检索结果-内蒙古大学图书馆

Dealing with Imbalanced Dataset Leveraging Boundary Samples Discovered by Support Vector Data Description

computers, Materials & Continua 2021年第3期66卷 2691-2708页

作者： Zhengbo Luo Hamïd Parvïn Harish Garg Sultan Noman Qasem Kim-Hung Pho Zulkefli Mansor Graduate School of Information Production and SystemsWaseda UniversityTokyoJapan Institute of Research and Development Duy Tan UniversityDa Nang550000Vietnam Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Department of Computer Science Nourabad Mamasani BranchIslamic Azad UniversityMamasaniIran School of Mathematics Thapar Institute of Engineering and TechnologyDeemed UniversityPatialaPunjab147004India Computer Science Department College of Computer and Information SciencesAl Imam Mohammad Ibn Saud Islamic UniversityRiyadhSaudi Arabia Computer Science Department Faculty of Applied ScienceTaiz UniversityTaizYemen Fractional Calculus Optimization and Algebra Research GroupFaculty of Mathematics and StatisticsTon Duc Thang UniversityHo Chi Minh CityVietnam Fakulti Teknologi dan Sains Maklumat Universiti Kebangsaan MalaysiaSelangorMalaysia

These days,imbalanced datasets,denoted throughout the paper by ID,(a dataset that contains some(usually two)classes where one contains considerably smaller number of samples than the other(s))emerge in many real world problems(like health care systems or disease diagnosis systems,anomaly detection,fraud detection,stream based malware detection systems,and so on)and these datasets cause some problems(like under-training of minority class(es)and over-training of majority class(es),bias towards majority class(es),and so on)in classification process and ***,these datasets take the focus of many researchers in any science and there are several solutions for dealing with this *** main aim of this study for dealing with IDs is to resample the borderline samples discovered by Support Vector Data Description(SVDD).There are naturally two kinds of resampling:Under-sampling(U-S)and oversampling(O-S).The O-S may cause the occurrence of over-fitting(the occurrence of over-fitting is its main drawback).The U-S can cause the occurrence of significant information loss(the occurrence of significant information loss is its main drawback).In this study,to avoid the drawbacks of the sampling techniques,we focus on the samples that may be *** data points that can be misclassified are considered to be the borderline data points which are on border(s)between the majority class(es)and minority class(es).First by SVDD,we find the borderline examples;then,the data resampling is applied over *** the next step,the base classifier is trained on the newly created ***,we compare the result of our method in terms of Area Under Curve(AUC)and F-measure and G-mean with the other state-of-the-art *** show that our method has betterresults than the other state-of-the-art methods on our experimental study.

关键词： Imbalanced learning classification borderline examples

来源：评论

学校读者我要写书评

暂无评论

Machine Vision Inspection of Early Failure and Line-Shaped Defects of Blue Ingan/Gan Light Emitting Diodes Soaked in Liquid Nitrogen for Cryogenic Tests

SSRN

引用

SSRN 2023年

作者： Yang, Chun-Yen Yu, Chih-Yuan Lin, You-Li Hon, Mou-Tuong Yang, Shao-Jui Zhang, Yi-Zong Kang, Hsuan-Chia Kuo, Yaw-Wen Lin, Chia-Feng Wu, You-Lin Chou, Hsin-Hung Chen, Hsiang Li, Yung-Hui Han, Jung Department of Electrical Engineering National Chi Nan University Nantou54561 Taiwan Department of Applied Materials and Optoelectronic Engineering National Chi Nan University Nantou54561 Taiwan Department of Computer Science and Information Engineering National Chi Nan University Nantou54561 Taiwan Department of Materials Science and Engineering National Chung Hsing University Taichung40227 Taiwan AI Research Center Hon Hai Research Institute Taipei11494 Taiwan Department of Electrical Engineering Yale University New HavenCT06511 United States National Chi Nan University Taiwan

