Feasibility of an Integrated Telemonitoring System for Home-Recorded EEG with Automated AI-Based EEG Analysis.

BACKGROUND: Self-recorded EEG by patients at home might present a viable alternative to inpatient epilepsy evaluations. OBJECTIVES AND METHODS: We developed a novel telemonitoring system comprising seamlessly integrated hard- and software with automated AI-based EEG analysis. RESULTS: The first complete study participation results demonstrate feasibility and clinical utility. CONCLUSION: Our telemonitoring solution potentially improves treatment of patients with epilepsy and moreover might help to better distribute resources in the healthcare system.

Efficient Respiratory Rate Extraction on a Smartwatch.

Using the Photoplethysmogram (PPG) sensor of a smartwatch to extract Respiratory Rate (RR) is very attractive. However, existing algorithms suffer from lack of accuracy and susceptibility to noise and movement artifacts. To tackle this issue, we propose performing Frequency Domain Peak (FDP) analysis using the Frequency Modulation (FM) feature. Moreover, our analysis of existing methods show that in contrast to the common practice Smart Fusion (SFU), despite incurring extra computational costs, is very little helpful. It is hence more preferable and efficient to avoid SFU. The proposed method shows an improvement of at least 130% in the Figure of Merit (FoM) and has more than 60% smaller mean error. Therefore, it can be reliably used in a wide range of applications.

A simple algorithm for emotion recognition, using physiological signals of a smart watch.

Recently, it has become easier and more common to measure physiological signals through wearable devices such as smart watches. Extracting emotional states of individuals with problems expressing it, such as autistic individuals, can help their parents, friends, and therapists to obtain a better understanding of what they feel throughout their day. Although emotion recognition methods based on physiological signals have been studied for many years, there is a smaller body of literature about systems working with data obtained from wearable devices. In this paper, we present an emotion recognition system with a small footprint suitable for limited resources of wearable devices. Other than identifying the emotions (with a success rate of 65%), The proposed system also tags each recognition with a confidence value (on average 57%).