Artificial Intelligence and Robotics Commons^™

Research On Generation Technology Of Computer Generated Force In Lvc Training System, Gao Ang, Zhiming Dong, Guohui Zhang, Liang Tao, Qisheng Guo

Journal of System Simulation

Abstract: LVC training system of the combat equipment under the condition of confrontation is an effective means of training, aiming at the problem that in LVC training system, computer generated forces are difficult to meet the demand of training problems. The concept of LVC training and LVC training system is clarified, according to the relationship between model and system structure, the corresponding modeling technology requirements of three different hierarchical models, namely logical range entity configuration, command entity and combat entity, are expounded. According to the specific requirements, four computer-generated force generation methods are proposed, namely, logical target range virtual and …

Exploring The Use Of Neural Transformers For Psycholinguistics, Antonio Laverghetta Jr.

USF Tampa Graduate Theses and Dissertations

Deep learning has the potential to help solve numerous problems in cognitive science andeducation, by providing us a way to model the cognitive profiles of individual people. If this were possible, it would allow us to design targeted tests and suggest specific remediation based on each individual’s needs. On the flip side, employing techniques from psychology can give us insight into the underlying skillsets neural networks have acquired during training, addressing the interpretability concern. This thesis explores these ideas in the context of transformer language models, which have achieved state-of-the-art results on virtually every natural language processing (NLP) task. First, …

A Deep Learning Approach To Diagnostic Classification Of Prostate Cancer Using Pathology–Radiology Fusion, Pegah Khosravi, Maria Lysandrou, Mahmoud Eljalby, Qianzi Li, Ehsan Kazemi, Pantelis Zisimopoulos, Alexandros Sigaras, Matthew Brendel, Josue Barnes, Camir Ricketts, Dmitry Meleshko, Andy Yat, Timothy D. Mcclure, Brian D. Robinson, Andrea Sboner, Olivier Elemento, Bilal Chughtai, Iman Hajirasouliha

Publications and Research

Background

A definitive diagnosis of prostate cancer requires a biopsy to obtain tissue for pathologic analysis, but this is an invasive procedure and is associated with complications.

Purpose

To develop an artificial intelligence (AI)-based model (named AI-biopsy) for the early diagnosis of prostate cancer using magnetic resonance (MR) images labeled with histopathology information.

Study Type

Retrospective.

Population

Magnetic resonance imaging (MRI) data sets from 400 patients with suspected prostate cancer and with histological data (228 acquired in-house and 172 from external publicly available databases).

Field Strength/Sequence

1.5 to 3.0 Tesla, T2-weighted image pulse sequences.

Assessment

MR images reviewed and selected …

Wider Vision: Enriching Convolutional Neural Networks Via Alignment To External Knowledge Bases, Xuehao Liu, Sarah Jane Delany, Susan Mckeever

Conference papers

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of hidden feature map activations is limited by the discriminative knowledge gleaned during training. The aim of our work is to explain and expand CNNs models via the mirroring or alignment of the network to an external knowledge base. This will allow us to give a semantic context or label for each visual feature. Using the resultant aligned embedding space, we can match CNN feature activations to nodes …

Cyclic Pursuit, Daniel E. Oke

Theses and Dissertations

This thesis analyzes cyclic pursuit with the intent of developing swarm attack strategies for autonomous agents. Research was focused on finding the effects of pursuers capture range, evader speed and size of formation on the probability of escape. The temporal evolution of several polygonal formations was analyzed. The polygons could be regular or arbitrary polygons. The thesis demonstrated that an increased capture range, formation size, reduced evader speed aided capture probability. Irregular n-gon formations reduced to n-1 gon repeatedly, pursuer clusters formed until two clusters remained which eventually came together, so all the n pursuers coalesced until convergence. Regular n-gon …

Node Classification On Relational Graphs Using Deep-Rgcns, Nagasai Chandra

Master's Theses

Knowledge Graphs are fascinating concepts in machine learning as they can hold usefully structured information in the form of entities and their relations. Despite the valuable applications of such graphs, most knowledge bases remain incomplete. This missing information harms downstream applications such as information retrieval and opens a window for research in statistical relational learning tasks such as node classification and link prediction. This work proposes a deep learning framework based on existing relational convolutional (R-GCN) layers to learn on highly multi-relational data characteristic of realistic knowledge graphs for node property classification tasks. We propose a deep and improved variant, …

