Search for: All records

While machine learning models perform well on offline data, assessing their performance in real-world, resource-constrained environments-considering accuracy, prediction time, power consumption, and memory usage-is crucial for practical applications. This research implements a mobile-based Human Activity Recognition solution to classify three postures-sitting, standing, and walking-using smartphone sensors, specifically accelerometer, gyroscope, and magnetometer. Time-domain features extracted from these sensors were used, with Random Forest employed for feature selection. One traditional machine learning model, Logistic Regression, and one deep learning model, Convolutional Neural Network, were trained and deployed via an Android application for real-time evaluation. While the Convolutional Neural Network achieved higher accuracy and better memory efficiency, Logistic Regression demonstrated faster prediction times during real-time use. Both models showed reduced accuracy for standing and walking postures in real-world conditions, emphasizing the challenges of deploying machine learning models in dynamic environments. This study highlights the importance of evaluating machine learning models in real-world settings to ensure reliability and efficiency, particularly in resource-constrained environments. 

In an indoor space, determining a person's mobility patterns has research significance and applicability in real-world scenarios. When mobility patterns are determined, layout optimization can be implemented in indoor spaces to improve efficiency. This research aimed to determine a person's path using Received Signal Strength Indicator (RSSI) data collected from Bluetooth-enabled mobile devices. Mobile app-based mobility detection using Bluetooth RSSI has the advantage of low cost and easy implementation. The research methodology involves developing a Bluetooth RSSI mobility application system to determine the path of a moving mobile device using a vectorized algorithm. The paper presents challenges in creating such a software system, its architecture, the data collection and analysis process, and the results of mobility detection. This research shows that Bluetooth-enabled mobile devices and Bluetooth RSSI data can be used to determine the path in an indoor space with workable accuracy. 

Getting students engaged with out-of-class activities has been a long-standing challenge. With large class sizes, providing timely feedback to students is also challenging for faculty members. Students are spending fewer hours to study class content outside the classroom for several reasons, including working more hours because of rising tuition and living expenses. This paper describes a newly developed mobile learning system, Dysgu, which provides an engaging learning experience for students outside the classroom. Dysgu has interactive and auto-graded exercises to help students practice concepts. Students can see their progress and class standing as they work on the exercises. The mobile platform was deployed in two semesters at two different universities. We saw improved student grades, more on-time submissions, and the acknowledgment of useful features such as interactive activity and the ability to see the overall class status using this new mobile platform. 

Student engagement with out-of-class activities is becoming more difficult as students spend fewer hours outside the classroom studying the content. This research developed a mobile educational platform, Dysgu, to provide students with an optimal learning experience outside of the classroom. Dysgu includes social networking and gamification features to increase student engagement. The platform offers interactive auto-graded assessments to help students practice concepts and take tests. Students can see their scores and a summary of the performance of the rest of the class. We used Dysgu for multiple out-of-class activities at two universities with different student demographics for two semesters. The data shows that students obtain better grades when using Dysgu. We also saw more on-time or ahead-of-time submissions with Dysgu. Survey responses indicated several Dysgu features which students found helpful. We conclude that digital educational platforms should consider features to support scaffolding to master the concept, peer influence to keep students engaged, self-reflection to foster critical thinking, and easy adaption of the platform to reduce faculty workload and improve students’ acceptance of the system. 

While there are numerous causes of waste in the healthcare system, some of this waste is associated with inefficiency. Among the proposed solutions to address inefficiency is clinic layout optimization. Such optimization depends on how operating resources and instruments are placed in the clinic, in what order they are accessed to attain a particular task, and the mobility of clinicians between different clinic rooms to accomplish different clinic tasks. Traditionally, such optimization research involves manual monitoring by human proctors, which is time consuming, erroneous, unproductive, and subjective. If mobility patterns in an indoor space can be determined automatically in real time, layout and operation-related optimization decisions based on these patterns can be implemented accurately and continuously in a timely fashion. This paper explores this application domain where precise localization is not required; however, the determination of mobility is essential on a real-time basis. Given that, this research explores how only mobile devices and their built-in Bluetooth received signal strength indicator (RSSI) can be used to determine such mobility. With a collection of stationary mobile devices, with their computational and networking capabilities and lack of energy requirements, the mobility of moving mobile devices was determined. The research methodology involves developing two new algorithms that use raw RSSI data to create visualizations of movements across different operational units identified by stationary nodes. Compared with similar approaches, this research showcases that the method presented in this paper is viable and can produce mobility patterns in indoor spaces that can be utilized further for data analysis and visualization. 

Generating paths of a mobile device in indoor space by sensing its Bluetooth RSSI value is challenging but has real-world applications. Although Bluetooth RSSI suffers from different factors that limit its usability, this research shows that it can still be used to detect mobility and, over a duration of time, can be used to form paths. This poster presents algorithms that can create a path of a moving mobile device by sensing its RSSI values over time and then presents early results of the algorithm's effectiveness while tracking health practitioners' movement within a community care clinic setting. 

It is a well-documented challenge to keep students engaged and motivated in out-of-class activities. More students now have part- or full-time jobs and less time to study. Supporting their academic growth and success requires acknowledging the higher commitments to the jobs while providing appropriate mechanisms to make the best use of their available times. This paper presents a mobile educational platform, Dysgu, that aims to engage students in out-of-class activities. An initial study completed on this platform investigates the role of peer influence to increase student engagement in an early college class. Data indicates students prefer Dysgu for out-of-class activities compared to traditional pen- and paper-based activities. Students noted that peer influence, in the form of scores compared to the rest of the class, was highly motivating. We also observed more on-time submissions when using Dysgu. 

Keeping students engaged with the course contents between classes is challenging. Although out-of-class activities are used to address this challenge, they have limited impacts on improving student's engagement outside the classroom because of the lack of real-time feedback and progress updates. For this reason, these types of activities are less appealing to the current generation of students who feel the pull of instant gratification more intensely. This paper presents a mobile learning system, named Dysgu, which enables students to work on their out-of-class activities, compare their progress with the rest of the class, and improve their self-efficacy. The goal of Dysgu is to better engage students with out-of-class activities and reduce procrastination in those activities. By using Dysgu, faculty can facilitate and monitor learning even after the students leave the classroom and intervene early when students fall behind their peers. 

This paper presents an out-of-class active learning environment, called Dysgu. Dysgu presents an innovative approach to out-of-class activities by combining multiple dimensions of best practices from different spectrum of student learning into a coherent idea and delivering such activities with personalization and adaptation. The goal of the Dysgu system is to study the impact of frequent out-of-class activities on student learning and engagement when the students can compare their progress with the rest of the class and where the activities are smaller (in scope) with scaffolding support, are interactive in nature, and delivered via a mobile platform. Initial usability tests and software engineering quality matrices show that the software is easy to use, manage and extend.