document

Binary Deep Learning: Binary Weights and Semantic Binary Data Compression

Li, Y. (author)

Improving the efficiency in deploying deep neural networks (DNNs) and processing complex high-dimensional data has drawn increasing attention in recent years. Yet, the deployment of large DNN models is challenged by the high computational complexity and energy consumption, making it difficult to run on resource-constrained devices such as mobile...

doctoral thesis 2024

document

The Estimation of Acoustic Parameters and Representations based on Room Impulse Responses

Yu, W. (author)

We are surrounded by all kinds of sounds at all times. What we hear varies with the physical environment and our position. Room impulse responses (RIRs) characterize the effect of the environment on a sound produced by a source. A first goal of this dissertation is to analyze RIRs and investigate how to extract environmental information from...

doctoral thesis 2024

document

Efficiency in Deep Learning: Image and Video Deep Model Efficiency

Liu, X. (author)

Deep learning is the core algorithmic tool for automatically processing large amounts of data. Deep learning models are defined as a stack of functions (called layers) with millions of parameters, that are updated during training by fitting them to data. Deep learning models have show remarkable accuracy gains on visual problems in video and...

doctoral thesis 2024

document

AI-Assisted Design & Optimization for Predictive Maintenance: A Case Study using Deep Learning and Search Metaheuristics for Structural Health Monitoring in Aviation

Ewald, Vincentius (author)

One of the classical solutions to maintain the aircraft structural integrity is to rely on the analysis of non-destructive testing (NDT) inspector with various inspection methods. However, it is relatively expensive in matter of time and costs to train human resources until the certification is reached. Further, in majority of the cases of...

doctoral thesis 2023

document

Design of Artificial Neural Network for predicting the reduction in permeability of porous media as a result of polymer gel injection

Kamel Targhi, Elahe (author), Emami Niri, Mohammad (author), Zitha, P.L.J. (author)

Cross-linked polymer gel is widely used in the oil and gas industry to block high permeability conduits and reduce water cut. The complex nature of this fluid, especially regarding flow in porous media, makes its numerical simulation very time-consuming. This study presents an approach to designing an Artificial Neural Network (ANN) model...

journal article 2023

document

No (good) loss no gain: Systematic evaluation of loss functions in deep learning-based side-channel analysis

Kerkhof, Maikel (author), Wu, L. (author), Perin, G. (author), Picek, S. (author)

Deep learning is a powerful direction for profiling side-channel analysis as it can break targets protected with countermeasures even with a relatively small number of attack traces. Still, it is necessary to conduct hyperparameter tuning to reach strong attack performance, which can be far from trivial. Besides many options stemming from the...

journal article 2023

document

Can We Empower Attentive E-reading with a Social Robot? An Introductory Study with a Novel Multimodal Dataset and Deep Learning Approaches

Lee, Y. (author), Specht, M.M. (author)

Reading on digital devices has become more commonplace, while it often poses challenges to learners' attention. In this study, we hypothesized that allowing learners to reflect on their reading phases with an empathic social robot companion might enhance learners' attention in e-reading. To verify our assumption, we collected a novel dataset ...

conference paper 2023

document

Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries

Al-Kaswan, A. (author), Ahmed, Toufique (author), Izadi, M. (author), Sawant, Anand Ashok (author), Devanbu, Premkumar (author), van Deursen, A. (author)

Binary reverse engineering is used to understand and analyse programs for which the source code is unavailable. Decompilers can help, transforming opaque binaries into a more readable source code-like representation. Still, reverse engineering is difficult and costly, involving considering effort in labelling code with helpful summaries....

conference paper 2023

document

Point Transformer-Based Human Activity Recognition Using High-Dimensional Radar Point Clouds

Guo, Zhongyuan (author), Guendel, Ronny (author), Yarovoy, Alexander (author), Fioranelli, F. (author)

Radar-based Human Activity Recognition(HAR) is considered by using snapshots of point clouds. Such point cloudsinterpret 2D images generated by an mm-wave FMCW MIMO radar enriched byincluding Doppler and temporal information. We use the similarity between suchradar data representation and the core of the self-attention concept inartificial...

conference paper 2023

document

Attack Graph Model for Cyber-Physical Power Systems Using Hybrid Deep Learning

Presekal, A. (author), Stefanov, Alexandru (author), Subramaniam Rajkumar, Vetrivel (author), Palensky, P. (author)

