Artificial Intelligence and Robotics Commons^™

Learning To Self-Train For Semi-Supervised Few-Shot Classification, Xinzhe Li, Qianru Sun, Yaoyao Liu, Shibao Zheng, Qin Zhou, Tat-Seng Chua, Bernt Schiele

Research Collection School Of Computing and Information Systems

Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model for FSC. In this paper we propose a novel semi-supervised meta-learning method called learning to self-train (LST) that leverages unlabeled data and specifically meta-learns how to cherry-pick and label such unsupervised data to further improve performance. To this end, we train the LST model through a large number of semi-supervised few-shot tasks. On each task, we train a few-shot model to predict pseudo labels for …

Harmony Search Algorithm For Time-Dependent Vehicle Routing Problem With Time Windows, Yun-Chia Liang, Vanny Minanda, Aldy Gunawan, Angela Hsiang-Ling Chen

Research Collection School Of Computing and Information Systems

Vehicle Routing Problem (VRP) is a combinatorial problem where a certain set of nodes must be visited within a certain amount of time as well as the vehicle’s capacity. There are numerous variants of VRP such as VRP with time windows, where each node has opening and closing time, therefore, the visiting time must be during that interval. Another variant takes time-dependent constraint into account. This variant fits real-world scenarios, where at different period of time, the speed on the road varies depending on the traffic congestion. In this study, three objectives – total traveling time, total traveling distance, and …

An Ai Approach To Measuring Financial Risk, Lining Yu, Wolfgang Karl Hardle, Lukas Borke, Thijs Benschop

Sim Kee Boon Institute for Financial Economics

AI artificial intelligence brings about new quantitative techniques to assess the state of an economy. Here, we describe a new measure for systemic risk: the Financial Risk Meter (FRM). This measure is based on the penalization parameter (λ" role="presentation" style="box-sizing: border-box; display: inline; font-style: normal; font-weight: normal; line-height: normal; font-size: 18px; text-indent: 0px; text-align: left; text-transform: none; letter-spacing: normal; word-spacing: normal; overflow-wrap: normal; white-space: nowrap; float: none; direction: ltr; max-width: none; max-height: none; min-width: 0px; min-height: 0px; border: 0px; padding: 0px; margin: 0px; position: relative;">λλ) of a linear quantile lasso regression. The FRM is calculated by taking the average …

Seer: An Explainable Deep Learning Midi-Based Hybrid Song Recommender System, Khalil Damak, Olfa Nasraoui

Faculty and Staff Scholarship

State of the art music recommender systems mainly rely on either matrix factorization-based collaborative filtering approaches or deep learning architectures. Deep learning models usually use metadata for content-based filtering or predict the next user interaction by learning from temporal sequences of user actions. Despite advances in deep learning for song recommendation, none has taken advantage of the sequential nature of songs by learning sequence models that are based on content. Aside from the importance of prediction accuracy, other significant aspects are important, such as explainability and solving the cold start problem. In this work, we propose a hybrid deep learning …

A Mathematical Programming Model For The Green Mixed Fleet Vehicle Routing Problem With Realistic Energy Consumption And Partial Recharges, Vincent F. Yu, Panca Jodiwan, Aldy Gunawan, Audrey Tedja Widjaja

Research Collection School Of Computing and Information Systems

A green mixed fleet vehicle routing with realistic energy consumption and partial recharges problem (GMFVRP-REC-PR) is addressed in this paper. This problem involves a fixed number of electric vehicles and internal combustion vehicles to serve a set of customers. The realistic energy consumption which depends on several variables is utilized to calculate the electricity consumption of an electric vehicle and fuel consumption of an internal combustion vehicle. Partial recharging policy is included into the problem to represent the real life scenario. The objective of this problem is to minimize the total travelled distance and the total emission produced by internal …

Falcon: Framework For Anomaly Detection In Industrial Control Systems, Subin Sapkota

Boise State University Theses and Dissertations

Industrial Control Systems (ICS) are used to control physical processes in the nation's critical infrastructures. They are composed of subsystems that control physical processes by analyzing the information received from the sensors. Based on the state of the process, the controller issues control commands to the actuators. These systems are utilized in a wide variety of operations such as water treatment plants, power, and manufacturing, etc. While the safety and security of these systems are of high concern, recent reports have shown an increase in targeted attacks that are aimed at manipulating the physical processes to cause catastrophic consequences. This …

