Artificial Intelligence and Robotics Commons^™

Research On A Novel Biogeography-Based Optimization Algorithm Based On Ga, Wang Ning, Lisheng Wei

Journal of System Simulation

Abstract: In order to further improve the optimization ability of biogeography-based optimization algorithm, a new genetic algorithm is proposed. The selection operation is added before the migration operation, and the migration individual is selected by the method of "roulette", so that the individuals with higher fitness can be preferentially migrated. The mutation operation combines the genetic gaussian mutation method, and the optimization performance of the algorithm is improved. The convergence condition of the method is derived in theory. Five test functions are used in the experiments, and the results prove that the ameliorated algorithm is better at the results of …

Bacterial Foraging Algorithm With Gravitational Mechanism, Yitao He, Li Jun, Liyan Hao

Journal of System Simulation

Abstract: Aiming at the weak quorum sensing ability and slow convergence in bacterial foraging algorithm, an algorithm with gravitational mechanism is proposed. The algorithm provides an optimization direction for each bacterium by introducing a gravitational mechanism in the gravitational search algorithm. The original swimming operation of bacterial foraging algorithm is used to realize the local optimization strategy, and the local dimension update is added after the swimming to widen the bacterial search scope in chemotaxis operation. In the migration operation of the bacterial foraging algorithm, the bimodal Gaussian function is introduced to re-initialize the position of the bacteria to avoid …

Interactive Assembly Simulation Platform For Complex Gearbox In Virtual Environmen, Chunyang Jia, Xiangjun Zou, Jinhui Li, Zeqin Zeng, Wang Jie

Journal of System Simulation

Abstract: Aiming at the human-computer interaction, behavior simulation and user design in virtual assembly, based on the complex gearbox of large tractors, the simulation method of dynamic motion and behavior of gear with multi-collision body is studied. The positioning method of multi-part model based on axis constraints and surface constraints in virtual environment is proposed. The virtual environment of human-computer interaction is developed. The consumed time of per frame is about 10 ms, and the complex variable-speed motion behavior and its simulation are realized. The virtual assembly system is equipped with AR interface, which can realize the active intelligent virtual …

Ship's Rudder/Fin Joint Anti-Rolling Mpc Control Based On Feedback Linearization, Li Hui, Yingnan Xie, Liqi Lan

Journal of System Simulation

Abstract: Aiming at the nonlinearity, strong coupling and multivariate characteristics of the ship motion system, and considering the influence of marine environment on ship motion, a four-degree-of-freedom (surging, swaying, rolling and yawing) motion nonlinear mathematical model is established to comprehensively represent the essential characteristics of ship motion. Since the model predictive control is an applied multivariable optimal control strategy, the ship rudder/fin joint anti-rolling Model Predictive Control (MPC) system based on feedback linearization is designed. The simulations of ship rolling and course-keeping joint control are carried out under different sea conditions, and the results show that the control method is …

Vertical Flight Simulation Performance Analysis Based On Power Function Control Command, Zhongjun Qu, Zeyu Kang, Yongmei Cheng

Journal of System Simulation

Abstract: Based on the fly height control method of modal direct switching, after the input of the control command, the control output may be oscillated or even diverged. The power function conforms to the variation law of the flight altitude command, and is used as the prototype function to derive the relationship between the given height, the current height and the vertical velocity. Using this transformation relationship as the input command of the vertical velocity control loop, a smooth control system is designed. The system does not require control modal switching and can achieve the flight altitude maintenance andflight altitude …

Dynamic Vehicle Distribution Path Optimization Based On Improved Intelligent Water Drop Algorithm, Shuangnan Fan, Jiming Chen, Weimin Gao, Zengfeng Wang

Journal of System Simulation

Abstract: In view of the unreasonable distribution path, low distribution efficiency and demand uncertainty in the current vehicle distribution process, a dynamic vehicle distribution path optimization method based on the improved intelligent drop algorithm is proposed. According to the customer's demand for delivery time, the soft time window penalty function and customer satisfaction function are constructed. Based on the characteristics of vehicle speed, damage cost, penalty cost and customer satisfaction of vehicle distribution, a vehicle path optimization model is established. The vehicle path optimization model is solved by the intelligent water droplet algorithm. The grey wolf optimization algorithm is used …

Optimal Control Research On Vehicle Magnetorheological Semi-Active Suspension Of Four Degrees Of Freedom, Yongshu Jia, Ahai Miu

