检索结果-内蒙古大学图书馆

Annual Conference on Information Sciences and Systems (CISS)

作者： Ian DeTore John Samsundar Cleon Davis Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD USA Electrical and Computer Engineering Program Johns Hopkins University Laurel MD USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection.

关键词： Time-frequency analysis Multi label classification Machine learning Electrocardiography Myocardium Brain modeling Transformers Data models Electromyography Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

引用

Journal of engineering and Applied Science 2023年第1期70卷 56页

作者： Attouri, Khadija Dhibi, Khaled Mansouri, Majdi Hajji, Mansour Bouzrara, Kais Nounou, Hazem Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine1200 Tunisia Chemical Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Electrical and Computer Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Monastir5019 Tunisia

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%). © 2023, This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic Cataract and Cholesterol Detection System Based on Recurrent Neural Network (RNN): A Comparison with Convolutional Neural Network (CNN) and Siamese Neural Network (SNN) 1

引用

19th International Conference of Intelligent Unmanned Systems, ICIUS 2023

作者： Lie, Zener S. Widodo, Jatmiko A. F. Hanesi, Isabel K. P. Moningka, Matthew R. N. Mariana, Y. Astuti, Winda Akmeliawati, Rini Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Product Design program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Robotics and Automation Research Group School of Electrical and Mechanical Engineering The University of Adelaide North Terrace Campus Adelaide Australia

ISBN: (数字)9789819765911

ISBN: (纸本)9789819765904

In Indonesia, the majority of blindness cases, approximately 81%, are attributed to cataract. Additionally, 35% of the population has higher cholesterol levels than the standard normal range. The lack of specialized medical equipment, such as the slit-lamp (Ruparelia in Dalhousie Med J 49(1), [1]) bio-microscope, and trained professionals, especially in rural areas, make it difficult to detect these conditions through eye examinations. To address this issue, a supervised machine learning method, the Recurrent Neural Network (RNN), has been utilized to create an iris scanner system that can identify cataract and high cholesterol in a patient. This system will classify eyes into three categories, i.e., cataract, high cholesterol, and normal iris. The computer simulations indicate that this technique is more accurate and requires less training time compared to the existing Convolutional Neural Network (ANN) and Siamese Neural Network (SNN)-based method, while achieving 100% accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Adopting Centroid and Bandwidth to Shape Security Line 4

Adopting Centroid and Bandwidth to Shape Security Line

引用

4th IEEE International Conference of computer Science and Information Technology, ICOSNIKOM 2022

作者： Pratiwi, Heni Ispur Kartowisastro, Iman Herwidiana Soewito, Benfano Budiharto, Widodo Doctorate Program School of Computer Science Bina Nusantara University Jakarta Indonesia Bina Nusantara University Binus Graduate Program Doctorate Program of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University Faculty of Engineering Computer Engineering Department Jakarta Indonesia Bina Nusantara University Computer Science Binus Graduate Program Computer Science Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350399073

The voice patterns of gender and age have been used as speaker's identity and implied into sectors such as smart cards, healthcare, banking, and other security access controls. However, age, illness, and ambient noise factors exist challenging issues of voice changes in speech recognition systems to be resolved. This paper presents experiment results of observing those issues, and its goal was obtaining the elements of voice features to secure the speaker's identity. Mel-frequency Cepstral Coefficient (MFCC) was used to conduct observations on spectral centroid and bandwidth, it has effectively performed capturing features of individual speech signal. The experiment was conducted with data split into three groups: under 13, range 13 to 19, and above 19 years old for both male and female. The results showed that both gender under 13 have centroid voices reached to 98%, age of 13 to 19 remain with centroid reached 98% of bandwidth for male and passing over 100% for female, then above 19 for both genders speak lower with centroid 50% of bandwidth, and male above age of 19 remains to keep centroid about 50% and female changes to 95%. MFCC fits to expose the speech spectrum for the purpose of an analysis frame on specific local spectral properties of voices, and the finding is to form a security line or an individual profiling adoption. © 2022 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Development of Automatic Detection and Monitoring Application System for Peristaltic Condition based on Machine Learning and Internet of Thing (IoT) System 7

Development of Automatic Detection and Monitoring Applicatio...

