Mixed transfer function neural networks for knowledge acquistition

Modeling helps to understand and predict the outcome of complex systems. Inductive modeling methodologies are beneficial for modeling the systems where the uncertainties involved in the system do not permit to obtain an accurate physical model. However inductive models, like artificial neural networks (ANNs), may suffer from a few drawbacks involving over-fitting and the difficulty to easily understand the model itself. This can result in user reluctance to accept the model or even complete rejection of the modeling results. Thus, it becomes highly desirable to make such inductive models more comprehensible and to automatically determine the model complexity to avoid over-fitting. In this paper, we propose a novel type of ANN, a mixed transfer function artificial neural network (MTFANN), which aims to improve the complexity fitting and comprehensibility of the most popular type of ANN (MLP - a Multilayer Perceptron).

Semantic and layered protein function prediction from PPI networks

Background The past few years have seen a rapid development in novel high-throughput technologies that have created large-scale data on protein-protein interactions (PPI) across human and most model species. This data is commonly represented as networks, with nodes representing proteins and edges representing the PPIs. A fundamental challenge to bioinformatics is how to interpret this wealth of data to elucidate the interaction of patterns and the biological characteristics of the proteins. One significant purpose of this interpretation is to predict unknown protein functions. Although many approaches have been proposed in recent years, the challenge still remains how to reasonably and precisely measure the functional similarities between proteins to improve the prediction effectiveness.

Results We used a Semantic and Layered Protein Function Prediction (SLPFP) framework to more effectively predict unknown protein functions at different functional levels. The framework relies on a new protein similarity measurement and a clustering-based protein function prediction algorithm. The new protein similarity measurement incorporates the topological structure of the PPI network, as well as the protein's semantic information in terms of known protein functions at different functional layers. Experiments on real PPI datasets were conducted to evaluate the effectiveness of the proposed framework in predicting unknown protein functions.

Conclusion The proposed framework has a higher prediction accuracy compared with other similar approaches. The prediction results are stable even for a large number of proteins. Furthermore, the framework is able to predict unknown functions at different functional layers within the Munich Information Center for Protein Sequence (MIPS) hierarchical functional scheme. The experimental results demonstrated that the new protein similarity measurement reflects more reasonably and precisely relationships between proteins.

Applying genetic algorithm for optimizing broadcasting process in ad-hoc network

Optimizing broadcasting process in mobile ad hoc network (MANET) is considered as a main challenge due to many problems, such as Broadcast Storm problem and high complexity in finding the optimal tree resulting in an NP-hard problem. Straight forward techniques like simple flooding give rise to Broadcast Storm problem with a high probability. In this work, genetic algorithm (GA) that searches over a population that represents a distinguishable ‘structure’ is adopted innovatively to suit MANETs. The novelty of the GA technique adopted here to provide the means to tackle this MANET problem lies mainly on the proposed method of searching for a structure of a suitable spanning tree that can be optimized, in order to meet the performance indices related to the broadcasting problem. In other words, the proposed genetic model (GM) evolves with the structure of random trees (individuals) ‘genetically’ generated using rules that are devised specifically to capture MANET behaviour in order to arrive at a minimal spanning tree that satisfies certain fitness function. Also, the model has the ability to give different solutions depending on the main factors specified such as, ‘time’ (or speed) in certain situations and ‘reachability’ in certain others.

Architecture of fiber network : from understanding to engineering of molecular gels

A new approach of engineering of molecular gels was established on the basis of a nucleation-initiated network formation mechanism. A variety of gel network structures can be obtained by regulating the starting temperature of the sol−gel transition. This enables us to tune the network from the spherulitic domains pattern to the extensively interconnected fibrillar network. As the consequence of fibrous network structure turning, desirable rheological and other in-use properties of the materials can be obtained accordingly. This approach of micro-/nanostructural fabrication may open up a new route for micro-/nanofunctional materials engineering in general.

Construction of wavelets and multiwavelets basis : a generalized method

Multiwavelets are wavelets with multiplicity r, that is r scaling functions and r wavelets, which define multiresolution analysis similar to scalar wavelets. They are advantageous over scalar wavelets since they simultaneously posse symmetry and orthogonality. In this work, a new method for constructing multiwavelets with any approximation order is presented. The method involves the derivation of a matrix equation for the desired approximation order. The condition for approximation order is similar to the conditions in the scalar case. Generalized left eigenvectors give the combinations of scaling functions required to reconstruct the desired spline or super function. The method is demonstrated by constructing a specific class of symmetric and non-symmetric multiwavelets with different approximation orders, which include Geranimo-Hardin-Massopust (GHM), Daubechies and Alperts like multi-wavelets, as parameterized solutions. All multi-wavelets constructed in this work, posses the good properties of orthogonality, approximation order and short support.

