Computer Sciences Commons^™

Three-Dimensional Adaptive Neural Network Guidance Law Against Maneuvering Targets, Yujie Si, Xiong Hua, Zhe Li

Journal of System Simulation

Abstract: The problem of designing a three-dimensional nonlinear guidance law accounting for saturation nonlinearity is concentrated to attack maneuvering targets. To solve the physical constraints of missile actuators, an anti-disturbance and anti-saturation terminal sliding mode guidance law is provided based on radial basis functions neural networks and adaptive method. The guidance law is bounded and ensures that the system state is uniformly ultimately bounded. Compared with the traditional anti-saturation guidance law, it has the advantages of fast convergence speed and high precision. Numerical simulations are introduced to demonstrate the effectiveness and superiority of the designed composite guidance law in theory.

Simulation Of Adaptive Track Control Of Ship Bending In Inland River Curved Channel, Langxiong Gan, Changsheng Wu, Deng Wei, Yuanzhou Zheng, Chunhui Zhou

Journal of System Simulation

Abstract: In view of the complex flow characteristics and difficult maneuvering of ships in curved river section, combined with the characteristics of ship AIS trajectory and customary route, the intelligent track and heading control algorithm is adopted to realize the automatic control of ship's safe turning. Firstly, the research waters are selected and according to the rules of lane-dividing navigation, the ship's turning track is reasonably planned. Then the ship motion simulation software is constructed, and the self-adaptive fuzzy PID course controller is designed by combining the self-adaptive fuzzy control algorithm and traditional PID control, the simulation of …

Correction Method Of Action Parameters Of Panzer Virtual Force Tactical Confrontation, Gao Ang, Xiaolu Wang, Zhiming Dong, Guohui Zhang

Journal of System Simulation

Abstract: Aiming at the problem of unreasonable virtual force tactical confrontation action parameters in the simulation training of armored force equipment system, resulting in unsatisfactory training effects, the idea of estimating posterior probability with prior probability is adopted to correct the parameters. According to the OODA theory, the tactical confrontation movement of armored forces is decomposed and an index system of influencing factors is constructed; the parameter collection method is proposed to establish the Bayesian network correction model and to realize dynamic adjustment; the expected optimization algorithm and the principal component analysis method are used to process the training data …

Negative Influence Minimization Algorithm For Social Networks, Yang Yi, Chunxiao Wu, He Ming, Zhou Bo

Journal of System Simulation

Abstract: While positive information is spreading in social networks, there is still a large amount of negative information spreading in the network. Aiming at the fact that there is few researches on suppressing the spread of negative information, a negative influence minimization algorithm for social networks is proposed. When negative information appears in social networks and some initial nodes are infected, the behavior of nodes propagating information depends on its coordination game with neighbor nodes. The objective function with minimal influence is used to find the K optimal blocking nodes, and finally the size of the final infected node is …

Addressing Artificial Intelligence Bias In Retinal Diagnostics, Philippe Burlina, Neil Joshi, William Paul, Katia D Pacheco, Neil M Bressler

Faculty, Staff and Students Publications

PURPOSE: This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on.

METHODS: The public domain Kaggle EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) from darker-skin individuals, who presumably have greater …

Speech Enhancement Using Speech Synthesis Techniques, Soumi Maiti

Dissertations, Theses, and Capstone Projects

Traditional speech enhancement systems reduce noise by modifying the noisy signal to make it more like a clean signal, which suffers from two problems: under-suppression of noise and over-suppression of speech. These problems create distortions in enhanced speech and hurt the quality of the enhanced signal. We propose to utilize speech synthesis techniques for a higher quality speech enhancement system. Synthesizing clean speech based on the noisy signal could produce outputs that are both noise-free and high quality. We first show that we can replace the noisy speech with its clean resynthesis from a previously recorded clean speech dictionary from …

3d Object Detection, Instance Segmentation And Classification From 3d Range And 2d Color Images, Xiaoke Shen

Dissertations, Theses, and Capstone Projects

We address the problem of 3D object detection and instance segmentation by proposing a novel object segmentation and detection system. First, we detect 2D objects based on RGB, Depth only, or RGB-D images. A 3D convolutional-based system, named Frustum VoxNet, is proposed. This system 1) generates frustums from 2D detection results, 2) proposes 3D candidate voxelized images for each frustum, and uses a 3D convolutional neural network (CNN) based on these candidates voxelized images to perform the 3D instance segmentation and object detection. Although the volumetric data representation is widely used for 3D object classification, there are fewer works on …

A New Feature Selection Method Based On Class Association Rule, Sami A. Al-Dhaheri

