Search

Among various eye diseases, glaucoma is one of the leading causes of blindness. Glaucoma is also one of the most common eye diseases in Taiwan. Glaucoma screenings can use optical coherence tomography (OCT) to locate areas in which the retinal nerve fiber layer is thinning. However, because OCT equipment is costly, only large hospitals with well-equipped facilities will have OCT, and regular eye clinics cannot afford such expensive equipment. This has caused many glaucoma patients to worsen because they cannot get an early diagnosis in regular eye clinics in time. This paper proposes a method of using a generative adversarial network (GAN) to generate corresponding OCT images from fundus images to assist family doctors in judging whether further examination is needed based on the generated OCT images to achieve early detection and treatment of glaucoma. In addition, in order to improve the classification accuracy of the system deployed in different hospitals or clinics, this paper also proposes to use the incremental training method to fine-tune the model. The model can be quickly applied by adding a small number of images from a specific clinic or hospital. Experimental results show that the cosine similarity between the generated OCT image and the real OCT image is 97.8%. Combined with the proposed transfer learning method, the classification accuracy of the classification model reaches 83.17%. As well as the use of the incremental method, the accuracy of identifying glaucoma is approximately 78.94%, which is 8.77% higher than the 70.17% accuracy of the initial model. Experimental results show the effectiveness and feasibility of our proposed method. [ABSTRACT FROM AUTHOR]

For the advancement of smart grids, solar power generation predictions have become an important research topic. In the case of using traditional modeling methods, excessive computational costs may be incurred and it is difficult for these methods to learn the multi-variable dependencies of the data. Therefore, in this paper, a deep learning model was used to combine convolutional neural networks and long short-term memory recurrent network predictions. This method enables hourly power generation one day into the future. Convolutional neural networks are used to extract the features of multiple time series, while long short-term memory neural networks predict multivariate outcomes simultaneously. In order to obtain more accurate prediction results, we performed feature selection on meteorological features and combined the selected weather features to train the prediction model. We further distinguished sunny- and rainy-day models according to the predicted daily rainfall conditions. In the experiment, it was shown that the method of combining meteorological features further reduced the error. Finally, taking into account the differences in climate conditions between the northern and southern regions of Taiwan, the experimental results of case studies involving multiple regions were evaluated to verify the proposed method. The results showed that training combined with selected meteorological features can be widely used in regions with different climates in Taiwan. [ABSTRACT FROM AUTHOR]

Digital shearography is a technique that has recently been applied to material inspections that cannot be performed by the naked eyes, including the detection of air bubble defects in tires. Although digital shearography detects bubbles that are not visible to the naked eyes, the process of determining tire defects still relies on field operators, with inconsistent results depending on the experiences of the field operator personnel. New or different types of bubble defects that AI models have not previously recognized are often missed, resulting in an inadequate quality detection model. In this paper, we propose a bubble defect detection method based on an incremental YOLO architecture. The data for this research was provided by the largest tire manufacturer in Taiwan. In our research, we classify the defects into six distinct categories, pre-process the images to allow better detections of less-noticeable defects, increase the amount of training data used, and generate an initial training model with the YOLO framework. We also propose an incremental YOLO method using small-model training for previously unobserved defects to improve the model detection rate. We have observed detection accuracy and sensitivity of 98% and 90% in the experimental results, respectively. The methods proposed in this paper can assist tire manufacturers in achieving semi-automatic quality inspections and labor cost reductions. [ABSTRACT FROM AUTHOR]

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]

Due to an arising COVID-19 positive confirmed case in Taiwan, the screening of body temperature, mask wearing and quarantined violation is enhanced. A mobile robot that conducts this task is demanded to reduce the human labor. However, conventional robots suffer from several limitations, perceptual aliasing (e.g., different places/objects can appear identical), occlusion (e.g., place/object appearance changes between visits), different viewpoints, the scale of objects, low mobility, less functionality, and some environmental limitations. As for the thermal imager, it displays the current heat spectrum colors, and needs manual monitoring. This paper proposes applying Simultaneous Localization and Mapping in an unknown environment and using deep learning for detection of temperature, mask wearing, and human face on the Raspberry Pi to overcome these problems. It also uses the A* algorithm to do path planning and obstacle avoidance via 3D Light Detection and Ranging to make the robot move more smoothly. Evaluating and implementing different Simultaneous Localization and Mapping algorithms and deep learning models, then selecting the most suitable method. Root Mean Square Error of three Simultaneous Localization and Mapping algorithms are compared. The predictions of deep learning models are evaluated via the metrics (model speed, accuracy, complexity, precision, recall, precision–recall curve, F1 score). In conclusion, Google Cartographer for building a map, Convolutional Neural Network for mask wearing detection, and only looking once for human face detection achieve the best result among all algorithms. [ABSTRACT FROM AUTHOR]

Featured Application: This work will be materialized into the Bioimage Diagnostic system in Kaohsiung Branch of Chang Gung Hospital, Taiwan. Image recognition through the use of deep learning (DL) techniques has recently become a hot topic in many fields. Especially for bioimage informatics, DL-based image recognition has been successfully used in several applications, such as cancer and fracture detection. However, few previous studies have focused on detecting scaphoid fractures, and the related effectiveness is also not significant. Aimed at this issue, in this paper, we present a two-stage method for scaphoid fracture recognition by conducting an effectiveness analysis of numerous state-of-the-art artificial neural networks. In the first stage, the scaphoid bone is extracted from the radiograph using object detection techniques. Based on the object extracted, several convolutional neural networks (CNNs), with or without transfer learning, are utilized to recognize the segmented object. Finally, the analytical details on a real data set are given, in terms of various evaluation metrics, including sensitivity, specificity, precision, F1-score, area under the receiver operating curve (AUC), kappa, and accuracy. The experimental results reveal that the CNNs with transfer learning are more effective than those without transfer learning. Moreover, DenseNet201 and ResNet101 are found to be more promising than the other methods, on average. According to the experimental results, DenseNet201 and ResNet101 can be recommended as considerable solutions for scaphoid fracture detection within a bioimage diagnostic system. [ABSTRACT FROM AUTHOR]

Featured Application: This research describes a prototype of a system that extracts data from a social network for the purposes of urban environment analysis and that can transform subjective citizen feelings into quantifiable data via machine learning. Urban planning is usually dependent on urban analysis and tends to use data from sensor networks collected over a long period time. However, in recent years, due to increased urbanization and the rapid growth of transport, a gap has developed between urban environments and citizen feelings. Rebuilding urban infrastructure or making urban planning changes require a lot of time and resource costs. The hardware in a city cannot be easily changed, but citizen activities change all the time. Distributing city space according to a software-based recommendation, such as arranging different locations for citizen activities or traffic, is a method that can be implemented to improve city environments and to avoid resource waste. In this paper, citizens were used as sensors to extract environmental information collected using a social network service (SNS), and the information was analyzed to turn subjective feelings into objective environmental phenomena. The research focused on how to collect citizens' feelings regarding urban environments and to develop a citizen-sensing system to bridge the gap between citizen feelings and sensor networks. The results prove that citizens who sense the city environment create small-sized data that are suitable for small-scaled, high-density cities. [ABSTRACT FROM AUTHOR]

