document

HAS-RL: A Hierarchical Approximate Scheme Optimized With Reinforcement Learning for NoC-Based NN Accelerators

Li, Siyue (author), Zhou, Shize (author), Xue, Yongqi (author), Fan, Wenjie (author), Cheng, Tong (author), Ji, Jinlun (author), Dai, Chenyang (author), Song, Wenqing (author), Gao, C. (author)

Network-on-Chip (NoC) is a scalable on-chip communication architecture for the NN accelerator, but with the increase in the number of nodes, the communication delay becomes higher. Applications such as machine learning have a certain resilience to noisy/erroneous transmitted data. Therefore, approximate communication becomes a promising solution...

journal article 2024

document

A Data-Driven Model for Power Loss Estimation of Magnetic Materials Based on Multi-Objective Optimization and Transfer Learning

Li, Z. (author), Wang, L. (author), Liu, R. (author), Mirzadarani, R. (author), Luo, T. (author), Lyu, D. (author), Ghaffarian Niasar, M. (author), Qin, Z. (author)

Traditional methods such as Steinmetz's equation (SE) and its improved variant (iGSE) have demonstrated limited precision in estimating power loss for magnetic materials. The introduction of Neural Network technology for assessing magnetic component power loss has significantly enhanced accuracy. Yet, an efficient method to incorporate detailed...

journal article 2024

document

Neural Network Applications in Aircraft Performance Functions

Attili, Cristiano (author)

One of the current trends in the aviation world is to work towards an increasingly more computer-aided approach to flying. Despite the improvements, limitations still inevitably exist in terms of power and storage capabilities in the aircraft avionics. To overcome this problem, different solutions have been proposed. A data-driven approach is...

master thesis 2023

document

Low-Power Gesture Recognition Using Convolutional Neural Networks and Ambient Lighting

de Beer, Arne (author)

This paper presents a study focused on developing an efficient signal processing pipeline and identifying suitable machine learning models for real-time gesture recognition using a testbed consisting of an Arduino Nano 33 BLE and three OPT101 photodiodes. Our research aims to address the challenges of limited computational power whilst...

bachelor thesis 2023

document

Comparative Study of Loss Functions in Personal Identification for Smartwatch Data: Examining Accuracy of Loss Functions in Personal Identification using Outlier Detection with Auto-encoders on Data from Smartwatches

Yümlü, Ege (author)

Smartwatches are equipped with sensors that allow continuous monitoring of physiological and physical activities, making them ideal sources of data for data analysis. However, accurately identifying individuals based on smartwatch data can be challenging due to the presence of outliers. Hence, outlier detection techniques play a crucial part in...

bachelor thesis 2023

document

Towards a low-cost air-written character recognition system: Designing an embedded machine learning system to recognise the first 10 letters of the Latin alphabet

Pronk, Paco (author)

This study introduces a novel system that leverages three photodiodes and ambient light to identify air-written characters on a resource-constrained device. Through experimentation, suitable methods of data preprocessing, machine learning and model compression were selected to recognize the first 10 characters of the Latin alphabet. The final...

bachelor thesis 2023

document

Towards Efficient Personalized Driver Behavior Modeling with Machine Unlearning

Song, Q. (author), Tan, Rui (author), Wang, J. (author)

Driver Behavior Modeling (DBM) aims to predict and model human driving behaviors, which is typically incorporated into the Advanced Driver Assistance System to enhance transportation safety and improve driving experience. Inverse reinforcement learning (IRL) is a prevailing DBM technique with the goal of modeling the driving policy by...

conference paper 2023

document

On the Reliability of RRAM-Based Neural Networks

Aziza, Hassen (author), Zambelli, Cristian (author), Hamdioui, S. (author), Diware, S.S. (author), Bishnoi, R.K. (author), Gebregiorgis, A.B. (author)

Emerging device technologies such as Resistive RAMs (RRAMs) are under investigation by many researchers and semiconductor companies; not only to realize e.g., embedded non-volatile memories, but also to enable energy-efficient computing making use of new data processing paradigms such as computation-in-memory. However, such devices suffer from...

conference paper 2023

document

Application of Deep Neural Networks to the Operator Space of Nonlinear PDE for Physics-Based Proxy Modelling

Hadjisotiriou, George (author), Mansour Pour, K. (author), Voskov, D.V. (author)

In this study, we utilize deep neural networks to approximate operators of a nonlinear partial differential equation (PDE), within the Operator-Based Linearization (OBL) simulation framework, and discover the physical space for a physics-based proxy model with reduced degrees of freedom. In our methodology, observations from a high-fidelity...