Dissertations, Theses, and Capstone Projects

Feature selection is a key process for supervised learning algorithms. It involves discarding irrelevant attributes from the training dataset from which the models are derived. One of the vital feature selection approaches is Filtering, which often uses mathematical models to compute the relevance for each feature in the training dataset and then sorts the features into descending order based on their computed scores. However, most Filtering methods face several challenges including, but not limited to, merely considering feature-class correlation when defining a feature’s relevance; additionally, not recommending which subset of features to retain. Leaving this decision to the end-user may …

Role Of Artificial Intelligence In The Internet Of Things (Iot) Cybersecurity, Murat Kuzlu, Corinne Fair, Ozgur Guler

Engineering Technology Faculty Publications

In recent years, the use of the Internet of Things (IoT) has increased exponentially, and cybersecurity concerns have increased along with it. On the cutting edge of cybersecurity is Artificial Intelligence (AI), which is used for the development of complex algorithms to protect networks and systems, including IoT systems. However, cyber-attackers have figured out how to exploit AI and have even begun to use adversarial AI in order to carry out cybersecurity attacks. This review paper compiles information from several other surveys and research papers regarding IoT, AI, and attacks with and against AI and explores the relationship between these …

Accelerating Large-Scale Heterogeneous Interaction Graph Embedding Learning Via Importance Sampling, Yugang Ji, Mingyang Yin, Hongxia Yang, Jingren Zhou, Vincent W. Zheng, Chuan Shi, Yuan Fang

Research Collection School Of Computing and Information Systems

In real-world problems, heterogeneous entities are often related to each other through multiple interactions, forming a Heterogeneous Interaction Graph (HIG in short). While modeling HIGs to deal with fundamental tasks, graph neural networks present an attractive opportunity that can make full use of the heterogeneity and rich semantic information by aggregating and propagating information from different types of neighborhoods. However, learning on such complex graphs, often with millions or billions of nodes, edges, and various attributes, could suffer from expensive time cost and high memory consumption. In this paper, we attempt to accelerate representation learning on large-scale HIGs by adopting …

Norm-Based Generalisation Bounds For Deep Multi-Class Convolutional Neural Networks, Antoine Ledent, Waleed Mustafa, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

We show generalisation error bounds for deep learning with two main improvements over the state of the art. (1) Our bounds have no explicit dependence on the number of classes except for logarithmic factors. This holds even when formulating the bounds in terms of the Frobenius-norm of the weight matrices, where previous bounds exhibit at least a squareroot dependence on the number of classes. (2) We adapt the classic Rademacher analysis of DNNs to incorporate weight sharing—a task of fundamental theoretical importance which was previously attempted only under very restrictive assumptions. In our results, each convolutional filter contributes only once …

Fine-Grained Generalization Analysis Of Vector-Valued Learning, Liang Wu, Antoine Ledent, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

Many fundamental machine learning tasks can be formulated as a problem of learning with vector-valued functions, where we learn multiple scalar-valued functions together. Although there is some generalization analysis on different specific algorithms under the empirical risk minimization principle, a unifying analysis of vector-valued learning under a regularization framework is still lacking. In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. Our discussions relax the existing assumptions on the restrictive constraint of hypothesis spaces, smoothness of loss …

Model Uncertainty Guides Visual Object Tracking, Lijun Zhou, Antoine Ledent, Qintao Hu, Ting Liu, Jianlin Zhang, Marius Kloft

Research Collection School Of Computing and Information Systems

Model object trackers largely rely on the online learning of a discriminative classifier from potentially diverse sample frames. However, noisy or insufficient amounts of samples can deteriorate the classifiers' performance and cause tracking drift. Furthermore, alterations such as occlusion and blurring can cause the target to be lost. In this paper, we make several improvements aimed at tackling uncertainty and improving robustness in object tracking. Our first and most important contribution is to propose a sampling method for the online learning of object trackers based on uncertainty adjustment: our method effectively selects representative sample frames to feed the discriminative branch …

Adversarial Meta Sampling For Multilingual Low-Resource Speech Recognition, Yubei Xiao, Ke Gong, Pan Zhou, Guolin Zheng, Xiaodan Liang, Liang Lin

Research Collection School Of Computing and Information Systems

Human doctors with well-structured medical knowledge can diagnose a disease merely via a few conversations with patients about symptoms. In contrast, existing knowledgegrounded dialogue systems often require a large number of dialogue instances to learn as they fail to capture the correlations between different diseases and neglect the diagnostic experience shared among them. To address this issue, we propose a more natural and practical paradigm, i.e., low-resource medical dialogue generation, which can transfer the diagnostic experience from source diseases to target ones with a handful of data for adaptation. It is capitalized on a commonsense knowledge graph to characterize the …

