Enhancing biofeedback-driven self-guided virtual reality exposure therapy through arousal detection from multimodal data using machine learning.

Virtual reality exposure therapy (VRET) is a novel intervention technique that allows individuals to experience anxiety-evoking stimuli in a safe environment, recognise specific triggers and gradually increase their exposure to perceived threats. Public-speaking anxiety (PSA) is a prevalent form of social anxiety, characterised by stressful arousal and anxiety generated when presenting to an audience. In self-guided VRET, participants can gradually increase their tolerance to exposure and reduce anxiety-induced arousal and PSA over time. However, creating such a VR environment and determining physiological indices of anxiety-induced arousal or distress is an open challenge. Environment modelling, character creation and animation, psychological state determination and the use of machine learning (ML) models for anxiety or stress detection are equally important, and multi-disciplinary expertise is required. In this work, we have explored a series of ML models with publicly available data sets (using electroencephalogram and heart rate variability) to predict arousal states. If we can detect anxiety-induced arousal, we can trigger calming activities to allow individuals to cope with and overcome distress. Here, we discuss the means of effective selection of ML models and parameters in arousal detection. We propose a pipeline to overcome the model selection problem with different parameter settings in the context of virtual reality exposure therapy. This pipeline can be extended to other domains of interest where arousal detection is crucial. Finally, we have implemented a biofeedback framework for VRET where we successfully provided feedback as a form of heart rate and brain laterality index from our acquired multimodal data for psychological intervention to overcome anxiety.

Classification of Mental Stress from Wearable Physiological Sensors Using Image-Encoding-Based Deep Neural Network.

The human body is designed to experience stress and react to it, and experiencing challenges causes our body to produce physical and mental responses and also helps our body to adjust to new situations. However, stress becomes a problem when it continues to remain without a period of relaxation or relief. When a person has long-term stress, continued activation of the stress response causes wear and tear on the body. Chronic stress results in cancer, cardiovascular disease, depression, and diabetes, and thus is deeply detrimental to our health. Previous researchers have performed a lot of work regarding mental stress, using mainly machine-learning-based approaches. However, most of the methods have used raw, unprocessed data, which cause more errors and thereby affect the overall model performance. Moreover, corrupt data values are very common, especially for wearable sensor datasets, which may also lead to poor performance in this regard. This paper introduces a deep-learning-based method for mental stress detection by encoding time series raw data into Gramian Angular Field images, which results in promising accuracy while detecting the stress levels of an individual. The experiment has been conducted on two standard benchmark datasets, namely WESAD (wearable stress and affect detection) and SWELL. During the studies, testing accuracies of 94.8% and 99.39% are achieved for the WESAD and SWELL datasets, respectively. For the WESAD dataset, chest data are taken for the experiment, including the data of sensor modalities such as three-axis acceleration (ACC), electrocardiogram (ECG), body temperature (TEMP), respiration (RESP), etc.

Detection of Breast Cancer from Five-View Thermal Images Using Convolutional Neural Networks.

Breast cancer is one of the most common forms of cancer. Its aggressive nature coupled with high mortality rates makes this cancer life-threatening; hence early detection gives the patient a greater chance of survival. Currently, the preferred diagnosis method is mammography. However, mammography is expensive and exposes the patient to radiation. A cost-effective and less invasive method known as thermography is gaining popularity. Bearing this in mind, the work aims to initially create machine learning models based on convolutional neural networks using multiple thermal views of the breast to detect breast cancer using the Visual DMR dataset. The performances of these models are then verified with the clinical data. Findings indicate that the addition of clinical data decisions to the model helped increase its performance. After building and testing two models with different architectures, the model used the same architecture for all three views performed best. It performed with an accuracy of 85.4%, which increased to 93.8% after the clinical data decision was added. After the addition of clinical data decisions, the model was able to classify more patients correctly with a specificity of 96.7% and sensitivity of 88.9% when considering sick patients as the positive class. Currently, thermography is among the lesser-known diagnosis methods with only one public dataset. We hope our work will divert more attention to this area.

Differential Modulation of Excitatory and Inhibitory Neurons during Periodic Stimulation.

Non-invasive transcranial neuronal stimulation, in addition to deep brain stimulation, is seen as a promising therapeutic and diagnostic approach for an increasing number of neurological diseases such as epilepsy, cluster headaches, depression, specific type of blindness, and other central nervous system disfunctions. Improving its effectiveness and widening its range of use may strongly rely on development of proper stimulation protocols that are tailored to specific brain circuits and that are based on a deep knowledge of different neuron types response to stimulation. To this aim, we have performed a simulation study on the behavior of excitatory and inhibitory neurons subject to sinusoidal stimulation. Due to the intrinsic difference in membrane conductance properties of excitatory and inhibitory neurons, we show that their firing is differentially modulated by the wave parameters. We analyzed the behavior of the two neuronal types for a broad range of stimulus frequency and amplitude and demonstrated that, within a small-world network prototype, parameters tuning allow for a selective enhancement or suppression of the excitation/inhibition ratio.