According to the World Energy Investment 2018 report, the global annual investment in renewable energy exceeded USD 200 billion for eight consecutive years until 2017. In this paper, a deep-learning-based time-series prediction method, namely a gated recurrent unit (GRU)-based prediction method, is proposed to predict energy generation in Taiwan. Data on thermal power (coal, oil, and gas power), renewable energy (conventional hydropower, solar power, and wind power), pumped hydropower, and nuclear power generation for 1991 to 2020 were obtained from the Bureau of Energy, Ministry of Economic Affairs, Taiwan, and the Taiwan Power Company. The proposed GRU-based method was compared with six common forecasting methods: autoregressive integrated moving average, exponential smoothing (ETS), Holt–Winters ETS, support vector regression (SVR), whale-optimization-algorithm-based SVR, and long short-term memory. Among the methods compared, the proposed method had the lowest mean absolute percentage error and root mean square error and thus the highest accuracy. Government agencies and power companies in Taiwan can use the predictions of accurate energy forecasting models as references to formulate energy policies and design plans for the development of alternative energy sources. [ABSTRACT FROM AUTHOR]

In recent years, the development and application of artificial intelligence have both been topics of concern. In the medical field, an important direction of medical technology development is the extraction and use of applicable information from existing medical records to provide more accurate and helpful diagnosis suggestions. Therefore, this paper proposes using the development of diseases with easily discernible symptoms to predict the development of other medically related but distinct diseases that lack similar data. The aim of this study is to improve the ease of assessing the development of diseases in which symptoms are difficult to detect, and to improve the utilization of medical data. First, a time series model was used to capture the continuous manifestations of diseases with symptoms that could be easily found at different time intervals. Then, through transfer learning and attention mechanism, the general features captured were applied to the predictive model of the development of diseases with insufficient data and symptoms that are difficult to detect. Finally, we conducted a comprehensive experimental study based on a dataset collected from the National Health Insurance Research Database in Taiwan. The results demonstrate that the effectiveness of our transfer learning approach outperforms state-of-the-art deep learning prediction models for disease course prediction. [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]

This paper proposes a new approach based on an unsupervised deep learning (DL) model for landslide detection. Recently, supervised DL models using convolutional neural networks (CNN) have been widely studied for landslide detection. Even though these models provide robust performance and reliable results, they depend highly on a large labeled dataset for their training step. As an alternative, in this paper, we developed an unsupervised learning model by employing a convolutional auto-encoder (CAE) to deal with the problem of limited labeled data for training. The CAE was used to learn and extract the abstract and high-level features without using training data. To assess the performance of the proposed approach, we used Sentinel-2 imagery and a digital elevation model (DEM) to map landslides in three different case studies in India, China, and Taiwan. Using minimum noise fraction (MNF) transformation, we reduced the multispectral dimension to three features containing more than 80% of scene information. Next, these features were stacked with slope data and NDVI as inputs to the CAE model. The Huber reconstruction loss was used to evaluate the inputs. We achieved reconstruction losses ranging from 0.10 to 0.147 for the MNF features, slope, and NDVI stack for all three study areas. The mini-batch K-means clustering method was used to cluster the features into two to five classes. To evaluate the impact of deep features on landslide detection, we first clustered a stack of MNF features, slope, and NDVI, then the same ones plus with the deep features. For all cases, clustering based on deep features provided the highest precision, recall, F1-score, and mean intersection over the union in landslide detection. [ABSTRACT FROM AUTHOR]

In an era where artificial intelligence (AI) bridges crucial communication gaps, this study extends AI's utility to American and Taiwan Sign Language (ASL and TSL) communities through advanced models like the hierarchical vision transformer with shifted windows (Swin). This research evaluates Swin's adaptability across sign languages, aiming for a universal platform for the unvoiced. Utilizing deep learning and transformer technologies, it has developed prototypes for ASL-to-English translation, supported by an educational framework to facilitate learning and comprehension, with the intention to include more languages in the future. This study highlights the efficacy of the Swin model, along with other models such as the vision transformer with deformable attention (DAT), ResNet-50, and VGG-16, in ASL recognition. The Swin model's accuracy across various datasets underscore its potential. Additionally, this research explores the challenges of balancing accuracy with the need for real-time, portable language recognition capabilities and introduces the use of cutting-edge transformer models like Swin, DAT, and video Swin transformers for diverse datasets in sign language recognition. This study explores the integration of multimodality and large language models (LLMs) to promote global inclusivity. Future efforts will focus on enhancing these models and expanding their linguistic reach, with an emphasis on real-time translation applications and educational frameworks. These achievements not only advance the technology of sign language recognition but also provide more effective communication tools for the deaf and hard-of-hearing community. [ABSTRACT FROM AUTHOR]

Taiwan, frequently affected by extreme weather causing phenomena such as earthquakes and typhoons, faces a high incidence of rockfall disasters due to its largely mountainous terrain. These disasters have led to numerous casualties, government compensation cases, and significant transportation safety impacts. According to the National Science and Technology Center for Disaster Reduction records from 2010 to 2022, 421 out of 866 soil and rock disasters occurred in eastern Taiwan, causing traffic disruptions due to rockfalls. Since traditional sensors of disaster detectors only record changes after a rockfall, there is no system in place to detect rockfalls as they occur. To combat this, a rockfall detection and tracking system using deep learning and image processing technology was developed. This system includes a real-time image tracking and recognition system that integrates YOLO and image processing technology. It was trained on a self-collected dataset of 2490 high-resolution RGB images. The system's performance was evaluated on 30 videos featuring various rockfall scenarios. It achieved a mean Average Precision (mAP50) of 0.845 and mAP50-95 of 0.41, with a processing time of 125 ms. Tested on advanced hardware, the system proves effective in quickly tracking and identifying hazardous rockfalls, offering a significant advancement in disaster management and prevention. [ABSTRACT FROM AUTHOR]

