Search

To achieve successful prevention of fire incidents originating from human activities, it is imperative to possess a thorough understanding. This paper introduces a machine learning approach, specifically utilizing deep neural networks (DNN), to develop predictive models for fire occurrence in Keelung City, Taiwan. It investigates ten factors across demographic, architectural, and economic domains through spatial analysis and thematic maps generated from geographic information system data. These factors are then integrated as inputs for the DNN model. Through 50 iterations, performance indices including the coefficient of determination (R2), root mean square error (RMSE), variance accounted for (VAF), prediction interval (PI), mean absolute error (MAE), weighted index (WI), weighted mean absolute percentage error (WMAPE), Nash–Sutcliffe efficiency (NS), and the ratio of performance to deviation (RPD) are computed, with average values of 0.89, 7.30 × 10−2, 89.21, 1.63, 4.90 × 10−2, 0.97, 2.92 × 10−1, 0.88, and 4.84, respectively. The model's predictions, compared with historical data, demonstrate its efficacy. Additionally, this study explores the impact of various urban renewal strategies using the DNN model, highlighting the significant influence of economic factors on fire incidence. This underscores the importance of economic factors in mitigating fire incidents and emphasizes their consideration in urban renewal planning. [ABSTRACT FROM AUTHOR]

Machine learning approaches are increasingly being employed to forecast the key characteristics of strong ground motions, including the challenging classification of Pulse-Like (PL) ground motions. The PL ground motions are characterized by their impulsive nature and have the potential to cause significant damage to structures. The classification of PL ground motions continues to be a significant challenge due to the absence of consensus on their definition and categorization. This paper investigates the potential benefits of several Machine Learning Classifiers (MLCs) algorithms such as decision tree, random forest, logistic regression, naive Bayes, support vector machine, K-nearest neighbor, ensemble model, and artificial neural network models for predicting PL and Non-Pulse-Like (NPL) ground motions. In this regard, a dataset comprising 200 near-fault ground motions records compiled from active tectonic regions like Taiwan, Turkey, Iran, and Japan, was divided into 2 portions, with 75% used to train the model and the remaining 25% used for testing. Plots of performance metrics, confusion matrix, and receiver operating curve indicate that the ensemble classifier outperforms the other classifier with 86.2% accuracy and the lowest misclassification of PL and NPL ground motions. Additionally, the trained MLC has been compared with the existing ground motion classification models to further assess the accuracy of the different classifiers in the present study. [ABSTRACT FROM AUTHOR]

With the rise of cultural and creative industries, cultural creativity has gradually become an important factor to promote the value of design in the future, and it is also a trend to integrate "cultural elements" into the design of products. At present, the cultural and creative industries in Western countries and Taiwan are the mainstay of their economic development. We should actively absorb their successful experiences and, with the support of national policies, carry out effective and lasting development of them, as well as continuously improve the quality of cultural and creative products. In today's steady economic development, the emotionalization of cultural and creative consumption has gradually formed a new consumption trend. When cultural and creative consumers buy stationery, they will inevitably have three situations: purchasing instinct, purchasing behavior, and reflection. Therefore, this paper adopts the method based on machine learning to conduct in-depth research on the users of cultural and creative products of "Forbidden Day and Night Set Gift Box." Through the research on the cultural and creative consumption intention of "Forbidden Day and Night Set Gift Box," it can effectively promote the development of domestic cultural and creative enterprises, and then promote the customer satisfaction of cultural and creative enterprises. This paper makes a detailed analysis of it from the perspectives of data processing, feature engineering, classification prediction models, and future development directions. By studying the cultural and creative behavior of users, a deep learning model based on neural network is established. The feature extraction, feature preprocessing, feature selection, and asymmetric data collection in the process of data processing are discussed in depth. In order to further improve the prediction accuracy and conduct more in-depth research, this paper establishes a deep learning prediction model based on depth. This model is experimentally validated and it can be observed that the model is 10% more efficient than the traditional model, so the model can learn data better from the user's behavior in several aspects, and the proposed and practice of this model has good practical significance. [ABSTRACT FROM AUTHOR]

Purpose: Taiwan experiences frequent seismic activity. Major earthquakes in recent history have seriously damaged the school buildings. School buildings in Taiwan are intended to serve both as places of education and as temporary shelters in the aftermath of major earthquakes. Therefore, the seismic performance assessments of school buildings are critical issues that deserve investigation. Design/methodology/approach: This paper develops a methodology that uses principal component analysis to generalize the seismic factors from the basic seismic parameters of school buildings, uses data mining to cluster different school building sizes and uses grey theory to analyze the relationship between seismic factors and the seismic performance of school buildings. Additionally, this paper employs the Artificial Neural Network (ANN) to deduce the seismic assessment model for school buildings. Finally, it adopts support vector machine to validate the ANN's deductive results. Findings: An empirical study was conducted on 326 school buildings in the central area of Taichung City, Taiwan, to illustrate the effectiveness of the proposed approach. Results show that thickness of wall and width of middle-row column relate significantly with school-building seismic performance. Originality/value: This paper provides a model that structural engineers or architects may use to design school buildings that are adequately resistant to earthquakes as well as a reference for future academic research. [ABSTRACT FROM AUTHOR]

