Computer Sciences Commons^™

Combining Micro And Macro Features For Online Pattern-Of-Life Movement Prediction, Shiau Hong Lim, Hasan Poonawala, Laura Wynter

Research Collection School Of Computing and Information Systems

We investigate the problem of predicting the future location of mobile objects, such as vehicles, ships, or people, in real time with a high degree of accuracy. Our premise is that an effective combination of recent and long-term historical data can significantly improve prediction performance by enabling a representation of the patterns-of-life of the objects. However, finding a feature representation that captures the long-term observed history of the objects in a compact yet informative manner is a key challenge in data mining and machine learning. To this end, we propose to combine “micro” features, which capture recent fine-grained trends, with …

Automatic Generation Of Pull Request Descriptions, Zhongxin Liu, Xin Xia, Christoph Treude, David Lo, Shanping Li

Research Collection School Of Computing and Information Systems

Enabled by the pull-based development model, developers can easily contribute to a project through pull requests (PRs). When creating a PR, developers can add a free-form description to describe what changes are made in this PR and/or why. Such a description is helpful for reviewers and other developers to gain a quick understanding of the PR without touching the details and may reduce the possibility of the PR being ignored or rejected. However, developers sometimes neglect to write descriptions for PRs. For example, in our collected dataset with over 333K PRs, more than 34% of the PR descriptions are empty. …

Revisiting Collaboration Through Mixed Reality: The Evolution Of Groupware, Barrett Ens, Joel Lanir, Anthony Tang, Scott Bateman, Gun Lee, Thammathip Piumsomboon, Mark Billinghurst

Research Collection School Of Computing and Information Systems

Collaborative Mixed Reality (MR) systems are at a critical point in time as they are soon to become more commonplace. However, MR technology has only recently matured to the point where researchers can focus deeply on the nuances of supporting collaboration, rather than needing to focus on creating the enabling technology. In parallel, but largely independently, the field of Computer Supported Cooperative Work (CSCW) has focused on the fundamental concerns that underlie human communication and collaboration over the past 30-plus years. Since MR research is now on the brink of moving into the real world, we reflect on three decades …

Visualizing The Invisible: Occluded Vehicle Segmentation And Recovery, Xiaosheng Yan, Feigege Wang, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan

Research Collection School Of Computing and Information Systems

In this paper, we propose a novel iterative multi-task framework to complete the segmentation mask of an occluded vehicle and recover the appearance of its invisible parts. In particular, firstly, to improve the quality of the segmentation completion, we present two coupled discriminators that introduce an auxiliary 3D model pool for sampling authentic silhouettes as adversarial samples. In addition, we propose a two-path structure with a shared network to enhance the appearance recovery capability. By iteratively performing the segmentation completion and the appearance recovery, the results will be progressively refined. To evaluate our method, we present a dataset, Occluded Vehicle …

Deepmutation++: A Mutation Testing Framework For Deep Learning Systems, Qiang Hu, Lei Ma, Xiaofei Xie, Bing Yu, Yang Liu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Deep neural networks (DNNs) are increasingly expanding their real-world applications across domains, e.g., image processing, speech recognition and natural language processing. However, there is still limited tool support for DNN testing in terms of test data quality and model robustness. In this paper, we introduce a mutation testing-based tool for DNNs, DeepMutation++, which facilitates the DNN quality evaluation, supporting both feed-forward neural networks (FNNs) and stateful recurrent neural networks (RNNs). It not only enables static analysis of the robustness of a DNN model against the input as a whole, but also allows the identification of the vulnerable segments of a …

A Quantitative Analysis Framework For Recurrent Neural Network, Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Yang Liu, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Recurrent neural network (RNN) has achieved great success in processing sequential inputs for applications such as automatic speech recognition, natural language processing and machine translation. However, quality and reliability issues of RNNs make them vulnerable to adversarial attacks and hinder their deployment in real-world applications. In this paper, we propose a quantitative analysis framework — DeepStellar— to pave the way for effective quality and security analysis of software systems powered by RNNs. DeepStellar is generic to handle various RNN architectures, including LSTM and GRU, scalable to work on industrial-grade RNN models, and extensible to develop customized analyzers and tools. We …

Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning, Yan Zheng, Xiaofei Xie, Ting Su, Lei Ma, Jianye Hao, Zhaopeng Meng, Yang Liu, Ruimin Shen, Yingfeng Chen, Changjie Fan

