SEDE 2022:Papers with Abstracts

Abstract. In the field of software development, the processes, technologies, and practices have matured over the time to achieve a higher level of delivery and quality. However, the de- velopment phase, which is an essential part of the software development life cycle (SDLC), is still consuming a significant cost (time and resources) in both approaches, waterfall and agile. The reason behind that, current technologies and approaches of software develop- ment are somehow following the same rules and practices for decades, and have not evolved with the proper velocity over the time. In this article, and based on real-life case studies, we will discuss how the utilization of components re-usability (API’s and frameworks), metadata-driven development, code generation, and Artificial Intelligence can make the software development more efficient by creating a holistic approach to creating software systems.
Abstract. Computational biology scientific software projects are continuously growing and the volume and the task of analyzing, designing, implementing, testing, and maintaining these projects to ensure high-quality software products are only getting harder and more complicated. Conventional software development methodologies are not sufficient in ensuring that scientific software is error-free or up to the standard or comparable to the software designed in the industry. For this reason, it is important to investigate projects that utilized the best software engineering practices during their development and find and understand the problems that arise during the development of those projects. Such understanding will serve as the first step in the process of developing high-quality software products and will enable us to design and propose solutions to the problems that commonly occur during the development of such projects. In this paper, we will discuss different studies that applied software engineering practices and approaches in their computational biology projects. The challenges they encountered and the benefits they gained from employing software engineering quality assurance and testing techniques. In addition, we will demonstrate some of our own experiences when designing, developing, and testing computational biology projects within academic settings. We will also present, based on our experience, some solutions, methodologies, and practices that when adopted will benefit the scientific computational biology software community throughout the process of designing and testing the software.
Abstract. In the current world, the applications of anomaly detection range from fraud detection to diagnosis in the medical area. Most of the current methodologies are applicable only when a particular dataset pertains to certain assumptions and a distinct domain. Such assumptions require prior knowledge of the dataset. The training development cycle time to find the best single model is time-consuming and challenging. Unsupervised anomaly detection methods do not use the target label for training. However, they result in high false positive rates. In this paper, we address the problem of the ensemble anomaly detection approach that generalizes well across multiple domains. We design a multi- level hybrid approach. At the first level, we train several weak classifiers (weak one class classifiers). Next, we utilize deep learning-based AutoEncoder to reduce the dimension of the dataset. These are the two sets of hybrid features. Next, different one-class classifiers have their strength and limitations. Thus, we propose an adaptive weightage approach that gives the weight to each classifier. Next, this input is passed to the second level. At this level, we have a deep neural network that learns the patterns of the dataset and generates an adaptive dynamic threshold to discriminate the input feature as an anomaly or benign. The major benefit of this approach is the low false-positive rate. The training time is reduced due to the reduction of the input feature dimensions at the first level.
Abstract. Intelligent American Sign Language System (IASLS) is a mobile application that allows users to operate their phone or tablet’s camera to capture American Sign Language (ASL) and convert it into text which could later be saved as a note or copied into a text message or document. Text captured from translated finger spelling or full words in ASL can be used to send a message cross-platform to other IASLS users, to take notes in the app, and to help support an in-person conversation between users with ranging abilities. Additionally, users who do not know ASL can use the app’s built-in dictation feature to communicate with people with deafness. IASLS is a mobile application that is designed to facilitate and speed up communication between parties using ASL.
Abstract. Graph-It is a Graph Theory toolbox and graph visualization desktop application for Windows, macOS, and Linux for students, teachers, and researchers, since creating graphs by hand and running graph algorithms repeatedly on the graphs can be time consuming. Users can create graphs, modify graphs, save graphs, and run various graph algorithms on the graphs and view the results. The application is built using Unity, utilizing C# for both the front end and back end. Graph-It aims to provide users an easy-to-use and efficient application for creating and running various algorithms on multiple graphs.
Abstract. The evolution of mobile technology has placed augmented reality (AR) into the hands of previously inaccessible users. AR, which previously required specialized hardware devices, is now capable of running on most smartphones and tablets. Due to the abundance of AR capable devices, the medium is being explored by developers to create novel applications for various purposes, such as entertainment and education. With an ever-growing supply of AR applications, only a minority ever flourish. Through a thorough investigation of fields currently using AR, this paper hypothesizes the following are key features to a successful AR application: safety in the real world, visualization of information, affordances of virtual objects, and the use of a real-world environment. To design quality experiments proficient in evaluating effectiveness of the hypothesized features, a deep dive into exemplary experiment design and subsequent pitfalls was conducted. With this information, this paper presents the methodology of the proposed experiments that yield quantitative feedback for each feature, as well as safety and privacy forms for participants. Once conducted, these experiments will yield results that may impact the future of AR application development.
Abstract. Due to the rapidly evolving nature of the Virtual Reality field, many frameworks for multiuser interaction have become outdated, with few (if any) designed to support mixed virtual and non-virtual interactions. We have developed a framework that lays an exten- sible and forward-looking foundation for mixed interactions based upon a novel method of ensuring that inputs, visuals, and networking can all communicate without needing to understand the others’ internals. We tested this framework in the development of several applications and proved that it can easily be adapted to support application requirements it was not originally designed for.
Abstract. Virtual Reality (VR) has existed for many years; however, it has only recently gained wide spread popularity and commercial use. This change comes from the innovations in head mounted displays (HMDs) and from the work of many software engineers making quality user experiences (UX). In this work we present a brief history, current research areas, and areas for improvement in virtual reality
Abstract. Augmented reality (AR) devices are becoming more prevalent and powerful enough to allow more virtual agents to be run simultaneously. This paper explores the ideal frequency to update the control logic for each virtual agent using the framerate as a measurement. This paper details the averaged result of a stair-step confidence test that was run five times for each frequency. This experiment was run on the Microsoft HoloLens 2.