Behavioural Adaptation Towards Efficient Resource Sharing under the Lack of Communication

Cerebellar model articulation controller (CMAC) is a useful neural network learning technique. It was developed two decades ago but yet lacks an adequate learning algorithm, especially when it is used in a hybrid- type controller. This work is intended to introduce a simulation study for examining the performance of a hybrid-type control system based on the conventional learning algorithm of CMAC neural network. This study showed that the control system is unstable. Then a new adaptive learning algorithm of a CMAC based hybrid- type controller is proposed. The main features of the proposed learning algorithm, as well as the effects of the newly introduced parameters of this algorithm have been studied extensively via simulation case studies. The simulation results showed that the proposed learning algorithm is a robust in stabilizing the control system. Also, this proposed learning algorithm preserved all the known advantages of the CMAC neural network. Part II of this work is dedicated to validate the effectiveness of the proposed CMAC learning algorithm experimentally.

Cerebellar model articulation controller (CMAC) is a useful neural network learning technique. It was developed two decades ago but yet lacks adequate learning algorithm especially when it is used in a hybrid-type controller. Part I of this work was devoted to introduce a new CMAC adaptive learning algorithm. Part II will be directed to experimental application of new learning algorithm of a CMAC based hybrid-type real time controller. The proposed controller is applied for the trajectory tracking of a piezoelectric actuated tool post. It has been proven that the piezoelectric actuated tool post has hysteretic behavior. Extensive experiments have been carried out on the experimental setup to evaluate the proposed adaptive learning algorithm of CMAC. Only few experiments and their results are being presented. In these experiments, the performance of the piezoelectric actuated tool post has been examined and evaluated using different types of control algorithms and applying external load disturbance. The control performance of the proposed controller is compared with those of conventional controllers (PI controller and the conventional CMAC based controller). The experimental results showed that performance of the hybrid-type controller using the proposed learning algorithm is stable and more effective than that of the conventional controllers. Testing and comparing the learning ability of the proposed learning algorithm with that of the conventional CMAC learning algorithm indicated the effectiveness of the learning ability of the proposed algorithm. Finally, the response using the proposed hybrid-type controller is slightly better than using the conventional PI controller under the effect of external load disturbance.

A coordinated multiband spectrum sensing (CMSS) policy for mobile and geographically dispersed cognitive radio networks (CRNs), referred to as cluster-CMSS, is proposed. The goal is to detect the spectrum holes and to assign each secondary user (SU) a sensing channel with the maximum probability of being empty. In geographically dispersed CRNs, channel availability varies over the space, and this makes the sensing outcomes and sensing assignments location dependent. However, if the SUs are not equipped with location-finding technologies, fusing the sensing outcomes to find the optimal spectrum sensing assignments for the next sensing time becomes challenging for the base station (BS). To tackle this problem, we introduce a metric solely based on the sensing outcomes of SUs. Using this metric, along with a low-complexity clustering algorithm, enables the BS to efficiently divide the network into clusters. Further, we present an adaptive learning algorithm, to learn the dynamic behavior of channel occupancy in the primary network. The proposed learning algorithm considers SUs mobility model to determine the optimal learning window. To determine the sensing assignments, the BS performs a graph-theory-based coordinated multiband spectrum sensing within each cluster. Specifically, a weighted bipartite matching is employed. We have shown that cluster-CMSS significantly increases the spectrum opportunity discovery ratio for SUs at the cost of a slight increase in the energy consumption associated with spectrum sensing.