Cryogenic tests were performed on blue InGaN/GaN light emitting diodes (LEDs) by placing the device in liquid nitrogen (LN2). To study the degradation of the LEDs, a combination of optical, electrical, material characterizations were conducted on the LN2 soaked device. Results indicate that noticeable emission spectral shifts were observed during the LED immersion owing the lattice deformation. Moreover, clustering of cracks were generated in the cross–section and line-shaped defects came up on the surface of GaN LED, which was different from the defects on AlInGaP LEDs after LN2 immersion. To track the trend of device damage, computer-assisted opencv-python software were used to zoom in nuanced variations on the certain areas of the emission images. Early degradation of certain areas can be detected by computer-assisted machine vision, which has potential to provide early warning and protective circuits for the system consisting of the initial degraded LEDs. Reliability studies on LN2-soaking InGaN/GaN LEDs show promises to study the reliability issues of GaN device applications in arctic regions and space exploration. © 2023, The Authors. All rights reserved.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

One Set to Rule Them All: How to Obtain General Chemical Conditions via Bayesian Optimization over Curried Functions

arXiv

引用

arXiv 2025年

作者： Schmid, Stefan P. Rajaonson, Ella Miray Ser, Cher Tian Haddadnia, Mohammad Leong, Shi Xuan Aspuru-Guzik, Alán Kristiadi, Agustinus Jorner, Kjell Strieth-Kalthoff, Felix Institute of Chemical and Bioengineering Department of Chemistry and Applied Biosciences ETH Zurich ZurichCH-8093 Switzerland Catalysis ETH Zurich ZurichCH-8093 Switzerland Department of Chemistry University of Toronto Toronto Canada Vector Institute Toronto Canada Department of Biological Chemistry & Molecular Pharmacology Harvard University CambridgeMA United States Dana-Farber Cancer Institute BostonMA United States School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singarpore Singapore Department of Computer Science University of Toronto Toronto Canada Department of Chemical Engineering and Applied Chemistry University of Toronto Toronto Canada Department of Materials Science and Engineering University of Toronto Toronto Canada Acceleration Consortium University of Toronto Toronto Canada Canada School of Mathematics and Natural Sciences University of Wuppertal Wuppertal Germany

General parameters are highly desirable in the natural sciences — e.g., chemical reaction conditions that enable high yields across a range of related transformations. This has a significant practical impact since those general parameters can be transferred to related tasks without the need for laborious and time-intensive re-optimization. While Bayesian optimization (BO) is widely applied to find optimal parameter sets for specific tasks, it has remained underused in experiment planning towards such general optima. In this work, we consider the real-world problem of condition optimization for chemical reactions to study how performing generality-oriented BO can accelerate the identification of general optima, and whether these optima also translate to unseen examples. This is achieved through a careful formulation of the problem as an optimization over curried functions, as well as systematic evaluations of generality-oriented strategies for optimization Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ML_Recognition: A Robust Model for Handwritten Digit Recognition Using Machine Learning Classifiers

ML_Recognition: A Robust Model for Handwritten Digit Recogni...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Diaa Salama AbdElminaam Magda M. Madbouly Magdy Abd-Elghany Zeid Laith Abualigah Faculty of Computer Science Misr International University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Computer and Data Science Alexandria University Alexandria Egypt Ibrahim Abd Elatif Gomaa Computer Science Department Alobour high institute for computer and informatics Cairo Egypt Computer Science Department Al al-Bayt University Mafraq Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan MEU Research Unit Middle East University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya Malaysia

Handwritten digit recognition is a branch of machine learning in which a computer is taught to recognize hand-written numbers. Classification and regression are applied using deep learning and machine learning algorithms. In this paper, we discussed the efficiency of different algorithms: Random Forest, KNN, Naive Bayes, SVM, CNN, and Decision Tree Algorithm. Those algorithms were applied in the handwritten digit recognition process using the MINIST data set. By comparing each algorithm by training every one of them on the data set, then by testing, we got the best algorithm to get the optimal results with the highest accuracy. After comparing the results of each algorithm, it has shown that the neural network has the best results with 97.3% classification accuracy followed by K- the nearest neighbor with 97.2%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of LSTM-based Deep Learning Models for HAR using Smartphone Sensor 6

Comparative Analysis of LSTM-based Deep Learning Models for ...

