A constructive algorithm to synthesize arbitrarily connected feedforward neural networks

In this work we present a constructive algorithm capable of producing arbitrarily connected feedforward neural network architectures for classification problems. Architecture and synaptic weights of the neural network should be defined by the learning procedure. The main purpose is to obtain a parsimonious neural network, in the form of a hybrid and dedicate linear/nonlinear classification model, which can guide to high levels of performance in terms of generalization. Though not being a global optimization algorithm, nor a population-based metaheuristics, the constructive approach has mechanisms to avoid premature convergence, by mixing growing and pruning processes, and also by implementing a relaxation strategy for the learning error. The synaptic weights of the neural networks produced by the constructive mechanism are adjusted by a quasi-Newton method, and the decision to grow or prune the current network is based on a mutual information criterion. A set of benchmark experiments, including artificial and real datasets, indicates that the new proposal presents a favorable performance when compared with alternative approaches in the literature, such as traditional MLP, mixture of heterogeneous experts, cascade correlation networks and an evolutionary programming system, in terms of both classification accuracy and parsimony of the obtained classifier.     

Remote sensing image classification based on neural network ensemble algorithm

The amounts and types of remote sensing data have increased rapidly, and the classification of these datasets has become more and more overwhelming for a single classifier in practical applications. In this paper, an ensemble algorithm based on Diversity Ensemble Creation by Oppositional Relabeling of Artificial Training Examples (DECORATEs) and Rotation Forest is proposed to solve the classification problem of remote sensing image. In this ensemble algorithm, the RBF neural networks are employed as base classifiers. Furthermore, interpolation technology for identical distribution is used to remold the input datasets. These remolded datasets will construct new classifiers besides the initial classifiers constructed by the Rotation Forest algorithm. The change of classification error is used to decide whether to add another new classifier. Therefore, the diversity among these classifiers will be enhanced and the accuracy of classification will be improved. Adaptability of the proposed algorithm is verified in experiments implemented on standard datasets and actual remote sensing dataset.     

Group search optimizer based optimal location and capacity of distributed generations

This paper presents a novel efficient population-based heuristic approach for optimal location and capacity of distributed generations (DGs) in distribution networks, with the objectives of minimization of fuel cost, power loss reduction, and voltage profile improvement. The approach employs an improved group search optimizer (iGSO) proposed in this paper by incorporating particle swarm optimization (PSO) into group search optimizer (GSO) for optimal setting of DGs. The proposed approach is executed on a networked distribution system—the IEEE 14-bus test system for different objectives. The results are also compared to those that executed by basic GSO algorithm and PSO algorithm on the same test system. The results show the effectiveness and promising applications of the proposed approach in optimal location and capacity of DGs.     

Adaptive neural control for strict-feedback stochastic nonlinear systems with time-delay

The problem of robust stabilization is investigated for strict-feedback stochastic nonlinear time-delay systems via adaptive neural network approach. Neural networks are used to model the unknown packaged functions, then the adaptive neural control law is constructed by a novel Lyapunov-Krasovskii functional and backstepping. It is shown that all the variables in the closed-loop system are semi-globally stochastic bounded, and the state variables converge into a small neighborhood in the sense of probability.     

Parameter estimation of q-Gaussian Radial Basis Functions Neural Networks with a Hybrid Algorithm for binary classification

A classification problem is a decision-making task that many researchers have studied. A number of techniques have been proposed to perform binary classification. Neural networks are one of the artificial intelligence techniques that has had the most successful results when applied to this problem. Our proposal is the use of q-Gaussian Radial Basis Function Neural Networks (q-Gaussian RBFNNs). This basis function includes a supplementary degree of freedom in order to adapt the model to the distribution of data. A Hybrid Algorithm (HA) is used to search for a suitable architecture for the q-Gaussian RBFNN. The use of this type of more flexible kernel could greatly improve the discriminative power of RBFNNs. In order to test performance, the RBFNN with the q-Gaussian basis functions is compared to RBFNNs with Gaussian, Cauchy and Inverse Multiquadratic RBFs, and to other recent neural networks approaches. An experimental study is presented on 11 binary-classification datasets taken from the UCI repository. Moreover, aerial imagery taken in mid-May, mid-June and mid-July was used to evaluate the potential of the methodology proposed for discriminating Ridolfia segetum patches (one of the most dominant and harmful weeds in sunflower crops) in two naturally infested fields in southern Spain.     

