Artificial Intelligence and Robotics Commons^™

Large Eddy Simulation Of Effect Of Geometric Parameters On Low Pressure Of Turbulent Flow Over Gate Slot, Shihua He, Lixiang Zhang

Journal of System Simulation

Abstract: The turbulent flow over the hydraulic plane gate slot was studied using large eddy simulation method. The effects of geometric parameters including width-to-depth ratio, stagger ratio, slope ratio and fillet ratio on hydraulic characteristics within and near the gate slot were simulated systematically. According to the vulnerable cavitation locations of the flow over the slot, the pressure distributions in swirl area and the separation zone at the rear of downstream corner of the slot were investigated emphatically. The results show that the effects of width-to-depth ratios and stagger ratios on the pressure distribution of the flow are significantly. …

Deep Learning Techniques For Structural Response Prediction During Strong Ground Motions, Ahmed A. Torky, Susumu Ohno Prof., Toshide Kashima Prof.

Civil Engineering

In this paper, deep learning techniques are applied to predict a building’s structural response to strong ground motions. Data from sensors near and inside structures measure accelerations during strong ground motions. The Building Research Institute (BRI) ANX building, an eight-story structure, has experienced major earthquakes since 1998. Sensors in the building provide and accumulate big data of historic events. Changes of the natural frequency of the ANX building from the big data is initially quantified. The time-series data of the historic events can be used to predict future response to future events using deep learning models rapidly. Although previous literature …

Machine Learning Applications For Drug Repurposing, Hansaim Lim

Dissertations, Theses, and Capstone Projects

The cost of bringing a drug to market is astounding and the failure rate is intimidating. Drug discovery has been of limited success under the conventional reductionist model of one-drug-one-gene-one-disease paradigm, where a single disease-associated gene is identified and a molecular binder to the specific target is subsequently designed. Under the simplistic paradigm of drug discovery, a drug molecule is assumed to interact only with the intended on-target. However, small molecular drugs often interact with multiple targets, and those off-target interactions are not considered under the conventional paradigm. As a result, drug-induced side effects and adverse reactions are often neglected …

Large Signal Modeling For Llc Resonant Converter, Zheng Kai, Jianbing Li, Zhou Dongfang, Li Kai, Songzhen Zhang

Journal of System Simulation

Abstract: The large-signal model modeling issue of LLC resonant converter was dealt with by using averaged large-signal modeling method, on the basis of a full-bridge LLC voltage-multiplying resonant converter. The SSOC (self-sustained oscillation controller) was analyzed, and the operation mode of LLC resonant converter under the SSOC mode was investigated. The nonlinear state space model of LLC resonant converter was established by analyzing linear approximation of nonlinear terms and harmonic balance, and the averaged large-signal model of LLC resonant converter was proposed. Two curves of large signal model and nonlinear state space model were proved to be identical …

Construction Of Virtual Atmospheric Environment Based On Mm5 And Sedris, Lianlei Lin, Ding Wei

Journal of System Simulation

Abstract: The new virtual test for virtual atmosphere environment puts forward higher requirements, such as providing complex atmospheric environment which includes a variety of atmospheric parameters and improving usability and reusability of atmospheric environment data. A method to construct virtual atmospheric environment based on MM5 and SEDRIS was proposed which met the above demands. The original data of complex atmospheric environment in any region and scale was generated by using MM5 model. According to the characteristics as well as the dynamic relationship between time and space of grid of atmospheric data, SEDRIS was selected to regulate appropriate DRM class, SRF …

Measuring The Perceived Social Intelligence Of Robots, Kimberly A. Barchard, Leiszle Lapping-Carr, R. Shane Westfall, Andrea Fink-Armold, Santosh Balajee Banisetty, David Feil-Seifer

Psychology Faculty Research

Robotic social intelligence is increasingly important. However, measures of human social intelligence omit basic skills, and robot-specific scales do not focus on social intelligence. We combined human robot interaction concepts of beliefs, desires, and intentions with psychology concepts of behaviors, cognitions, and emotions to create 20 Perceived Social Intelligence (PSI) Scales to comprehensively measure perceptions of robots with a wide range of embodiments and behaviors. Participants rated humanoid and non-humanoid robots interacting with people in five videos. Each scale had one factor and high internal consistency, indicating each measures a coherent construct. Scales capturing perceived social information processing skills (appearing …

