Future Multi-access edge computing (MEC) systems are required to execute applications composed of dependent tasks under end-to-end delay requirements. Further, they are likely to rely on renewable (or green) energy sources that are limited and fluctuate over time. These conditions give rise to a fundamental optimization problem that involves determining how tasks should be offloaded across edge servers so that dependency and delay constraints are satisfied while maximizing green energy usage or reducing an operator’s reliance on brown energy. In addition, the problem involves how green energy is shared among servers. Henceforth, we address a novel problem, called Green Dependent Task Offloading (G-DTO), that aims to maximize green energy usage, subject to the following constraints: (i) each edge server has limited green energy and computational capacity, and (ii) each task of an application, with a specified size, energy, and computational requirement, must be executed by a given deadline. To determine the optimal solution, we outline a Mixed-Integer Linear Programming (MILP) model. We also outline a genetic-algorithm-based approach, called G-DTO/GA. The simulation results on 18 synthetic network scenarios with small problem instances show that G-DTO/GA achieves an average of 96.83% green energy usage, closely matching the optimal MILP solution while requiring only 9.93% of the MILP runtime. Further experiments on the same 18 synthetic network scenarios, but with large problem instances, show that G-DTO/GA sustains high green energy usage, averaging 90.10%.

With the emergence of 5G technology, the demand for data communication between mobile users has significantly increased, and the number of cellular network infrastructure and mobile devices has also grown rapidly. However, a large number of base stations conducting wireless communication simultaneously inevitably brings serious interference due to the limited spectrum resources and dense distribution. Since the channels in the 5G dense cellular network with mobile users are complex and it is difficult to capture the channel state, the power allocation scheme adapting to a dynamic environment has become an important issue. In this article, a multiagent deep Q-network (DQN) distributed algorithm based on environmental awareness (MADQN-EA) is proposed. Specifically, the downlink between each base station and the user is treated as an agent, and a multiagent distributed approach is developed to improve the scalability of the algorithm. In response to the time-varying nature of the 5G dense cellular network environment, an environmental awareness training method is adopted. This method provides the agent with the opportunity to observe more changes in the 5G dense cellular network environment during the training process. This design significantly enhances the robustness of the proposed algorithm under the changing channel conditions. The proposed MADQN-EA is compared to fractional programming with a perfect CSI (FP-PC), multiagent DQN with experienced instance transfer (MADQN-EIT), and the random power selection scheme (Random). Simulation results show that MADQN-EA is robust against dynamic environment and achieves a higher sum rate performance.

Abstract Solving combined economic emission dispatch (CEED) problem optimizes power generation by balancing cost minimization with emission reduction, addressing economic and environmental goals simultaneously. This trade-off results in a Pareto front, where each non-dominated solution represents an optimal balance between costs and emissions. Decision-makers can select solutions based on their preferences. This paper proposes an Epsilon-based multi-objective genetic algorithm (MOGA) to solve the CEED problem. By integrating evolutionary techniques and Epsilon constraint methods, the proposed method actively explores diverse solutions, avoiding local optima and enhancing the Pareto front. The two-objective CEED problem is reformulated into two single-objective problems, alternately minimizing cost or emissions. The Epsilon constraint algorithm accelerates the search for optimal solutions. Two quality indicators are proposed to evaluate the Pareto fronts. The first indicator measures solution spread; it assesses the diversity of generator settings and the dominated volume. The second indicator evaluates the uniformity of solution distribution, where smaller distances indicate better uniformity. High spread and uniform distribution signify superior Pareto fronts. If diversity is insufficient, the proposed Epsilon-based MOGA continues to refine the front. The performance of the proposed method was tested on IEEE 30-bus and 118-bus systems, showing improved results compared to RNSGA-II, the Epsilon constraint algorithm, and NSGA-II. The proposed method produced more diverse and uniformly distributed non-dominated solutions; it offers grid operators a broader range of options to balance costs and emissions. Additionally, it achieved lower costs and emissions. The computational time for the larger IEEE 118 system is manageable and does not increase exponentially compared to the smaller IEEE 30 system.

In recent years, underwater acoustic sensor networks (UASNs) have played an increasingly important role in ocean exploration. However, underwater sensor networks suffers from severe propagation attenuation, limited energy and sensor mobility compared with terrestrial networks. Also, the value of sensing data is quite different in some applications of underwater data collection. To tackle these challenges, this paper proposes a hierarchical collection strategy based on value of information (VoI). Taking account of the mobility of nodes close to sea level, we divide the network into two layers according to the Ekman drift current model. In the upper layer, the nodes move violently with the sea water. We adopt opportunistic routing to allow these nodes to search for the appropriate next hop nodes actively. Meanwhile, nodes in the lower layer are clustered. According to the rarity of the data received in the historical data, we propose a novel mathematical formula to measure the VoI of the data, and define the ratio of received data value to energy consumption as the evaluation index of network energy efficiency. AUV-aided transmission and multi-hop transmission are utilized separately to determine the tradeoff between energy consumption and network performance. The choice of transmission mode depends on the VoI in a cluster. Simulation results indicate that the proposed strategy shows satisfactory performance in improving energy efficiency.

Abstract Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept; large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches.

Deep neural networks (DNNs) are currently being deployed as machine learning technology in a wide range of important real-world applications. DNNs consist of a huge number of parameters that require millions of floating-point operations (FLOPs) to be executed both in learning and prediction modes. A more effective method is to implement DNNs in a cloud computing system equipped with centralized servers and data storage sub-systems with high-speed and high-performance computing capabilities. This paper presents an up-to-date survey on current state-of-the-art deployed DNNs for cloud computing. Various DNN complexities associated with different architectures are presented and discussed alongside the necessities of using cloud computing. We also present an extensive overview of different cloud computing platforms for the deployment of DNNs and discuss them in detail. Moreover, DNN applications already deployed in cloud computing systems are reviewed to demonstrate the advantages of using cloud computing for DNNs. The paper emphasizes the challenges of deploying DNNs in cloud computing systems and provides guidance on enhancing current and new deployments.

