Based on the theory of quantum mechanics and quantum computing, a path planning method for mobile robot based on quantum genetic algorithm was presented in this paper. By using the quantum-bit with the superposition s...
详细信息
Network Boosting (NB) is an ensemble learning method which combines weak learners together based on a network and can learn the target hypothesis asymptotically. NB has higher generalization ability compared to Baggin...
详细信息
Network Boosting (NB) is an ensemble learning method which combines weak learners together based on a network and can learn the target hypothesis asymptotically. NB has higher generalization ability compared to Bagging and AdaBoost. But, when datasets are class-imbalanced, the performance of NB will decrease quickly. In order to solve this problem, we present a Partition based Network Boosting method (PNB) to classify imbalanced data. For PNB method, every classifier node of the classifier network is provided with the same number of training data which are all of same weights. The classifier in the network is built by the balanced training set sampled from the training data according to the weights record of the training data it holds. And then, the weights of the instances of every node classifier are updated based on the classification results of self-node and its neighbor nodes. The classifier network is trained repeatedly in such a way. Weight factor of hypothesis in the training progress is introduced to improve the performance. The final classification is formed by all the hypotheses of the classifier network learned during the training progress so that the label of new instances can be decided by the weight voting. The experimental results on UCI data and imbalanced biomedical data show that the PNB algorithm has better AUC and recall performance compared with NB learning machine.
Video event detection is an important research area *** the video event is a key problem in video event *** this paper,we combine dynamic description logic with linear time temporal logic to build a logic system for v...
详细信息
Video event detection is an important research area *** the video event is a key problem in video event *** this paper,we combine dynamic description logic with linear time temporal logic to build a logic system for video event *** proposed logic system is named as LTD_(ALCO)which can represent and inference the static,dynamic and temporal knowledge in one uniform logic *** on the LTD_(ALCO),a framework for video event detection is *** video event detection framework can automatically obtain the logic description of video content with the help of ontology-based computer vision techniques and detect the specified video event based on satisfiability checking on LTD_(ALCO)formulas.
Roadmap methods were widely used in route planning fields, both for robots and unmanned aircrafts. Traditional roadmap is constituted by connecting the vertexes of convex obstacle, which is related to the locations of...
详细信息
Roadmap methods were widely used in route planning fields, both for robots and unmanned aircrafts. Traditional roadmap is constituted by connecting the vertexes of convex obstacle, which is related to the locations of start and goal of route, so the roadmap can not be reused when anyone of start and goal changed. Absence of reusability reduces the efficiency of route planning by using roadmap. A new roadmap constitution method was proposed in this paper, which is build on dividing the 2D configuration space into multi-scale grids and setting nodes of roadmap on grid boundary using Level-Set method, same method was used to construct the map cells of roadmap between any two nodes lays on same grid. The roadmap constituted with new method can be reused when the start or goal was changed; it is efficient for replanning problem.
To drive a single joint of rehabilitation robotic arm, we propose a new PM-TS actuator comprising a Pneumatic Muscle (PM) and a Torsion Spring (TS). Unlike the traditional agonist/antagonist PM actuator, the PM is arr...
详细信息
To drive a single joint of rehabilitation robotic arm, we propose a new PM-TS actuator comprising a Pneumatic Muscle (PM) and a Torsion Spring (TS). Unlike the traditional agonist/antagonist PM actuator, the PM is arranged in appropriate place as agonist and the torsion spring provides opposing torque as antagonist in the proposed actuator. The 1-DOF and 2-DOF rehabilitation robotic arm models are derived considering the PM-TS dynamic model. To realize a high-accurate trajectory tracking control of the robotic arms, an intelligent PID controller based on an Echo State Neural Network (ESN) is proposed, where the ESN state is updated by the online Recursive Least Square (RLS) algorithm. Simulation results demonstrate the validity of PM-TS actuators. The performance of RLS-ESN based PID controller is found more satisfactory than conventional PID controller in our study.
Shuffle operation on trajectories is useful in modeling parallel composition of words and languages. In this work, a new class of P systems with shuffle operation is presented. Such a system has language-objects and s...
详细信息
Shuffle operation on trajectories is useful in modeling parallel composition of words and languages. In this work, a new class of P systems with shuffle operation is presented. Such a system has language-objects and shuffle-operation rules in its regions. It can be used as a language generator; specifically it is used to generate languages from sets of languages. Some comparison results are obtained, which show that the power of shuffle operation is enlarged in the framework of P systems.
Randić et al. proposed a significant graphical representation for DNA sequences, which is very compact and avoids loss of information. In this paper, we build a fast algorithm for this graphical representation with ti...
详细信息
Randić et al. proposed a significant graphical representation for DNA sequences, which is very compact and avoids loss of information. In this paper, we build a fast algorithm for this graphical representation with time complexity O(n 2 ), and find another important advantage in the representation: no degeneracy. Moreover, we propose a new method to do similarity analysis of DNA sequences based on the representation. The approach adopts four elements of covariance matrix as a descriptor, and is illustrated on the first exon of beta-globin genes from 11 different species.
Randić et al. proposed a famous spectral graphical representation of DNA sequences, and claimed that it avoids loss of information. In this paper we build two mathematical models for this graphical representation and ...
详细信息
Randić et al. proposed a famous spectral graphical representation of DNA sequences, and claimed that it avoids loss of information. In this paper we build two mathematical models for this graphical representation and prove that the claim is correct, and that it also avoids degeneracy. Moreover, we propose a new method to do similarity analysis of DNA sequences based on the spectral representation. The method adopts M value to characterize a graphical representation and uses 24-component vector as descriptor. The approach is illustrated on the complete coding sequence of beta-globin genes from 7 different species.
In order to analyze the eddy current caused by the excitation signal and its influence on the secondary field response, the general analytical expressions of eddy current density for low frequency electromagnetic in c...
详细信息
Joint flexibility is an important factor to consider in the robot control design if high performance is expected for the robot manipulators. Research works on control of rigid-link flexible-joint (RLFJ) robot in liter...
详细信息
Joint flexibility is an important factor to consider in the robot control design if high performance is expected for the robot manipulators. Research works on control of rigid-link flexible-joint (RLFJ) robot in literature have assumed that the kinematics of the robot is known exactly. There have been few results that can deal with the kinematics uncertainty in RLFJ robot. In this paper, we propose an adaptive tracking control method which can deal with the kinematics uncertainty and uncertainties in both link and actuator dynamics of the RLFJ robot system. Nonlinear observers are designed to avoid accelerations measurement due to the fourth-order overall system dynamics. Asymptotic stability of the closed-loop system is shown and sufficient conditions are presented to guarantee the stability.
暂无评论