A Semi-Automated Approach To Medical Image Segmentation Using Conditional Random Field Inference, Yu-Chi Hu

Dissertations, Theses, and Capstone Projects

Medical image segmentation plays a crucial role in delivering effective patient care in various diagnostic and treatment modalities. Manual delineation of target volumes and all critical structures is a very tedious and highly time-consuming process and introduce uncertainties of treatment outcomes of patients. Fully automatic methods holds great promise for reducing cost and time, while at the same time improving accuracy and eliminating expert variability, yet there are still great challenges. Legally and ethically, human oversight must be integrated with ”smart tools” favoring a semi-automatic technique which can leverage the best aspects of both human and computer.

In this work …

Learning To Collaborate In Multi-Module Recommendation Via Multi-Agent Reinforcement Learning Without Communication, Xu He, An Bo, Yanghua Li, Haikai Chen, Rundong Wang, Xinrun Wang, Runsheng Yu, Xin Li, Zhirong Wang

Research Collection School Of Computing and Information Systems

With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning approach with the restriction that different modules cannot communicate. Our contributions are …

Extracting Deep Features From Short Ecg Signals For Early Atrial Fibrillation Detection, Xiaodan Wu, Yumeng Zheng, Chao-Hsien Chu, Zhen He

Research Collection School Of Computing and Information Systems

Atrial Fibrillation (AF) at an early stage has a short duration and is sometimes asymptomatic, making it difficult to detect. Although the use of mobile sensing devices has provided the possibility of real-time cardiac detection, it is highly susceptible to the noise signals generated by body movement. Therefore, it is of great importance to study early AF detection for mobile terminals with noise immunity. Extracting effective features is critical to AF detection, but most existing studies used shallow time, frequency or time-frequency energy (TFE) features with weak representation that need to rely on long ECG signals to capture the variation …

Time-Warped Sparse Non-Negative Factorization For Functional Data Analysis, Chen Zhang, Steven C. H. Hoi, Fugee Tsung

Research Collection School Of Computing and Information Systems

This article proposes a novel time-warped sparse non-negative factorization method for functional data analysis. The proposed method on the one hand guarantees the extracted basis functions and their coefficients to be positive and interpretable, and on the other hand is able to handle weakly correlated functions with different features. Furthermore, the method incorporates time warping into factorization and hence allows the extracted basis functions of different samples to have temporal deformations. An efficient framework of estimation algorithms is proposed based on a greedy variable selection approach. Numerical studies together with case studies on real-world data demonstrate the efficacy and applicability …

Research 4.0: Research In The Age Of Automation, Rob Procter, Ben Glover, Elliot Jones

Copyright, Fair Use, Scholarly Communication, etc.

Executive Summary

There is a growing consensus that we are at the start of a fourth industrial revolution, driven by developments in Artificial Intelligence, machine learning, robotics, the Internet of Things, 3-D printing, nanotechnology, biotechnology, 5G, new forms of energy storage and quantum computing. This wave of technical innovations is already having a significant impact on how research is conducted, with dramatic change across research methods in recent years within some disciplines, as this project’s interim report set out.

Whilst there are a wide range of technologies associated with the fourth industrial revolution, this report primarily seeks to understand what …

Research About Method Of Face Detection And Tracking Based On Active Vision, Enzeng Dong, Shengxu Yan, Jigang Tong

Journal of System Simulation

Abstract: Based on the method of combining the Camshift algorithm mixing Kalman filter with Adaboost algorithm, a face-detection and tracking algorithm on the active vision was proposed. The algorithm proposed realized the face automatic detection and tracking by using Adaboost algorithm and Camshift mixed algorithm; according to the positional relation of target centroid and the view centre, and the difference of area between the region of the face target and the view, the Pan-Tilt-Zoom (PTZ) control algorithm was designed. Through the rules designed for pan, tilt and zoom control, the algorithm achieved the goal of …

Three-Dimensional Fuzzy Control Of Catheter Robotic In Endovascular Master-Slave Interventional Surgery, Ximei Zhao, Jiankang You, Liu Hao, Hongyi Li

