Background: A majority of adults in the United States are exposed to a potentially traumatic event but only a handful go on to develop impairing mental health conditions such as posttraumatic stress disorder (PTSD). Objective: Identifying those at elevated risk shortly after trauma exposure is a clinical challenge. The aim of this study was to develop computational methods to more effectively identify at-risk patients and, thereby, support better early interventions. Methods: We proposed machine learning (ML) induction of models to automatically predict elevated PTSD symptoms in patients 1 month after a trauma, using self-reported symptoms from data collected via smartphones. Results: We show that an ensemble model accurately predicts elevated PTSD symptoms, with an area under the curve (AUC) of .85, using a bag of support vector machines, naive Bayes, logistic regression, and random forest algorithms. Furthermore, we show that only 7 self-reported items (features) are needed to obtain this AUC. Most importantly, we show that accurate predictions can be made 10 to 20 days posttrauma. Conclusions: These results suggest that simple smartphone-based patient surveys, coupled with automated analysis using ML-trained models, can identify those at risk for developing elevated PTSD symptoms and thus target them for early intervention.
Rapid assessment of breathing patterns is important for several emergency medical situations. In this research, we developed a non-invasive breathing analysis system that automatically detects different types of breathing patterns of clinical significance. Accelerometer and gyroscopic data were collected from light-weight wireless sensors placed on the chest and abdomen of 100 normal volunteers who simulated various breathing events (central sleep apnea, coughing, obstructive sleep apnea, sighing, and yawning). We then constructed synthetic datasets by injecting annotated examples of the various patterns into segments of normal breathing. A one-dimensional convolutional neural network was implemented to detect the location of each event in each synthetic dataset and to classify it as belonging to one of the above event types. We achieved a mean F1 score of 92% for normal breathing, 87% for central sleep apnea, 72% for coughing, 51% for obstructive sleep apnea, 57% for sighing, and 63% for yawning. These results demonstrate that using deep learning to analyze chest and abdomen movement data from wearable sensors provides an unobtrusive means of monitoring the breathing pattern. This could have application in a number of critical medical situations such as detecting apneas during sleep at home and monitoring breathing events in mechanically ventilated patients in the intensive care unit.
14 August 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Cross-View Geo-Localization (CVGL) estimates the location of a ground image by matching it to a geo-tagged aerial image in a database. Recent works achieve outstanding progress on CVGL benchmarks. However, existing methods still suffer from poor performance in cross-area evaluation, in which the training and testing data are captured from completely distinct areas. We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models’ overfitting to low-level details. Our preliminary work (Zhang et al. 2022) introduced a Geometric Layout Extractor (GLE) to capture the geometric layout from input features. However, the previous GLE does not fully exploit information in the input feature. In this work, we propose GeoDTR+ with an enhanced GLE module that better models the correlations among visual features. To fully explore the LS techniques from our preliminary work, we further propose Contrastive Hard Samples Generation (CHSG) to facilitate model training. Extensive experiments show that GeoDTR+ achieves state-of-the-art (SOTA) results in cross-area evaluation on CVUSA (Workman et al. 2015), CVACT (Liu and Li, 2019), and VIGOR (Zhu et al. 2021) by a large margin (16.44%, 22.71%, and 13.66% without polar transformation) while keeping the same-area performance comparable to existing SOTA. Moreover, we provide detailed analyses of GeoDTR+.
The rapid development of technology in the past decades created a society heavily dependent on electricity, where even short disturbances in the power supply can result in grave socio-economic consequences. Therefore, assuring a safe and reliable operation of the power system has become of utmost importance. False data injection attacks (FDIAs) represent a class of cyber-attacks targeting the power system state estimation. FDIAs alter the perspective of the power system’s state which can lead to inappropriate control actions. Thus, a reliable method for the detection of FDIAs represents a key prerequisite to the safe operation of the power system in the context of cybersecurity. Noticing the scarce literature analyzing the detection of FDIAs in power systems with a high share of renewable energy sources, this paper demonstrates that the performance of the existing methods deteriorates when faced with the volatile nature of renewable energy sources. This paper presents a deep learning approach to the detection of FDIAs concerning the power systems with high penetration of renewable energy sources. The performance of the proposed method is validated through different scenarios based on the modified versions of the IEEE 14-bus system and the IEEE 118-bus system. The proposed method is able to detect most of the attacks under different test scenarios, outperforming the benchmark techniques with an average detection rate of 99% for the IEEE 14-bus system and 97% for the IEEE 118-bus system.
Object geo-localization from images is crucial to many applications such as land surveying, self-driving, and asset management. Current visual object geo-localization algorithms suffer from hardware limitations and impractical assumptions limiting their usability in real-world applications. Most of the current methods assume object sparsity, the presence of objects in at least two frames, and most importantly they only support a single class of objects. In this paper, we present a novel two-stage technique that detects and geo-localizes dense, multi-class objects such as traffic signs from street videos. Our algorithm is able to handle low frame rate inputs in which objects might be missing in one or more frames. We propose a detector that is not only able to detect objects in images, but also predicts a positional offset for each object relative to the camera GPS location. We also propose a novel tracker algorithm that is able to track a large number of multi-class objects. Many current geo-localization datasets require specialized hardware, suffer from idealized assumptions not representative of reality, and are often not publicly available. In this paper, we propose a public dataset called ARTSv2, which is an extension of ARTS dataset that covers a diverse set of roads in widely varying environments to ensure it is representative of real-world scenarios. Our dataset will both support future research and provide a crucial benchmark for the field.