3d-Printing And Machine Learning Control Of Soft Ionic Polymer-Metal Composite Actuators, James D. Carrico, Tucker Hermans, Kwang J. Kim, Kam K. Leang

Mechanical Engineering Faculty Research

This paper presents a new manufacturing and control paradigm for developing soft ionic polymer-metal composite (IPMC) actuators for soft robotics applications. First, an additive manufacturing method that exploits the fused-filament (3D printing) process is described to overcome challenges with existing methods of creating custom-shaped IPMC actuators. By working with ionomeric precursor material, the 3D-printing process enables the creation of 3D monolithic IPMC devices where ultimately integrated sensors and actuators can be achieved. Second, Bayesian optimization is used as a learning-based control approach to help mitigate complex time-varying dynamic effects in 3D-printed actuators. This approach overcomes the challenges with existing methods …

Augmenting Education: Ethical Considerations For Incorporating Artificial Intelligence In Education, Dana Remian

Instructional Design Capstones Collection

Artificial intelligence (AI) has existed in theory and practice for decades, but applications have been relatively limited in most domains. Recent developments in AI and computing have placed AI-enhanced applications in various industries and a growing number of consumer products. AI platforms and services aimed at enhancing educational outcomes and taking over administrative tasks are becoming more prevalent and appearing in more and more classrooms and offices. Conversations about the disruption and ethical concerns created by AI are occurring in many fields. The development of the technology threatens to outpace academic discussion of its utility and pitfalls in education, however. …

“Where’S The I-O?” Artificial Intelligence And Machine Learning In Talent Management Systems, Manuel F. Gonzalez, John F. Capman, Frederick L. Oswald, Evan R. Theys, David L. Tomczak

Personnel Assessment and Decisions

Artificial intelligence (AI) and machine learning (ML) have seen widespread adoption by organizations seeking to identify and hire high-quality job applicants. Yet the volume, variety, and velocity of professional involvement among I-O psychologists remains relatively limited when it comes to developing and evaluating AI/ML applications for talent assessment and selection. Furthermore, there is a paucity of empirical research that investigates the reliability, validity, and fairness of AI/ML tools in organizational contexts. To stimulate future involvement and research, we share our review and perspective on the current state of AI/ML in talent assessment as well as its benefits and potential pitfalls; …

Robot Simulation Analysis, Jacob Miller, Jeremy Evert

Student Research

• Simulate virtual robot for test and analysis

• Analyze SLAM solutions using ROS

• Assemble a functional Turtlebot

• Emphasize projects related to current research trajectories for NASA, and general robotics applications

Robust And Self-Synchronous Steganography For Voice-Over-Ip Based On Ldpc Codes, Zhanzhan Gao, Guangming Tang, Haitao Song

Journal of System Simulation

Abstract: VoIP (Voice over IP) is a kind of voice communication technology based on UDP/IP protocols, so packet loss will inevitably happen when the channel environment deteriorates. Besides that, stego VoIP data flows are real-time and have no head or tail, which pose more challenges to accurately extract the secret messages. This paper proposes a robust and self-synchronous VoIP steganography method, which solves the above two problems under the premise of maintaining good imperceptibility. In this method, low density parity check (LDPC) codes are introduced to preprocess the secret data, and the encoded data are embedded into voice …

No-Collision Curling Trajectory Simulation System, Tian Yu, Xu Ming

Journal of System Simulation

Abstract: In just a few decades, China’s curling accomplished splendid work. But it’s scientific research falling behind a lot. Applying computer simulation technology in sports training can effectively help the athletes to understand the problems that exist in the training. When curling stone slides on the ice, it can be regarded as two-dimensional motion of rigid body, which can be decomposed into two parts: translation of the center of mass and rotation of a fixed axis around the center of mass. Using computer simulation technology to simulate the curling trajectory, and with the help of this system, the athletes can …

Ground Coverage Stitching Simulation Algorithm For Remote Sensing Satellite, Shuhao Liu, Wang Tong, Zhang Yue

