Artificial Intelligence and Robotics Commons^™

Sensor-Based Human Activity Recognition Using Bidirectional Lstm For Closely Related Activities, Arumugam Thendramil Pavai

Electronic Theses, Projects, and Dissertations

Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 …

Automatic Identification Of Animals In The Wild: A Comparative Study Between C-Capsule Networks And Deep Convolutional Neural Networks., Joel Kamdem Teto, Ying Xie

Master of Science in Computer Science Theses

The evolution of machine learning and computer vision in technology has driven a lot of

improvements and innovation into several domains. We see it being applied for credit decisions, insurance quotes, malware detection, fraud detection, email composition, and any other area having enough information to allow the machine to learn patterns. Over the years the number of sensors, cameras, and cognitive pieces of equipment placed in the wilderness has been growing exponentially. However, the resources (human) to leverage these data into something meaningful are not improving at the same rate. For instance, a team of scientist volunteers took 8.4 years, …

Cmos Compatible Memristor Networks For Brain-Inspired Computing, Can Li

Doctoral Dissertations

In the past decades, the computing capability has shown an exponential growth trend, which is observed as Moore’s law. However, this growth speed is slowing down in recent years mostly because the down-scaled size of transistors is approaching their physical limit. On the other hand, recent advances in software, especially in big data analysis and artificial intelligence, call for a break-through in computing hardware. The memristor, or the resistive switching device, is believed to be a potential building block of the future generation of integrated circuits. The underlying mechanism of this device is different from that of complementary metal-oxide-semiconductor (CMOS) …

Multi-Robot Coordination And Scheduling For Deactivation & Decommissioning, Sebastian A. Zanlongo

FIU Electronic Theses and Dissertations

Large quantities of high-level radioactive waste were generated during WWII. This waste is being stored in facilities such as double-shell tanks in Washington, and the Waste Isolation Pilot Plant in New Mexico. Due to the dangerous nature of radioactive waste, these facilities must undergo periodic inspections to ensure that leaks are detected quickly. In this work, we provide a set of methodologies to aid in the monitoring and inspection of these hazardous facilities. This allows inspection of dangerous regions without a human operator, and for the inspection of locations where a person would not be physically able to enter.

First, …

Integration Of Robotic Perception, Action, And Memory, Li Yang Ku

Doctoral Dissertations

In the book "On Intelligence", Hawkins states that intelligence should be measured by the capacity to memorize and predict patterns. I further suggest that the ability to predict action consequences based on perception and memory is essential for robots to demonstrate intelligent behaviors in unstructured environments. However, traditional approaches generally represent action and perception separately---as computer vision modules that recognize objects and as planners that execute actions based on labels and poses. I propose here a more integrated approach where action and perception are combined in a memory model, in which a sequence of actions can be planned based on …

Enhancing 3d Visual Odometry With Single-Camera Stereo Omnidirectional Systems, Carlos A. Jaramillo

Dissertations, Theses, and Capstone Projects

We explore low-cost solutions for efficiently improving the 3D pose estimation problem of a single camera moving in an unfamiliar environment. The visual odometry (VO) task -- as it is called when using computer vision to estimate egomotion -- is of particular interest to mobile robots as well as humans with visual impairments. The payload capacity of small robots like micro-aerial vehicles (drones) requires the use of portable perception equipment, which is constrained by size, weight, energy consumption, and processing power. Using a single camera as the passive sensor for the VO task satisfies these requirements, and it motivates the …

Higher-Level Consistencies: Where, When, And How Much, Robert J. Woodward

Department of Computer Science and Engineering: Dissertations, Theses, and Student Research

Determining whether or not a Constraint Satisfaction Problem (CSP) has a solution is NP-complete. CSPs are solved by inference (i.e., enforcing consistency), conditioning (i.e., doing search), or, more commonly, by interleaving the two mechanisms. The most common consistency property enforced during search is Generalized Arc Consistency (GAC). In recent years, new algorithms that enforce consistency properties stronger than GAC have been proposed and shown to be necessary to solve difficult problem instances.

We frame the question of balancing the cost and the pruning effectiveness of consistency algorithms as the question of determining where, when, and how much of a higher-level …

Investigating Dataset Distinctiveness, Andrew Ulmer, Kent W. Gauen, Yung-Hsiang Lu, Zohar R. Kapach, Daniel P. Merrick

The Summer Undergraduate Research Fellowship (SURF) Symposium

Just as a human might struggle to interpret another human’s handwriting, a computer vision program might fail when asked to perform one task in two different domains. To be more specific, visualize a self-driving car as a human driver who had only ever driven on clear, sunny days, during daylight hours. This driver – the self-driving car – would inevitably face a significant challenge when asked to drive when it is violently raining or foggy during the night, putting the safety of its passengers in danger. An extensive understanding of the data we use to teach computer vision models – …

