Greetings! My name is Zhuoning Yuan. I am a graduate student studying computer science in the University of Iowa.
I earned a bachelor's degree of Electrical Engineering. I have accomplished many cool projects and some of them are still in progress.
My career goal is to become a computer scientist who can facilitate people's life using the techniques I learned, such as machine learning and data mining.
Now, I am a member of Machine Learning and Optimization Research Group of CS Dept.
Obesity is a serious issue in US and more than 68.8 percent of adults are considered to be overweight or obese. We implemented data mining and machine learning techniques to link obesity with Social Media, such Twitter, to find interesting patterns of obesity.
Nowadays, people are always worrying about their weights and diets. It is really hard to take care of our bodies in such a busy life.
We designed this App to facilitate people's life by monitoring nutrition intake everyday and make healthier suggestions based on different cases.
Predicting Traffic Accidents Through Heterogeneous Urban
Data: A Case Study
With the urbanization process around the globe, traffic accidents
have undergone a rapid growth in recent decades,
causing significant life and property losses. Predicting traffic
accidents is a crucial problem to improving transportation
and public safety as well as safe routing. However, the problem
is also challenging due to the imbalanced classes, spatial
heterogeneity, and the non-linear relationship between dependent
and independent variables. Most previous research on
traffic accident prediction conducted by domain researchers
simply applied classical prediction models on limited data
without addressing the above challenges properly, thus leading
to unsatisfactory performance. This paper, through a
case study, presents our explorations on effective techniques
to address the above challenges for better prediction results.
Specifically, we formulate the problem as a binary classification
problem. For each road segment in each hour, we
predict whether an accident will occur. Big data including all
the motor vehicle crashes from 2006 to 2013 in the state of
Iowa, detailed road network, and various weather attributes
at 1-hour granularity have been collected and map-matched.
We evaluate four classification models, i.e., Support Vector
Machine (SVM), Decision Tree, Random Forest, and Deep
Neural Network (DNN). To tackle the imbalanced class problem,
we perform an informative negative sampling approach.
To tackle the spatial heterogeneity challenge, we incorporate
SpatialGraph features through Eigen-analysis of the road
network. Results show that employing informative sampling
and incorporating the SpatialGraph features could effectively
improve the performance of all the models. Random Forest
and DNN generally perform better than other models.
Obesity has been a public health problem in the United States.
The online social media platforms such as Twitter, Facebook,
Google+ give users quick and easy way to engage in conversation
about issues, problems, and concerns of their daily lives.
In this exploratory research, our goal is to determine if the
obesity conversation among Twitter users from fattest places is
different than that among people from thinnest places.
We conducted a comparative study of obesity conversations on Twitter
by location of top ten fattest and thinnest cities as well as top ten
fattest and thinnest states in the United States. Our results show
that users in fattest cities and states participate significantly
less in conversation covering the topics on and around obesity than
that of thinnest cities and states.
This project presents a detailed, systematic procedure for developing a Micro Aerial
Vehicle (MAV), which is capable of autonomous flight in GPS-denied environments. This
MAV is designed for a gross weight of 490 g and flight endurance of 8 minutes. The
hardware structure (including the sensors, processors, and mechanical components), the
software architecture (including operating system, navigation, control, and data logging), the
communication system, and the ground station unit are discussed in detail.
Obesity is a serious issue among US today. We designed this App to help people control their
nutrition intake every day, such as, sugar, calories, sodium, etc. and also we would like to make
friendly suggestions based on users' nutrition balance. For example, a user sets a limit of sugar intake of 100g per day,
it will show a warning sign if he would like to add a new product to his database which leads to the total sugar intake over
100g at that day. The below link is a short video demo including some basic functions of this App. The current progress is
that we are working on a better UI as well as adding more applicable features.