Osteoporosis is a common problem in orthopedic medicine, and it has become an important medical issue in orthopedics as Taiwan is gradually becoming an aging society. In the diagnosis of osteoporosis, the bone mineral density (BMD) derived from dual-energy X-ray absorptiometry (DXA) is the main criterion for orthopedic diagnosis of osteoporosis, but due to the high cost of this equipment and the lower penetration rate of the equipment compared to the X-ray images, the problem of osteoporosis has not been effectively solved for many people who suffer from osteoporosis. At present, in clinical diagnosis, doctors are not yet able to accurately interpret X-ray images for osteoporosis manually and must rely on the data obtained from DXA. In recent years, with the continuous development of artificial intelligence, especially in the fields of machine learning and deep learning, significant progress has been made in image recognition. Therefore, it is worthwhile to revisit the question of whether it is possible to use a convolutional neural network model to read a hip X-ray image and then predict the patient's BMD. In this study, we proposed a hip X-ray image segmentation model and a hip X-ray image recognition classification model. First, we used the U-Net model as a framework to segment the femoral neck, greater trochanter, Ward's triangle, and the total hip in the hip X-ray images. We then performed image matting and data augmentation. Finally, we constructed a predictive model for osteoporosis using deep learning algorithms. In the segmentation experiments, we used intersection over union (IoU) as the evaluation metric for image segmentation, and both the U-Net model and the U-Net++ model achieved segmentation results greater than or equal to 0.5. In the classification experiments, using the T-score as the classification basis, the total hip using the DenseNet121 model has the highest accuracy of 74%. [ABSTRACT FROM AUTHOR]

Accurate and rapid taxonomy identification is the initial step in spider image recognition. More than 50,000 spider species are estimated to exist worldwide; however, their identification is still challenging due to the morphological similarity in their physical structures. Deep learning is a known modern technique in computer science, biomedical science, and bioinformatics. With the help of deep learning, new opportunities are available to reveal advanced taxonomic methods. In this study, we applied a deep-learning-based approach using the YOLOv7 framework to provide an efficient and user-friendly identification tool for spider species found in Taiwan called Spider Identification APP (SpiderID_APP). The YOLOv7 model is integrated as a fully connected neural network. The training of the model was performed on 24,000 images retrieved from the freely available annotated database iNaturalist. We provided 120 genus classifications for Taiwan spider species, and the results exhibited accuracy on par with iNaturalist. Furthermore, the presented SpiderID_APP is time- and cost-effective, and researchers and citizen scientists can use this APP as an initial entry point to perform spider identification in Taiwan. However, for detailed species identification at the species level, additional methods like DNA barcoding or genitalic structure dissection are still considered necessary. [ABSTRACT FROM AUTHOR]

Taiwan is highly susceptible to global warming, experiencing a 1.4 °C increase in air temperature from 1911 to 2005, which is twice the average for the Northern Hemisphere. This has potentially led to higher rates of respiratory and cardiovascular mortality. Accurately predicting maximum temperatures during the summer season is crucial, but numerical weather models become less accurate and more uncertain beyond five days. To enhance the reliability of a forecast, post-processing techniques are essential for addressing systematic errors. In September 2020, the NOAA NCEP implemented the Global Ensemble Forecast System version 12 (GEFSv12) to help manage climate risks. This study developed a Hybrid statistical post-processing method that combines Artificial Neural Networks (ANN) and quantile mapping (QQ) approaches to predict daily maximum temperatures (Tmax) and their extremes in Taiwan during the summer season. The Hybrid technique, utilizing deep learning techniques, was applied to the GEFSv12 reforecast data and evaluated against ERA5 reanalysis. The Hybrid technique was the most effective among the three techniques tested. It had the lowest bias and RMSE and the highest correlation coefficient and Index of Agreement. It successfully reduced the warm bias and overestimation of Tmax extreme days. This led to improved prediction skills for all forecast lead times. Compared to ANN and QQ, the Hybrid method proved to be more effective in predicting daily Tmax, including extreme Tmax during summer, on extended-range time-scale deterministic and ensemble probabilistic forecasts over Taiwan. [ABSTRACT FROM AUTHOR]

In the context of the growing emphasis on energy conservation and carbon reduction, the widespread deployment of smart meters in residential and commercial buildings is instrumental in promoting electricity savings. In Taiwan, local governments are actively promoting the installation of smart meters, empowering residents to monitor their electricity consumption and detect abnormal usage patterns, thus mitigating the risk of electrical fires. This safety-oriented approach is a significant driver behind the adoption of smart meters. However, the analysis of the substantial data generated by these meters necessitates pre-processing to address anomalies. Presently, these data primarily serve billing calculations or the extraction of power-saving patterns through big data analytics. To address these challenges, this study proposes a comprehensive approach that integrates a relational database for storing electricity consumption data with knowledge graphs. This integrated method effectively addresses data scarcity at various time scales and identifies prolonged periods of excessive electricity consumption, enabling timely alerts to residents for specific appliance shutdowns. Deep learning techniques are employed to analyze historical consumption data and real-time smart meter readings, with the goal of identifying and mitigating hazardous usage behavior, consequently reducing the risk of electrical fires. The research includes numerical values and text-based predictions for a comprehensive evaluation, utilizing data from ten Taiwanese households in 2022. The anticipated outcome is an improvement in household electrical safety and enhanced energy efficiency. [ABSTRACT FROM AUTHOR]

Patient safety is a paramount concern in the medical field, and advancements in deep learning and Artificial Intelligence (AI) have opened up new possibilities for improving healthcare practices. While AI has shown promise in assisting doctors with early symptom detection from medical images, there is a critical need to prioritize patient safety by enhancing existing processes. To enhance patient safety, this study focuses on improving the medical operation process during X-ray examinations. In this study, we utilize EfficientNet for classifying the 49 categories of pre-X-ray images. To enhance the accuracy even further, we introduce two novel Neural Network architectures. The classification results are then compared with the doctor's order to ensure consistency and minimize discrepancies. To evaluate the effectiveness of the proposed models, a comprehensive dataset comprising 49 different categories and over 12,000 training and testing sheets was collected from Taichung Veterans General Hospital. The research demonstrates a significant improvement in accuracy, surpassing a 4% enhancement compared to previous studies. [ABSTRACT FROM AUTHOR]

The study of managing risk in aviation is the key to improving flight safety. Compared to the other flight operation phases, the approach and landing phases are more critical and dangerous. This study aims to detect and analyze unstable approaches in Taiwan through historical flight data. In addition to weather factors such as low visibility and crosswinds, human factors also account for a large part of the risk. From the accidents studied in the stochastic report of the Flight Safety Foundation, nearly 70% of the accidents occurred during the approach and landing phases, which were caused by improper control of aircraft energy. Since the information of the flight data recorder (FDR) is regarded as the airline's confidential information, this study calculates the aircraft's energy-related metrics and investigates the influence of non-weather-related factors on unstable approaches through a publicly available source, automatic dependent surveillance-broadcast (ADS-B) flight data. To evaluate the influence of weather- and non-weather-related factors, the outliers of each group classified by weather labels are detected and eliminated from the analysis by applying hierarchical density-based spatial clustering of applications with noise (HDBSCAN), which is utilized for detecting abnormal flights that are spatial anomalies. The deep learning method was adopted to detect and predict unstable arrival flights landing at Taipei Songshan Airport. The accuracy of the prediction for the normalized total energy and trajectory deviation of all flights is 85.15% and 82.11%, respectively. The results show that in different kinds of weather conditions, or not considering the weather, the models have similar good performance. The input features were analyzed after the model was obtained, and the flights detected as abnormal are discussed. [ABSTRACT FROM AUTHOR]