In the semiconductor industry, the testing section has always played an important role. The testing section often requires engineers to judge the defect, which wastes a lot of time and cost. The accurate classification can provide useful information for engineers through neural networks. In this paper, we present a method for wafer map data augmentation and defect classification. Data augmentation is based on CNN encoder-decoder and the classification is based on depthwise separable convolutions. There are two datasets used, one is open dataset WM-811K and the other is built with a Taiwan company. We train two models with mobilenetV1 and V2 for the different datasets. The light-weight deep convolution can reduce model parameters and calculations, which is very efficient for the testing house with large production volumes. On two different data sets, our proposed method can reduce the number of parameters by 30% and 95%, and reduce the amount of calculation by 75% and 25%, respectively. The test accuracy of the first dataset is 93.95%. The second dataset test accuracy is 87.04%. After the data augmentation, accuracy is increased to 97.01% and 95.09%, respectively. [ABSTRACT FROM AUTHOR]

Missing values are common in the Internet of Things (IoT) environment for various reasons, including regular maintenance or malfunction. In time-series prediction in the IoT, missing values may have a relationship with the target labels, and their missing patterns result in informative missingness. Thus, missing values can be a barrier to achieving high accuracy of prediction and analysis in data mining in the IoT. Although several methods have been proposed to estimate values that are missing, few studies have investigated the comparison of interpolation methods using conventional and deep learning models. There has thus far been relatively little research into interpolation methods in the IoT environment. To address these problems, this paper presents the use of linear regression, support vector regression, artificial neural networks, and long short-term memory to make time-series predictions for missing values. Finally, a full comparison and analysis of interpolation methods are presented. We believe that these findings can be of value to future work in IoT applications. [ABSTRACT FROM AUTHOR]

Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women. [ABSTRACT FROM AUTHOR]

• Developed a novel optimal chiller loading regulator to reduce energy consumption in industries. • Deep neural network and conditional generative adversarial network were employed to achieve energy saving. • Practical feasibility is verified by conducting 1-year field validation in panel manufacturing factory. • Energy can be saved in the range of 81.9 MWh to 198 MWh per year by employing OCLR. This paper proposes a new method termed backward modeling approach (BMA) to achieve optimal chiller loading (OCL) for reducing energy consumption in industries running multiple-chillers with different efficiency. The developed OCL regulator (OCLR) based on novel BMA approach is composed of conditional generative network (cGAN) and deep neural network (DNN). Most works on the optimal chiller loading problem are to find out the setting of partial load rate (PLR) for each chiller. However, PLR for each chiller cannot be controlled directly and can only be achieved through setting chilled water supply temperature. A novel feedback control framework was developed to identify the relationship between chilled water supply temperature and the PLR. In light of this, the control instruction for chilled water supply temperature can be set to achieve the desired energy saving. The practical feasibility of loading optimization based on developed OCLR was evaluated by conducting field validation for 1 year in a reputed panel manufacturing factory based in Taiwan running multiple-chiller system. From the experimental results, it is evident that the developed data-driven OCLR based on BMA has very high performance and was able to conserve significant energy in the range of 81.9 MWh to 198 MWh per year. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a new algorithm to construct the optimal radial basic function (RBF) neural network for fast restoration of distribution systems with load variations. Service restoration of distribution systems is to restore power to the blacked out but unfaulted area. Basically, it is a stressful and urgent task that must be performed by system operators. In this paper, a new algorithm which combines orthogonal least-squares (OLS) and enhanced differential evolution (EDE) methods is developed to construct the optimal RBF network that shall further achieve the fast restoration of distribution systems. The proposed scheme comprises training data creation phase and network construction phase. In the training data creation phase, a heuristic-based fuzzy inference (HBFI) method is employed to build the restoration plans under various load levels. Then an optimal RBF network is constructed by OLS and EDE algorithms in the network construction phase. Once the RBF network is constructed properly, the desired restoration plan can be produced as soon as the inputs are given. The proposed method was tested on a typical distribution system of the Taiwan Power Company (TPC). Results show that the proposed method outperforms the existing methods in terms of convergence performance and forecasting accuracy. [Copyright &y& Elsevier]

Abstract: This paper is aimed at creating an empirical model for assessing failure potential of highway slopes, with a special attention to the failure characteristics of the highway slopes in the Alishan, Taiwan area prior to, and post, the 1999 Chi-Chi, Taiwan earthquake. The basis of the study is a large database of 955 slope records from four highways in the Alishan area. Artificial neural network (ANN) is utilized to “learn” from this database. The developed ANN model is then used to study the effect of the Chi-Chi earthquake on the slope failure characteristics in the Alishan area. Significant changes in the degrees of influence of several factors (variables) are found and possible reasons for such changes are discussed. The novelty of this paper lies in the fact that the developed ANN models are used as a tool to investigate the slope failure characteristics before and after the Chi-Chi earthquake. [Copyright &y& Elsevier]

This paper investigates the power load composition of an isolated power system using a load survey and estimates wind power generation with a probabilistic network. The typical load pattern of various customer classes is derived, which are then used to derive the total power consumption of all customers within each class. A probabilistic neural network is used to solve the win power generation based on the wind speed for an offshore island in Taiwan. With the hourly wind speed and load composition, the power generation of diesel generators was obtained. Results of this paper demonstrate that wind power generation can economically and effectively replace the power generation of the island's diesel power plant and provide partial power-supply capability for the net peak load requirement. [ABSTRACT FROM AUTHOR]