This article investigates the robust secure transmission problem in two-tier B5G heterogeneous networks with multiple noncollusive eavesdroppers and users, where two types of imperfect channel state information (CSI) scenarios, i.e., instantaneous and statistic CSI scenarios, are considered. Given the two-sidedness of co-channel interference in physical-layer security and the selfishness of femtocell base stations (FBSs), an imperfect-CSI-based noncooperative game framework is proposed to maximize the profits of the macro base station (MBS) and FBSs, while guaranteeing user’s Quality-of-Service (QoS) requirement in terms of outage probability. Specifically, based on the involved two CSI scenarios, the original game where the MBS and FBSs act as players is elaborated as two robust game problems. To address channel uncertainties in the objective function, the worst-case and the mean value of the channel gains are used separately. Besides, the remaining channel uncertainties embodied in the intractable outage probability constraints are treated in a unified way, i.e., the extended Bernstein approximation. The existence and uniqueness of the Nash equilibrium (NE) are analyzed, and the sufficient condition on the uniqueness of the NE is derived. Then, two robust iterative algorithms are given to approach the robust game equilibrium. Finally, numerical results are presented to verify the theoretical analysis and show the robustness and effectiveness of the proposed algorithms.

Abstract Monitoring the perceptual quality of digital images is fundamentally important since digital image transmissions through the Internet continue to increase exponentially. Many automatic image quality evaluation (IQE) metrics have been developed based on image features correlated to image distortions; however, those metrics are only effective on particular image distortion types. In recent years, convolutional neural network (CNNs) have been developed for IQEs. These CNNs first capture image features from distorted images; image qualities are predicted based on the captured image features. Since the CNN weights are randomly initialized and are updated with respect to a loss function, image features which are strongly correlated to image quality are not guaranteed to be captured. In this paper, a hybrid deep neural network (DNN) is proposed by integrating image quality metrics to capture image features which are correlated to image quality; the approach guarantees that significant image features are included to predict image quality. Also, a tree-based classifier namely geometric semantic genetic programming is proposed to perform the overall predictions by incorporating CNN predictions and image features; the approach is simpler than the fully connected network but is able to model the nonlinear image qualities. The performance of the proposed hybrid DNN is evaluated by an image quality database with 3000 distorted images. The mean correlation achieved by the proposed hybrid DNN is 0.57 which is higher than the other tested methods. Experimental results with thet- test,F-test and Tueky’s range tests show that the proposed hybrid DNN achieves more accurate image predictions with a 99.9% confidence level, compared to the state-of-the-art IQE metics and the most recently developed CNN for IQEs.

Big data is generally captured by sensor networks in various industrial and manufacturing sectors; this big data is transmitted by mobile devices and Internet of Things (IoT) devices through the 5G mobile networks. 5G mobile edge computing is generally integrated with artificial intelligence (AI) in order to perform data mining for big data. 5G mobile edge computing attempts to help the industries to increase product quality, improve robustness and reliability of manufacturing processes, enhance manufacturing productivity and effectiveness, and reduce production costs. Recently, cryptocurrencies such as Bitcoin and Litecoins are used in virtual transactions by many financial sectors. Blockchain is integrated with the cryptocurrencies. Blockchain attempts to ensure security, trust and privacy of the virtual transactions, while centralized authorities or management are not necessary to be involved. Blockchain connects all transaction parties in order to monitor and verify each transaction. It reduces transaction risks and financial fraud without the involvement of centralized authorities or management. While blockchain is implemented in mobile devices and IoT devices, data trust and honesty can be guaranteed in the 5Gmobile networks. When the captured data ismore reliable, accurate datamining and analysis can be performed by the 5Gmobile edge computing. This special section focus on 5G mobile edge computing methods in order to perform better data analysis, simulations, and predictions for industrial applications when blockchain is integrated in the 5G mobile networks. We received 30 high quality submissions for this special section on "Blockchain and AI Enabled 5G Mobile Edge Computing." After the review and revision processes, six articles were selected to be published in this valuable document. Those articles are briefly summarized.

Although the Cognitive Radio Ad‐Hoc Network (CRAHN) is an effective technology to fully utilize the spectrum resource, the appearance of selfish nodes seriously reduces the communication efficiency of CRAHN and generates unfair resource competition. In this paper, a new incentive strategy is proposed to tackle selfish nodes in CRAHN. In our CRAHN model, the Secondary‐User (SU) cooperates with the Primary‐User (PU) in a spectrum leasing mode. Since PU can select multiple SUs as relays but only leases a common authorized spectrum usage time to SUs, the SU has the selfish tendency to reduce its power in relay task, which seriously damage the partnership between PU and SUs. We propose an evaluation coefficient to evaluate the behavior of each SU, where the evaluation coefficient establishes the reward and punishment mechanism to suppress the selfish behavior of SU in relay task. Meanwhile, in order to solve resource allocation problem, a Stackelberg game between PU and SUs is formulated and the optimal solutions are determined in a distributed manner. Simulation results validate that the incentive strategy can effectively suppress the selfish behavior of SUs, in the meantime, the total communication throughput is increased.

