Artificial Intelligence and Robotics Commons^™

A Matheuristic Algorithm For Solving The Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

This paper studies the integration of the vehicle routing problem with cross-docking, namely VRPCD. The aim is to find a set of routes to deliver single products from a set of suppliers to a set of customers through a cross-dock facility, such that the operational and transportation costs are minimized, without violating the vehicle capacity and time horizon constraints. A two-phase matheuristic approach that uses the routes of the local optima of an adaptive large neighborhood search (ALNS) as columns in a set-partitioning formulation of the VRPCD is designed. This matheuristic outperforms the state-of-the-art algorithms in solving a subset of …

Improving Syntactic Relationships Between Language And Objects, Benjamin Wilke, Tej Tenmattam, Anand Rajan, Andrew Pollock, Joel Lindsey

SMU Data Science Review

This paper presents the integration of natural language processing and computer vision to improve the syntax of the language generated when describing objects in images. The goal was to not only understand the objects in an image, but the interactions and activities occurring between the objects. We implemented a multi-modal neural network combining convolutional and recurrent neural network architectures to create a model that can maximize the likelihood of word combinations given a training image. The outcome was an image captioning model that leveraged transfer learning techniques for architecture components. Our novelty was to quantify the effectiveness of transfer learning …

Multi-Objective Signal Timing Optimal Model For Rural-Urban Fringe Area Intersection, Xiaoyu Zhang, Chunfu Shao

Journal of System Simulation

Abstract: With the acceleration of the urbanization process in our country, the road traffic problems in the urban-rural fringe area are becoming serious. In order to improve the traffic efficiency, environmental benefits and traffic safety, a multi-objective optimal model for signal timing is established under the comprehensive consideration of several factors, such as the delay, capacity, number of stops and vehicle emissions. The genetic algorithm is used to solve the problem. A typical intersection is taken as the example for the analysis and the improved design schemes can be achieved and evaluated by the road traffic simulation. The …

Lightmap-Based Gi Collaborative Rendering System For Web3d Application, Shao Wei, Liu Chang, Jinyuan Jia

Journal of System Simulation

Abstract: For the real-time dynamic lighting rendering in low-end web environment, a view-independent collaborative real-time rendering system is presented. The whole system consists of a cloud renderer which produces the global illumination, a web renderer which computes the local illumination, and a scalable collaboration solution which takes the user behavior into account to adjust the range and frequency of the lighting computation. The cloud renderer computes the lighting data into the Lightmap, streams the Lightmap to the web client. After computing the direct light, the web renderer achieves the global illumination information by Sampling the Lightmap, and shows the …

Research On Modeling And Analyzing Method Of Task-Oriented Network Information System Of Systems, Zhu Tao, Weitai Liang, Songhua Huang, Jieyong Zhang

Journal of System Simulation

Abstract: As the catalyst and fusion agent of the system combat capability in the information age, the network information system of systems has been changing the form of information-based warfare and the mode of combat effectiveness generation. On the basis of studying the concept of the network information system of systems and introducing association mapping rules between tasks and systems, a new modeling and analyzing method of the network information system of systems with two dimensions and four networks, based on super-network and service-oriented characteristics, is proposed. The definitions of services information flow motif delay, the task execution accuracy …

Thinking On Digital Twin For Weapon System, Junhua Zhou, Junjie Xue, Heyu Li, Ji Hang, Tingyu Lin, Guoqiang Shi

Journal of System Simulation

Abstract: The main development process of the digital twin technology is reviewed and its necessity for the weapon system is put forward. The definition and composition of the digital twin for the weapon system is given and its application architecture and key technologies, such as the construction of the digital thread, bi-directional collaborative simulation and control, intelligent autonomous evolution, digital twin operation support based on the container-simulation-cloud, et al, are analyzed. The preliminary research and practice of some key technologies is expounded, and the future research directions are summarized and looked forward to.

Modeling And Propeller Location Optimization For Diving Propeller Vehicle, Jianjun Zhang, Yang Bing, Jinhui Wu, Yan Qiang

Journal of System Simulation

Abstract: Focus on the rapid physical exertion and the poor flexibility of diving propeller vehicle, a wearable diving propeller equipped with buoyancy control devices is proposed, and the position of the propeller in the device is optimized. The human body structure is regarded as a rigid body to establish a spatial 6-degree-of-freedom motion equation, and its surrounding hydrodynamic performance is analyzed. The hydrodynamic parameters in the model are obtained based on the FLUENT. The propeller position optimization model based on the minimum external force of rectilinear diving and slewing motions is established. The optimization results demonstrate that the optimized …

Research On Image Description Method Based On Neural Network, Kong Rui, Xie Wei, Lei Tai

