Enabling accurate and low-cost classification of a range of motion activities is of significant importance for wireless health through body worn inertial sensors and smartphones, due to the need by healthcare and fitn...
详细信息
ISBN:
(纸本)9781479935130
Enabling accurate and low-cost classification of a range of motion activities is of significant importance for wireless health through body worn inertial sensors and smartphones, due to the need by healthcare and fitness professonals to monitor exercises for quality and compliance. This paper proposes a novel contextual multi-armed bandits approach for large-scale activity classification. The proposed method is able to address the unique challenges arising from scaling, lack of training data and adaptation by melding context augmentation and continuous online learning into traditional activity classification. We rigorously characterize the performance of the proposed learning algorithm and prove that the learning regret (i.e. reward loss) is sublinear in time, thereby ensuring fast convergence to the optimal reward as well as providing short-term performance guarantees. Our experiments show that the proposed algorithm outperforms existing algorithms in terms of both providing higher classification accuracy as well as lower energy consumption.
This paper deals with the design of low complexity dynamic spectrum access (DSA) scheme for Cognitive Radios (CRs) to search the vacant band of tunable bandwidth, B_h. Such DSA scheme with tunable Bh is very critical ...
详细信息
ISBN:
(纸本)9781479984992
This paper deals with the design of low complexity dynamic spectrum access (DSA) scheme for Cognitive Radios (CRs) to search the vacant band of tunable bandwidth, B_h. Such DSA scheme with tunable Bh is very critical for CRs considering the coexistence of multiple communication standards in wideband input signal with channel bandwidths ranging from 25 kHz to 20 MHz and users expectations of seamless integration of multiple services on single mobile terminal. The proposed scheme is designed by integration of our allpass transformation and coefficient decimation method based variable digital filter and suitably modified Upper Confidence Bound based decision making algorithm. The simulation results and complexity comparisons show that the proposed DSA scheme offers superior performance in terms of vacant band selection rate (and hence high spectrum throughput) for wide range of Bh as well as different spectrum occupancies and total gate count savings of 20-90% over existing schemes.
A linear programming formulation of the optimal stopping problem for Markov decision processes is approximated using linear function approximation. Using this formulation, a reinforcement learning scheme based on a pr...
详细信息
A linear programming formulation of the optimal stopping problem for Markov decision processes is approximated using linear function approximation. Using this formulation, a reinforcement learning scheme based on a primal-dual method and incorporating a sampling device called 'split sampling' is proposed and analyzed. An illustrative example from option pricing is also included.
In this study, the linguistic information feed-back-based dynamical fuzzy system (LIFBDFS) proposed earlier by the authors is first introduced. The principles of alpha-level sets and backpropagation through time appro...
详细信息
In this study, the linguistic information feed-back-based dynamical fuzzy system (LIFBDFS) proposed earlier by the authors is first introduced. The principles of alpha-level sets and backpropagation through time approach are also briefly discussed. We next employ these two methods to derive an explicit learning algorithm for the feedback parameters of the LIFBDFS. With this training algorithm, our LIFBDFS indeed becomes a potential candidate in solving real-time modeling and prediction problems.
In this paper we implement six different learning algorithms in Optical Character Recognition (OCR) problem and achieve the criteria of end-time, number of iterations, train-set performance, test-set performance, vali...
详细信息
In this paper we implement six different learning algorithms in Optical Character Recognition (OCR) problem and achieve the criteria of end-time, number of iterations, train-set performance, test-set performance, validate-set performance and overall performance of these methods and compare them. Finally, we show the advantages and disadvantages of each method.
In this paper,the Wavelet Process Neural Network(WPNN) model is proposed based on the wavelet theory and the Process Neural Network(PNN) *** incorporates the neural network in learning from processes and the time-freq...
详细信息
In this paper,the Wavelet Process Neural Network(WPNN) model is proposed based on the wavelet theory and the Process Neural Network(PNN) *** incorporates the neural network in learning from processes and the time-frequency localization property of ***,the network can deal with continuous input signals,which make it facilitates in tackling dynamics of complex *** corresponding learning algorithm is given and the network is used to solve the problems of power load *** simulation test results indicate that the WPNN has a faster convergence speed and higher accuracy than the same scale *** provided an effective way for the problems of power load forecasting.
