Ramesh Paudel

Ramesh Paudel

Contact

Graph Computing Lab (GraphLab)
The George Washington University
Washington, DC 20052
rpaudel42 at gwu dot edu



The percentage of people living over 65 years has increased steadily over the last few decades, and with it is coming a rapid increase in cognitive health issues among the baby boomers. In order to address the issue of caring for this particular aging population, intelligent solutions need to be provided. Sensor-based smart home provide the ability to track resident activities without interfering in their daily routine. It is useful to detect and predict the behaviors of an elderly resident in order to improve the safety of the residents’ home environment and provide aid for their caregiver.

  1. Graph-based Approach:

    This work presents a graph-based approach that successfully discover patterns and anomalies in resident activities. We analyze activity graphs constructed from smart home daily activities to detect normative patterns as well as temporal, spatial, and behavioral anomalies. We also present case studies for cognitively impaired participants and discuss how these anomalies can be linked to the decline in their cognitive abilities which will ultimately provide clinicians and care givers important knowledge regarding their patients. Refer the paper published in ICDATA-2018 Conference Preceedings for details.

  2. Machine Learning Approach:

    It is our hypothesis that through the application of various data mining and machine learning approaches, we can analyze data from the sensors installed in smart homes in order to predict whether an elderly resident has cognitive impairments, which will hinder their ability to perform daily tasks. With the growing senior citizen population, it is imperative to detect and try to predict these kinds of behaviors because it can improve the quality and safety of the residents’ home environment as well as provide aid and well-being for their caregiver. In this work, we present our proposed approach, the real-world data set used in our experiments, and results from this study. Refer the paper published in FLAIRS-31 Conference Preceedings for details.

Zerkouk, Meriem, and Belkacem Chikhaoui. (2018) Long Short Term Memory Based Model for Abnormal Behavior Prediction in Elderly Persons. International Conference on Smart Homes and Health Telematics pdf

Moallem, M., H. Hassanpour, and A. A. Pouyan (2019) Anomaly Detection in Smart Homes Using Deep Learning. Iranian (Iranica) Journal of Energy and Environment pdf