引用

Joint 6th International Conference on Digital Arts, Media and Technology with 4th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunication engineering, ECTI DAMT and NCON 2021

作者： Rojanavasu, Pornthep Jitpattanakul, Anuchit Mekruksavanich, Sakorn University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665415699

Due to rapid advancement of wearable sensor technology, Human Activity Recognition (HAR) using smartphone sensors data are becoming a trendy research topic there are many mobile applications adopting from outstanding HAR researches such as health monitoring, performance tracking of sport, and etc. In the last decade, machine learning methods have been introduced to solve the HAR problem. However, the conventional approaches were limited their performance in the process of feature extraction. With the limitation, deep learning approaches have been recently presented with outstanding performances. This paper proposed a comparative analysis of deep learning techniques for HAR using sensor data captured from accelerometer and gyroscope. In the proposed study, we employ various types of Convolutional Neural Networks (CNNs) with Long Short-Term Memory Networks (LSTMs), disregarding the needs for hand-crafted feature extraction the comparative results indicate that the hybrid LSTM outperforms baseline models. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Detection of Freezing of Gait in Parkinson's Disease by Squeeze-and-Excitation Convolutional Neural Network with Wearable Sensors 15

Detection of Freezing of Gait in Parkinson's Disease by Sque...

引用

15th International Conference on Open Source Systems and Technologies, ICOSST 2021

作者： Mekruksavanich, Sakorn Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665413053

It is one of the most severe motor indications of Parkinson's disease that one's stride becomes freezing of gait (FOG). Patients' quality of life is negatively impacted by FOG, which may lead to falls. Typically, questionnaires have been used to diagnose FOG;however, this method is subjective and may not correctly represent the severity of this disorder. It is possible to monitor symptoms using sensor-based devices, which can provide reliable and objective data. In this paper, the SE-DeepConvNet, a compact deep convolutional neural network including squeeze-and-excite components for fog detection, was proposed. In conducted to evaluate SE-DeepConvNet, we employed Daphnet, a publicly accessible benchmark FOG dataset. In terms of effectiveness, the SE-DeepConvNet excels most traditional deep learning models, receiving a score of 95.66% on the accuracy evaluation. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network and Data Augmentation for Behavioral-Based Biometric User Identification 5th

Convolutional Neural Network and Data Augmentation for Behav...

引用

5th International Conference on ICT for Sustainable Development, ICT4SD 2020

作者： Mekruksavanich, Sakorn Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9789811582882

One classification problem that is especially challenging is biometric identification, which links cybersecurity to the analysis of human behavior. Biometric data can be collected through the use of wearable devices, especially smartphones that incorporate a variety of sensors, during the performance of activities by the users. In recent research, numerous identification systems using machine learning classification algorithms have been proposed to provide solutions to this classification problem. However, their ability to perform identification is limited to only suitable selected features of time-series data from the biometric raw data. Therefore, in this study, an architecture for the biometric user identification using walking patterns that employs a convolutional neural network is proposed. Validation of the proposed framework for biometric identification was accomplished through the generation of synthetic data from datasets of samples from public walking. As a result, the framework described in this study provides more effective outcomes in terms of the accuracy of the model and additional metrics than the conventional machine learning utilized for biometric user identification. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Cancer Death Cases Forecasting using Supervised Machine Learning

Cancer Death Cases Forecasting using Supervised Machine Lear...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Sheshang Degadwala Dhairya Vyas Ankita Kothari Urmila Khunt Computer Engineering Department Sigma University Vadodara Gujarat The Maharaja Sayajirao University of Baroda Vadodara Gujarat India Dept. of Comp. Sci. & Eng. Krishna School Of Emerging Technology And Applied Research KPGU Vadodara Computer Science Engineering ITM vocational University Vadodara