In the face of increasingly growing health demands and the impact of various public health emergencies, it is of great significance to study the regional differences in the allocation efficiency of the rural public health resources and its improvement mechanism. In this paper, the game competition relationship is included in the evaluation model, and the game cross-efficiency model is used to measure the allocation efficiency of the rural public health resources in 31 provinces of China from 2008 to 2017. Then, the Theil index model and the Gini index model are applied in exploring the regional differences in the allocation efficiency of rural public health resources and its sources. Finally, the bootstrap truncated regression model is used to analyze the influencing factors of the allocation efficiency of the rural public health resources in China. The results show that, first, the total allocation efficiency level of the rural public health resources in China from 2008 to 2017 is relatively low, and it presents a U-shaped trend, first falling and then rising. Second, the changing trend of the allocation efficiency of the rural public health resources in the eastern, central, and western regions of China is similar to that in the nationwide region, and it shows a gradient trend that “the allocation efficiency in the eastern region is high, the allocation efficiency in the western region is low, and the allocation efficiency in the Central region is at the medium level”. However, the gap among the three regions is continually narrowing. Third, the calculation results of the Theil index and the Gini index show that intra-regional differences are the major source of the regional differences in the allocation efficiency of the rural public health resources in China, and the inter-regional differences demonstrate an expansion trend. Finally, the improvement of the education level and the social support level will generally improve the allocation efficiency of the rural public health resources in China and its three regions. The increased governmental financial support and urbanization level will reduce the allocation efficiency of the rural public health resources in China and its three regions. The economic development level, the living conditions and the population density are the important influencing factors of the allocation efficiency differences of the rural public health resources in the three regions. Therefore, on the basis of ensuring the increase of the total supply of the rural public health resources, more attention should be paid to the improvement of the allocation efficiency. Moreover, on the basis of continually narrowing the inter-regional differences among the eastern, central, and western regions, more attention should be paid to the intra-regional differences of the allocation efficiency of the rural public health resources among the different provinces. The various economic and social policies should be constantly optimized to jointly improve the allocation efficiency of the rural public health resources.

A new fuzzy filter, called fuzzy stack filter (FSF), is proposed to extend the filtering capability of conventional stack filter (SF), which is based on the positive Boolean function (PBF) as its window operator. We fuzzify the onset and off-set of a given PBF to obtain two types of fuzzy PBFs. Then, we adopt the architecture of threshold decomposition to develop this new fuzzy filter with a fuzzy PBF as its window operator. Each fuzzy PBF is associated with a set of control parameters. Therefore, the original PBF can be estimated from above and below by two fuzzy PBFs with appropriate control parameters. Furthermore, we can apply the fuzzy modifiers to modify the fuzzy PBFs such that the PBFs can be completely estimated by the fuzzy PBFs. Hence, the stack filter is a special case of fuzzy stack filter. Since some control parameters are added in this new filter, the neural learning algorithms can be easily developed under the flexibility of the given control parameters. We first propose the fuzzy (m,n) rank-order filter to test our proposed learning algorithm. In this simple learning algorithm, we can remove the noise-corrupted images very well in contrast to the filtering behavior of rank-order filters. We believe that the results presented will lead to more fruitful research on more advanced and powerful learning algorithms dedicated to the appropriate applications.

Training of multilayered feed-forward neural networks (MLFFNNs) is considered in this work.A procedure to derive high performance learning algorithm for updating the network weights is proposed.The proposed algorithm is based on heuristic technique that is developed from an analysis of the performance of the basicbackpropagation training algorithm.A unified formulation of the conventional learning algorithms including the basic-backpropagation algorithm, the momentum algorithm, and the exponential-smoothing algorithm alongside with the proposed learning algorithm is introduced.Recursive relations for updating the weights of the network are derived which greatly simplifies the application of these rules.Simulation results are presented and comparative studies are carried out to demonstrate the effectiveness of the new learning algorithm.The new algorithm can converge more than hundred times faster than the conventional algorithms.

Distributed learning for Random Vector Functional-Link networks

In this paper, we propose a new learning algorithm for multilayer neural networks. In the backpropagation learning algorithm, weights are adjusted to reduce the error or cost function that reflects the difference between the computed and desired outputs. In the proposed learning algorithm, we consider each term of the output layer as a function of weights and adjust the weights directly so that the output layers produce the desired outputs. Experiments show the proposed algorithm consistently performs better than the backpropagation learning algorithm.

