Computer Sciences Commons^™

Effective T2fpso-Based T2fsvm Scene Classification Algorithm, Shuqiong Xu, Conggui Yuan

Journal of System Simulation

Abstract: A systematic design methodology of Type-2 Fuzzy Particle Swarm Optimization (T2FPSO) based Type-2 Fuzzy Support Vector Machine (T2FSVM) classification system was proposed for scene image to improve selectivity and robustness in the machine vision. In the novel classification system, the T2FSVM model was presented to realize a comprehensive learning of the correct class and show the superiority of the generalization capability for classification problem. Furthermore, in order to improve the performance of PSO on complex uncertain environments, the type-2 fuzzy concept was incorporated to PSO to construct T2FPSO searching algorithm, in which the interval type-2 fuzzy inertia weight …

Intelligent Effectiveness Evaluation And Optimization On Weapon System Of Systems Based On Deep Learning, Li Ni, Yuhong Li, Guanghong Gong, Xiaodong Huang

Journal of System Simulation

Abstract: In the process of conventional WSoS (Weapon System of Systems) operational effectiveness evaluation, multiple complex steps including reconfiguring the scenario, rerunning the WSoS simulation system, and conducting effectiveness evaluation model calculations are taken. For the problems of conventional effectiveness evaluation method, such as the complex process and time-consuming, the intelligent evaluation method of WSoS combat effectiveness based on machine learning regression is proposed, and the optimization process of combat effectiveness based on evolutionary strategy is introduced. Taking the full connection depth regression network as the prediction model, the guiding selection principles of network hidden layer number and sample …

Research On Nodes Re-Optimization Of Microwave Relay Network, Yunjun Lu, Kebin Chen, Mengyao Han, Yiqiao Jin

Journal of System Simulation

Abstract: The microwave relay network nodes are studied and the topology is optimized. Considering the link attenuation probability, node attraction coefficient and communication redundancy, the optimal link set is obtained by genetic algorithm with the idea of network topology optimization. By calculating the degree of each node in the optimal link set and sorting the node with the value of degree, the candidates of the trunk nodes are given. The microwave relay network topology given by the conventional method is optimized. The method has certain versatility. It can be applied to the selection of other network trunks and relay nodes …

Dynamic Equivalent Modeling And Simulation Of Wind Farm Based On Asw-Fcm Algorithm, Mudan Li, Yinsong Wang

Journal of System Simulation

Abstract: A new dynamic equivalent modeling method is proposed for the wind farm of directly-driven wind turbine with permanent magnet synchronous generator (D-PMSG). The wake effect and wind direction change between multiple wind turbines are considered to calculate the effective input wind speed, the effective wind speed, rotor speed, pitch angle and output power are selected as the multi-group indicators after analyzing the wind turbine operating characteristics. Considering the differences and relevance of the operating conditions between the turbines, an adaptive sample weighting fuzzy C-means clustering algorithm (ASW-FCM) is designed to optimally cluster the wind farm. The clustered wind turbine …

Investigation Of Hybrid Positioning Algorithm Based On Wifi, Fucheng Yin, Wu Dong, Wang Yan, Zhicheng Ji

Journal of System Simulation

Abstract: TDOA(Time Difference of Arrival) and AOA(Angel of Arrival) methods require additional sensing mechanisms and have poor positioning accuracy used in WiFi environment, so a novel TDOAAOE hybrid positioning algorithm was proposed. The proposed algorithm used the AOE (Angle of Emission) information instead of AOA information to estimate the position of a WiFi-based mobile terminal. In this method, access points emitted signals with angle information encoded in beacon packets through directional antennas; which was rotated by motors. WiFi-based mobile devices estimated angles of the access points by receiving and decoding these beacon packets, which calculated the position themselves. This method …

Self-Adaptive Multi-Swarm Particle Swarm Optimization Algorithm, Xuewen Xia, Bojian Wang, Jin Chang, Guoliang He, Chengwang Xie, Wei Bo