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Identification And Optimal Linear Tracking Control Of Odu Autonomous Surface Vehicle, Nadeem Khan

Mechanical & Aerospace Engineering Theses & Dissertations

Autonomous surface vehicles (ASVs) are being used for diverse applications of civilian and military importance such as: military reconnaissance, sea patrol, bathymetry, environmental monitoring, and oceanographic research. Currently, these unmanned tasks can accurately be accomplished by ASVs due to recent advancements in computing, sensing, and actuating systems. For this reason, researchers around the world have been taking interest in ASVs for the last decade. Due to the ever-changing surface of water and stochastic disturbances such as wind and tidal currents that greatly affect the path-following ability of ASVs, identification of an accurate model of inherently nonlinear and stochastic ASV system …

Real-Time Simulator For Spatial Information Networks Based On Analog If Signal Processing, Zeguo Yang, Ma Shang, Diaopeng Huang, Jianhao Hu, Lixiang Liu

Journal of System Simulation

Abstract: To solve the problem of real-time simulation of spatial information network with high dynamic network topology, a real-time simulator based on the IF signal processing is proposed. Compared with traditional channel simulator, it supports both the channel transmission characteristics like channel fading, Doppler shift, noise, and path delay, and the real-time simulation of dynamic network topology changes. The simulator supports 8~128 70 MHz IF (0~20 MHz signal bandwidth) emulated nodes with flexible link type configuration. The maximal fading depth is 100 dB, the maximal Doppler shift is 2 MHz, and the maximal path delay can reach up …

Online Synthesis Incremental Data Streams Classification Algorithm, Sanmin Liu, Yuxia Liu

Journal of System Simulation

Abstract: Online learning is the effective way to solve the sample's non-recurrence in data streams classification, and how to deal with the problem of sample deficiency is the critical point for improving online learning efficiency. According to the mean square error decomposition theory of the model's parameter estimation and the idea of cluster, the new samples are constructed by linear synthesis with the class center and the sample, which can improve the distribution information of sample and reduce the lower bound of parameter value. The online incremental learning is executed and the class center point is continuously updated. Through theory …

Route Planning For Vessel Based On Dynamic Complexity Map, Zhe Du, Yuanqiao Wen, Huang Liang, Chunhui Zhou, Changshi Xiao

Journal of System Simulation

Abstract: Aiming at multiple mobile objects in complex navigation environment, a route planning method based on the dynamic complexity map is proposed. According to the theory of complexity measurement, a dynamic complexity map is established. By taking advantage of the idea of A * algorithm, the complexity value is taken as an actual cost and the Euclidean Distance from current point to the target is taken as a heuristic costs. Considering the ship dimensions, the channel boundary constraint function is added. The experimental results show that on the premises of satisfying the constraint of ship dimensions, the planned route …

Synthesizing Rotational Human Motion With Physical Reality, Wei Yi, Shihong Xia

Journal of System Simulation

Abstract: Both keyframes and their timings play an important role in synthesizing physically realistic human motion. However, physically plausible timings are hard to set by manual. By combing keyframes and the physics-based optimization, a new method is proposed to solve physically plausible timings of given keyframes. Firstly, the keyframes and the initial value of the timings of keyframes are set through a graphical user interface. Secondly, the physically plausible timings of keyframes are obtained by optimizing a small-size nonlinear optimization model. Finally, the rotational human motion is synthesized by the keyframes and the computed timings of keyframes. Experiments are performed …

Monkey Algorithm For Solving Logistics Center Location Selection Problem, Xiaoping Xu, Dongjie Zhang

Journal of System Simulation

Abstract: The location selection of logistics center is the most basic problem that affects the whole development of logistics center; an improved monkey algorithm is used to solve the problem. The basic idea is that the chaos variables are used to generate the initial feasible solution of the monkey algorithm, the decreasing factor is taken as the climbing step in the climbing process and a chaotic search method is introduced in the looking process to improve the performance of the algorithm. Through simulation experiment, the solution results of typical function and logistics center location problem are given to illustrate the …

Design Of Mini Folding Electric Scooter Based On Relative Attitude Angle Control, Lijun Jiang, Zhanghong Wu, Shaohui Pan, Zhelin Li, Zhiyong Xiong, Yongqing Fu

Journal of System Simulation

Abstract: To help people move conveniently after getting off the public transport in the city, anew mini electric scooter design is proposed. This new scooter uses a smart mobile phone to receive driving intention and owns more efficient, convenient and space-saving folding pattern. A kinematics model of scooter is set up and discussed. A control strategy based on the relative attitude angle, an attitude sensor data consolidation approach based on the complementary filter, a solution to the Euler angle jumping and an estimate method to the wrong operation are proposed. The design is made into a prototype based on …

