A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Fault Identification of Electric Submersible Pumps Based on Unsupervised and Multi-Source Transfer Learning Integration
2022
Sustainability
extraction integrated with migration learning was proposed. ...
Thirdly, the variation between the source domain and target domain was reduced by combining weighted balanced distribution adaptation (W-BDA). ...
abnormal samples by the model and a higher false recognition rate. ...
doi:10.3390/su14169870
fatcat:molkhsbihjbzlo6nmezywdxtiu
An Efficient Two-Stage Network Intrusion Detection System in the Internet of Things
2023
Information
In the IoT environment, we propose a novel two-stage intrusion detection model that combines machine learning and deep learning to deal with the class imbalance of network traffic data and achieve fine-grained ...
Experimental results show that, compared with SMOTE technology, the two-stage intrusion detection model can adapt to imbalanced datasets well and reveal higher efficiency and better performance when processing ...
[34] proposed a dynamic network anomaly detection system, which adds an attention mechanism to LSTM and uses SMOTE and a weighted loss function to deal with class imbalance problem. ...
doi:10.3390/info14020077
fatcat:uux7ir5zzfaotcbhpgx6tyn2ja
An Efficient Domain-Adaptation Method using GAN for Fraud Detection
2020
International Journal of Advanced Computer Science and Applications
The experimental results indicated that the proposed model is applicable to both test datasets; furthermore, it requires less time for learning. ...
Also, although the detection performance of the CNN-based model is similar to that of the proposed domain-adaptation model, its learning process is longer. ...
Oversampling Approaches to solving the data imbalance problem can be divided into four categories: sampling-based, cost-based, kernel-based, and active-learning-based methods [15] . ...
doi:10.14569/ijacsa.2020.0111113
fatcat:7bdimlw6wbholnvzvwpxg2xapu
Physical Activity Monitoring and Classification Using Machine Learning Techniques
2022
Life
Different training splits are used to introduce class imbalance which reveals the performance of the selected state-of-the-art algorithms with various degrees of imbalance. ...
sensitive to class imbalance than others. ...
class imbalance due to its inherited property of adaptive weighting at the training stage to compensate for class imbalance up to some extent. ...
doi:10.3390/life12081103
pmid:35892905
pmcid:PMC9332439
fatcat:eis2yluy5zgjjbet5fhngzawy4
Improved Wafer Map Inspection Using Attention Mechanism and Cosine Normalization
2022
Machines
This paper reconsiders the causes of the imbalance and proposes a deep learning method that can learn robust knowledge from an imbalanced dataset using the attention mechanism and cosine normalization. ...
To compensate for feature distribution imbalance, we add an improved convolutional attention module to the DCNN to enhance representation. ...
Overcoming the problem of dataset imbalance can promote the application of the algorithm in real manufacturing. ...
doi:10.3390/machines10020146
fatcat:hkqn7ydy5jaejkudbqcufbscbq
Anomaly detecting and ranking of the cloud computing platform by multi-view learning
[article]
2019
arXiv
pre-print
Traditional detecting methods based on statistic, analysis, etc. lead to the high false-alarm rate due to non-adaptive and sensitive parameters setting. ...
Our method exploits the complement information between sub-systems sufficiently, and avoids the influence from imbalance dataset, therefore, deal with various challenges from the cloud computing platform ...
The authors would like to thank the anonymous reviewers for the valuable suggestions they provided. ...
arXiv:1901.09294v1
fatcat:ru3yxukv75eg3hikbwblnmgo6a
A Semi-Supervised Transfer Learning with Dynamic Associate Domain Adaptation for Human Activity Recognition Using WiFi Signals
2021
Sensors
In this paper, by using the channel state information (CSI) of the WiFi signal, semi-supervised transfer learning with dynamic associate domain adaptation is proposed for human activity recognition. ...
Human activity recognition without equipment plays a vital role in smart home applications, freeing humans from the shackles of wearable devices. ...
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable. Data Availability Statement: Data sharing is not applicable to this article. ...
doi:10.3390/s21248475
pmid:34960569
pmcid:PMC8705376
fatcat:pck57saxgbcx3bkxxrd5fgeydm
An Effective and Lightweight Deep Electrocardiography Arrhythmia Recognition Model Using Novel Special and Native Structural Regularization Techniques on Cardiac Signal
2022
Journal of Healthcare Engineering
Recently, cardiac arrhythmia recognition from electrocardiography (ECG) with deep learning approaches is becoming popular in clinical diagnosis systems due to its good prognosis findings, where expert ...
