document

End-to-end neural network based optimal quadcopter control

Ferede, R. (author), de Croon, G.C.H.E. (author), de Wagter, C. (author), Izzo, Dario (author)

Developing optimal controllers for aggressive high-speed quadcopter flight poses significant challenges in robotics. Recent trends in the field involve utilizing neural network controllers trained through supervised or reinforcement learning. However, the sim-to-real transfer introduces a reality gap, requiring the use of robust inner loop...

journal article 2024

document

Improving End-to-End Models for Children’s Speech Recognition

Patel, T.B. (author), Scharenborg, O.E. (author)

Children’s Speech Recognition (CSR) is a challenging task due to the high variability in children’s speech patterns and limited amount of available annotated children’s speech data. We aim to improve CSR in the often-occurring scenario that no children’s speech data is available for training the Automatic Speech Recognition (ASR) systems....

journal article 2024

document

Small end-to-end OCR model

Dun, Jingwen (author)

Optical Character Recognition (OCR) is a pivotal technology used to extract text information from images, finding wide-ranging applications in document digitization and medical records management. The integration of machine learning has ushered in an era of swift and precise OCR models. Broadly, OCR comprises two key components: detecting the...

master thesis 2023

document

End-to-End model for free-space-optical Air-to-Space communication services

Helsdingen, Wieger (author)

FSO satellite communication enables data transfer at high bandwidths, low latency, and high security. Due to these benefits, FSO communication services with satellite constellations can hugely improve global connectivity and bandwidth, while maintaining sufficient security. Modeling a global FSO satellite communication service is beneficial for...

master thesis 2023

document

Going dark? Analysing the impact of end-to-end encryption on the outcome of Dutch criminal court cases

Hartel, P.H. (author), van Wegberg, R.S. (author)

Law enforcement agencies struggle with criminals using end-to-end encryption (E2EE). A recent policy paper states: “while encryption is vital and privacy and cyber security must be protected, that should not come at the expense of wholly precluding law enforcement”. The main argument is that E2EE hampers attribution and prosecution of...

journal article 2023

document

Improving Whispered Speech Recognition Performance Using Pseudo-Whispered Based Data Augmentation

Lin, Zhaofeng (author), Patel, T.B. (author), Scharenborg, O.E. (author)

Whispering is a distinct form of speech known for its soft, breathy, and hushed characteristics, often used for private communication. The acoustic characteristics of whispered speech differ substantially from normally phonated speech and the scarcity of adequate training data leads to low automatic speech recognition (ASR) performance. To...

conference paper 2023

document

End-to-End Learning with Multiple Modalities for System-Optimised Renewables Nowcasting

Vohra, Rushil (author), Rajaei, A. (author), Cremer, Jochen (author)

With the increasing penetration of renewable power sources such as wind and solar, accurate short-term, nowcasting renewable power prediction is becoming increasingly important. This paper investigates the multi-modal (MM) learning and end-to-end (E2E) learning for nowcasting renewable power as an intermediate to energy management systems. MM...

conference paper 2023

document

Multi-Modal End-to-End Learning for Real-Time Monitoring of Sustainable Energy Systems

Vohra, Rushil (author)

The growth of renewable energy technologies is leading to energy systems that are more reliant than ever on renewables such as Wind and Photovoltaic (PV) power. Despite their benefits in terms of sustainability, their ubiquity poses challenges in maintaining grid stability given their intermittency, emphasising the prediction of power...

master thesis 2022

document

Biophysical mechanisms responsible for ultrasound neuromodulation in bilayer lipid membranes: Enabling the research that uncovers the mysterious interactions between ultrasound and neurons

Burghoorn, Niels (author)

Medical technology has seen great progress over the last centuries, developing increasingly more specialised therapy to benefit human health. The rise of the pharmaceutical industry and the research it drives are contributors to this success. However, in humanity's attempt to tackle more and more complex health issues, the conventional methods...

master thesis 2022

document

Cross-layer Optimization of MAC Scheduling for Multi-User Virtual Reality over 5G

Du, Zheng (author)

As a result of a global pandemic, there has been an increasing interest in tools for remote video conferencing and collaboration. One of these new innovations is social eXtended Reality (XR). By combining Virtual Reality (VR) and Augmented Reality (AR) technologies, social XR can provide a more immersive experience than any other VR application...

master thesis 2022

document

Using cross-model learnings for the Gram Vaani ASR Challenge 2022

Patel, T.B. (author), Scharenborg, O.E. (author)