Research Collection School Of Computing and Information Systems

—Game testing has been long recognized as a notoriously challenging task, which mainly relies on manual playing and scripting based testing in game industry. Even until recently, automated game testing still remains to be largely untouched niche. A key challenge is that game testing often requires to play the game as a sequential decision process. A bug may only be triggered until completing certain difficult intermediate tasks, which requires a certain level of intelligence. The recent success of deep reinforcement learning (DRL) sheds light on advancing automated game testing, without human competitive intelligent support. However, the existing DRLs mostly focus …

Safe Inputs Approximation For Black-Box Systems, Bai Xue, Yang Liu, Lei Ma, Xiyue Zhang, Meng Sun, Xiaofei Xie

Research Collection School Of Computing and Information Systems

Given a family of independent and identically distributed samples extracted from the input region and their corresponding outputs, in this paper we propose a method to under-approximate the set of safe inputs that lead the blackbox system to respect a given safety specification. Our method falls within the framework of probably approximately correct (PAC) learning. The computed under-approximation comes with statistical soundness provided by the underlying PAC learning process. Such a set, which we call a PAC under-approximation, is obtained by computing a PAC model of the black-box system with respect to the specified safety specification. In our method, the …

Low-Resource Name Tagging Learned With Weakly Labeled Data, Yixin Cao, Zikun Hu, Tat-Seng Chua, Zhiyuan Liu, Heng Ji

Research Collection School Of Computing and Information Systems

Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can efficiently and robustly pretrain the tag …

Predicting Audience Engagement Across Social Media Platforms In The News Domain, Kholoud Khalil Aldous, Jisun An, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

We analyze cross-platform factors for posts on both single and multiple social media platforms for numerous news outlets to better predict audience engagement, precisely the number of likes and comments. We collect 676,779 social media posts from 53 news outlets during eight months on four social media platforms (Facebook, Instagram, Twitter, and YouTube), along with the associated comments (more than 31 million) and the number of likes (more than 840 million). We develop a framework for predicting the audience engagement based on both linguistic features of the post and social media platform factors. Among other findings, results show that content …

Stylistic Features Usage: Similarities And Differences Using Multiple Social Networks, Kholoud Khalil Aldous, Jisun An, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

User engagement on social networks is essential for news outlets where they often distribute online content. News outlets simultaneously leverage multiple social media platforms to reach their overall audience and to increase marketshare. In this research, we analyze ten common stylistic features indicative of user engagement for news postings on multiple social media platforms. We display the stylistic features usage differences of news posts from various news sources. Results show that there are differences in the usage of stylistic features across social media platforms (Facebook, Instagram, Twitter, and YouTube). Online news outlets can benefit from these findings in building guidelines …

Gender And Racial Diversity In Commercial Brands' Advertising Images On Social Media, Jisun An, Haewoon Kwak

Research Collection School Of Computing and Information Systems

Gender and racial diversity in the mediated images from the media shape our perception of different demographic groups. In this work, we investigate gender and racial diversity of 85,957 advertising images shared by the 73 top international brands on Instagram and Facebook. We hope that our analyses give guidelines on how to build a fully automated watchdog for gender and racial diversity in online advertisements.

Vireojd-Mm @ Trecvid 2019: Activities In Extended Video (Actev), Zhijian Hou, Ying-Wei Pan, Ting Yao, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

In this paper, we describe the system developed for Activities in Extended Video(ActEV) task at TRECVid 2019 [1] and the achieved results. Activities in Extended Video(ActEV): The goal of Activities in Extended Video is to spatially and temporally localize the action instances in a surveillance setting. We have participated in previous ActEV prize challenge. Since the only difference between the two challenges is evaluation metric, we maintain previous pipeline [2] for this challenge. The pipeline has three stages: object detection, tubelet generation and temporal action localization. This time we extend the system for two aspects separately: better object detection and …

Eurecom At Trecvid Avs 2019, Danny Francis, Phuong Anh Nguyen, Benoit Huet, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This notebook reports the model and results of the EURECOM runs at TRECVID AVS 2019.

