Artificial Intelligence and Robotics Commons^™

Understanding And Predicting Retractions Of Published Work, Sai Ajay Modukuri, Sarah Rajtmajer, Anna Cinzia Squicciarini, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Recent increases in the number of retractions of published papers reflect heightened attention and increased scrutiny in the scientific process motivated, in part, by the replication crisis. These trends motivate computational tools for understanding and assessment of the scholarly record. Here, we sketch the landscape of retracted papers in the Retraction Watch database, a collection of 19k records of published scholarly articles that have been retracted for various reasons (e.g., plagiarism, data error). Using metadata as well as features derived from full-text for a subset of retracted papers in the social and behavioral sciences, we develop a random forest classifier …

Extractive Research Slide Generation Using Windowed Labeling Ranking, Athar Sefid, Prasenjit Mitra, Jian Wu, C. Lee Giles

Computer Science Faculty Publications

Presentation slides generated from original research papers provide an efficient form to present research innovations. Manually generating presentation slides is labor-intensive. We propose a method to automatically generates slides for scientific articles based on a corpus of 5000 paper-slide pairs compiled from conference proceedings websites. The sentence labeling module of our method is based on SummaRuNNer, a neural sequence model for extractive summarization. Instead of ranking sentences based on semantic similarities in the whole document, our algorithm measures the importance and novelty of sentences by combining semantic and lexical features within a sentence window. Our method outperforms several baseline methods …

Partial Adversarial Behavior Deception In Security Games, Thanh H. Nguyen, Arunesh Sinha, He He

Research Collection School Of Computing and Information Systems

Learning attacker behavior is an important research topic in security games as security agencies are often uncertain about attackers’ decision making. Previous work has focused on developing various behavioral models of attackers based on historical attack data. However, a clever attacker can manipulate its attacks to fail such attack-driven learning, leading to ineffective defense strategies. We study attacker behavior deception with three main contributions. First, we propose a new model, named partial behavior deception model, in which there is a deceptive attacker (among multiple attackers) who controls a portion of attacks. Our model captures real-world security scenarios such as wildlife …

Scalable Online Vetting Of Android Apps For Measuring Declared Sdk Versions And Their Consistency With Api Calls, Daoyuan Wu, Debin Gao, David Lo

Research Collection School Of Computing and Information Systems

Android has been the most popular smartphone system with multiple platform versions active in the market. To manage the application’s compatibility with one or more platform versions, Android allows apps to declare the supported platform SDK versions in their manifest files. In this paper, we conduct a systematic study of this modern software mechanism. Our objective is to measure the current practice of declared SDK versions (which we term as DSDK versions afterwards) in real apps, and the (in)consistency between DSDK versions and their host apps’ API calls. To successfully analyze a modern dataset of 22,687 popular apps (with an …

A Continual Deepfake Detection Benchmark: Dataset, Methods, And Essentials, Chuqiao Li, Zhiwu Huang, Danda Pani Paudel, Yabin Wang, Mohamad Shahbazi, Xiaopeng Hong, Van Gool Luc

Research Collection School Of Computing and Information Systems

There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, …

Cybersecurity Leaders: Knowledge Driving Human Capital Development, Sharon L. Burton

Publications

Cybersecurity leaders must be able to use critical reading and thinking skills, exercise judgment when policies are not distinct and precise, and have the knowledge, skills, and abilities to tailor technical and planning data to diverse customers’ levels of understanding. Ninety-three percent of cybersecurity leaders do not report directly to the chief operating officer. While status differences influence interactions amid groups, attackers are smarter. With the aim of protecting organizations and reducing risk, knowledge about security must increase. Understanding voids are costly and increased breach chances are imminent. Burning questions exist. What are needed technological learnings for cybersecurity leaders to …

Binary Black Widow Optimization Algorithm For Feature Selection Problems, Ahmed Al-Saedi

Theses and Dissertations (Comprehensive)

This thesis addresses feature selection (FS) problems, which is a primary stage in data mining. FS is a significant pre-processing stage to enhance the performance of the process with regards to computation cost and accuracy to offer a better comprehension of stored data by removing the unnecessary and irrelevant features from the basic dataset. However, because of the size of the problem, FS is known to be very challenging and has been classified as an NP-hard problem. Traditional methods can only be used to solve small problems. Therefore, metaheuristic algorithms (MAs) are becoming powerful methods for addressing the FS problems. …

