Query auto-completion (QAC) displays a list of completions that start with input characters and is integrated into modern search engines. The goal is not only to reduce typing effort but also to help users formulate t...
详细信息
ISBN:
(纸本)9781538674383
Query auto-completion (QAC) displays a list of completions that start with input characters and is integrated into modern search engines. The goal is not only to reduce typing effort but also to help users formulate their search intent. Most prior QAC models focus on ranking completions on the basis of query log, whether considered on a whole or split into sessions based on time. However, a great amount of queries are issued to accomplish complex search tasks which straddle several sessions, and no previous work investigates QAC problem in this scenario. To tackle this challenge, we propose a supervised framework for QAC personalization, where three levels of task-related factors are considered separately and synthetically, including history-level, session-level, and query-level. Experimental results on a real-world search log confirm that our learning to rank model significantly outperforms the competitive baselines and enables a more comprehensive understanding of users' search history.
Story problems are of ultimate importance of mathematics. This stems from the fact that they help improve various students' skills including reading the story problem, extracting the embedded mathematical informat...
详细信息
ISBN:
(纸本)9781538664070
Story problems are of ultimate importance of mathematics. This stems from the fact that they help improve various students' skills including reading the story problem, extracting the embedded mathematical information and the unknown quantity to compute, and applying the correct mathematical operators to solve the problem. Unfortunately, this type of problems may suffer from misinterpretation errors and errors due to overlooking some embedded information regardless of the proficiency of the students in mathematics. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system of probability story problems. The focus of this paper is to explain how MAST deals with those problems using the Question Generation Module (QGM) and the Cognitive Module (CM). The QGM is able to generate story problems based on Natural Language Generation (NLG) techniques. This results in known semantic descriptions and linguistic structures of each story problem part. The CM, on the other hand generates the correct answer through interpreting the story problem parts and converting them into a corresponding mathematical model. This helps MAST in tracing the student answer and addressing any misinterpretations or overlooked information using different types of feedback. A satisfaction questionnaire has shown extreme satisfaction of the students and teachers with the capabilities of MAST.
In this article, we propose a planning algorithm for coverage of complex structures with a network of robotic sensing agents, with multi-robot surveillance missions as our main motivating application. The sensors are ...
详细信息
ISBN:
(纸本)9781538626825
In this article, we propose a planning algorithm for coverage of complex structures with a network of robotic sensing agents, with multi-robot surveillance missions as our main motivating application. The sensors are deployed to monitor the external surface of a 3D structure. The algorithm controls the motion of each sensor so that a measure of the collective coverage attained by the network is nondecreasing, while the sensors converge to an equilibrium configuration. A modified version of the algorithm is also provided to introduce collision avoidance properties. The effectiveness of the algorithm is demonstrated in a simulation and validated experimentally by executing the planned paths on an aerial robot.
This paper aims to explore the usefulness of a simple genetic algorithm (GA) optimized Fuzzy Logic controller (FLC) to reduce the response of a three-DOF framed structure equipped with a MagnetoRheological (MR) damper...
详细信息
This paper aims to explore the usefulness of a simple genetic algorithm (GA) optimized Fuzzy Logic controller (FLC) to reduce the response of a three-DOF framed structure equipped with a MagnetoRheological (MR) damper. These actuators can be controlled in bi-state control mode and/or in a semi-active configuration by continuously adjusting the amount of damping according to the actual response. Generally, model based controllers are designed to determine the actuator output. In recent years, soft computing techniques have been implemented to deal with the highly non-linear nature of structural systems. Among others, fuzzy based controllers seem to be adequate approach for these cases due to the inherent ability to deal with uncertain systems. However, a FLC design requires a wide experience in operating the system. This can be very difficult to implement in complexsystems and several optimization techniques have been suggested to enhance the design process of fuzzy controllers. In this paper, a genetic algorithm (GA) optimized semi-active fuzzy based controller is proposed to reduce the seismic response of a three degree-of-freedom (DOF) structure using a MR damper at the first DOF. The uncontrolled and controlled structural responses are compared to evaluate the effectiveness of the semi-active fuzzy based controller.
This paper presents a study of fuzzy optimal variance control problem for dynamical systems subject to actuator amplitude and rate constraints. Using Takagi-Sugeno fuzzy modeling and dynamic Parallel Distributed Compe...
详细信息
ISBN:
(纸本)9781509060344
This paper presents a study of fuzzy optimal variance control problem for dynamical systems subject to actuator amplitude and rate constraints. Using Takagi-Sugeno fuzzy modeling and dynamic Parallel Distributed Compensation technique, the stability and the constraints can be cast as a multi-objective optimization problem in the form of Linear Matrix Inequalities. By utilizing the formulations and solutions for the input and output variance constraint problems, we develop a fuzzy full-state feedback controller. The stability and performance of the proposed controller are demonstrated through its application to the airfoil flutter suppression.
