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. 

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. 

In an indoor space, determining a person’s speed of mobility has a lot of research significance and applicability in real-world scenarios. This research has developed a mobile application to investigate how to determine a person’s walking speed. The goal was to determine a person’s walking speed by using the number of steps. There has been similar work to test the accelerometer sensor in detecting steps. However, the accuracy of using the steps to calculate the velocity was not studied. This application uses the accelerometer sensor in the mobile device to detect steps and then compute the velocity. The accelerometer provides information about the user’s motion and acceleration, and an algorithm was developed to use that data to determine the steps. Once steps are determined, the person’s speed is calculated by using the change of location within a pre-determined space and time. Therefore, accurately measuring the number of steps was vital and it was determined that the position of the mobile device in the body plays a significant role in that accuracy. Therefore, the experiment used three device positions: the pants front pocket, the right hand, and the backpack. While walking, the number of steps were manually counted and recorded. A comparison was made between the recorded number of steps to the application’s measured steps. The experiment was conducted multiple times for each device position. The placement of the mobile devices in the front pants pocket gives the most accurate results, whereas the other two device positions gave reasonably accurate results. The position of the device played an important part in the research and had a significant impact on the accuracy of the results. In the future, testing can include additional device positions. Additionally, other mobile device sensors could be included in the testing and can be compared with this approach.