Artificial Intelligence and Robotics Commons^™

Any-Shot Object Detection, Shafin Rahman, Salman Khan, Nick Barnes, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Previous work on novel object detection considers zero or few-shot settings where none or few examples of each category are available for training. In real world scenarios, it is less practical to expect that ‘all’ the novel classes are either unseen or have few-examples. Here, we propose a more realistic setting termed ‘Any-shot detection’, where totally unseen and few-shot categories can simultaneously co-occur during inference. Any-shot detection offers unique challenges compared to conventional novel object detection such as, a high imbalance between unseen, few-shot and seen object classes, susceptibility to forget base-training while learning novel classes and distinguishing novel classes …

Treatment Effects Of Modafinil For Cocaine Use Disorders: A Retrospective Analysis Of Aggregated Clinical Trial Data From Three Cocaine Treatment Studies, Daniel Ruskin

Honors Scholar Theses

Approximately 913,000 individuals in the United States meet the diagnostic criteria for cocaine use disorder (CUD). The widespread usage of cocaine, along with the negative cardiac and neurological effects associated with the drug, has made cocaine one of the top three drugs associated with overdose deaths in the United States. This epidemic has brought cocaine dependency into the public spotlight and has prompted extensive research into treatment strategies. However, at the time of writing, no drugs have been approved by the United States Food and Drug Administration (FDA) for use in treating CUD. The purpose of this study is to …

Some Advice For Psychologists Who Want To Work With Computer Scientists On Big Data, Cornelius J. König, Andrew M. Demetriou, Philipp Glock, Annemarie M. F. Hiemstra, Dragos Iliescu, Camelia Ionescu, Markus Langer, Cynthia C. S. Liem, Anja Linnenbürger, Rudolf Siegel, Ilias Vartholomaios

Personnel Assessment and Decisions

This article is based on conversations from the project “Big Data in Psychological Assessment” (BDPA) funded by the European Union, which was initiated because of the advances in data science and artificial intelligence that offer tremendous opportunities for personnel assessment practice in handling and interpreting this kind of data. We argue that psychologists and computer scientists can benefit from interdisciplinary collaboration. This article aims to inform psychologists who are interested in working with computer scientists about the potentials of interdisciplinary collaboration, as well as the challenges such as differing terminologies, foci of interest, data quality standards, approaches to data analyses, …

A New Ectotherm 3d Tracking And Behavior Analytics System Using A Depth-Based Approach With Color Validation, With Preliminary Data On Kihansi Spray Toad (Nectophrynoides Asperginis) Activity, Philip Bal, Damian Lyons, Avishai Shuter

Faculty Publications

The Kihansi spray toad (Nectophrynoides asperginis), classified as Extinct in the Wild by the IUCN, is being bred at the Wildlife Conservation Society’s (WCS) Bronx Zoo as part of an effort to successfully reintroduce the species into the wild. Thousands of toads live at the Bronx Zoo presenting an opportunity to learn more about their behaviors for the first time, at scale. It is impractical to perform manual observations for long periods of time. This paper reports on the development of a RGB-D tracking and analytics approach that allows researchers to accurately and efficiently gather information about the toads’ behavior. …

Algorithm Selection Framework: A Holistic Approach To The Algorithm Selection Problem, Marc W. Chalé

Theses and Dissertations

A holistic approach to the algorithm selection problem is presented. The “algorithm selection framework" uses a combination of user input and meta-data to streamline the algorithm selection for any data analysis task. The framework removes the conjecture of the common trial and error strategy and generates a preference ranked list of recommended analysis techniques. The framework is performed on nine analysis problems. Each of the recommended analysis techniques are implemented on the corresponding data sets. Algorithm performance is assessed using the primary metric of recall and the secondary metric of run time. In six of the problems, the recall of …

Artificial Agents In Corporate Boardrooms, Sergio Alberto Gramitto Ricci

Faculty Works

Thousands of years ago, Roman businessmen often ran joint businesses through commonly owned, highly intelligent slaves. Roman slaves did not have full legal capacity and were considered property of their co-owners. Now business corporations are looking to delegate decision-making to uber intelligent machines through the use of artificial intelligence in boardrooms. Artificial intelligence in boardrooms could assist, integrate, or even replace human directors. However, the concept of using artificial intelligence in boardrooms is largely unexplored and raises several issues. This Article sheds light on legal and policy challenges concerning artificial agents in boardrooms. The arguments revolve around two fundamental questions: …

Pedestrian Navigation Using Artificial Neural Networks And Classical Filtering Techniques, David J. Ellis