Wg2An: Synthetic Wound Image Generation Using Generative Adversarial Network, Salih Sarp, Murat Kuzlu, Emmanuel Wilson, Ozgur Guler

Engineering Technology Faculty Publications

In part due to its ability to mimic any data distribution, Generative Adversarial Network (GAN) algorithms have been successfully applied to many applications, such as data augmentation, text-to-image translation, image-to-image translation, and image inpainting. Learning from data without crafting loss functions for each application provides broader applicability of the GAN algorithm. Medical image synthesis is also another field that the GAN algorithm has great potential to assist clinician training. This paper proposes a synthetic wound image generation model based on GAN architecture to increase the quality of clinical training. The proposed model is trained on chronic wound datasets with various …

How Do Users Answer Matlab Questions On Q&A Sites? A Case Study On Stack Overflow And Mathworks, Mahshid Naghashzadeh, Amir Hagshenas, Ashkan Sami, David Lo

Research Collection School Of Computing and Information Systems

MATLAB is an engineering programming language with various toolboxes that has a dedicated Question and Answer (Q&A) platform on the MathWorks website, which is similar to Stack Overflow (SO). Moreover, some MATLAB users ask their questions on SO. This paper aims to compare these two Q&A platforms to see what kind of questions are asked and how developers answer these questions in each platform. The result of our analysis on 80,382 MATLAB questions on SO and 266,367 questions on MathWorks show that MATLAB questions on topics ranging from the MATLAB software installation to questions related to programming received high votes …

Is The Ground Truth Really Accurate? Dataset Purification For Automated Program Repair, Deheng Yang, Yan Lei, Xiaoguang Mao, David Lo, Huan Xie, Meng Yan

Research Collection School Of Computing and Information Systems

Datasets of real-world bugs shipped with human-written patches are intensively used in the evaluation of existing automated program repair (APR) techniques, wherein the human-written patches always serve as the ground truth, for manual or automated assessment approaches, to evaluate the correctness of test-suite adequate patches. An inaccurate human-written patch tangled with other code changes will pose threats to the reliability of the assessment results. Therefore, the construction of such datasets always requires much manual effort on isolating real bug fixes from bug fixing commits. However, the manual work is time-consuming and prone to mistakes, and little has been known on …

Learning To Assess The Quality Of Stroke Rehabilitation Exercises, Min Hun Lee, Daniel P. Siewiorek, Asim Smailagic, Alexandre Bernardino, Sergi Bermúdez I Badia

Research Collection School Of Computing and Information Systems

Due to the limited number of therapists, task-oriented exercises are often prescribed for post-stroke survivors as in-home rehabilitation. During in-home rehabilitation, a patient may become unmotivated or confused to comply prescriptions without the feedback of a therapist. To address this challenge, this paper proposes an automated method that can achieve not only qualitative, but also quantitative assessment of stroke rehabilitation exercises. Specifically, we explored a threshold model that utilizes the outputs of binary classifiers to quantify the correctness of a movements into a performance score. We collected movements of 11 healthy subjects and 15 post-stroke survivors using a Kinect sensor …

Low-Cost Terrestrial Demonstration Of Autonomous Satellite Proximity Operations, Zackary R. Hewitt

Theses and Dissertations

The lack of satellite servicing capabilities significantly impacts the development and operation of current orbital assets. With autonomous solutions under consideration for servicing, the purpose of this research is to build and validate a low-cost hardware platform to expedite the development of autonomous satellite proximity operations. This research aims to bridge the gap between simulation and existing higher fidelity hardware testing with an affordable alternative. An omnidirectional variant of the commercially available TurtleBot3 mobile robot is presented as a 3-DOF testbed that demonstrates a satellite servicing inspection scenario. Reference trajectories for the scenario are generated via optimal control using the …

Brain Tumor Detection And Classification From Mri Images, Anjaneya Teja Sarma Kalvakolanu

Master's Theses

A brain tumor is detected and classified by biopsy that is conducted after the brain surgery. Advancement in technology and machine learning techniques could help radiologists in the diagnosis of tumors without any invasive measures. We utilized a deep learning-based approach to detect and classify the tumor into Meningioma, Glioma, Pituitary tumors. We used registration and segmentation-based skull stripping mechanism to remove the skull from the MRI images and the grab cut method to verify whether the skull stripped MRI masks retained the features of the tumor for accurate classification. In this research, we proposed a transfer learning based approach …

