Search results

Regression via classification (RvC) is a common method used for regression problems in deep learning, where the target variable belongs to a set of continuous values. By discretizing the target into a set of non-overlapping classes, it has been shown that training a classifier can improve neural network accuracy compared to using a standard regression approach. However, it is not clear how the set

This work considers direction-finding using a monostatic multiple-input multiple-output (MIMO) radar in the presence of impulsive noise. Employing a novel low-order covariance-based exponential kernel function, the proposed maximum likelihood (ML) formulation exploits an introduced quantum whale optimization algorithm (QWOA) to form the direction estimates. The resulting estimates are shown to be

This is a comment on the review by Korolev and Leisner (2020, hereafter KL2020). The only two laboratory/field studies ever to measure the breakup in ice-ice collisions for in-cloud conditions were negatively criticised by KL2020, as were our subsequent theoretical and modelling studies informed by both studies. First, hypothetically, even without any further laboratory experiments, such theoretic

Prior results on target localization and circumnavigation with bearing measurements in $\mathbb {R}^{2}$ are extended with integral action, resulting in a control system that is robust to bounded load disturbances on the control inputs. Such disturbances may arise in practice due to modeling errors and need to be considered to ensure small tracking errors. The control inputs are modeled as the sys

Jump models switch infrequently between states to fit a sequence of data while taking the ordering of the data into account We propose a new framework for joint feature selection, parameter and state-sequence estimation in jump models. Feature selection is necessary in high-dimensional settings where the number of features is large compared to the number of observations and the underlying states d

In this paper, we extend the generalized SPICE estimator to the multichannel case, illustrating the resulting performance gain for direction of arrival estimation. The resulting estimator is found to offer improved estimation performance and robustness to the presence of correlated sources.

In the dawning age of autonomous driving, accurate and robust tracking of vehicles is a quintessential part. This is inextricably linked with the problem of Simultaneous Localisation and Mapping (SLAM), in which one tries to determine the position of a vehicle relative to its surroundings without prior knowledge of them. The more you know about the object you wish to track—through sensors or mecha

We present a model for generating 3d articulated pedestrian locomotion in urban scenarios, with synthesis capabilities informed by the 3d scene semantics and geometry. We reformulate pedestrian trajectory forecasting as a structured reinforcement learning (RL) problem. This allows us to naturally combine prior knowledge on collision avoidance, 3d human motion capture and the motion of pedestrians

Precipitation over the Tibetan Plateau (TP) has major societal impacts in South and East Asia, but its spatiotemporal variations are not well understood, mainly because of the sparsely distributed in situ observation sites. With the help of the Global Precipitation Measurement satellite product IMERG and the ERA5 dataset, distinct precipitation seasonality features over the TP were objectively cla

A wide range of medical examinations are using analysis of images from different types of equipment. Using artificial intelligence, the assessments could be done automatically. This can have multiple benefits for the healthcare; reduce workload for medical doctors, decrease variations in diagnoses and cut waiting times for the patient as well as improve the performance. The aim of this thesis has

For decades, measured ice crystal number concentrations have been found to be orders of magnitude higher than measured ice-nucleating particle number concentrations in moderately cold clouds. This observed discrepancy reveals the existence of secondary ice production (SIP) in addition to the primary ice nucleation. However, the importance of SIP relative to primary ice nucleation remains highly un

3D human body reconstruction from monocular images has wide applications in our life, such as movie, animation, Virtual/Augmented Reality, medical research and so on. Due to the high freedom of human body in real scene and the ambiguity of inferring 3D objects from 2D images, it is a challenging task to accurately recover 3D human body models from images. In this thesis, we explore the methods for

We compare classic scalar temporal difference learning with three new distributional algorithms for playing the game of 5-in-a-row using deep neural networks: distributional temporal difference learning with constant learning rate, and two distributional temporal difference algorithms with adaptive learning rate. All these algorithms are applicable to any two-player deterministic zero sum game and

The task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. This work proposes a coarse-to-fine method to reconstruct detailed 3D human body from multi-view images combining Voxel Super-Resolution (VSR) based on learning the implicit representation. Firstly, the coarse 3D models are estimated by lea

Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications. Experimental results suggest that sufficiently deep and wide neural networks are not negatively impacted by suboptimal local minima. Despite recent progress, the reason for this outcome is not fully understood. Could deep networks have very few, if

Given a network of receivers and transmitters, the process of determining their positions from measured pseudoranges is known as network self-calibration. In this paper we consider 2D networks with synchronized receivers but unsynchronized transmitters and the corresponding calibration techniques, known as Time-Difference-Of-Arrival (TDOA) techniques. Despite previous work, TDOA self-calibration i

In this paper we present the matched window reassignment method, generalizing the results to complex valued signals in multiple dimensions. For an oscillating transient signal with an envelope shape described by an arbitrary twice differentiable function, the reassigned spectrogram, with a matched window, concentrates all energy into one single time-frequency point. An estimator for the parameters

Over the last couple of years audio and radio sensors have become cheaper and more common in our everyday life. Such sensors can be used to form a network, from which one can obtain distance measures by correlating the different received signals. One example of such distance measures is time-difference of arrival measurements (TDoA), which can be used to estimate the positions of the senders and r

The matched window reassigned spectrogram relocates all signal energy of an oscillating transient to the time- and frequency locations, resulting in a sharp peak in the time-frequency plane. However, previous research has shown that the method may result in split energy peaks for close components and in high noise levels, and the peak energy is then erroneously estimated. With use of novel knowled

In this work, we study under which circumstances it is appropriate to use simplified models for range determination using radar. Typically, pulsed radar systems result in the backscattered, demodulated, and matched signal having a chirp signal structure, with the frequency rate being related to the range to the reflecting target and the relative velocity of the transmitter and reflector. Far from