A5107250319- Machine Learning and Data Classification
- Anomaly Detection Techniques and Applications
- Energy Load and Power Forecasting
- Software System Performance and Reliability
- Neural Networks and Applications
- Building Energy and Comfort Optimization
- Adversarial Robustness in Machine Learning
- Software Engineering Research
- Technology and Security Systems
Cornell University
2024
Gansu Agricultural University
2024
Northeastern University
2023
Shanghai Jiao Tong University
2021
A Machine Learning (ML) pipeline configures the workflow of a learning task using APIs provided by ML libraries. However, pipeline's performance can vary significantly across different configurations library versions. Misconfigured pipelines result in inferior performance, such as poor execution time and memory usage, numeric errors even crashes. is subject to misconfiguration if it exhibits inconsistent upon changes versions its configured libraries or combination these We refer...
Numerous works study black-box attacks on image classifiers, where adversaries generate adversarial examples against unknown target models without having access to their internal information. However, these make different assumptions about the adversary's knowledge, and current literature lacks cohesive organization centered around threat model. To systematize knowledge in this area, we propose a taxonomy over space spanning axes of feedback granularity, interactive queries, quality quantity...
The knowledge within wheat production chain data has multiple levels and complex semantic relationships, making it difficult to extract from them. Therefore, this paper proposes a fine-grained extraction method for the based on ontology. For first time, conceptual layers of ploughing, planting, managing, harvesting were defined around main agricultural activities chain. Based this, entities, attributes in at level, spatial–temporal association pattern layer with four layers, twenty-eight...