As a result of the increasing use of artificial intelligence technology in transportation, numerous real-time crash prediction techniques have been developed. In the context of highway traffic management, machine learning models and classifiers are used to analyze electronic toll collection (ETC) and vehicle detector (VD) data to predict crash occurrences. However, traffic accidents are influenced by multiple factors, such as traffic speed differences, traffic density, and weather conditions, and direct associations may not exist between sensor data and crash incidents. Therefore, data integration and association methods must be used to examine ETC and VD data through traffic flow theories, to extract key data from datasets and to facilitate model training. In this study, a data association method and framework combined with deep learning was proposed to construct a crash prediction and warning model for national highways in Taiwan. The results revealed a model accuracy of 94%, indicating that the model had a low error rate and was suitable for the prediction of traffic accidents. Overall, this study provides referential data for the Freeway Bureau of Taiwan to conduct comprehensive assessments and develop strategies for crash prevention. [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]

Taiwan's economy mainly relies on the export of agricultural products. If even the suspicion of a pest is found in the crop products after they are exported, not only are the agricultural products returned but the whole batch of crops is destroyed, resulting in extreme crop losses. The species of mealybugs, Coccidae, and Diaspididae, which are the primary pests of the scale insect in Taiwan, can not only lead to serious damage to the plants but also severely affect agricultural production. Hence, to recognize the scale pests is an important task in Taiwan's agricultural field. In this study, we propose an AI-based pest detection system for solving the specific issue of detection of scale pests based on pictures. Deep-learning-based object detection models, such as faster region-based convolutional networks (Faster R-CNNs), single-shot multibox detectors (SSDs), and You Only Look Once v4 (YOLO v4), are employed to detect and localize scale pests in the picture. The experimental results show that YOLO v4 achieved the highest classification accuracy among the algorithms, with 100% in mealybugs, 89% in Coccidae, and 97% in Diaspididae. Meanwhile, the computational performance of YOLO v4 has indicated that it is suitable for real-time application. Moreover, the inference results of the YOLO v4 model further help the end user. A mobile application using the trained scale pest recognition model has been developed to facilitate pest identification in farms, which is helpful in applying appropriate pesticides to reduce crop losses. [ABSTRACT FROM AUTHOR]

Airborne particulate matter 2.5 (PM2.5) can have a profound effect on the health of the population. Many researchers have been reporting highly accurate numerical predictions based on raw PM2.5 data imported directly into deep learning models; however, there is still considerable room for improvement in terms of implementation costs due to heavy computational overhead. From the perspective of environmental science, PM2.5 values in a given location can be attributed to local sources as well as external sources. Local sources tend to have a dramatic short-term impact on PM2.5 values, whereas external sources tend to have more subtle but longer-lasting effects. In the presence of PM2.5 from both sources at the same time, this combination of effects can undermine the predictive accuracy of the model. This paper presents a novel combinational Hammerstein recurrent neural network (CHRNN) to enhance predictive accuracy and overcome the heavy computational and monetary burden imposed by deep learning models. The CHRNN comprises a based-neural network tasked with learning gradual (long-term) fluctuations in conjunction with add-on neural networks to deal with dramatic (short-term) fluctuations. The CHRNN can be coupled with a random forest model to determine the degree to which short-term effects influence long-term outcomes. We also developed novel feature selection and normalization methods to enhance prediction accuracy. Using real-world measurement data of air quality and PM2.5 datasets from Taiwan, the precision of the proposed system in the numerical prediction of PM2.5 levels was comparable to that of state-of-the-art deep learning models, such as deep recurrent neural networks and long short-term memory, despite far lower implementation costs and computational overhead. [ABSTRACT FROM AUTHOR]

The number of people suffering from diabetes in Taiwan has continued to rise in recent years. According to the statistics of the International Diabetes Federation, about 537 million people worldwide (10.5% of the global population) suffer from diabetes, and it is estimated that 643 million people will develop the condition (11.3% of the total population) by 2030. If this trend continues, the number will jump to 783 million (12.2%) by 2045. At present, the number of people with diabetes in Taiwan has reached 2.18 million, with an average of one in ten people suffering from the disease. In addition, according to the Bureau of National Health Insurance in Taiwan, the prevalence rate of diabetes among adults in Taiwan has reached 5% and is increasing each year. Diabetes can cause acute and chronic complications that can be fatal. Meanwhile, chronic complications can result in a variety of disabilities or organ decline. If holistic treatments and preventions are not provided to diabetic patients, it will lead to the consumption of more medical resources and a rapid decline in the quality of life of society as a whole. In this study, based on the outpatient examination data of a Taipei Municipal medical center, 15,000 women aged between 20 and 80 were selected as the subjects. These women were patients who had gone to the medical center during 2018–2020 and 2021–2022 with or without the diagnosis of diabetes. This study investigated eight different characteristics of the subjects, including the number of pregnancies, plasma glucose level, diastolic blood pressure, sebum thickness, insulin level, body mass index, diabetes pedigree function, and age. After sorting out the complete data of the patients, this study used Microsoft Machine Learning Studio to train the models of various kinds of neural networks, and the prediction results were used to compare the predictive ability of the various parameters for diabetes. Finally, this study found that after comparing the models using two-class logistic regression as well as the two-class neural network, two-class decision jungle, or two-class boosted decision tree for prediction, the best model was the two-class boosted decision tree, as its area under the curve could reach a score of 0.991, which was better than other models. [ABSTRACT FROM AUTHOR]