Journal of System Simulation

Abstract: Ground coverage stitching is the base of remote sensing satellite mission simulation. A coverage stitching simulation algorithm is proposed, considering big time step and attitude maneuver simulation. Transient coverage region is computed by light of view intersection and tangent searching methods. Transient coverage boundaries of different simulation times are stitched by two-dimension convex hull algorithm. Between points of the stitched region polygon edges, new vertexes are interpolated. With the method proposed, limb coverage problem and coverage fusion when time step is large can be solved. Computer simulation results show that the algorithm achieves a fine accuracy and …

Locally Weighted Learning Control For Dynamic Restricted Manipulators, Wang Gang, Tairen Sun, Shengpei Ding

Journal of System Simulation

Abstract: This paper proposes a locally weighted learning control law for a manipulator with state and input constraints and modeling uncertainties. By visualizing the control input as an extended state, the control problem is converted into control design for a state-constraint uncertain nonlinear system. Barrier Lyapunov functions are introduced into a backstepping procedure and a locally weighted learning control is designed, which ensures the exponential convergence of the barrier functions to a small neighborhood of zero and then guarantees satisfaction of system constraints and the tracking error convergence. The control feasibility and effectiveness is validated by theoretical analysis and …

Simulation Analysis Of Vehicle Electromagnetic Environment Under Excitation Of Vhf Antenna, Xiaoying Sun, Hanqing Wang, Jinpeng Yang, Zhao Yu

Journal of System Simulation

Abstract: Aiming at the issue of distribution regularity of field strength in vehicle cab under excitation of vehicle-borne high-power VHF antenna, a method of numerical simulation combining with extreme value theory to predict maximum field strength is proposed, which minimizes sample collecting difficulty and fitting deviation. CST simulation software is applied to get field strength sample in vehicle cab, and generalized extreme value (GEV) is used to fitting entire field strength distribution. peak over threshold (POT) model based on Generalized Pareto distribution is used to research high field strength value sample statistical characteristics. Resultsshow that under antenna excitation of 92.5 …

Ti-A* Based Multi-Robot Dynamic Planning And Coordination Method, Zhao Ping, Xinyu Lei, Bozhi Chen, Jiaoyun Yang

Journal of System Simulation

Abstract: Multiple robots path planning problem in dynamic environment is one of the significant and basic problems of cluster robot perception and coordination. The planning problem is decomposed into two modules: the path planning and the conflict coordination. By introducing time-cost function, the Time Integrated A* algorithm (TI-A*) is introduced. Variable speed is employed simultaneously to coordinate the motion and hereby to avoid the deadlock and conflict. By adjusting the timing when the coordination phase is involved, two different coordination TI-A* algorithms are presented, including the speed-changing algorithm and path-changing algorithm. The two algorithms are compared and the respective …

Travel Time Reliability Of Inside Area Of Roundabouts, Yuzhou Duan, Tingting Chai, Jian Jie

Journal of System Simulation

Abstract: Based on the travel time reliability, this paper analyzes the traffic states in the inside area of the roundabout. The travel time reliability model is established from three aspects: route path, entrance and system, and the practicability of the model is verified by the VISSIM simulation. On this basis, the correlation analysis is made on between the adjacent paths of the same entrance and adjacent paths of the adjacent entrances, and the fitting equations are obtained. Taking the number of lanes, traffic volumes, proportion of left-turns and the rate of heavy vehicles as variables, a sensitivity analysis …

Integrated Simulation Optimization Of Hard Shoulder Running Combined With Speed Harmonization, Ruimin Li, Ye Zhen, Bin Li

Journal of System Simulation

Abstract: We have a study on hard shoulder running (HSR) combined with speed harmonization. The breakdown events were screened out during the study period from massive detector data. The impact of hard shoulder volume on breakdown probabilities was analyzed. The nonparametric breakdown probabilities distribution model and logistic regression model were put forward based on highway mainline traffic volume, hard shoulder volume and ramp volume from the study case which was divided into three factors-basic segment, on-ramp merging segment and off-ramp diverging segment. The speed harmonization and HSR were optimized through reducing the traffic breakdown probabilities of a congested traffic network. …

