Internet inquiry is playing an increasingly important role as the complement of the traditional medical service system, especially the similar cases recommendation. It can not only save the patients' waiting time,...
详细信息
ISBN:
(纸本)9781467384155
Internet inquiry is playing an increasingly important role as the complement of the traditional medical service system, especially the similar cases recommendation. It can not only save the patients' waiting time, but also make use of the historical resources, for many cases with the same purpose have been solved perfectly. However, because of the diversity and non-standard of the patients' descriptions, the inquiry platform cannot find the cases with similar semantic easily. Most traditional retrieval methods require the overlap of two sentences, and this is not suitable with the diversity and non-standard descriptions. In this paper, we try to utilize the sentences' semantic representation in a continuous space to understand the cases, and then recommend the similar cases. We also incorporate it into query likelihood language models, trying to get better results. Our experimental data are all collected from a real internet inquiry platform, and the results show that our methods significantly outperform the state-of-the-art translation based methods for similar cases recommendation.
In this paper, the continuous-time unknown nonlinear zero-sum game is investigated using a model-free online learning method. First, motivated by model-based policy iteration, an iterative equation without any knowled...
详细信息
ISBN:
(纸本)9781509006212
In this paper, the continuous-time unknown nonlinear zero-sum game is investigated using a model-free online learning method. First, motivated by model-based policy iteration, an iterative equation without any knowledge of system dynamics is derived by introducing simultaneous explorations. Then, the model-free reinforcement learning based on the derived iterative equation is developed to approach the solution of the Hamilton-Jacobi-Isaacs equation. For the online implementation purpose, three neural networks are constructed to approach the value function, control and disturbance policies, respectively. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed scheme.
As legged robots are suitable to be used in unstructured environments, it becomes a popular field of research nowadays. In this paper, the development of quadruped robots is summarized. And several typical and recent ...
详细信息
As legged robots are suitable to be used in unstructured environments, it becomes a popular field of research nowadays. In this paper, the development of quadruped robots is summarized. And several typical and recent robot systems are addressed in details, such as HyQ series, StarlETH, ANYmal, MIT Cheetah and BigDog, etc. Furthermore, some key techniques of environment perception for quadruped robots, including sensors, feature extraction and identification, mapping and SLAM, are also discussed. Finally, future researches of quadruped robots in environment perception are given.
Nowadays, urban parking circumstances are becoming more and more challenging. To solve this problem, many methods have been proposed, such as infrastructure expansion, economic leverage and technical theory. However, ...
详细信息
ISBN:
(纸本)9781467385800
Nowadays, urban parking circumstances are becoming more and more challenging. To solve this problem, many methods have been proposed, such as infrastructure expansion, economic leverage and technical theory. However, these solutions are generally used independently, thus it is infeasible to solve all existing problems. Therefore, a novel and revolutionary solution is urgently required. In this paper, we first comprehensively investigate the background of parking difficulties, and find that all of the current existing solutions are not able to meet the requirements of dynamic, systematization, high efficiency and accuracy. Then we briefly introduce the parallel theory, and propose the intelligent parking system based on the parallel theory, which can provide a systematic intelligent solution to meet the needs of current parking systems. The parallel parking system is made up of three parts, including the artificial system, the computational experiments, and the parallel execution. The proposed parallel parking system not only provides a novel direction to solve the parking problem, but also is an important guidance for the specific implementation of parallel parking theory.
In this paper, we propose a new role analyzing paradigm for social networks enlightened by topic modeling, which can be adopted as a primitive building block in various security related tasks, such as hidden community...
详细信息
ISBN:
(纸本)9781509038664
In this paper, we propose a new role analyzing paradigm for social networks enlightened by topic modeling, which can be adopted as a primitive building block in various security related tasks, such as hidden community finding, important person recognizing and so on. We first present the social network under analyzing as a heterogeneous network constructed by both the users and the subjects discussed among them. We then view this network in a Bag-of-Users schema, which mimics its classical Bag-of-Words counterpart. In this schema, the subjects discussed are treated as “documents” while the users are treated as “words” which construct the “documents”. Based on this novel presentation, we finally apply topic modeling technology to perform the social role clustering. Experiments on a practical security-related social network dataset prove the effectiveness of our approach.