Journal of System Simulation

Abstract: In minimally invasive endovascular interventional surgery, catheter was vulnerable to be interfered by uncertain factors such as heartbeat and breathing of patients during catheter robot of slave side conveyed catheter. In order to retrain impact on catheter transport of these factors and realize that slave side of catheter robot system tracked control command of master side accurately and quickly, kinematic model of catheter distal bending section was established, and catheter robot system based on three-dimensional fuzzy controller was designed. Three-dimensional fuzzy controller that introduced the function of rate of error change on the basis of two-dimensional fuzzy controller …

Velocity Deception Jamming Analysis Of Coherent Video Simulation Of Anti-Ship Pd Seeker, Cuiqiong Mo, Jiahai Li, Huanyao Dai, Qiuju Chen, Zhao Jing

Journal of System Simulation

Abstract: According to existed experimental evaluation of radar electronic jamming simulation for terminal guidance, the ballistic calculation model was simplified relatively. Particle model was usually adopted which made simulation results have serious distortion. The pulse Doppler radar seeker was discussed in six degree of freedom trajectory simulation of the closed loop (PDRS) for coherent video simulation, and simulation results show that the VGPO has no direct effect on the angle tracking loop, just through guidance filter affects the convergence angle velocity estimation, which leads to little change of guidance precision. The conclusion and anechoic chamber measurements results show that the …

Algorithm For Solving Symmetric Cone Complementarity Problems, Leifu Gao, Dongmei Yu

Journal of System Simulation

Abstract: A monotonic trust region algorithm for symmetric cone complementarity problems was proposed based on a smoothing function. The problem was transformed into unconstrained optimization problem and the trust region subproblem was constructed. The problem was solved by using trust region algorithm combined with nonmonotonic strategies, and the global convergence of the algorithm was proved. Numerical experimental results demonstrate that the algorithm is effective for symmetric cone complementarity problems.

Pid Closed Loop Control Performance Analysis Of Piezostack-Driven Jet Dispensing Valve, Yunbo Fu, Xinbo Li, Guojun Liu, Jianfang Liu, Yaowu Shi

Journal of System Simulation

Abstract: A new type of piezostack-driven jetting dispenser was proposed which used hydraulic magnification, and analyzed its injection process and injection condition. The open loop model of dispensing system was built by AMESim software. The simulation proved the feasibility. The closed loop control system with PID (Proportion Integration Differentiation) algorithm was set up to improve performance of open loop dispensing system, and the open and closed loop control performance was compared under the simulation environment. Analysis shows that PID closed loop system can improve performance of piezostack-driven jetting dispensing system. When nozzle diameter is 0.1mm and syringe pressure …

Simulation Of Physical Field Of 300ka Prebaked Aluminum Reduction Cell, Shuiping Zeng, Shasha Wang, Rongjuan Wang

Journal of System Simulation

Abstract: The SY300 Prebake cell of some factory as a basic simplified model, the solidworks software was used to build a three-dimensional physical model of aluminum reduction cell. In the use of some assumptions, reasonable ideal field segmentation and under the premise of sharing model information and results, the physical model of electric field, magnetic field, flow field and its calculation module of coupling field were established respectively by using the the finite element software Comsol and Matlab Multiphysics software. On Comsol platform, electric, magnetic field of aluminum electrolytic cell were solved when replacing the anode, and current density …

Low Complexity Method Based On Fc-Ce-Slm For Papr Reduction In Ofdm System, Ce Ji, Lijuan Wang

Journal of System Simulation

Abstract: Selected mapping (SLM) algorithm uses Cross Entropy (CE) algorithm to get the most optimal sign sequence so that SLM can make the effect of PAPR Reduction achieve optimum. However, it needs too many times iterative computations, so it will increase the complexity of the algorithm. In order to solve this problem, a fast convergence factor in the CE-SLM algorithm was introduced to make the sampling probability converge to 0 or 1 quickly in the system, which reduced the iterative times of getting the optimal sign sequence. Computer simulation results show that the approved algorithm reduces the iterative times of …