Dynamic Interference Detection Algorithm For Bearing With Scar, Jinyuan Jia, Naihao Zheng

Journal of System Simulation

Abstract: To solve the dynamic interference detection problem of scar bearing in visual assembly, an efficient dynamic interference inspection algorithm for scar bearing is proposed. The first step is to perform vertex management on the 3D reconstructed scar bearing model through the quad-tree; the second step is to select the appropriate algorithm for the calculation of the maximum interference distance by considering bearing shape and its motion characteristics. The research shows that the algorithm can quickly and efficiently test the dynamic interference and calculate the interference distance for the bearing with scar, which can effectively improve the efficiency of bearing …

Optimal Compensation Control Strategy For Four-Axle Vehicle With All-Wheel Steering System, Baohua Wang, Yu Chao

Journal of System Simulation

Abstract: Aiming at the problem of poor stability of traditional multi-axle commercial vehicles, an optimal control strategy for multi-axle steering wheel is proposed. Through the establishment of the four-axis vehicle model, the wheel angle proportional feed-forward control algorithm and the yaw rate feedback control algorithm are studied. The optimal compensating control algorithm of the wheel angle proportional feed-forward and yaw rate feedback is proposed, and the control strategy is also verified through joint simulation. The results show that the full-wheel steering optimal compensation control strategy can keep the center-of-mass skew angle close to zero at all vehicle speeds, …

Simulation Estimation On Directional Green-Wave Traffic Control In Nanning City, Yiman Du, Hongfan Su, Chen Yu, Longfei Liu, Jianping Wu

Journal of System Simulation

Abstract: Due to the noticeable development of Nanning city, traffic congestion has become a serious problem, especially during the peak hours along the Binhu road. The development of Nanning city is restricted by the imbalance distribution of traffic flow. In order to ease the overload burden of traffic along the Binhu road during the peak hours, the current problems are analyzed and some solutions with directional green-wave traffic control are proposed. Traffic microscopic simulation software is used to estimate the improvement between before and after implementations of the solutions.

Novel Star Map Identification Algorithm Using Improved Radial Features, Junyang Zhao, Zhili Zhang, Dianjian Liu, Zhaofa Zhou, Zhenjun Chang

Journal of System Simulation

Abstract: In order to improve the star map identification efficiency and insure the identification veracity, the radial feature is ameliorated by cyclic feature, and a new star map identification method based on the ameliorative radial feature matching is proposed. The star map data are processed according to quadrant order to establish the database of new radial feature. The radial feature matching between the observation stars in the matching star map and the reference star in the feature database is carried out in the order of circumferential quadrant. The star with the largest count in the star database is the final …

Study On The Matching Mediation Method Between Virtual Maintenance Personnel And Work Steps, Yunrong Zhang, Zhili Zhang, Xiangyang Li, Weichang Xu, Kuixia Han, Li Liang

Journal of System Simulation

Abstract: Aiming at the problem that each maintenance worker cannot play a full role in dealing with the concurrent conflict of maintenance steps, this paper puts forward a matching mechanism between maintenance steps and maintenance workers according to the level of authority, expounds the status information of maintenance workers, divides the difficulty level of maintenance steps, and gives the matching process between maintenance workers and maintenance steps. The matching process is modeled and simulated by using colored Petri nets and CPN tools. The simulation results show that the matching mechanism can solve the problem that the role of …

Two-Machine Co-Simulation Based On Mobile Augmented Reality, Zhili Zhang, Wang Chao, Long Yong, Shaodi Wang

Journal of System Simulation

Abstract: Aiming at the problems that virtual training system was not convenient and was only performed in a single operation at present, a dual-machine collaborative system based on mobile augmented reality was designed. A portable augmented reality system was developed on the Unity3D platform with Tango technology. The photon server and LAN architecture were built on the basis. The client was built on the mobile platform of Lenovo PHAB2 Pro, and the co-simulation on dual-machine was implemented. Resultof the simulation proved the feasibility of combining augmented reality with photon server, and provided a set of practical development solutions for …

Numerical Simulation For Airflow Field Around Car Wheels, Haibo Huang, Xudong Yu, Qingguo Liu, Zhang Tao, Jianan Dong