This paper investigates the output feedback tracking control for a fuzzy-model-based (FMB) control system when the control input is saturated, where the FMB is developed based on a T-S fuzzy model and a fuzzy controller. The controller is employed to close the feedback loop and generate the system to trace the trajectory of the states of a stable reference model subject to H∞ performance. To enhance the fuzzy controller design flexibility, the number of rules and premise membership functions can be adjusted. Stability analysis for the FMB control system is performed based on Lyapunov stability theory. To address the control input saturation problem, linear sectors are created by local linear upper and lower bounds to include the possible control area. Hence, the nonlinear saturation problem can be tackled by the stability analysis of linear sectors. The membership-functions-dependent technique is used to bring the information and address the nonlinearity of embedded membership functions into the stability analysis. The numerical simulation example demonstrates the effectiveness of the proposed approach and discusses the effect of H∞ performance and control input saturation rate according to the tracking result.

In this study, a power allocation scheme for two‐tier femtocell networks is proposed to maximise the user utilities constrained with satisfactory quality of service, where femtocell users share the same frequency with macrocell users (MUEs). Since the environment changes and the channel gains cannot be assumed to be constants, a worst‐case method is used to address the uncertainty of the power allocation problem. A non‐cooperative game model is developed to maximise the utilities of femtocell users by letting the users competing the utilities with others. As the robustness can be affected by the changing gains of communication links, the robust Stackelberg game is proposed to model this hierarchical competition where the MUEs and femtocell users act as leaders and followers, respectively. Two effective pricing schemes are applied to maximise the utilities, when different user demands are required, where the uniqueness of Nash equilibrium is proved in the two schemes. Numerical results show the convergence of the Stackelberg game with uncertainty and also the results demonstrate the effectiveness of the power allocation algorithm.

Summary Ultra dense deployment of base stations is one of most significant features in smart city communication networks. Aiming at the large‐scale wireless communication issue in smart city, we propose a distributed robust power allocation scheme with proportional fairness for cooperative orthogonal frequency‐division‐multiple‐access relay network. With the amplify‐and‐forward relay mode, all of the relays assist the information transmission simultaneously on orthogonal subcarriers. Considering the uncertainty of channel gains, first we aim at achieving the maximum utility subject to the constraints of outage probability threshold and power bound. Subsequently, the problem is transformed to a solvable convex optimization problem with determination constraints. The dual‐decomposition method is applied to solve the formulated optimization problem. To reduce the information exchange of the whole system, we propose a computationally efficient distributed iteration algorithm. Numerical results reveal the effectiveness of the proposed robust optimization algorithm. Copyright © 2016 John Wiley & Sons, Ltd.

Design of preferred products requires affective quality information which relates to human emotional satisfaction. However, it is expensive and time consuming to conduct a full survey to investigate affective qualities regarding all objective features of a product. Therefore, developing a prediction model is essential in order to understand affective qualities on a product. This paper proposes a novel fuzzy regression method in order to predict affective quality and estimate fuzziness in human assessment, when objective features are given. The proposed fuzzy regression also improves on traditional fuzzy regression that simulate only a single characteristic with the resulting limitation that the amount of fuzziness is linear correlated with the independent and dependent variables. The proposed method uses a varying spread to simulate nonlinear and nonsymmetrical fuzziness caused by affective quality assessment. The effectiveness of the proposed method is evaluated by two very different case studies, affective design of an electric iron and image quality assessment, which involve different amounts of data, varying fuzziness, and discrete and continuous data. The results obtained by the proposed method are compared with those obtained by the state of art and the recently developed fuzzy regression methods. The results show that the proposed method can generate better prediction models in terms of three fuzzy criteria, which address both predictions of magnitudes and fuzziness.

Development of new products or services requires knowledge and understanding of aesthetic qualities that correlate to perceptual pleasure. As it is not practical to develop a survey to assess aesthetic quality for all objective features of a new product or service, it is necessary to develop a model to predict aesthetic qualities. In this paper, a fuzzy regression method is proposed to predict aesthetic quality from a given set of objective features and to account for uncertainty in human assessment. The proposed method overcomes the shortcoming of statistical regression, which can predict only quality magnitudes but cannot predict quality uncertainty. The proposed method also attempts to improve traditional fuzzy regressions, which simulate a single characteristic with which the estimated uncertainty can only increase with the increasing magnitudes of objective features. The proposed fuzzy regression method uses genetic programming to develop nonlinear structures of the models, and model coefficients are determined by optimizing the fuzzy criteria. Hence, the developed model can be used to fit the nonlinearities of sample magnitudes and uncertainties. The effectiveness and the performance of the proposed method are evaluated by the case study of perceptual images, which are involved with different sampling natures and with different amounts of samples. This case study attempts to address different characteristics of human assessments. The outcomes demonstrate that more robust models can be developed by the proposed fuzzy regression method compared with the recently developed fuzzy regression methods, when the model characteristics and fuzzy criteria are taken into account.

Images captured by digital cameras are generally not perfect as image blurring is usually generated by camera motion through long hand-held exposure. Deblurring filters can be used to improve image quality by removing image blur. Prior to develop a deblurring filter, a simulator for image quality assessment is essential to optimize filter parameters. Although subjective image quality assessment (subjective IQA) is commonly used for evaluating the visual effect of digital images for a wide range of image processing applications, it is inconvenient to be implemented in real-time. Generally, statistical regression is used to generate a functional map to correlate the subjective IQA and the objective image quality metrics. However, it cannot address the uncertainty caused by human judgment during the subjective IQA. This paper first proposes a fuzzy regression method to develop the functional map that overcomes the limitation of statistical regression that cannot account for uncertainty introduced through human judgment. Based on the fuzzy regression models, the deblurring filter parameters can be optimized. Experimental results show that the satisfactory deblurring can be achieved on blurred images captured by a smartphone camera.