Abstract: This paper uses linear and nonlinear statistical models, including artificial neural network (ANN) methods, to investigate the influence of the four economic factors, which are the national income (NI), population (POP), gross of domestic production (GDP), and consumer price index (CPI) on the electricity consumption in Taiwan and then to develop an economic forecasting model. Both methods agree that POP and NI influence electricity consumption the most, whereas GDP the least. The results of comparing the out-of-sample forecasting capabilities of the two methods indicate the following. (1) If given a large amount of historical data, the forecasts of ARMAX are better than the other linear models. (2) The linear model is weaker on foretelling peaks and bottoms regardless the amount of historical data. (3) The forecasting performance of ANN is higher than the other linear models based on two sets of historical data considered in the paper. This is probably due to the fact that the ANN model is capable of catching sophisticated nonlinear integrating effects through a learning process. To sum up, the ANN method is more appropriate than the linear method for developing a forecasting model of electricity consumption. Moreover, researchers can employ either ANN or linear model to extract the important economic factors of the electricity consumption in Taiwan. [Copyright &y& Elsevier]

The operations of power systems are becoming increasingly challenging due to the high penetration of renewable power generation, which is uncertain and stochastic. Highly accurate day-ahead renewable power forecasting helps operators in a dispatch center schedule power generations for conventional thermal generators. Efficient day-ahead renewable power forecasting requires information from widely separated locations. This paper proposes a novel day-ahead spatiotemporal wind speed forecasting method based on a convolutional neural network (CNN), which is an image-based deep learning method. This paper exploits a robust design based on Taguchi's orthogonal array to determine the numbers of cascade/parallel layers, convolutions in each layer, kernels and hidden layers, as well as the kernel size, zero-padding and dropout ratio in the proposed CNN to ensure that the proposed CNN is insensitive to the seasonal characteristics of wind speeds while retaining high accuracy. In this paper, the day-ahead forecasting of wind speed at an offshore wind farm (Fuhai) near Taiwan is performed using historical wind speeds at seven sites in Taiwan, China, South Korea and the Philippines. Simulation results reveal that the proposed robust design-based CNN outperforms existing methods. Image 1 • Structure parameters of the CNN are determined by robust design. • Hyperparameters of the CNN are determined by robust design without empirical tests. • Spatiotemporal wind speeds provide the 2D information applied to the CNN. • Other ancillary wind farms are determined by cross-correlation analysis. [ABSTRACT FROM AUTHOR]

Developing on-site earthquake early warning systems has been a challenging problem because of time limitations and the amount of information that can be collected before the warning needs to be issued. A potential solution that could prevent severe disasters is to predict the potential strong motion using the initial P-wave signal and provide warnings before serious ground shaking starts. In practice, the accuracy of prediction is the most critical issue for earthquake early warning systems. Traditional methods use certain criteria, selected through intuition or experience, to make the prediction. However, the criteria thresholds are difficult to select and may significantly affect the prediction accuracy. This paper investigates methods based on artificial intelligence for predicting the greatest earthquake ground motion early, when the P-wave arrives at seismograph stations. A neural network model is built to make the predictions using a small window of the initial P-wave acceleration signal. The model is trained by seismic waves collected from 1991 to 2019 in Taiwan and is evaluated by events in 2020 and 2021. From these evaluations, the proposed scheme significantly outperforms the threshold-based method in terms of its accuracy and average leading time. [ABSTRACT FROM AUTHOR]

Energy efficiency and renewable energy are the two main research topics for sustainable energy. In the past ten years, countries around the world have invested a lot of manpower into new energy research. However, in addition to new energy development, energy efficiency technologies need to be emphasized to promote production efficiency and reduce environmental pollution. In order to improve power production efficiency, an integrated solution regarding the issue of electric power load forecasting was proposed in this study. The solution proposed was to, in combination with persistence and search algorithms, establish a new integrated ultra-short-term electric power load forecasting method based on the adaptive-network-based fuzzy inference system (ANFIS) and back-propagation neural network (BPN), which can be applied in forecasting electric power load in Taiwan. The research methodology used in this paper was mainly to acquire and process the all-day electric power load data of Taiwan Power and execute preliminary forecasting values of the electric power load by applying ANFIS, BPN and persistence. The preliminary forecasting values of the electric power load obtained therefrom were called suboptimal solutions and finally the optimal weighted value was determined by applying a search algorithm through integrating the above three methods by weighting. In this paper, the optimal electric power load value was forecasted based on the weighted value obtained therefrom. It was proven through experimental results that the solution proposed in this paper can be used to accurately forecast electric power load, with a minimal error. [ABSTRACT FROM AUTHOR]

Financial constraints necessitate the tradeoff among proposed railroad projects, so that the project priorities for implementation and budget allocation need to be determined by the ranking mechanisms in the government. At present, the Taiwan central government prioritizes funding allocations primarily using the analytic hierarchy process (AHP), a methodology that permits the synthesizing of subjective judgments systematically and logically into objective consensus. However, due to the coopetition and heterogeneity of railway projects, the proper priorities of railroad projects could not be always evaluated by the AHP. The decision makers prefer subjective judgments to referring to the AHP evaluation results. This circumstance not only decreased the AHP advantages, but also raised the risk of the policies. A method to consider both objective measures and subjective judgments of project attributes can help reduce this problem. Accordingly, combining the AHP with the artificial neural network (ANN) methodologies would theoretically be a proper solution to bring a ranking predication model by creating the obscure relations between objective measures by the AHP and subjective judgments. However, the inconsistency between the AHP evaluation and subjective judgments resulted in the inferior soundness of the AHP/ANN ranking forecast model. To overcome this problem, this study proposes the data preprocessing method (DPM) to calculate the correlation coefficient value using the subjective and objective ranking incidence matrixes; according to the correlation coefficient value, the consistency between the AHP rankings and subjective judgments of railroad projects can be evaluated and improved, so that the forecast accuracy of the AHP/ANN ranking forecast model can also be enhanced. Based on this concept, a practical railroad project ranking experience derived from the Institute of Transportation of Taiwan is illustrated in this paper to reveal the feasibility of applying the DPM to the AHP/ANN ranking prediction model. [ABSTRACT FROM PUBLISHER]