Journal of System Simulation

Abstract: To overcome the shortcomings of poor ability to escape a local optimal, premature convergence and low precision of the traditional particle swarm optimization algorithm (PSO), a self-adaptive multi-swarm particle swarm optimization (SMPSO) was proposed. In SMPSO, the whole population was divided into many parallel-evolution multi-swarms, the aim of which was to keep diversity of the population. Furthermore, a self-adaptive regrouping operator was proposed to reinforce the information sharing and interaction between different swarms. In addition, particles’ historical information were periodic sampling and the statistics results were used to direct the best solution to carry out a detecting …

Precisely Algorithm And Simulation Of Plurality Of Random Deployed Circulars’ Total Coverage Area, Zhang Ye, Liu Kui, Yuzhi Chen, Junyang Liu, Jianchao Du

Journal of System Simulation

Abstract: A precisely algorithm of total coverage area when a plurality of circulars are random deployed and overlapping with each other is needed. The key issues of the solution are the calculating principle of the overlapping area, the differentiation and enumeration of the multi-overlapping circulars, and the calculation of the multi-shaped curved edges. Based on the inclusion-exclusion principle, overlapping area was added or subtracted to the amount area. The computer calculation process was proposed. Because the circulars are random deployed, in order to ensure the area coverage, the area cover rate problem of repeatedly deployment of the circulars were …

Assessment Model Of Conflict Probability At Airport Surface Intersection, Weijun Pan, Xiaolin Luo, Kang Rui, Chenyu Huang, Zhenghong Xia, Wenbin Qiu

Journal of System Simulation

Abstract: Based on aircraft characteristics, the assessment model of conflict probability at airport surface intersection was studied to ensure the safety of airport ground safety. The engine jet effect distance was introduced to expand the scope of intersection conflict, describing the process of aircraft conflict. The model with the actual operation data was verified, and the speed interval's impact on the model was analyzed and discussed. In the view of three motion states of aircraft, this model analyzed the variations in conflict probability. When speed variation range is 0.5m/s, probability analysis of the conflict is more ideal, and can improve …

Method To Calculate Multi-Objective And H2/H∞ Control Of Vehicle Vertical Vibration System, Jianjun Meng, Bai Huan, Mou Jian, Yin Ming, Xuri Guan

Journal of System Simulation

Abstract: Aiming at the disadvantage of single object in railway vehicle damping system,the multi-objective optimal control law of railway vehicle damping system was devised to balance shock absorption control and energy saving control. To improve the riding comfortability and reduce the energy consumption, the multi-objective H₂/H_∞ output-feedback controller based on LMI was developed for an active suspension of 6-DOF vertical vibration model of railway vehicle. Norm H₂ of the actuator output was taken as the energy consumption indexes, and norm H_∞ of the vertical vibration displacement, the acceleration and the nutation angle was taken as …

New Voltage Balancing Method For Cascaded Rectifier Based On Predictive Power Model, Hongbin Pan, Linhai Liu, Zhiyong Xiao, Sicheng Ou, Maokun Zhu, Fen Xu

Journal of System Simulation

Abstract: The dq synchronous system was built by constructing virtual orthogonal voltage and current based on second order generalized integrator. The predictive power model was derived to construct main control system of cascaded H-bridge rectifier combining the instantaneous power theory, which took the duty cycle of active and reactive power as control object. Then, a new voltage balancing control strategy was proposed dealing with the problem of DC voltage imbalance in cascaded H-bridge rectifier. The modification of active power was obtained by the voltage balance controller when the objective function of coupling effect achieves minimum and the active power was …

Global Optimized Photovoltaic Mppt Algorithm Based On Pso And Incremental Conductance Method, Yunjun Yu, Liu Tao, Shisheng Wang, Jianbo Xin, Xiaohua Nie

Journal of System Simulation

Abstract: The P-V array characteristic curve exhibits a plurality of local maximum power point under conditions of partial shading. The incremental conductance method maybe track an extreme value point that is not the largest power point, thus lead to tracking failure. The PSO algorithm has the characteristics of global optimization, but its tracking precision is deficient. A global MPPT algorithm based on PSO algorithm by incremental conductance method was proposed, PSO algorithm could quickly locate to the approximate global MPP, INC could further precise the MPP. Compared to the traditional incremental conductance method Simulink simulation and the research when …

Viability Control Of Rigid Body Wheeled Robots For High Speed Obstacle Avoidance, Liu Lei, Gao Yan, Yuepeng Wu

