Design and Implementation of a Wearable Accelerometer-Based Motion/Tilt Sensing Internet of Things Module and Its Application to Bed Fall Prevention

Accelerometer-based motion sensing has been extensively applied to fall detection. However, such applications can only detect fall accidents; therefore, a system that can prevent fall accidents is desirable. Bed falls account for more than half of patient falls and are preceded by a clear warning indicator: the patient attempting to get out of bed. This study designed and implemented an Internet of Things module, namely, Bluetooth low-energy-enabled Accelerometer-based Sensing In a Chip-packaging (BASIC) module, with a tilt-sensing algorithm based on the patented low-complexity COordinate Rotation DIgital Computer (CORDIC)-based algorithm for tilt angle conversions. It is applied for detecting the postural changes (from lying down to sitting up) and to protect individuals at a high risk of bed falls by prompting caregivers to take preventive actions and assist individuals trying to get up. This module demonstrates how motion and tilt sensing can be applied to bed fall prevention. The module can be further miniaturized or integrated into a wearable device and commercialized in smart health-care applications for bed fall prevention in hospitals and homes.

Fall Detection via Inaudible Acoustic Sensing

The fall detection system is of critical importance in protecting elders through promptly discovering fall accidents to provide immediate medical assistance, potentially saving elders' lives. This paper aims to develop a novel and lightweight fall detection system by relying solely on a home audio device via inaudible acoustic sensing, to recognize fall occurrences for wide home deployment. In particular, we program the audio device to let its speaker emit 20kHz continuous wave, while utilizing a microphone to record reflected signals for capturing the Doppler shift caused by the fall. Considering interferences from different factors, we first develop a set of solutions for their removal to get clean spectrograms and then apply the power burst curve to locate the time points at which human motions happen. A set of effective features is then extracted from the spectrograms for representing the fall patterns, distinguishable from normal activities. We further apply the Singular Value Decomposition (SVD) and K-mean algorithms to reduce the data feature dimensions and to cluster the data, respectively, before input them to a Hidden Markov Model for training and classification. In the end, our system is implemented and deployed in various environments for evaluation. The experimental results demonstrate that our system can achieve superior performance for detecting fall accidents and is robust to environment changes, i.e., transferable to other environments after training in one environment.

A Correlation Analysis of Construction Site Fall Accidents Based on Text Mining

Construction site fall accidents are a high-frequency accident type in the construction industry and have received extensive attention from accident causal factor analysis and risk management research, but evaluating the relationship between accident causal factors and unstructured texts remains an area in urgent need of further study. In this paper, an analysis method based on text mining was chosen to analyze and process the collected data of 557 investigation reports of construction site fall accidents in China from 2013 to 2019. First, the accident reports were preprocessed to identify six types and 28 causal factors of fall accidents; subsequently, the 28 causal factors were classified into critical causal factors, subcritical causal factors and general causal factors according to their document frequency. Then, the Apriori algorithm was used to analyze the correlation of construction site fall accidents. Finally, strong association rules were obtained between the accident causal factors and between the causal factors and the types of construction site fall accidents. The results showed that 1) insufficient safety technology training and untimely elimination of hidden danger in safe production were the most frequent accident causal factors in fall accident reports. 2) There were different degrees of strong and weak correlations among the causal factors of construction site fall accidents, among which the higher the importance was, the stronger the correlation. 3) There were strong potential laws between the causal factors and the types of fall accidents, and the combination of some causal factors was most likely to lead to the occurrence of the corresponding accident types. This study scientifically and logically elucidated the inherent risk factors for fall accidents, which provides a theoretical basis for preventing fall accidents in construction projects.

Suggestions for Improving South Korea’s Fall Accidents Prevention Technology in the Construction Industry: Focused on Analyzing Laws and Programs of the United States

Since the enactment of the Occupational Safety and Health Act in 1981, the Korea Occupational Safety and Health Agency has endeavored to prevent fall accidents in the construction industry. However, many fatalities still occur in the South Korean construction industry. Meanwhile, the United States improved various systems and conducted studies to prevent fall accidents, significantly reducing such occurrences in the construction industry. The objective of this study is to present improvements to South Korea’s fall prevention technology by analyzing the laws and programs of the United States. To achieve this, this study has analyzed the United States’ fall prevention technology and derived improvements applicable in South Korea through an expert opinion survey. This study suggests to (1) set the height standard of a fall accident to 2 m, (2) adopt an active fall prevention system, (3) create a map of fallen fatalities, and (4) employ safety experts to support foreign workers. In the future, the results of this study are expected to be used as basic data for policies and programs related to fall accidents in the construction industry.

Understanding the fall-related safety issues in concrete formwork

The construction industry recorded high rates of fatalities and injuries due to falls at the workplace. Among other activities, concrete formwork tends to have more fatal falls. This study aims to understand the fall-related safety issues in the formwork lifecycle of construction projects. To achieve this, the process of formwork activities was mapped, and the safety risks associated with each activity were classified. Method development and risk identification focused on interviews with construction professionals involved in the construction of formwork and site observations of the formwork activities. The overall finding was that pouring, stripping, and erection activities have more issues related to falls. Future research is being carried out to assess the risks of falls from the construction experts’ views to prevent fall accidents in the future.

Ambient Intelligence to Improve Construction Site Safety: Case of High-Rise Building in Thailand

The relatively high rate of injuries in construction is not surprising, as site work by its very nature ranks highly on fundamental risk factors. Working at heights often magnifies these risk factors. The literature reveals that falls from heights accounts for a large percentage of injuries in construction worldwide. Thailand is no exception, where fall accidents constitute the majority of high-rise construction accidents despite preventive measures being implemented. This paper examines how the use of a simple Ambient Intelligence (AmI) system—a device comprising a microcontroller, microwave sensors, Light Emitting Diode (LED) and audio alarm—could help to affect safety behavioural change of on-site construction workers in order to decrease the potential for fall accidents. An experiment was conducted at a high-rise building construction site in Bangkok, Thailand to examine the effectiveness of the AmI in helping workers mitigate the risk of falling from heights. The analysis of the data collected over two work weeks from the pre- and post-AmI application using X-bar charts and one-way analysis of variance (ANOVA) revealed a significant reduction of about 78% in the number of workers passing through the fall hazard zones. The finding established the potential of a simple AmI for reducing the risk of fall accidents.