Electrical power grids are vulnerable to cyber attacks, as seen in Ukraine in 2015 and 2016. However, existing attack detection methods are limited. Most of them are based on power system measurement anomalies that occur when an attack is successfully executed at the later stages of the cyber kill chain. In contrast, the attacks on the Ukrainian...

journal article 2023

document

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

Guendel, Ronny (author), Ullmann, I. (author), Fioranelli, F. (author), Yarovoy, Alexander (author)

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...

conference paper 2023

document

To Spike or Not To Spike: A Digital Hardware Perspective on Deep Learning Acceleration

Ottati, F. (author), Gao, Chang (author), Chen, Qinyu (author), Brignone, Giovanni (author), Casu, Mario R. (author), Eshraghian, Jason K. (author), Lavagno, Luciano (author)

As deep learning models scale, they become increasingly competitive from domains spanning from computer vision to natural language processing; however, this happens at the expense of efficiency since they require increasingly more memory and computing power. The power efficiency of the biological brain outperforms any large-scale deep...

journal article 2023

document

Radar-only Instantaneous Ego-motion Estimation Using Neural Networks

Zhu, S. (author), Fioranelli, F. (author), Yarovoy, Alexander (author)

The problem of 2D instantaneous ego-motion estimation for vehicles equipped with automotive radars is studied. To leverage multi-dimensional radar point clouds and exploit point features automatically, without human engineering, a novel approach is proposed that transforms ego-motion estimation into a weighted least squares (wLSQ) problem using...

conference paper 2023

document

On the Strengths of Pure Evolutionary Algorithms in Generating Adversarial Examples

Bartlett, A.J. (author), Liem, C.C.S. (author), Panichella, A. (author)

Deep learning (DL) models are known to be highly accurate, yet vulnerable to adversarial examples. While earlier research focused on generating adversarial examples using whitebox strategies, later research focused on black-box strategies, as models often are not accessible to external attackers. Prior studies showed that black-box approaches...

conference paper 2023

document

Surface-related multiple estimation and removal with focus on shallow water

Zhang, D. (author)

For exploration and development of the earth, seismic surveys are acquired to provide information about the subsurface, within specifications of accuracy set by geologists and engineers, and within business constraints on budgets and turn-around time for processing and interpretation of the data. The case of seismic surveys that are acquired,...

doctoral thesis 2022

document

Data-efficient learning of geometric structures from single-view images

Lin, Y. (author)

The humanly constructed world is well-organized in space. A prominent feature of this artificial world is the presence of repetitive structures and coherent patterns, such as lines, junctions, wireframes of a building, and footprints of a city. These structures and patterns facilitate visual scene understanding by providing abundant geometry...

doctoral thesis 2022

document

A Hybrid Spatial-temporal Sequence-to-one Neural Network Model for Lane Detection

Dong, Y. (author), Patil, Sandeep (author), Farah, H. (author), van Arem, B. (author)

Reliable and accurate lane detection is of vital importance for the safe performance of Lane Keeping Assistance and Lane Departure Warning systems. However, under certain challenging peculiar circumstances (e.g., marking degradation, serious vehicle occlusion), it is quite difficult to get satisfactory performance in accurately detecting the...

poster 2022

document

Deep learning based prediction of fibrous microstructure permeability

Caglar, Baris (author), Broggi, G.C. (author), Ali, Muhammad A. (author), Orgéas, Laurent (author), Michaud, Véronique (author)

Knowledge of permeability of fibrous microstructures is crucial for predicting the mold fill times and resin flow path in composite manufacturing. Herein we report a method to rapidly predict the permeability of 3D fibrous microstructures. Our method relies on predicting the permeability of 2D cross-sections via deep neural networks and...

conference paper 2022

document

Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network

Moradi, M. (author), Ghorbani, R. (author), Sfarra, Stefano (author), Tax, D.M.J. (author), Zarouchas, D. (author)

Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of the artworks while avoiding the loss of any precious materials that make it up. The use of Infrared Thermography (IRT) is an interesting concept since surface and subsurface faults can be...

conference paper 2022

document

Deep learning accelerated prediction of the permeability of fibrous microstructures

Caglar, Baris (author), Broggi, G.C. (author), Ali, Muhammad A. (author), Orgéas, Laurent (author), Michaud, Véronique (author)

Permeability of fibrous microstructures is a key material property for predicting the mold fill times and resin flow path during composite manufacturing. In this work, we report an efficient approach to predict the permeability of 3D microstructures from deep learning based permeability predictions of 2D cross-sections combined via a circuit...

journal article 2022