Journal of System Simulation

Abstract: Based on system dynamics theory of vehicle, aiming at the model of 1/2 vehicle suspension, the vehicle magnetorheological semi-active suspension dynamic equation and space state equation with four degrees of freedom are established. A linear two times optimal controller and control algorithm for semi-active suspension are designed, and the control strategy based on magnetorheological damper of subdivision vibration velocity is proposed. Suspension simulation model is established to analyze the optimal control effect in SIMULINK. The results show that the magnetorheological semi-active suspension system based on the optimal control of the vehicle can reduce vehicle vertical vibration acceleration and vehicle …

Dynamic Environmental And Economic Dispatching Of Wind Farm Based On Multi-Objective, Le Wei, Xijin Li

Journal of System Simulation

Abstract: Wind farms are developing rapidly under the new policy on energy resources vigorously advocated by the state. Its output scheduling is very complex, and needs the integration of economic and environmental factors. Aiming at the large prediction error of wind power, in the dynamic environmental economic dispatch of wind farm, the cost of rotating reserve is taken into account within the generation cost, and the demand of wind power prediction error for rotating reserve capacity is taken into account within the constraint condition. Aiming at the minimum total cost of power generation, the minimum total pollutant emission and minimum …

Combat Effectiveness Simulation Evaluation Framework Of Complex Weapon System, Yonglin Lei, Zhu Zhi, Bin Gan, Lei Sen, Chen Yong

Journal of System Simulation

Abstract: Combat effectiveness evaluation of complex weapon system is a scientific issue both military departments and defense industry concern. Current researches on simulation-based weapon system combat effectiveness evaluation lack the specificity to complex weapon system and a simulation-based formal combat effectiveness evaluation framework is especially desired. A framework is created and formalized on three measure layers of performance-outcome-effectiveness. Within the framework, simulation inputs are classified into different categories different outcome measure layers and different effectiveness measure layers are considered. An example of combat effectiveness evaluation framework for typical ballistic missiles is presented to demonstrate the proposed framework.

A Continuous Non-Invasive Blood Pressure Prediction Method Based On Improved Svr Learning, Haixia Fan, Xiaohui Chen

Journal of System Simulation

Abstract: Aiming at the accuracy of continuous non-invasmive monitoring of blood pressure by photoelectric method based on the photoplethysmography (PPG) signal and the electrocardiography (ECG) signal, is influenced by the differences of human characteristics, a blood pressure prediction method based on principal component analysis (PCA) and genetic algorithm (GA) to optimize machine learning model is proposed. The method processes the PPG signal, ECG signal and human body features to form a feature matrix, and uses an improved SVR learning model to perform regression training on the feature matrix and the real-time blood pressure value measured by the mercury sphygmomanometer. …

Cover Song Identification - A Novel Stem-Based Approach To Improve Song-To-Song Similarity Measurements, Lavonnia Newman, Dhyan Shah, Chandler Vaughn, Faizan Javed

SMU Data Science Review

Music is incorporated into our daily lives whether intentional or unintentional. It evokes responses and behavior so much so there is an entire study dedicated to the psychology of music. Music creates the mood for dancing, exercising, creative thought or even relaxation. It is a powerful tool that can be used in various venues and through advertisements to influence and guide human reactions. Music is also often "borrowed" in the industry today. The practices of sampling and remixing music in the digital age have made cover song identification an active area of research. While most of this research is focused …

F-Measure Optimisation And Label Regularisation For Energy-Based Neural Dialogue State Tracking Models, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

In recent years many multi-label classification methods have exploited label dependencies to improve performance of classification tasks in various domains, hence casting the tasks to structured prediction problems. We argue that multi-label predictions do not always satisfy domain constraint restrictions. For example when the dialogue state tracking task in task-oriented dialogue domains is solved with multi-label classification approaches, slot-value constraint rules should be enforced following real conversation scenarios.