引用

7th International Conference of computer and Informatics engineering, IC2IE 2024

作者： Astuti, Winda Giovanni Benedict Davin, K. Nurul Puji, Muhammad Kunaifi, Matthew Andriatin, Yuli Astuti Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Program Computer Engineering Department Jakarta Indonesia Cilacap Regional General Hospital Gatot Subroto No.28 Cilacap Indonesia

ISBN: (纸本)9798331505530

Poor sanitation and limited access to clean water are the main causes of increased risk of gastrointestinal diseases. In Indonesia, environmental hygiene problems are the main cause of digestive tract disorders, which contribute to more than 25% of deaths each year according to data from the Ministry of Health. Digestive disease is one of the diseases that often appears due to Poor sanitation and limited access to clean water. The development of a digital stethoscope for early detection of problems in the digestive tract would be useful, especially in remote areas. The sound was recorded from a Mel Frequency Cepstral Coefficient (MFCC) technique. The resulting features extracted from the stethoscope sound signal, are used as the inputs for the machine learning which applied three types of method, they are Logistic Regression (LR), combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN), combination of Logistic Regression (LR) and Support Vector Machine (SVM). The experiment of MFCC with three types of machine learning methods above, based the sound from a stethoscope. Experimental results show the combination of Logistic Regression (LR) and K-Nearest Neighbors (KNN) has exceeded results among other methods, with the training and testing accuracy of 90 % and 88 % respectively. They confirm the effectiveness of the proposed intelligent automatic stethoscope sound identification based on Mel-Frequency Cepstral Coefficient (MFCC) and Linear Regression. Furthermore, the system continuously saves and monitors the result of the patient. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Boost DC-DC Converter with Non-dissipative Snubber

引用

IEEJ Transactions on Electrical and Electronic engineering 2024年第11期19卷 1858-1878页

作者： Yau, Yeu-Torng Department of Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung No.57 Sec. 2 Zhongshan Rd. Taiping Dist Taichung41170 Taiwan

To provide a hold-up time function in DC-DC supplies for cell site stations or data centers, using a boost converter with a bulk output capacitor as a front-end converter stage is a simple and highly cost-effective solution. However, conventional boost converters with a hard-switching operation result in low conversion efficiency and increased electromagnetic interference emissions. In this paper, a boost converter with a new non-dissipative snubber is proposed that only requires two additional diodes, an inductor, and a multilayer ceramic capacitor. The main feature of the proposed snubber is that the components are not located on the main power processing path. This means they only require low ratings, improving cost-effectiveness. A prototype converter is analyzed, realized, and applied to a 300 W redundant DC-DC power supply module for a 5G cell base station. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： Boost converter

来源：评论

学校读者我要写书评

暂无评论

Improvement of PID Based on Fuzzy Logic Controller for Controlling Attitude of a Quadcopter 1

Improvement of PID Based on Fuzzy Logic Controller for Contr...

引用

1st International Conference of Adisutjipto on Aerospace Electrical engineering and Informatics, ICAAEEI 2024

作者： Rizki Dalimunthe, Ernando Sibuea, Horas Nico L. P. Rama Setiadi, Dirga Jayadi, Akhmad Persada Sembiring, Jaka Pranita, Elka Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandar Lampung Indonesia Politenik Negeri Lampung Informatic Management Study Program Bandar Lampung Indonesia

ISBN: (纸本)9798331507930

The quadcopter has a fairly simple mechanical design because it does not require other drives to perform various movements such as roll, pitch, and yaw. The simplicity of this mechanical design has a considerable impact on the complexity of its control. Therefore, it is necessary to have a good control method to maintain the stability of the quadcopter. The research aims to maintain stability of quadcopter by using a combination of the Fuzzy Logic Controller (FLC) with the Proportional-Integral-Derivative (PID) method, where FLC is used to initialize the input of the PID method to find the quadcopter stability point. The application of fuzzy methods for the initial tuning of PID parameters has proven effective in enhancing the system's fundamental performance, such as overshoot, rise time, and settling time, compared to the conventional PID approach. The proposed method can reduce overshoot by over 20%, with reductions reaching up to 88% in yaw motion. Additionally, the Fuzzy-PID approach significantly improves stability, shortening the time to achieve steady-state by less than 1 seconds for all movements while PID did more than 2s for pitch and roll motions and over 1s for yaw motion. © 2024 IEEE.

