Search the digital library catalog

Abstract: Because of the prevalence of depression, its often-chronic course, relapse and associated disability, early detection and non-intrusive monitoring is a crucial tool for timely diagnosis and treatment, remission of depression and prevention of relapse. In this way, its impact on quality of life and well-being can be limited. Current attempts to use artificial intelligence for the early classification of depression are mostly data-driven and thus non-transparent and lack effective means to deal with uncertainties. Therefore, in this paper, we propose an end-to-end framework for extracting observable depression cues from diary recordings. Furthermore, we also explore its feasibility for automatic detection of depression symptoms using observable behavioural cues. The proposed end-to-end framework for extracting depression was used to evaluate 28 video recordings from the Symptom Media dataset and 27 recordings from the DAIC-WOZ dataset. We compared the presence of the extracted features between recordings of individuals with and without a depressive disorder. We identified several cues consistent with previous studies in terms of their differentiation between individuals with and without depressive disorder across both datasets among language (i.e., use of negatively valanced words, use of first-person singular pronouns, some features of language complexity, explicit mentions of treatment for depression), speech (i.e., monotonous speech, voiced speech and pauses, speaking rate, low articulation rate), and facial cues (i.e., rotational energy of head movements). The nature/context of the discourse, the impact of other disorders and physical/psychological stress, and the quality and resolution of the recordings all play an important role in matching the digital features to the relevant background. In this way, the work presented in this paper provides a novel approach to extracting a wide range of cues relevant to the classification of depression and opens up new opportunities for further research.
Keywords: digital biomarkers of depression, facial cues, speech cues, language cues, deep learning, end-to-end pipeline, artificial intelligence
Published in DKUM: 17.01.2025; Views: 0; Downloads: 3
Full text (2,34 MB)

Keywords: cities green mobility, bike sharing demand prediction, cable car demand prediction, machine learning, deep learning
Published in DKUM: 22.08.2024; Views: 76; Downloads: 7
Full text (4,33 MB)

Abstract: This paper presents the design of a high-voltage pulse-based radar and a supervised data processing method for soil moisture estimation. The goal of this research was to design a pulse-based radar to detect changes in soil moisture using a cross-hole approach. The pulse-based radar with three transmitting antennas was placed into a 12 m deep hole, and a receiver with three receive antennas was placed into a different hole separated by 100 m from the transmitter. The pulse generator was based on a Marx generator with an LC filter, and for the receiver, the high-frequency data acquisition card was used, which can acquire signals using 3 Gigabytes per second. Used borehole antennas were designed to operate in the wide frequency band to ensure signal propagation through the soil. A deep regression convolutional network is proposed in this paper to estimate volumetric soil moisture using time-sampled signals. A regression convolutional network is extended to three dimensions to model changes in wave propagation between the transmitted and received signals. The training dataset was acquired during the period of 73 days of acquisition between two boreholes separated by 100 m. The soil moisture measurements were acquired at three points 25 m apart to provide ground truth data. Additionally, water was poured into several specially prepared boreholes between transmitter and receiver antennas to acquire additional dataset for training, validation, and testing of convolutional neural networks. Experimental results showed that the proposed system is able to detect changes in the volumetric soil moisture using Tx and Rx antennas.
Keywords: ground penetrating radar, cross-hole, L-band, deep learning, convolutional neural network, soil moisture estimation
Published in DKUM: 03.04.2024; Views: 448; Downloads: 26
Full text (3,22 MB)
This document has many files! More...

Abstract: With the rise of deep learning technology, the field of medical image segmentation has undergone rapid development. In recent years, convolutional neural networks (CNNs) have brought many achievements and become the consensus in medical image segmentation tasks. Although many neural networks based on U-shaped structures and methods, such as skip connections have achieved excellent results in medical image segmentation tasks, the properties of convolutional operations limit their ability to effectively learn local and global features. To address this problem, the Transformer from the field of natural language processing (NLP) was introduced to the image segmentation field. Various Transformer-based networks have shown significant performance advantages over mainstream neural networks in different visual tasks, demonstrating the huge potential of Transformers in the field of image segmentation. However, Transformers were originally designed for NLP and ignore the multidimensional nature of images. In the process of operation, they may destroy the 2D structure of the image and cannot effectively capture low-level features. Therefore, we propose a new multi-scale cross-attention method called M-VAN Unet, which is designed based on the Visual Attention Network (VAN) and can effectively learn local and global features. We propose two attention mechanisms, namely MSC-Attention and LKA-Cross-Attention, for capturing low-level features and promoting global information interaction. MSC-Attention is designed for multi-scale channel attention, while LKA-Cross-Attention is a cross-attention mechanism based on the large kernel attention (LKA). Extensive experiments show that our method outperforms current mainstream methods in evaluation metrics such as Dice coefficient and Hausdorff 95 coefficient.
Keywords: CNNs, deep learning, medical image processing, NLP, semantic segmentation
Published in DKUM: 14.03.2024; Views: 496; Downloads: 311
Full text (1,46 MB)
This document has many files! More...

Abstract: A few promising solutions for thermal imaging Unexploded Ordnance (UXO) detection were proposed after the start of the military conflict in Ukraine in 2014. At the same time, most of the landmine clearance protocols and practices are based on old, 20th-century technologies. More than 60 countries worldwide are still affected by explosive remnants of war, and new areas are contaminated almost every day. To date, no automated solutions exist for surface UXO detection by using thermal imaging. One of the reasons is also that there are no publicly available data. This research bridges both gaps by introducing an automated UXO detection method, and by publishing thermal imaging data. During a project in Bosnia and Herzegovina in 2019, an organisation, Norwegian People's Aid, collected data about unexploded ordnances and made them available for this research. Thermal images with a size of 720 x 480 pixels were collected by using an Unmanned Aerial Vehicle at a height of 3 m, thus achieving a very small Ground Sampling Distance (GSD). One of the goals of our research was also to verify if the explosive war remnants' detection accuracy could be improved further by using Convolutional Neural Networks (CNN). We have experimented with various existing modern CNN architectures for object identification, whereat the YOLOv5 model was selected as the most promising for retraining. An eleven-class object detection problem was solved primarily in this study. Our data were annotated semi-manually. Five versions of the YOLOv5 model, fine-tuned with a grid-search, were trained end-to-end on randomly selected 640 training and 80 validation images from our dataset. The trained models were verified on the remaining 88 images from our dataset. Objects from each of the eleven classes were identified with more than 90% probability, whereat the Mean Average Precision (mAP) at a 0.5 threshold was 99.5%, and the mAP at thresholds from 0.5 to 0.95 was 87.0% up to 90.5%, depending on the model's complexity. Our results are comparable to the state-of-the-art, whereat these object detection methods have been tested on other similar small datasets with thermal images. Our study is one of the few in the field of Automated UXO detection by using thermal images, and the first that solves the problem of identifying more than one class of objects. On the other hand, publicly available thermal images with a relatively small GSD will enable and stimulate the development of new detection algorithms, where our method and results can serve as a baseline. Only really accurate automatic UXO detection solutions will help to solve one of the least explored worldwide life-threatening problems.
Keywords: unmanned aerial vehicle, unexploded ordnance, thermal imaging, UXOTi_NPA dataset, convolutional neural networks, deep learning
Published in DKUM: 12.02.2024; Views: 389; Downloads: 26
Full text (16,94 MB)
This document has many files! More...