Abstract: Stock price variation predictions are at the core of many research issues, and neural networks (NNs) are widely applied and were proven to be more efficient than time series forecasting for stock price forecasting. However, this type of research always determines the parameter settings of the NNs rationally through a trial-and-error methodology. This paper integrates design of experiment (DOE), Taguchi method, and back-propagation NN (BPNN) to construct a robust engine to further optimize the prediction accuracy under a robust DOE-based predictor. Adopting data from Taiwan Stock Exchange (TWSE), the technical analytical indexes and β value of the listed stocks of TWSE were computed. The research results indicated that the proposed approach can effectively improve the forecasting rate of stock price variations. [Copyright &y& Elsevier]

Abstract: Site classification is an important procedure for a reliable site-specific seismic hazard assessment. On the other hand, the site conditions at strong-motion stations are essential for accurate interpretation and analysis of the recorded ground motion data obtained from different regions of the world. For some countries with insufficient data on the subsurface geological settings, the required site condition information is not available. This paper presents a new and efficient approach for site classification based on artificial neural networks (ANN) along with a selected set of representative horizontal to vertical spectral ratio (HVSR) curves for four site classes. The nonlinear nature of ANN and their ability to learn in a complex environment make it highly suitable for function approximation and solving complicated engineering problems. Two types of radial basis function (RBF) neural networks, namely, probabilistic neural networks (PNN) and generalized regression neural networks (GRNN) were chosen in this study, as no separate training phase is required, rendering them particularly suitable for site classification. The proposed approach has been tested using data of the Chi-Chi, Taiwan, earthquake (Mw=7.6) recorded from 87 stations at which the site conditions are known. Analyses show that both the PNN and the GRNN perform very well with similar accuracy in estimating site conditions, with successful rates of 78% and 75%, respectively. [Copyright &y& Elsevier]

Abstract: Under limited resources in corporation education training, to enhance human resources quality, making education training program planning more efficient is a significant issue in training future talents. In accordance with Taiwan TrainQuali System (TTQS), the basic training structure is ton specify P (Plan) and D (Design). Ensuing results will be easier and successful. From TTQS database of Bureau of Employment and Vocational Training, corporations in Taoyuan, Hsinchu and Miaoli winning Gold Medals (Group B) have gaps outside control line in P and D. Enhancement is needed in the gap. The paper aims at a certain company winning Gold Medals in Taoyuan, Hsinchu and Miaoli to locate hidden or unobvious information with data mining, which will help future education training course planning and design. The researchers use two-stage clustering (SOM and K-means) under data mining theory to collect personnel training data of Automobile Corporation A in Taiwan and China with data mining and analysis. The results under the two algorithms will serve as reference for future education training courses. In the end, in combination of back-propagation neural network to develop education training prediction model, the research offers reference for writing knowledge management system to enhance effects of personnel participation in training at corporations. [ABSTRACT FROM AUTHOR]

Abstract: This paper establishes a simulation model for the supply chain of the hospital logistic system (SCHLS) based on the dynamic Taguchi method. The model derives optimal factor level combinations in the SCHLS setting when establishing adjustable contracting capacity between SCHLS and the pharmaceutical company. To attempt the goal, this study adopts the SCHLS case in the North Alliance of the Department of Health of Taiwan. The data collection uses a simulation based on Taguchi’s L 18 orthogonal table for SCHLS. This work also proposes an optimal approach, including the neural network (NN) and genetic algorithm (GA), to obtain an optimal robust design in achieving optimal SCHLS multi-performance. The research results show that the predicted response of multi-performance in the optimal approach is better than that in Taguchi. [ABSTRACT FROM AUTHOR]

Product delivery time is as vital as the yield rate for semiconductor manufacturing companies since the industry has become highly competitive and more dynamic nowadays. In the manufacturing process, appropriate parameter settings can shorten the machine cycle time and in turn the product delivery time. This paper presents the application of 'IF-THEN' rules extracted from a multilayer perceptron (MLP) artificial neural network to tune moulding machine parameters to improve the machine cycle time. We can extract the 'IF-THEN' rules by scrutinising the connecting weights inside the MLP network. Historical genuine operating data of a moulding machine input parameters and cycle time were collected from an integrated circuit packaging company in Taiwan. The data were fitted in with an MLP network, and the 'IF-THEN' rules were extracted afterwards. The 'IF-THEN' rules not only indicate which input parameters dominate the machine cycle time but also explain how to tune them. We have applied the extracted rules to tune the moulding machine parameters. Practical results show that the moulding machine cycle time agrees very well with the extracted rules, and also justify the feasibility of the proposed method. [ABSTRACT FROM PUBLISHER]