Deep Learning For Anomaly Detection: Challenges, Methods, And Opportunities, Guansong Pang, Longbing Cao, Charu Aggarwal

Research Collection School Of Computing and Information Systems

In this tutorial we aim to present a comprehensive survey of the advances in deep learning techniques specifically designed for anomaly detection (deep anomaly detection for short). Deep learning has gained tremendous success in transforming many data mining and machine learning tasks, but popular deep learning techniques are inapplicable to anomaly detection due to some unique characteristics of anomalies, e.g., rarity, heterogeneity, boundless nature, and prohibitively high cost of collecting large-scale anomaly data. Through this tutorial, audiences would gain a systematic overview of this area, learn the key intuitions, objective functions, underlying assumptions, advantages and disadvantages of different categories of …

A High-Precision Machine Learning Algorithm To Classify Left And Right Outflow Tract Ventricular Tachycardia, Jianwei Zhang, Guohua Fu, Islam Abudayyeh, Magdi Yacoub, Anthony Chang, William Feaster, Louis Ehwerhemuepha, Hesham El-Askary, Xianfeng Du, Bin He, Mingjun Feng, Yibo Yu, Binhao Wang, Jing Liu, Hai Yao, Hulmin Chu, Cyril Rakovski

Mathematics, Physics, and Computer Science Faculty Articles and Research

Introduction: Multiple algorithms based on 12-lead ECG measurements have been proposed to identify the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT) locations from which ventricular tachycardia (VT) and frequent premature ventricular complex (PVC) originate. However, a clinical-grade machine learning algorithm that automatically analyzes characteristics of 12-lead ECGs and predicts RVOT or LVOT origins of VT and PVC is not currently available. The effective ablation sites of RVOT and LVOT, confirmed by a successful ablation procedure, provide evidence to create RVOT and LVOT labels for the machine learning model.

Methods: We randomly sampled training, validation, and testing …

An Improved Firefly Algorithm And Its Application In Washout Optimization, Wang Hui, Xingshun Lü

Journal of System Simulation

Abstract: To improve the accuracy of the firefly algorithm (FA) and solve the problem of fixed iteration step of the algorithm and easy to fall into local optimum, an improved firefly algorithm is proposed, i.e., EOFA. The EOFA algorithm combines the strong local search ability of extremal optimization algorithm with the strong search ability of firefly algorithm, and adopts the iterative step size of inverted s-type function to improve the optimization ability of the firefly algorithm. The simulation results of function optimization test shows that the improved EOFA algorithm has better optimization performance than firefly algorithm and particle swarm optimization …

Overview Of Cgf-Oriented Cognitive Architecture, Xu Kai, Junjie Zeng, Weilong Yang, Qin Long, Quanjun Yin

Journal of System Simulation

Abstract: In order to further formalize and boost standardized behavioral model development of Computer Generated Forces (CGF), the CGF-oriented cognitive architecture is reviewed and the implementation details of one of the CGF cognitive behaviors, i.e. plan recognition, upon standard cognitive architecture are designed. The results show that the well-designed architecture has a strong support for complex behavior modeling. Four specific suggestions, including requirement analysis, design implementation, theoretical principle and cooperation mechanism, for architecture design and complex behavior modeling are provided.

Modeling Of Adversarial Behavior On Road Network Based On Non-Cooperative Game, Xiangyu Wei, Zhang Qi

Journal of System Simulation

Abstract: The modeling of adversarial behavior is the key to the study of various military-like confrontation problems. Existing research mainly focus on the target domain, but in reality, many confrontation problems occur on the road network. Combined with the network flow representation of adversarial behavior, a network adversarial game modeling framework based on non-cooperative games is proposed, and a novel road network confrontation problem—network evasion interdiction game is given based on the framework. Simulation experiments show that the new double oracle algorithm performs better than the original linear solution algorithm. Data experiments based on real road networks further verify …

Behavior Modeling For Computer Generated Forces Based On Machine Learning, Zhang Qi, Junjie Zeng, Xu Kai, Qin Long, Quanjun Yin

Journal of System Simulation

Abstract: With the rapid development of Machine Learning, especially deep learning, it has become an important way of modeling Computer Generated Force (CGF) behavior by ML methods, which can overcome the challenges of traditional methods. The existing research and application of three typical learning methods in CGF behavior modeling are discussed, and the effects of introducing learning into different stages of the typical CGF applications are analyzed, and the function and performance requirements of CGF behavior modeling using machine learning are proposed. Four potential research directions in the field for future are proposed.

