Search

In the medical field, researchers are often unable to obtain the sufficient samples in a short period of time necessary to build a stable data-driven forecasting model used to classify a new disease. To address the problem of small data learning, many studies have demonstrated that generating virtual samples intended to augment the amount of training data is an effective approach, as it helps to improve forecasting models with small datasets. One of the most popular methods used in these studies is the mega-trend-diffusion (MTD) technique, which is widely used in various fields. The effectiveness of the MTD technique depends on the degree of data diffusion. However, data diffusion is seriously affected by extreme values. In addition, the MTD method only considers data fitted using a unimodal triangular membership function. However, in fact, data may come from multiple distributions in the real world. Therefore, considering the fact that data comes from multi-distributions, in this paper, a distance-based mega-trend-diffusion (DB-MTD) technique is proposed to appropriately estimate the degree of data diffusion with less impacts from extreme values. In the proposed method, it is assumed that the data is fitted by the triangular and trapezoidal membership functions to generate virtual samples. In addition, a possibility evaluation mechanism is proposed to measure the applicability of the virtual samples. In our experiment, two bladder cancer datasets are used to verify the effectiveness of the proposed DB-MTD method. The experimental results demonstrated that the proposed method outperforms other VSG techniques in classification and regression items for small bladder cancer datasets.

Significance: Few studies have analyzed how loneliness-related factors differ across generations for older adults in non-Western societies. Building upon the stress process model, this study aimed to explore the relationships between work-family conflict before retirement, social engagement after retirement and changes in loneliness after retirement among retirees across two birth cohorts (Baby Boomers and pre-Boomers) in Taiwan. Methods: Data from the Taiwan Health and Retirement Study, a nationwide retired cohort sample collected from two waves between 2015/2016 and 2018/2019, was analyzed. A total of 2370 retirees aged 50–74 years were included in the analysis after excluding those who died or were lost to follow-up. Multivariate multinomial logistic models were used to estimate four types of changes in loneliness: (1) remaining not lonely, (2) becoming not lonely, (3) becoming lonely, and (4) remaining lonely. Results: About two-thirds of the retirees remained not lonely, and less than 10% maintained their feelings of loneliness across two waves. Multinomial logit models showed that both cohorts who experienced work-family conflict before retirement and stressful life events after retirement had higher odds of remaining lonely than those who remained not lonely. However, an increase in social engagement, especially social contact, appeared to be a protective factor against becoming and remaining lonely for both cohorts. Yet, work-related characteristics before retirement were significantly related to the changes in loneliness among pre-Boomers rather than Baby Boomers. Conclusions: The results suggest that work-family conflict before retirement produces an exacerbating effect; in contrast, social engagement after retirement is beneficial to not feeling lonely across two birth cohorts in Taiwan. This investigation highlights the importance of social stressors occurring before retirement because these have an effect on retirees’ feelings of loneliness beyond individual socioeconomic status.

The cost of investing in new product development (NPD) is high, and it is a feasible way to use demand forecasts for customer or end-users as a decisive reference. However, this short-term time-series data has difficulties in learning because there is no past performance on which to base the estimates. In the past, it has been proven that the cumulative method of the fractional grey prediction model (FGM) is better than the traditional integer cumulative method of the grey model (GM) model. There are many studies using different optimal algorithms to determine the moderate score order. How to set the coefficient of α in FGM is also worth exploring. Therefore, this research reveals a new fractional grey prediction model which uses box-and-whisker plots to estimate the trends of data, known as the boxplot-based fractional scale prediction model (boxplot-based FGM, BP-FGM) to improve the accuracy of predictors by setting the coefficient sets of α. In the experiment, the examined dataset was collected from a well-known equipment manufacturer as the research object. For modeling, the mean absolute percentage error (MAPE) was established as the objective function of the optimization model, the results from three datasets verified the effect through the commodity attributes and public test data of its production, and the experimental results show that BP-FGM has better prediction results than FGM.