Journal of System Simulation

Abstract: The robot is taken as a point during most existing obstacle avoidance control methods for wheeled robot. These methods have limitations in actual situation. When a robot is considered as a rigid body, in order to get high speed performance, the relationship between robot model, contour and obstacle should be considered in detail. An approach to avoiding obstacle with high speed based on viability theory was proposed for wheeled robots. The line features were extracted from the obstacles, and then high dimension viability boundaries were designed via these features, rigid body contours and states of the robot. According to …

Energy Efficiency Optimization For Discrete Manufacturing Workshop Based On Discrete Teaching-Learning-Based Optimization Algorithm, Junhui Xu, Wang Yan

Journal of System Simulation

Abstract: Because the discrete manufacturing workshop is multi-objective and multi-constraint, an energy efficiency optimization model whose optimization objective was to minimize the total energy consumption was built for discrete manufacturing workshop. Besides, an improved teaching-learningbased (TLBO) optimization algorithm for discrete energy efficiency workshop optimization was proposed. This improved algorithm introduced adaptive parameter in training phase to improve the learning efficiency and adaptability of the algorithm. In addition, second discrete process was introduced in the teaching stage and learning stage, respectively. This algorithm could be applied to the optimization of discrete manufacturing workshop under the precondition of ensuring the …

Simulation Technology Research On Streak Tube Imaging Lidar, Wenze Xia, Shaokun Han, Jingya Cao

Journal of System Simulation

Abstract: A simulation model on streak tube imaging lidar was introduced. The range equation of lidar, the pulse model of illuminating laser and the scanning equation were used in the model. The system noise was analyzed. The experiment result shows the effectiveness of proposed simulation model. The effect of the pulse laser peak power on distance precision of reconstructed range image was analyzed. This method provided theoretical guidance and desired result inspection for designing of the streak tube imaging lidar.

Modeling And Simulation Of Offshore Support Vessel Anchoring Operation, Hongbo Sun, Chaojian Shi, Wenjin Lin

Journal of System Simulation

Abstract: In order to understand the configurations of mooring line and working wire, tension variation at release point of working wire and the influence of the offshore support vessel during anchoring operation, a mathematical models of OSV anchoring operation was established. According to the MMG (Ship Manoeuvring Mathematical Model Group) ship motion mathematical modeling theory, a 6dof ship motion mathematical model was built. And a 6dof cable motion mathematical model was established with finite difference method. A coupling ship-cable-anchor-cable system model was established. The system motion simulations were carried out, and the results indicate that the model …

Energy Consumption Analysis Of Discrete Manufacturing Based On Improved Principal Component Analysis Method, Chen Yan, Wang Yan

Journal of System Simulation

Abstract: Due to the complexity of energy consumption of the discrete manufacturing system and the interaction between energy consumption indexes, the result of energy consumption analysis is hard to obtain, establishing energy efficiency evaluation index of discrete system, based on the three levels of energy consumption of products, equipment energy efficiency, the energy efficiency of task process. Furthermore, a method was proposed to analyze the discrete manufacturing process energy consumption based on improved principal component analysis method. The method introduced importance weights, overcame the shortcoming of traditional component analysis, which only emphasized the information weights, combined the subjective and …

Multi‑View Clustering For Multi‑Omics Data Using Unifed Embedding, Mohammed Hasanuzzaman, Sayantan Mitra, Sriparna Saha

Articles

In real world applications, data sets are often comprised of multiple views, which provide consensus and complementary information to each other. Embedding learning is an effective strategy for nearest neighbour search and dimensionality reduction in large data sets. This paper attempts to learn a unified probability distribution of the points across different views and generates a unified embedding in a low-dimensional space to optimally preserve neighbourhood identity. Probability distributions generated for each point for each view are combined by conflation method to create a single unified distribution. The goal is to approximate this unified distribution as much as possible when …

Multi‑View Clustering For Multi‑Omics Data Using Unifed Embedding, Mohammed Hasanuzzaman, Sayantan Mitra, Sriparna Saha

