Search results

The purpose of this study was to examine the influence of participating in an eight‐week physical training (ie. balance or weight training) on psychosocial outcomes for independently living healthy older adults. Eighteen older adults (65 years old or older) voluntarily participated in this study. Participants were randomly and evenly distributed in three different groups such as balance, weight or control group; six participants in each. Fear of falling and social activity levels were statistically tested by evaluating questionnaires validated in previous studies. Psychological factors improved in all groups after eight weeks (P < 0.05). Social interaction levels did not improve in any of the three groups, although all participants exhibited improvements in being physically independent (P < 0.05). Results suggested that being physically active as well as being socially active could result in being less fearful of falls, more confident of leaving residency, being more independent, and being more active.

The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.

The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications” is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.

Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.

The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.

The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.

The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.

As a foundational issue of social mining, sentiment classification suffered from a lack of unlabeled data. To enhance accuracy of classification with few labeled data, many semi-supervised algorithms had been proposed. These algorithms improved the classification performance when the labeled data are insufficient. However, precision and efficiency are difficult to be ensured at the same time in many semi-supervised methods. This paper aims to present a novel method for using unlabeled data in a more accurate and more efficient way.

First, the authors designed a boosting-based method for unlabeled data selection. The improved boosting-based method can choose unlabeled data which have the same distribution with the labeled data. The authors then proposed a novel strategy which can combine weak classifiers into strong classifiers that are more rational. Finally, a semi-supervised sentiment classification algorithm is given.

Experimental results demonstrate that the novel algorithm can achieve really high accuracy with low time consumption. It is helpful for achieving high-performance social network-related applications.

The novel method needs a small labeled data set for semi-supervised learning. Maybe someday the authors can improve it to an unsupervised method.

The mentioned method can be used in text mining, image classification, audio processing and so on, and also in an unstructured data mining-related field. Overcome the problem of insufficient labeled data and achieve high precision using fewer computational time.

Sentiment mining has wide applications in public opinion management, public security, market analysis, social network and related fields. Sentiment classification is the basis of sentiment mining.

According to what the authors have been informed, it is the first time transfer learning be introduced to AdaBoost for semi-supervised learning. Moreover, the improved AdaBoost uses a totally new mechanism for weighting.

No methodology has been directly proposed to address the parameter optimization problem with weight effect on the categorical response. The aim of this paper is to propose a suitable procedure to address such a problem.

The computation of aggregation weight and neural network modeling technique were employed into forming the core architecture of the proposed approach. The consistency and difference of the weight effect between several experts or professionals can be included into the weight computation. The backpropagation neural network model is chosen to model the non‐linear relationship among the control factors, the probability, and the accumulated probability of categories for a qualitative response.

Weight effect for different categories of a qualitative response significantly exists in L/F manufacturing process. Including such weight effect into the L/F manufacturing analysis can achieve the parameter optimization and enhance their quality improvement.

This paper can be viewed as the first to address the parameter optimization problem for the categorical response with the weight effect consideration. The proposed approach can aid engineers making necessary decisions about quality improvement.

The Police Training Institute at the University of Illinois designed a fitness training programme which allowed the participants to choose the intensity and mode of their exercise. Between June 1993 and March 1995, the incoming recruits’ fitness level was assessed before and after the training programme in order to measure the improvement induced by the training and to compare the recruits’ fitness level to the general population. The recruits significantly improved their flexibility (19.10 vs 15.13 degrees) and abdominal strength (4.91 vs 4.98 Lovett score). The male recruits improved their aerobic capacity (recovery heart rate: 86.27 vs 81.32 bpm) and the female recruits improved their back strength (4.86 vs 4.97 Lovett score). No significant changes were observed for grip strength (54.62 vs 54.21 kg), relative body fat (19.5 vs 18.5 per cent body fat), blood pressure (diastolic: 77.99 vs 77.52 mm Hg; systolic: 125.47 vs 125.10 mm Hg), and resting heart rate (74.89 vs 74.23 bpm). Compared to population norms, the majority of the recruits were within the normal range for blood pressure, resting heart rate, abdominal and back muscle strength. A large proportion of the recruits had good flexibility, average grip strength, and fair to excellent per cent body fat. Still, 33.4 per cent of the males and 25 per cent of the females were low to very low in aerobic capacity. As a result, the fitness programme has been modified in order to further improve recruits’ fitness.

Increasing availability of the financial data has opened new opportunities for quantitative modeling. It has also exposed limitations of the existing frameworks, such as low accuracy of the simplified analytical models and insufficient interpretability and stability of the adaptive data-driven algorithms. I make the case that boosting (a novel, ensemble learning technique) can serve as a simple and robust framework for combining the best features of the analytical and data-driven models. Boosting-based frameworks for typical financial and econometric applications are outlined. The implementation of a standard boosting procedure is illustrated in the context of the problem of symbolic volatility forecasting for IBM stock time series. It is shown that the boosted collection of the generalized autoregressive conditional heteroskedastic (GARCH)-type models is systematically more accurate than both the best single model in the collection and the widely used GARCH(1,1) model.

This paper aims to identify and prioritize the dimensions that impact employee social sustainability in the airline industry in the United Arab Emirates (UAE).

The five main criteria (employee well-being, communication, management support, reward and control system and training) and 18 sub-criteria were identified from the literature. The sample comprised four experts covering the HR, finance and training functions from a major UAE airline organization. Applying the analytical-hierarchy-process (AHP) methodology resulted in obtaining priority weights for the factors assigned to employee-social-sustainability implementation.

