Physical Sciences and Mathematics Commons^™

On The Use Of Machine Learning For Causal Inference In Extreme Weather Events, Yuzhe Wang

Discovery Undergraduate Interdisciplinary Research Internship

Machine learning has become a helpful tool for analyzing data, and causal Inference is a powerful method in machine learning that can be used to determine the causal relationship in data. In atmospheric and climate science, this technology can also be applied to predicting extreme weather events. One of the causal inference models is Granger causality, which is used in this project. Granger causality is a statistical test for identifying whether one time series is helpful in forecasting the other time series. In granger causality, if a variable X granger-causes Y: it means that by using all information without …

Crowd-Machine Partnership On Road Infrastructure Quality Recognition And Resilience, Eric J. Thompson

Discovery Undergraduate Interdisciplinary Research Internship

Public roads are a vital component of modern-day society, as they are necessary for the transportation of people and capital; consequently, it is important that they are regularly and effectively maintained. Unfortunately, this maintenance is difficult to manage due to the sheer area that roads span. It is an arduous task to locate every instance of road damage, as well as to determine the urgency that each bit of damage necessitates. Repairing road damage has high costs in labor, time, and money. To provide a more efficient way to monitor road conditions, we are designing a mobile application that collects …

Physics-Informed Machine Learning To Predict Extreme Weather Events, Rthvik Raviprakash, Jonathan Buchanan, Mahdi Bu Ali

Discovery Undergraduate Interdisciplinary Research Internship

Extreme weather events refer to unexpected, severe, or unseasonal weather events, which are dynamically related to specific large-scale atmospheric patterns. These extreme weather events have a significant impact on human society and also natural ecosystems. For example, natural disasters due to extreme weather events caused more than $90 billion global direct losses in 2015. These extreme weather events are challenging to predict due to the chaotic nature of the atmosphere and are highly correlated with the occurrence of atmospheric blocking. A key aspect for preparedness and response to extreme climate events is accurate medium-range forecasting of atmospheric blocking events.

Unlike …

Characterizing Students’ Engineering Design Strategies Using Energy3d, Jasmine Singh, Viranga Perera, Alejandra Magana, Brittany Newell

Discovery Undergraduate Interdisciplinary Research Internship

The goals of this study are to characterize design actions that students performed when solving a design challenge, and to create a machine learning model to help future students make better engineering design choices. We analyze data from an introductory engineering course where students used Energy3D, an open source computer-aided design software, to design a zero-energy home (i.e. a home that consumes no net energy over a period of a year). Student design actions within the software were recorded into text files. Using a sample of over 300 students, we first identify patterns in the data to assess how students …

Deep Machine Learning For Mechanical Performance And Failure Prediction, Elijah Reber, Nickolas D. Winovich, Guang Lin

The Summer Undergraduate Research Fellowship (SURF) Symposium

Deep learning has provided opportunities for advancement in many fields. One such opportunity is being able to accurately predict real world events. Ensuring proper motor function and being able to predict energy output is a valuable asset for owners of wind turbines. In this paper, we look at how effective a deep neural network is at predicting the failure or energy output of a wind turbine. A data set was obtained that contained sensor data from 17 wind turbines over 13 months, measuring numerous variables, such as spindle speed and blade position and whether or not the wind turbine experienced …

Predict The Failure Of Hydraulic Pumps By Different Machine Learning Algorithms, Yifei Zhou, Monika Ivantysynova, Nathan Keller

The Summer Undergraduate Research Fellowship (SURF) Symposium

Pump failure is a general concerned problem in the hydraulic field. Once happening, it will cause a huge property loss and even the life loss. The common methods to prevent the occurrence of pump failure is by preventative maintenance and breakdown maintenance, however, both of them have significant drawbacks. This research focuses on the axial piston pump and provides a new solution by the prognostic of pump failure using the classification of machine learning. Different kinds of sensors (temperature, acceleration and etc.) were installed into a good condition pump and three different kinds of damaged pumps to measure 10 of …

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Predictive Power And Validity Of Connectome Predictive Modeling: A Replication And Extension, Michael Wang, Joaquin Goni, Enrico Amico

The Summer Undergraduate Research Fellowship (SURF) Symposium

Neuroimaging, particularly functional magnetic resonance imaging (fMRI), is a rapidly growing research area and has applications ranging from disease classification to understanding neural development. With new advancements in imaging technology, researchers must employ new techniques to accommodate the influx of high resolution data sets. Here, we replicate a new technique: connectome-based predictive modeling (CPM), which constructs a linear predictive model of brain connectivity and behavior. CPM’s advantages over classic machine learning techniques include its relative ease of implementation and transparency compared to “black box” opaqueness and complexity. Is this method efficient, powerful, and reliable in the prediction of behavioral measures …

Modeling Visual Features To Recognize Biological Motion: A Developmental Approach, Giulio Sandini, Nicoletta Noceti, Alessia Vignolo, Alessandra Sciutti, Francesco Rea, Alessandro Verri, Francesca Odone

MODVIS Workshop

In this work we deal with the problem of designing and developing computational vision models – comparable to the early stages of the human development – using coarse low-level information.

More specifically, we consider a binary classification setting to characterize biological movements with respect to non-biological dynamic events. To this purpose, our model builds on top of the optical flow estimation, and abstract the representation to simulate the limited amount of visual information available at birth. We take inspiration from known biological motion regularities explained by the Two-Thirds Power Law, and design a motion representation that includes different low-level features, …