arXiv subjects

Stefan Schneider

Publications and source records attributed to Stefan Schneider.

13 recordsLinked to original sources

arXiv2024

Transformer-based nowcasting of radar composites from satellite images for severe weather

Weather radar data are critical for nowcasting and an integral component of numerical weather prediction models. While weather radar data provide valuable information at high resolution, their ground-based nature limits their availability, which impedes large-scale applications. In contrast, meteorological satellites cover larger domains but with coarser resolution. However, with the rapid advancements in data-driven methodologies and modern sensors aboard geostationary satellites, new opportunities are emerging to bridge the gap between ground- and space-based observations, ultimately leading to more skillful weather prediction with high accuracy. Here, we present a Transformer-based model for nowcasting ground-based radar image sequences using satellite data up to two hours lead time. Trained on a dataset reflecting severe weather conditions, the model predicts radar fields occurring under different weather phenomena and shows robustness against rapidly growing/decaying fields and complex field structures. Model interpretation reveals that the infrared channel centered at 10.3 $μm$ (C13) contains skillful information for all weather conditions, while lightning data have the highest relative feature importance in severe weather conditions, particularly in shorter lead times. The model can support precipitation nowcasting across large domains without an explicit need for radar towers, enhance numerical weather prediction and hydrological models, and provide radar proxy for data-scarce regions. Moreover, the open-source framework facilitates progress towards operational data-driven nowcasting.

physics.ao-ph↗

arXiv2020

Counting Fish and Dolphins in Sonar Images Using Deep Learning

Deep learning provides the opportunity to improve upon conflicting reports considering the relationship between the Amazon river's fish and dolphin abundance and reduced canopy cover as a result of deforestation. Current methods of fish and dolphin abundance estimates are performed by on-site sampling using visual and capture/release strategies. We propose a novel approach to calculating fish abundance using deep learning for fish and dolphin estimates from sonar images taken from the back of a trolling boat. We consider a data set of 143 images ranging from 0-34 fish, and 0-3 dolphins provided by the Fund Amazonia research group. To overcome the data limitation, we test the capabilities of data augmentation on an unconventional 15/85 training/testing split. Using 20 training images, we simulate a gradient of data up to 25,000 images using augmented backgrounds and randomly placed/rotation cropped fish and dolphin taken from the training set. We then train four multitask network architectures: DenseNet201, InceptionNetV2, Xception, and MobileNetV2 to predict fish and dolphin numbers using two function approximation methods: regression and classification. For regression, Densenet201 performed best for fish and Xception best for dolphin with mean squared errors of 2.11 and 0.133 respectively. For classification, InceptionResNetV2 performed best for fish and MobileNetV2 best for dolphins with a mean error of 2.07 and 0.245 respectively. Considering the 123 testing images, our results show the success of data simulation for limited sonar data sets. We find DenseNet201 is able to identify dolphins after approximately 5000 training images, while fish required the full 25,000. Our method can be used to lower costs and expedite the data analysis of fish and dolphin abundance to real-time along the Amazon river and river systems worldwide.

cs.CV↗

arXiv2020

Similarity Learning Networks for Animal Individual Re-Identification -- Beyond the Capabilities of a Human Observer

Deep learning has become the standard methodology to approach computer vision tasks when large amounts of labeled data are available. One area where traditional deep learning approaches fail to perform is one-shot learning tasks where a model must correctly classify a new category after seeing only one example. One such domain is animal re-identification, an application of computer vision which can be used globally as a method to automate species population estimates from camera trap images. Our work demonstrates both the application of similarity comparison networks to animal re-identification, as well as the capabilities of deep convolutional neural networks to generalize across domains. Few studies have considered animal re-identification methods across species. Here, we compare two similarity comparison methodologies: Siamese and Triplet-Loss, based on the AlexNet, VGG-19, DenseNet201, MobileNetV2, and InceptionV3 architectures considering mean average precision (mAP)@1 and mAP@5. We consider five data sets corresponding to five different species: humans, chimpanzees, humpback whales, fruit flies, and Siberian tigers, each with their own unique set of challenges. We demonstrate that Triplet Loss outperformed its Siamese counterpart for all species. Without any species-specific modifications, our results demonstrate that similarity comparison networks can reach a performance level beyond that of humans for the task of animal re-identification. The ability for researchers to re-identify an animal individual upon re-encounter is fundamental for addressing a broad range of questions in the study of population dynamics and community/behavioural ecology. Our expectation is that similarity comparison networks are the beginning of a major trend that could stand to revolutionize animal re-identification from camera trap data.