Classical and superposed learning for quantum weightless neural networks

A supervised learning algorithm for quantum neural networks (QNN) based on a novel quantum neuron node implemented as a very simple quantum circuit is proposed and investigated. In contrast to the QNN published in the literature, the proposed model can perform both quantum learning and simulate the classical models. This is partly due to the neural model used elsewhere which has weights and non-linear activations functions. Here a quantum weightless neural network model is proposed as a quantisation of the classical weightless neural networks (WNN). The theoretical and practical results on WNN can be inherited by these quantum weightless neural networks (qWNN). In the quantum learning algorithm proposed here patterns of the training set are presented concurrently in superposition. This superposition-based learning algorithm (SLA) has computational cost polynomial on the number of patterns in the training set.     

On optimization of expertise matching with various constraints

This paper studies the problem of expertise matching with various constraints. Expertise matching, which aims to find the alignment between experts and queries, is a common problem in many applications such as conference paper-reviewer assignment, product-reviewer alignment, and product-endorser matching. Most existing methods formalize this problem as an information-retrieval problem and focus on finding a set of experts for each query independently. However, in real-world systems, various constraints are often needed to be considered. For example, in order to review a paper, it is desirable that there is at least one senior reviewer to guide the reviewing process. An important question is: “Can we design a framework to efficiently find the optimal solution for expertise matching under various constraints?” This paper explores such an approach by formulating the expertise matching problem in a constraint-based optimization framework. In the proposed framework, the problem of expertise matching is linked to a convex cost flow problem, which guarantees an optimal solution under various constraints. We also present an online matching algorithm to support incorporating user feedbacks in real time. The proposed approach has been evaluated on two different genres of expertise matching problems, namely conference paper-reviewer assignment and teacher-course assignment. Experimental results validate the effectiveness of the proposed approach. Based on the proposed method, we have also developed an online system for paper-reviewer suggestions, which has been used for paper-reviewer assignment in a top conference and feedbacks from the conference organizers are very positive.     

Spectral efficiency of cognitive radio networks under interference constraint and QoS guarantees

We study the problem of maximizing spectral efficiency of cognitive radio network deployments subject to an interference constraint and under specific quality of service (QoS) guarantees. The interference constraint corresponds to the upper limit of the received power that can be tolerated at the licensed users’ due to transmissions from unlicensed users. The QoS guarantees stem from the requirements imposed by the applications running at the users’ terminals. A cross-layer design is adopted that maps the user’s requirements into delay related QoS guarantees at the data link layer and error probability QoS guarantees at the physical layer. The obtained numerical results provide important insights regarding the impact of the considered constraint and guarantees on the achievable spectral efficiency of cognitive radio networks.     

An efficient scheduler of RTOS for multi/many-core system

Recently there is a trend to broaden the usage of lower-power embedded media processor core to build the future high-end computing machine or the supercomputer. However the embedded solution also faces the operating system (OS) design challenge which the thread invoking overhead is higher for fine-grained scientific workload, the message passing among threads is not managed efficiently enough and the OS does not provide convenient enough service for parallel programming. This paper presents a scheduler of master-slave real-time operating system (RTOS) to manage the thread running for the distributed multi/many-core system without shared memories. The proposed scheduler exploits the data-driven feature of scientific workloads to reduce the thread invoking overhead. And it also defines two protocols: (1) one is between the RTOS and application program, which is used to reduce the burden of parallel programming for the programmer; (2) another one is between the RTOS and networks-on-chip, which is used to manage the message passing among threads efficiently. The experimental results show that the proposed scheduler can manage the thread running with lower overhead and less storage requirement, thereby, improving the multi/many-core system performance.     

Receiving-peer-driven multi-video-source scheduling algorithms in mobile P2P overlay networks

This paper proposes two algorithms for multi-video-source in a new mobile P2P architecture for streaming media systems. One is serial, and the other is parallel. When the service peer set providing expected QoS is not empty, the former is called, otherwise the latter is called. The former triggers the video source change event, re-selects a video source, and synchronizes the multi-video-source by the time model of the streaming sequence when QoS is degraded. The latter allows the multiple video sources to concurrently send the data to the receiving peer according to the assigned transmission. Compared to the existing papers, the contribution of this paper is fourfold: (1) the serial and parallel scheduling algorithms, correctly switched according to the actual situation, are firstly proposed; (2) the mobile feature of peers are firstly considered and validated; (3) the client nodes have better and smoother video quality; (4) our algorithms have shorter run time, which is a crucial factor for an on-line system.