Single And Differential Morph Attack Detection, Baaria Chaudhary

Graduate Theses, Dissertations, and Problem Reports (ETD)

Face recognition systems operate on the assumption that a person's face serves as the unique link to their identity. In this thesis, we explore the problem of morph attacks, which have become a viable threat to face verification scenarios precisely because of their inherent ability to break this unique link. A morph attack occurs when two people who share similar facial features morph their faces together such that the resulting face image is recognized as either of two contributing individuals. Morphs inherit enough visual features from both individuals that both humans and automatic algorithms confuse them. The contributions of this …

Identification And Classification Of Radio Pulsar Signals Using Machine Learning, Di Pang

Graduate Theses, Dissertations, and Problem Reports (ETD)

Automated single-pulse search approaches are necessary as ever-increasing amount of observed data makes the manual inspection impractical. Detecting radio pulsars using single-pulse searches, however, is a challenging problem for machine learning because pul- sar signals often vary significantly in brightness, width, and shape and are only detected in a small fraction of observed data.

The research work presented in this dissertation is focused on development of ma- chine learning algorithms and approaches for single-pulse searches in the time domain. Specifically, (1) We developed a two-stage single-pulse search approach, named Single- Pulse Event Group IDentification (SPEGID), which automatically identifies and clas- …

Zero-Shot Action Recognition With Knowledge Enhanced Generative Adversarial Networks, Kaiqiang Huang, Luis Miralles-Pechuán, Susan Mckeever

Conference papers

Zero-Shot Action Recognition (ZSAR) aims to recognise action classes in videos that have never been seen during model training. In some approaches, ZSAR has been achieved by generating visual features for unseen classes based on the semantic information of the unseen class labels using generative adversarial networks (GANs). Therefore, the problem is converted to standard supervised learning since the unseen visual features are accessible. This approach alleviates the lack of labelled samples of unseen classes. In addition, objects appearing in the action instances could be used to create enriched semantics of action classes and therefore, increase the accuracy of ZSAR. …

K-Nearest Neighbour Classifiers - A Tutorial, Padraig Cunningham, Sarah Jane Delany

Conference papers

Perhaps the most straightforward classifier in the arsenal or Machine Learning techniques is the Nearest Neighbour Classifier – classification is achieved by identifying the nearest neighbours to a query example and using those neighbours to determine the class of the query. This approach to classification is of particular importance because issues of poor run-time performance is not such a problem these days with the computational power that is available. This paper presents an overview of techniques for Nearest Neighbour classification focusing on; mechanisms for assessing similarity (distance), computational issues in identifying nearest neighbours and mechanisms for reducing the dimension of …

Light Field Compression And Manipulation Via Residual Convolutional Neural Network, Eisa Hedayati

Dissertations, Master's Theses and Master's Reports

Light field (LF) imaging has gained significant attention due to its recent success in microscopy, 3-dimensional (3D) displaying and rendering, augmented and virtual reality usage. Postprocessing of LF enables us to extract more information from a scene compared to traditional cameras. However, the use of LF is still a research novelty because of the current limitations in capturing high-resolution LF in all of its four dimensions. While researchers are actively improving methods of capturing high-resolution LF's, using simulation, it is possible to explore a high-quality captured LF's properties. The immediate concerns following the LF capture are its storage and processing …

Modeling Human Visual Detection Using Deep Networks, Zach Dekraker

Dissertations, Master's Theses and Master's Reports

The work in this report describes the use of machine learning to model human visual detection. This is in contrast to typical machine learning models, which seek to optimize detection performance overall, e.g., precision versus recall or F1 scores. Instead the goal is to develop models that can accurately match humans' abilities to detect objects in images. There are many AI algorithms that have far surpassed humans in, for example, object detection in large image databases or games such as Go. What is different about this work is that the objective is to accurately model humans' performance in visual detection …

Interpretable, Not Black-Box, Artificial Intelligence Should Be Used For Embryo Selection, Michael Anis Mihdi Afnan, Yanhe Liu, Vincent Conitzer, Cynthia Rudin, Abhishek Mishra, Julian Savulescu, Masoud Afnan