Automatic peer-to-peer energy trading can be defined as a Markov decision process and designed using deep reinforcement learning. We consider prosumer as an entity that consumes and produces electric energy with an energy storage system, and define the prosumer's objective as maximizing the profit through participation in peer-to-peer energy trading, similar to that of the agents in stock trading. In this paper, we propose an automatic peer-to-peer energy trading model by adopting a deep Q-network-based automatic trading algorithm originally designed for stock trading. Unlike in stock trading, the assets held by a prosumer may change owing to factors such as the consumption and generation of energy by the prosumer in addition to the changes from trading activities. Therefore, we propose a new trading evaluation criterion that considers these factors by defining profit as the sum of the gains from four components: electricity bill, trading, electric energy stored in the energy storage system, and virtual loss. For the proposed automatic peer-to-peer energy trading algorithm, we adopt a long-term delayed reward method that evaluates the delayed reward that occurs once per month by generating the termination point of an episode at each month and propose a long short-term delayed reward method that compensates for the issue with the long-term delayed reward method having only a single evaluation per month. This long short-term delayed reward method enables effective learning of the monthly long-term trading patterns and the short-term trading patterns at the same time, leading to a better trading strategy. The experimental results showed that the long short-term delayed reward method-based energy trading model achieves higher profits every month both in the progressive and fixed rate systems throughout the year and that prosumer participating in the trading not only earns profits every month but also reduces loss from over-generation of electric energy in the case of South Korea. Further experiments with various progressive rate systems of Japan, Taiwan, and the United States as well as in different prosumer environments indicate the general applicability of the proposed method. [ABSTRACT FROM AUTHOR]

The complex and extensive mechanism of landslides and their direct connection to climate change have turned these hazards into critical events on a global scale, which can have significant negative influences on the long-term sustainable development of nations. Taiwan experiences numerous landslides on different scales almost every year. However, Typhoon Morakot (2009), with large-scale landslides that trapped people, demonstrated the importance of an early warning system. The absence of an effective warning system for landslides along with the impossibility of its accurate monitoring highlighted the necessity of landslide rainfall threshold prediction. Accordingly, the prediction of the landslide rainfall threshold as an early warning system could be an effective tool with which to develop an emergency evacuation protocol. The purpose of this study is to present the capability of the deep learning algorithm to determine the distribution of landslide rainfall thresholds in a potential large-scale landslide area and to assess the distribution of recurrence intervals using probability density functions, as well as to assist decision makers in early responses to landslides and reduce the risk of large-scale landslides. Therefore, the algorithm was developed for one of the potential large-scale landslide areas (the Alishan D098 sub-basin), Taiwan, which is classified as a Type II Landslide Priority Area. The historical landslide data, maximum daily rainfall, 11 topographic factors from 2004 to 2017, and the Keras application programming interface (API) python library were used to develop two deep learning models for landslide susceptibility classification and landslide rainfall threshold regression. The predicted result shows the lowest landslide rainfall threshold is located primarily in the northeastern downstream of the Alishan catchment, which poses an extreme risk to the residential area located upstream of the landslide area, particularly if large-scale landslides were to be triggered upstream of Alishan. The landslide rainfall threshold under controlled conditions was estimated at 780 mm/day (20-year recurrence interval), or 820 mm/day (25-year recurrence interval). Since the frequency of extreme rainfall events caused by climate change is expected to rise in the future, the overall landslide rainfall threshold was considered 980 mm/day for the entire area. [ABSTRACT FROM AUTHOR]

Modern space missions provide a great number of height profiles of ionospheric electron density, measured by the remote sensing technique of radio occultation (RO). The deducing of the profiles from the RO measurements suffers from bias, resulting in negative values of the electron density. We developed a machine learning technique that allows automatic identification of ionospheric layers and avoids the bias problem. An algorithm of convolutional neural networks was applied for the classification of the height profiles. Six classes of the profiles were distinguished on the base of prominent ionospheric layers F2, Es, E, F1 and F3, as well as distorted profiles (Sc). For the models, we selected the ground truth of more than 712 height profiles measured by the COSMIC/Formosat-3 mission above Taiwan from 2011 to 2013. Two different models, a 1D convolutional neural network (CNN) and fully convolutional network (FCN), were applied for classification. It was found that both models demonstrate the best classification performance, with the average accuracy around 0.8 for prediction of the F2 layer-related class and the E layer-related class. The F1 layer is classified by the models with good performance (>0.7). The CNN model can effectively classify the Es layer with an accuracy of 0.75. The FCN model has good classification performance (0.72) for the Sc-related profiles. The lowest performance (<0.4) was found for the F3 layer-related class. It was shown that the more complex FCN model has better classification performance for both large-scale and small-scale variations in the height profiles of the ionospheric electron density. [ABSTRACT FROM AUTHOR]

The advancement of the Internet has changed people's ways of expressing and sharing their views with the world. Moreover, user-generated content has become a primary guide for customer purchasing decisions. Therefore, motivated by commercial interest, some sellers have started manipulating Internet ratings by writing false positive reviews to encourage the sale of their goods and writing false negative reviews to discredit competitors. These reviews are generally referred to as deceptive reviews. Deceptive reviews mislead customers in purchasing goods that are inconsistent with online information and thus obstruct fair competition among businesses. To protect the right of consumers and sellers, an effective method is required to automate the detection of misleading reviews. Previously developed methods of translating text into feature vectors usually fail to interpret polysemous words, which leads to such functions being obstructed. By using dynamic feature vectors, the present study developed several misleading review-detection models for the Chinese language. The developed models were then compared with the standard detection-efficiency models. The deceptive reviews collected from various online forums in Taiwan by previous studies were used to test the models. The results showed that the models proposed in this study can achieve 0.92 in terms of precision, 0.91 in terms of recall, and 0.91 in terms of F1-score. The improvement rate of our proposal is higher than 20%. Accordingly, we prove that our proposal demonstrated improved performance in detecting misleading reviews, and the models based on dynamic feature vectors were capable of more accurately capturing semantic terms than the conventional models based on the static feature vectors, thereby enhancing effectiveness. [ABSTRACT FROM AUTHOR]

The automotive industry is the leading producer of machines in Taiwan and worldwide. Developing effective methods for forecasting car sales can allow car companies to arrange their production and sales plans. Capitalizing on the growth of social media and deep learning algorithms, this research aimed to improve the overall performance of the forecasting of Taiwan car sales movement direction forecasting by using online sentiment data and CNN-LSTM method. First, the historical sales volumes and multi-channel online sentiment data for six car brands in Taiwan were collected and preprocessed for labeling of car sales movement direction. Then, three models, namely, the classical, sentimental, and CNN-LSTM models, were constructed and trained/fitted for forecasting car sales movement directions in Taiwan. Finally, the performance of the three prediction models were compared to verify the effects of online sentiment data and the CNN-LSTM model on forecasting performance. The results showed that four forecasting performance indices, i.e., accuracy, precision, recall and F1-score, improved by 27.78% (from 41.67% to 69.45%), 0.39 (from 0.38 to 0.77), 0.27 (from 0.42 to 0.69) and 0.33 (from 0.35 to 0.68), respectively. Therefore, the online sentiment data and CNN-LSTM method can indeed improve the overall performance of car sales movement direction in Taiwan. [ABSTRACT FROM AUTHOR]