The problem of imbalanced data has a heavy impact on the performance of learning models. In the case of an imbalanced text dataset, minority class data are often classified to the majority class, resulting in a loss of minority information and low accuracy. Thus, it is a serious challenge to determine how to tackle the high imbalance ratio distribution of datasets. Here, we propose a novel classification method for learning tasks with imbalanced test data. It aims to construct a method for data preprocessing that researchers can apply to their learning tasks with imbalanced text data and save the efforts to search for more dedicated learning tools. In our proposed method, there are two core stages. In stage one, balanced datasets are generated using an asymmetric cost-sensitive support vector machine; in stage two, the balanced dataset is classified using the symmetric cost-sensitive support vector machine. In addition, the learning parameters in both stages are adjusted with a genetic algorithm to create an optimal model. A Yelp review dataset was used to validate the effectiveness of the proposed method. The experimental results showed that the proposed method led to a better performance subject to the targeted dataset, with at least 75% accuracy, and revealed that this new method significantly improved the learning approach.

Oversampling is the most popular data preprocessing technique. It makes traditional classifiers available for learning from imbalanced data. Through an overall review of oversampling techniques (oversamplers), we find that some of them can be regarded as danger-information-based oversamplers (DIBOs) that create samples near danger areas to make it possible for these positive examples to be correctly classified, and others are safe-information-based oversamplers (SIBOs) that create samples near safe areas to increase the correct rate of predicted positive values. However, DIBOs cause misclassification of too many negative examples in the overlapped areas, and SIBOs cause incorrect classification of too many borderline positive examples. Based on their advantages and disadvantages, a boundary-information-based oversampler (BIBO) is proposed. First, a concept of boundary information that considers safe information and dangerous information at the same time is proposed that makes created samples near decision boundaries. The experimental results show that DIBOs and BIBO perform better than SIBOs on the basic metrics of recall and negative class precision; SIBOs and BIBO perform better than DIBOs on the basic metrics for specificity and positive class precision, and BIBO is better than both of DIBOs and SIBOs in terms of integrated metrics.

In recent years, generative adversarial networks (GANs) have been proposed to generate simulated images, and some works of literature have applied GAN to the analysis of numerical data in many fields, such as the prediction of building energy consumption and the prediction and identification of liver cancer stages. However, these studies are based on sufficient data volume. In the current era of globalization, the demand for rapid decision-making is increasing, but the data available in a short period of time is scarce. As a result, machine learning may not provide precise results. Obtaining more information from a small number of samples has become an important issue. Therefore, this study aimed to modify the generative adversarial network structure for learning with small numerical datasets, starting with the Wasserstein GAN (WGAN) as the GAN architecture, and using mega-trend-diffusion (MTD) to limit the bound of virtual samples that the GAN generates. The model verification of our proposed structure was conducted with two datasets in the UC Irvine Machine Learning Repository, and the performance was evaluated using three criteria: accuracy, standard deviation, and p-value. The experiment result shows that, using this improved GAN architecture (WGAN_MTD), small sample data can also be used to generate virtual samples that are similar to real samples through GAN.

It is difficult for learning models to achieve high classification performances with imbalanced data sets, because with imbalanced data sets, when one of the classes is much larger than the others, most machine learning and data mining classifiers are overly influenced by the larger classes and ignore the smaller ones. As a result, the classification algorithms often have poor learning performances due to slow convergence in the smaller classes. To balance such data sets, this paper presents a strategy that involves reducing the sizes of the majority data and generating synthetic samples for the minority data. In the reducing operation, we use the box-and-whisker plot approach to exclude outliers and the Mega-Trend-Diffusion method to find representative data from the majority data. To generate the synthetic samples, we propose a counterintuitive hypothesis to find the distributed shape of the minority data, and then produce samples according to this distribution. Four real datasets were used to examine the performance of the proposed approach. We used paired t-tests to compare the Accuracy, G-mean, and F-measure scores of the proposed data pre-processing (PPDP) method merging in the D3C method (PPDP+D3C) with those of the one-sided selection (OSS), the well-known SMOTEBoost (SB) study, and the normal distribution-based oversampling (NDO) approach, and the proposed data pre-processing (PPDP) method. The results indicate that the classification performance of the proposed approach is better than that of above-mentioned methods.