Scalable Verification Of Quantized Neural Networks, Thomas A. Henzinger, Mathias Lechner, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network’s correctness. Thus, …

Relative And Absolute Location Embedding For Few-Shot Node Classification On Graph, Zemin Liu, Yuan Fang, Chenghao Liu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

Node classification is an important problem on graphs. While recent advances in graph neural networks achieve promising performance, they require abundant labeled nodes for training. However, in many practical scenarios there often exist novel classes in which only one or a few labeled nodes are available as supervision, known as few-shot node classification. Although meta-learning has been widely used in vision and language domains to address few-shot learning, its adoption on graphs has been limited. In particular, graph nodes in a few-shot task are not independent and relate to each other. To deal with this, we propose a novel model …

Terrace-Based Food Counting And Segmentation, Huu-Thanh Nguyen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper represents object instance as a terrace, where the height of terrace corresponds to object attention while the evolution of layers from peak to sea level represents the complexity in drawing the finer boundary of an object. A multitask neural network is presented to learn the terrace representation. The attention of terrace is leveraged for instance counting, and the layers provide prior for easy-to-hard pathway of progressive instance segmentation. We study the model for counting and segmentation for a variety of food instances, ranging from Chinese, Japanese to Western food. This paper presents how the terrace model deals with …

Deep Learning For Multi-Tissue Cancer Classification Of Gene Expressions, Tarek Khorshed

Theses and Dissertations

We contribute in saving the lives of cancer patients through early detection and diagnosis, since one of the major challenges in cancer treatment is that patients are diagnosed at very late stages when appropriate medical interventions become less effective and full curative treatment is no longer achievable. Cancer classification using gene expressions is extremely challenging given the complexity and high dimensionality of the data. Current classification methods typically rely on samples collected from a single tissue type and perform a prerequisite of gene feature selection to avoid processing the full set of genes. These methods fall short in taking advantage …

Efficient Cnn Building Blocks For Encrypted Data, Nayna Jain, Karthik Nandakumar, Nalini K. Ratha, Sharath U. Pankanti, Uttam Kumar

Computer Vision Faculty Publications

Machine learning on encrypted data can address the concerns related to privacy and legality of sharing sensitive data with untrustworthy service providers, while leveraging their resources to facilitate extraction of valuable insights from otherwise non-shareable data. Fully Homomorphic Encryption (FHE) is a promising technique to enable machine learning and inferencing while providing strict guarantees against information leakage. Since deep convolutional neural networks (CNNs) have become the machine learning tool of choice in several applications, several attempts have been made to harness CNNs to extract insights from encrypted data. However, existing works focus only on ensuring data security and ignore security …

Generative Multi-Label Zero-Shot Learning, Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost Van De Weijer

Computer Vision Faculty Publications

Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of …

Simulation Research On Abandonment Rate Of Contact Center Based On Patience Threshold, Junxiang Li, Wanbin Zang

Journal of System Simulation

Abstract: Customer abandonment rate is an important indicator to measure the service level of contact center. Customers in a traditional call center follow the principle of first come, first served, but some customers will be lost in the queuing process because of their limited patience. In this regard, by setting the customer's patience threshold and considering adding a specific agent channel to the member customers, or adjusting the number of agent channels under the original staffing, a new contact center queuing model is established based on the traditional call center model. The ProModel simulation software is used to study the …

Joint Low Rank And Sparsity-Based Channel Estimation For Fdd Massive Mimo, Zhou Jin

Journal of System Simulation

Abstract: Channel estimation of millimeter wave communication needs large system load. In order to reduce the load, a low-rank and sparse feature of the wireless channel is combined, and a channel estimation algorithm framework based on non-convex low-rank approximation is proposed. Aiming at the large computation of the channel model-based dictionary learning algorithm, a dictionary learning algorithm for deep neural network channel feature classification is designed. The simulation shows that the average square error of the proposed method is better than the channel model-based dictionary learning method, the channel estimation method under the Bayesian framework, and the compressed …

Research On Precision Parking Control Method For Emu Inbound Process, Zhongqi Li, Yueshuang Xing

Journal of System Simulation

Abstract: By analyzing the relationship between braking force and speed during the stop-stop process of high-speed EMU(Electric Multiple Units), the multi-point dynamics model of EMU is constructed. The Smith predictor is introduced due to the delay effect on the system caused by the braking force generated during the late braking, and the RBF(Radial Basis Function) neural network-based PID control strategy is combined with the Smith predictor to achieve tracking control of a given speed during braking. Simulation analysis shows that the error of train speed and set speed controlled by RBF neural network PID-Smith controller is less than ±1 …