Trap-neuter-return (TNR) has become an effective solution to reduce the prevalence of stray animals. Due to the non-culling policy for stray cats and dogs since 2017, there is a great demand for the sterilization of cats and dogs in Taiwan. In 2020, Heart of Taiwan Animal Care (HOTAC) had more than 32,000 cases of neutered cats and dogs. HOTAC needs to take pictures to record the ears and excised organs of each neutered cat or dog from different veterinary hospitals. The correctness of the archived medical photos and the different shooting and imaging angles from different veterinary hospitals must be carefully reviewed by human professionals. To reduce the cost of manual review, Yolo's ensemble learning based on deep learning and a majority voting system can effectively identify TNR surgical images, save 80% of the labor force, and its average accuracy (mAP) exceeds 90%. The best feature extraction based on the Yolo model is Yolov4, whose mAP reaches 91.99%, and the result is integrated into the voting classification. Experimental results show that compared with the previous manual work, it can decrease the workload by more than 80%. [ABSTRACT FROM AUTHOR]

Road surfaces in Taiwan, as well as other developed countries, often experience structural failures, such as patches, bumps, longitudinal and lateral cracking, and potholes, which cause discomfort and pose direct safety risks to motorists. To minimize damage to vehicles from pavement defects or provide the corresponding comfortable ride promotion strategy later, in this study, we developed a pavement defect detection system using a deep learning perception scheme for implementation on Xilinx Edge AI platforms. To increase the detection distance and accuracy of pavement defects, two cameras with different fields of view, at 70 ∘ and 30 ∘ , respectively, were used to capture the front views of a car, and then the YOLOv3 (you only look once, version 3) model was employed to recognize the pavement defects, such as potholes, cracks, manhole covers, patches, and bumps. In addition, to promote continuous pavement defect recognition rate, a tracking-via-detection strategy was employed, which first detects pavement defects in each frame and then associates them to different frames using the Kalman filter method. Thus, the average detection accuracy of the pothole category could reach 71%, and the miss rate was about 29%. To confirm the effectiveness of the proposed detection strategy, experiments were conducted on an established Taiwan pavement defect image dataset (TPDID), which is the first dataset for Taiwan pavement defects. Moreover, different AI methods were used to detect the pavement defects for quantitative comparative analysis. Finally, a field-programmable gate-array-based edge computing platform was used as an embedded system to implement the proposed YOLOv3-based pavement defect detection system; the execution speed reached 27.8 FPS while maintaining the accuracy of the original system model. [ABSTRACT FROM AUTHOR]

In Taiwan, mushrooms are an agricultural product with high nutritional value and economic benefit. However, global warming and climate change have affected plant quality. As a result, technological greenhouses are replacing traditional tin houses as locations for mushroom planting. These greenhouses feature several complex parameters. If we can reduce the complexity such greenhouses and improve the efficiency of their production management using intelligent schemes, technological greenhouses could become the expert assistants of farmers. In this paper, the main goal of the developed system is to measure the mushroom size and to count the amount of mushrooms. According to the results of each measurement, the growth rate of the mushrooms can be estimated. The proposed system also records the data of the mushrooms and broadcasts them to the mobile phone of the farmer. This improves the effectiveness of the production management. The proposed system is based on the convolutional neural network of deep learning, which is used to localize the mushrooms in the image. A positioning correction method is also proposed to modify the localization result. The experiments show that the proposed system has a good performance concerning the image measurement of mushrooms. [ABSTRACT FROM AUTHOR]

(1) Background: The role of using artificial intelligence (AI) with electrocardiograms (ECGs) for the diagnosis of significant coronary artery disease (CAD) is unknown. We first tested the hypothesis that using AI to read ECG could identify significant CAD and determine which vessel was obstructed. (2) Methods: We collected ECG data from a multi-center retrospective cohort with patients of significant CAD documented by invasive coronary angiography and control patients in Taiwan from 1 January 2018 to 31 December 2020. (3) Results: We trained convolutional neural networks (CNN) models to identify patients with significant CAD (>70% stenosis), using the 12,954 ECG from 2303 patients with CAD and 2090 ECG from 1053 patients without CAD. The Marco-average area under the ROC curve (AUC) for detecting CAD was 0.869 for image input CNN model. For detecting individual coronary artery obstruction, the AUC was 0.885 for left anterior descending artery, 0.776 for right coronary artery, and 0.816 for left circumflex artery obstruction, and 1.0 for no coronary artery obstruction. Marco-average AUC increased up to 0.973 if ECG had features of myocardial ischemia. (4) Conclusions: We for the first time show that using the AI-enhanced CNN model to read standard 12-lead ECG permits ECG to serve as a powerful screening tool to identify significant CAD and localize the coronary obstruction. It could be easily implemented in health check-ups with asymptomatic patients and identifying high-risk patients for future coronary events. [ABSTRACT FROM AUTHOR]

The prediction of stocks is complicated by the dynamic, complex, and chaotic environment of the stock market. Investors put their money into the financial market, hoping to maximize profits by understanding market trends and designing trading strategies at the entry and exit points. Most studies propose machine learning models to predict stock prices. However, constructing trading strategies is helpful for traders to avoid making mistakes and losing money. We propose an automatic trading framework using LSTM combined with deep Q-learning to determine the trading signal and the size of the trading position. This is more sophisticated than traditional price prediction models. This study used price data from the Taiwan stock market, including daily opening price, closing price, highest price, lowest price, and trading volume. The profitability of the system was evaluated using a combination of different states of different stocks. The profitability of the proposed system was positive after a long period of testing, which means that the system performed well in predicting the rise and fall of stocks. [ABSTRACT FROM AUTHOR]

The technique of active ionospheric sounding by ionosondes requires sophisticated methods for the recovery of experimental data on ionograms. In this work, we applied an advanced algorithm of deep learning for the identification and classification of signals from different ionospheric layers. We collected a dataset of 6131 manually labeled ionograms acquired from low-latitude ionosondes in Taiwan. In the ionograms, we distinguished 11 different classes of the signals according to their ionospheric layers. We developed an artificial neural network, FC-DenseNet24, based on the FC-DenseNet convolutional neural network. We also developed a double-filtering algorithm to reduce incorrectly classified signals. That made it possible to successfully recover the sporadic E layer and the F2 layer from highly noise-contaminated ionograms whose mean signal-to-noise ratio was low, SNR = 1.43. The Intersection over Union (IoU) of the recovery of these two signal classes was greater than 0.6, which was higher than the previous models reported. We also identified three factors that can lower the recovery accuracy: (1) smaller statistics of samples; (2) mixing and overlapping of different signals; (3) the compact shape of signals. [ABSTRACT FROM AUTHOR]

