A5011422509- Imbalanced Data Classification Techniques
- Advanced Chemical Sensor Technologies
- Gold and Silver Nanoparticles Synthesis and Applications
- Electricity Theft Detection Techniques
- Digital Media Forensic Detection
- Financial Distress and Bankruptcy Prediction
- Biosensors and Analytical Detection
- Gas Sensing Nanomaterials and Sensors
- Analytical Chemistry and Chromatography
- Nanocluster Synthesis and Applications
- Generative Adversarial Networks and Image Synthesis
- Sports Analytics and Performance
- Cell Image Analysis Techniques
- Text and Document Classification Technologies
- Video Analysis and Summarization
- Data Mining Algorithms and Applications
- Vehicle License Plate Recognition
- Advanced biosensing and bioanalysis techniques
- Anomaly Detection Techniques and Applications
Sungkyunkwan University
2014-2023
Metabolomx (United States)
2018
Although transmission electron microscopy (TEM) may be one of the most efficient techniques available for studying morphological characteristics nanoparticles, analyzing them quantitatively in a statistical manner is exceedingly difficult. Herein, we report method mass-throughput analysis morphologies nanoparticles by applying genetic algorithm to an image technique. The proposed enables over 150,000 with high precision 99.75% and low false discovery rate 0.25%. Furthermore, clustered...
In order to handle the class imbalance problem, synthetic data generation methods such as SMOTE, ADASYN, and Borderline-SMOTE have been developed. These use a common parameter k, number of nearest neighbors. Nonetheless most effective k value depends on given dataset, there is no guideline determine k. Moreover, if dataset has noises, small sub-clusters, or complex patterns, existing SMOTE its variants show poor classification performance. Our method that we named Automatic Neighborhood size...
Here, we systematically investigated the independent, multiple, and synergic effects of three major components, namely, ascorbic acid (AA), seed, silver ions (Ag+), on characteristics gold nanorods (GNRs), i.e., longitudinal localized surface plasmon resonance (LSPR) peak position, shape, size, monodispersity. To quantitatively assess shape dimensions GNRs, used an automated transmission electron microscopy image analysis method using a MATLAB-based code developed in-house concept solidity,...
In this research, we employed various data mining techniques to build predictive models for win-loss prediction in Korean professional baseball games. The historical containing information about players and teams was obtained from the official materials that are provided by KBO website. Using collected raw data, additionally prepared two more types of dataset, which ratio binary format respectively. Dividing away-team's records corresponding home-team generated while dataset comparing record...
To create printing substrates for colorimetric sensor arrays, chemically resistant membranes are prepared by coating cellulose filter paper with perfluoroalkoxy (PFA) polymer nanoparticles. A water-based fluorothermoplastic dispersion was diluted an organic solvent that causes weak aggregation of The resulting solution improved adhesion between the and membrane, providing a more mechanically stable substrate. These PFA polymer-coated demonstrated superior chemical resistance against strong...
This paper presents a novel end-to-end oversampling-classification approach, which we refer to as imbalanced data-classifying generative adversarial network (ImbGAN), for data classification. ImbGAN has classifier-embedded structure within GAN and consists of five components: (1) generator, (2) discriminator, (3) classifier, (4) storage misclassified minority class data, (5) artificial data. By iterative interaction with the embedded first two components generate instances that are similar...
This paper presents a novel end-to-end oversampling-classification approach, which we refer to as imbalanced data-classifying generative adversarial network (ImbGAN), for data classification. ImbGAN has classifier-embedded structure within GAN and consists of five components: (1) generator, (2) discriminator, (3) classifier, (4) storage misclassified minority class data, (5) artificial data. By iterative interaction with the embedded first two components generate instances that are similar...
The imbalance of classes in real-world datasets poses a major challenge machine learning and classification, traditional synthetic data generation methods often fail to address this problem effectively. A limitation these is that they tend separate the process generating samples from training process, resulting lack necessary informative characteristics for proper model training. We present new method addresses issue by combining adversarial sample with triplet loss method. This approach...