Artificial Intelligence and Robotics Commons^™

Improved Particle Swarm Optimization Based On Lévy Flights, Rongyu Li, Wang Ying

Journal of System Simulation

Abstract: The particle swarm optimization (PSO) has some demerits, such as relapsing into local extremum, slow convergence velocity and low convergence precision in the late evolutionary. The Lévy particle swarm optimization (Lévy PSO) was proposed. In the particle position updating formula, Lévy PSO eliminated the impact of speed on the convergence rate, and used Levy flight to change the direction of particle positions movement to prevent particles getting into local optimum value, and then using greedy strategy to update the evaluation and choose the best solution to obtain the global optimum. The experimental results show that Lévy PSO can effectively …

Performance Modeling Of Cryptographic Service System Virtualization Based On Issm, Songhui Guo, Qingbao Li, Sun Lei, Xuerong Gong, Tianchi Yang

Journal of System Simulation

Abstract: The complicated architecture of cryptographic service system virtualization raised the difficulty of performance modeling. A performance modeling approach based on ISSMs was proposed. The approach divided the execution process into two stages, host preprocessing and arithmetic-module calculating, and built two sub-models based on queuing theory. On this basis, the effectiveness of this approach was verified. The results show that this method can analyze the impacts on system performance caused by task arrival rates, host and cryptographic card configurations quantitatively, and also be helpful for providing reasonable solutions to deploy virtualized cryptographic service system on cloud computing platforms.

Simulation Of Three-Region Commutation Torque Ripple Reduction For Brushless Dc Motor, Junjie Zhu, Haoran Liu

Journal of System Simulation

Abstract: Aiming at brushless DC motor torque ripple during commutation section, new three-step three phases PWM method was proposed based on voltage balance principle, improving existing two phase PWM suppression method and suitable for all speed section. In this new method, the principle of non-commutation phase voltage and the neutral point voltage variation was researched. Voltage difference was remained the same by three-step PWM control strategy before and after commutation in order to suppression current ripple. Comparing with existing current slope research method, this new method is with a series of advantages: simple parameters, computing, and sampling circuit design. …

Research On Natural Gas Explosion Rules For Cuboid Obstacles In Offshore Oil Platform, Pengcheng Wang, Yuqing Sun

Journal of System Simulation

Abstract: Quantities and blockage ratios of equipment on the platform has a great effect on the peak overpressure and temperature. The loss caused by explosion can be reduced to the minimum through the reasonable distribution of equipment, and the finite element method has been widely used in the simulation of gas cloud explosion. Offshore oil platform models with different cuboid obstacles were established by the finite element method and cuboid obstacles were distributed in 15 different situations. Mathematical relationships between overpressure and cuboid obstacles' quantities and blockage ratios were obtained. The results show that with the increase of quantities and …

Research On Picking Robot Vision Localization Based On Semi-Physical Simulation, Keyin Chen, Xiangjun Zou, Hongxing Peng, Haiying Liang, Yuanchuang Hu

Journal of System Simulation

Abstract: Aiming at the problems of accuracy and stability of the vision localization based on physical picking robot, which were easy to make mistakes, long cycle, and not easy to be carried out indoors, a picking robot vision localization method based on the semi-physical simulation technology was proposed combining with the robot vision localization mechanism and robot kinematics. This method adopted the virtual picking robot to instead of the physical robot, and studied the vision localization of the fruit target in the virtual simulated environment, which was as the vision localization based on semi-physical simulation. The test results show that: …

Observer-Based Integral Backstepping Control For Permanent Magnet Synchronous Motor, Yonghong Lan, Liangliang Wang, Caixue Chen

Journal of System Simulation

Abstract: For the speed tracking control problem of Permanent Magnet Synchronous Motor (PMSM), an observer-based back-stepping speed tracking control method was presented. To reconstruct the motor speed and stator axis current, a full order Luenberger observer for PMSM was constructed. By using Lyapunov stability theory, the linear matrix inequality (LMI) based design method of observer was obtained. Through the design of the virtual control input that include the reconstruction variables, using back-stepping control strategy and integrating with tracking errors, the controller of the closed-loop system was proposed. The obtained controller can achieve high precision speed tracking. The …

Improved Threshold Function Simulation Research In Vibration Signal Denoising, Hongxing Sun, Zhang Yang

