Deep Learning with network of Wearable sensors for preventing the Risk of Falls for Older People

Abstract

Activity recognition (AR) systems for older adults are common in residential health care including hospitals or nursing homes; therefore, numerous solutions and studies presented to improve the performance of the AR systems. Yet, delivering sufficiently robust AR systems from sensor data recorded is a challenging task. AR in a smart environment utilizes large amounts of sensor data to derive effective features from the data to track the activity daily living. This paper maximizes the performance of AR system from using the convolutional neural network (CNN). Here, it analyzes signals from the network sensors distributed in different places in two clinical rooms at the Elizabeth hospital, such as W2ISP and RFID sensors. The proposed approach recognized the daily activities that consider a key to falling cases for older adults at a hospital or a nursing health house. A deep activity CNNets is used to train the effective features of daily activities sensors data then used for recognizing the highest falling risk activities in testing data. This approach used existing data of fourteen healthy older volunteers (ten females and four males) and then compared to other proposed approaches that used the same dataset. The experimental results show that this approach is superior to others. It achieved (96.37±3.63%) in the first clinic room and (98.37±1.63%) in the second clinic room. As the result, this experiment concludes that deep learning methodology is effectively assessing fall risk based on wearable sensors.

Role of Deep Learning in Predicting Aging-Related Diseases: A Scoping Review

“…The studies [17,19,[86][87][88][89][90][91][92][93][94][95], highlighted DL-based prediction of other age-related other issues such as Type -2 diabetics, COVID-19 in older patients, coronary blockage in arteries, age-related eye diseases, brain age with old age, age-related disease gene associations, and heart stroke. Interesting findings and summary of these studies [17,19,[86][87][88][89][90][91][92][93][94][95] is provided in Tables A5 and A6 in Appendix A.…”

“…The use of genomic data in DL in studying age-related conditions shows promising direction, but domain knowledge is needed to guide the DL model extracting patterns [48]. Some interesting studies have shown the usage of sensor data for guiding and predicting age-related issues [87,88,95]. However, data gathered from sensors may have a certain degree of errors, noise, or redundant information due to battery or communication loss in sensor readings.…”

“…Out of 1804 articles on Google Scholar, PubMed and IEEE, based on our keyword-search terms and subsequently sorting by relevance, 34 studies met our inclusion criteria, and these were reviewed. Interestingly, these involved varied data types, such as imaging data [78,81,82,[89][90][91]98], EHR data [77], ECG data [71], fundus images [67,69,92] and sensor data [87,88,95]. From these studies, we observed that there is a surge in the application of DL methods for studying such diseases.…”

“…Nowadays, patients can monitor their health with smart sensor-based devices in real time, thus minimizing frequent visits to the doctor. DL over data collected from smart devices could aid patients in providing better health care [87].…”

Defining the Concepts of a Smart Nursing Home and Its Potential Technology Utilities That Integrate Medical Services and Are Acceptable to Stakeholders: a Scoping Review

“…Monitoring and noti cation of abnormal events: Monitoring devices have been proven to ensure the safety of the nursing home residents in fall prevention (32)(33)(34)(35)(36)(37)(38)(39)(40)(41)(42)(43)(44)(45), automatic monitoring of health conditions, and noti cation of emerging events such as heart attacks and fatal accidents (11,12,19,31,. The vital sign of older adults could be collected and recorded by the wearable devices such as clothes and shoes on nursing home residents (35, 95).…”