To address these issues we propose an energy-based neural model to solve the dialogue state tracking task as a structured prediction problem. Furthermore we propose two improvements over previous methods with respect …

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 …

An Enhancement Of Age And Gender Classification Accuracy With Hybrid Handcrafted And Deep Features Using Hierarchical Extreme Learning Machine, Mohammad Javidan Darugar

Student Works (2020-2029)

Age and gender classification are some of the essential algorithms that have many use cases in our everyday life. For example, in robotics, field robots can interact with a human base on their gender in data analysis, to have statistics about age and gender of audiences in social events, YouTube video analysis, and many other applications. In this research, we have addressed limitations in deep neural networks, which by overcoming this limitation, we can gain better accuracy and performance. Our study has several other possible applications which are not limited only to age and gender classification. This dissertation is about …

Research Overview On Modeling And Solution Of Aerospace Tt&C Scheduling Problem, Qingqing Yan, Huairong Shen, Qiongling Shao

Journal of System Simulation

Abstract: The research of Aerospace TT&C Scheduling (ATT&CS) is very important, because of its support for TT&C scheme decision-making and TT&C resource net constructing. The classification and resolution flow of the ATT&CS problem were introduced. Then, the modeling methods and related key techniques, such as designing of object function, analysis of constraints, and priority determining, were analyzed. The solving algorithms and conflict resolution methods were summed up, and the major categories of algorithm were evaluated. The main content of scheduling evaluation research was summarized. The possible future researches for related techniques were discussed based on the analysis of development and …

Overview Of Development And Current Progress In Maritime Simulation Research, Xinping Yan, Wu Bing, Wang Yang, Xiaoyang Wei

Journal of System Simulation

Abstract: Maritime simulation plays an essential role in security of ship navigation, the innovation of the administration and the improvement of management ability. The traditional maritime simulation was surveyed, and the scope of maritime simulation was specified. Moreover, the research related to maritime simulation was overviewed under the proposed scope of maritime simulation. To gain a deeper insight into the research domain, maritime simulation was scrutinized in two dimensions. From the perspective of the simulation scale, modeling characters, and user requirements, maritime simulation was divided into macro, medium and micro scales; whereas in the viewpoint of comprehensive safety …

Principe Of Behavior Computing On Emotional Game, Guofeng Zhang, Wang Niu, Xiong Hu

Journal of System Simulation

Abstract: Emotions is analyzed by mathematical statistics as an influence factor on behavior interaction in the current behavioral game researches. On the face of the status quo, premising emotion rationality that is the alternative to results rationality, a fresh emotional game computing principle was proposed by building emotion behavior schemata function. The suggested thought was applied to a modified ultimatum game computing, an emotional equilibrium outcome was obtained, and the psychological mechanism of the brave behavior was revealed. Meanwhile, the basic principle of pattern recognition to behavior selection mode was established. According to the constraint conditions of …

Simulation And Analysis Of Wind Turbine Echoes, Weikun He, Yuluo Shi, Xiaoliang Wang, Yuzhao Ma, Renbiao Wu

Journal of System Simulation

Abstract: Wind turbines can have serious effect on ATC radar, communication and navigation equipments. Thus electromagnetic scattering features of wind turbine and its echo simulation technology are of vital significance to wind farm clutter suppression and ensure air traffic safety. Based on the model of wind turbine scattering points superposition, the radar echo simulation of the wind turbine was studied. Meanwhile, the effect of azimuth angle and elevation angle of the incident wave on the echoes were considered and the model of radar echo signal for any observation points was established. In addition, the characteristics of time domain, …

Full-Scale Dynamic Simulation For Structure Safety And Schedule Coupling Of Rcc Gravity Dams, Sherong Zhang, Chengbo Du, Wenqi Sa, Gaohui Wang, Wang Chao

Journal of System Simulation

Abstract: By establishing the dynamic mapping relationship between the set of the construction state and the set of the emulation state of numerical simulation model, the method of three dimension and full-scale dynamic simulation for structure safety and schedule coupling during construction process was built. The method was used to dynamically analyze structure safety under any construction schedule condition of dam. VTK was utilized to realize three dimension and full-scale dynamic visualization for structure safety and schedule status coupling of RCC gravity dam during construction process. A three dimension and full-scale dynamic simulation and visualization system for structure safety and …

Research Of Radio Frequency Environment Algorithms For Radar System Of System Combat Simulation, Xinjun Zhao, Quanmin Wang, Yongxian Zou, Yufei Jia

Journal of System Simulation

Abstract: In weapons and equipment system of system simulation, radar systems are usually necessary composition. A complete radar combat system generally consists of radar models and electromagnetic (EM) environment models, and the reliability of simulation results was decided by these two elements. Despite of various radars, the EM environment simulation, especially radio frequency(RF) environment simulation, could be synthesized into a common and general purpose model, and support various radar simulation system. Based on RF environment effects analysis and their algorithms, a synthesized RF environment effect model was proposed, which could provide calculation for RF radar simulation. Two simulation examples involving …