Journal of System Simulation

Abstract: Filtering noise component of mechanical vibration signal effectively can observe the characteristics of vibration signal more clearly. So based on the wavelet threshold de-noising method, a new improved threshold function was proposed. The coefficient of wavelet transform mechanical vibration signals were estimated by the threshold selection method based on kurtosis value. Not only new threshold function conforms to the distribution characteristics of the vibration signal, but also new threshold function is continuous in the threshold point. And the new threshold function overcomes the inherent deviation which traditional threshold function brings. The research of noise reduction on the simulation signal …

Interaction Of Particle-Particle And Particle-Bubble In Water:Molecular Dynamics Simulation, Qingqun Luo, Jieming Yang

Journal of System Simulation

Abstract: Graphene and a bulk of gas were used to represent a part of particle and a part of bubble, respectively, and their interactions in liquid water with dissolved gas were simulated. Changes of the structural phase diagram, the gas density, and the potential of mean force were analyzed. The results show that the interactions of particle-particle and particle-bubble are both related to the nanobubble bridges therein. The forming processes of nanobubble bridges were shown in details. The range of nanobubble bridges and the energy change of the system were quantitatively calculated.

A Way Of Integrated Navigation Fault Detection Of Near Space Hypersonic Cruising Aircraft, Hailin Li, Bin Zhang, Dewei Wu, Lu Hu

Journal of System Simulation

Abstract: The doppler shift is augmented, that causes acquisition and tracking of GNSS losing, error of CNS's ray propagation also causes the problem of celestial body tracking when aircraft is hypersonically flighting. A way of INS/GNSS/CNS integrated navigation fault detection of the hypersonic cruising aircraft based on the residual chi-square-Fuzzy ARTMAP (Adaptive Resonance Theory Map) fast neural networks was proposed. The fault diagnostic elements of INS/GNSS/CNS integrated navigation system of the hypersonic cruising aircraft were given; the detection function formula of residual chi-square test and Fuzzy ARTMAP fast neural networks arithmetic was deduced; the realizing way was studied. The …

Ect Image Reconstruction Algorithm Based On Generalized Regularization, Ma Min, Guo Qi, Chaoqi Yan

Journal of System Simulation

Abstract: Aiming at the numerical instability caused by the singular value decomposition algorithm and the over-smooth caused by the Tiknonov regularization in the image reconstruction of electrical capacitance tomography (ECT) system, a more generalized regularization algorithm was proposed. The penalty phase of the regularized objective function was modified by the positive definite matrix so that it could reconstruct the image with non smooth information, In the process of solving the objective function, the diagonal weight matrix was introduced, and the data items based on l₂-norm were improved. By comparing the image quality, the relative error of the image …

Simulation And Analysis Of Ultra High Frequency Induction Heating Circuit Based On Current Source, Mangyuan Ma, Xinchun Shi, Wang Hui, Jianhui Meng

Journal of System Simulation

Abstract: The operating frequency range, operating mode and output power are determined by the circuit. A suitable circuit is very important for induction heating power supply. On the basis of Class-E and Boost Chopper circuit, a new current source was analyzed with parallel resonant load circuit by energy conservation law and Fourier decomposition, which derived mathematical relation among the parameters and provided application theory. This circuit was studied by using Matlab/Simulink with variable parameters, which obtained the operating waves with different parameters and values. Comparing the operating waves with the theoretical analysis, the simulation results are completely consistent with the …

Modeling Method Of Air Command And Security Work Process Service Oriented, Yongliang Luo, Yuanhui Qin

Journal of System Simulation

Abstract: A modeling method of air command and security work process service oriented was proposed combined with the typical process equipment air command and support building requirements. Air command and process characteristics was analyzed systematically. On this basis, a complex process modeling method was proposed. From the concept of process meta-model, process formalized description mechanism was studied. A prototype flow modeling tool was developed, and the rationality of the proposed method was analyzed combined with the application example.

Using Generative Adversarial Networks To Classify Structural Damage Caused By Earthquakes, Gian P. Delacruz

Master's Theses

The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. There are several solution to automate post-earthquake reconnaissance image tagging using Machine Learning (ML) solutions to classify each occurrence of damage per building material and structural member type. ML algorithms are data driven; improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, ML and in particular Deep Learning (DL) has become one of the most …

Transfer Learning: Bridging The Gap Between Deep Learning And Domain-Specific Text Mining, Chaoran Cheng

Dissertations

Inspired by the success of deep learning techniques in Natural Language Processing (NLP), this dissertation tackles the domain-specific text mining problems for which the generic deep learning approaches would fail. More specifically, the domain-specific problems are: (1) success prediction in crowdfunding, (2) variants identification in biomedical literature, and (3) text data augmentation for domains with low-resources.