The complexity and dynamics of urban multimodal transportation environment make the optimum routing of freight a challenging task due to the unpredictability of the impact of incidents, disruptions and traffic demand ...
详细信息
ISBN:
(纸本)9781538615263
The complexity and dynamics of urban multimodal transportation environment make the optimum routing of freight a challenging task due to the unpredictability of the impact of incidents, disruptions and traffic demand changes. Routing decisions in complex and dynamical urban area networks rely on the minimization of a certain objective function which depends on accurate estimation of future states of the network which are not readily available. The purpose of this paper is to present a new load balancing algorithm for multimodal freight routing with hard vehicle availability and capacity constraints in a hierarchical Co-Simulation Optimization control approach. The evaluation results on a simulation testbed for the Los Angeles/Long Beach Port area demonstrate that the proposed load balancing algorithm provides a good performance of convergence.
The supervisory control theory is widely used to deal with problems of controller design in the field of discrete event systems. Despite the academic attention over last several decades, there were few application cas...
详细信息
The design of flow controlsystems remains a challenge due to the nonlinear nature of the equations that govern fluid flow. However, recent advances in computational fluid dynamics (CFD) have enabled the simulation of...
The design of flow controlsystems remains a challenge due to the nonlinear nature of the equations that govern fluid flow. However, recent advances in computational fluid dynamics (CFD) have enabled the simulation of complex fluid flows with high accuracy, opening the possibility of using learning-based approaches to facilitate controller design. We present a method for learning the forced and unforced dynamics of airflow over a cylinder directly from CFD data. The proposed approach, grounded in Koopman theory, is shown to produce stable dynamical models that can predict the time evolution of the cylinder system over extended time horizons. Finally, by performing model predictive control with the learned dynamical models, we are able to find a straightforward, interpretable control law for suppressing vortex shedding in the wake of the cylinder.
Long-term situation prediction plays a crucial role for intelligent vehicles. A major challenge still to overcome is the prediction of complex downtown scenarios with multiple road users, e.g., pedestrians, bikes, and...
详细信息
Long-term situation prediction plays a crucial role for intelligent vehicles. A major challenge still to overcome is the prediction of complex downtown scenarios with multiple road users, e.g., pedestrians, bikes, and motor vehicles, interacting with each other. This contribution tackles this challenge by combining a Bayesian filtering technique for environment representation, and machine learning as long-term predictor. More specifically, a dynamic occupancy grid map is utilized as input to a deep convolutional neural network. This yields the advantage of using spatially distributed velocity estimates from a single time step for prediction, rather than a raw data sequence, alleviating common problems dealing with input time series of multiple sensors. Furthermore, convolutional neural networks have the inherent characteristic of using context information, enabling the implicit modeling of road user interaction. Pixel-wise balancing is applied in the loss function counteracting the extreme imbalance between static and dynamic cells. One of the major advantages is the unsupervised learning character due to fully automatic label generation. The presented algorithm is trained and evaluated on multiple hours of recorded sensor data and compared to Monte-Carlo simulation. Experiments show the ability to model complex interactions.
Nowadays, the controlsystems based on communication networks are used various industries such as manufacturing, automotive, aerospace, power generation and distribution, with many advantages and a couple of disadvant...
详细信息
ISBN:
(纸本)9781538638422
Nowadays, the controlsystems based on communication networks are used various industries such as manufacturing, automotive, aerospace, power generation and distribution, with many advantages and a couple of disadvantages. The latter can seriously affect the performances and the stability of each control system in the network and of the complex system as a whole. Moreover, it is well known that packet losses or data-packet dropouts are key factors for determining the quality of time-critical applications. As such, in this paper, the error caused by the data-packet dropouts which appear while sending the data through a communication network from the remote process to the controller and vice versa is modeled as a disturbance. Moreover, a novel methodology to find the limits of the hypothetical disturbance is proposed. Furthermore, the boundaries of the disturbances caused by the data-packet dropouts are taken into account explicitly during the designing phase of a predictive controller with inherited robustness based on flexible control Lyapunov functions. The system's input-to-state stability is guaranteed in a non-conservative way by the control algorithm. The predictive controller designed based on the proposed modeling methodology was tested on an electric power assisted steering (EPAS) system controlled through controller area network (CAN). Simulations were performed in Matlab/Simulink and the obtained results show that the modeling methodology and the control strategy are effective in achieving the desired performances.
暂无评论