BioDiffusion: A Versatile Diffusion Model for Biomedical Signal Synthesis.

Machine learning tasks involving biomedical signals frequently grapple with issues such as limited data availability, imbalanced datasets, labeling complexities, and the interference of measurement noise. These challenges often hinder the optimal training of machine learning algorithms. Addressing these concerns, we introduce BioDiffusion, a diffusion-based probabilistic model optimized for the synthesis of multivariate biomedical signals. BioDiffusion demonstrates excellence in producing high-fidelity, non-stationary, multivariate signals for a range of tasks including unconditional, label-conditional, and signal-conditional generation. Leveraging these synthesized signals offers a notable solution to the aforementioned challenges. Our research encompasses both qualitative and quantitative assessments of the synthesized data quality, underscoring its capacity to bolster accuracy in machine learning tasks tied to biomedical signals. Furthermore, when juxtaposed with current leading time-series generative models, empirical evidence suggests that BioDiffusion outperforms them in biomedical signal generation quality.

Personalized Watch-Based Fall Detection Using a Collaborative Edge-Cloud Framework.

The majority of current smart health applications are deployed on a smartphone paired with a smartwatch. The phone is used as the computation platform or the gateway for connecting to the cloud while the watch is used mainly as the data sensing device. In the case of fall detection applications for older adults, this kind of setup is not very practical since it requires users to always keep their phones in proximity while doing the daily chores. When a person falls, in a moment of panic, it might be difficult to locate the phone in order to interact with the Fall Detection App for the purpose of indicating whether they are fine or need help. This paper demonstrates the feasibility of running a real-time personalized deep-learning-based fall detection system on a smartwatch device using a collaborative edge-cloud framework. In particular, we present the software architecture we used for the collaborative framework, demonstrate how we automate the fall detection pipeline, design an appropriate UI on the small screen of the watch, and implement strategies for the continuous data collection and automation of the personalization process with the limited computational and storage resources of a smartwatch. We also present the usability of such a system with nine real-world older adult participants.

Virtual Reality Exposure Simulation for Student Veteran Social Anxiety and PTSD: A Case Study.

Exposure based exercises are a common element of many gold standard treatments for anxiety disorders and post-traumatic stress disorder and virtual reality simulations have been evaluated as a platform for providing clients with opportunities for repeated exposure during treatment. Although research on virtual reality exposure therapy (VRET) indicates effectiveness and high levels of user satisfaction, VRETs require a participant to complete exposure exercises in-offices with specialized equipment. The current exploratory case method study evaluates the experience and outcomes of one student veteran with social anxiety disorder and PTSD completing twelve sessions of VRET exposure using a mobile phone simulation of a virtual grocery store. The participant reported decreases in psychological symptoms, improvements in neurological connectivity, and better sleep quality upon completing the trial. Results suggest that VRET using a mobile application is feasible and warrants further research to evaluate effectiveness more fully. Implications include the use of a mobile based virtual reality simulation for intervening in social anxiety for student veterans.

In Situ Wireless Channel Visualization Using Augmented Reality and Ray Tracing.

This article presents a novel methodology for predicting wireless signal propagation using ray-tracing algorithms, and visualizing signal variations in situ by leveraging Augmented Reality (AR) tools. The proposed system performs a special type of spatial mapping, capable of converting a scanned indoor environment to a vector facet model. A ray-tracing algorithm uses the facet model for wireless signal predictions. Finally, an AR application overlays the signal strength predictions on the physical space in the form of holograms. Although some indoor reconstruction models have already been developed, this paper proposes an image to a facet algorithm for indoor reconstruction and compares its performance with existing AR algorithms, such as spatial understanding that are modified to create the required facet models. In addition, the paper orchestrates AR and ray-tracing techniques to provide an in situ network visualization interface. It is shown that the accuracy of the derived facet models is acceptable, and the overall signal predictions are not significantly affected by any potential inaccuracies of the indoor reconstruction. With the expected increase of densely deployed indoor 5G networks, it is believed that these types of AR applications for network visualization will play a key role in the successful planning of 5G networks.

SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning.

This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model's ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject's wellbeing.

DNA Copy Number Selection Using Robust Structured Sparsity-Inducing Norms.

Array comparative genomic hybridization (aCGH) is a newly introduced method for the detection of copy number abnormalities associated with human diseases with special focus on cancer. Specific patterns in DNA copy number variations (CNVs) can be associated with certain disease types and can facilitate prognosis and progress monitoring of the disease. Machine learning techniques have been used to model the problem of tissue typing as a classification problem. Feature selection is an important part of the classification process, because many biological features are not related to the diseases and confuse the classification tasks. Multiple feature selection methods have been proposed in the different domains where classification has been applied. In this work, we will present a new feature selection method based on structured sparsity-inducing norms to identify the informative aCGH biomarkers which can help us classify different disease subtypes. To validate the performance of the proposed method, we experimentally compare it with existing feature selection methods on four publicly available aCGH data sets. In all empirical results, the proposed sparse learning based feature selection method consistently outperforms other related approaches. More important, we carefully investigate the aCGH biomarkers selected by our method, and the biological evidences in literature strongly support our results.

A web ontology for brain trauma patient computer-assisted rehabilitation.

In this paper we describe CABROnto, which is a web ontology for the semantic representation of the computer assisted brain trauma rehabilitation. This is a novel and emerging domain, since it employs the use of robotic devices, adaptation software and machine learning to facilitate interactive and adaptive rehabilitation care. We used Protégé 4.2 and Protégé-Owl schema editor. The primary goal of this ontology is to enable the reuse of the domain knowledge. CABROnto has nine main classes, more than 50 subclasses, existential and cardinality restrictions. The ontology can be found online at Bioportal.

Heterogeneous data fusion for brain tumor classification.

Current research in biomedical informatics involves analysis of multiple heterogeneous data sets. This includes patient demographics, clinical and pathology data, treatment history, patient outcomes as well as gene expression, DNA sequences and other information sources such as gene ontology. Analysis of these data sets could lead to better disease diagnosis, prognosis, treatment and drug discovery. In this report, we present a novel machine learning framework for brain tumor classification based on heterogeneous data fusion of metabolic and molecular datasets, including state-of-the-art high-resolution magic angle spinning (HRMAS) proton (1H) magnetic resonance spectroscopy and gene transcriptome profiling, obtained from intact brain tumor biopsies. Our experimental results show that our novel framework outperforms any analysis using individual dataset.