An Intrusion Detection Algorithm Based On Ifoa And Welm, Jianwu Dang, Tan Ling

Journal of System Simulation

Abstract: An intrusion detection algorithm of WELM optimized by IFOA is proposed. The advantages of short training time and good generalization performance of WELM are used, and the weight of minority attacks is increased, so that the recall rate of minority attacks in network attacks is greatly improved.The FOA with adaptive adjustment of the iterative step size is used, so the input weights and bias of the hidden layer in the WELM are globally optimized to avoid the algorithm falling into local optimal solution and realize the classification of the NSL-KDD intrusion detection data set. The experimental results show …

Integrated Design And Simulation Of A Giant Magnetostrictive Driving Positioning And Vibration Suppression System, Xiaoqing Sun, Hu Wei, Yucheng Liu, Zhilei Wang, Hu Jun

Journal of System Simulation

Abstract: Aiming at the ultra-precision positioning and vibration suppression for sensitive payloads on-orbital working environment, a giant magnetostrictive driving positioning and vibration suppression system is proposed. The passive vibration isolation performance is selected as the optimization objective to realize the optimization design of the key part of the integrated system. The dynamic model of the whole system is built and the simulation model is constructed through Simulink. The simulation analysis and experimental tests are carried out to test the integrated system. The results show that the proposed integrated system realizes the ultra-precision positioning, and suppresses the vibration above 60 Hz, …

Longitudinal Adaptive Control Of Autonomous Vehicles Base On Optimization Algorithm, Zhishuai Yin, Jiaxiong He, Linzhen Nie, Jiayi Guan

Journal of System Simulation

Abstract: Aiming at the nonlinear, time-varying and uncertain characteristics of the longitudinal motion of autonomous vehicles, a Radial Basis Function neural network(RBFNN) Proportional Integral Derivative(PID) controller base on Particle Swarm Optimization(PSO) is designed. A RBFNN is integrated into a PID controller so that parameters of the PID controller could be adjusted self-adaptively. To solve the problem that poor selection of initial parameters of RBFNN and PID might lead to overshoot or instability in the control system, PSO is adopted to optimize aforementioned initial parameters off-line. Finally, a closed-loop adaptive control system model is built in MATLAB/Simulink. Simulation results show that …

A Quantized State System Method With Adaptive Quantum, Zhihua Li, Dongjin Fu, Li Guang, Zhihua Fan

Journal of System Simulation

Abstract: Quantized state system (QSS) is a new numerical integration method. It has advantages over the traditional time-discrete integration methods in solving general ordinary differential equation (ODE) systems. But it is hard to choose an appropriate quantum for the QSS method. In order to improve the accuracy and efficiency of QSS, a quantized state system method with adaptive quantum (VQSS) is proposed. Combined with the idea of step control in the variable step Runge-Kutta method, it can adaptively change the quantum in the process of computation. The feasibility of this algorithm is verified by the simulation of two examples …

Visualization Of Tropical Cyclone Disaster Information Based On Cesium, Shuoben Bi, Yezhou Chen, Yucheng Gong, Mingyue Lu, Ruizhuang Xu

Journal of System Simulation

Abstract: The disaster information of tropical cyclones not only expresses the intensity, but also reflects the degree of influence on human life, which has very important research significance. At present, no scholar has given a dynamic visualization method based on Cesium for water flooding disasters, nor has it integrated with other disaster information of tropical cyclones. In response to these problems, a dynamic visualization method for water inundation is proposed, and it is integrated with other disaster information such as the path of tropical cyclone and loss caused by it in the same digital earth platform. Experiments show that the …

Spatio-Temporal Memory Models In Spatial Cognitive Behavioral Modeling, Hu Yue, Xu Kai, Qin Long, Quanjun Yin, Yabing Zha

Journal of System Simulation

Abstract: It is crucial for military simulation systems to model the layouts of spatial environments and the temporal logic of entity activities. To improve the human-likeness of Computer Generated Forces (CGFs) and the runtime efficiency of the systems, building spatio-temporal memory representations and reasoning mechanisms that accord to mankind cognition is required. The neuro cognition science background of spatio-temporal memory is presented, and the related work on modeling the memory in deep learning and computational intelligence communities is summarized. Following the OODA (Observe-Orient-Decide-Act) loop, a general framework of spatial cognitive behavioral modeling is designed and the application of spatio-temporal memory …