This paper presents a new learning algorithm with an adaptive structure for Spiking Neural Networks (SNNs). STDP and anti-STDP learning windows were combined with a 'virtual' supervisory neuron which remotely controls whether the STDP or anti-STDP window is used to adjust the synaptic efficacies of the connections between the hidden and the output layer. A simple new technique for updating the centres of hidden neurons is embedded in the hidden layer. The structure is dynamically adapted based on how close are the centres of hidden neurons to the incoming sample. Lateral inhibitory connections are used between neurons of the output layer to achieve competitive learning and make the network converge quickly. The proposed learning algorithm was demonstrated on the IRIS and the Wisconsin Breast Cancer benchmark datasets. Preliminary results show that the proposed algorithm can learn incoming data samples in one epoch only and with comparable accuracy to other existing training algorithms.

Methods of machine learning and data mining are becoming the cornerstone in information technologies with real-time image and video recognition methods getting more and more attention. While computational system architectures are getting larger and more complex, their learning methods call for changes, as training datasets often reach tens and hundreds of thousands of samples, therefore increasing the learning time of such systems. It is possible to reduce computational costs by tuning the system structure to allow fast, high accuracy learning algorithms to be applied. This paper proposes a system based on extended multidimensional neo-fuzzy units and its learning algorithm designed for data streams processing tasks. The proposed learning algorithm, based on the information entropy criterion, has significantly improved the system approximating capabilities. Experiments have confirmed the efficiency of the proposed system in solving real-time video stream recognition tasks.

Creating an applicable and precise failure prediction system is highly desirable for decision makers and regulators in the finance industry. This study develops a new Failure Prediction (FP) approach which effectively integrates a fuzzy logic-based adaptive inference system with the learning ability of a neural network to generate knowledge in the form of a fuzzy rule base. This FP approach uses a preprocessing phase to deal with the imbalanced data-sets problem and develops a new Fuzzy Neural Network (FNN) including an adaptive inference system in the learning algorithm along with its network structure and rule generation algorithm as a means to reduce prediction error in the FP approach.

BYY harmony learning, structural RPCL, and topological self-organizing on mixture models

An agent must learn and adapt quickly when playing against other agents. This process is challenging in particular when playing in stochastic environments against other learning agents. In this paper, we introduce a fast and adaptive learning algorithm for repeated stochastic games (FAL-SG). FAL-SG utilizes lossy game abstraction to reduce the state space of the game and facilitate learning and adapting rapidly. We analyze FAL-SG's performance by proving bounds on the abstraction loss and prediction mistakes and show that FAL-SG satisfies three criteria prescribed for multiagent learning algorithms. We successfully establish the robustness and scalability of FAL-SG with extensive theoretical and experimental results.

Isomap is a classic and representative manifold learning algorithm for nonlinear dimensionality reduction, which aims to circumvent the problem of “the curse of dimensionality” and attempts to recover the intrinsic structure hidden in high-dimensional data based on the assumption that data lie in or near a single manifold. However, Isomap fails to work when data set consists of multi-clusters or multiple sub-manifolds due to the requirement of preserving global geometric structure within data points. Several extended Isomap algorithms have been proposed to handle this issue, such as D-C Isoamp, M-Isomap, etc.. Here, we describe a new multi-manifolds learning algorithm by using a universal concept of neighbor: natural nearest neighbor (3N neighbor), which can be utilized automatically to construct a single or multiple adaptive neighborhood graphs that roughly coincide with the corresponding real multi-manifolds. The new algorithm preserves local adaptive neighborhood graph structure in terms of multi-manifolds as good as possible, in contrast to the previous algorithms, no category information about multi-manifolds are required. So it is a natural extension to the original Isomap, and also an adaptive multi-manifolds learning algorithm without the use of free parameter.

Simulation of E-learning in English personalized learning recommendation system based on Markov chain algorithm and adaptive learning algorithm