Fast and resource-efficient inference in artificial neural networks (ANNs) is of utmost importance and drives many new developments in the area of new hardware architectures, e.g., by means of systolic arrays or algorithmic optimization such as pruning. In this paper, we present a novel method for lowering the computation effort for ANN inference utilizing ideas from information theory.Weight matrices are sliced into submatrices of logarithmic aspect ratios. These slices are then factorized. This reduces the number of required computations without compromising on fully parallel processing. We create a new hardware architecture for this dedicated purpose. We also provide a tool to map these sliced and factorized matrices efficiently to reconfigurable hardware. By comparing to the state of the art FPGA implementations, we can prove our claim by lowering hardware resources measured in look-up-tables (LUTs) by a factor of three to six. Our method does not rely on any particular property of the weight matrices of the ANN. It works for the general task of multiplying an input vector with a constant matrix and is also suitable for digital signal processing beyond ANNs.

Wild and forest fires pose a threat to forests and thereby, in extension, to wild life and humanity. Recent history shows an increase in devastating damages caused by fires. Traditional fire detection systems, such as video surveillance, fail in the early stages of a rural forest fire. Such systems would see the fire only when the damage is immense. Novel low-power smoke detection units based on gas sensors can detect smoke fumes in the early development stages of fires. The required proximity is only achieved using a distributed network of sensors interconnected via 5G. In the context of battery-powered sensor nodes, energy efficiency becomes a key metric. Using AI classification combined with XAI enables improved confidence regarding measurements. In this work, we present both a low-power gas sensor for smoke detection and a system elaboration regarding energy-efficient communication schemes and XAI-based evaluation. We show that leveraging edge processing in a smart way combined with buffered data samples in a 5G communication network yields optimal energy efficiency and rating results.

Condition monitoring of multirotor drones is challenging due to slight motor asynchrony and variations in rotational speed, which can cause detectors to misclassify states despite unchanged operating conditions. This work proposes a semi-supervised pipeline for anomaly detection in drone vibration signals, designed to attenuate the effect of rotational speed. Vibration data from nine signals (five healthy and four faulty) were collected at different speeds. The pipeline includes signal envelope extraction, computation of 51 features, detrending, and feature selection, yielding four key attributes. Six anomaly detectors were evaluated: a fuzzy ensemble (Meta-Fuzzy), Isolation Forest (IF), One-Class SVM (OCSVM), Extended-IF 1, Autoencoder (AE) and Variational Autoencoder (VAE). IF achieved the best accuracy (94% for the three-class setup and 93.6% for the two-class setup), followed by Meta-Fuzzy (92.81% and 93.64%). The main contribution lies in developing an integrated, lightweight, and experimentally validated methodology that unifies signals from multiple speeds into a single healthy class, maintaining high accuracy and paving the way for future onboard implementations.