cs.CV↗

arXiv2019

The Softwarised Network Data Zoo

More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input data to train their internal models. However, such training data is barely available for the software networking domain and most presented solutions rely on their own, sometimes not even published, data sets. This makes it hard, or even infeasible, to reproduce and compare many of the existing solutions. As a result, it ultimately slows down the adoption of machine learning approaches in softwarised networks. To this end, we introduce the "softwarised network data zoo" (SNDZoo), an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. We present a general methodology to collect, archive, and publish those data sets for use by other researches and, as an example, eight initial data sets, focusing on the performance of virtualised network functions.

cs.NI↗

arXiv2018

Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data

The ability of a researcher to re-identify (re-ID) an individual animal upon re-encounter is fundamental for addressing a broad range of questions in the study of ecosystem function, community and population dynamics, and behavioural ecology. In this review, we describe a brief history of camera traps for re-ID, present a collection of computer vision feature engineering methodologies previously used for animal re-ID, provide an introduction to the underlying mechanisms of deep learning relevant to animal re-ID, highlight the success of deep learning methods for human re-ID, describe the few ecological studies currently utilizing deep learning for camera trap analyses, and our predictions for near future methodologies based on the rapid development of deep learning methods. By utilizing novel deep learning methods for object detection and similarity comparisons, ecologists can extract animals from an image/video data and train deep learning classifiers to re-ID animal individuals beyond the capabilities of a human observer. This methodology will allow ecologists with camera/video trap data to re-identify individuals that exit and re-enter the camera frame. Our expectation is that this is just the beginning of a major trend that could stand to revolutionize the analysis of camera trap data and, ultimately, our approach to animal ecology.

cs.CV↗

arXiv2018

Specifying and Analyzing Virtual Network Services Using Queuing Petri Nets

For optimal placement and orchestration of network services, it is crucial that their structure and semantics are specified clearly and comprehensively and are available to an orchestrator. Existing specification approaches are either ambiguous or miss important aspects regarding the behavior of virtual network functions (VNFs) forming a service. We propose to formally and unambiguously specify the behavior of these functions and services using Queuing Petri Nets (QPNs). QPNs are an established method that allows to express queuing, synchronization, stochastically distributed processing delays, and changing traffic volume and characteristics at each VNF. With QPNs, multiple VNFs can be connected to complete network services in any structure, even specifying bidirectional network services containing loops. We propose a tool-based workflow that supports the specification of network services and the automatic generation of corresponding simulation code to enable an in-depth analysis of their behavior and performance. In a case study, we show how developers can benefit from analysis insights, e.g., to anticipate the impact of different service configurations. We also discuss how management and orchestration systems can benefit from our clear and comprehensive specification approach and its extensive analysis possibilities, leading to better placement of VNFs and improved Quality of Service.

cs.NI↗

arXiv2018

Fast Exact k-Means, k-Medians and Bregman Divergence Clustering in 1D

The $k$-Means clustering problem on $n$ points is NP-Hard for any dimension $d\ge 2$, however, for the 1D case there exists exact polynomial time algorithms. Previous literature reported an $O(kn^2)$ time dynamic programming algorithm that uses $O(kn)$ space. It turns out that the problem has been considered under a different name more than twenty years ago. We present all the existing work that had been overlooked and compare the various solutions theoretically. Moreover, we show how to reduce the space usage for some of them, as well as generalize them to data structures that can quickly report an optimal $k$-Means clustering for any $k$. Finally we also generalize all the algorithms to work for the absolute distance and to work for any Bregman Divergence. We complement our theoretical contributions by experiments that compare the practical performance of the various algorithms.

cs.DS↗

arXiv2018

Deep Learning Object Detection Methods for Ecological Camera Trap Data

Deep learning methods for computer vision tasks show promise for automating the data analysis of camera trap images. Ecological camera traps are a common approach for monitoring an ecosystem's animal population, as they provide continual insight into an environment without being intrusive. However, the analysis of camera trap images is expensive, labour intensive, and time consuming. Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images. Here, we demonstrate their capabilities by training and comparing two deep learning object detection classifiers, Faster R-CNN and YOLO v2.0, to identify, quantify, and localize animal species within camera trap images using the Reconyx Camera Trap and the self-labeled Gold Standard Snapshot Serengeti data sets. When trained on large labeled datasets, object recognition methods have shown success. We demonstrate their use, in the context of realistically sized ecological data sets, by testing if object detection methods are applicable for ecological research scenarios when utilizing transfer learning. Faster R-CNN outperformed YOLO v2.0 with average accuracies of 93.0\% and 76.7\% on the two data sets, respectively. Our findings show promising steps towards the automation of the labourious task of labeling camera trap images, which can be used to improve our understanding of the population dynamics of ecosystems across the planet.