Department of Computer Science Publications

In real world applications, data sets are often comprised of multiple views, which provide consensus and complementary information to each other. Embedding learning is an effective strategy for nearest neighbour search and dimensionality reduction in large data sets. This paper attempts to learn a unified probability distribution of the points across different views and generates a unified embedding in a low-dimensional space to optimally preserve neighbourhood identity. Probability distributions generated for each point for each view are combined by conflation method to create a single unified distribution. The goal is to approximate this unified distribution as much as possible when …

Modeling And Simulation On Dynamics Of Epidemic Disease Based On Social Division Of Labor, Haibin Li

Journal of System Simulation

Abstract: Prediction is an essential part of the epidemic prevention and control system, and it is of great significance to accurately establish a dynamic model of epidemiological evolution. The existing epidemiological modeling methods rarely consider the social division of labor of different groups. The entire group is divided into three subgroups, the ordinary residents, the social service personnel, and the front-line medical workers. Based on the heterogeneous uniform mixing theory, the subgroup adjacency matrix is used to represent the contact relationship between individuals, and a time-lapse dynamic model of epidemic spread and evolution is established. The simulation results show that …

Machine Learning Uncovers The Most Robust Self-Report Predictors Of Relationship Quality Across 43 Longitudinal Couples Studies, Samantha Joel, Paul W. Eastwick, Colleen J. Allison, Ximena B. Arriaga, Laura B. Luchies

University Faculty Publications and Creative Works

Given the powerful implications of relationship quality for health and well-being, a central mission of relationship science is explaining why some romantic relationships thrive more than others. This large-scale project used machine learning (i.e., Random Forests) to 1) quantify the extent to which relationship quality is predictable and 2) identify which constructs reliably predict relationship quality. Across 43 dyadic longitudinal datasets from 29 laboratories, the top relationship-specific predictors of relationship quality were perceived-partner commitment, appreciation, sexual satisfaction, perceived-partner satisfaction, and conflict. The top individual-difference predictors were life satisfaction, negative affect, depression, attachment avoidance, and attachment anxiety. Overall, relationship-specific variables predicted …

Modified Surrogate Cutting Plane Algorithm (Mscpa) For Integer Linear Programming Problems, Israa Hasan

Emirates Journal for Engineering Research

This work concerned with introducing a new algorithm for solving integer linear programming problems. The improved algorithm can help by decreasing a calculation the complexity of these problems, an advantages of the proposed method are to reduce the solution time and to decrease algorithmic complexity. Some specific numerical examples are discussed to demonstrate the validity and applicability of the proposed method. The numerical results are compared with the solution of integer linear programming problems by using cutting plane method (Gomory method).

Exploring The Efficacy Of Transfer Learning In Mining Image‑Based Software Artifacts, Natalie Best, Jordan Ott, Erik J. Linstead

Engineering Faculty Articles and Research

Background

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. In previous attempts to classify image-based software artifacts in the absence of big data, it was noted that standard off-the-shelf deep architectures such as VGG could not be utilized due to their large parameter space and therefore had to be replaced by customized architectures with fewer layers. This proves to be challenging to empirical software engineers who would like to make use of existing architectures without …

Combining Crf And Deformable Part Model For Pedestrian Detection, Ma Ji, Jingjiao Li, Ma Li, Zhao Yue

Journal of System Simulation

Abstract: Pedestrian detection has been widely used in many fields. It is one of the focus in computer vision. The part-based detection method in the pedestrian detection shows excellent performance and has a strong adaptability in posture change of human body. But it is not good for Occlusion problem. When the Discriminative threshold is higher, miss rate is very high. Considering the disadvantage of LSVM method for mining hidden information, a two layers classifier was proposed based on the deformable parts model establishing conditional random field model for Occlusion problem. For learning model parameters, the stochastic gradient descent and …

Virtual Needle Insertion And Haptic Interaction, Gao Zhan, Pan Fei, Jiehua Wang, Haiyan Pan, Zhengzheng Jiang

Journal of System Simulation

Abstract: Needle insertion or puncture has been widely practiced in clinical medicine. A VR based training system for needle insertion was implemented in this study. The mechanical model during insertion process was designed. Linear element model was applied to realize the simulation of soft tissue deformation. The friction and the stick-slip motion model between the puncture needle and the soft tissue were implemented to simulate the force interaction between needle and soft tissue. The haptic interaction of needle insertion was realized as well to enhance the user experience. The experiment results show that the simulation can reflect the process …

