Sean Mealin

An exploratory study of blind software developers

As a research community, we currently know very little about the challenges faced by blind software developers. Without knowing what those challenges are, the community cannot effectively address these challenges. In this paper, we describe the first exploratory empirical study, where we conducted eight interviews with blind software developers to identify aspects of software development that are a challenge. Our results suggest that visually impaired software developers face challenges, for instance, when using screen readers to look up information when writing code. We discuss a variety of implications, including that blind software developers need additional support in discovering relevant software development tools.

Balancing noise sensitivity, response latency, and posture accuracy for a computer-assisted canine posture training system

This paper describes a canine posture detection system composed of wearable sensors and instrumented devices that detect the postures sit, stand, and eat. The system consists of a customized harness outfitted with wearable Inertial Measurement Units (IMUs) and a base station for processing IMU data to classify canine postures. Research in operant conditioning, the science of behavior change, indicates that successful animal training requires consistent and accurate feedback on behavior. Properly designed computer systems excel at timeliness and accuracy, which are two characteristics most amateur trainers struggle with and professionals strive for. Therefore, in addition to the system being ergonomically designed to ensure the dogs comfort and well-being, it is engineered to provide posture detection with timing and accuracy on par with a professional trainer. We contend that providing a system with these characteristics will one day aid dogs in learning from humans by overcoming poor or ineffective timing during training. We present the initial steps in the development and validation of a computer-assisted training system designed to work outside of laboratory environments.The main contributions of this work are (a) to explore the trade-off between low-latency responses to changes in time-series IMU data representative of posture changes while maintaining accuracy and timing similar to a professional trainer, and (b) to provide a model for future ACI technologies by documenting the user-centered approach we followed to create a computer-assisted training system that met the criteria identified in (a). Accordingly, in addition to describing our system, we present the results of three experiments to characterize the performance of the system at capturing sit postures of dogs and providing timely reinforcement. These trade-offs are illustrated through the comparison of two algorithms. The first is Random Forest classification and the second is an algorithm which uses a Variance-based Threshold for classification of postures. Results indicate that with proper parameter tuning, our system can successfully capture and reinforce postures to provide computer-assisted training of dogs.

GSK: universally accessible graph sketching

Combinatorial graphs, often conveyed as node-link diagrams, figure prominently in Computer Science and other Science, Technology, Engineering, and Mathematics (STEM) disciplines. Unfortunately, they are most often inaccessible to blind students and professionals. This paper introduces GSK, a self-contained Graph SKetching tool that allows blind and sighted people to easily create, edit, and share graphs in real-time using interaction mechanisms (mouse, keyboard, monitor, screen reader) that are standard for them. GSK was successfully used by a blind Computer Science student and his sighted instructors to create and access graphs specific to his automata theory and operating systems courses. Our hope is that GSK will enable more blind STEM students and professionals to actively participate in their disciplines by providing them and their sighted colleagues with a cross-collaboration tool that allows them to share graphs just as easily as they share text and word processing documents.

Towards Unsupervised Canine Posture Classification via Depth Shadow Detection and Infrared Reconstruction for Improved Image Segmentation Accuracy

Hardware capable of 3D sensing, such as the Microsoft Kinect, has opened up new possibilities for low-cost computer vision applications. In this paper, we take the first steps towards unsupervised canine posture classification by presenting an algorithm to perform canine-background segmentation, using depth shadows and infrared data for increased accuracy. We report on two experiments to show that the algorithm can operate at various distances and heights, and examine how that effects its accuracy. We also perform a third experiment to show that the output of the algorithm can be used for k-means clustering, resulting in accurate clusters 83 % of the time without any preprocessing and when the segmentation algorithm is at least 90 % accurate.

Including blind people in computing through access to graphs

Our goal in creating the Graph SKetching tool, GSK, was to provide blind screen reader users with a means to create and access graphs as node-link diagrams and share them with sighted people in real-time. Through this effort, we hoped to better include blind people in computing and other STEM disciplines in which graphs are important. GSK proved very effective for one blind computer science student in courses that involved graphs and graph structures such as automata, decision trees, and resource-allocation diagrams. In order to determine how well GSK works for other blind people, we carried out a user study with ten blind participants. We report on the results of the user study, which demonstrates the efficacy of GSK for the examination, navigation, and creation of graphs by blind users. Based on the study results, we improved the efficiency of GSK for blind users. We plan more enhancements to help meet the need for accessible graph tools as articulated by the blind community.

Stimulus Control for Semi-autonomous Computer Canine-Training

For thousands of years, humans have domesticated and trained dogs to perform tasks for them. Humans have developed areas of study, such as Applied Behavior Analysis, which aim to improve the training process. We introduce a semi-autonomous, canine-training system by combining existing research in Applied Behavior Analysis with computer systems consisting of hardware, software, audio, and visual components. These components comprise a biohybrid system capable of autonomously training a dog to perform a specific behavior on command. In this paper we further our previous computer canine-training system by the application of stimulus control over a newly-acquired, free operant behavior. This system uses light and sound as a discriminative stimulus for the behavior of a dog pushing a button with its nose. Indications of simple stimulus control of this behavior were achieved. Our pilot of this system indicates canine learning comparable to that from a professional dog trainer.

Creating an Evaluation System for Future Guide Dogs: A Case Study of Designing for Both Human and Canine Needs

It is incredibly expensive to breed, train, and place a working guide dog; costs are tens of thousands of dollars for many organizations. During this training process, approximately 40% of canines are dropped due to medical, behavioral, or other reasons. Since guide dog schools do not have unlimited resources, they must focus on the most promising candidates so they can maximize resources to meet the growing need for guide dogs. Staff at some schools use evaluations to predict how successful a dog will be in the program. While current processes have achieved some positive results, they are highly-subjective, and rely on people with years of experience and knowledge. As a major first step towards an objective evaluation, we developed a system for a human operator to annotate canine behavior while simultaneously collecting physiological and accelerometer data. In collaboration with Guiding Eyes for the Blind, we designed the system from the ground up to meet the needs of both canine and human users.

Smart connected canines: IoT design considerations for the lab, home, and mission-critical environments

The canine-human relationship continues to grow as dogs become an increasingly critical part of our society. As reliance on dogs has increased from simple companionship, to service dogs, urban security, and national defense, the opportunities for enhanced communications between the working canine and their handler increase. Wireless sensor networks and the Internet of Things (IoT) can extend traditional canine-human communication to integrate canines into the cyber-enabled world. This is what we call the Smart Connected Canine (SCC). Canine-computer interaction is sufficiently different from human-computer interaction so as to present some challenging research and design problems. There are physical and performance limits to what a dog will naturally tolerate. There are communications requirements for monitoring dogs, monitoring the environment, and for canine-human communications. Depending on the working environment there are different performance, security, and ergonomic considerations. This paper summarizes three example canine-human systems we presented earlier along with their Ion data characteristics and design criteria in order to explore how smart connected canines can improve our lives, the future of smart connected canines, and the requirements on IoT technologies to facilitate this future.