Fuzzy regression methods have commonly been used to develop consumer preferences models, which correlate the engineering characteristics with consumer preferences regarding a new product; the consumer preference models provide a platform, whereby product developers can decide the engineering characteristics in order to satisfy consumer preferences prior to developing the products. Recent research shows that these fuzzy regression methods are commonly used to model customer preferences. However, these approaches have a common limitation in that they do not investigate the appropriate polynomial structure, which includes significant regressors with only significant engineering characteristics; also, they cannot generate interaction or high-order regressors in the models. The inclusion of insignificant regressors is not an effective approach when developing the models. Exclusion of significant regressors may affect the generalization capability of the consumer preference models. In this paper, a novel fuzzy modeling method is proposed, namely fuzzy stepwise regression (F-SR), in order to develop a customer preference model which is structured with an appropriate polynomial, which includes only significant regressors. Based on the appropriate polynomial structure, the fuzzy coefficients are determined using the fuzzy least-squares regression. The developed fuzzy regression model attempts to obtain a better generalization capability using a smaller number of regressors. The effectiveness of the F-SR is evaluated based on two design problems, namely a tea maker design and a solder paste dispenser design. Results show that better generalization capabilities can be obtained compared with the fuzzy regression methods commonly used for new product development. In addition, smaller scale consumer preference models with fewer engineering characteristics can be obtained. Hence, a simpler and more effective product development platform can be provided.

In many applications, such as way finding and navigation, the quality of image sequences are generally poor, as motion blur caused from body movement degrades image quality. It is difficult to remove the blurs without prior information about the camera motion. In this paper, we utilize inertial sensors, including accelerometers and gyroscopes, installed in smartphones, in order to determine geometric data of camera motion during exposure. Based on the geometric data, we derive a blurring function namely point spread function (PSF) which deblur the captured image by reversing motion effect. However, determination of the optimal PSF with respect to the image quality is multioptimum, as deblurred images are not linearly correlated to image intelligibility. Therefore, this paper proposes a hybrid optimization method, which is, incorporated the mechanisms of particle swarm optimization (PSO) and gradient search method, in order to optimize PSF parameters. It aims to incorporate the advantages of the two methods, where the PSO is effective in localizing the global region and the gradient search method is effective in converging local optimum. Experimental results indicated that deblurring can be successfully performed using the optimal PSF. Also, the performance of proposed method is compared with the commonly used deblurring methods. Better results in term of image quality can be achieved. The resulting deblurring methodology is an important component. It will be used to improve deblurred images to perform edge detection, in order to detect paths, stairs ways, movable and immovable objects for vision-impaired people.

Takagi-Sugeno neural fuzzy models (TS-models) have commonly been applied in the development of traffic flow predictors based on traffic flow data captured by the on-road sensors installed along a freeway. However, using all captured traffic flow data is ineffective for the TS-models for traffic flow predictions. Therefore, an appropriate on-road sensor configuration consisting of significant sensors is essential to develop an accurate TS-model for traffic flow forecasting. Although the trial and error method is usually used to determine the appropriate on-road sensor configuration, it is time-consuming and ineffective in trialing all individual configurations. In this paper, a systematic and effective experimental design method involving orthogonal arrays is used to determine appropriate on-road sensor configurations for TS-models. A case study was conducted based on the development of TS-models using traffic flow data captured by on-road sensors installed on a Western Australia freeway. Results show that an appropriate on-road sensor configuration for the TS-model can be developed in a reasonable amount of time when an orthogonal array is used. Also, the developed TS-model can generate accurate traffic flow forecasting.

In this letter, a hybrid descent method is used to determine a set of filter parameters for a sigmoid filter which attempts to work under various SNR conditions. It overcomes the limitations of the current sigmoid filters that performs effectively only at a single SNR. Results show that significant improvement in terms of better speech qualities can be achieved by the proposed sigmoid filter when working under various SNR conditions.

Prior to manufacture a new products, consumers with similar purchasing attitudes are grouped into clusters of which their central points are used as ideal points for new product development. However, many clustering methods ignore the fuzziness of consumers in purchasing products or conducing survey. This paper presents a new method which integrates a fuzzy data processing technique for dimension reduction of customer attributes and a fuzzy clustering technique for grouping consumers with similar purchasing attributes. Hence, the central points of each group are treated as the ideal points for new product development. The effectiveness of the proposed method is demonstrated based on a new product design problem for new digital cameras.

Neural networks have been applied for short-term traffic flow forecasting with reasonable accuracy. Past traffic flow data, which has been captured by on-road sensors, is used as the inputs of neural networks. The size of this data significantly affects the performance of short-term traffic flow forecasting, as too many inputs result in over-specification of neural networks and too few inputs result in under-learning of neural networks. However, the amount of past traffic flow data input, is usually determined by the trial and error method. In this paper, an experimental design method, namely orthogonal design, is used to determine appropriate amount of past traffic flow data for neural networks for short-term traffic flow forecasting. The effectiveness of the orthogonal design is demonstrated by developing neural networks for short-term traffic flow forecasting based on past traffic flow data captured by on-road sensors located on a freeway in Western Australia.

Hypoglycemia (or low blood glucose) is dangerous for Type 1 diabetes mellitus (T1DM) patients, as this can cause unconsciousness or even death. However, it is impossible to monitor the hypoglycemia by measuring patients' blood glucose levels all the time, especially at night. In this paper, a hypoglycemic episode diagnosis system is proposed to determine T1DM patients' blood glucose levels based on these patients' physiological parameters which can be measured online. It can be used not only to diagnose hypoglycemic episodes in T1DM patients, but also to generate a set of rules, which describe the domains of physiological parameters that lead to hypoglycemic episodes. The hypoglycemic episode diagnosis system addresses the limitations of the traditional neural network approaches which cannot generate implicit information. The performance of the proposed hypoglycemic episode diagnosis system is evaluated by using real T1DM patients' data sets collected from the Department of Health, Government of Western Australia, Australia. Results show that satisfactory diagnosis accuracy can be obtained. Also, explicit knowledge can be produced such that the deficiency of traditional neural networks can be overcome. A clear understanding of how they perform diagnosis can be indicated.

