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.

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.

An improved hybrid particle swarm optimization (PSO)-based wavelet neural network (WNN) for modeling the development of fluid dispensing for electronic packaging (MFD-EP) is presented in this paper. In modeling the fluid dispensing process, it is important to understand the process behavior as well as determine the optimum operating conditions of the process for a high-yield, low-cost, and robust operation. Modeling the fluid dispensing process is a complex nonlinear problem. This kind of problem is suitable to be solved by applying a neural network. Among the different kinds of neural networks, the WNN is a good choice to solve the problem. In the proposed WNN, the translation parameters are variables depending on the network inputs. Due to the variable translation parameters, the network becomes an adaptive one that provides better performance and increased learning ability than conventional WNNs. An improved hybrid PSO is applied to train the parameters of the proposed WNN. The proposed hybrid PSO incorporates a wavelet-theory-based mutation operation. It applies the wavelet theory to enhance the PSO in more effectively exploring the solution space to reach a better solution. A case study of MFD-EP is employed to demonstrate the effectiveness of the proposed method.

Purpose: This paper aims to obtain the domain of the textual content generated by users of online social network (OSN) platforms. Understanding a users’ domain (s) of interest is a significant step towards addressing their domain-based trustworthiness through an accurate understanding of their content in their OSNs. Design/methodology/approach: This study uses a Twitter mining approach for domain-based classification of users and their textual content. The proposed approach incorporates machine learning modules. The approach comprises two analysis phases: the time-aware semantic analysis of users’ historical content incorporating five commonly used machine learning classifiers. This framework classifies users into two main categories: politics-related and non-politics-related categories. In the second stage, the likelihood predictions obtained in the first phase will be used to predict the domain of future users’ tweets. Findings: Experiments have been conducted to validate the mechanism proposed in the study framework, further supported by the excellent performance of the harnessed evaluation metrics. The experiments conducted verify the applicability of the framework to an effective domain-based classification for Twitter users and their content, as evident in the outstanding results of several performance evaluation metrics. Research limitations/implications: This study is limited to an on/off domain classification for content of OSNs. Hence, we have selected a politics domain because of Twitter’s popularity as an opulent source of political deliberations. Such data abundance facilitates data aggregation and improves the results of the data analysis. Furthermore, the currently implemented machine learning approaches assume that uncertainty and incompleteness do not affect the accuracy of the Twitter classification. In fact, data uncertainty and incompleteness may exist. In the future, the authors will formulate the data uncertainty and incompleteness into fuzzy numbers which can be used to address imprecise, uncertain and vague data. Practical implications: This study proposes a practical framework comprising significant implications for a variety of business-related applications, such as the voice of customer/voice of market, recommendation systems, the discovery of domain-based influencers and opinion mining through tracking and simulation. In particular, the factual grasp of the domains of interest extracted at the user level or post level enhances the customer-to-business engagement. This contributes to an accurate analysis of customer reviews and opinions to improve brand loyalty, customer service, etc. Originality/value: This paper fills a gap in the existing literature by presenting a consolidated framework for Twitter mining that aims to uncover the deficiency of the current state-of-the-art approaches to topic distillation and domain discovery. The overall approach is promising in the fortification of Twitter mining towards a better understanding of users’ domains of interest.

On-road sensor systems installed on freeways are used to capture traffic flow data for short-term traffic flow predictors for traffic management, to reduce traffic congestion and improve vehicular mobility. This paper intends to tackle the impractical time-invariant assumptions which underlie the methods currently used to develop short-term traffic flow predictors: 1) the characteristics of current data captured by on-road sensors are assumed to be time invariant with respect to those of the historical data, which is used to developed short-term traffic flow predictors; and 2) the configuration of the on-road sensor systems is assumed to be time-invariant. In fact, both assumptions are impractical in the real world, as the current traffic flow characteristics can be very different from the historical ones, and also the on-road sensor systems are time varying in nature due to damaged sensors or component wear. Therefore, misleading forecasting results are likely to be produced when short-term traffic flow predictors are designed using these two time-invariant assumptions. To tackle these time-invariant assumptions, an intelligent particle swarm optimization (IPSO) algorithm is proposed to develop short-term traffic flow predictors by integrating the mechanisms of PSO, neural network and fuzzy inference system, to adapt to the time-varying traffic flow characteristics and the time-varying configurations of the on-road sensor systems. The proposed IPSO was applied to forecast traffic flow conditions on a section of freeway in Western Australia, whose traffic flow information can be captured on-line by the on-road sensor system. These results clearly demonstrate the effectiveness of using the proposed IPSO for real-time traffic flow forecasting based on traffic flow data captured by on-road sensor systems.