In the field of small-sample domains, since its introduction, the effectiveness and practicality of the megatrend diffusion (MTD) method have been demonstrated in various studies. Recently, with the popularity of generative deep learning, researchers have integrated Wasserstein generative adversarial networks (WGANs) with the MTD method and proposed a novel framework called WGAN-MTD for virtual data generation. It uses the MTD for producing estimates, which restricts the generative model's output value range and generates effective synthetic samples. However, the validity of developing virtual samples using real-world data containing outliers remains controversial, and the weight clipping method in WGAN has been shown to affect the stability of model training. In this study, we propose an advanced framework in which the boxplot is integrated with a penalization term to limit the effect of outliers, especially from small samples. The proposed framework considers the convolutional layers to capture local information features and lower the complexity of the model by reducing the number of parameters between the input and output layers. Additionally, we adopt a WGAN with the gradient penalty (GP) method instead of WGAN alone to improve the training stability and precision in the generative model. Experimental results demonstrate that both the boxplot and the penalization term enhance the accuracy of the generative models for small datasets containing outliers. [ABSTRACT FROM AUTHOR]

Accurate short-term demand forecasting is crucial for the production plan development, but a shorter forecasting period implies that the product demands are more unstable and, thus, that ascertaining their developing trends is difficult. Therefore, using large historical observations to build forecasting models may not result in favorable forecasting performance. Prediction methods based on the latest limited data have thus become vital for maintaining management efficiency and competitive advantage. Grey system theory is a technique for resolving this dijficulty. However, the conventional grey model is designed for time-series data featuring equigaps, which limits its application scope. Although in the current published research, scholars have proposed some non-equigap grey models; however, the newest datum is usually weakened to alleviate the randomness of data in these models, which may result in a larger prediction error. To conquer these shortcomings, this study introduces linear extrapolation to modeling procedures for emphasizing the importance of the newest datum and then proposes an improved non-equigap grey model. In the experiments of two real cases, the proposed method exhibits favorable forecasting performance, indicating a feasible solution for small non-equigap data forecasting. [ABSTRACT FROM AUTHOR]

Accelerating new product development has become an important marketing strategy for manufacturers who are competing globally. However, this may lead to the small data learning issue. Although machine learning algorithms are used to extract knowledge from training samples, algorithms may not output satisfactory predictions when training sizes are small. This paper provides a real case of a TFT-LCD (thin film transistor liquid crystal display) maker when a new strengthened cover glass is developed using chemical processes. With very little prior experience about the processes involved, engineers attempted to improve the yield rates by determining the parameters from a few pilot-run data. However, owing to the fact that the processes were different from those required to make TFT-LCD panels, the highly uncertain characteristics of the processes led to the use of two virtual sample generation (VSG) approaches, bootstrap aggregating (bagging) and the synthetic minority over-sampling technique, from which unsatisfactory results were obtained. Accordingly, this study was used to develop a systematic VSG method based on fuzzy theory to tackle the learning issue. The experimental results show that support vector regressions built with training sets containing the proposed samples present more precise predictions and thus can help engineers infer more correct manufacturing parameters. [ABSTRACT FROM AUTHOR]

The TFT-LCD (thin-film transistor liquid crystal display) industry in Taiwan has been developed for decades. To provide better service for customers, most Taiwan companies in the supply chain have set up their warehouse in mainland China for vendor managed inventory (VMI). However, over the last decade, owing to the industry issues of product diversity strategies and short product lifecycles, it has become difficult for suppliers to control well the stock level in VMI, especially the operation of defective product returns. In order to keep high customer satisfaction, it is considered an option by forecasting possible future defectives for preparing the returning products to satisfy customers. The non-equigap grey model (NGM) used to be applied to such short-term time series data and has shown to be an effective tool. However, NGM predictions still can be improved by making more appropriate background values by determining their parameter a values. Accordingly, this paper employs the mega-trend-diffusion (MTD) technique to estimate better a values, and the model is thus called MTD-NGM(1,1). In the experiments, two data sets taken from a supplier are examined for effectiveness validation. The experimental results indicate that MTD-NGM(1,1) can generally produce better predictions than NGM(1,1). [ABSTRACT FROM AUTHOR]

