In recent years, growing interest in deep learning neural networks has raised a question on how they can be used for effective processing of high-dimensional datasets produced by hyperspectral imaging (HSI). HSI, traditionally viewed as being within the scope of remote sensing, is used in non-invasive substance classification. One of the areas of potential application is forensic science, where substance classification on the scenes is important. An example problem from that area—blood stain classification—is a case study for the evaluation of methods that process hyperspectral data. To investigate the deep learning classification performance for this problem we have performed experiments on a dataset which has not been previously tested using this kind of model. This dataset consists of several images with blood and blood-like substances like ketchup, tomato concentrate, artificial blood, etc. To test both the classic approach to hyperspectral classification and a more realistic application-oriented scenario, we have prepared two different sets of experiments. In the first one, Hyperspectral Transductive Classification (HTC), both a training and a test set come from the same image. In the second one, Hyperspectral Inductive Classification (HIC), a test set is derived from a different image, which is more challenging for classifiers but more useful from the point of view of forensic investigators. We conducted the study using several architectures like 1D, 2D and 3D convolutional neural networks (CNN), a recurrent neural network (RNN) and a multilayer perceptron (MLP). The performance of the models was compared with baseline results of Support Vector Machine (SVM). We have also presented a model evaluation method based on t-SNE and confusion matrix analysis that allows us to detect and eliminate some cases of model undertraining. Our results show that in the transductive case, all models, including the MLP and the SVM, have comparative performance, with no clear advantage of deep learning models. The Overall Accuracy range across all models is 98–100% for the easier image set, and 74–94% for the more difficult one. However, in a more challenging inductive case, selected deep learning architectures offer a significant advantage; their best Overall Accuracy is in the range of 57–71%, improving the baseline set by the non-deep models by up to 9 percentage points. We have presented a detailed analysis of results and a discussion, including a summary of conclusions for each tested architecture. An analysis of per-class errors shows that the score for each class is highly model-dependent. Considering this and the fact that the best performing models come from two different architecture families (3D CNN and RNN), our results suggest that tailoring the deep neural network architecture to hyperspectral data is still an open problem.

High demand for computational power significantly limits the possibility of using modern deep learning methods in the environments where one has to deal with devices limited by the performance and the energy constraints. To address this issue, this paper proposes a novel method of combining the pruning and the transfer learning (TL) techniques for the purpose of delivering solid accuracy while simultaneously lowering the demand for energy and computing power. This method is referred to as finicky TL as it is finicky during the process of selecting filters from a pretrained feature extractor to compose a sparser architecture. The proposed filter selection process is based on an original approach utilizing the Jaccard similarity coefficient calculated between the activation maps and the masks obtained by semantic segmentation. This enables the use of convolutional neural networks, trained previously on a large generic dataset, in a crack classification task. The presented method significantly lowers the inference time while maintaining or even slightly increasing the classification accuracy, enabling real-time operation on single-board computers.

Augmented reality (AR) is becoming increasingly popular due to its numerous applications. This is especially evident in games, medicine, education, and other areas that support our everyday activities. Moreover, this kind of computer system not only improves our vision and our perception of the world that surrounds us, but also adds additional elements, modifies existing ones, and gives additional guidance. In this article, we focus on interpreting a reality-based real-time environment evaluation for informing the user about impending obstacles. The proposed solution is based on a hybrid architecture that is capable of estimating as much incoming information as possible. The proposed solution has been tested and discussed with respect to the advantages and disadvantages of different possibilities using this type of vision.

This study is focused on applying genetic algorithms (GAs) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspectral images with blood and five visually similar substances to test GA-optimised classifiers in two scenarios: when the training and test data come from the same image and when they come from different images, which is a more challenging task due to significant spectral differences. In our experiments, we compare GA with a classic model optimisation through a grid search. Our results show that GA-based model optimisation can reduce the number of bands and create an accurate classifier that outperforms the GS-based reference models, provided that, during model optimisation, it has access to examples similar to test data. We illustrate this with experiments highlighting the importance of a validation set.

The LoRa radio transmission is a popular low power WAN technology due to the use of unlicensed spectrum, low cost and long-range. LoRa devices use different Spreading Factors, which are dynamically selected by an Adaptive Data Rate (ADR) algorithm, based on signal-to-noise ratio (SNR) measurements. We discuss the influence of ADR parameters on the network performance. We use extensive simulations to estimate the probability of message delivery and energy consumption for different configurations of ADR parameters. The analysis has been performed using OMNeT++ Discrete Event Simulator together with FLoRa framework for two types of network topologies: random uniform and based on a sample city-wide LoRa deployment. The results show that there is a significant trade-off between the energy utilization and message delivery ratio probability and that the default configuration of ADR leads to over-optimistic decrease of SF and TX power, as a consequence leading to packet loss ratio >50 %.