This paper presents a novel fuzzy particle swarm optimization with cross-mutated operation (FPSOCM), where a fuzzy logic is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation based on human knowledge. By introducing the fuzzy system, the value of the inertia weight of PSO becomes adaptive. The new cross-mutated operation effectively drives the solution to escape from local optima. To illustrate the performance of the FPSOCM, a suite of benchmark test functions are employed. Experimental results show the proposed FPSOCM method performs better than some existing hybrid PSO methods in terms of solution quality and solution reliability (standard deviation upon many trials). Moreover, an industrial application of economic load dispatch is given to show that the FPSOCM method performs statistically more significant than the existing hybrid PSO methods.

In this paper, multiple detection engines with multi-layered intrusion detection mechanisms are proposed for enhancing computer security. The principle is to coordinate the results from each single-engine intrusion alert system, which seamlessly integrates with a multiple layered distributed service-oriented structure. An improved hidden Markov model (HMM) is created for the detection engine which is capable of the immunology-based self/nonself discrimination. The classifications of normal and abnormal behaviours of system calls are further examined by an advanced fuzzy-based inference process tuned by HPSOWM. Considering a real benchmark dataset from the public domain, our experimental results show that the proposed scheme can greatly shorten the training time of HMM and significantly reduce the false positive rate. The proposed HPSOWM works especially well for the efficient classification of unknown behaviors and malicious attacks.

Speech recognition has been used in various real-world applications such as automotive control, electronic toys, electronic appliances etc. In many applications involved speech control functions, a commercial speech recognizer is used to identify the speech commands voiced out by the users and the recognized command is used to perform appropriate operations. However, users' commands are often corrupted by surrounding ambient noise. It decreases the effectiveness of speech recognition in order to implement the commands accurately. This paper proposes a multichannel filter to enhance noisy speech commands, in order to improve accuracy of commercial speech recognizers which work under noisy environment. An innovative particle swarm optimization (PSO) is proposed to optimize the parameters of the multichannel filter which intends to improve accuracy of the commercial speech recognizer working under noisy environment. The effectiveness of the multichannel filter was evaluated by interacting with a commercial speech recognizer, which was worked in a warehouse.

Over the past two decades, neural networks have been applied to develop short-term traffic flow predictors. The past traffic flow data, captured by on-road sensors, is used as input patterns of neural networks to forecast future traffic flow conditions. The amount of input patterns captured by the on-road sensors is usually huge, but not all input patterns are useful when trying to predict the future traffic flow. The inclusion of useless input patterns is not effective to developing neural network models. Therefore, the selection of appropriate input patterns, which are significant for short-term traffic flow forecasting, is essential. This can be conducted by setting an appropriate configuration of input nodes of the neural network; however, this is usually conducted by trial and error. In this paper, the Taguchi method, which is a robust and systematic optimization approach for designing reliable and high-quality models, is proposed for the purpose of determining an appropriate neural network configuration, in terms of input nodes, in order to capture useful input patterns for traffic flow forecasting. The effectiveness of the Taguchi method is demonstrated by a case study, which aims to develop a short-term traffic flow predictor based on past traffic flow data captured by on-road sensors located on a Western Australia freeway. Three advantages of using the Taguchi method were demonstrated: 1) short-term traffic flow predictors with high accuracy can be designed; 2) the development time for short-term traffic flow predictors is reasonable; and 3) the accuracy of short-term traffic flow predictors is robust with respect to the initial settings of the neural network parameters during the learning phase.

For over two decades, speech control mechanisms have been widely applied in manufacturing systems such as factory automation, warehouse automation, and industrial robotic control for over two decades. To implement speech controls, a commercial speech recognizer is used as the interface between users and the automation system. However, users' commands are often contaminated by environmental noise which degrades the performance of speech recognition for controlling automation systems. This paper presents a multichannel signal enhancement methodology to improve the performance of commercial speech recognizers. The proposed methodology aims to optimize speech recognition accuracy of a commercial speech recognizer in a noisy environment based on a beamformer, which is developed by an intelligent particle swarm optimization. It overcomes the limitation of the existing signal enhancement approaches whereby the parameters inside commercial speech recognizers are required to be tuned, which is impossible in a real-world situation. Also, it overcomes the limitation of the existing optimization algorithm including gradient descent methods, genetic algorithms and classical particle swarm optimization that are unlikely to develop optimal beamformers for maximizing speech recognition accuracy. The performance of the proposed methodology was evaluated by developing beamformers for a commercial speech recognizer, which was implemented on warehouse automation. Results indicate a significant improvement regarding speech recognition accuracy.

This paper proposes a novel neural network (NN) training method that employs the hybrid exponential smoothing method and the Levenberg-Marquardt (LM) algorithm, which aims to improve the generalization capabilities of previously used methods for training NNs for short-term traffic flow forecasting. The approach uses exponential smoothing to preprocess traffic flow data by removing the lumpiness from collected traffic flow data, before employing a variant of the LM algorithm to train the NN weights of an NN model. This approach aids NN training, as the preprocessed traffic flow data are more smooth and continuous than the original unprocessed traffic flow data. The proposed method was evaluated by forecasting short-term traffic flow conditions on the Mitchell freeway in Western Australia. With regard to the generalization capabilities for short-term traffic flow forecasting, the NN models developed using the proposed approach outperform those that are developed based on the alternative tested algorithms, which are particularly designed either for short-term traffic flow forecasting or for enhancing generalization capabilities of NNs.