Over the past two decades, the grey model (GM) and its extensions have shown to be an effective tool to deal with short-term time series (STTS) data. To further improve the accuracy of GM models, this paper proposes a novel GM modelling procedure based on a fuzzy-set concept. In the procedure, STTS data is fuzzified by measuring the forces between existing data and a newly coming datum to form fuzzy time series for building GM models, and final predictions are defuzzified by aggregating the predictions of the GM models with the proposed weights. The experimental results of a real case indicate that the proposed procedure can further improve the accuracy of GM models in general. [ABSTRACT FROM AUTHOR]

When developing a production plan, accurate forecasting short-term demand is challenging for managers because a short forecast period indicates that the change in product demand exhibits an unsteady trend. Therefore, forecast models generated using a large amount of historical observations do not fully explain the data collected on developing patterns and, consequently, do not robustly forecast outcomes. However, if a low number of samples featuring the most recent information is used for developing a forecast, management efficiency could be enhanced and enterprises could gain a competitive advantage. To solve the problems associated with forecasting short-term demand when small datasets are available, we developed a residual discrete grey model that is based on modeling residual analysis. Specifically, we first applied the discrete grey model to create a forecasting model, and then used the obtained fitting residuals to generate training samples using the Latent Information function to learn the topology of a backpropagation neural network. Finally, the predictive errors obtained using the constructed network for adjusting the forecast to enhance the forecasting performance. We conducted an experiment using the demand data obtained from a thin film transistor liquid crystal display panel, and the results indicated that a highly accurate forecast could be obtained using the proposed modeling procedure. This finding suggests that the model developed in this study is a tool that enables short-term demand to be forecast accurately using small datasets. [ABSTRACT FROM AUTHOR]

While back-propagation neural networks (BPNN) are effective learning tools for building non-linear models, they are often unstable when using small-data-sets. Therefore, in order to solve this problem, we construct artificial samples, called virtual samples, to improve the learning robustness. This research develops a novel method of virtual sample generation (VSG), named genetic algorithm-based virtual sample generation (GABVSG), which considers the integrated effects and constraints of data attributes. We first determine the acceptable range by using mega-trend diffusion (MTD) functions, and construct the feasibility-based programming (FBP) model with BPNN. A genetic algorithm (GA) is then applied to accelerate the generation of the most-feasible virtual samples. Finally, we use two real cases to verify the performance of the proposed method by comparing the results with two well-known forecasting models, BPNN, support vector machine for regression (SVR) and one newly published approach MTD method [1]. The experimental results indicate that the performance of the GABVSG method is superior to that of using original training data without artificial samples. Consequently, the proposed method can improve learning performance significantly when working with small samples. [ABSTRACT FROM AUTHOR]

Electronics product life cycles are becoming shorter and shorter because of the severe global competition. In such highly competitive industry, it has become an important strategy to accelerate new products launching to the market to earn more shares. However, the lead times of pilot runs are usually long in new product development (NPD) processes, and reducing pilot runs has thus become one of the key tasks of manufacturing systems. Specifically, since the shorter a test period is the smaller sample size one can obtain, making that to find a small data learning method for a manufacturing system being a new challenge. Facing the problem, this work, based on the box plots and the fuzzy techniques, develops an approach to systematically generate synthetic samples to help stabilize the learning process for the used back-propagation neural network (BPN). A real learning task taken from the Array process of a TFT-LCD manufacturer (a new high-resolution product of 4K2K in 2013) is employed as an example to illustrate the details of the proposed method. The task contains nine inputs and 72 output manufacturing attributes, but only with 20 samples. It is quite difficult for most existing modeling algorithms to deal with such a high dimensional situation when the sample size is small. The experiment results show that the proposed approach can effectively improve the robustness and preciseness of a BPN forecasting model. In addition to the reduction of pilot runs, more process knowledge is obtained in the input-output analysis. [ABSTRACT FROM AUTHOR]