In India, like in the rest of the world, cancer is a major killer. This research objective is to predict cancer mortality in India, using supervised machine learning methods. Cancer mortality rates in India between 1990 and 2017 are provided by age group, gender, and region using data from the Global Burden of Disease Study. We employ three distinct supervised learning algorithms—linear regression, decision tree regression, and random forest regression—after performing data preprocessing, which includes missing value imputation and feature engineering. Using a variety of criteria, we analyze the effectiveness of these models and conclude that the random forest regression model is superior to the other two. The scope of research is provide a long-term prediction of cancer mortality in India using the best model so it will help health department to work on it. Our research has implications for policymakers and healthcare providers in India, where it may inform efforts to reduce cancer rates and improve cancer care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synthesis and Prediction of Anemia from Multi-Data Attribute Co-Existence

引用

IEEE Access 2024年

作者： Qadah, Talal Munshi, Asmaa King Abdulaziz University Faculty of Applied Medical Sciences Department of Medical Laboratory Sciences Jeddah Saudi Arabia King Abdulaziz University Hematology Research Unit King Fahad Medical Research Center Jeddah Saudi Arabia University of Jeddah College of Computer Science and Engineering Jeddah21959 Saudi Arabia

The medical community has recognized that when a single attribute or variable is consistently proven to be a definitive indicator of a disease state, it is generally considered the standard. However, with the progress of Information and Communication Technology, particularly Artificial Intelligence, many other attributes can now contribute to determining certain diseases to varying extents. Therefore, this study has reevaluated the claims within the domain of detecting and predicting Anemia with the best machine learning algorithm. While previous studies on predicting Anemia used limited machine learning algorithm within limited range of datasets, this current study utilized many machine leaning algorithms with broad categories of Anemia dataset and formulate three hypotheses that were tested. Statistical analysis indicated that all the hypotheses are accepted. It was also reviled that when it comes to »cross-validation accuracy,» »AdaBoost» performs the best with 92.8%. On the other hand, when it comes to »Test accuracy,» »Precision» of »Non-Anemic,» and the »Recall» of »Anemic,» »Random Forest» and »XGBoost» both perform the best with values of 0.863, 0.89, and 0.96 respectively. However, »XGBoost» performed the best in terms of ROC-AUC score, with a value of 0.9447. Due to the fact that this research came to the conclusion that there is no particular machine learning that covers the entire performance metric for the prediction of anemia using the anemic parameters, it can be concluded that there is always a need for an ensemble approach, and that the intervention of doctors is still very necessary in cases of anemia. © 2013 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Process Analysis of the Online Course Development 16th

Process Analysis of the Online Course Development

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2020

作者： Sambuu, Uyanga Tuul, Suvdmaa Banzragch, Otgontugs Mend, Narantuya Department of Information and Computer Science NUM’s School of Engineering and Applied Sciences Ulaanbaatar Mongolia Cabinet Secretariat of the Government of Mongolia Ulaanbaatar Mongolia Department of Economics NUM’s School of Sciences Ulaanbaatar Mongolia Department of Education and Psychology NUM’s School of Sciences Ulaanbaatar Mongolia

ISBN: (纸本)9789813367562

The current article presents the results of the analysis of the online course development process on the example of a 2-credit hour English course taught for the master students of the Mongolian National University of Medical sciences (MNUMS). The rationale was to determine, understand the processes of the online course development, define its inputs and outputs of each process, and compare it with the traditional course. The purpose is to conduct a process analysis of online course development. ADDIE framework was used for process analysis. The business process can be divided into two scenarios such as "as-is" which depicts the current state, "to-be" which presents the future state. The current state process analysis revealed that 30 activities lasted for 138 business days to develop and deliver the course. "To-be" or future state has two scenarios. We’ve estimated that the "to-be" state to last for 147.5 days for higher education institutions (HEIs) without the studio, 188 days for HEIs with the studio for the online course development, delivery, and evaluation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： E-learning

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：