Physical Sciences and Mathematics Commons^™

Chicago Alliance For Equity In Computer Science, Steven Mcgee, Lucia Dettori, Ronald I. Greenberg, Andrew M. Rasmussen, Dale F. Reed, Don Yanek

Computer Science: Faculty Publications and Other Works

In 2016, CPS enacted a high school computer science graduation requirement as a means to broaden participation in computer science. ECS is the primary course that supports enactment of this policy. With limited numbers of certified computer science teachers, CPS relied on teachers from a variety of disciplines to teach ECS. The ECS professional development program is designed to prepare teachers from all backgrounds to support student success in ECS. This study examines how the profile of ECS teachers changed and the impact of that change on teachers' experiences with ECS professional development.

Camera Placement Meeting Restrictions Of Computer Vision, Sara Aghajanzadeh, Roopasree Naidu, Shuo-Han Chen, Caleb Tung, Abhinav Goel, Yung-Hsiang Lu, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

In the blooming era of smart edge devices, surveillance cam- eras have been deployed in many locations. Surveillance cam- eras are most useful when they are spaced out to maximize coverage of an area. However, deciding where to place cam- eras is an NP-hard problem and researchers have proposed heuristic solutions. Existing work does not consider a signifi- cant restriction of computer vision: in order to track a moving object, the object must occupy enough pixels. The number of pixels depends on many factors (how far away is the object? What is the camera resolution? What is the focal length?). …

Modular Neural Networks For Low-Power Image Classification On Embedded Devices, Abhinav Goel, Sara Aghajanzadeh, Caleb Tung, Shuo-Han Chen, George K. Thiruvathukal, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

Embedded devices are generally small, battery-powered computers with limited hardware resources. It is difficult to run deep neural networks (DNNs) on these devices, because DNNs perform millions of operations and consume significant amounts of energy. Prior research has shown that a considerable number of a DNN’s memory accesses and computation are redundant when performing tasks like image classification. To reduce this redundancy and thereby reduce the energy consumption of DNNs, we introduce the Modular Neural Network Tree architecture. Instead of using one large DNN for the classifier, this architecture uses multiple smaller DNNs (called modules) to progressively classify images …

Addressing Rogue Vehicles By Integrating Computer Vision, Activity Monitoring, And Contextual Information, Brook Abegaz, David Chan-Tin, Neil Klingensmith, George K. Thiruvathukal

Computer Science: Faculty Publications and Other Works

In this paper, we address the detection of rogue autonomous vehicles using an integrated approach involving computer vision, activity monitoring and contextual information. The proposed approach can be used to detect rogue autonomous vehicles using sensors installed on observer vehicles that are used to monitor and identify the behavior of other autonomous vehicles operating on the road. The safe braking distance and the safe following time are computed to identify if an autonomous vehicle is behaving properly. Our preliminary results show that there is a wide variation in both the safe following time and the safe braking distance recorded using …

A Real-Time Feature Indexing System On Live Video Streams, Aditya Chakraborty, Akshay Pawar, Hojoung Jang, Shunqiao Huang, Sripath Mishra, Shuo-Han Chen, Yuan-Hao Chang, George K. Thiruvathukal, Yung-Hsiang Lu

Computer Science: Faculty Publications and Other Works

Most of the existing video storage systems rely on offline processing to support the feature-based indexing on video streams. The feature-based indexing technique provides an effec- tive way for users to search video content through visual features, such as object categories (e.g., cars and persons). However, due to the reliance on offline processing, video streams along with their captured features cannot be searchable immediately after video streams are recorded. According to our investigation, buffering and storing live video steams are more time-consuming than the YOLO v3 object detector. Such observation motivates us to propose a real-time feature indexing (RTFI) system …

Ivpair: Context-Based Fast Intra-Vehicle Device Pairing For Secure Wireless Connectivity, Kyuin Lee, Neil Klingensmith, Dong He, Suman Banerjee, Younghyun Kim

Computer Science: Faculty Publications and Other Works

The emergence of advanced in-vehicle infotainment (IVI) systems, such as Apple CarPlay and Android Auto, calls for fast and intuitive device pairing mechanisms to discover newly introduced devices and make or break a secure, high-bandwidth wireless connection. Current pairing schemes are tedious and lengthy as they typically require users to go through pairing and verification procedures by manually entering a predetermined or randomly generated pin on both devices. This inconvenience usually results in prolonged usage of old pins, significantly degrading the security of network connections.