Journal of System Simulation

Abstract: The automatic recognition and automatically describing image content is an important research direction to the artificial intelligence to connect the computer vision and the natural language processing. A method of describing the image content is proposed to generate the natural language by using the deep neural network model. The model consists of a convolutional neural network (CNN) and a recurrent neural network (RNN). The CNN is used to extract features of the input image to generate a fixed-length feature vector, which initializes the RNN to generate the sentences. Experimental results on the MSCOCO image description dataset show the syntactic …

Multi-Objective Dynamic Programming Algorithm Of Energy-Efficient Scheduling For Tow-Train, Xinyan Zhang, Yuqing Zhou

Journal of System Simulation

Abstract: To balance the performance and energy consumption of the mixed-model assembly lines effectively, a multi-objective energy-saving scheduling method for the tow-train is proposed. The energy-saving objective is introduced into the traditional material handling scheduling model for the tow-train and a multi-objective mixed integer programming model is constructed with two objective functions of minimizing the maximum line-side inventory and the total energy consumption. A forwards multi-objective dynamic programming based on the time window and dominance rules is presented to obtain the Pareto solutions: the definition for new states is given to obtain the Markov property, the time window and dominance …

Design Of Space-Based Surveillance Distributed Simulation System For Space Targets, Zhang Yang, Qingbo Gan, Yuan Hong, Jiangliang Fu, Chengming Sun

Journal of System Simulation

Abstract: Following the wide application of the HLA in the aerospace system simulation, the space-based surveillance distributed simulation system for the space targets based on the HLA is designed. In the infrastructure design level, the hierarchical structure including data layer, model layer and mission layer are designed. In the system design level, the simulation control members, space-based surveillance member, space target member, optical payload member, and visual simulation member are divided and confirmed. The orbit dynamics and maneuvering model, attitude dynamics and control model, payload pointing and optical imaging model are established. In system implement level, the …

One Design Mode Of Highly Configurable Modular Simulation System, Chunsheng Hu, Chengdong Xu, Penfei Zhang

Journal of System Simulation

Abstract: The computer simulation technology is an essential verification way to the design, construction and application optimization of the modern complex system. Following the continuous growing complexity of the system, the higher requirement on the configurability of the simulation system is needed to face the rapidly change. Based on the analysis on the configurability and some coupling factors with the adverse effect, a design mode of highly configurable and open and easy to expend modular simulation system is proposed. The results show that, despite the cost of some real-time performance, the design mode can realize the high configurability of the …

Modeling And Simulation Of Locating Water Resources For Forest Fire Extinguishing, Guoxiong Zhou, Li Tong, Aibin Chen, Mingfang He

Journal of System Simulation

Abstract: At the time of the forest fire, the effective water resource position is a good assistance to the firefighters to put out the fire. Taking a state-owned tree-farm, Huangfeng Bridge as an example in You Xian, an approach is proposed to optimally locate and determine the water resources to extinguish the forest fires, which uses the barycenter of a Weighted Voronoi Diagram and is generated dynamically via Cellular Automata and locally optimized by Alternative Location and Allocation algorithm. In order to reduce the low ratio impact of the water resource to the high fire risk areas, a barycenter model …

Cost-Efficiency Analysis Of Weapon System Portfolios For Effect Based Operation, Zhong Lin, Mingan Tong, Zhang Jian, Jianhai Liang

Journal of System Simulation

Abstract: In considertion of the cost-efficiency analysis of weapon system mainly for the target based operation, the uncertainties about preferences and possible interactions of different weapon systems, a cost-efficiency analysis method weapon system portfolios for effect based operation is presented. The framework of weapon system assignment for effect based operation is presented, the Bayesian network is used to build up the connection between effects and targets, and the cost-efficiency analysis model based on robust portfolio optimization is carried out. In view of the combinatorial explosion, the approximation algorithm based on the Tchebycheff norm and the linear integer programming is proposed …

System Dynamics And Multi-Agent Simulation Research On Ground Combatpersonnel Attrition, Xiaoxiong Hao, Jianwei Ma, Zhaohui Huang, Yungui Wang

Journal of System Simulation

Abstract: In order to study the law of the combat personnel attrition and guide the military medical logistics support, the relevant researches are systematically sorted out and the key questions are clarified. Based on Lanchester equation theory, a system dynamics model of the combat attrition process is established, and the consistency between the model conclusion and the historical experience is analyzed. A multi-agent model of the combat attrition process is also constructed, and the advantages and disadvantages of the two models are analyzed. The main conclusion is that the theoretical model’s outcomes of combat attrition are relatively consistent with the …

Modeling Method Of Emergency Response Based On Internal And External Areas Of Disaster Zone, Liang Wei, Yanyan Huang, Jianyu Wang