Theses and Dissertations

The objective of this thesis is to explore the improvements achieved through using classical filtering methods with Artificial Neural Network (ANN) for pedestrian navigation techniques. ANN have been improving dramatically in their ability to approximate various functions. These neural network solutions have been able to surpass many classical navigation techniques. However, research using ANN to solve problems appears to be solely focused on the ability of neural networks alone. The combination of ANN with classical filtering methods has the potential to bring beneficial aspects of both techniques to increase accuracy in many different applications. Pedestrian navigation is used as a …

Artificial Intelligence: A New Paradigm In Obstetrics And Gynecology Research And Clinical Practice, Pulwasha Iftikhar, Marcela V. Kuijpers, Azadeh Khayyat, Aqsa Iftikhar, Maribel Degouvia De Sa

Publications and Research

Artificial intelligence (AI) is growing exponentially in various fields, including medicine. This paper reviews the pertinent aspects of AI in obstetrics and gynecology (OB/GYN) and how these can be applied to improve patient outcomes and reduce the healthcare costs and workload for clinicians.

Herein, we will address current AI uses in OB/GYN, and the use of AI as a tool to interpret fetal heart rate (FHR) and cardiotocography (CTG) to aid in the detection of preterm labor, pregnancy complications, and review discrepancies in its interpretation between clinicians to reduce maternal and infant morbidity and mortality. AI systems can be used …

Improving Ocr Accuracy Of Damaged Pictures With Generative Adversarial Networks, Pu Du

LSU Master's Theses

In this thesis, we focus on resolving the inpainting problem and improving Optical Character Recognition (OCR) accuracy of damaged text images at character level. We present a Generative Adversarial Network (GAN)-based model conditioned on class labels for image inpainting. This model is a deep convolutional neural network with encoder-decoder style architecture which can process images with holes at random locations. Experiments on the character images dataset demonstrate that our proposed model generates promising inpainting results and significantly improve OCR accuracy by reconstructing missing parts of damaged character images.

Cyber-Physical Security With Rf Fingerprint Classification Through Distance Measure Extensions Of Generalized Relevance Learning Vector Quantization, Trevor J. Bihl, Todd J. Paciencia, Kenneth W. Bauer Jr., Michael A. Temple

Faculty Publications

Radio frequency (RF) fingerprinting extracts fingerprint features from RF signals to protect against masquerade attacks by enabling reliable authentication of communication devices at the “serial number” level. Facilitating the reliable authentication of communication devices are machine learning (ML) algorithms which find meaningful statistical differences between measured data. The Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier is one ML algorithm which has shown efficacy for RF fingerprinting device discrimination. GRLVQI extends the Learning Vector Quantization (LVQ) family of “winner take all” classifiers that develop prototype vectors (PVs) which represent data. In LVQ algorithms, distances are computed between exemplars and PVs, and …

Demand Forecasting Of Wartime Spares Based On Evidence Theory, Yunjing Zhang, Xinxin Wang, Wang Yang, Guangming Tang

Journal of System Simulation

Abstract: A new method based on evidence theory is proposed to solve the lack of data for the demand prediction of spares in wartime. Utilizing Markov chain model to research the rule of spares demand of peacetime from the historical data. A Markov chain transfer probability adjustment strategy, based on the change of combat intensity, is designed, which can be used to simulation the rule of spares demand in wartime. Under the experience of experts and the combination of the Fuzzy theory and evidence theory, the spares demand is wartime is forecasted. The simulation example shows that the …

Moea/D Algorithm Based On The Hybrid Framework For Multi-Objective Evolutionary Algorithm, Hongjun Tian, Wang Lei, Qidi Wu

Journal of System Simulation

Abstract: Aimto the difficulties of designing the bonding mechanism of global optimization algorithm and local search strategy for hybrid multi-objective evolutionary algorithm, and of improving the performance of multi-objective evolutionary algorithms, based on the feedback control idea, a systematic and modular hybrid MOEA/D algorithm combining the global optimization and local search is proposed. In the algorithm, a diversity measure method based on crowded entropy is designed; a local search strategy based on simplified quadratic approximation and population diversity enhancement strategy for MOEA/D is proposed. The numerical experiments show that the proposed HMOEA/D can achieve a balance between diversity …

Tele-Robot Control System With Online Virtual Simulation Prediction, Lingyan Hu, Kangbai Shi, Bichun Zhang, Shaoping Xu

Journal of System Simulation

Abstract: When a tele-robot with virtual simulation system works in a complicated environment, the virtual scene may not synchronize with the real one. This may cause the operator on the master side to give wrong instruction. This paper presents a tele-robot with online virtual model correction. The virtual simulation system on the master side builds a virtual model of environment and robot on the slave side. It predicts the motion of the slave robot in real time according the commands from the operator. In order to ensure the virtual scene synchronize with the real one, the measured data on the …

Research On Cavitation Evolution Model In Venturi Tube, Guihua Han, Yanan Liu, Junpeng Shao, Cijun Zhang