The ultimate goal of an electric utility is to create maximum profit while maintaining reliability and security of the power supply. The operation and control of power system is sensitive to system demand. Therefore, improvements in load-forecasting accuracy will lead to cost savings and enhance system security. Due to Taiwan's distinct climate characteristics, it is difficult to obtain satisfactory load-forecasting results by treating the whole island as a single region. In addition, weather factors, such as temperature, relative humidity, and the Heat Index (HI) (a human-perceived equivalent temperature) may also affect load-consumption patterns. This paper proposes a multiregion short-term load-forecasting methodology, taking into account the HI to improve load-forecasting accuracy in Taiwan Power Company's (Taipower's) system. The results show that adopting the HI as a parameter can effectively improve the accuracy if the temperature of the region under investigation is above 27 ^\circ\C (80 ^ \circ\F). By considering both the load/weather diversity and the HI, further improvements to the load forecasting for the Taipower system during summer can be achieved. [ABSTRACT FROM AUTHOR]

Abstract: This paper describes a business intelligence application of neural networks in analyzing consumer heterogeneity in the context of eating-out behavior in Taiwan. We apply a neural network rule extraction algorithm which automatically groups the consumers into identifiable segments according to their socio-demographic information. Within each of these segments, the consumers are distinguished between those who eat-out frequently from those who do not based on their psychological traits and eat-out considerations. The data set for this study has been collected through a survey of 800 Taiwanese consumers. Demographic information such as gender, age and income were recorded. In addition, information about their psychological traits and eating-out considerations that might influence the frequency of eating-out were obtained. The results of our data analysis show that the neural network rule extraction algorithm is able to find distinct consumer segments and predict the consumers within each segment with good accuracy. [Copyright &y& Elsevier]

Abstract: Outsourcing manufacturing is a trend in today’s global business operations. Vendor selection is an essential factor affecting outsourcing operations performance and has been determined as a multiple criteria decision making (MCDM) problem. The purpose of this paper is to propose a novel hybrid MCDM technique to cope with the complex and interactive vendor evaluation and selection problem which can determine the structural relationships and the interrelationships amongst all the evaluation’s dimensions and support the Analytic Network Process (ANP) method to arrange appropriate weightings to each dimension and criterion in the evaluation model by summarizing the opinions of the experts. Finally, the overall performance ranking of all alternatives can be obtained to assist the decision making. Taiwan semiconductor industry is the largest provider in worldwide market. It is vertically disintegrated and outsourcing is a main stream practice. Wafer-testing is a critical manufacturing step in the semiconductor supply chain that distinguishes whether the IC can meet the specifications. Consequently, it’s crucial to establish a thorough model for selecting the wafer-testing vendors in order to achieve the success of the outsourcing operation. A case study of a Taiwan semiconductor company in selecting its wafer-testing outsourcing vendor by using the proposed MCDM technique is demonstrated to enhance the decision making quality. The results and proposed solution can be referred to by not only the semiconductor companies, but also other industries so that they can improve the vendor selection process in order to achieve a higher performance and satisfaction level. [Copyright &y& Elsevier]

Abstract: In this paper, we elaborate a neural network model to predict innovation performance with fuzzy rules, as well as implement an adaptive neuro-fuzzy inference systems (ANFIS) to measure the innovation performance through technical information resource and innovation objective. Building on the findings from fuzzy neural network approach, using Sugeno ANFIS, we also compared the artificial neural network with statistical techniques. We found strong support for ANFIS method has better results than the neural network and statistical techniques with regards to forecast performance. Finally, on the basis of our analysis, our results hold an important lesson for decision makers who may clearly picture the rules and adjust the resource allocation to meet their innovation objectives. [Copyright &y& Elsevier]

Abstract: One of the costs of Taiwan''s massive economic development has been severe air pollution problems in many parts of the island. Since vehicle emissions are the major source of air pollution in most of Taiwan''s urban areas, Taiwan''s government has implemented policies to rectify the degrading air quality, especially in areas with high population density. To reduce vehicle pollution emissions an on-road remote sensing and monitoring system is used to check the exhaust emissions from gasoline engine automobiles. By identifying individual vehicles with excessive emissions for follow-up inspection and testing, air quality in the urban environment is expected to improve greatly. Because remote sensing is capable of measuring a large number of moving vehicles in a short period, it has been considered as an assessment technique in place of the stationary emission-sampling techniques. However, inherent measurement uncertainty of remote sensing instrumentation, compounded by the indeterminacy of monitoring site selection, plus the vagaries of weather, causes large errors in pollution discrimination and limits the application of the remote sensing. Many governments are still waiting for a novel data analysis methodology to clamp down on heavily emitting vehicles by using remote sensing data. This paper proposes an artificial neural network (ANN), with vehicle attributes embedded, that can be trained by genetic algorithm (GA) based on different strategies to predict vehicle emission violation. Results show that the accuracy of predicting emission violation is as high as 92%. False determinations tend to occur for vehicles aged 7–13 years, peaking at 10 years of age. [Copyright &y& Elsevier]

Abstract: Accurate predictions of storm surge and surge deviation are essential for industrial activities in coastal areas. Usually numerical hydrodynamic models or empirical methods are used to estimate the storm surge. This paper proposes an alternative back-propagation neural network (BPN) approach to forecast the storm surge and surge deviation. The prediction of storm surge from a previous typhoon is used as a training set to form predictions for the next event. Wind velocity, wind direction, atmospheric pressure and astronomical tide were selected as inputs in the neural network. The observations obtained during three typhoons from four stations in Taiwan were used to illustrate performance of the BPN model. Comparisons with numerical methods indicate that the storm surge and surge deviation can be efficiently predicted using BPN. [Copyright &y& Elsevier]

