Data Mining - Concepts and Techniques.

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

527 articles related to imbalanced data and rare events are reviewed.Viewing reviewed papers from both technical and practical perspectives.Summarizing existing methods and corresponding statistics by a new taxonomy idea.Categorizing 162 application papers into 13 domains and giving introduction.Some opening questions are discussed at the end of this manuscript. Rare events, especially those that could potentially negatively impact society, often require humans decision-making responses. Detecting rare events can be viewed as a prediction task in data mining and machine learning communities. As these events are rarely observed in daily life, the prediction task suffers from a lack of balanced data. In this paper, we provide an in depth review of rare event detection from an imbalanced learning perspective. Five hundred and seventeen related papers that have been published in the past decade were collected for the study. The initial statistics suggested that rare events detection and imbalanced learning are concerned across a wide range of research areas from management science to engineering. We reviewed all collected papers from both a technical and a practical point of view. Modeling methods discussed include techniques such as data preprocessing, classification algorithms and model evaluation. For applications, we first provide a comprehensive taxonomy of the existing application domains of imbalanced learning, and then we detail the applications for each category. Finally, some suggestions from the reviewed papers are incorporated with our experiences and judgments to offer further research directions for the imbalanced learning and rare event detection fields.

Learning from class-imbalanced data

Trends in extreme learning machines

Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management, including applications on yield prediction, disease detection, weed detection crop quality, and species recognition; (b) livestock management, including applications on animal welfare and livestock production; (c) water management; and (d) soil management. The filtering and classification of the presented articles demonstrate how agriculture will benefit from machine learning technologies. By applying machine learning to sensor data, farm management systems are evolving into real time artificial intelligence enabled programs that provide rich recommendations and insights for farmer decision support and action.

Machine Learning in Agriculture: A Review.

This paper develops a damage-risk assessing method with dynamic feature extraction optimization (DFEO) in the Thermal-wave image technique, to evaluate the hypervelocity impact (HVI) damages in dynamic meteoroid/orbital debris (M/OD) environment rapidly. The proposed DFEO not only investigates how to select effectively each representative temperature point (RTP) with consideration of similarities and differences of thermal characteristic data, but also studies how to utilize historical information to extract rapidly impact damage feature from thermal image sequence. A multi-directional prediction method (MPM) in DFEO calculates the degree of environment change to depict the configuration of previous Pareto set (PS) and predict the moving directions of the optimal solutions. Meanwhile, a dynamic multi-objective particle-swarm optimization strategy (DM-PSOS) in DFEO guarantees that the obtained initial population evolves successfully to Pareto Front (PF). Besides DFEO, the assessing method contains variable step-size search, clustering analysis and damage visualization, to enhance the detection efficiency. The experimental study on HVI damage detection demonstrates the capabilities of the proposed method.

Infrared feature extraction and prediction method based on dynamic multi-objective optimization for space debris impact damages inspection

Model initialization and feature extraction are crucial in supervised landmark detection Mismatching caused by detector error and discrepant initialization is very common in these existing methods To solve this problem, we have proposed a new method based on ELM feature selection and Improved Supervised Descent Method (ELMFS-iSDM), which also includes an automatic initialization model, for the robust facial landmark localization In our new method, firstly, a fast detection will be processed to locate the eyes and mouth, and the initialization model will adapt to the real location according to fast facial points detection Secondly, ELM based feature selection is adopted on our Improved Supervised Descent Method model to achieve a better performance For each task, multiple features will be jointly learned by ELM feature selection and their weights will be calculated during training process Experiments on four benchmark databases show that our method achieves state-of-the-art performance

Facial Landmark Detection via ELM Feature Selection and Improved SDM

The differences in magnetic resonance imaging (MRI) between children with classic acute disseminated encephalomyelitis (ADEM) and myelinal oligodendrocyte glycoprotein antibody associated disease (MOGAD) with ADEM-like presentation are controversial. The purpose of this study was to investigate whether the radiological characteristics of the MRI-FLAIR sequence can predict MOGAD in children with ADEM-like presentation and to further explore its imaging differences.We extracted 1041 radiomics features from MRI-FLAIR lesions. Then we used the redundancy analysis (Spearman correlation coefficient), significance test (student test or Mann-Whitney U test), least absolute contraction and selection operator (LASSO) to select potential predictors from the feature groups. The selected potential predictors and MOG antibody test results were used to fit the machine learning model for classification. Combined with feature selection and machine learning classifiers, the optimal model for each subgroup was derived. The resulting models have been evaluated using the receiver operator characteristic curve (ROC) at the lesion level and the model performance was evaluated at the case level using decision curve analysis.We retrospectively reviewed and re-diagnosed 70 ADEM-like presentation cases in our center from April 2015 to January 2020. Including 49 cases with classic ADEM and 21 cases with MOGAD. 30(43%) were female, with a median age of 5.3 years. On the four subgroups by age and gender, the area under the curve (AUC) of the optimal models were 89%, 90%, 98%, and 99%, and the MOGAD detection rates (Specificity) were 83%, 83%, 92%, and 75%, respectively.The machine learning model trained on radiomics features of MR-FLAIR images can effectively predict patients' MOGAD. This study provides a fast, objective, and quantifiable method for MOGAD diagnosis. 

Differentiation of MOGAD in ADEM-like presentation children based on FLAIR MRI features.

Proceedings of ELM-2015 Volume 1

The invention discloses a heart sound signal classification method based on a convolutional recurrent neural network. The method comprises the following steps: performing noise processing on heart sound data; extracting heart sound characteristics of the heart sound signals; standardizing the data; constructing a convolutional recurrent neural network model; training the constructed neural networkby using the training sample data characteristics, and storing the trained network structure and parameters; and testing the test sample data by using the trained model parameters to obtain a final classification and identification result. According to the invention, the system complexity is reduced; the extracted heart sound characteristics do not need to segment heart sound signals; according to the heart sound signal classification method based on the convolutional neural network, the convolutional neural network and the recurrent neural network are connected in series, a deep learning model with the processing advantages of the convolutional neural network and the recurrent neural network is provided, better expressive force is provided for heart sound signal classification, and an effective and convenient tool is provided for detection of normal and abnormal heart sound signals.

Jiuwen Cao

Papers

Infrared feature extraction and prediction method based on dynamic multi-objective optimization for space debris impact damages inspection

Facial Landmark Detection via ELM Feature Selection and Improved SDM

Differentiation of MOGAD in ADEM-like presentation children based on FLAIR MRI features.

Proceedings of ELM-2015 Volume 1

Heart sound signal classification method based on convolutional recurrent neural network