N/A

Counterfactual Explanations (CE) is a type of eXplainable Artificial Intelligence (XAI) that addresses the common question of what options a user has to achieve a desired output. In this thesis, the authors propose utilizing the CE technique on regression tasks with a reject option to provide feedback to forklift drivers regarding their energy usage. Recent developments in CE shows that most of the research on CE focuses on classification tasks. Hence, the research question addresses how CE techniques can be used for regression tasks, particularly feedback-providing applications. The data was collected from the Toyotalab for forklifts using a Controller Area Network (CAN). Forklifts are an important component in logistics operations and the demand for them is increasing day by day due to the increasing trend of e-commerce and express delivery. Optimizing their energy usage can lead to significant energy savings. The study is in the direction of providing only the important feedback to the driver by using a reject option as a decision making system. The data is pre-processed and used to train an Machine Learning (ML) model and is used to predict future energy consumption based on the current values. Evaluation of results shows that theCE method exhibits slower performance compared to Local Interpretable Model-Agnostic Explanations(LIME) and SHapley Additive exPlanations (SHAP). However, it demonstrates a high degree of stability in its results. Additionally, the results show that if the driver follows the suggestions proposed by the reject option driven CE, substantial energy savings can be achieved. This work can also be extended to other regression applications where feedback is required.

The general problem of application development of interactive GUI applications has been addressed by toolkits, libraries, user interface management systems, and more recently domain-specific application frameworks. However, the most sophisticated solution offered by frameworks still lacks a number of features which are addressed by this research: 1) limited functionality -- the framework does little to help the developer implement the application's functionality. 2) weak model of the application -- the framework does not incorporate a strong model of the overall architecture of the application program. 3) representation of control sequences is difficult to understand, edit, and reuse -- higher-level, direct-manipulation tools are needed. We address these problems with a new framework design called Oregon Speedcode Universe version 3.0 (OSU v3.0) which is shown, by demonstration, to overcome the limitations above: 1) functionality is provided by a rich set of built-in functions organized as a class hierarchy, 2) a strong model is provided by OSU v3.0 in the form of a modified MVC paradigm, and a Petri net based sequencing language which together form the architectural structure of all applications produced by OSU v3.0. 3) representation of control sequences is easily constructed within OSU v3.0 using a Petri net editor, and other direct manipulation tools built on top of the framework. In ddition: 1) applications developed in OSU v3.0 are partially portable because the framework can be moved to another platform, and applications are dependent on the class hierarchy of OSU v3.0 rather than the operating system of a particular platform, 2) the functionality of OSU v3.0 is extendable through addition of classes, subclassing, and overriding of existing methods. The main contribution of this research is in the design of an application framework that uses Petri nets as the computational model of data processing in the synthesized application. OSU v3.0 is the first framework to formalize sequencing, and to show that complex GUI applications can indeed be quickly and reliably produced from such a framework. / Graduation date: 1992

Thesis (M.S.)--Mississippi State University. Department of Electrical and Computer Engineering. / Title from title screen. Includes bibliographical references.

Most interaction with computers today takes place in a two dimensional environment. Even when using three dimensional graphics applications, input is often still restricted to two dimensions. Many believe that the use of three dimensional input devices will alleviate this restriction and allow for a much more natural human-machine dialog. This thesis seeks to establish how factors dealing with visual feedback and task structure affect the ability to perform interactive tasks in a three dimensional virtual environment. The factors investigated were stereoscopic vision, motion parallax, stimulus arrangement and stimulus complexity. Four tasks were studied. These tasks were: point location, docking, line tracing and curve tracing. All the tasks used a six degree of freedom input device to control a pointer in a three dimensional virtual environment. Four experiments corresponding to the four tasks were conducted to investigate these factors. Among other things the results showed the following. Stereoscopic vision provided a strong benefit to positioning-based tasks, but this benefit was weakened in the case of tracing tasks. Motion parallax via head-tracking often had no effect upon task performance and where an effect was found it was often detrimental. The position of stimuli influenced performance across all of the tasks. The orientation of stimuli influenced performance in the task in which it was varied.

No description available.

Thesis (M.F.A.)--Rochester Institute of Technology, 1991. / On T.p. "[copyright]" appears as the copyright symbol. Includes bibliographic reference: (leaf 50).

Thesis (M.S.)--University of Texas at El Paso, 2009. / Title from title screen. Vita. CD-ROM. Includes bibliographical references. Also available online.

Thesis (M.S. in computer science)--Washington State University, May 2009. / Title from PDF title page (viewed on May 26, 2009). "Department of Electrical Engineering and Computer Science." Includes bibliographical references (p. 66-68).

Thesis (M.S.)--University of California, Santa Cruz, 2000. / Typescript. Includes bibliographical references (leaves 54-56).