Research outputs 2014 to 2021

Artificial intelligence (AI) techniques are starting to be used in IVF, in particular for selecting which embryos to transfer to the woman. AI has the potential to process complex data sets, to be better at identifying subtle but important patterns, and to be more objective than humans when evaluating embryos. However, a current review of the literature shows much work is still needed before AI can be ethically implemented for this purpose. No randomized controlled trials (RCTs) have been published, and the efficacy studies which exist demonstrate that algorithms can broadly differentiate well between ‘good-’ and ‘poor-’ quality embryos but …

Development Of A Real Time Human Face Recognition Software System, Askar Boranbayev, Seilkhan Boranbayev, Mukhamedzhan Amirtaev, Malik Baimukhamedov, Askar Nurbekov

Physics & Astronomy Faculty Publications

In this study, a system for real-time face recognition was built using the Open Face tools of the Open CV library. The article describes the methodology for creating the system and the results of its testing. The Open CV library has various modules that perform many tasks. In this paper, Open CV modules were used for face recognition in images and face identification in real time. In addition, the HOG method was used to detect a person by the front of his face. After performing the HOG method, 128 face measurements were obtained using the image encoding method. A convolutional …

A Deep Machine Learning Approach For Predicting Freeway Work Zone Delay Using Big Data, Abdullah Shabarek

Dissertations

The introduction of deep learning and big data analytics may significantly elevate the performance of traffic speed prediction. Work zones become one of the most critical factors causing congestion impact, which reduces the mobility as well as traffic safety. A comprehensive literature review on existing work zone delay prediction models (i.e., parametric, simulation and non-parametric models) is conducted in this research. The research shows the limitations of each model. Moreover, most previous modeling approaches did not consider user delay for connected freeways when predicting traffic speed under work zone conditions. This research proposes Deep Artificial Neural Network (Deep ANN) and …

Inexact Tensor Methods And Their Application To Stochastic Convex Optimization, Artem Agafonov, Dmitry Kamzolov, Pavel Dvurechensky, Alexander Gasnikov, Martin Takac

Machine Learning Faculty Publications

We propose general non-accelerated and accelerated tensor methods under inexact information on the derivatives of the objective, analyze their convergence rate. Further, we provide conditions for the inexactness in each derivative that is sufficient for each algorithm to achieve a desired accuracy. As a corollary, we propose stochastic tensor methods for convex optimization and obtain sufficient mini-batch sizes for each derivative. © 2020, CC BY.

Distributed Load Testing By Modeling And Simulating User Behavior, Chester Ira Parrott

LSU Doctoral Dissertations

Modern human-machine systems such as microservices rely upon agile engineering practices which require changes to be tested and released more frequently than classically engineered systems. A critical step in the testing of such systems is the generation of realistic workloads or load testing. Generated workload emulates the expected behaviors of users and machines within a system under test in order to find potentially unknown failure states. Typical testing tools rely on static testing artifacts to generate realistic workload conditions. Such artifacts can be cumbersome and costly to maintain; however, even model-based alternatives can prevent adaptation to changes in a system …

A Neat Approach To Malware Classification, Jason Do

Master's Projects

Current malware detection software often relies on machine learning, which is seen as an improvement over signature-based techniques. Problems with a machine learning based approach can arise when malware writers modify their code with the intent to evade detection. This leads to a cat and mouse situation where new models must constantly be trained to detect new malware variants. In this research, we experiment with genetic algorithms as a means of evolving machine learning models to detect malware. Genetic algorithms, which simulate natural selection, provide a way for models to adapt to continuous changes in a malware families, and thereby …

Pyxtal_Ff: A Python Library For Automated Force Field Generation, Howard Yanxon, David Zagaceta, Binh Tang, David S. Matteson, Qiang Zhu

Physics & Astronomy Faculty Research

We present PyXtal_FF—a package based on Python programming language—for developing machine learning potentials (MLPs). The aim of PyXtal_FF is to promote the application of atomistic simulations through providing several choices of atom-centered descriptors and machine learning regressions in one platform. Based on the given choice of descriptors (including the atom-centered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal_FF can train MLPs with either generalized linear regression or neural network models, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from ab-initio simulations. The trained MLP model from PyXtal_FF is interfaced with …