The way to gain knowledge and experience of producing a product in a firm can be seen as new solution for reducing the unit cost in scheduling problems, which is known as "learning effects." In the scheduling of batch processing machines, it is sometimes advantageous to form a nonfull batch, while in other situations it is a better strategy to wait for future job arrivals in order to increase the fullness of the batch. However, research with learning effect and release times is relatively unexplored. Motivated by this observation, we consider a single-machine problem with learning effect and release times where the objective is to minimize the total completion times. We develop a branch-and-bound algorithm and a genetic algorithm-based heuristic for this problem. The performances of the proposed algorithms are evaluated and compared via computational experiments, which showed that our approach has superior ability in this scenario. [ABSTRACT FROM AUTHOR]

Product lifecycles are becoming shorter and shorter because of the global competition. In such highly competitive condition, the importance for enterprises to build forecasting models with short-term time series data significantly arises in recent decade. Unfortunately, since the information the short-term data provides is limited, it is a great challenge to learn its pattern behavior. To overcome the issue, the Grey Model (GM) reveals a clear direction by accumulating data values to make them represent as a monotonically increasing sequence. Accordingly, improving the forecasting accuracy of GM has remarkable developments in theories in decades. Among them, the Adaptive Grey Model (AGM) tries to find the suitable background values by means of taking the data occurring trend into consideration. In fact, setting the suitable background values of GM can be regarded as a process of searching the optimal solutions. This paper thus employs the genetic algorithm (GA) to facilitate the improvement of searching process, where the initial solutions are obtained from AGM, to build a more accurate model named as GAAGM(1,1). The experiment results show that GAAGM outperforms AGM and some other improved GM models in prediction accuracy; and furthermore, this demonstrates that searching for more suitable coefficient sets can indeed help enhance the theory structure of GM models. [ABSTRACT FROM AUTHOR]

The learning effect has gained much attention in the scheduling research recently, where many researchers have focused their problems on only one optimization. This study further addresses the scheduling problem in which two agents compete to perform their own jobs with release times on a common single machine with learning effect. The aim is to minimize the total weighted completion time of the first agent, subject to an upper bound on the maximum lateness of the second agent. We propose a branchand- bound approach with several useful dominance properties and an effective lower bound for searching the optimal solution and three simulated-annealing algorithms for the near-optimal solutions. The computational results show that the proposed algorithms perform effectively and efficiently. [ABSTRACT FROM AUTHOR]

The wafer-level packaging process is an important technology used in semiconductor manufacturing, and how to effectively control this manufacturing system is thus an important issue for packaging firms. One way to aid in this process is to use a forecasting tool. However, the number of observations collected in the early stages of this process is usually too few to use with traditional forecasting techniques, and thus inaccurate results are obtained. One potential solution to this problem is the use of grey system theory, with its feature of small dataset modeling. This study thus uses the AGM(1,1) grey model to solve the problem of forecasting in the pilot run stage of the packaging process. The experimental results show that the grey approach is an appropriate and effective forecasting tool for use with small datasets and that it can be applied to improve the wafer-level packaging process. [ABSTRACT FROM AUTHOR]

From computational learning theory, sample size in machine learning problems indeed affects the learning performance. Since only few samples can be obtained in the early stages of a system and fewer exemplars usually lead to a low learning accuracy, this research compares different machine learning methods through their classification accuracies to improve small-data-set learning. Techniques used in this paper include the mega-trend diffusion technique, a backpropagation neural network, a support vector machine, and decision trees to explore the machine learning issue with two real medical data sets concerning cancer. The result of the experiment shows that the mega-trend diffusion technique and backpropagation approaches are effective methods of small-data-set learning. [ABSTRACT FROM AUTHOR]

This study presents a new method [In–Out Combined Dynamic Weighted Round-Robin (CDWRR)] for balancing network loads in multiple link environments that provide both input and output interfaces. The purpose of this research is to balance loads for reducing Internet traffic jams. Using the novel line detection prediction approach, the main benefit of the presented algorithm is that it does not need to trace the system load every instant but achieves a far better load balancing than the traditional Round-Robin does. In addition, CDWRR keeps multiple links balanced in both input and output links. Mathematical equations are developed for predicting the best time instant of detecting, and both theoretical and practical approaches are provided for performance comparisons. Results obtained from the simulations show that CDWRR is effective and is efficient in maintaining load balance for multiple input and output network structures. [ABSTRACT FROM AUTHOR]