Performance Analysis And Research Of Shark Fin Structure Based On Simulation, Liu Shuang, Lü Chao, Rao Yong, Shiming Wang

Journal of System Simulation

Abstract: The shark fin, the pectoral fin and the dorsal fin were studied based on the numerical simulation method; the pressure field, velocity field and flow field of the specimen structure were analyzed with three different flow velocities; the analysis and comparison of the mechanical properties of caudal fin, dorsal fin and pectoral fin were presented. The results show that the setting width of the tail fin can be set to 0.5 ~ 4.8 meters so as to improve the anti-karman vortex effect; the width of the tail fins should be relatively narrow in order to guarantee the base of …

Study And Performance Analysis Of Bar Tsv Structure, Zhensong Li, Miao Min

Journal of System Simulation

Abstract: A bar-through silicon via (B-TSV) structure is studied, and its 3D model and equivalent circuit model are proposed. The effects of design parameters formulas are investigated and concluded by a 3D electromagnetic solver. Performance comparison between B-TSV and the conventional cylindrical one is provided by simulation under the Ground-Signal-Ground configuration. The B-TSV structures are designed and fabricated in a printed circuit board (PCB) and the measured performance is given. Test results confirm that B-TSV has better performance than traditional one.

Physically-Based Dynamic Algorithms For Time-Varying Of Flowers And Leaves, Jiao Di, Yang Meng, Yang Gang

Journal of System Simulation

Abstract: This paper presents physically-based simulations of dynamic algorithms of the blossom and fading of flowers as well as the time-varying leaves following the seasons. The models of the flowers are constructed according to the previously collected primary biological data of organs of flowers. The dynamic simulation is presented by two phases: the process of blooming and the process of fading. To simulate the former, the curved surfaces of petals are controlled by controlling the points on the Bezier surface; for realizing the simulation of the latter, the physical method is used. The dynamic effects of colors of leaves according …

Emergency Condition Selection Based On Tcp-Nets, Weihong Liu, Zheng Xiao, Cheng Chen, Li Qiao

Journal of System Simulation

Abstract: The representative or relative important emergency conditions need to be selected for making well-directed emergency plans. The quantitative method is normally used to select emergency conditions, but it requires users to specify the weight of every attribute, which does not conform to the users' habit. A qualitative method for emergency condition selection is put forward which includes two steps: for the first step, TCP-nets is adopted to describe users' requirements; and for the second step, the most important emergency conditions are selected based on TCP-nets. The effectiveness of the method is proved, and the efficiency is verified by experiments …

Simulation Analysis Of Magnetic Field Effect In Induction Heating Coil Of Porous Silicon Core Furnace, Jingang Li, Gaoyuan Liu

Journal of System Simulation

Abstract: A new technology of porous coil disposable drawing a plurality of single crystal silicon rod can solve the problem of low efficiency and high cost of zone melting method of single induction heating coil in drawing monocrystalline silicon. However,the missing of the theoretical research and mature technology leads to different sizes of monocrystalline silicon rods. According to electromagnetic theory,Some characterisitics of the porous coil are studied,including magnetic field model,operating principle,magnetic field distribution.To prove the mechanism of the technology, a mathematical model of the porous coil is constructed based on Matlab and Ansys software. The magnetic flux density distribution …

Vascular Image Enhancement Using Steerable Filters, Yiren Wang, Guoqing Deng, Yingwei Xia, Zhang Long, Liu Yong, Zhang Wen

Journal of System Simulation

Abstract: Based on the weakness of traditional image enhancement algorithms, an enhancement algorithm with steerable filter is put forward, which uses computer vision system as hardware platform. A steerable filter is applied for taking vein information in different directions. The wavelet transform is used to fuse image for high frequency information on vein. The nonlinear unsharp masking enhancement algorithm is used to escalate vein image. Experiment results show that the new algorithm can effectively suppress noise, reduce information loss and achieve better enhancement.

Key Technology Of Oil Spill Visualization At Sea Surface, Changjun Zou, Yin Yong, Xiuwen Liu, Feifei Wan

Journal of System Simulation

Abstract: An intensive study is made on the visualization method and oil equipment interaction. To solve the blind area problem and to realize the interactive of oil film, the following methods are proposed: new visualization method based on texture projection; modeling technique of oil boom based on mass-spring model; dynamic interaction method between oil boom and oil film texture based on polygon clipping. Real-time oil spill visualization at sea is implemented on GPU, the test results show the correctness and reliability of the methods.