A Predictive Model For Diabetes Using Machine Learning Techniques (A Case Studyof Some Selected Hospitals In Kaduna Metropolis), A E. Evwiekpaefe, Nafisat Abdulkadir

Master of Science in Computer Science Theses

Diabetes Mellitus (DM) which refers to a metabolic disorder that occurs when the level of blood sugar in the body is considered high, which could be a resulting effect of inadequate availability of insulin in the body. It is a chronic disease which may lead to myriads of complications in the body system. Statistics by the World Health Organization (WHO) in 2013, indicated that DM was the cause of death of over 1.5 million people around the world and in 2016, 8.5% of adults within age seventeen (17) and above were reported to be diabetic and diabetic patients have continued …

Uncertainty Quantitative Analysis In Risk Assessment Of Returning To School In The Post-Covid-19 Era, Haibin Li, Jialiang Wang, Haiyan Li

Journal of System Simulation

Abstract: After the epidemic, taking the spread of the epidemic in returning to school as an example, a quantitative risk assessment study is conducted. Taking the activity trajectory description of the whole process of susceptible individuals from infection to isolation as a clue, an epidemiological model for risk assessment is established. The number of infected persons in the risk indicators of returning to school is quantified based on the quantified model parameters. According to the value characteristics of the parameters, the number of infected persons is taken as a function of discrete random variables. The probability distribution of the infected …

Research On Double Input Motion Somatosensory Algorithm Based On Logic Control, Wang Hui, Yingtao Liu

Journal of System Simulation

Abstract: Aiming at the two-input classic washout algorithm in the flight simulator, there are problems such as loss of perceived angular velocity signal, phase error, and insufficient fidelity. A logic control washing-out algorithm is proposed. Based on the vestibular system theory, the classic washout algorithm is used to improve the high-pass angular velocity channel structure. A logic controller and an angular displacement continuous generator are designed to optimize the coupling angular velocity in the high-pass angular velocity channel and the tilt coordination channel and stabilize the jump change washout angular displacement, so the improved algorithm is more consistent with the …

Visualization Of Finite Element Analysis Deformation Results Based On Hololens, Jinli Xu, Zhou Zheng

Journal of System Simulation

Abstract: An UWP application of virtual review of the finite element analysis based on Microsoft HoloLens is developed by using Unity3D software. A set of programs are completed to realize three-dimensional solid static finite element analysis in Matlab. To realize the visualization of the deformation effect, the useful information of the finite element analysis result is extracted and exported to VTK file, then converted into DAE file. A vertex shader is written in Unity3D software to realize the color display and the visualization of deformation effect of one-sided model, and finally the UWP application is released to HoloLens. The test …

Collision Simulation Analysis Of Sam Movable Guardrail, Hongjun Cui, Sixue Li, Minqing Zhu, Li Xia

Journal of System Simulation

Abstract: Aiming at the problem of low anti-collision grade of the movable guardrail at the opening of the central divding belt of the expressway, a SAm-level concrete movable guardrail and a new connecting device are proposed. Based on the finite element method, the collision model between the vehicle and the guardrail is established, and the collision process is also calculated by LS-DYNA. According to the collision results of different vehicle types, the safety performance of the guardrail is evaluated in terms of cushioning, blocking and guiding performance. The OIV value is less than 12 m/s for small vehicles' collision with …

Research On Sins/Gnss/Train-Speed Integrated Navigation Algorithm, Wang Ke, Ligang Liu, Bin Zhou, Zhiyong Bu

Journal of System Simulation

Abstract: The precise train positioning under complicated railway environment has been a key technical challenge for train navigation currently. In the conventional solutions, in case of satellite signals being weak or indiscernible, the task of positioning has to be undertaken by SINS alone. This will cause some serious error-accumulation problems, especially when low-cost inertial devices are used. In order to solve this problem, we propose a novel integrated train navigation algorithm, which includes two working modes. The SINS/GNSS mode is designed for the situation that satellite signals are valid, whereas the SINS/wheel-speed mode is for the weak signal environments. Both …

Threat Assessment For The Defense Penetration Paths Of Air Strike Aircrafts Based On Radar Chart, Shengli Liu, Wang Gang

Journal of System Simulation

Abstract: Threat assessment for the defense penetration paths of air strike aircrafts provides important evidence for evaluating and improving the deployment of air defense. Considering that traditional threat assessment methods are difficult to intuitively reflect the threat degree of each path and the value of each evaluation indicator, a novel method of threat assessment for defense penetration paths based on radar chart is proposed. The threat assessment indicator system for the defense penetration paths of air strike aircrafts is put forward. The weights of threat assessment indicators are calculated by the group decision analytic hierarchy process (AHP) and the method …