Assessment of symptom severity in psychotic disorder patients based on heart rate variability and accelerometer mobility data.

BACKGROUND: Advancement in mental health care requires easily accessible, efficient diagnostic and treatment assessment tools. Viable biomarkers could enable objectification and automation of the diagnostic and treatment process, currently dependent on a psychiatric interview. Available wearable technology and computational methods make it possible to incorporate heart rate variability (HRV), an indicator of autonomic nervous system (ANS) activity, into potential diagnostic and treatment assessment frameworks as a biomarker of disease severity in mental disorders, including schizophrenia and bipolar disorder (BD). METHOD: We used a commercially available electrocardiography (ECG) chest strap with a built-in accelerometer, i.e. Polar H10, to record R-R intervals and physical activity of 30 hospitalized schizophrenia or BD patients and 30 control participants through ca. 1.5-2 h time periods. We validated a novel approach to data acquisition based on a flexible, patient-friendly and cost-effective setting. We analyzed the relationship between HRV and the Positive and Negative Syndrome Scale (PANSS) test scores, as well as the HRV and mobility coefficient. We also proposed a method of rest period selection based on R-R intervals and mobility data. The source code for reproducing all experiments is available on GitHub, while the dataset is published on Zenodo. RESULTS: Mean HRV values were lower in the patient compared to the control group and negatively correlated with the results of the PANSS general subcategory. For the control group, we also discovered the inversely proportional dependency between the mobility coefficient, based on accelerometer data, and HRV. This relationship was less pronounced for the treatment group. CONCLUSIONS: HRV value itself, as well as the relationship between HRV and mobility, may be promising biomarkers in disease diagnostics. These findings can be used to develop a flexible monitoring system for symptom severity assessment.

Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios.

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.

Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks.

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.

Aggregation of GPS, WLAN, and BLE Localization Measurements for Mobile Devices in Simulated Environments.

There are multiple available technologies to find the location of a mobile device, such as the Global Positioning System (GPS), Bluetooth Low-Energy beacons (BLE), and Wireless LAN (WLAN) localization. We propose a novel method to estimate the location of a moving device by aggregating information from multiple positioning systems into a single, more precise location estimation. The aggregated location is calculated as the place in which the product of the probability density functions (PDF) of individual methods has the maximum value. The experimental probability density functions of the three analyzed technologies are fitted by gamma distributions based on error histograms found in the literature and measurement data. The location measurements of the individual technologies are provided at different time instants, so the weighted product of the PDFs is used to improve aggregation accuracy. The discrete event-simulation model was used to evaluate the aggregation method with the Gauss­Markov mobility model. Simulations demonstrated that the calculated aggregated location was more accurate than any of the methods taken as the input, and average error was decreased by almost 13% compared to an arithmetic mean of the three considered localization methods, and by more than 36% compared to the single method with the highest accuracy.

Obstacle Detection as a Safety Alert in Augmented Reality Models by the Use of Deep Learning Techniques.

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.