we evaluate the behavior of the Apollo AV system in 30 scenarios in SVL simulator. The results show that the scenarios generated by our framework can cover most conditions occurring, thus addressing the challenge of testing AVs for safety and reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing and Comparing Results for Multiple Machine Learning Models

Analyzing and Comparing Results for Multiple Machine Learnin...

引用

computer engineering and Intelligent Control (ICCEIC) International Conference on

作者： Jefferson Ng Yijian Li Xuxiao Ji Can Yang Jiaqiao Wan Xingyu Lu Department of Mechanical Engineering University of California Irvine USA Courant Institute of Mathematical Sciences New York University NY USA School of Computer Science University of Waterloo Waterloo CA Department of Electrical Engineering and Computer Science Oregon State University Corvallis USA Software College Zhengzhou University Zhengzhou China United World College Changshu China Jiangsu China

In the contemporary landscape of atmospheric sciences, the ability to recognize specific weather phenomena accurately and efficiently has become paramount, largely due to the exponential growth in sensor-generated data. This paper undertakes an in-depth analysis of advanced algorithms, namely YOLOV8, ResNet50, and Convolutional Neural Networks (CNN), for the purpose of weather pattern identification and classification. Building on the foundation of deep learning, the YOLOV8's real-time object detection capabilities are leveraged to discern intricate weather patterns in diverse datasets, from meteorological stations to satellite imagery. On the other hand, Resnet 50 which is another CNN based model was also tested along with CNN for comparison. An exhaustive evaluation of these algorithms covers various metrics, including accuracy, precision, computational efficiency, and real-world applicability. Special emphasis is placed on the crucial stages of data preprocessing, feature extraction, and model tuning, highlighting their impact on the algorithms' overall performance. Our findings suggest that, when appropriately optimized, both YOLOV8 and CNN exhibit exceptional capabilities in discerning and classifying intricate weather patterns, whereas ResNet50 exhibits comparatively less performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open-Vocabulary Affordance Detection in 3D Point Clouds

arXiv

引用

arXiv 2023年

作者： Nguyen, Toan Vu, Minh Nhat Vuong, An Nguyen, Dzung Vo, Thieu Le, Ngan Nguyen, Anh FPT Software AI Center Viet Nam VNUHCM-University of Science Ho Chi Minh City Viet Nam TU Wien Vienna Austria Vienna Austria Faculty of Mathematics and Statistics Ton Duc Thang University Ho Chi Minh City Viet Nam Department of Computer Science & Computer Engineering University of Arkansas United States Department of Computer Science University of Liverpool United Kingdom

Affordance detection is a challenging problem with a wide variety of robotic applications. Traditional affordance detection methods are limited to a predefined set of affordance labels, hence potentially restricting the adaptability of intelligent robots in complex and dynamic environments. In this paper, we present the Open-Vocabulary Affordance Detection (OpenAD) method, which is capable of detecting an unbounded number of affordances in 3D point clouds. By simultaneously learning the affordance text and the point feature, OpenAD successfully exploits the semantic relationships between affordances. Therefore, our proposed method enables zero-shot detection and can be able to detect previously unseen affordances without a single annotation example. Intensive experimental results show that OpenAD works effectively on a wide range of affordance detection setups and outperforms other baselines by a large margin. Additionally, we demonstrate the practicality of the proposed OpenAD in real-world robotic applications with a fast inference speed. Our project is available at https://***. © 2023, CC0.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

S-Rocket: Selective Random Convolution Kernels for Time Series Classification

arXiv

引用

arXiv 2022年

作者： Salehinejad, Hojjat Wang, Yang Yu, Yuanhao Jin, Tang Valaee, Shahrokh The Department of Electrical & Computer Engineering University of Toronto Toronto Canada The Noah's Ark Laboratory Huawei Technologies Co. Ltd Canada Toronto Canada Department of Computer Science and Software Engineering Concordia University Montreal Canada

Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-D convolution kernels of different configurations. The output of the convolution operation on each time series is represented by a partial positive value (PPV). A concatenation of PPVs from all kernels is the input feature vector to a Ridge regression classifier. Unlike typical deep learning models, the kernels are not trained and there is no weighted/trainable connection between kernels or concatenated features and the classifier. Since these kernels are generated randomly, a portion of these kernels may not positively contribute in performance of the model. Hence, selection of the most important kernels and pruning the redundant and less important ones is necessary to reduce computational complexity and accelerate inference of Rocket for applications on the edge devices. Selection of these kernels is a combinatorial optimization problem. In this paper, we propose a scheme for selecting these kernels while maintaining the classification performance. First, the original model is pre-trained at full capacity. Then, a population of binary candidate state vectors is initialized where each element of a vector represents the active/inactive status of a kernel. A population-based optimization algorithm evolves the population in order to find a best state vector which minimizes the number of active kernels while maximizing the accuracy of the classifier. This activation function is a linear combination of the total number of active kernels and the classification accuracy of the pre-trained classifier with the active kernels. Finally, the selected kernels in the best state vector are utilized to train the Ridge regression classifier with the selected kernels. This approach is evaluated on the standard time series datasets and the results show that on average it can achieve a similar performance to

关键词： Time series

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：