In this paper, process conditions of epoxy dispensing processes are determined by the proposed genetic algorithm based neural fuzzy networks, which consists of two tasks: a) the approach of neural fuzzy networks, which was shown to be better than the other existing approaches, is proposed to develop models in relating between process parameters and quality characteristics for the epoxy dispensing processes; b) the approach of genetic algorithm is used to determine process parameters with respect to pre-defined quality requirements based on the developed neural fuzzy network models. The results indicate that, based on the proposed genetic algorithm based neural fuzzy network, estimated process parameters can achieve specified requirements of microchip encapsulations with high and robust qualities.

Fuzzy regression is a commonly used approach for modeling manufacturing processes in which the availability of experimental data is limited. Fuzzy regression can address fuzzy nature of experimental data in which fuzziness is not avoidable while carrying experiments. However, fuzzy regression can only address linearity in manufacturing process systems, but nonlinearity, which is unavoidable in the process, cannot be addressed. In this paper, an evolutionary fuzzy regression which integrates the mechanism of a fuzzy regression and genetic programming is proposed to generate manufacturing process models. It intends to overcome the deficiency of the fuzzy regression, which cannot address nonlinearities in manufacturing processes. The evolutionary fuzzy regression uses genetic programming to generate the structural form of the manufacturing process model based on tree representation which can address both linearity and nonlinearities in manufacturing processes. Then it uses a fuzzy regression to determine outliers in experimental data sets. By using experimental data excluding the outliers, the fuzzy regression can determine fuzzy coefficients which indicate the contribution and fuzziness of each term in the structural form of the manufacturing process model. To evaluate the effectiveness of the evolutionary fuzzy regression, a case study regarding modeling of epoxy dispensing process is carried out.

A fuzzy particle swarm optimization (PSO) for the minimization of makespan in permutation flow shop scheduling problem is presented in this paper. In the proposed fuzzy PSO, the inertia weight of PSO and the control parameter of the cross mutated operation are determined by a set of fuzzy rules. To escape the local optimum, cross-mutated operation is introduced. In order to make PSO suitable for solving permutation flow shop scheduling problem, a roulette wheel mechanism is proposed to convert the continuous position values of particles to job per mutations. Meanwhile, a swap-based local search for scheduling problem is designed for the local exploration on a discrete job permutation space. Flow shop benchmark functions are employed to evaluate the performance of the fuzzy PSO for flow shop scheduling problems and the results indicate that the algorithm performs better compared with existing hybrid PSO algorithms.

This paper, proposes a hybrid fuzzy logic-based particle swarm optimization (PSO) with cross-mutated operation method for the minimization of makespan in permutation flow shop scheduling problem. This problem is a typical non-deterministic polynomial-time (NP) hard combinatorial optimization problem. In the proposed hybrid PSO, fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the inertia weight becomes adaptive. The cross-mutated operation effectively forces the solution to escape the local optimum. To make PSO suitable for solving flow shop scheduling problem, a sequence-order system based on the roulette wheel mechanism is proposed to convert the continuous position values of particles to job permutations. Meanwhile, a new local search technique namely swap-based local search for scheduling problem is designed and incorporated into the hybrid PSO. Finally, a suite of flow shop benchmark functions are employed to evaluate the performance of the proposed PSO for flow shop scheduling problems. Experimental results show empirically that the proposed method outperforms the existing hybrid PSO methods significantly.

Modeling of manufacturing processes is important because it enables manufacturers to understand the process behavior and determine the optimum operating conditions of the process for a high yield, low cost and robust operation. However, existing techniques in modeling manufacturing processes cannot address the whole common issues in developing models for manufacturing processes: a) manufacturing processes are usually nonlinear in nature; b) a small amount of experimental data is only available for developing manufacturing process models; c) outliers often exist in experimental data; d) explicit models in a polynomial form are often preferred by manufacturing process engineers; and e) models with satisfactory prediction accuracy are required. In this paper, a modeling algorithm, namely, the particle swarm optimization-based fuzzy regression (PSO-FR) approach, is proposed to generate fuzzy nonlinear regression models, which seek to address all of the common issues in developing models for manufacturing processes. The PSO-FR first employs the operations of particle swarm optimization to generate the structures of the process models in nonlinear polynomial form, and then it employs a fuzzy coefficient generator to identify outliers in the original experimental data. Fuzzy coefficients of the process models are determined by the fuzzy coefficient generator in which the experimental data excluding the outliers is used. The effectiveness of the PSO-FR approach is evaluated by modeling the manufacturing process liquid epoxy molding process which is a commonly used technology for microchip encapsulation in electronic packaging. Results were compared with those based on the commonly used modeling methods. It was found that PSO-FR can achieve better goodness-of-fitness than other methods. Also, the prediction accuracy of the model developed based on the PSO-FR is better than the other methods.

Even if genetic programming (GP) has rich literature in development of polynomial models for manufacturing processes, the polynomial models may contain redundant terms which may cause the overfitted models. In other words, those models have good accuracy on training data sets but poor accuracy on untrained data sets. In this paper, a mechanism which aims at avoiding overfitting is proposed based on a statistical method, backward elimination, which intends to eliminate insignificant terms in polynomial models. By modeling a solder paste dispenser for electronic manufacturing, results show that the insignificant terms in the polynomial model can be eliminated by the proposed mechanism. Results also show that the polynomial model generated by the proposed GP can achieve better predictions than the existing methods.

Hypoglycemia is dangerous for Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, we have developed a classification unit with hybridizing the approaches of neural networks and genetic algorithm to identify the presences of hypoglycemic episodes for TIDM patients. The proposed classification unit is built and is validated by using the real T1DM patients' data sets collected from Department of Health, Government of Western Australia. Experimental results show that the proposed neural network based classification unit can achieve more accurate results on both trained and unseen T1DM patients' data sets compared with those developed based on the commonly used classification methods for medical diagnosis including statistical regression, fuzzy regression and genetic programming.

