The technological developments of sensors, actuators, communication devices, and especially cloud computing, enable cloud robotics to be studied and designed. A cloud robot is a robot with lightweight inherent configu...
详细信息
Factorization Machines [1, 2] is a new factorization model that can combine the merits of SVM model with matrix factorization models. It can model all the interactive actions using factorized parameters. So it could m...
详细信息
ISBN:
(纸本)9781479967162
Factorization Machines [1, 2] is a new factorization model that can combine the merits of SVM model with matrix factorization models. It can model all the interactive actions using factorized parameters. So it could mimic most other matrix factorization models by feature engineering. Due to the superior flexible, Factorization Machines has already been widely used in many recommended algorithm competitions and practical online recommended system. But, because of the prevalence of large dataset, there is a need to improve the scalability of computation in factorization machines model. In this paper, we propose a parallel algorithm can be used on Factorization Machines model. The experimental results show that the proposed algorithm has good speed-up and scalability on big dataset.
Aircraft parameter estimation is a vital technology in aeronautical industry. It is the fundamental of control law design and aircraft performance evaluation. Harmony Search (HS) is proposed in 2001, which mimics musi...
详细信息
Aircraft parameter estimation is a vital technology in aeronautical industry. It is the fundamental of control law design and aircraft performance evaluation. Harmony Search (HS) is proposed in 2001, which mimics music players composing fantastic music. Its performance has been verified by many benchmark problems. In 1986, Reynolds proposed a mathematical model describing animals' group behavior, and he generally named the flocking creature “boids”, which can be interpreted as “bird like objects”. We modify the pitch adjustment step of HS inspired by the boid model. Our new method is named Boid-Inspired Harmony Search (BIHS). This paper investigates the application of BIHS to aircraft parameter estimation problem. In this work, the longitudinal state-space model of F-18 jet is used. It is shown that the BIHS approach is efficient, and in some ways, has an advantage over the classical Maximum Likelihood (ML) method.
This paper studies semi-global leader-following output consensus of a multi-agent system. Each follower agent in the system, described by a general linear system subject to external disturbances and actuator saturatio...
详细信息
This paper studies semi-global leader-following output consensus of a multi-agent system. Each follower agent in the system, described by a general linear system subject to external disturbances and actuator saturation, is to track the leader agent. Conditions on the agent dynamics are identified under which a low gain feedback based linear state control algorithm is constructed for each follower agent such that the leader-following output consensus is achieved when the communication topology among the agents is a directed graph that contains no loop and the leader is globally reachable. In addition, discussions and simulations are also provided for the output consensus in the presence of actuator saturation.
Since the energy constraint is a fundamental issue for wireless sensor networks(WSNs),the expectation of network lifetime has become a critical performance *** actual applications,due to the data traffics may fluctuat...
详细信息
Since the energy constraint is a fundamental issue for wireless sensor networks(WSNs),the expectation of network lifetime has become a critical performance *** actual applications,due to the data traffics may fluctuate randomly,there is a compelling need for a routing strategy that is robust to the variation amplitude of time varied data *** this paper,we jointly consider the lifetime maximization and a routing strategy with robustness,both of which are in compliance with the framework of cross-layer *** two correlated subproblems can be further modeled as a nonlinear optimization *** using the risk measures defined in the financial mathematics,the proposed optimization problem can be relaxed while the non-convex constraint can be transformed into a solvable *** Simulation results are further provided to validate our robust routing proposal.
The correspondence between key points is an important problem in lunar surface image processing, and further lays the foundation for the navigation of a rover and the terrain reconstruction of the lunar surface. Howev...
详细信息
The correspondence between key points is an important problem in lunar surface image processing, and further lays the foundation for the navigation of a rover and the terrain reconstruction of the lunar surface. However, the problem is still challenging due to the existence of large scale and rotation transformations, reflected view of the same scenery, and different illumination conditions between acquired images as the lunar rover moves forward. Traditional appearance matching algorithms, like SIFT, often fail in handling the above situations. By utilizing the structural cues between points, in this paper we propose a probabilistic spectral graph matching method to tackle the point correspondence problem in lunar surface images acquired by Yutu lunar rover which has been recently transmitted to the moon by China's Chang'e-3 lunar probe. Compared with traditional methods, the proposed method has three advantages. First, the incorporation of the structural information makes the matching more robust with respect to geometric transformations and illumination changes. Second, the assignment between points is interpreted in a probabilistic manner, and thus the best assignments can be easily figured out by ranking the probabilities. Third, the optimization problem can be efficiently approximately solved by spectral decomposition. Simulations on real lunar surface images witness the effectiveness of the proposed method.
In this paper, a novel signum-activated weights-and-structure-determination neuronet (SAWASDN) is proposed, investigated and tested. Being different from the past WASD neuronet, the proposed SAWASDN employs discontinu...
详细信息
In this paper, a novel signum-activated weights-and-structure-determination neuronet (SAWASDN) is proposed, investigated and tested. Being different from the past WASD neuronet, the proposed SAWASDN employs discontinuous functions as its activation functions. In addition, we can determine the optimal weights directly and the optimal neuronet structure automatically by the WASD method. Finally, numerical experiments of learning and testing XOR logic via noisy input and output data are conducted, with Gaussian noise and with uniform noise added. Numerical results substantiate the feasibility, efficacy and robustness of the SAWASDN.
In this paper, we proposed a biologically inspired model to solve the optimization problem of building district heating networks. The optimization strategy of the model was inspired from physiological observations of ...
详细信息
We introduce a notion of the entanglement transformation rate to characterize the asymptotic comparability of two multipartite pure entangled states under stochastic local operations and classical communication (SLOCC...
详细信息
We introduce a notion of the entanglement transformation rate to characterize the asymptotic comparability of two multipartite pure entangled states under stochastic local operations and classical communication (SLOCC). For two well known SLOCC inequivalent three-qubit states |GHZ⟩=(1/2)(|000⟩+|111⟩) and |W⟩=(1/3)(|100⟩+|010⟩+|001⟩), we show that the entanglement transformation rate from |GHZ⟩ to |W⟩ is exactly 1. That means that we can obtain one copy of the W state from one copy of the Greenberg-Horne-Zeilinger (GHZ) state by SLOCC, asymptotically. We then apply similar techniques to obtain a lower bound on the entanglement transformation rates from an N-partite GHZ state to a class of Dicke states, and prove the tightness of this bound for some special cases which naturally generalize the |W⟩ state. A new lower bound on the tensor rank of the matrix permanent is also obtained by evaluating the tensor rank of Dicke states.
Blood vessel segmentation is an important problem for quantitative structure analysis of retinal images, and many diseases are related to the structure changes. Manual segmentation is time consuming and computer aided...
详细信息
Blood vessel segmentation is an important problem for quantitative structure analysis of retinal images, and many diseases are related to the structure changes. Manual segmentation is time consuming and computer aided segmentation is required to deal with large amount images. This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. Multiple kernel learning (MKL) is introduced to deal with the problem, utilizing features from Hessian matrix based vesselness measure, response of multiscale Gabor filter, and multiple scale line strength features. The method is evaluated on the publicly available DRIVE and STARE databases. The performance of the MKL method is evaluated and experimental results show the high accuracy of the proposed method.
暂无评论