When Players Affect Target Values: Modeling And Solving Dynamic Partially Observable Security Games, Xinrun Wang, Milind Tambe, Branislav Bosanky, Bo An

Research Collection School Of Computing and Information Systems

Most of the current security models assume that the values of targets/areas are static or the changes (if any) are scheduled and known to the defender. Unfortunately, such models are not sufficient for many domains, where actions of the players modify the values of the targets. Examples include wildlife scenarios, where the attacker can increase value of targets by secretly building supporting facilities. To address such security game domains with player-affected values, we first propose DPOS3G, a novel partially observable stochastic Stackelberg game where target values are determined by the players’ actions; the defender can only partially observe these targets’ …

Characterizing And Predicting Repeat Food Consumption Behavior For Just-In-Time Interventions, Yue Liu, Helena Huey Chong Lee, Palakorn Achananuparp, Ee-Peng Lim, Tzu-Ling Cheng, Shou-De Lin

Research Collection School Of Computing and Information Systems

Human beings are creatures of habit. In their daily life, people tend to repeatedly consume similar types of food items over several days and occasionally switch to consuming different types of items when the consumptions become overly monotonous. However, the novel and repeat consumption behaviors have not been studied in food recommendation research. More importantly, the ability to predict daily eating habits of individuals is crucial to improve the effectiveness of food recommender systems in facilitating healthy lifestyle change. In this study, we analyze the patterns of repeat food consumptions using large-scale consumption data from a popular online fitness community …

Learning-Guided Network Fuzzing For Testing Cyber-Physical System Defences, Yuqi Chen, Chris Poskitt, Jun Sun, Sridhar Adepu, Fan Zhang

Research Collection School Of Computing and Information Systems

The threat of attack faced by cyber-physical systems (CPSs), especially when they play a critical role in automating public infrastructure, has motivated research into a wide variety of attack defence mechanisms. Assessing their effectiveness is challenging, however, as realistic sets of attacks to test them against are not always available. In this paper, we propose smart fuzzing, an automated, machine learning guided technique for systematically finding 'test suites' of CPS network attacks, without requiring any knowledge of the system's control programs or physical processes. Our approach uses predictive machine learning models and metaheuristic search algorithms to guide the fuzzing of …

A Framework For Personalized Content Recommendations To Support Informal Learning In Massively Diverse Information Wikis, Heba M Ismail

Dissertations

Personalization has proved to achieve better learning outcomes by adapting to specific learners’ needs, interests, and/or preferences. Traditionally, most personalized learning software systems focused on formal learning. However, learning personalization is not only desirable for formal learning, it is also required for informal learning, which is self-directed, does not follow a specified curriculum, and does not lead to formal qualifications. Wikis among other informal learning platforms are found to attract an increasing attention for informal learning, especially Wikipedia. The nature of wikis enables learners to freely navigate the learning environment and independently construct knowledge without being forced to follow a …

Artificial Intelligence And The Challenge For Rural Medicine, James Denvir

Marshall Journal of Medicine

Recent advances in artificial intelligence, machine learning, and deep learning are beginning to have an impact on everyday experiences, from natural language processing used in automated telephone call centers to semi-autonomous vehicles. These techniques have also been applied to medical care. In this editorial we discuss applications of AI to medicine and argue for a proactive approach to include rural medicine in this paradigm shift.

Read And Publish: What Can Libraries Expect?, Josh Horowitz

Charleston Library Conference

The author provides a publisher's perspective on the challenges and opportunities faced by a mid-sized society in navigating the current transition to open access licensing models.

Data Curation Workshop: Tips And Tools For Today, Matthew M. Benzing

Charleston Library Conference

The current state of research data is like a disorganized photo collection: a mix of formats scattered across different media without a lot of authority control. That is changing as the need to make data available to researchers across the world is becoming recognized. Researchers know that their data needs to be maintained and made accessible, but often they do not have the time or the inclination to get involved in all of the details. This provides an excellent opportunity for librarians. Data curation is the process of preparing data to be made available in a repository with the goal …

Deepcon-Pre: Improved Protein Contact Map Prediction Using Inverse Covariance And Deep Residual Networks, Nachammai Palaniappan

Theses

As with most domains where machine learning methods are applied, correct feature engineering is critical when developing deep learning algorithms for solving the protein folding problem. Unlike the domains such as computer vision and natural language processing, feature engineering is not rigorously studied towards solving the protein folding problem. A recent research has highlighted that input features known as precision matrix are most informative for predicting inter-residue contact map, the key for building three-dimensional models. In this work, we study the significance of the precision matrix feature when very deep residual networks are trained. Using a standard dataset of 3456 …