conference paper 2023

document

Recognising Gestures Using Ambient Light and Convolutional Neural Networks: Adapting Convolutional Neural Networks for Gesture Recognition on Resource-constrained Microcontrollers

Narchi, William (author)

This paper presents how a convolutional neural network can be constructed in order to recognise gestures using photodiodes and ambient light. A number of candidates are presented and evaluated, with the most performant being adopted for in-depth analysis. This network is then compressed in order to be ran on an Arduino Nano 33 BLE...

bachelor thesis 2022

document

Link adaptation and equalization for underwater acoustic communication using machine learning

van Heteren, Mauries (author)

The underwater acoustic environment is amongst the most challenging mediums for wireless communications. The three distinct challenges of underwater acoustic communication are the low and nonuniform propagation speed, frequency-dependent attenuation and time-varying multipath propagation.<br/>To cope with these challenges, physical layer...

master thesis 2022

document

Evaluation of Creep Behavior of Soft Soils by Utilizing Multisensor Data Combined with Machine Learning

Kovacevic, Meho Sasa (author), Bačić, Mario (author), Librić, Lovorka (author), Gavin, Kenneth (author)

To identify the unknown values of the parameters of Burger’s constitutive law, commonly used for the evaluation of the creep behavior of the soft soils, this paper demonstrates a procedure relying on the data obtained from multiple sensors, where each sensor is used to its best advantage. The geophysical, geotechnical, and unmanned aerial...

journal article 2022

document

Supervised machine learning in microfluidic impedance flow cytometry for improved particle size determination

de Bruijn, Douwe S. (author), ten Eikelder, Henricus R.A. (author), Papadimitriou, V. (author), Olthuis, Wouter (author), van den Berg, Albert (author)

The assessment of particle and cell size in electrical microfluidic flow cytometers has become common practice. Nevertheless, in flow cytometers with coplanar electrodes accurate determination of particle size is difficult, owing to the inhomogeneous electric field. Pre-defined signal templates and compensation methods have been introduced to...

journal article 2022

document

Secondary Frequency Control of Microgrids: An Online Reinforcement Learning Approach

Adibi, M. (author), van der Woude, J.W. (author)

In this article, we present a reinforcement learning-based scheme for secondary frequency control of lossy inverter-based microgrids. Compared with the existing methods in the literature, we relax the common restrictions on the system, i.e., being lossless, and the transmission lines and loads to have known constant impedances. The proposed...

journal article 2022

document

A Data-drive Approach for Robust Cockpit Crew Training Scheduling

van Kempen, J. (author), Santos, Bruno F. (author), Scherp, L. (author)

This work addresses the cockpit crew training scheduling problem. The objective is to produce a robust cockpit crew training schedule, including the assignment of trainees, instructors and simulators. To attain this objective, we propose a scheduling framework composed of four modules: a Training Scheduling &amp; Assignment Model (TS&amp;AM),...

journal article 2022

document

RRAM-based Low-Power Neuromorphic Computing Engine for Space Applications

Rudge, Zacharia (author)

With recent breakthroughs in AI and deep learning, applying these techniques to on-board computers for space applications has grown in interest to engineers on space applications. The space field brings its own challenges, such as reliability and power restrictions. The proposed solution in this work concerns a neuromorphic accelerator for a...

master thesis 2021

document

Improving the Performance of Object Counting Using Training Images in the Frequency Domain

Rogmans, Dani (author)

Convolutional Neural Networks (CNNs) have made significant strides in the field of image processing over the last decade. Different approaches have been taken and improvements have been suggested. This paper looks at a newer novelty to neural networks for image counting, which is based on single-pixel center localization instead of the...

bachelor thesis 2021

document

A Compact Neural Network for Fused Lasso Signal Approximator

Mohammadi, Majid (author)

The fused lasso signal approximator (FLSA) is a vital optimization problem with extensive applications in signal processing and biomedical engineering. However, the optimization problem is difficult to solve since it is both nonsmooth and nonseparable. The existing numerical solutions implicate the use of several auxiliary variables in order...

journal article 2021

document

Privacy preserving detection and classification of playground users

Bekker, Bernard (author)

Large cities in the Netherlands, like Rotterdam, have hundreds of playgrounds, but local governments have little information on how children and adults use them. Usage data can help create playgrounds that better fit with the residents' needs by identifying what elements of a playground are the most popular, and which do not get used. The AMS...

master thesis 2020

document

An energy efficient time-mode digit classification neural network implementation

Akgün, O.C. (author), Mei, J. (author)

This paper presents the design of an ultra-low energy neural network that uses time-mode signal processing). Handwritten digit classification using a single-layer artificial neural network (ANN) with a Softmin-based activation function is described as an implementation example. To realize time-mode operation, the presented design makes use of...

journal article 2020