Machine Learning & A.I

A.I controlled image making using convolutional neural network (CNN) by Google Deep Dream. Machine Learning. By Ming Tang, students in ARCH4001, ARCH7014, SAID, DAAP, UC. Fall 2018.

urban mobility studio

ARCH4001. Fall. 2018. SAID, DAAP, UC.

Faculty: Ming Tang, RA, LEED AP, Associate Professor. UC

Using Cincinnati Uptown and proposed Smart Corridor area as the focus area, the studio presents a study investigating the urban mobility with an emphasis on the simulated human behavior cues and movement information as input parameters. The research is defined as a hybrid method which seeks logical architecture/urban forms and analyzes its’ performance. As one of the seven-courses-clusters supported by UC Forward, the studio project extends urban mobility study by exploring, collecting, analyzing, and visualizing geospatial information and physically representing the information through various computational technologies.
The studio investigation is intended to realize the potential of quantifying demographic, social, and behavior data into a parametric equation. In the experiments, the integration of non-geometrical parameters within the form seeking and performance evaluation process resulted in a series of a conceptual model to represent the movement and access. The projects will be developed by optimizing transportation network, analyzing way-finding and human behavior. Ultimately, the studio looks to build upon the strengths pre-defined in the evaluation method and capture the benefits of Geographic Information System (GIS), virtual reality (VR), eye-tracking, and wayfinding simulation by seamlessly integrating vital geospatial components in the equation and altering the way people explore the possible design solutions in order to generate the ideal urban and building forms.



UC Forward Collaborative on Smart Transportation Forum at Niehoff studio

eye tracking

More info on the studio and the student projects.


AR based Digi_Fab

Augmented Reality for Digital Fabrication.  Projects from SAID, DAAP, UC. Fall 2018.

Hololens. Fologram, Grasshopper.

Faculty: Ming Tang, RA, Associate Prof. University of Cincinnati

Students: Alexandra Cole, Morgan Heald, Andrew Pederson,Lauren Venesy,Daniel Anderi, Collin Cooper, Nicholas Dorsey, ,John Garrison, Gabriel Juriga, Isaac Keller, Tyler Kennedy, Nikki Klein, Brandon Kroger, Kelsey Kryspin, Laura Lenarduzzi, Shelby Leshnak, Lauren Meister,De’Sean Morris, Robert Peebles, Yiying Qiu, Jordan Sauer, Jens Slagter, Chad Summe, David Torres, Samuel Williamson, Dongrui Zhu, Todd Funkhouser.

Project team lead: Jordan Sauer, Yiying Qiu, Robert Peebles,David Torres.


Videos of working in progress


Training Simulation for ODOT Snow and Ice Drivers

Grant supported by the Ohio Department of Transportation.

PI: Jiaqi Ma. Co-PI: Ming Tang. Julian Wang.

Training using driving simulator & VR-based training applications

The purpose of this research is to conduct an in-depth analysis of ODOT’s current process for training snow and ice drivers and provide recommendations on how to enhance their snow and ice experience.

To accomplish this research, the scope of work should be divided into two phases. The scope of work should include, at a minimum, the activities noted below. Additional tasks may be included in the proposal by the UC team as appropriate to ensure achievement of research objectives. ODOT’s decision to invest in Phase 2 will be based on Phase 1 interim report and recommendations, and it will consider both ODOT’s ability to implement and the expected cost-benefit.

The first phase of the research requires a comprehensive look at how ODOT currently trains their snow and ice drivers and a review of nationwide practices for snow and ice driver training. An analysis of the past practices shall be considered. During Phase 1, the UC team will work closely with ODOT Lorain County personnel. The recommendations will be developed by reviewing and documenting ODOT’s current practices, past practices, and then developing a matrix of choices and opportunities to enhance ODOT’s travel time recovery.

In order to understand the available technologies for training snow and ice drivers, we performed a preliminary literature search and found the key technologies can be categorized into driving simulator-based, VR-based, AR-based type. In the following section, we will discuss these three simulation training types, and some previous associated works conducted by PIs are also provided.

“Evaluate Opportunities to Provide Training Simulation for ODOT Snow and Ice Drivers”. Ohio Department of Transportation. PI: Jiaqi Ma. Co-PI: Ming Tang, Julian Wang.

SAID students: Sam Dezarn, Ganesh Raman, Dongrui Zhu, Jordan Sauer.

Download the demo file. zip (1GB)

instruction: “C” switch camera view. “E” get in/out car, “L” trun on/off light. “space bar” break. “W”, “A”, “S”, “D” for navigation.

Gamepad: Right Trigger, to start engine,  Left Trigger tostop engine.


publication in Urban Rail Transit journal

Paper published in the Urban Rail Transit journal

This paper describes an innovative integration of eye-tracking (ET) with virtual reality (VR), and details the application of these combined technologies for the adaptive reuse redesign of the Wudaokou rail station in Beijing. The objective of the research is to develop a hybrid approach, combining ET and VR technologies, as part of an experimental study of how to improve wayfinding and pedestrian movement in crowded environments such as those found in urban subway stations during peak hours. Using ET analysis, design features such as edges, and color contrast are used to evaluate several proposed rail station redesigns. Through VR and screen-based ET, visual attention and related spatial responses are tracked and analyzed for the selected redesign elements. This paper assesses the potential benefits of using ET and VR to assist identification of station design elements that will improve wayfinding and pedestrian movement, and describes how the combination of VR and ET can influence the design process. The research concludes that the combination of VR and ET offers unique advantages for modeling how the design of rail transit hub interiors can influence the visual attention and movement behavior of those using the redesigned station.  This is especially true for crowded conditions in complex interior spaces. The use of integrated ET and VR technology is shown to inform innovative design approaches for facilitating improved wayfinding and pedestrian movement within redesigned rail stations.

Full paper: download PDF, read HTML

Check out Tang’s eye-tracking research with transit hub design studio ARCH4002, Spring 2018.