Tracheal activity recognition based on acoustic signals.

Tracheal activity recognition can play an important role in continuous health monitoring for wearable systems and facilitate the advancement of personalized healthcare. Neck-worn systems provide access to a unique set of health-related data that other wearable devices simply cannot obtain. Activities including breathing, chewing, clearing the throat, coughing, swallowing, speech and even heartbeat can be recorded from around the neck. In this paper, we explore tracheal activity recognition using a combination of promising acoustic features from related work and apply simplistic classifiers including K-NN and Naive Bayes. For wearable systems in which low power consumption is of primary concern, we show that with a sub-optimal sampling rate of 16 kHz, we have achieved average classification results in the range of 86.6% to 87.4% using 1-NN, 3-NN, 5-NN and Naive Bayes. All classifiers obtained the highest recognition rate in the range of 97.2% to 99.4% for speech classification. This is promising to mitigate privacy concerns associated with wearable systems interfering with the user's conversations.

Potential barriers in adoption of a medication compliance neckwear by elderly population.

This paper presents results of a study to understand potential barriers of geriatric population with chronic illnesses towards adoption of a wireless wearable medication compliance system in the form of a neckwear. The neck being a critical part of the body can serve as a good source to collect a range of health related information on an individual. The primary research question we investigate here is this: for individuals with chronic illnesses especially amongst the elderly population how willing are they to adopt a neckwear system if it can monitor and mitigate health complications? Elderly patients deal with constant prescription changes over time and this further degrades medication compliance and thereby complicates an already wavering health status. A semi-structured interview was conducted to better understand medication adherence, regimen and issues encountered using reminder devices with the goal of informing the design of a new compliance monitoring system. Results show that preserving health is one of the primary concerns of people living with chronic illnesses therefore there is a promising potential for seamless adoption of a neckwear medication compliance system with additional capabilities to monitor general health status.