To address this challenge, we propose ivPair, a secure and usable device pairing protocol that …

Crowdsourcing Detection Of Sampling Biases In Image Datasets, Xiao Hu, Haobo Wang, Anirudh Vegesana, Somesh Dube, Kaiwen Yu, Gore Kao, Shuo-Han Chen, Yung-Hsiang Lu, George K. Thiruvathukal, Ming Yin

Computer Science: Faculty Publications and Other Works

Despite many exciting innovations in computer vision, recent studies reveal a number of risks in existing computer vision systems, suggesting results of such systems may be unfair and untrustworthy. Many of these risks can be partly attributed to the use of a training image dataset that exhibits sampling biases and thus does not accurately reflect the real visual world. Being able to detect potential sampling biases in the visual dataset prior to model development is thus essential for mitigating the fairness and trustworthy concerns in computer vision. In this paper, we propose a three-step crowdsourcing workflow to get humans into …

Does A Computer Science Graduation Requirement Contribute To Increased Enrollment In Advanced Computer Science Coursework?, Steven Mcgee, Randi Mcgee-Tekula, Jennifer Duck, Lucia Dettori, Ronald I. Greenberg, Andrew M. Rasmussen, Erica Wheeler, Adam Shelton

Computer Science: Faculty Publications and Other Works

Prior research has shown that students pursuing Exploring Computer Science (ECS) as their first elective course were more likely to pursue another computer science course in high school, as compared to students who took a traditional course as the first course. This study investigated whether the results are consistent when students are pursuing ECS to fulfill the Chicago Public Schools' graduation requirement. ECS is designed to foster deep engagement through equitable inquiry around computer science concepts. It is hypothesized that students who are fulfilling a graduation requirement will pursue additional computer science coursework at rates similar to students who were …

The Impact Of Cs For All On College Placement In Computer Science, Ronald I. Greenberg, Julie Medero, Samuel A. Rebelsky, Frances P. Trees, Dale Reed

Computer Science: Faculty Publications and Other Works

With the CS for All movement increasingly gaining traction nationally, students entering colleges and universities are arriving with deeper and broader CS experiences. This in turn can change students' higher education starting point. This panel of CS faculty with expertise in this area will present perspectives and models to describe how higher education choices for placement, credit, and curriculum design affect the efforts to broaden participation in student pathways into computing and related studies.

The Changing Profile Of Ecs Teachers, Steven Mcgee, Lucia Dettori, Ronald I. Greenberg, Andrew M. Rasmussen, Dale F. Reed, Don Yanek

Computer Science: Faculty Publications and Other Works

This study compares the characteristics and professional development (PD) experiences between teachers who began teaching Exploring Computer Science before and after the enactment of a CS graduation requirement in the Chicago Public Schools. The post-requirement teachers were less likely to have a CS background, but their experience in the ECS PD and their level of confidence at the end of the PD were equivalent to the early adopters.

Computer Science Through Concurrent Enrollment: A Strategy To Broaden Participation, Renee Fall, Seth Freeman, Ronald I. Greenberg, Dan Kaiser, Nigamanth Sridhar

Computer Science: Faculty Publications and Other Works

Most U.S. states support college-readiness and access through dual enrollment, in which high school students enroll in college courses. Concurrent enrollment (CE) allows students to take college courses in their own high school, taught by high school teachers approved by the partner college. CE has positive effects on students' education, but rarely is CS available through CE. Unlike AP, CE provides college credit to students who are assessed throughout the course rather than by a single high-stakes exam/project. This panel will showcase four different types of post-secondary institutions' experiences offering CS-through-CE and discuss its potential as an entry point into …