Abstract: In this paper we construct the consumer loan default predicting model through conducting the empirical analysis on the customers of unsecured consumer loan from a certain financial institution in Taiwan, and adopt the borrower’s demographic variables and money attitude as the real-timeaneous discriminant information. Furthermore, we construct respectively through four predicting methods, such as DA, LR, NN and DEA–DA, to compare the suitability of these four mentioned methods. The results show that DEA–DA and NN are possessed better predicting capability and they are the optimal predicting model that this study longing for. In addition, this study showed that the default loan predicting model will be possessed higher level of predicting capability after added money attitude. [Copyright &y& Elsevier]

Abstract: The total consumption of electricity and petroleum energies accounts for almost 90% of the total energy consumption in Taiwan, so it is critical to model and forecast them accurately. For univariate modeling, this paper proposes two new hybrid nonlinear models that combine a linear model with an artificial neural network (ANN) to develop adjusted forecasts, taking into account heteroscedasticity in the model''s input. Both of the hybrid models can decrease round-off and prediction errors for multi-step-ahead forecasting. The results suggest that the new hybrid model generally produces forecasts which, on the basis of out-of-sample forecast encompassing tests and comparisons of three different statistic measures, routinely dominate the forecasts from conventional linear models. The superiority of the hybrid ANNs is due to their flexibility to account for potentially complex nonlinear relationships that are not easily captured by linear models. Furthermore, all of the linear and nonlinear models have highly accurate forecasts, since the mean absolute percentage forecast error (MAPE) results are less than 5%. Overall, the inclusion of heteroscedastic variations in the input layer of the hybrid univariate model could help improve the modeling accuracy for multi-step-ahead forecasting. [Copyright &y& Elsevier]

Summary: A hybrid neural network model is proposed in this paper to forecast the typhoon rainfall. Two different types of artificial neural networks, the self-organizing map (SOM) and the multilayer perceptron network (MLPN), are combined to develop the proposed model. In the proposed model, a data analysis technique is developed based on the SOM, which can perform cluster analysis and discrimination analysis in one step. The MLPN is used as the nonlinear regression technique to construct the relationship between the input and output data. First, the input data are analyzed using a SOM-based data analysis technique. Through the SOM-based data analysis technique, input data with different properties are first divided into distinct clusters, which can help the multivariate nonlinear regression of each cluster. Additionally, the topological relationships among data are discovered from which more insight into the typhoon-rainfall process can be revealed. Then, for each cluster, the individual relationship between the input and output data is constructed by a specific MLPN. For evaluating the forecasting performance of the proposed model, an application is conducted. The proposed model is applied to the Tanshui River Basin to forecast the typhoon rainfall. The results show that the proposed model can forecast more precisely than the model developed by the conventional neural network approach. [Copyright &y& Elsevier]

Abstract: Fuzzy time series model has been successfully employed in predicting stock prices and foreign exchange rates. In this paper, we propose a new fuzzy time series model termed as distance-based fuzzy time series (DBFTS) to predict the exchange rate. Unlike the existing fuzzy time series models which require exact match of the fuzzy logic relationships (FLRs), the distance-based fuzzy time series model uses the distance between two FLRs in selecting prediction rules. To predict the exchange rate, a two factors distance-based fuzzy time series model is constructed. The first factor of the model is the exchange rate itself and the second factor comprises many candidate variables affecting the fluctuation of exchange rates. Using the exchange rate data released by the Central Bank of Taiwan, we conducted several experiments on exchange rate forecasting. The experiment results showed that the distance-based fuzzy time series outperformed the random walk model and the artificial neural network model in terms of mean square error. [Copyright &y& Elsevier]

Abstract: Stock market price index prediction is regarded as a challenging task of the financial time series prediction process. Support vector regression (SVR) has successfully solved prediction problems in many domains, including the stock market. This paper hybridizes SVR with the self-organizing feature map (SOFM) technique and a filter-based feature selection to reduce the cost of training time and to improve prediction accuracies. The hybrid system conducts the following processes: filter-based feature selection to choose important input attributes; SOFM algorithm to cluster the training samples; and SVR to predict the stock market price index. The proposed model was demonstrated using a real future dataset – Taiwan index futures (FITX) to predict the next day’s price index. The experiment results show that the proposed SOFM-SVR is an improvement over the traditional single SVR in average prediction accuracy and training time. [Copyright &y& Elsevier]

Accounting frauds have continuously happened all over the world. This leads to the need of predicting business failures. Statistical methods and machine learning techniques have been widely used to deal with this issue. In general, financial ratios are one of the main inputs to develop the prediction models. This paper presents a hybrid financial analysis model including static and trend analysis models to construct and train a back-propagation neural network (BPN) model. Further, the experiments employ four datasets of Taiwan enterprises which support that the proposed model not only provides a high predication rate but also outperforms other models including discriminant analysis, decision trees, and the back-propagation neural network alone. [Copyright &y& Elsevier]