Research On Parallel Simulation Of Hypersonic Vehicles, Xuegong Sun, Chunye Gong

Journal of System Simulation

Abstract: The system simulation of hypersonic vehicles was a multi-physics coupling process. It needed many iterations with large scale data to finish the simulation. To fix up the computational challenges, the distributed simulation was developed. But distributed simulation had no obvious effect on the computational efficiency. In order to enhance the computational efficiency, the grid parallel method and model parallel algorithm were studied based on the high performance cluster system. The parallel simulation method for fluid dynamics, data exchange method for partition boundary and load balance technology for parallel computing were developed and applied to the system simulation of hypersonic …

Traffic Simulation Of Elementary And Middle School's Gate Road During Student Departing School Based On Ca Model, Mingbao Pang, Chen Jing, Yang Min

Journal of System Simulation

Abstract: The simulation problem of student departing school to the traffic flow of elementary and middle school's gate road was studied by using a cellular automaton model. Based on STNS (symmetric two-lane Nagel-Schreckenberg) model, a cellular automaton model on the interference road section of elementary and middle school's gate during student departure school was established. The traffic flow characteristics of the road during student departure school time were discussed via the simulation experiment. The effects were analyzed how the proportion of students departing school by private cars, the proportion of students departing school by school buses, and the …

Simulation Research On Influence Of Blood Flow On Heating During Hifu Treatment, Suqin Dai, Shengyou Qian, Yaosheng Gui, Xiao Sheng

Journal of System Simulation

Abstract: When blood vessel exists in the tumor tissue, and its boundary portion close to the vessel will be strongly influenced by the cooling effect of the blood vessel. This influence will lead to the incomplete cancer treatment. To study the influence of blood flow on heating towards the above situation, concave spherical transducer was used as the heat source, and sound intensity distribution was obtained by Rayleigh integral. Pennes equation was solved with finite difference method, then the dose distribution was calculated to determine the thermal damage degree of tissue using quantitative relationship between the heating time and temperature. …

Hardware-In-The-Loop Test-Bed For Testing Of Lunar Rover Gnc Based On Vision-In-The-Loop, Zhiping Li, Zhang Zhi, Jianxin Chen, Wang Lei, Hehua Ju

Journal of System Simulation

Abstract: A hardware-in-the-loop and vision-in-the-loop test-bed for the testing of the lunar rover guide navigation control (GNC) subsystem was introduced. The composition of the test-bed and its dataflow were delicately designed. Then the vision-in-the-loop concept was designed. To overcome the problem of matching between the hazard-camera's focus and the images' distortion parameters, the distortion computation on the edge of the image pixels was ignored. Furthermore, to fulfill the closed-loop testing, the stereo vision function was accomplished by using multiple processes that made the images rapidly generated and the cameras' position and attitude parameters were supplied from rover's dynamics. Many …

Balanced Bee Colony Algorithm Based On Fitness Euclidean-Distance Ratio, Zhang Ming, Tian Na, Zhicheng Ji

Journal of System Simulation

Abstract: According to the power exploration and poor exploitation ability of artificial bee colony (ABC), a balanced bee colony (FER-ABC) was proposed. This algorithm modified the search equation based on “fitness Euclidean-distance ratio” and differential algorithm (DE). The FER strategy is useful for multi-optimization and the DE is beneficial to single- optimization. In order to exploit the advantages to full, a new search structure was proposed which balanced the exploitation and exploration. For continuous problems, the simulations on twelve benchmark functions indicate that this FER-ABC algorithm can improve the accuracy effectively and increase the convergence rate apparently. For the discrete …

Digital Water Depth Processing For Multibeam Based On Average Slope Of Terrain, Jiacheng Yu, Xueqiang Xu

Journal of System Simulation

Abstract: According to the characteristic of multibeam bathymetry in which measurement depth is influenced by terrain, revision algorithm was proposed based on average slope along the horizontal and vertical terrain. Five depth revision factors were obtained, and a depth smooth template was designed. The initial scan depth data were revised by the 5 revision factors, and then the revised depth data were filtered by the template. Simulation results show that, the depth of measurement error can be reduced greatly after revision, the designed template relative to the conventional Gauss template has higher smooth precision, more adapted to the water …