Monolayer feedback network is often used to realize the function of associative memory. In this paper, four algorithms used in monolayer feedback network for the realization of auto associative memory, namely the oute...
详细信息
Monolayer feedback network is often used to realize the function of associative memory. In this paper, four algorithms used in monolayer feedback network for the realization of auto associative memory, namely the outer product rule, the pseudo-inverse method, the LSSM algorithm, and the NDRAM algorithm are studied and compared by using a large number of randomly generated samples. The performance of the four algorithms in memory capacity and associative error rate are revealed and compared by simulation experiments, which provide a reference for applications and in-depth study of associative memory networks.
This paper surveys the artificial neural networks approach. Researchers believe that these networks have the wide range of applicability, they can treat complicated problems as well. The work described here discusses ...
详细信息
This paper surveys the artificial neural networks approach. Researchers believe that these networks have the wide range of applicability, they can treat complicated problems as well. The work described here discusses an efficient computational method that can treat complicated problems. The paper intends to introduce an efficient computational method which can be applied to approximate solution of the linear two-dimensional Fredholm integral equation of the second kind. For this aim, a perceptron model based on artificial neural networks is introduced. At first, the unknown bivariate function is replaced by a multilayer perceptron neural net and also a cost function to be minimized is defined. Then a famous learning technique, namely, the steepest descent method, is employed to adjust the parameters (the weights and biases) to optimize their behavior. The article also examines application of the method which turns to be so accurate and efficient. It concludes with a survey of an example in order to investigate the accuracy of the proposed method.
We consider a bistatic radar network that consists of multiple separated radar transmitters and receivers, which are deployed to detect potential attacks at some points of interest (PoIs). To better defend these PoIs,...
详细信息
We consider a bistatic radar network that consists of multiple separated radar transmitters and receivers, which are deployed to detect potential attacks at some points of interest (PoIs). To better defend these PoIs, the design of the bistatic radar network is investigated in two stages. First, we study the problem of optimally placing a number of radar transmitters and receivers in the sense of minimizing the maximum distance product between a PoI and its closest transmitter-receiver pair. For this problem, we propose a randomized Voronoi algorithm. Next, given the radars' locations, assuming that the transmitters use fixed and orthogonal frequencies to illuminate signals for interference avoidance, we study the problem of frequency selection for the receivers. Since an intelligent attacker can adaptively change the PoI to attack, the receivers should dynamically adapt their frequencies to cover different subsets of the PoIs. Accordingly, we model the dynamic interactions between the bistatic radar network and the attacker as a repeated security game. Based on their respective information, we propose two learning algorithms for each of them, respectively. We show that if both players follow the modified-regret-matching procedures, the empirical distributions of their actions converge to the set of correlated equilibria.
Calculation of reference evapotranspiration (ETo) is essential in hydrology and agriculture. ETo plays an important role in planning and management of water resources and irrigation scheduling. The results of many stu...
详细信息
Calculation of reference evapotranspiration (ETo) is essential in hydrology and agriculture. ETo plays an important role in planning and management of water resources and irrigation scheduling. The results of many studies strongly support the use of the Penman-Monteith FAO 56 (PMF-56) method as the standard method of estimating ETo. The basic obstacle to using this method widely is the numerous meteorological variables required. Multilayer perceptron (MLP) networks optimized with different learning algorithms and activation functions were applied for estimating ETo in a semiarid region in Iran. Four MLP models comprising various combinations of meteorological variables are developed. The MLP model which needs all of the meteorological parameters performed best for ETo estimation amongst the other MLP models. It was also found that the ConjugateGradient, DeltaBarDelta, DeltaBarDelta and Levenberg-Marquardt were the best algorithms for training the MLP1, MLP2, MLP3 and MLP4 models, respectively.
暂无评论