Embedded Files
Research Projects
Outlier/Anomaly Detection
Funding Agency: CSUN FRPDI
This project focuses on developing machine learning and deep learning methods for outlier and anomaly detection in complex real-world datasets. An anomaly refers to a data instance or pattern that deviates significantly from the expected behavior or underlying distribution of the data. The goal is to automatically identify such rare or unusual instances across diverse data modalities. Applications include computer vision, cybersecurity, surveillance systems, medical image analysis, industrial monitoring, autonomous systems, and financial fraud detection, enabling more reliable and intelligent decision-making in real-world environments.Â
GEO AI: Computer Vision Techniques for Orchard Management
This project focuses on applying computer vision and geospatial AI techniques for precision orchard management, enabling automated analysis of fruit trees and crop conditions from field imagery. It leverages deep learning-based object detection and counting methods to support tasks such as fruit detection, yield estimation, and spatial variability analysis in orchard environments. The system is designed to improve agricultural decision-making by providing scalable, data-driven insights for smart farming applications.
Past Projects
Behind the Curtain: Spotting Deepfakes
Funding Agency: CSUN RSCA Award
This project developed a multimodal framework for detecting AI-generated content in text, image, and video data, addressing emerging threats from generative AI and deepfakes, with a particular focus on adversarial attack scenarios that challenge model robustness. The work produced six peer-reviewed publications and provided research training for six graduate students and one undergraduate student.
Feature Selection
Funding Agency: National Science Foundation (NSF)
In real-world applications, it is not practical to wait until all features have been generated before feature selection begins. Therefore, many interesting and challenging research questions arise for streaming data: (1) how to select relevant features when feature space is unknown? (2) how to update the feature set as new features are available over time? (3) How can feature relevance be assessed without label information? We are developing methods for streaming feature selection in two settings: (i) supervised, and (ii) unsupervised. In addition, we are designing novel algorithms for static feature selection.
Noise Detection in Supervised Learning
Funding Agency: National Science Foundation (NSF)
The key ingredient for any machine learning model is data. Along with the continuing development of new technologies, the volume of data collection increases in almost all fields of human endeavor. Lack of data is no longer the problem; lack of effective and efficient methods to prepare, learn, and act on the massive data has become a crucial problem. In this project, we investigate ``Learning from Noisy Data'' which addresses the problem of learning in the presence of noise. We developed three novel techniques to handle noisy data to improve the predictive performance of machine learning models.
Page updated
Google Sites
Report abuse