Detecting Digitally Forged Faces In Online Videos, Neilesh Sambhu

USF Tampa Graduate Theses and Dissertations

We use Rossler’s FaceForensics dataset of 1004 online videos and their corresponding forged counterparts [1] to investigate the ability to distinguish digitally forged facial images from original images automatically with deep learning. The proposed convolutional neural network is much smaller than the current state-of-the-art solutions. Nevertheless, the network maintains a high level of accuracy (99.6%), all while using the entire FaceForensics dataset and not including any temporal information. We implement majority voting and show the impact on accuracy (99.67%), where only 1 video of 300 is misclassified. We examine why the model misclassified this one video. In terms of tuning …

Interactive Fitness Domains In Competitive Coevolutionary Algorithm, Atm Golam Bari

USF Tampa Graduate Theses and Dissertations

Evolutionary Algorithms (EA) have been successfully applied to a wide range of optimization and search problems where no mathematical model of the quality of a candidate solution is available. Interactive Evolutionary Algorithms (IEA) and Competitive Coevolutionary Algorithms (CCoEA) go one step further by being able to tackle problems where the only means to evaluate the quality of a candidate solution is via interactions. In a typical IEA, interactions take place between the solution being evolved and human evaluators. In a CCoEA, interactions take place between solutions themselves, without need for human interaction. This dissertation identifies computer-aided learning as an application …

Guest Editorial, Jiju Anthony, Chad Laux, Beth Cudney

Faculty Publications

No abstract provided.

Classifying Fiction And Non-Fiction Works Using Machine Learning, Rachna Gupta '21

Student Publications & Research

The objective of this project was to create a program that can determine whether an unknown text is a work of fiction or non-fiction using machine learning. Various datasets of speeches, ebooks, poems, scientific papers, and texts from Project Gutenberg and the Wolfram Example Data were utilized to train and test a Markov Chain machine learning model. A microsite was deployed with the final product that returns a probability of fictionality based on input from the user with 95% accuracy.

Deep Neural Network Based Iterative Self-Taught Learning On Text Mining, Xiangwen Liu

Theses and Dissertations

[Motivation] Machine learning and deep learning models is the main methodology for discovering hidden knowledge of data. Data plays a significant role in the training process. However, lack of data especially labeled data is precious due to accessibility and high cost. How to use the abundant unlabeled data to enhance the downstream learning process on labeled data is an urgent task in machine learning and pattern recognition. [Methods] An STL (Self-taught learning) model is proposed in this dissertation, which can successfully learn features from downloaded unlabeled text and enhance the downstream tasks on labeled text. In addition, DLI-IT (Drug labeling …

Digital Addiction: A Conceptual Overview, Amarjit Kumar Singh, Pawan Kumar Singh

Library Philosophy and Practice (e-journal)

Abstract

Digital addiction referred to an impulse control disorder that involves the obsessive use of digital devices, digital technologies, and digital platforms, i.e. internet, video game, online platforms, mobile devices, digital gadgets, and social network platform. It is an emerging domain of Cyberpsychology (Singh, Amarjit Kumar and Pawan Kumar Singh; 2019), which explore a problematic usage of digital media, device, and platforms by being obsessive and excessive. This article analyses, reviewed the current research, and established a conceptual overview on the digital addiction. The research literature on digital addiction has proliferated. However, we tried to categories the digital addiction, according …

On Automation Of Code Transformations For Concept Inventory Misconceptions, Dmytro Vitel

USF Tampa Graduate Theses and Dissertations

Identifying common misconceptions held by novice programmers is a primary goalof the Computing Education Research agenda. This thesis proposes to formalize such mis-conceptions through program transformations. We first describe the implementation of theEvoParsons system, that allows students to practice programming skills with the help ofso-called Parsons puzzles. This software serves as a tool for gathering data on how studentsinteract with such puzzles. Our first contribution is the system architecture reorganization:development of Web SPA UI, REST service back-end, hypothesis validation infrastructureand student-UI data collection. We then review and compare several code-transformationtools (ANTLR, Rascal MPL and StrategoXT) and show how they might …

Ai Leverage In Easing The 5g Complexity And Enhancing 5g Intelligent Connectivity, Xhafer Krasniqi

UBT International Conference

As 5G era is approaching fast and pre-commercial 5G tests and trials are happening everywhere around the world, one of the key challenges for carriers and 5G providers is to maintain and operate the network complexity required to meet diverse services and personalized user experience requirements. This maintenance and operation have to be smarter and more agile in 5G than it was in previous generations. AI and ML can be leveraged in this case to ease 5G complexity and at the same time enhance the intelligent connectivity between diverse devices and diverse tiny end points, e.g. IoT sensors.

Machine learning …