Journal of System Simulation

Abstract: The insufficient ability of the rescuers and the insufficient self-rescue ability of the victims are the two main reasons of the low efficiency in some conventional event emergency. An emergency response model which combines the rescue ability and the self-rescue ability is presented. The division of the internal and the external system in the disaster field is defined, the basic structure of the model and the emergency response process characteristics are described. MAS (multi-agent system) is used to describe the law of the emergency behavior. The synergistic rescue effect is simulated through an imaginary case. The results show that …

Simplification And Compression Service Construction Of 3d Model For Complex Products, Junjie Xue, Guoqiang Shi, Junhua Zhou, Huiyang Qu, Tao Luan, Ruiying Pu

Journal of System Simulation

Abstract: A simplification and compression (S&C) service construction method of the 3D model for the complex products is proposed. An improved method of the model data export and spatial index generation is adopted to preserve the assembly tree and label information of the model in the process of model S&C. An adaptive mesh simplification algorithm based on the mesh density is designed and implemented, and the meshes can be simplified adaptively on condition of satisfying the requirement of error for the geometric model. And a model data compression algorithm with the high compression ratio and efficiency is adopted to reduce …

Time Domain Vertical Dynamics Model Of Electric Vehicle Considering Electric Motor Vibration, Guoying Tian, Pengyi Deng, Shulei Sun, Yiqiang Peng, Haiying Lu

Journal of System Simulation

Abstract: On the basis of considering the electric motor vibration, a time domain vertical dynamics model of the electric vehicle with 11 DOF is built, and the road roughness input model and the numerical method are given. Aiming at an electric passenger vehicle, the basic characteristics of the typical vehicle dynamics responses under the condition of the impulse and random road roughness inputs are calculated, the influence of the different mount stiffness, damping and motor mass on the motor and the vehicle vibration is analyzed under the condition of the impulse input. The results show that the proposed model is …

Trajectory Planning Of Wheeled Mobile Robot Based On Model Predictive Control, You Bo, Mingrui Wang, Li Zhi, Ding Liang

Journal of System Simulation

Abstract: Aiming at the underactuation of the Wheeled Mobile Robot (WMR) and considering the various limitations and constraints during the actual operation, a trajectory planning method based on the Model Predictive Control (MPC) is proposed.This method can deal with the kinematics constraints, physical constraints and obstacle avoidance constraints unifiedly and effectively. It can generate the feasible trajectories that conform to the characteristics of the car body model and satisfy the various constraints. It fully guarantees the feasibility, safety and efficiency of the autonomous driving of wheeled mobile robots. The simulation results fully verify the effectiveness of the proposed method.

Fault Diagnosis Method Of Vehicle Power Supply Based On Deep Learning And Sequential Test, Li Wei, Bingxiang Zhou, Dongnian Jiang

Journal of System Simulation

Abstract: Focus on the health maintenance of vehicle power supply, a fault diagnosis method of vehicle power supply is proposed, which is based on the long and short time memory LSTM(Long Short Time Memory) network and the sequential probability ratio test SPRT(Sequential Probability Ratio Test). Based on the LSTM network, the multivariate time series model of vehicle power supply is established, and the SPRT method is used to perform the adaptive multi-sample fault diagnosis. The experiment on the vehicle power supply simulation system shows that the LSTM diagnosis model has stronger learning and mapping capabilities, and the fault diagnosis method …

Research On Flight Ground Service Time Prediction Based On Deep Neural Network, Zhiwei Xing, Li Biao, Zhu Hui, Luo Qian

Journal of System Simulation

Abstract: Flight ground service time prediction is one of the key issues in improving the airport operational efficiency and decision making capacity. Taking into account the complexity, particularity and uncertainty of the service process, a Gaussian probability model of flight ground service resource in place time is established, a flight ground service time prediction model based on the deep neural network is proposed. According to the regular changes of operational data, the model parameters are adjusted to reducet the generalization error caused by other factors. The research results show that the average absolute error of time prediction under single …

Unmanned Crane Dispatching System Based On Grid Method In Steel Works, Weigang Li, Wang Xiao, Yuntao Zhao, Zixiang Li

Journal of System Simulation

Abstract: A grid method is used to model a storeroom to solve the problem of the unmanned crane automatic scheduling of the iron and steel industry. An improved A* algorithm is proposed to make the path planning. Different moving costs are assigned for the different route sections in storeroom and the different moving modes of cranes, and the path with the minimum total cost which can avoid the slab obstacles alongside is calculated by the algorithm. A set of intelligent dispatching rules are designed to solve the inefficiency of the manual operation, which can effectively deal with the problems about …

Vehicle Coordination Strategy For Semi-Active Suspension Vehicles, Quanmin Guo, Haowen Zhang, Wang Yan

