March 3rd, 2022

Runze and Afsaneh's paper titled "Exploratory Machine Learning Modeling of Adaptive and Maladaptive Personality Traits from Passively Sensed Behavior" was accepted to ACM Transactions on Intelligent Systems and Technology (TIST) Journal. The paper presents a computational framework to detect cyclic biobehavior, model commonality and differences in rhythms of human participants in the sample datasets, and predict their health and readiness status using models of biobehavioral rhythms. This framework seeks to generate new knowledge and findings through rigorous micro- and macro-level modeling of human rhythms from mobile and wearable data streams collected in the wild and uses them to assess and predict different life and health outcomes.

Find the paper here: A Computational Framework for Modeling Biobehavioral Rhythms from Mobile and Wearable Data Streams

February 24th, 2022

Runze and Afsaneh had a paper accepted to the  Future Generation Computer Systems journal. The paper, titled "Exploratory Machine Learning Modeling of Adaptive and Maladaptive Personality Traits from Passively Sensed Behavior", shows that both adaptive and maladaptive traits are associated with passively sensed behavior, which provides initial evidence for the utility of this type of data to study personality and its pathology.

Find the paper here: Exploratory Machine Learning Modeling of Adaptive and Maladaptive Personality Traits from Passively Sensed Behavior

September 26th, 2021

I co-organized the Wild by Design workshop at UbiComp. In the digital age, there has been a proliferation of cheap, off-the-shelf mobile sensing devices, combined with limitations of traditional health assessments that creates a demand for monitoring health in the uncontrolled, "wild" environment of daily life. Devices such as fitness trackers and smartphones are exploding in popularity, yet there is still a long way to go for ubiquitous health monitoring technology to truly become ubiquitous. This workshop explored the possibilities, limitations, and current state of these technologies.

Read more here: Workshop on Designing Ubiquitous Health Monitoring Technologies for Challenging Environments 

September 21st-26th, 2021

I was a general organizer for the ubiquitous computing conference UbiComp. UbiComp brings together designers, researchers, and developers from all over the world to discuss ubiquitous and pervasive computing technologies and the understanding of human experiences and social impacts that these technologies facilitate. This year's conference was held virtually due to COVID-19 concerns, which had the added effect of expanding access to those who could not travel.

Read more here: UbiComp 2021 

February 7th-12th, 2020

I presented my research in collaboration with Xi Chen at the 34th AAAI Conference on Artificial Intelligence in New York, New York. The paper proposes a novel approach to improving the accuracy of feature selection, specifically in data sets with large feature sets and a small number of data points. Existing methods of feature selection typically do not achieve high accuracy. The approach presented optimizes feature selection through Frequent Pattern Growth algorithm to identify frequently occurring sets that appear among the top features selected.

Find the paper here: Optimizing the Feature Selection Process for Better Accuracy in Datasets with a Large Number of Features