Modeling And Computer Simulation Of Numerical Experiments On Laser Propagation Through Atmospheric Turbulence, Chunyi Chen, Huamin Yang, Bin Ren, Zhengang Jiang

Journal of System Simulation

Abstract: Focusing on numerical simulations of laser propagation in atmospheric turbulence, a method for determining the grid size of optical-field samples that need to be stored in a data file was first suggested, and a simulation scheme based on a parallel computer cluster was proposed. By performing simulation examples, both the average intensity of collimated fundamental Gaussian beams propagating through atmospheric turbulence and the change in spatial-mode composition of Laguerre-Gaussian (LG) beams travelling in atmospheric turbulence were studied. Analyses show that for the case of horizontal propagation, the use of a matching approach based on zero-order moment to determine …

Aerodynamic Simulation Of Multi-Dof Flapping-Wing Air Vehicle Of Bird-Like Based On Xflow Software, Yonggang Yang, Hanping Su

Journal of System Simulation

Abstract: The aerodynamic characteristics analysis of flapping-wing is of great significance to the design, manufacturing and control of the aircraft. In this paper, a simple motion model of multiple-Degrees-of- Freedom (multi-DOF) of “swing-torsion-bending and folding” is established by analyzing the flight characteristics of bird-like flapping wing. The flapping-wing air vehicle of multi-DOF is numerically simulated in the case of unsteady flow at low Reynolds number by XFlow software. The effects of flapping wing shape, frequency and inflow on surrounding air are analyzed. The simulation results provide theory and technique supports for the flapping-wing air vehicle'research and development.

Matlab Simulation For Electrically Excited Synchronous Motors With Low Switching Frequency, Qingqing Yuan, Bin Song, Yang Na

Journal of System Simulation

Abstract: Switch loss is one of the main energy consumption of the high power transmission system, while the low switching frequency approach is an effective way to improve above issues. However, it will result in a severe harmonic distortion and further affect the control performance. A selective harmonic elimination pulse width modulation (SHEPWM) strategy has been used to ensure the low energy consumption operation of a diode clamped three-level converter whose load is a high power electrically excited synchronous motors (EESM). For the SHEPWM's characteristics of specific harmonic elimination and harmonic energy moving on the high order, a simple high-pass …

Simulation Analysis Of Nearest Neighbor Searching For Anti-Ship Missile Target Selector Performance, Sun Jie, Tianyun Wang, Huanyao Dai, Cuiqiong Mo, Zhao Jing

Journal of System Simulation

Abstract: In view of that the current admission comparing searching mode is difficult to adapt to the offshore operation of anti-ship missile in multi target selection, the nearest neighbor selector applied to the target search scheme is put forward. By setting the typical searching situation, a target searching model is established; and on the basis of reasonable simplification, the nearest neighbor selector capture probability of display expression is deduced. Typical scenes in numerical simulation show that the scheme based on distance criterion for admission multiple targets for prioritization effectively improves the search performance of the target. A …

Effect Of Interfacial Curvature On Drag Reduction Of Superhydrophobic Microchannels, Chunxi Li, Zhang Shuo, Xuemin Ye

Journal of System Simulation

Abstract: The two-dimensional fluid flow in superhydrophobic microchannels with transverse grooves was numerically simulated with Fluent to investigate the impact of the liquid-gas interface curvature on the effective slip behavior in the laminar regime. The effects of shear-free fraction, normalized periodic cell length and Reynolds number on the normalized slip length and pressure drop reduction are also examined. The results show that as protrusion angle increases, the normalized slip length and pressure drop reduction exhibit with single-hump variations. When θ=θ_opt, increments in the normalized slip length and pressure drop reduction tend to be greater as shear-free …

Channel Capacity Analysis Of Diffusion-Based Molecular Communication Model, Cheng Zhen, Lin Fei, Yanjing Lei, Huiting Zhao

Journal of System Simulation

Abstract: At present, the research on the channel capacity of diffusion-based molecular communication (DBMC) model is very limited. In the slotted point to point communication scenario, considering all the inter-symbol interferences from all the previous time slots, the optimal decisive threshold is provided by using the criterion of minimum average error probability in the detection process for the receiver nanomachine, and the mutual information expression is derived in DBMC model. Thus channel capacity of this model is analyzed. The simulation results show that the different parameters have important influences on the channel capacity. Compared to the existed point to point …

Identification Of Closed Loop Projection Subspace For Motor Based On Hankel Correlation Function, Minghong She

Journal of System Simulation

Abstract: To solve estimation deviation problem of model parameter in the closed-loop system identification, the subspace identification model and state space model based on the estimation of the correlation function are presented, and through the correlation function estimation and zero space followed by projection, the block Hankel matrix of identification framework was filled so as to obtain the scope of the extended observability matrix; on the basis of the same projection on the time offset set of related data, the RQ decomposition of the projection is calculated by numerical calculation, and the dynamic estimation of the system model is obtained. …