Journal of System Simulation

Abstract: The dynamic cavitation model of venturi tube air-water two-phase flow was established according to the time variation of air precipitation and digestion process in water. FLUENT three-dimension numerical simulation were studied to simulate the air-water two-phase flow, and the variation law of venturi tube throat diameter and inlet pressure on vapor volume fraction were obtained. The results of numerical simulation and experiments show that the vapor volume fraction increases following the increase of the inlet pressure. If the throat diameter is increased, the inlet pressure can be increased as the compensation to achieve the same cavitation effect. The …

Self-Organizing Aggregation Behavior Modeling Of Swarm Robots Based On Ant Colony Algorithm, Yang Wei, Zeng Liang, Xinchen Kang

Journal of System Simulation

Abstract: Aiming at the formation of aggregation behavior model of swarm robots, a self-organizing motion model based on particle system mechanics and perceptual state weighting is established to realize the autonomous transfer of robot motion state. The aggregation degree and uniformity index of aggregation behavior are established, and the aggregation performances of different models are analyzed by experiment, which lay a foundation for the formation of self-organized aggregation behavior model of swarm robots. Using the selected model, the self-organizing aggregation behavior simulation experiments are conducted in two cases with boundary constraints and no boundary constraints. The maximum coverage of …

Auv Vertical Plane Control Based On Improved Pid Neural Network Algorithm, Runan Huang, Ding Ning

Journal of System Simulation

Abstract: An improved PID neural network controller is designed for the movement control of a small low-speed autonomous underwater vehicle (AUV) in vertical plane, and the global control of the depth and pitch angle of the underwater vehicle in vertical plane is obtained. The AUV simulation control system is built by using REMUS underwater vehicle model in Simulink. The simulation results show that the improved control method with better dynamic performance has solved the original excessive saturation issue, and can adapt to different learning rates and network initial weight,and is of certain reference value to the practical application …

Integrated Simulation Test Platform For Environment Perception And Planning Decision Of Intelligent Vehicle, Sun Jian, Runhan Huang, Li Lin, Qiyuan Liu, Yudi Li

Journal of System Simulation

Abstract: The simplicity of testing modules and the lack of high-fidelity and high-density traffic scenes are the primary issues in the intelligent vehicle' simulation test. To solve these problems, a "software in the loop" integration test platform is built. The environmental perception module is integrated on the basis of the PreScan, the planning decision-making module designed by MATLAB/Simulink and the virtual traffic flow environment from Vissim. Based on this platform, high-fidelity traffic flow scenes can be generated rapidly to support the test of environment perception and decision-making integratedly and effectively. Moreover, the intelligent vehicle's influence on the traffic flow …

Research On Motion Cueing Algorithm Based On Vr Motion Simulator, Xiaolu Li, Jianfeng Yan, Cangsu Xu, Zongming Wu, Yuanhui Zhang, Junjiang Zhu

Journal of System Simulation

Abstract: Aiming at the phase delay and the false suggest of the classical motion-sensing simulation algorithm in VR motion simulator that lead to insufficient consistency between virtual and real movement and cause VR motion sickness disease, an improved motion-sensing simulation algorithm is proposed. Based on the classical simulation algorithm, the algorithm compromises the vestibular sensory system, feeds back the output error, and applies the fuzzy control algorithm to modify and forecast the input acceleration and angular velocity. This improved motion-sensing simulation algorithm is trained in the condition of virtual choppy terrain. The MATLAB/Simulink simulation results show that the improved motion-sensing …

Cascade Transmission Evaluation Of Ecosystem Damage Caused By Dust Migration, Guangqiu Huang, He Tong, Qiuqin Lu

Journal of System Simulation

Abstract: To solve the cascade transmission evaluation of ecosystem damage caused by dust migration in mining area, the migration network is constructed by dust migration path, and the potential hazard source path is identified. The definition of Petri-net simulation model of ecosystem damage with cascade propagation (PN-EDCP) is given, and the general method of abstracting migration paths network into a Petri net model is expounded. By introducing the concepts of attributes and methods of place objects into Petri net model, the real meaning of the model is clear, and the ability of describing and analyzing the logical relationship between ecosystem …

Control Improvement And Simulation Of Dfig Under Power Grid Failure, Hongyang Zhang, Zhentang Shi, Zhifeng Zhang

Journal of System Simulation

Abstract: Following the increasing scale of installed wind power, the wind turbines, as an important part of the future energy internet, its ability to cope with the fault of the power grid becomes more and more important. Aiming at the transient characteristics of doubly fed induction generator (DFIG) under power grid fault, a comprehensive control strategy, based on the classification of power grid faults, the optimization of controller parameters and auxiliary equipments, is proposed. Compared with the traditional control method, the large control error and response lag is overcome, and the fine control is realized. Based on MATLAB and VC++ …