Real-World Applications of Artificial Intelligence in Architecture

Real-world applications of Artificial Intelligence (AI) in architecture have been explored more recently at Technical University (TU) Delft by integrating AI in Design-to-Robotic-Production-Assembly and -Operation (D2RPA&O) methods. These embed robotics into building processes and buildings by linking computational design with robotic...

Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI

Modern AI practices all strive towards the same goal: better results. In the context of deep learning, the term "results"often refers to the achieved accuracy on a competitive problem set. In this paper, we adopt an idea from the emerging field of Green AI to consider energy consumption as a metric of equal importance to accuracy and to...

Radar Perception for Autonomous Unmanned Aerial Vehicles: A Survey

The advent of consumer and industrial Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, has opened business opportunities in many fields, including logistics, smart agriculture, inspection, surveillance, and construction. In addition, the autonomous operations of UAVs reduce risks by minimizing the time spent by human workers...

User Scheduling in Massive MIMO: A Joint Deep Learning and Genetic Algorithm Approach

Due to the limited number of radio frequency (RF) chains in millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) receivers using analog beamforming/hybrid beamforming, there is a restriction in scheduling the number of users in each transmission time interval. Therefore, fast and low-complexity user scheduling methods based on...

3-D contrast enhanced ultrasound imaging of an in vivo chicken embryo with a sparse array and deep learning based adaptive beamforming

3-D contrast enhanced ultrasound enables better visualization of inherently 3-D vascular geometries compared to an intersecting plane. Additionally, it would allow the application of motion correction techniques for all directions. Both contrast detection and motion correction work better on high-frame rate data. However high-frame rate 3-D...

Detection and Identification of Generator Disconnection Using Multi-layer Perceptron Neural Network Considering Low Inertia Scenario

This research paper presents a method that uses measurements of voltages angles, as provided by phasor measurement units (PMU), to accurately detect the sudden disconnection of a generation unit from a power grid. Results in this research paper have demonstrated, in a practical fashion, that a multi-layer perceptron (MLP) neural network (NN) can...

Learning-aided joint time-frequency channel estimation for 5G new radio

In this paper, we propose a learning-aided signal processing solution for channel estimation in 5G new radio (NR). Channel estimation is an important algorithm for baseband modem design. In 5G NR, estimating the channel is challenging due to two reasons. First, the pilot signals are transmitted over a small fraction of the available time...

Training for Implicit Norms in Deep Reinforcement Learning Agents through Adversarial Multi-Objective Reward Optimization

We propose a deep reinforcement learning algorithm that employs an adversarial training strategy for adhering to implicit human norms alongside optimizing for a narrow goal objective. Previous methods which incorporate human values into reinforcement learning algorithms either scale poorly or assume hand-crafted state features. Our algorithm...

Deep Learning-based identification of human gait by radar micro-Doppler measurements

For the first time identification of human individuals using micro-Doppler (m-D) features measured at X-band has been demonstrated. Deep Convolutional Neural Networks (DCNNs) have been used to perform classification. Inspection and visualization of the classification results were performed using Uniform Manifold Approximation and Projection ...

Day-ahead Wind Power Predictions at Regional Scales: Post-processing Operational Weather Forecasts with a Hybrid Neural Network

A hybrid neural network model, comprising of a convolutional neural network and a multilayer perceptron network, has been developed for day-ahead forecasting of regional scale wind power production. This model requires operational weather forecasts as input and also has the capability to ingest data from ensemble forecasts. Even though the...

Human activity classification with radar signal processing and machine learning

As the number of older adults increases worldwide, new paradigms for indoor activity monitoring are required to keep people living at home independently longer. Radar-based human activity recognition has been identified as a sensing modality of choice because it is privacy-preserving and does not require end-users compliance or manipulation. In...

DeepTC-Enhancer: Improving the Readability of Automatically Generated Tests

Automated test case generation tools have been successfully proposed to reduce the amount of human and infrastructure resources required to write and run test cases. However, recent studies demonstrate that the readability of generated tests is very limited due to (i) uninformative identifiers and (ii) lack of proper documentation. Prior...

DeepSHM: A deep learning approach for structural health monitoring based on guided Lamb wave technique

In our previous work, we demonstrated how to use inductive bias to infuse a convolutional neural network (CNN) with domain knowledge from fatigue analysis for aircraft visual NDE. We extend this concept to SHM and therefore in this paper, we present a novel framework called DeepSHM which involves data augmentation of captured sensor signals...