Related papers: Robust Event Classification Using Imperfect Real-w…

Labeled data is a critical resource for training and evaluating machine learning models. However, many real-life datasets are only partially labeled. We propose a semi-supervised machine learning training strategy to improve event detection…

The use of machine learning systems in clinical routine is still hampered by the necessity of a medical device certification and/or by difficulty to implement these systems in a clinic's quality management system. In this context, the key…

This paper presents an information-theoretic approach to address the phasor measurement unit (PMU) placement problem in electric power systems. Different from the conventional 'topological observability' based approaches, this paper…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

This paper introduces a self-supervised learning framework designed for pre-training neural networks tailored to dense prediction tasks using event camera data. Our approach utilizes solely event data for training. Transferring achievements…

Real-life parallel machine scheduling problems can be characterized by: (i) limited information about the exact task duration at scheduling time, and (ii) an opportunity to reschedule the remaining tasks each time a task processing is…

The problem of effective use of Phasor Measurement Units (PMUs) to enhance power systems awareness and security is a topic of key interest. The central question to solve is how to use this new measurements to reconstruct the state of the…

In recent years, machine learning has been adopted to complex networks, but most existing works concern about the structural properties. To use machine learning to detect phase transitions and accurately identify the critical transition…

Deep learning has been able to outperform humans in terms of classification accuracy in many tasks. However, to achieve robustness to adversarial perturbations, the best methodologies require to perform adversarial training on a much larger…

In this paper, we aim to enhance the robustness of Universal Information Extraction (UIE) by introducing a new benchmark dataset, a comprehensive evaluation, and a feasible solution. Existing robust benchmark datasets have two key…

Classification is a fundamental task in machine learning. While conventional methods-such as binary, multiclass, and multi-label classification-are effective for simpler problems, they may not adequately address the complexities of some…

Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints. Instead, in many real-world applications, the constraints are derived from side information, such as…

Objective: Conventional urodynamics (UDS) provide critical diagnostic information, but requires invasive dual catheterization and manual labeling of clinically important events. Wireless, catheter-free bladder function tests are becoming…

We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels. Previous datasets are created by either capturing real…

Instance selection is a vital technique for energy big data analytics. It is challenging to process a massive amount of streaming data generated at high speed rates by intelligent monitoring devices. Instance selection aims at removing…

This thesis develops data-driven machine learning algorithms to managing and optimizing the next-generation highly complex cyberphysical systems, which desperately need ground-breaking control, monitoring, and decision making schemes that…

This paper studies the vulnerability of phasor measurement units (PMUs) to false data injection (FDI) attacks. Prior work demonstrated that unobservable FDI attacks that can bypass traditional bad data detectors based on measurement…

Data preprocessing is often paid little attention in machine learning, despite its potentially significant impact on model performance. While automated machine learning pipelines are starting to recognize and integrate data preprocessing…

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious…

The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large…