Feature Mining
Feature mining focuses on extracting meaningful and informative features from diverse data sources to improve the performance of machine learning models and enhance their interpretability. Current research emphasizes developing efficient algorithms, such as those based on attention mechanisms, variational autoencoders, and novel clustering techniques (like P-KMeans and P-LDA), to identify optimal feature sets from complex data, including images, speech, and network traffic. This work is crucial for advancing applications in various fields, ranging from medical diagnosis and agricultural monitoring to cybersecurity and transportation optimization, by enabling more accurate, robust, and explainable AI systems.
Papers
Self-supervised Fusarium Head Blight Detection with Hyperspectral Image and Feature Mining
Yu-Fan Lin, Ching-Heng Cheng, Bo-Cheng Qiu, Cheng-Jun Kang, Chia-Ming Lee, Chih-Chung Hsu
Density Adaptive Attention-based Speech Network: Enhancing Feature Understanding for Mental Health Disorders
Georgios Ioannides, Adrian Kieback, Aman Chadha, Aaron Elkins
Halcyon -- A Pathology Imaging and Feature analysis and Management System
Erich Bremer, Tammy DiPrima, Joseph Balsamo, Jonas Almeida, Rajarsi Gupta, Joel Saltz
Feature Mining for Encrypted Malicious Traffic Detection with Deep Learning and Other Machine Learning Algorithms
Zihao Wang, Vrizlynn L. L. Thing