In the diverse and multilingual land of India, Hindi is spoken as a first language by a majority of its population. Efforts are made to obtain data in terms of audio, transcriptions, dictionary, etc. to develop speech-technology applications in Hindi. Similarly, the Gram-Vaani ASR Challenge 2022 provides spontaneous telephone speech, with...

journal article 2022

document

Learning Interactively to Resolve Ambiguity in Sensor Policy Fusion for Robot

Bootsma, B.G.N. (author)

This work applies interactive imitation learning for the navigation of a mobile robot. The algorithm"Learning Interactively to Resolve Ambiguity in Sensor Policy Fusion" (LIRA-SPF) is introduced in the field of machine learning for robot navigation. This algorithm extends on existing methods by allowing the ambiguity-free fusion of existing...

master thesis 2021

document

End-to-end language diarization for bilingual code-switching speech

Liu, Hexin (author), Perera, Leibny Paola Garcia (author), Zhang, Xinyi (author), Dauwels, J.H.G. (author), Khong, Andy W.H. (author), Khudanpur, Sanjeev (author), Styles, Suzy J. (author)

We propose two end-to-end neural configurations for language diarization on bilingual code-switching speech. The first, a BLSTM-E2E architecture, includes a set of stacked bidirectional LSTMs to compute embeddings and incorporates the deep clustering loss to enforce grouping of languages belonging to the same class. The second, an XSA-E2E...

conference paper 2021

document

Reinforcement Learning for the Knapsack Problem

Pierotti, J. (author), Kronmueller, Maximilian (author), Alonso-Mora, J. (author), van Essen, J.T. (author), Böhmer, J.W. (author)

Combinatorial optimization (CO) problems are at the heart of both practical and theoretical research. Due to their complexity, many problems cannot be solved via exact methods in reasonable time; hence, we resort to heuristic solution methods. In recent years, machine learning (ML) has brought immense benefits in many research areas,...

book chapter 2021

document

Attended end-to-end architecture for age estimation from facial expression videos

Pei, Wenjie (author), Dibeklioglu, H. (author), Baltrusaitis, Tadas (author), Tax, D.M.J. (author)

The main challenges of age estimation from facial expression videos lie not only in the modeling of the static facial appearance, but also in the capturing of the temporal facial dynamics. Traditional techniques to this problem focus on constructing handcrafted features to explore the discriminative information contained in facial appearance...

journal article 2020

document

STEREOID Data Processor: Design and Performance Analysis

Laguduvan Thyagarajan, Prithvi (author)

Stereo Thermo-Optically Enhanced Radar for Earth, Ocean, Ice, and land Dynamics (STEREOID) is one of the candidates of the ESA (European Space Agency) , Earth Explorer 10 missions. The novel constellation system will consist of the active Sentinel-1 satellites and two passive spacecrafts, which can provide flexible baseline configurations. The...

master thesis 2019

document

Comparing the Performance of different Market Structures for Regional Heat Networks: A simulation study into the impact of fuel prices, consumption growth and investment decisions

Hartwig, wilan (author)

This research has compared three different market mechanisms in a quantitative way. The influences of these market mechanisms on the heating system were investigated for CO2 emissions, consumer price and producer surplus. In addition, the influences of investment decisions and price and consumption growth scenarios were tested. The research...

master thesis 2019

document

End-to-End learning of decision trees and forests

Hehn, T.M. (author), Kooij, J.F.P. (author), Hamprecht, Fred A. (author)

Conventional decision trees have a number of favorable properties, including a small computational footprint, interpretability, and the ability to learn from little training data. However, they lack a key quality that has helped fuel the deep learning revolution: that of being end-to-end trainable. Kontschieder et al. (ICCV, 2015) have...

journal article 2019

document

Regularization of end-to-end learning for cardiac diagnosis by multitask learning with segmentation

Snaauw, Gerard (author)

Cardiac magnetic resonance (CMR) is used extensively in the diagnosis and management of cardiovascular disease. Deep learning methods have proven to deliver segmentation results comparable to human experts in CMR imaging, however, no successful attempts have been made at fully automated diagnosis. This has been contributed to a lack of...

master thesis 2018

document

Privacy-Preserving Collection and Retrieval of Medical Wearables Data

Nateghizad, M. (author), Maulany, Christian (author), Erkin, Z. (author)

In recent years we have seen a rise in the amount of fitness tracking and self monitoring devices. These devices which often work in conjunction with a smartphone are becoming more accurate and are becoming widely adopted. This trend goes hand in hand with Electronic Health Care (e-health): the shift of health care to the digital domain. E...

conference paper 2017