Planar Structure Reconstruction For Indoor Scenes With Kinectfusion, Chenjianong Cai, Yifei Shi, Xu Kai, Dang Gang

Journal of System Simulation

Abstract: Online scanning and reconstruction with KinectFusion has greatly improved real-time reconstruction of indoor scenes with consumer depth camera. However, due to the limitation of depth resolution of current depth cameras, the quality of reconstructed scenes is in general unsatisfactory. This is especially true for planar structures which are commonly seen in indoor scenes and important in defining the major structure of an indoor room. A novel method was proposed for extracting and reconstructing planar structures from point clouds of indoor scenes scanned acquired by KinectFusion.

Automatic Hair Contour Extraction Method With Complex Background, Yaoli Jin, Shiliang Wang, Xu Gang, Weihua Hu, Yigang Wang

Journal of System Simulation

Abstract: Hair contour extraction has important application in digital entertainment and simulation. An automatic hair contour extraction method for images with complex background was proposed. Image segmentation algorithm from foreground image was used to eliminate the interference of background image; face recognition and hair detection algorithms were employed to find the hair position and realize the automatic identification of the hair; in order to improve the accuracy of contour extraction, adaptive skin detection algorithm was used to eliminate the interference of face. The proposed method was applied on a lot of image examples. Experimental results demonstrate that this method can …

Research For Skeleton Tree Matching Of Microscopic Image Of Diatom Cells, Xiaoyan Qiao

Journal of System Simulation

Abstract: The image analysis technology based on morphological differences has become an important method of algae recognition in recent years. A skeleton similarity matching method was proposed to recognize microscopic images of diatom cells. The gray surface vector model of image was established to make segmentation by keeping obscure seta; The skeleton was used to represent the Chaetoceros, and it was decomposed hierarchically by competition strategy. The Chaetoceros object was represented by skeleton tree by forming the rachis elements and branches into it. The similarity mode for microscopic images of Chaetoceros was established by defining the topological and geometric difference. …

Simulation Model Of Crowd Following Phenomenon In Emergencies, Fang Hao, Liu Zhen, Lu Tao, Liangping Liu, Tingting Liu, Cuijuan Liu

Journal of System Simulation

Abstract: Researches on crowd behavior in emergent events are important practical significance for emergency management, most of the current crowd models are collision detection, motion plan and so on. According to the emergency scene analysis of surveillance video, following behaviors of crowd are obviously, modeling following behaviors is an interesting topic in crowd simulation. A following model was proposed based on classical social force model and OCEAN personlity theory, the concept of panic was introduced,, and following conditions of individual was set up, the speed formulas of individual were constructed. Experimental results show that the following model can closely simulate …

Real-Time Rendering Of Large-Scale Coastal Water Based On Adaptive Optimization, Shunli Wang, Fengju Kang, Jianhua Xu

Journal of System Simulation

Abstract: Focusing on the complex of the wave model and the poor performance of real-time in the large-scale coastal water visualization, a new method based on adaptive optimization for coastal water rendering in real-time was proposed. By introducing the automatic merging algorithm, the complex wave model could be constructed. According to the collision detection technology, the water mesh could be adaptively optimized. In order to improve the realistic, a noise was added to the water surface. The foam and reflection were realized by applying the dynamic texture mapping technology. The experimental results show that the generated coastal water has higher …

Development Of A Virtual Reality System For Space Planning Simulation, Wenbo Yang, Yinhao Song, Zhao Xin

Journal of System Simulation

Abstract: A virtual reality platform for space simulation was developed to simplify the implementation of weapon and based design. First, the architecture of the simulation system was described briefly; Second, based on the characteristics of space simulation platform, several key modules were introduced, including terrain real-time generation, analysis of space layout, and closest distance calculation. The terrain generation for space simulation platform was based on database management. The closest distance calculation was based on nearest neighbor k-d tree searching. In addition, a three-dimensional (3-D) model library, containing vehicles, test equipment, plant facilities, and other tools, was established for dynamic loading …