ICE-MoCha: Intelligent Crowd Engineering using Mobility Characterization and Analytics.

Human injuries and casualties at entertaining, religious, or political crowd events often occur due to the lack of proper crowd safety management. For instance, for a large scale moving crowd, a minor accident can create a panic for the people to start stampede. Although many smart video surveillance tools, inspired by the recent advanced artificial intelligence (AI) technology and machine learning (ML) algorithms, enable object detection and identification, it is still challenging to predict the crowd mobility in real-time for preventing potential disasters. In this paper, we propose an intelligent crowd engineering platform using mobility characterization and analytics named ICE-MoCha. ICE-MoCha is to assist safety management for mobile crowd events by predicting and thus helping to prevent potential disasters through real-time radio frequency (RF) data characterization and analysis. The existing video surveillance based approaches lack scalability thus have limitations in its capability for wide open areas of crowd events. Via effectively integrating RF signal analysis, our approach can enhance safety management for mobile crowd. We particularly tackle the problems of identification, speed, and direction detection for the mobile group, among various crowd mobility characteristics. We then apply those group semantics to track the crowd status and predict any potential accidents and disasters. Taking the advantages of power-efficiency, cost-effectiveness, and ubiquitous availability, we specifically use and analyze a Bluetooth low energy (BLE) signal. We have conducted experiments of ICE-MoCha in a real crowd event as well as controlled indoor and outdoor lab environments. The results show the feasibility of ICE-MoCha detecting the mobile crowd characteristics in real-time, indicating it can effectively help the crowd management tasks to avoid potential crowd movement related incidents.

Headphone Evaluation for App-Based Automated Mobile Hearing Screening

Abstract Introduction With the need for hearing screenings increasing across multiple populations, a need for automated options has been identified. This research seeks to evaluate the hardware requirements for automated hearing screenings using a mobile application. Objective Evaluation of headphone hardware for use with an app-based mobile screening application. Methods For the purposes of this study, hEAR, a Bekesy-based mobile application designed by the research team, was compared with pure tone audiometric tests administered by an audiologist. Both hEAR and the audiologist's test used 7 frequencies (125 Hz, 250 Hz, 500 Hz, 1,000 Hz, 2000 Hz, 4,000 Hz and 8,000 Hz) adopting four different sets of commercially available headphones. The frequencies were regarded as the independent variable, whereas the sound pressure level (in decibels) was the dependent variable. Thirty participants from a university in Texas were recruited and randomly assigned to one of two groups, whose only difference was the order in which the tests were performed. Data were analyzed using a generalized estimating equation model at α = 0.05. Results Findings showed that, when used to collect data with the mobile app, both the Pioneer HDJ-2000 (Pioneer, Bunkyo, Tokyo, Japan) (p> 0.05) and the Sennheiser HD280 Pro (Sennheiser, Wedemark, Hanover, Germany) (p> 0.05) headphones presented results that were not statistically different from the audiologist's data across all test frequencies. Analyses indicated that both headphones had decreased detection probability at 4kHz and 8kHz, but the differences were not statistically significant. Conclusion Data indicate that a mobile application, when paired with appropriate headphones, is capable of reproducing audiologist-quality data.

Headphone Evaluation for App-Based Automated Mobile Hearing Screening.

Introduction With the need for hearing screenings increasing across multiple populations, a need for automated options has been identified. This research seeks to evaluate the hardware requirements for automated hearing screenings using a mobile application. Objective Evaluation of headphone hardware for use with an app-based mobile screening application. Methods For the purposes of this study, hEAR, a Bekesy-based mobile application designed by the research team, was compared with pure tone audiometric tests administered by an audiologist. Both hEAR and the audiologist's test used 7 frequencies (125 Hz, 250 Hz, 500 Hz, 1,000 Hz, 2000 Hz, 4,000 Hz and 8,000 Hz) adopting four different sets of commercially available headphones. The frequencies were regarded as the independent variable, whereas the sound pressure level (in decibels) was the dependent variable. Thirty participants from a university in Texas were recruited and randomly assigned to one of two groups, whose only difference was the order in which the tests were performed. Data were analyzed using a generalized estimating equation model at α = 0.05. Results Findings showed that, when used to collect data with the mobile app, both the Pioneer HDJ-2000 (Pioneer, Bunkyo, Tokyo, Japan) ( p > 0.05) and the Sennheiser HD280 Pro (Sennheiser, Wedemark, Hanover, Germany) ( p > 0.05) headphones presented results that were not statistically different from the audiologist's data across all test frequencies. Analyses indicated that both headphones had decreased detection probability at 4kHz and 8kHz, but the differences were not statistically significant. Conclusion Data indicate that a mobile application, when paired with appropriate headphones, is capable of reproducing audiologist-quality data.

Development of a Mobile App for Family Planning Providers.

PURPOSE: To provide an overview of lessons learned during the development process of an app for iOS and Android based on national recommendations for providing quality family planning services. STUDY AND DESIGN: After a review of existing apps was conducted to determine whether an app of clinical recommendations for family planning existed, a team of clinicians, training specialists, and app developers created a resource app by first drafting a comprehensive content map. A prototype of the app was then pilot tested using smart tablets by a volunteer convenience sample of women's healthcare professionals. Outcomes measured included usability, acceptability, download analytics, and satisfaction by clinicians as reported through an investigator-developed tool. RESULTS: Sixty-nine professionals tested a prototype of the app, and completed a user satisfaction tool. Overall, user feedback was positive, and a zoom function was added to the final version as a result of the pilot test. Within 3 months of being publicly available, the app was downloaded 677 times, with 97% of downloads occurring on smart phones, 76% downloads occurring on iOS devices, and 24% on Android devices. This trend persisted throughout the following 3 months. CLINICAL IMPLICATIONS: Clinicians with an interest in developing an app should consider a team approach to development, pilot test the app prior to wider distribution, and develop a web-based version of the app to be used by clinicians who are unable to access smart devices in their practice setting.