A generalised cost-aware caching scheme for caching continuous media objects in best-effort network environments

In this paper, we investigate the potential of caching to improve QoS in the context of continuous media applications over wired best-effort networks. We propose the use of a flexible caching scheme, called GD-Multi in caching continuous media (CM) objects. An important novel feature of our scheme is the provision of user or system administrator inputs in determining the cost function. Based on the proposed flexible cost function, Multi, an improvised Greedy Dual (GD) replacement algorithm called GD-multi (GDM) has been developed for layered multi-resolution multimedia streams. The proposed Multi function takes receiver feedback into account. We investigate the influence of parameters such as loss rate, jitter, delay and area in determining a proxy’s cache contents so as to enhance QoS perceived by clients. Simulation studies show improvement in QoS perceived at the clients in accordance to supplied optimisation metrics. From an implementation perspective, signalling requirements for carrying QoS feedback are minimal and fully compatible with existing RTSP-based Internet applications.

Upgrading arc median shortest path problem for an urban transportation network

In this paper, we propose an algorithm for an upgrading arc median shortest path problem for a transportation network. The problem is to identify a set of nondominated paths that minimizes both upgrading cost and overall travel time of the entire network. These two objectives are realistic for transportation network problems, but of a conflicting and noncompensatory nature. In addition, unlike upgrading cost which is the sum of the arc costs on the path, overall travel time of the entire network cannot be expressed as a sum of arc travel times on the path. The proposed solution approach to the problem is based on heuristic labeling and exhaustive search techniques, in criteria space and solution space, respectively. The first approach labels each node in terms of upgrading cost, and deletes cyclic and infeasible paths in criteria space. The latter calculates the overall travel time of the entire network for each feasible path, deletes dominated paths on the basis of the objective vector and identifies a set of Pareto optimal paths in the solution space. The computational study, using two small-scale transportation networks, has demonstrated that the algorithm proposed herein is able to efficiently identify a set of nondominated median shortest paths, based on two conflicting and noncompensatory objectives.

A neural network-based multi-agent classifier system with a Bayesian formalism for trust measurement

In this paper, a neural network (NN)-based multi-agent classifier system (MACS) utilising the trust-negotiation-communication (TNC) reasoning model is proposed. A novel trust measurement method, based on the combination of Bayesian belief functions, is incorporated into the TNC model. The Fuzzy Min-Max (FMM) NN is used as learning agents in the MACS, and useful modifications of FMM are proposed so that it can be adopted for trust measurement. Besides, an auctioning procedure, based on the sealed bid method, is applied for the negotiation phase of the TNC model. Two benchmark data sets are used to evaluate the effectiveness of the proposed MACS. The results obtained compare favourably with those from a number of machine learning methods. The applicability of the proposed MACS to two industrial sensor data fusion and classification tasks is also demonstrated, with the implications analysed and discussed.

Knowledge mobilization on decision making for school improvement : Canadian principals learning network.

Principals duties have expanded beyond instructional leadership. Roles now include being curriculum leader, supervisor, manager, head of finance, administration, compliance, and legal matters, and so on. These additional responsibilities impact their decision-making in relation to teaching, learning and school improvement in general. How, and on what basis, they make these decisions is crucial both to their development as instructional leaders and to educational reform processes. To contribute to knowledge on principals’ decision making skills, we have created a strategic knowledge mobilization initiative called 'Canadian Principals Learning Network (CPLN)'. Through a variety of face-to-face and online activities, it collaboratively links together an international group of practicing principals and university-based researchers with related expertise. This paper describes the initiative and outcomes.

Combination of decisions from a multiple neural network classifier system

In this paper, a study of the effectiveness of a multiple classifier system (MCS) in a medical diagnostic task is described. A hybrid network, based on the integration of a fuzzy ARTMAP and the probabilistic neural network, is employed as the basis of the MCS. Outputs from multiple networks are combined using some decision combination method to reach a final prediction. By using a real medical database, a set of experiments has been conducted to evaluate the performance of the MSC with different network configurations. The experimental results reveal the potential of the MCS as a useful decision support tool in the medical field.