Abstract: It is essential to forecast the variation of storm surge in coastal areas during the typhoon attacks. Conventional investigations of storm surge often used the method of numerical hydrodynamic models or empirical formula. In this paper, the back-propagation neural network (BPN) is applied to predict the short-term typhoon surge and surge deviation in order to overcome the problem of exclusive and nonlinear relationships. The observations obtained during three typhoons of Taichung harbor in Taiwan are verified by the present model. From the comparison with numerical methods, it can be found that the short-term storm surge and surge deviation can be efficiently predicted 1 to 6h ahead using BPN. [Copyright &y& Elsevier]

Abstract: A typhoon-surge forecasting model was developed with a back-propagation neural network (BPN) in the present paper. The typhoon''s characteristics, local meteorological conditions and typhoon surges at a considered tidal station at time t−1 and t were used as input data of the model to forecast typhoon surges at the following time. For the selection of a better forecasting model, four models (Models A–D) were tested and compared under the different composition of the above-mentioned input factors. A general evaluation index that is a composition of four performance indexes was proposed to evaluate the model''s overall performance. The result of typhoon-surge forecasting was classified into five grades: A (excellent), B (good), C (fair), D (poor) and E (bad), according to the value of the general evaluation index. Sixteen typhoon events and their corresponding typhoon surges and local meteorological conditions at Ken–fang Tidal Station in the coast of north-eastern Taiwan between 1993 and 2000 were collected, 12 of them were used in model''s calibration while the other four were used in model''s verification. The analysis of typhoon-surge forecasting results at Ken–fang tidal station show that the Model D composing 18 input factors has better performance, and that it is a suitable BPN-based model in typhoon-surge forecasting. The Model D was also applied to typhoon-surge forecasting at Cheng-kung Tidal Station in south-eastern coast of Taiwan and at Tung-shih Tidal Station in the coast of south-western Taiwan. Results show that the application of Model D in typhoon-surge forecasting at Cheng-kung Tidal Station has better performance than that at Tung-shih Tidal Station. [Copyright &y& Elsevier]

Abstract: This paper proposes a hybrid methodology that exploits the unique strength of the seasonal autoregressive integrated moving average (SARIMA) model and the support vector machines (SVM) model in forecasting seasonal time series. The seasonal time series data of Taiwan’s machinery industry production values were used to examine the forecasting accuracy of the proposed hybrid model. The forecasting performance was compared among three models, i.e., the hybrid model, SARIMA models and the SVM models, respectively. Among these methods, the normalized mean square error (NMSE) and the mean absolute percentage error (MAPE) of the hybrid model were the lowest. The hybrid model was also able to forecast certain significant turning points of the test time series. [Copyright &y& Elsevier]

Abstract: By providing credit risk information, credit rating systems benefit most participants in financial markets, including issuers, investors, market regulators and intermediaries. In this paper, we propose an automatic classification model for issuer credit ratings, a type of fundamental credit rating information, by applying the support vector machine (SVM) method. This is a novel classification algorithm that is famous for dealing with high dimension classifications. We also use three new variables: stock market information, financial support by the government, and financial support by major shareholders to enhance the effectiveness of the classification. Previous research has seldom considered these variables. The data period of the input variables used in this study covers three years, while most previous research has only considered one year. We compare our SVM model with the back propagation neural network (BP), a well-known credit rating classification method. Our experiment results show that the SVM classification model performs better than the BP model. The accuracy rate (84.62%) is also higher than previous research. [Copyright &y& Elsevier]

Abstract: This paper employs artificial neural network and decision tree to derive knowledge about the job attitudes of Generation Xers. The sample frame consisted of 1000 large Manufacturing Industries and 500 large Service Industries, randomly selected from the Common Wealth Magazine 1000 index of Taiwan Manufacturing Industries and Service Firms. Then, we exploited the ART2 neural model to take the collected data as inputs and form performance classes according to their similarities. Finally, the decision tree was employed to determine definitions for each class, resulting in 52 rules associated with certainty factors. The results could be used to develop an intelligent decision support system for the recruitment and management of Generation Xers. [Copyright &y& Elsevier]

Abstract: Using a sample of 59 Taiwanese firms in distress, we investigate investor gains or losses around the filing date and the confirmation date of the reorganization plan and propose ex ante trading strategies that can generate potentially substantial returns from these stocks. We further experiment with a novel approach to sensitivity analysis of neural network inputs for refining and rating the most important input variables and then construct artificial neural network (ANN) models to classify and predict the post-reorganization filing resolutions in a three- (Model 1) and two-group (Models 2 and 3) resolution setting. We are unaware of any other paper that has used artificial intelligence techniques in analyzing post-bankruptcy resolutions. The results show that our five-variable models produce a consistent estimate between the training and testing sets; that is, both three- and two-group models are of a high degree of accuracy and stability, demonstrating the robustness of the ANN models. [Copyright &y& Elsevier]

Seismic early warning has been very important and has become feasible in Taiwan. Perhaps because of the lack of quick and reliable estimations of the induced structural response, however, the triggering criteria of almost all of the existing earthquake protection or early warning systems in the world are merely based on the collected or estimated data of the ground motion, without any information regarding the structural response. This paper presents a methodology of generating quick seismic response estimations of a prestressed concrete (PC) bridge using artificial neural networks (ANNs), which may be incorporated in a seismic early warning system for the bridge. In the methodology ANNs were applied to model the critical structural response of a PC bridge subjected to earthquake excitation of various magnitudes along various directions. The objective was to implement a well-trained network that is capable of providing a quick prediction for the critical response of the target bridge. The well-known multilayer perception (MLP) networks with back propagation algorithm were employed. A simple augmented form of MLP that can be quantitatively determined was proposed. These networks were trained and tested based on the analytical data obtained from the nonlinear dynamic finite fiber element analyses of the target PC bridge. The augmented MLPs were found to be much more efficient than the MLPs in modeling the critical bending moments of the piers and girder of the PC bridge. [ABSTRACT FROM AUTHOR]