Management support was found to have the highest priority among the study dimensions impacting employee social sustainability. Surprisingly, reward system was found to be the least important dimension.

The study was carried out on a single airline organization, limiting the generalizability of the findings. Future studies should be extended to cater to different organizational contexts and varying operational conditions.

The findings should be of value to human resource management and policymakers in developing countries, such as the UAE, where employee social sustainability should be sought as a means to develop an efficient and sustainable workforce in different industrial sectors.

This study is among the few pioneering studies that focus on employee social sustainability. The use of AHP to prioritize employee-social-sustainability dimensions is also considered pioneering within the field and is anticipated to support future studies, and a deeper understanding, of employee social sustainability.

Government employees have various challenges of adopting e-government which include administrative problems, technological challenges, infrastructural problems, lack of trust on computer applications, security concerns and the digital divide. The purpose of this paper is to identify the most salient factors that influence the employee adoption of e-government in India as perceived by government employees involved in e-government service delivery.

The paper first identifies different factors influencing the employee adoption of e-government on the basis of literature review and then finds their relative importance by prioritizing them using the analytic hierarchy process (AHP). The AHP is a multi-criteria decision-making (MCDM) tool which combines all the factors into a hierarchical model and quantitatively measures their importance through pair-wise comparisons (Saaty, 1980). Eleven influencing factors of employee adoption of e-government have been identified, which are categorized under four main factors, namely, “employee’s personal characteristics”, “technical factors”, “organizational factors” and “trust”. The data pertaining to pair-wise comparisons of various factors and sub-factors related to the study is collected from ten senior government employees working with different departments and bodies of the Government of National Capital Territory of Delhi.

Based on the results obtained, the findings reveal that “organizational factors” and “technical factors” are the two most important factors which influence the intention of government employees to adopt e-government. Moreover, “training”, “technical infrastructure”, “access speed”, “technical support” and “trust” in infrastructure are the top five sub-factors which are considered to be important for the employee adoption of e-government.

One of the limitations regarding the methodology used in the study is that the rating scale used in the AHP is conceptual. There are chances of biasing while making pair-wise comparisons of different factors. Therefore, due care should be taken while deciding relative scores to different factors. Also, some factors and sub-factors selected, for the model may have interrelationships such as educational level and training; computer skills and trust; etc., and these interrelationships are not considered by the AHP, which is a limitation of the present study. In that case, the analytic network process (ANP) can be a better option. Therefore, this study can be further extended by considering some other factors responsible for e-government adoption by employees and applying the ANP in the revised model.

The results of the study may help government organizations, to evaluate critical factors of employee adoption of e-government. This may help them in achieving cost-effective implementation of e-government applications by efficiently managing their resources. Briefly, the findings of the study imply that government departments should provide sufficient training and support to their employees for enhancing their technical skills so that they can use the e-government applications comfortably. Moreover, the government departments should also ensure fast access speed of the e-government applications so that the employees can carry out their tasks efficiently.

Most of the existing literature on e-government is focused on citizens’ point of view, and very few studies have focused on employee adoption of e-government (Alshibly and Chiong, 2015). Moreover, these studies have majorly used generic technology adoption models which are generally applicable to situations where technology adoption is voluntary. As employee adoption of e-government is not voluntary, the present study proposes a hierarchy of influencing factors and sub-factors of employee adoption of e-government, which is more relevant to the situations where technology adoption is mandatory. Also, most of the previous studies have used statistical methods such as multiple regression analysis or structural equation modelling for examining the significant factors influencing the e-government adoption. The present study contributes to this area by formulating the problem as an MCDM problem and by using the AHP as the methodology to determine the weights of various factors influencing adoption of e-government by employees.

To realize classification of different pavements, a road roughness acquisition system design and an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation algorithm for road roughness detection is presented in this paper. The developed measurement system, including hardware designs and algorithm for software, constitutes an independent system which is low-cost, convenient for installation and small.

The inputs of restricted Boltzmann machine deep neural network are the vehicle vertical acceleration power spectrum and the pitch acceleration power spectrum, which is calculated using ADAMS finite element software. Adaboost Backward Propagation algorithm is used in each restricted Boltzmann machine deep neural network classification model for fine-tuning given its performance of global searching. The algorithm is first applied to road spectrum detection and experiments indicate that the algorithm is suitable for detecting pavement roughness.

The detection rate of RBM deep neural network algorithm based on Adaboost Backward Propagation is up to 96 per cent, and the false positive rate is below 3.34 per cent. These indices are both better than the other supervised algorithms, which also performs better in extracting the intrinsic characteristics of data, and therefore improves the classification accuracy and classification quality. Additionally, the classification performance is optimized. The experimental results show that the algorithm can improve performance of restricted Boltzmann machine deep neural networks. The system can be used for detecting pavement roughness.

This paper presents an improved restricted Boltzmann machine deep neural network algorithm based on Adaboost Backward Propagation for identifying the road roughness. Through the restricted Boltzmann machine, it completes pre-training and initializing sample weights. The entire neural network is fine-tuned through the Adaboost Backward Propagation algorithm, verifying the validity of the algorithm on the MNIST data set. A quarter vehicle model is used as the foundation, and the vertical acceleration spectrum of the vehicle center of mass and pitch acceleration spectrum were obtained by simulation in ADAMS as the input samples. The experimental results show that the improved algorithm has better optimization ability, improves the detection rate and can detect the road roughness more effectively.