In this paper, a hybrid evolutionary algorithm (HEA) based on the approaches of the evolutionary algorithm and a local search (LS) is proposed to determine the gene signatures for predicting histologic response of chemotherapy on osteosarcoma patients, which is one of the most common malignant bone tumor in children. The HEA consists of a population of individuals but the evolution of individuals is conducted by a LS, rather than the crossover and mutation used in the traditional evolutionary algorithms. The proposed HEA can simultaneously optimize the feature subset and the classifier through a common solution coding mechanism. Experimental results indicate that HEA can obtain more accurate signatures than the other existing approaches in determining chemoresponse for osteosarcoma.

Low blood glucose (Hypoglycaemia) is dangerous and can result in unconsciousness, seizures and even death. It has a common and serious side effect of insulin therapy in patients with diabetes. We measure physiological parameters (heart rate, corrected QT interval of the electrocardiogram (ECG) signal, change of heart rate, and the change of corrected QT interval) continuously to provide detection of hypoglycaemic. Based on these physiological parameters, we have developed a genetic algorithm based multiple regression model to determine the presence of hypoglycaemic episodes. Genetic algorithm is used to determine the optimal parameters of the multiple regression. The overall data were organized into a training set (8 patients) and a testing set (another 8 patient) which are randomly selected. The clinical results show that the proposed algorithm can achieve predictions with good sensitivities and acceptable specificities.

In affective product design, one of the main goals is to maximize customers' affective satisfaction by optimizing design variables of a new product. To achieve this, a model in relating customers' affective responses and design variables of a new product is required to be developed based on customers' survey data. However, previous research on modelling the relationship between affective response and design variables cannot address the development of explicit models either involving nonlinearity or fuzziness, which exist in customers' survey data. In this paper, an evolutionary fuzzy regression approach is proposed to generate explicit models to represent this nonlinear and fuzzy relationship between affective responses and design variables. In the approach, genetic programming is used to construct branches of a tree representing structures of a model where the nonlinearity of the model can be addressed. Fuzzy coefficients of the model, which is represented by the tree, are determined based on a fuzzy regression algorithm. As a result, the fuzzy nonlinear regression model can be obtained to relate affective responses and design variables.

To improve cancer diagnosis and drug development, the classification of tumor types based on genomic information is important. As DNA microarray studies produce a large amount of data, expression data are highly redundant and noisy, and most genes are believed to be uninformative with respect to the studied classes. Only a fraction of genes may present distinct profiles for different classes of samples. Classification tools to deal with these issues are thus important. These tools should learn to robustly identify a subset of informative genes embedded in a large dataset that is contaminated with high dimensional noises. In this paper, an integrated approach of support vector machine (SVM) and particle swarm optimization (PSO) is proposed for this purpose. The proposed approach can simultaneously optimize the selection of feature subset and the classifier through a common solution coding mechanism. As an illustration, the proposed approach is applied to search the combinational gene signatures for predicting histologic response to chemotherapy of osteosarcoma patients. Cross-validation results show that the proposed approach outperforms other existing methods in terms of classification accuracy. Further validation using an independent dataset shows misclassification of only one out of fourteen patient samples, suggesting that the selected gene signatures can reflect the chemoresistance in osteosarcoma.

This paper proposes a genetic algorithm (GA) based beamformer to optimize speech recognition accuracy for a pretrained speech recognizer. The proposed beamformer is designed to tackle the non-differentiable and non-linear natures of speech recognition by employing the GA algorithm to search for the optimal beamformer weights. Specifically, a population of beamformer weights is reproduced by crossover and mutation until the optimal beamformer weights are obtained. Results show that the speech recognition accuracies can be greatly improved even in noisy environments.

This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the value of the inertia weight becomes variable. The cross-mutated operation is effectively force the solution to escape the local optimum. Tuning parameters (weights) of neural networks is presented using the FPSOCM. Numerical example of neural network is given to illustrate that the performance of the FPSOCM is good for tuning the parameters (weights) of neural networks.

Classification of tumor types based on genomic information is essential for improving future cancer diagnosis and drug development. Since DNA microarray studies produce a large amount of data, effective analytical methods have to be developed to sort out whether specific cancer samples have distinctive features of gene expression over normal samples or other types of cancer samples. In this paper, an integrated approach of support vector machine (SVM) and genetic algorithm (GA) is proposed for this purpose. The proposed approach can simultaneously optimize the feature subset and the classifier through a common solution coding mechanism. As an illustration, the proposed approach is applied in searching the combinational gene signatures for predicting histologic response to chemotherapy of osteosarcoma patients, which is the most common malignant bone tumor in children. Cross-validation results show that the proposed approach outperforms other existing methods in terms of classification accuracy. Further validation using an independent dataset shows misclassification of only one of fourteen patient samples suggesting that the selected gene signatures can reflect the chemoresistance in osteosarcoma.

An hybrid Particle Swarm Optimization PSO-based wavelet neural network for modelling the development of fluid dispensing for electronic packaging is presented in this paper. In modelling the fluid dispensing process, it is important to understand the process behaviour as well as determine optimum operating conditions of the process for a high-yield, low cost and robust operation. Modelling the fluid dispensing process is a complex non-linear problem. This kind of problem is suitable to be solved by neural network. Among different kinds of neural networks, the wavelet neural network is a good choice to solve the problem. In the proposed wavelet neural network, the translation parameters are variables depending on the network inputs. Thanks to the variable translation parameters, the network becomes an adaptive one. Thus, the proposed network provides better performance and increased learning ability than conventional wavelet neural networks. An improved hybrid PSO [1] is applied to train the parameters of the proposed wavelet neural network. A case study of modelling the fluid dispensing process on electronic packaging is employed to demonstrate the effectiveness of the proposed method.