The need for accurate tourism demand forecasting is widely recognized. The unreliability of traditional methods makes tourism demand forecasting still challenging. Using deep learning approaches, this study aims to adapt Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Gated Recurrent Unit networks (GRU), which are straightforward and efficient, to improve Taiwan's tourism demand forecasting. The networks are able to seize the dependence of visitor arrival time series data. The Adam optimization algorithm with adaptive learning rate is used to optimize the basic setup of the models. The results show that the proposed models outperform previous studies undertaken during the Severe Acute Respiratory Syndrome (SARS) events of 2002–2003. This article also examines the effects of the current COVID-19 outbreak to tourist arrivals to Taiwan. The results show that the use of the LSTM network and its variants can perform satisfactorily for tourism demand forecasting. [ABSTRACT FROM AUTHOR]

Taiwan is an island, and its economic activities are primarily dependent on maritime transport and international trade. However, Taiwan is also located in the region of typhoon development in the Northwestern Pacific Basin. Thus, it frequently receives strong winds and large waves brought by typhoons, which pose a considerable threat to port operations. To determine the real-time status of winds and waves brought by typhoons near the coasts of major ports in Taiwan, this study developed models for predicting the wind speed and wave height near the coasts of ports during typhoon periods. The forecasting horizons range from 1 to 6 h. In this study, the gated recurrent unit (GRU) neural networks and convolutional neural networks (CNNs) were combined and adopted to formulate the typhoon-induced wind and wave height prediction models. This work designed two wind speed prediction models (WIND-1 and WIND-2) and four wave height prediction models (WAVE-1 to WAVE-4), which are based on the WIND-1 and WIND-2 model outcomes. The Longdong and Liuqiu Buoys were the experiment locations. The observatory data from the ground stations and buoys, as well as radar reflectivity images, were adopted. The results indicated that, first, WIND-2 has a superior wind speed prediction performance to WIND-1, where WIND-2 can be used to identify the temporal and spatial changes in wind speeds using ground station data and reflectivity images. Second, WAVE-4 has the optimal wave height prediction performance, followed by WAVE-3, WAVE-2, and WAVE-1. The results of WAVE-4 revealed using the designed models with in-situ and reflectivity data directly yielded optimal predictions of the wind-based wave heights. Overall, the results indicated that the presented combination models were able to extract the spatial image features using multiple convolutional and pooling layers and provide useful information from time-series data using the GRU memory cell units. Overall, the presented models could exhibit promising results. [ABSTRACT FROM AUTHOR]

The chicken industry, in which broiler chickens are bred, is the largest poultry industry in Taiwan. In a traditional poultry house, breeders must usually observe the health of the broilers in person on the basis of their breeding experience at regular times every day. When a breeder finds unhealthy broilers, they are removed manually from the poultry house to prevent viruses from spreading in the poultry house. Therefore, in this study, we designed and constructed a novel small removal system for dead chickens for Taiwanese poultry houses. In the mechanical design, this system mainly contains walking, removal, and storage parts. It comprises robotic arms with a fixed end and sweep-in devices for sweeping dead chickens, a conveyor belt for transporting chickens, a storage cache for storing chickens, and a tracked vehicle. The designed system has dimensions of approximately 1.038 × 0.36 × 0.5 m3, and two dead chickens can be removed in a single operation. The walking speed of the chicken removal system is 3.3 cm/s. In order to enhance the automation and artificial intelligence in the poultry industry, the identification system was used in a novel small removal system. The conditions of the chickens in a poultry house can be monitored remotely by using a camera, and dead chickens can be identified through deep learning based on the YOLO v4 algorithm. The precision of the designed system reached 95.24% in this study, and dead chickens were successfully moved to the storage cache. Finally, the designed system can reduce the contact between humans and poultry to effectively improve the overall biological safety. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) represents a heavy burden on the healthcare system because of the increasing number of patients, high risk of progression to end-stage renal disease, and poor prognosis of morbidity and mortality. The aim of this study is to develop a machine-learning model that uses the comorbidity and medication data obtained from Taiwan's National Health Insurance Research Database to forecast the occurrence of CKD within the next 6 or 12 months before its onset, and hence its prevalence in the population. A total of 18,000 people with CKD and 72,000 people without CKD diagnosis were selected using propensity score matching. Their demographic, medication and comorbidity data from their respective two-year observation period were used to build a predictive model. Among the approaches investigated, the Convolutional Neural Networks (CNN) model performed best with a test set AUROC of 0.957 and 0.954 for the 6-month and 12-month predictions, respectively. The most prominent predictors in the tree-based models were identified, including diabetes mellitus, age, gout, and medications such as sulfonamides and angiotensins. The model proposed in this study could be a useful tool for policymakers in predicting the trends of CKD in the population. The models can allow close monitoring of people at risk, early detection of CKD, better allocation of resources, and patient-centric management. [ABSTRACT FROM AUTHOR]

Because of the financial information asymmetry, the stakeholders usually do not know a company's real financial condition until financial distress occurs. Financial distress not only influences a company's operational sustainability and damages the rights and interests of its stakeholders, it may also harm the national economy and society; hence, it is very important to build high-accuracy financial distress prediction models. The purpose of this study is to build high-accuracy and effective financial distress prediction models by two representative deep learning algorithms: Deep neural networks (DNN) and convolutional neural networks (CNN). In addition, important variables are selected by the chi-squared automatic interaction detector (CHAID). In this study, the data of Taiwan's listed and OTC sample companies are taken from the Taiwan Economic Journal (TEJ) database during the period from 2000 to 2019, including 86 companies in financial distress and 258 not in financial distress, for a total of 344 companies. According to the empirical results, with the important variables selected by CHAID and modeling by CNN, the CHAID-CNN model has the highest financial distress prediction accuracy rate of 94.23%, and the lowest type I error rate and type II error rate, which are 0.96% and 4.81%, respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer is the leading cause of death in Taiwan. Compared with other types of cancer, the incidence of lung cancer is high. In this study, the National Health In-surance Research Database (NHIRDB) was used to determine the diseases and symptoms associ-ated with lung cancer, and a 10-year probability deep neural network prediction model for lung cancer was developed. The proposed model could allow patients with a high risk of lung cancer to receive an earlier diagnosis and support the physicians' clinical decision-making. As a result, a total of 13 diseases were selected as the predicting factors. The proposed model showed an accuracy of 85.4%, a sensitivity of 72.4% and a specificity of 85%, as well as an 87.4% area under ROC (95%, 0.8604–0.8885) model precision. Based on data analysis and deep learning, our prediction model discovered some features that had not been previously identified by clinical knowledge. This study tracks a decade of clinical diagnostic records to identify possible symptoms and comorbidities of lung cancer, allows early prediction of the disease, and assists more patients with early diagnosis. Cancer is the leading cause of death in Taiwan. According to the Cancer Registration Report of Taiwan's Ministry of Health and Welfare, a total of 13,488 people suffered from lung cancer in 2016, making it the second-most common cancer and the leading cancer in men. Compared with other types of cancer, the incidence of lung cancer is high. In this study, the National Health Insurance Research Database (NHIRDB) was used to determine the diseases and symptoms associated with lung cancer, and a 10-year probability deep neural network prediction model for lung cancer was developed. The proposed model could allow patients with a high risk of lung cancer to receive an earlier diagnosis and support the physicians' clinical decision-making. The study was designed as a cohort study. The subjects were patients who were diagnosed with lung cancer between 2000 and 2009, and the patients' disease histories were back-tracked for a period, extending to ten years before the diagnosis of lung cancer. As a result, a total of 13 diseases were selected as the predicting factors. A nine layers deep neural network model was created to predict the probability of lung cancer, depending on the different pre-diagnosed diseases, and to benefit the earlier detection of lung cancer in potential patients. The model is trained 1000 times, the batch size is set to 100, the SGD (Stochastic gradient descent) optimizer is used, the learning rate is set to 0.1, and the momentum is set to 0.1. The proposed model showed an accuracy of 85.4%, a sensitivity of 72.4% and a specificity of 85%, as well as an 87.4% area under ROC (AUROC) (95%, 0.8604–0.8885) model precision. Based on data analysis and deep learning, our prediction model discovered some features that had not been previously identified by clinical knowledge. This study tracks a decade of clinical diagnostic records to identify possible symptoms and comorbidities of lung cancer, allows early prediction of the disease, and assists more patients with early diagnosis. [ABSTRACT FROM AUTHOR]

