HONEY: A Multimodality Fall Detection and Telecare System

Abstract

ABSTRACT-The increasing cost of finance and healthcare resources is driving healthcare providers to provide home-based telecare instead of institutionalized healthcare. Falling is one of the most common and dangerous accidents for elderly group and a significant factor affecting the living quality of the elderly. Many efforts have been put towards providing a robust method to detect falls accurately and timely. To facilitate a reliable, safe and real-time home-based healthcare environment, we propose the HONEY system to detect falls for elderly people in the home telecare environment. The basic idea of HONEY is a three-step detection scheme which consists of multimodality signal sources, including an accelerometer sensor, audio, images and video clips via speech recognition and on-demand video techniques. The magnitude acceleration, corresponding to a user's movements, triggers fall detection combining speech recognition and on-demand video. If a fall occurs, an alarm email is delivered to a medical staff or caregivers at once, containing the fall information so that caregivers could make a primary diagnosis based on it. This paper also describes the implementation of the prototype of HONEY. A comprehensive evaluation with 10 volunteers shows that HONEY has high accuracy of 94% for fall detection, 18% higher than Advanced Magnitude Algorithm (AMA), which is a wearable sensor-based method, while the false positive rate and false negative rate are 3% and 10%, 19% and 16% lower than AMA, respectively. The average response time for a detected fall is 46.2 seconds, which is also short enough for first aid.Index Terms-Fall detection, Health information management, Home telecare, Medical information systems I. INTRODUTIONThe impending influx of elderly citizens aged over 65 will soon be a much larger ratio to all population around the world. For example, in 15.07% of 23 million population of Shanghai is more than 60 years old [1]. Falling is a common and dangerous accident for elderly group and an important factor affecting the living quality of the elderly. It is estimated that more than one in three elder people aged over 65 living at home fall at least once each year. The risk of falling will also rise with the increasing age. Falling also leads to decreased mobility, fear of fall, and even deaths [2,3,4]. Furthermore, a research among Medicare (the largest healthcare insurer in USA) beneficiaries shows that the total medical care costs each year for elderly adults who fall once a year, are 29 % higher than the ones for other elderly adults who never fall in one year. Similarly, the costs for elderly adults who fall more than two times a year are 79 % higher than ones for those who report no fall [5]. However, the limited funds for public healthcare service and an aging population are driving factors for reducing the institutionalized healthcare based on entity service and moving to home healthcare based on wireless sensor networks.Accelerometers with low-cost and low-power features make the wearable and reliable fa...

Low-power fall detection in home-based environments

“…The family healthcare network consisting of Fallsensor and Homeserver, responds to collection of alarm information and transmits those data to CloudPIS. CloudPIS is an information-sharing platform for patients and caregivers [13]. Then, a remote monitoring center or caregivers can obtain related data from CloudPIS, so that one can be helped in time once an emergency occurs.…”

Consumption Analysis of Smartphone based Fall Detection Systems with Multiple External Wireless Sensors

“…If an extra fall detection app is running permanently on the phone, this typical lifespan of 24 h could be lessened. In fact, according to certain questionnaires fulfilled by the volunteers of a real life trial of an FDS [24], FDSs should be operative for at least six months with no battery recharge in order to be considered satisfactory by the users (an autonomy which is obviously far from the actual features of current devices).…”

Wearable Internet of Things: Concept, Architectural Components and Promises for Person-Centered Healthcare

“…Research has shown that weight scales transmit data to a mobile smartphone that forwards the information to a cloud based server, so that clinicians can assess weight management in youth [8]. Smartphones sync with the cloud servers to monitor fall detection in elderly individuals [9]. These few examples show that how wearable or devices used by the person interact with smartphone or phones to send information to remote servers.…”