This paper presents a method on how to estimate main effects of gene representation. This estimate can be used not only to understand the domination of genes in the representation but also to design the mutation rate in genetic algorithms (GAs). A new approach of dynamic mutation rate is proposed by integrating the information of the main effects into the genes. By introducing the proposed method in GAs, both solution quality and solution stability can be improved in solving a set of parametrical test functions. The algorithm was applied to two illustrative applications to evaluate the performance of the proposed method, where the first application is on solving uncapacitated facility location problems and the next is on optimal power flow problems, which are employed. Results indicate that the proposed method yields significantly better results than the existing methods.

Uncertainty in manufacturing processes is caused both by randomness, as in material properties, and by fuzziness, as in the inexact knowledge. Previous research has seldom considered these two types of uncertainty when modeling manufacturing processes. In this paper, a hybrid fuzzy least-squares regression (HFLSR) approach to modeling manufacturing processes, which does take into consideration these two types of uncertainty, is proposed and described, and a new form of weighted fuzzy arithmetic is introduced to develop the hybrid fuzzy least-squares regression method. The proposed HFLSR approach not only features the capability of dealing with the two types of uncertainty, but also addresses the consideration of replication of responses in experiments. To investigate the effectiveness of the proposed approach to process modeling, it was applied to the modeling solder paste dispensing process. Modeling results were compared with those based on statistical regression and fuzzy linear regression. It was found that the accuracy of prediction based on the HFLSR is slightly better than that based on statistical regression and much better than that based on the Peters fuzzy regression.

A new hybrid particle swarm optimization (PSO) that incorporates a wavelet-theory-based mutation operation is proposed. It applies the wavelet theory to enhance the PSO in exploring the solution space more effectively for a better solution. A suite of benchmark test functions and three industrial applications (solving the load flow problems, modeling the development of fluid dispensing for electronic packaging, and designing a neural-network-based controller) are employed to evaluate the performance and the applicability of the proposed method. Experimental results empirically show that the proposed method significantly outperforms the existing methods in terms of convergence speed, solution quality, and solution stability.

In this paper, an improved genetic algorithm has been proposed for solving multi-contingency transient stability constrained optimal power flow (MC-TSCOPF) problems. The MC-TSCOPF problem is formulated as an extended optimal power flow (OPF) with additional generator rotor angle constraints and is converted into an unconstrained optimization problem, which is suitable for genetic algorithms to deal with, using a penalty function. The improved genetic algorithm is proposed by incorporating an orthogonal design in exploring solution spaces. A case study indicates that the improved genetic algorithm outperforms the existing genetic algorithm-based method in terms of robustness of solutions and the convergence speed while the solution quality can be kept.

Determination of the initial process parameters for fluid dispensing process is a highly skilled task and is usually based on skilled engineers’ intuitive sense acquired through long-term experience rather than on a knowledge-based approach. In the face of global competition, the current trial-and -error practice is inadequate. In this paper, a rule-based system is developed to aid the determination of initial process parameters for fluid dispensing process by the genetic algorithm. Based on the rule based system, a set of ranges of process parameters can be recommended with a pre-defined quality requirement of microchip encapsulation. The preliminary validation test of the rule-based system has indicated that it can determine a set of ranges of initial process parameters for fluid dispensing process effectively, from which quality requirement can be achieved without totally relying on engineers’ experience.

An improved hybrid particle swarm optimization (PSO) that incorporates a wavelet-based mutation operation is proposed It applies wavelet theory to enhance PSO in exploring solution spaces more effectively for better solutions. A suite of benchmark test functions and an application example on tuning an associative-memory neural network are employed to evaluate the performance of the proposed method. It is shown empirically that the proposed method outperforms significantly the existing methods in terms of convergence speed, solution quality and solution stability.

In the past, empirical studies have shown that factorial design based crossover can outperform standard crossover on parametrical problems. However, up to now, no conclusion has been reached as to what kind of landscape factorial design based crossover outperforms standard crossover on. In this paper, we have tested the performance of a factorial design based crossover operator embedded in a classical genetic algorithm and investigated whether or not it outperforms the standard crossover operator on a set of benchmark problems. We found that the factorial design based crossover performed significantly better than the standard crossover operator on landscapes that have a single optimum.

This work describes how to estimate the main effect of genes in genetic algorithms (GAs). The resulting estimates can not only be used to understand the domination of genes in a GA but also employed to tailor the mutation rate in the GA. A new approach to varying the mutation rate across the representation and over the run of the GA depending on estimates of the main effect of genes is proposed. We demonstrate the use of the proposed method for solving uncapacitated facility location problems. For many well known benchmark problems, the proposed method yields better results than the previously used method.

Epistasis is a measure of interdependence between genes and an indicator of problem difficulty in genetic algorithms. Many researches have concentrated on the epistasis measure in binary coded representation in genetic algorithms. However, a few attempts for epistasis measure in real-coded representation have been reported in the literature. In this paper, we have demonstrated how to use the approach of analysis of variance (ANOVA) to estimate the epistasis in real-coded representation. The approach is useful to analyse epistasis in genetic algorithms in a more detailed level. Examples have been given for showing how to use ANOVA for measuring the amount of epistasis in parametrical problems, and then we have applied this epistatic information provided by ANOVA to improve the performance of genetic algorithm.

Based on our observation, some major steps in the genetic algorithm, such as the crossover operator, can be considered as experiments. The aim is to apply experimental design techniques to improve the crossover operator, so that the resulting operator can be more robust and statistically sound. Taguchi method is a systematic and time-efficient approach that can aid in experimental design. Here we apply Taguchi method to tailor a new crossover operator so that the operator can estimate the best point in the search space determined by the parents. Experimental result shows that the proposed operator outperforms the classical GA crossover strategy on some parametrical problems.