To detect the racket pose faster and easier, a new method combining the HSV and RGB color spaces are presented. The purpose of using the HSV color space is to get enough information in the RGB color space. By detectin...
详细信息
ISBN:
(纸本)9781467374439
To detect the racket pose faster and easier, a new method combining the HSV and RGB color spaces are presented. The purpose of using the HSV color space is to get enough information in the RGB color space. By detecting the mark on the racket in real-time, the racket pose could be obtained. The experimental results show that the proposed method has a great advantage on the robustness of corner extraction of the rectangle on the racket.
Articulated tracked vehicles possess outstanding traveling capability due to the special articulated steering mechanism(ASM), which makes them be widely used in many application areas. In view of the importance of ASM...
详细信息
ISBN:
(纸本)9781467374439
Articulated tracked vehicles possess outstanding traveling capability due to the special articulated steering mechanism(ASM), which makes them be widely used in many application areas. In view of the importance of ASM, we design a new structure of such mechanisms. The designed 4-DOF ASM can perform yaw and pitch movement actively while roll movement passively. To work efficiently, the ASM is designed to operate in three different modes: "float" mode, "lock" mode, and "active control" mode. Then we deduce the kinematics of articulated vehicle and analyze the workspace of the front vehicle with respect to the rear vehicle to demonstrate the motion performance of the designed ASM. With the elongation and shortening of hydraulic cylinders, the maximum steer angle is beyond 0.4 rad, the range of the rear pitch angle is(-0.22, 0.27) rad, and the range of the front pitch angle is(-0.45, 0.5) rad.
This paper presents a novel adaptive/approximate dynamic programming algorithm to solve the H∞ control problem of constrained-input continuous-time nonlinear systems. The developed algorithm employs a single critic n...
详细信息
ISBN:
(纸本)9781467374439
This paper presents a novel adaptive/approximate dynamic programming algorithm to solve the H∞ control problem of constrained-input continuous-time nonlinear systems. The developed algorithm employs a single critic neural network(NN)to derive the approximate solution of the Hamilton-Jacobi-Isaacs equation. With two additional terms introduced, namely, the stabilizing term and the robustifying term to update the critic NN, no initial stabilizing control is required. Meanwhile, the developed critic tuning rule not only ensures that the optimal saddle point can be obtained but also guarantees stability of the closed-loop system. In addition, all signals in the closed-loop system are proved to be uniformly ultimately bounded via Lyapunov's direct method. Finally, an illustrate example is provided to verify the effectiveness of the developed approach.
In this paper, the robust stabilization problem for a class of discrete-time uncertain nonlinear systems is investigated by using a neuro-optimal control strategy. The robust stabilization problem is converted into an...
详细信息
ISBN:
(纸本)9781467374439
In this paper, the robust stabilization problem for a class of discrete-time uncertain nonlinear systems is investigated by using a neuro-optimal control strategy. The robust stabilization problem is converted into an optimal control problem under some proper conditions. Then, in order to deal with the transformed optimal control problem, the discrete-time generalized HamiltonJacobi-Bellman equation is introduced and solved by employing the successive approximation method. The convergence proof of the iterative algorithm and the design procedure of the neural network implementation are developed as well. A numerical simulation is also provided to illustrate the effectiveness of the control strategy.
Student motivation is one of the most important individual characters for explaining student performance in class. Existing researches show that it can be affected largely by social-contextual factors. Rather than foc...
详细信息
Student motivation is one of the most important individual characters for explaining student performance in class. Existing researches show that it can be affected largely by social-contextual factors. Rather than focusing on social relationship, in this paper we construct social activity networks for analyzing the impact of collective behaviors on student motivation. We conduct field experiments to compare social activity networks with relationship networks by analyzing the structural characteristics. We also investigate the dynamic of social activities,and validate the effectiveness of social activity network in reflecting social influence on student motivation. Our results show that social activities are important factors affecting student motivation.
暂无评论