But a lightweight and effective deep model is highly demanded to face the challenges of deploying the model in real-life applications and diagnosis accurately. ...
accuracy, guaranteed data imbalance problem-solving, and a lightweight end-to-end 2D deep learning model is more essential for real-life applications. ...
doi:10.1155/2022/3408501
pmid:35449862
pmcid:PMC9018174
fatcat:rexwkwvwdjdq7pzaktolrbjpai
Supervised and Unsupervised Pattern Recognition: Feature Extraction and Computational Intelligence [Book Review]
2001
IEEE Transactions on Neural Networks
The same authors continue in the next chapter presenting another application to recognition of normal and abnormal visual evoked potentials (VEPs). ...
For synaptic weight adaptation a method combining the Hebbian rule and ALOPEX procedure is used. ...
doi:10.1109/tnn.2001.925570
fatcat:cjrvu3xkvrc6jbj3hc2tt3rhha
Self-Adaption AAE-GAN for Aluminum Electrolytic Cell Anomaly Detection
2021
IEEE Access
In traditional machine learning algorithms, such as support vector machine (SVM) and convolutional neural network (CNN), it is difficult to obtain high classification accuracy on the problem of class imbalance ...
The problem of unbalanced time series samples is common in industrial applications. The number of samples under normal conditions is much larger than that under abnormal conditions. ...
Many deep learning models are only applicable to a single field, but it is usually difficult to apply them to industrial fields.
B. ...
doi:10.1109/access.2021.3097116
fatcat:ufxi7wohc5hjjd7esyv3uksd5q
Cost-Sensitive Broad Learning System for Imbalanced Classification and Its Medical Application
2022
Mathematics
As an effective and efficient discriminative learning method, the broad learning system (BLS) has received increasing attention due to its outstanding performance without large computational resources. ...
However, imbalanced data are widely encountered in real-world applications. To address this issue, a novel cost-sensitive BLS algorithm (CS-BLS) is proposed. ...
to enhancement nodes with random weights (W ej and β ej ) and a series of nonlinear activation functions (ξ j ). ...
doi:10.3390/math10050829
fatcat:ckvenvwbebginanjac4qxo7itm
A novel 1-D densely connected feature selection convolutional neural network for heart sounds classification
2021
Annals of Translational Medicine
Using this attention mechanism, our model was able to achieve adaptively spatial feature fusion by adjusting a hyper-feature that contains higher level visual information and lower-level features including ...
In this paper, we present a method for identifying abnormal heart sounds based on a novel Dense Feature Selection Convolution Network framework (Dense-FSNet). ...
Acknowledgments We would like to thank Qin Gao and Zhaoxi Wang from Xinhua Harvard International Healthcare Innovation Collaboration Initiatives for manuscript discussion and review. ...
doi:10.21037/atm-21-4962
pmid:35071446
pmcid:PMC8756246
fatcat:yhiqzzhap5go5k3tr3ovou4gg4
Imbalance Data Classification Using Local Mahalanobis Distance Learning Based on Nearest Neighbor
2020
SN Computer Science
Many standard learning algorithms face the classification problem in performance due to imbalance data. ...
Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. ...
Meenakshi Sundaram. sampling approaches, cost-sensitive learning, active learning, kernel-based methods and ensemble learning [8] [9] [10] [11] [12] . ...
doi:10.1007/s42979-020-0085-x
fatcat:g7bsuxew3zdc5lkidzer24e3va
Network Intrusion Detection System Based on Domain Adaptation for Industrial Control System
[chapter]
2024
Frontiers in Artificial Intelligence and Applications
data imbalance, which can affect the training effectiveness. ...
domain in a universal domain adaptation scenario. ...
In addition to comparing with the threshold τ to discriminate the samples, the weight is also used to calculate the weighted loss of the private samples in the target domain. ...
doi:10.3233/faia231326
fatcat:qwbclofdmrhdrbrg3sr3fou7wm
Sleep Apnea Detection Based on Multi-Scale Residual Network
2022
Life
In order to overcome the impact of class imbalance, a focal loss function is introduced to replace the traditional cross-entropy loss function, which makes the model pay more attention to learning difficult ...
These results indicate that the proposed method not only achieves greater recognition accuracy than other methods, but it also effectively resolves the problem of low sensitivity caused by class imbalance ...
Class weight (class weight) is a common method to deal with data imbalance, but this method does not solve the problem of different sample classification difficulty caused by sample imbalance. ...
doi:10.3390/life12010119
pmid:35054512
pmcid:PMC8781811
fatcat:g3tqpki3obethapbiyzlsnk7vu
« Previous
Showing results 1 — 15 out of 12,094 results