In the first part, transfer learning in a multimodal perspective is utilized to facilitate solving the project success prediction on the crowdfunding application. Even though the information in a project profile can be of different modalities such as text, images, and metadata, most existing …

Efficient Hardware Implementations Of Bio-Inspired Networks, Anakha Vasanthakumaribabu

Dissertations

The human brain, with its massive computational capability and power efficiency in small form factor, continues to inspire the ultimate goal of building machines that can perform tasks without being explicitly programmed. In an effort to mimic the natural information processing paradigms observed in the brain, several neural network generations have been proposed over the years. Among the neural networks inspired by biology, second-generation Artificial or Deep Neural Networks (ANNs/DNNs) use memoryless neuron models and have shown unprecedented success surpassing humans in a wide variety of tasks. Unlike ANNs, third-generation Spiking Neural Networks (SNNs) closely mimic biological neurons by operating …

Model-Based Deep Siamese Autoencoder For Clustering Single Cell Rna-Seq Data, Zixia Meng

Theses

In the biological field, the smallest unit of organisms in most biological systems is the single cell, and the classification of cells is an everlasting problem. A central task for analysis of single-cell RNA-seq data is to identify and characterize novel cell types. Currently, there are several classical methods, such as K-means algorithm, spectral clustering, and Gaussian Mixture Models (GMMs), which are widely used to cluster the cells. Furthermore, typical dimensional reduction methods such as PCA, t-SNE, and ZIDA have been introduced to overcome “the curse of dimensionality”. A more recent method scDeepCluster has demonstrated improved and promising performances in …

Analysis Of Gameplay Strategies In Hearthstone: A Data Science Approach, Connor W. Watson

Theses

In recent years, games have been a popular test bed for AI research, and the presence of Collectible Card Games (CCGs) in that space is still increasing. One such CCG for both competitive/casual play and AI research is Hearthstone, a two-player adversarial game where players seeks to implement one of several gameplay strategies to defeat their opponent and decrease all of their Health points to zero. Although some open source simulators exist, some of their methodologies for simulated agents create opponents with a relatively low skill level. Using evolutionary algorithms, this thesis seeks to evolve agents with a higher skill …

Evaluating Driving Performance Of A Novel Behavior Planning Model On Connected Autonomous Vehicles, Keyur Shah

Honors Scholar Theses

Many current algorithms and approaches in autonomous driving attempt to solve the "trajectory generation" or "trajectory following” problems: given a target behavior (e.g. stay in the current lane at the speed limit or change lane), what trajectory should the vehicle follow, and what inputs should the driving agent apply to the throttle and brake to achieve this trajectory? In this work, we instead focus on the “behavior planning” problem—specifically, should an autonomous vehicle change lane or keep lane given the current state of the system?

In addition, current theory mainly focuses on single-vehicle systems, where vehicles do not communicate with …

Ship Detection Feature Analysis In Optical Satellite Imagery Through Machine Learning Applications, Sylvia Charchut

LSU New Orleans Theses and Dissertations

Ship detection remains an important challenge within the government and the commercial industry. Current research has focused on deep learning and has found high success with large labeled datasets. However, deep learning becomes insufficient for limited datasets as well as when explainability is required. There exist scenarios in which explainability and human-in-the-loop processing are needed, such as in naval applications. In these scenarios, handcrafted features and traditional classification algorithms can be useful. This research aims at analyzing multiple textures and statistical features on a small optical satellite imagery dataset. The feature analysis consists of Haar-like features, Haralick features, Hu moments, …

Evidence-Based Detection Of Pancreatic Canc, Rajeshwari Deepak Chandratre

Master's Projects

This study is an effort to develop a tool for early detection of pancreatic cancer using evidential reasoning. An evidential reasoning model predicts the likelihood of an individual developing pancreatic cancer by processing the outputs of a Support Vector Classifier, and other input factors such as smoking history, drinking history, sequencing reads, biopsy location, family and personal health history. Certain features of the genomic data along with the mutated gene sequence of pancreatic cancer patients was obtained from the National Cancer Institute (NIH) Genomic Data Commons (GDC). This data was used to train the SVC. A prediction accuracy of ~85% …