Improved GART neural network model for pattern classification and rule extraction with application to power systems

Generalized adaptive resonance theory (GART) is a neural network model that is capable of online learning and is effective in tackling pattern classification tasks. In this paper, we propose an improved GART model (IGART), and demonstrate its applicability to power systems. IGART enhances the dynamics of GART in several aspects, which include the use of the Laplacian likelihood function, a new vigilance function, a new match-tracking mechanism, an ordering algorithm for determining the sequence of training data, and a rule extraction capability to elicit if-then rules from the network. To assess the effectiveness of IGART and to compare its performances with those from other methods, three datasets that are related to power systems are employed. The experimental results demonstrate the usefulness of IGART with the rule extraction capability in undertaking classification problems in power systems engineering.

Construction of neural network-based prediction intervals using particle swarm optimization

Prediction intervals (PIs) are excellent tools for quantification of uncertainties associated with point forecasts and predictions. This paper adopts and develops the lower upper bound estimation (LUBE) method for construction of PIs using neural network (NN) models. This method is fast and simple and does not require calculation of heavy matrices, as required by traditional methods. Besides, it makes no assumption about the data distribution. A new width-based index is proposed to quantitatively check how much PIs are informative. Using this measure and the coverage probability of PIs, a multi-objective optimization problem is formulated to train NN models in the LUBE method. The optimization problem is then transformed into a training problem through definition of a PI-based cost function. Particle swarm optimization (PSO) with the mutation operator is used to minimize the cost function. Experiments with synthetic and real-world case studies indicate that the proposed PSO-based LUBE method can construct higher quality PIs in a simpler and faster manner.

Dynamically searching for a domain for protein function prediction

The availability of large amounts of protein-protein interaction (PPI) data makes it feasible to use computational approaches to predict protein functions. The base of existing computational approaches is to exploit the known function information of annotated proteins in the PPI data to predict functions of un-annotated proteins. However, these approaches consider the prediction domain (i.e. the set of proteins from which the functions are predicted) as unchangeable during the prediction procedure. This may lead to valuable information being overwhelmed by the unavoidable noise information in the PPI data when predicting protein functions, and in turn, the prediction results will be distorted. In this paper, we propose a novel method to dynamically predict protein functions from the PPI data. Our method regards the function prediction as a dynamic process of finding a suitable prediction domain, from which representative functions of the domain are selected to predict functions of un-annotated proteins. Our method exploits the topological structural information of a PPI network and the semantic relationship between protein functions to measure the relationship between proteins, dynamically select a suitable prediction domain and predict functions. The evaluation on real PPI datasets demonstrated the effectiveness of our proposed method, and generated better prediction results.

A new neural network-based type reduction algorithm for interval type-2 fuzzy logic systems

This paper introduces a new type reduction (TR) algorithm for interval type-2 fuzzy logic systems (IT2 FLSs). Flexibility and adaptiveness are the key features of the proposed non-parametric algorithm. Lower and upper firing strengths of rules as well as their consequent coefficients are fed into a neural network (NN). NN output is a crisp value that corresponds to the defuzzified output of IT2 FLSs. The NN type reducer is trained through minimization of an error-based cost function with the purpose of improving modelling and forecasting performance of IT2 FLS models. Simulation results indicate that application of the proposed TR algorithm greatly enhances modelling and forecasting performance of IT2 FLS models. This benefit is achieved in no cost, as the computational requirement of the proposed algorithm is less than or at most equivalent to traditional TR algorithms.

Short-term load and wind power forecasting using neural network-based prediction intervals

Electrical power systems are evolving from today's centralized bulk systems to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level of uncertainty in power systems. Accurate load forecasting becomes more complex, yet more important for management of power systems. Traditional methods for generating point forecasts of load demands cannot properly handle uncertainties in system operations. To quantify potential uncertainties associated with forecasts, this paper implements a neural network (NN)-based method for the construction of prediction intervals (PIs). A newly introduced method, called lower upper bound estimation (LUBE), is applied and extended to develop PIs using NN models. A new problem formulation is proposed, which translates the primary multiobjective problem into a constrained single-objective problem. Compared with the cost function, this new formulation is closer to the primary problem and has fewer parameters. Particle swarm optimization (PSO) integrated with the mutation operator is used to solve the problem. Electrical demands from Singapore and New South Wales (Australia), as well as wind power generation from Capital Wind Farm, are used to validate the PSO-based LUBE method. Comparative results show that the proposed method can construct higher quality PIs for load and wind power generation forecasts in a short time.