Use of Connected Technologies to Assess Barriers and Stressors for Age and Disability-Friendly Communities

Welding Spark Detection on Construction Sites Using Contour Detection with Automatic Parameter Tuning and Deep-Learning-Based Filters

One of the primary causes of fires at construction sites is welding sparks. Fire detection systems utilizing computer vision technology offer a unique opportunity to monitor fires in construction sites. However, little effort has been made to date in regard to real-time tracking of small sparks that can lead to major fires at construction sites. In this study, a novel method is proposed to detect welding sparks in real-time contour detection with deep learning parameter tuning. An automatic parameter tuning algorithm employing a convolutional neural network was developed to identify the optimum hue saturation value. Additional filtering methods regarding the non-welding zone and a contour area-based filter were also newly developed to enhance the accuracy of welding spark prediction. The method was evaluated using 230 welding spark images and 104 videos. The results obtained from the welding images indicate that the suggested model for detecting welding sparks achieves a precision of 74.45% and a recall of 63.50% when noise images, such as flashing and reflection light, were removed from the dataset. Furthermore, our findings demonstrate that the proposed model is effective in capturing the number of welding sparks in the video dataset, with a 95.2% accuracy in detecting the moment when the number of welding sparks reaches its peak. These results highlight the potential of automated welding spark detection to enhance fire surveillance at construction sites.

Comparing Use Patterns and Acceptability of Mobile Digital Devices Between Care Recipients and Caregivers

BACKGROUND

The use of smartphones and other digital devices (such as tablets and smartwatches) is important for the aging population to enhance and optimize communications with caregivers, families, friends, and providers. It also provides a platform for app-based activities to promote mental, physical, spiritual, and social well-being and virtual social connectedness. We, therefore, examined types of digital devices and categories of smartphone functions used by caregivers and care recipients in comparison to those without any caregiving roles.

METHOD

The project team has developed a smartphone app based on Buddhist meditative practice principles for the enhancement of the physical, mental, cognitive, and emotional well-being of older adults and their caregivers and tested it in Galveston, Houston, and Dallas, TX. The study comprised a convenient sample of older adults, including members or volunteers of the International Buddhist Progress Society-Dallas (IBPS Dallas) and the University of Texas Medical Branch Osher Lifelong Learning Institute (UTMB OLLI). The survey focused on people who were 55 years and older (n = 219), with 177 valid responses (~80.8%) meeting the study's inclusion criteria. The survey collected data on (1) caregiving role, (2) demographic characteristics and caregiving concerns, and (3) types of devices, functions, and utilization. Descriptive analysis and logistic regression were used to describe and compare patterns of smartphone function/use by the different groups, i.e., caregivers, care recipients, and neither.

RESULTS

All of our survey respondents were 55 years and older, and among them, 17.5% were caregivers, 9.1% were care recipients, and 73.4% did not have any role. The majority of the caregivers were females (80.6%), and the average age of their care recipients was 66 years. The care recipients in our sample reported that the average age of their caregiver is only 55 years. Around three-fourths of caregivers reported that they have an app related to health or they are willing to use a health-related app, 32% of them use smart home appliances, whereas only 16% of people who are neither caregivers nor care recipients use such apps. Approximately 42% of caregivers reported taking care of their parents or parents-in-law, and their major concerns are about maintaining their income, scheduling tasks, and updating their knowledge as needed to better care for their loved ones. People use texting or messaging the most. However, the second and third highest utilization are different. The "neither" group significantly spends more time checking email and watching TV; the care recipients spend more time reading and watching TV (sedentary activities); the caregiver group spends more time on phone calls and listening to music.

CONCLUSIONS

Findings of different patterns of digital device use exist between caregivers, care recipients, and the "neither" group, with 75% of caregivers using a digital device app related to health or reporting willingness to use a health-related app developed from our study. Our findings of their caregiving experiences might also inform the design of different intervention programs aimed at promoting mental, physical, and social well-being, improving quality of life while reducing disease/disability burden for older adults, and preventing burnout among caregivers.

Location-based collective distress using large-scale biosignals in real life for walkable built environments

Biosignals from wearable sensors have shown great potential for capturing environmental distress that pedestrians experience from negative stimuli (e.g., abandoned houses, poorly maintained sidewalks, graffiti, and so forth). This physiological monitoring approach in an ambulatory setting can mitigate the subjectivity and reliability concerns of traditional self-reported surveys and field audits. However, to date, most prior work has been conducted in a controlled setting and there has been little investigation into utilizing biosignals captured in real-life settings. This research examines the usability of biosignals (electrodermal activity, gait patterns, and heart rate) acquired from real-life settings to capture the environmental distress experienced by pedestrians. We collected and analyzed geocoded biosignals and self-reported stimuli information in real-life settings. Data was analyzed using spatial methods with statistical and machine learning models. Results show that the machine learning algorithm predicted location-based collective distress of pedestrians with 80% accuracy, showing statistical associations between biosignals and the self-reported stimuli. This method is expected to advance our ability to sense and react to not only built environmental issues but also urban dynamics and emergent events, which together will open valuable new opportunities to integrate human biological and physiological data streams into future built environments and/or walkability assessment applications.

Two-Step k-means Clustering Based Information Entropy for Detecting Environmental Barriers Using Wearable Sensor

Walking is the most basic means of transportation. Therefore, continuous management of the walking environment is very important. In particular, the identification of environmental barriers that can impede walkability is the first step in improving the pedestrian experience. Current practices for identifying environmental barriers (e.g., expert investigation and survey) are time-consuming and require additional human resources. Hence, we have developed a method to identify environmental barriers based on information entropy considering that every individual behaves differently in the presence of external stimuli. The behavioral data of the gait process were recorded for 64 participants using a wearable sensor. Additionally, the data were classified into seven gait types using two-step k-means clustering. It was observed that the classified gaits create a probability distribution for each location to calculate information entropy. The values of calculated information entropy showed a high correlation in the presence or absence of environmental barriers. The results obtained facilitated the continuous monitoring of environmental barriers generated in a walking environment.