Research On Cgf-Oriented Virtual Human Perceptual Attention Model, Weilong Yang, Xu Kai, Xie Xu, Sun Lin

Journal of System Simulation

Abstract: Perception model is an important research field of CGF behavior modeling. As the input of the reasoning module, the information obtained from the perception model has an important influence on the fidelity of the simulation. The CGF perception model is researched, and the attention mechanism, effective time of attention model is analyzed, compared with the traditional model of perception. By modeling the knowledge base and information feedback, a virtual human perception framework based on attention mechanism is proposed, and the experiment is carried out in the simulation environment.

Review On The Construction And Application Of Digital Twins In Transportation Scenes, Zhaohui Wu, Zhenzheng Liu, Shi Ke, Wang Liang, Xiaojie Liang

Journal of System Simulation

Abstract: Digital twins connect the physical world and the information world, and provide new ideas for the analysis and solution of complex traffic problems. The research and application status of digital twins in transportation scenes are reviewed on the basis of sorting out the basic concepts, development history and key technologies of digital twins. The key technologies for the construction of digital twins in transportation scenes that need to be breakthrough are analyzed from the four aspects of "people-vehicle-road-environment" combined with the characteristics of the elements of traffic operation. The prospect of digital twin transportation applications in the development of …

Modulation Recognition Algorithm Based On Improved Lda And Autoencoders, Yecai Guo, Haoran Zhang

Journal of System Simulation

Abstract: The traditional modulation recognition algorithms are based on the Gaussian white noise channel, which significantly degrade recognition performance in complex channel conditions. Aiming at this problem, a modulation recognition algorithm based on A-ALDA (Anti-alias Linear Discriminant Analysis) and SSDAE (Stacked Sparse Denoising Autoencoders) is proposed. In this algorithm, A-ALDA algorithm reconstructs signal cumulants feature into new features, which has better separability. The combination of original features and new features is input into SSDAE for classification, and SSADE has the ability to extract key information and resist noise. Simulation results show that …

Preliminary Research On Verification And Validation For Cgf Behavioral Modeling, Jianbing Tang, Zhang Qi, Jiao Peng, Yabing Zha

Journal of System Simulation

Abstract: Building computer generated force model is a very important job in combat simulation. Its core content is modeling of complicated human behavior, including cognition behavioral modeling and physical behavioral modeling. The credibility is vital for behavioral model. Verification and validation (V&V) in all life circle of behavioral modeling can insure the credibility of behavioral model. On the basis of explaining V&V of behavioral modeling and other conceptions, the process model of behavioral modeling is proposed. The V&V process of CGF behavioral modeling is studied emphasizly. Many effective V&V methods for CGF behavioral modeling are explored.

Refined Alignment Method For Single-Axis Rotary Inertial Navigation Based On Fuzzy Adaptive Filtering, Hu Jie, Xiaozhu Shi

Journal of System Simulation

Abstract: In order to restrain the influence of saw tooth velocity error caused by the inertial measurement unit (IMU) rotation on the initial alignment accuracy of single-axis rotary strapdown inertial navigation system (SINS), a refined alignment method based on fuzzy adaptive Kalman filtering is proposed. After calculating the ratio of actual covariance to theoretical covariance of the innovation sequence, the method adaptively adjusts the measurement noise covariance matrix by using the fuzzy inference system (FIS), so that it can adapt to the changes of measurement noise caused by IMU rotation. The initial alignment validation experiments under the swing environment …

Research On Virtual Avatar Position And Orientation Technology For Augmented Reality Virtual Sandbox, Tiantian Yu, Xiaoping Wang, Weiqing Li, Zhiyong Su

Journal of System Simulation

Abstract: When using augmented reality (AR) virtual sandbox for multi-person collaborative command or discussion, the local operator needs to know the specific direction and location of the remote operator to avoid wrong direction, position conflict and to better communicate with the other. Aiming at this problem, a three-dimensional marker suitable for AR environment is designed, and a vision-based position and orientation algorithm is researched and implemented. The PnP algorithm is used to estimate the pose of the marker, and the area ratio method is used to calculate the azimuth. The experimental results show that the proposed algorithm can achieve …