Accurate tidal prediction and supplement is an important task in determining constructions and human activities in coastal and oceanic areas. The harmonic tidal level is conventionally used to predict tide levels. However, determination of the tidal components using the spectral analysis requires a long-term tidal level record (more than one year [Handbook of coastal and ocean engineering 1 (1990) 534]). In addition, calculating the coefficients abbreviated of tide component using the least-squares method also requires a large database of tide measurements. This paper presents an application of the artificial neural network for predicting and supplementing the long-term tidal-level using the short term observed data. On site, tidal-level data at Taichung Harbor in Taiwan will be used to test the performance of the artificial neural network model. The results show that the tidal levels over a long duration can be efficiently predicted or supplemented using only a short-term tidal record. [Copyright &y& Elsevier]

In recent years, the technology of artificial intelligence (AI) and robots is rapidly spreading to countries around the world. More and more scholars and industry experts have proposed AI deep learning models and methods to solve human life problems and improve work efficiency. Modern people's lives are very busy, which led us to investigate whether the demand for Bento buffet cafeterias has gradually increased in Taiwan. However, when eating at a buffet in a cafeteria, people often encounter two problems. The first problem is that customers need to queue up to check out after they have selected and filled their dishes from the buffet. However, it always takes too much time waiting, especially at lunch or dinner time. The second problem is sometimes customers question the charges calculated by cafeteria staff, claiming they are too expensive at the checkout counter. Therefore, it is necessary to develop an AI-enabled checkout system. The AI-enabled self-checkout system will help the Bento buffet cafeterias reduce long lineups without the need to add additional workers. In this paper, we used computer vision and deep-learning technology to design and implement an AI-enabled checkout system for Bento buffet cafeterias. The prototype contains an angle steel shelf, a Kinect camera, a light source, and a desktop computer. Six baseline convolutional neural networks were applied for comparison on food recognition. In our experiments, there were 22 different food categories in a Bento buffet cafeteria employed. Experimental results show that the inception_v4 model can achieve the highest average validation accuracy of 99.11% on food recognition, but it requires the most training and recognition time. AlexNet model achieves a 94.5% accuracy and requires the least training time and recognition time. We propose a hierarchical approach with two stages to achieve good performance in both the recognition accuracy rate and the required training and recognition time. The approach is designed to perform the first step of identification and the second step of recognizing similar food images, respectively. Experimental results show that the proposed approach can achieve a 96.3% accuracy rate on our test dataset and required very little recognition time for input images. In addition, food volumes could be estimated using the depth images captured by the Kinect camera, and a framework of visual checkout system was successfully built. [ABSTRACT FROM AUTHOR]

The high utilization of renewable energy to manage climate change and provide green energy requires short-term photovoltaic (PV) power forecasting. In this paper, a novel forecasting strategy that combines a convolutional neural network (CNN) and a salp swarm algorithm (SSA) is proposed to forecast PV power output. First, the historical PV power data and associated weather information are classified into five weather types, such as rainy, heavy cloudy, cloudy, light cloudy and sunny. The CNN classification is then used to determine the prediction for the next day's weather type. Five models of CNN regression are established to accommodate the prediction for different weather types. Each CNN regression is optimized using a salp swarm algorithm (SSA) to tune the best parameter. To evaluate the performance of the proposed method, comparisons were made to the SSA based support vector machine (SVM-SSA) and long short-term memory neural network (LSTM-SSA) methods. The proposed method was tested on a PV power generation system with a 500 kWp capacity located in south Taiwan. The results showed that the proposed CNN-SSA could accommodate the actual generation pattern better than the SVM-SSA and LSTM-SSA methods. [ABSTRACT FROM AUTHOR]

Picking seismic events is a time-consuming task by just relying on manpower, especially in high seismicity regions. For instance, Taiwan, on February 2018, over 4,000 aftershocks were detected within 12 days after the Hualien earthquake. Although there are lots of papers propose various deep learning models that are suitable for dealing the problem, there is still a gap between the picking routine and the AI research. Thus, we design a toolbox that can be easily integrated into the regular work flow. In this study, based on PhaseNet developed by Zhu et al. (2018), the masking arrival-time label with a Gaussian distribution is the essential part for the training methodology. In addition, we implement the neural network model UNet++, which re-designs the skip pathways for better performance comparing to the original U-Net that is used by the PhaseNet. Here, we provide an open-source framework that can be easily installed and operated. This automatic picking toolbox is built upon Obspy and Keras with Tensorflow backbone, by reading S-file catalogs from SEISAN for generating labeled datasets. Besides, a Docker image is available for fast server deployment. As a result, in our scenario, most of the temporary stations are only contained single channel and mainly focus on P arrivals. We reduce the training set from input: three-components – output: P/S/Noise categories into input: Z-component – output: P category. The testing data is successfully identified by the model trained with 90,000 traces. Moreover, minor events missed by manually picking are detected by the model. [ABSTRACT FROM AUTHOR]