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]

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]

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]

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]

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]

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]

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]