Decoupling Control Research Of Neutral Buoyancy Plant Based On Cmac, Peilong Li, Wang Lei, Gaofeng Li

Journal of System Simulation

Abstract: To solve the control problem of neutral buoyancy plant, a dynamic decoupling and multidimensional compound control agorithm was proposed. By the plant force situation analysis, its six degree motion control model was developed. Then a dynamic decoupling neural network was designed with the merit of adaptation of the dynamic changing coupling situation. CMAC (Cerebellar Model Articulation Controller) and PID compound control was adopted in single channel control, whose advantage is that it combines the rapidity of CMAC feedforward control and anti-interference of PID feedback control. MATLAB simulation results show that the algorithm can control the plant's position and posture …

Simulation Study Of Nodes Deployment Of Underwater Sensor Network Based On Reliability Coverage Algorithm, Juwei Zhang, Yachuang Liu

Journal of System Simulation

Abstract: For 3D nodes-deployment of the underwater sensor networks, the definitions of detection reliability and reliability coverage was proposed. According to the advanced D-S theory of evidence, the change of reliability coverage in underwater sensor networks' detection area was analyzed, and a Nodes-deployment Algorithm Based on Advanced D-S Theory of Evidence and Prior Probability (NAAEP) combining with the prior probability of target nodes distribution was proposed. The value of the target perceived reliability was transformed into a virtual potential field force that a node was suffered in size, and the position of the nodes was adjusted according to …

Simulation Research On Airborne Lidar Bathymetry System, Chengqun Fu, Xiuyuan Lü, Wang Yong, Huaixiao Wang

Journal of System Simulation

Abstract: The simulations were performed to study the Airborne Lidar Bathymetry System by application of Monte Carlo model and Phenomenological model to describe the transmission of Gauss laser beam in ocean water. Research on the relation between seawater dielectric attenuation coefficient and maximum detecting depth was conducted. The change of facular size with detecting depth was explored. Simulation results show that two models are appropriate for different instance. Part of the Airborne Lidar's parameters was analyzed by the two models. According to simulation results, the Airborne Lidar scheme is demonstrated to be feasible.

Energy Entropy And Particle Swarm Optimization Bp Neural Network Of Fault Diagnosis Techniques Of Coal Mine Cable, Zhiling Ren, Yuanyuan Zhang

Journal of System Simulation

Abstract: Aimed at solving the problem of the type of fault difficult to identification when power feeder of coal mine occurred single-phase ground fault, in order to ensure coal mines production safety, a method of fault diagnosis based on wavelet packet energy entropy (WP-EE) and combined with particle swarm optimization neural network was proposed. The type of cable fault was simulated by Matlab, the acquired post-fault voltage signal was performed the three layers wavelet Packet decomposition, the fault characteristic signals was divided into eight segments by frequency, characteristics calculated the entropy energy spectrum according to the information entropy theory, …

Study On Equipment Domain Ontology Construction For Integration Of Data Semantics, Li Kang, Xinming Li, Liu Dong

Journal of System Simulation

Abstract: Equipment domain ontology could accurately describe definition of concepts in the field and the relationships between the concepts, which is foundation and prerequisite in semantic integration of equipment data. With the analysis of the existing methods, a semi-automatic domain ontology construction method was proposed. The top-level domain ontology was built under the standard of authoritative documents in the equipment field. An initial partial ontology was generated from the equipment database by mapping. The ontology was standardized through mapping process. The results of the experiment show that this method can build equipment domain ontology which provides a unified global …

Design Of Iaas Mode “Cloud Training” System, Zhijia Chen, Yuanchang Zhu, Yanqiang Di, Shaochong Feng

Journal of System Simulation

Abstract: There are some problems in equipment web simulating training, including poor sense of reality, low efficiency of training and high difficulty of management. To solve those problems, Infrastructure as a Service mode “cloud training” was proposed. The architecture and operation flow were explained in detail and the key technologies of “cloud training” were focused on. By GPU virtualization technology, the problem of client 3D image processing capability was solved. According to the characters of simulation training, the user requirement model was established. Fuzzy algorithm was introduced to realize resource dynamic scheduling. To assure the stability and reliability, …