cs.CV↗

arXiv2017

On the Fine-grained Complexity of One-Dimensional Dynamic Programming

In this paper, we investigate the complexity of one-dimensional dynamic programming, or more specifically, of the Least-Weight Subsequence (LWS) problem: Given a sequence of $n$ data items together with weights for every pair of the items, the task is to determine a subsequence $S$ minimizing the total weight of the pairs adjacent in $S$. A large number of natural problems can be formulated as LWS problems, yielding obvious $O(n^2)$-time solutions. In many interesting instances, the $O(n^2)$-many weights can be succinctly represented. Yet except for near-linear time algorithms for some specific special cases, little is known about when an LWS instantiation admits a subquadratic-time algorithm and when it does not. In particular, no lower bounds for LWS instantiations have been known before. In an attempt to remedy this situation, we provide a general approach to study the fine-grained complexity of succinct instantiations of the LWS problem. In particular, given an LWS instantiation we identify a highly parallel core problem that is subquadratically equivalent. This provides either an explanation for the apparent hardness of the problem or an avenue to find improved algorithms as the case may be. More specifically, we prove subquadratic equivalences between the following pairs (an LWS instantiation and the corresponding core problem) of problems: a low-rank version of LWS and minimum inner product, finding the longest chain of nested boxes and vector domination, and a coin change problem which is closely related to the knapsack problem and (min,+)-convolution. Using these equivalences and known SETH-hardness results for some of the core problems, we deduce tight conditional lower bounds for the corresponding LWS instantiations. We also establish the (min,+)-convolution-hardness of the knapsack problem.

cs.CC↗

arXiv2016

Subquadratic Algorithms for Succinct Stable Matching

We consider the stable matching problem when the preference lists are not given explicitly but are represented in a succinct way and ask whether the problem becomes computationally easier and investigate other implications. We give subquadratic algorithms for finding a stable matching in special cases of natural succinct representations of the problem, the $d$-attribute, $d$-list, geometric, and single-peaked models. We also present algorithms for verifying a stable matching in the same models. We further show that for $d = ω(\log n)$ both finding and verifying a stable matching in the $d$-attribute and $d$-dimensional geometric models requires quadratic time assuming the Strong Exponential Time Hypothesis. This suggests that these succinct models are not significantly simpler computationally than the general case for sufficiently large $d$.

cs.DS↗

arXiv2014

0-1 Integer Linear Programming with a Linear Number of Constraints

We give an exact algorithm for the 0-1 Integer Linear Programming problem with a linear number of constraints that improves over exhaustive search by an exponential factor. Specifically, our algorithm runs in time $2^{(1-\text{poly}(1/c))n}$ where n is the number of variables and cn is the number of constraints. The key idea for the algorithm is a reduction to the Vector Domination problem and a new algorithm for that subproblem.

cs.CC↗

arXiv2013

Satisfiability Algorithms for Restricted Circuit Classes

In recent years, finding new satisfiability algorithms for various circuit classes has been a very active line of research. Despite considerable progress, we are still far away from a definite answer on which circuit classes allow fast satisfiability algorithms. This survey takes a (far from exhaustive) look at some recent satisfiability algorithms for a range of circuit classes and high- lights common themes. A special focus is given to connections between satisfiability algorithms and circuit lower bounds. A second focus is on reductions from satisfiability algorithms to a range of polynomial time problems, such as matrix multiplication and the Vector Domination Problem.

cs.CC↗

arXiv2013

A Satisfiability Algorithm for Sparse Depth Two Threshold Circuits

We give a nontrivial algorithm for the satisfiability problem for cn-wire threshold circuits of depth two which is better than exhaustive search by a factor 2^{sn} where s= 1/c^{O(c^2)}. We believe that this is the first nontrivial satisfiability algorithm for cn-wire threshold circuits of depth two. The independently interesting problem of the feasibility of sparse 0-1 integer linear programs is a special case. To our knowledge, our algorithm is the first to achieve constant savings even for the special case of Integer Linear Programming. The key idea is to reduce the satisfiability problem to the Vector Domination Problem, the problem of checking whether there are two vectors in a given collection of vectors such that one dominates the other component-wise. We also provide a satisfiability algorithm with constant savings for depth two circuits with symmetric gates where the total weighted fan-in is at most cn. One of our motivations is proving strong lower bounds for TC^0 circuits, exploiting the connection (established by Williams) between satisfiability algorithms and lower bounds. Our second motivation is to explore the connection between the expressive power of the circuits and the complexity of the corresponding circuit satisfiability problem.

cs.CC↗