To precisely forecast downstream water levels in catchment areas during typhoons, the deep learning artificial neural networks were employed to establish two water level forecasting models using sequential neural networks (SNNs) and multiple-input functional neural networks (MIFNNs). SNNs, which have a typical neural network structure, are network models constructed using sequential methods. To develop a network model capable of flexibly consolidating data, MIFNNs are employed for processing data from multiple sources or with multiple dimensions. Specifically, when images (e.g., radar reflectivity images) are used as input attributes, feature extraction is required to provide effective feature maps for model training. Therefore, convolutional layers and pooling layers were adopted to extract features. Long short-term memory (LSTM) layers adopted during model training enabled memory cell units to automatically determine the memory length, providing more useful information. The Hsintien River basin in northern Taiwan was selected as the research area and collected relevant data from 2011 to 2019. The input attributes comprised one-dimensional data (e.g., water levels at river stations, rain rates at rain gauges, and reservoir release) and two-dimensional data (i.e., radar reflectivity mosaics). Typhoons Saola, Soudelor, Dujuan, and Megi were selected, and the water levels 1 to 6 h after the typhoons struck were forecasted. The results indicated that compared with linear regressions (REG), SNN using dense layers (SNN-Dense), and SNN using LSTM layers (SNN-LSTM) models, superior forecasting results were achieved for the MIFNN model. Thus, the MIFNN model, as the optimal model for water level forecasting, was identified. [ABSTRACT FROM AUTHOR]

Forecasting the demand for container throughput is a critical indicator to measure the development level of a port in global business management and industrial development. Time-series analysis approaches are crucial techniques for forecasting the demand for container throughput. However, accurate demand forecasting for container throughput remains a challenge in time-series analysis approaches. In this study, we proposed a mixed-precision neural architecture to forecasting the demand for container throughput. This study is the first work to use a mixed-precision neural network to forecast the container throughput—the mixed-precision architecture used the convolutional neural network for learning the strength of the features and used long short-term memory to identify the crucial internal representation of time series depending on the strength of the features. The experiments on the demand for container throughput of the five ports in Taiwan were conducted to compare our deep learning architecture with other forecasting approaches. The results indicated that our mixed-precision neural architecture exhibited higher forecasting performance than classic machine learning approaches, including adaptive boosting, random forest regression, and support vector regression. The proposed architecture can effectively predict the demand for port container throughput and effectively reduce the costs of planning and development of ports in the future. [ABSTRACT FROM AUTHOR]

A scheme for wind-speed simulation during typhoons in Taiwan is highly desirable, considering the effects of the powerful winds accompanying the severe typhoons. The developed combination of deep learning (DL) algorithms with a weather-forecasting numerical model can be used to determine wind speed in a rapid simulation process. Here, the Weather Research and Forecasting (WRF) numerical model was employed as the numerical simulation-based model for precomputing solutions to determine the wind velocity at arbitrary positions where the wind cannot be measured. The deep neural network (DNN) was used for constructing the DL-based wind-velocity simulation model. The experimental area of Northern Taiwan was used for the simulation. Regarding the complex typhoon system, the collected data comprised the typhoon tracks, FNL (Final) Operational Global Analysis Data for the WRF model, typhoon characteristics, and ground weather data. This study included 47 typhoon events that occurred over 2000–2017. Three measures were used to analyze the models for identifying optimal performance levels: Mean absolute error, root mean squared error, and correlation coefficient. This study compared observations with the WRF numerical model and DNN model. The results revealed that (1) simulations by using the WRF-based models were satisfactorily consistent with the observed data and (2) simulations by using the DNN model were considerably consistent with those of the WRF-based model. Consequently, the proposed DNN combined with WRF model can be effectively used in simulations of wind velocity at arbitrary positions of study area. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) offers the most detailed brain structure image available today; it can identify tiny lesions or cerebral cortical abnormalities. The primary purpose of the procedure is to confirm whether there is structural variation that causes epilepsy, such as hippocampal sclerotherapy, local cerebral cortical dysplasia, and cavernous hemangioma. Cerebrovascular disease, the second most common factor of death in the world, is also the fourth leading cause of death in Taiwan, with cerebrovascular disease having the highest rate of stroke. Among the most common are large vascular atherosclerotic lesions, small vascular lesions, and cardiac emboli. The purpose of this thesis is to establish a computer-aided diagnosis system based on small blood vessel lesions in MRI images, using the method of Convolutional Neural Network and deep learning to analyze brain vascular occlusion by analyzing brain MRI images. Blocks can help clinicians more quickly determine the probability and severity of stroke in patients. We analyzed MRI data from 50 patients, including 30 patients with stroke, 17 patients with occlusion but no stroke, and 3 patients with dementia. This system mainly helps doctors find out whether there are cerebral small vessel lesions in the brain MRI images, and to output the found results into labeled images. The marked contents include the position coordinates of the small blood vessel blockage, the block range, the area size, and if it may cause a stroke. Finally, all the MRI images of the patient are synthesized, showing a 3D display of the small blood vessels in the brain to assist the doctor in making a diagnosis or to provide accurate lesion location for the patient. [ABSTRACT FROM AUTHOR]