关键词： Two term control systems

来源：评论

学校读者我要写书评

暂无评论

Intelligence Based Condition Monitoring Model 7th

Intelligence Based Condition Monitoring Model

引用

7th International Congress and Workshop on Industrial AI and eMaintenance, IAI 2023

作者： Jenab, Kouroush Ward, Tyler Isaza, Cesar Ortega-Moody, Jorge Anaya, Karina School of Engineering & Computer Science Morehead State University MoreheadKY United States Networking and Telecommunication Academic Program Polytechnique University of Queretaro Queretaro Mexico

ISBN: (纸本)9783031396182

Condition-Based Maintenance (CBM) is a maintenance strategy that reduces equipment downtime, production loss, and maintenance cost based on changes in equipment condition (e.g., changes in vibration, changes in power usage, changes in operating performance, changes in temperatures, changes in noise levels, changes in chemical composition, increase in debris content and changes in the volume of material). In this study, we present the newly developed Condition Monitoring Model (CMM) based on an ensemble machine-learning model that utilizes the random forest, support vector machine, and artificial neural network classifiers, to classify data points from the normal state of a rotating machine. The efficacy of the model in adequately detecting and diagnosing faults in the rotating machine for maintenance planning is discussed in this paper. The developed model can efficiently avoid unnecessary maintenance and make timely actions by analyzing the received vibration signals from the rotating machine. An illustrative example is demonstrated to present the application of the model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Graph Neural Network Multi-Task Learning-Based Approach for Detection and Localization of Cyberattacks in Smart Grids 48

A Graph Neural Network Multi-Task Learning-Based Approach fo...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Takiddin, Abdulrahman Atat, Rachad Ismail, Muhammad Davis, Katherine Serpedin, Erchin Texas A and M University Department of Electrical and Computer Engineering College StationTX United States Texas A and M University at Qatar Electrical and Computer Engineering Program Doha Qatar Tennessee Technological University Department of Computer Science CookevilleTN United States

ISBN: (纸本)9781728163277

False data injection attacks (FDIAs) on smart power grids' measurement data present a threat to system stability. When malicious entities launch cyberattacks to manipulate the measurement data, different grid components will be affected, which leads to failures. For effective attack mitigation, two tasks are required: determining the status of the system (normal operation/under attack) and localizing the attacked bus/power substation. Existing mitigation techniques carry out these tasks separately and offer limited detection performance. In this paper, we propose a multi-Task learning-based approach that performs both tasks simultaneously using a graph neural network (GNN) with stacked convolutional Chebyshev graph layers. Our results show that the proposed model presents superior system status identification and attack localization abilities with detection rates of 98.5-100% and 99-100%, respectively, presenting improvements of 5-30% compared to benchmarks. © 2023 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Intelligent Small Scale Autonomous Vehicle Development Based on Convolutional Neural Network (CNN) for Steering Angle Prediction 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Asy’ari, Muhammad Zacky Phang, Maxson Suganda, Nicholas Mariana, Yosica Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Architecture Department Faculty of Engineering Binus University Jakarta Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Human error is the most significant factor in traffic accidents. 61% of accidents in Indonesia are caused by driver negligence. Autonomous vehicles are unmanned vehicles that are believed to be able to reduce the number of accidents caused by human error. This study aims to create a prototype of a small-scale unmanned vehicle using computer vision that can move around the track. The prototype captures an image using a USB webcam and is processed by a Raspberry Pi 4 to predict the correct steering angle based on input from the camera. A convolutional neural network (CNN) algorithm is used to recognize the path. The material used to make the prototype is PLA (polylactic acid). The prototype steering system uses a servo motor, and the drive system uses a brushless DC motor controlled by the PCA9685 module. More than 1600 image data were used and taken based on a simplified track. The results of this study indicate that the prototype can move along the given track with a steering angle range of 20°–130° for right turns and 60°–170° for left turns. The throttle value capable of moving the prototype at a steady speed is 0.075. The Keras Tensorflow model, dataset, and autonomous car design can achieve the desired level of autonomy with an RMSE accuracy of 0.1145. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

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

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

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：