Journal of System Simulation

Abstract: In order to realize the coordinated control of the vertical, pitch and roll vibration of vehicle, a coordinated control strategy of vehicle semi-active suspension is proposed. In the strategy, the fuzzy PID controllers estimate three adjustment forces according to the vibration state in vertical, pitch and roll directions. Through the designed force coordinator with the control parameters of the front and back axes and the steering control strategy, the expected adjustment forces are coordinated to the four magnetorheological dampers to output the adjustable damping forces and realize the coordinated control of the vehicle vibration in three directions. The experimental …

3d Tree Model Matching Based On Tree Shape Space, Liang Shuang, Zuoteng Zhu, Jinyuan Jia

Journal of System Simulation

Abstract: The retrieval of the 3D tree models cannot get the higher accuracy, retrieving efficiency and descripting match. In order to solve the problems, a three-dimensional tree model matching method based on tree space is proposed. By constructing the tree space of the three-dimensional tree model dataset, the method computes the difference between the Euclidean distance and the geodesic distance in the tree space by means of spindle matching, contour matching, and branch matching, and gradually matches the corresponding model. The matching implementation results are displayed in the general model dataset and the self-designed model dataset respectively. …

Achieving Obfuscation Through Self-Modifying Code: A Theoretical Model, Heidi Waddell

Senior Honors Theses

With the extreme amount of data and software available on networks, the protection of online information is one of the most important tasks of this technological age. There is no such thing as safe computing, and it is inevitable that security breaches will occur. Thus, security professionals and practices focus on two areas: security, preventing a breach from occurring, and resiliency, minimizing the damages once a breach has occurred. One of the most important practices for adding resiliency to source code is through obfuscation, a method of re-writing the code to a form that is virtually unreadable. …

Storage Management Strategy In Mobile Phones For Photo Crowdsensing, En Wang, Zhengdao Qu, Xinyao Liang, Xiangyu Meng, Yongjian Yang, Dawei Li, Weibin Meng

Department of Computer Science Faculty Scholarship and Creative Works

In mobile crowdsensing, some users jointly finish a sensing task through the sensors equipped in their intelligent terminals. In particular, the photo crowdsensing based on Mobile Edge Computing (MEC) collects pictures for some specific targets or events and uploads them to nearby edge servers, which leads to richer data content and more efficient data storage compared with the common mobile crowdsensing; hence, it has attracted an important amount of attention recently. However, the mobile users prefer uploading the photos through Wifi APs (PoIs) rather than cellular networks. Therefore, photos stored in mobile phones are exchanged among users, in order to …

Simulation Environment For Object Manipulation With Soft Robots In Shared Autonomy, Devin Hunter, Fabio Stroppa, Allison Okamura

Showcase of Osprey Advancements in Research and Scholarship (SOARS)

The robots of today have grown to be of much more significant use than their predecessors. Robots are now being used in industries outside of the factory setting which can be seen primarily in the medical, transportation, and social fields. With robots taking on all of these new roles within our society, the establishment of robust human-robot collaboration is crucial in order for robots to be able to successfully complete desired tasks without becoming a hinderance to nearby humans. We explored this concept by implementing a shared-autonomy algorithm named MBSA (Motion Based Smart Assistance) to a soft robot simulation and …

Artificial Intelligence Towards The Wireless Channel Modeling Communications In 5g, Saud Mobark Aldossari

USF Tampa Graduate Theses and Dissertations

Channel prediction is a mathematical predicting of the natural propagation of the signal that helps the receiver to approximate the affected signal, which plays an important role in highly mobile or dynamic channels. The standard wireless communication channel modeling can be facilitated by either deterministic or stochastic channel methodologies. The deterministic approach is based on the electromagnetic theories and every single object in that environment has to be known in that propagation space and an example of this method is ray tracing. While the stochastic modeling method is based on measurements that involve statistical distributions of the channel parameters and …

Book Genre Classification By Its Cover Using A Multi-View Learning Approach, Chandra Shakhar Kundu

Masters Theses & Specialist Projects

An interesting topic in the visual analysis is to determine the genre of a book by its cover. The book cover is the very first communication to the reader which shapes the reader’s expectation about the type of the book. Each book cover is carefully designed by the cover designers and typographers to convey the visual representation of its content. In this study, we explore several different deep learning approaches for predicting the genre from the cover image alone, such as MobileNet V1, MobileNet V2, ResNet50, Inception V2. Moreover, we add an extra modality by extracting text from the cover …

Finding Critical And Gradient-Flat Points Of Deep Neural Network Loss Functions, Charles Gearhart Frye '09

Doctoral Dissertations

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. This makes neural networks easy to train, which, combined with their high representational capacity and implicit and explicit regularization strategies, leads to machine-learned algorithms of high quality with reasonable computational cost in a wide variety of domains.

One thread of work has focused on explaining this phenomenon by numerically characterizing the local curvature at critical points of the loss function, where gradients are zero. Such studies have reported that the loss functions …

Data Science Meets Compliance, Christian Clarke

Petersheim Academic Exposition

No abstract provided.