Physics-Informed Machine Learning for Solder Joint Qualification Tests

The ability to accurately predict the reliability and lifetime of electronics is of great importance to the industry. The failure of the solder joint is of particular interest for these predictions, because of their susceptibility to failure under thermo-mechanical stress. However, the experimental or even conventional simulation techniques...

Predicting streamflow with LSTM networks using global datasets

Streamflow predictions remain a challenge for poorly gauged and ungauged catchments. Recent research has shown that deep learning methods based on Long Short-Term Memory (LSTM) cells outperform process-based hydrological models for rainfall-runoff modeling, opening new possibilities for prediction in ungauged basins (PUB). These studies usually...

Surrogate modelling of railway pantograph-catenary interaction using deep Long-Short-Term-Memory neural networks

The interaction performance of the pantograph-catenary is of great importance as it directly determines the current collection quality and operational safety of trains. The finite element method (FEM) is dominantly used for simulating pantograph-catenary interaction, which is normally computationally heavy. In this work, addressing the...

Leveraging Transfer Learning in LSTM Neural Networks for Data-Efficient Burst Detection in Water Distribution Systems

Researchers and engineers employ machine learning (ML) tools to detect pipe bursts and prevent significant non-revenue water losses in water distribution systems (WDS). Nonetheless, many approaches developed so far consider a fixed number of sensors, which requires the ML model redevelopment and collection of sufficient data with the new...

Continuous People Crowd Monitoring defined as a Regression Problem using Radar Networks

Radar-based human activity recognition in crowded environments using regression approaches is addressed. Whereas previous research has focused on single activities and subjects, the problem of continuous activity recognition involving up to five individuals moving in arbitrary directions in an indoor area is introduced. To treat the problem, a...

Cyber Forensic Analysis for Operational Technology Using Graph-Based Deep Learning

The cyber attacks in Ukraine in 2015 and 2016 demonstrated the vulnerability of electrical power grids to cyber threats. They highlighted the significance of Operational Technology (OT) communication-based anomaly detection. Many anomaly detection methods are based on real-time traffic monitoring, i.e., Intrusion Detection Systems (IDS) that may...

Evaluation Metrics for Continuous Human Activity Classification Using Distributed Radar Networks

Continuous Human Activity Recognition (HAR) in arbitrary directions is investigated using 5 spatially distributed pulsed Ultra-Wideband (UWB) radars. Such activities performed in arbitrary and unconstrained trajectories render a more natural occurrence of Activities of Daily Living (ADL) to be recognized. An innovative signal level fusion method...

An End-to-End Deep Learning Pipeline for Football Activity Recognition Based on Wearable Acceleration Sensors

Action statistics in sports, such as the number of sprints and jumps, along with the details of the corresponding locomotor actions, are of high interest to coaches and players, as well as medical staff. Current video-based systems have the disadvantage that they are costly and not easily transportable to new locations. In this study, we...

Deep-Learning-Based Compliant Motion Control of a Pneumatically-Driven Robotic Catheter

In cardiovascular interventions, when steering catheters and especially robotic catheters, great care should be paid to prevent applying too large forces on the vessel walls as this could dislodge calcifications, induce scars or even cause perforation. To address this challenge, this paper presents a novel compliant motion control algorithm...

Hysteresis Modeling of Robotic Catheters based on Long Short-Term Memory Network for Improved Environment Reconstruction

Catheters are increasingly being used to tackle problems in the cardiovascular system. However, positioning precision of the catheter tip is negatively affected by hysteresis. To ensure tissue damage due to imprecise positioning is avoided, hysteresis is to be understood and compensated for. This work investigates the feasibility to model...

Research on Bearing Fault Diagnosis Method Based on Filter Features of MOMLMEDA and LSTM

As the supporting unit of rotating machinery, bearing can ensure efficient operation of the equipment. Therefore, it is very important to monitor the status of bearings accurately. A bearing fault diagnosis mothed based on Multipoint Optimal Minimum Local Mean Entropy Deconvolution Adjusted (MOMLMEDA) and Long Short-Term Memory (LSTM) is...

Video Captioning by Adversarial LSTM

In this paper, we propose a novel approach to video captioning based on adversarial learning and long short-term memory (LSTM). With this solution concept, we aim at compensating for the deficiencies of LSTM-based video captioning methods that generally show potential to effectively handle temporal nature of video data when generating...

Towards Seed-Free Music Playlist Generation: Enhancing collaborative Filtering with Playlist Title Information

In this paper, we propose a hybrid Neural Collaborative Filtering (NCF) model trained with a multi-objective function to achieve a music playlist generation system. The proposed approach focuses particularly on the cold-start problem (playlists with no seed tracks) and uses a text encoder employing a Recurrent Neural Network (RNN) to exploit...