Journal of System Simulation

Abstract: The airflow field characteristics around the wheels have great influence on the flying of road dust and tire wear particles. Using the rotating wall boundary technology, an aerodynamic model of the vehicle-tire was built and verified. The airflow field around the wheels was obtained. The results show that the two airflows between the wheel and the wheel guard meet leading to the vortex. The airflows mainly overflow near the intersection. Due to the significant pumping effects, the airflow tends to fly to outside and upward near the front and rear wheels, respectively. In the …

Multi-Agent Modeling And Simulation On China's Marine Energy Channel Security, Yongchen Guo, Shen Yang

Journal of System Simulation

Abstract: Security factors influencing China's offshore energy channel are analyzed, and the actual situation of China's oil import and transportation is described. Based on multi-agent modeling and simulation method, and starting at the micro level, the energy transport process is simulated and a multi-agent model of China's offshore energy channel (middle east lines) is built; and the simulation program on the NetLogo platform is conducted. The results show that the quantity of China’s VLCC is far from enough; the security impact of tropical cyclones is more serious than that of pirates; the increase proportion of carrier’s quantity is usually lower …

Simulation Of Gas-Liquid Mixing Flow In A Stirred Tank With Inverted Umbrella-Type Surface Aerator, Wenli Wei, Weili Lou, Panpan Li, Yuling Liu

Journal of System Simulation

Abstract: The way of computational fluid dynamics with k-ε turbulence model as well as multiple reference frame method was used to simulate the hydraulic characteristics of gas-liquid mixing flow in a stirred tank installed with an inverted umbrella-type surface aerator. The inverted umbrella aerator consists of eight blades, and rotates at 5.23rad/s. The main purpose of this simulation is to study the distributions of air volume fraction and characteristics of mixing flow. The simulation results show that the distribution of the mixing flow is symmetrical; the change rules of the gas distribution at different positions along the axis direction are …

Parameter Optimization Analysis For Double Reheat Units Based On Particle Swarm Optimization, Wenfeng Fu, Haiwen Chen, Lanjing Wang

Journal of System Simulation

Abstract: The thermodynamic system parameter optimization was established for double reheat ultra-supercritical units. Taking a 660MW unit as an example, some vital parameters including feedwater enthalpy rise distribution, feedwater temperature, reheat steam pressure, number of feedwater heaters and main steam parameter were analyzed based on particle swarm optimization. The result shows the unit thermal efficiency can be further improved by optimizing apparatus interface parameters. The second reheat pressure has more influence on the unit thermal efficiency than the first reheat pressure. When adding the number of feedwater heaters, low pressure heater is a better choice for improving unit thermal efficiency. …

Quantity Optimization Of Aircraft Ground Deicing Equipment Based On Flight Dynamics, Bin Chen, Liwen Wang

Journal of System Simulation

Abstract: Flight delays and deicing equipment parameter optimization questions were studied aiming at two kinds of typical airport. The formation mechanism of deicing flight delay queue was studied, and the flight delay queue model was proposed corresponding to the departure dynamics of triangle and parabolic shape function. An optimization model of deicing nozzle quantity demand for two typical flight departure dynamics was established aiming at minimizing the flight delay and deicing cost. The nozzle quantity demand optimization model was simulated and verified using deicing flight dynamic data of Beijing International Airport and Harbin Taiping Airport. Simulation results are close to …

Extending Lifetime Of Sensor Networks Based On Sleep-Scheduled Routing Algorithm, Zhuojin Pan, Stuart D., Luo Zhen, Yang Hua

Journal of System Simulation

Abstract: In order to minimize energy consumption of sensor nodes in wireless sensor networks, this paper presents an Energy Efficient Sleep-Scheduled Tree-Based Routing Protocol (EESSTBRP) that modifies the chain formation in PEGASIS to create a set of paired and unpaired nodes in the network based on a distance and sensing range threshold. The paired nodes switch between active and sleep modes so as to remove redundant data and save battery power. To minimize energy consumption as nodes switching between the modes, this scheme considers the transitioning to be done based on a point of near depletion of the nodes’ residual …