Jin CaoResearch

PhD Candidate · AI / Data Mining · Industry Researcher

Human judgment for intelligent data systems.

I study how machine intelligence can make complex data more selective, explainable, and useful, then connect those methods to human-centered systems at enterprise scale.

Expected 2027PhD Candidate · Degree PendingSichuan University · Computer Science · AI and Data Mining
IndustryAI + Data PlatformsEnterprise data, streaming, security, and HCI
ServiceEditorial Board MemberArtificial intelligence and medical imaging

Three connected questions guide my work.

Data intelligence

How can models find the right signal?

Feature selection, rough sets, high-dimensional data, efficient learning, and interpretable classification.

Methods · data mining · machine learning
Human–agent systems

How should people direct and control agents?

Delegation, orchestration, explainability, uncertainty, tool permissions, intervention, and decision-centered evaluation.

Agent manager UX · responsible autonomy · evaluation
Intelligent infrastructure

How does intelligence operate in the physical world?

Network planning, streaming data, sensing, health applications, and spatial visualization.

Networks · sensing · applied AI

Selected scholarly work.

2026 · Elsevier

Feature Selection via Enhanced Rough Hypercuboid Approach with Overlap Degree and Distance Measure

Jin Cao, Chuan Luo, Linlin Xie, Tianrui Li, Hongmei Chen · Boundary-region distance and overlap-degree pre-sorting for efficient feature selection in high-dimensional datasets.

View ↗
2021 · Elsevier

Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN

Haowei Jiang, Feiwei Qin, Jin Cao, Yong Peng, Yanli Shao · A computational perspective on recurrent neural network architecture.

View ↗
2024 · IEEE

Credit Card Fraud Detection Using Advanced Transformer Model

Chang Yu, Yongshun Xu, Jin Cao, Ye Zhang, Yinxin Jin, Mengran Zhu · Transformer-based fraud detection evaluated against established machine-learning baselines.

View ↗
2023 · Elsevier

Fine-grained Imbalanced Leukocyte Classification with Global-Local Attention Transformer

Attention-based classification for imbalanced medical imaging data.

View ↗
2024 · IEEE

Rough Set Improved Therapy-Based Metaverse Assisting System

Jin Cao, Yanhui Jiang, Chang Yu, Feiwei Qin, Zekun Jiang · Rough-set methods applied to an interactive therapeutic support system.

View ↗
2022 · Samsung US Patent Publication (A1)

Interactive Control with Ranging and Gesturing Between Devices

Hoang Viet Nguyen, Jin Cao, Guanbo Chen, Boon Loong Ng · US20220137204A1.

View ↗
2021 · Samsung US Granted Patent (B2)

Terminal-Specific Beamforming Adaptation for Advanced Wireless Systems

Boon Loong Ng, Jianzhong Zhang, Jin Cao, Joonyoung Cho · US11108473B2.

View ↗
Author-maintained publication recordView Google Scholar ↗

Industry gives agent research real constraints.

My product work spans enterprise data security, real-time streaming, network intelligence, and agent-assisted workflows. These systems make research questions concrete: tool permissions affect action, latency affects orchestration, uncertainty affects trust, and organizational scale affects whether autonomy can survive contact with reality.

Enterprise problemsResearch questionsEvaluated methodsHuman decisions

Areas I am interested in teaching.

These are future teaching interests informed by research and industry practice. I have not held a formal teaching appointment.

Potential seminar

Human-Centered AI Systems

Interaction models, evaluation, uncertainty, explainability, guardrails, and accountable automation.

Potential methods course

Data Mining for Product Decisions

Feature selection, classification, experiment design, visualization, and turning analysis into decisions.

Potential studio

Designing Enterprise AI Platforms

Systems thinking, UX architecture, data governance, AI workflows, and cross-functional specifications.

AI journal editorial service

Editorial Board Member
Discover Artificial Intelligence, 2024–present

AI + medical imaging

Editorial Board Member, AI Section
Abdominal Radiology, 2024–present

Research or academic collaboration

Let’s connect ideas to systems.

Academic email ↗Google Scholar ↗