Min Wu

Active learning for accurate analysis of streaming partial discharge data

2015

Partial discharge (PD) is a phenomenon of electric discharge typically caused by the damaged or aged insulation of high voltage equipment in power grids, such as transformers, switch gears, and cable terminals. In the context …

A Johnson's-Rule-Based Genetic Algorithm for Two-Stage-Task Scheduling Problem in Data-Centers of Cloud Computing

2017 · IEEE Transactions on Cloud Computing

One of the keys to making cloud data-centers (CDCs) proliferate impressively is the implementation of efficient task scheduling. Since all the resources of CDCs, even including operating systems (OSes) and application programs, can be stored …

Learning User Dependencies for Recommendation

2017

Social recommender systems exploit users' social relationships to improve recommendation accuracy. Intuitively, a user tends to trust different people regarding with different scenarios. Therefore, one main challenge of social recommendation is to exploit the most …

Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm

2018 · arXiv (Cornell University)

Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper …

Safety and Trustworthiness of Deep Neural Networks: A Survey

2018 · arXiv (Cornell University)

In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level intelligence on several long-standing tasks. With broader deployment of DNNs on various applications, the concerns on its …

Safety Verification of Deep Neural Networks

2016 · arXiv (Cornell University)

Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify …

Adaptive cost-sensitive online classification

2019 · Singapore Management University Institutional Knowledge (InK) (Singapore Management University)

National Research Foundation (NRF) Singapore under International Research Centres in Singapore Funding Initiative

PulseEdit: Editing Physiological Signals in Facial Videos for Privacy Protection

2022

Recent studies have shown that physiological signals such as heart beat and breathing can be remotely captured from human faces using a regular color camera under ambient light. This technology, referred to as remote photoplethysmography …

SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance

2022 · arXiv (Cornell University)

Ad relevance modeling plays a critical role in online advertising systems including Microsoft Bing. To leverage powerful transformers like BERT in this low-latency setting, many existing approaches perform ad-side computations offline. While efficient, these approaches …

A Novel Outdoor Edge Server Design with Hybrid Air Cooling and Refrigeration

2022 · 2022 21st IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (iTherm)

Edge servers are trending up to 24% of total global server deployment in 2024. Several emerging applications are required to deploy with edge servers in harsh outdoor edge environments where special system design is required …

SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Unsupervised Domain Adaptation (UDA) methods can reduce label dependency by mitigating the feature discrepancy between labeled samples in a source domain and unlabeled samples in a similar yet shifted target domain. Though achieving good performance, …

Papers by this author