Search

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]

Due to the increasing cost of health insurance, for decades, many countries have endeavored to constrain the cost of insurance by utilizing a DRG payment system. In most cases, under the DRG payment system, hospitals cannot exactly know which DRG code inpatients are until they are discharged. This paper focuses on the prediction of what DRG code appendectomy patients will be classified with when they are admitted to hospital. We utilize two models (or classifiers) constructed using the C4.5 algorithm and back-propagation neural network (BPN). We conducted experiments with the data collected from two hospitals. The results show that the accuracies of these two classification models can be up to 97.84% and 98.70%, respectively. According to the predicted DRG code, hospitals can effectively arrange medical resources with certainty, then, in turn, improve the quality of the medical care patients receive. [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]

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]

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]

Research background: The global financial crisis from 2007 to 2012, the COVID-19 pandemic, and the current war in Ukraine have dramatically increased the risk of consumer bankruptcies worldwide. All three crises negatively impact the financial situation of households due to increased interest rates, inflation rates, volatile exchange rates, and other significant macroeconomic factors. Financial difficulties may arise when the private person is unable to maintain a habitual standard of living. This means that anyone can become financially vulnerable regardless of wealth or education level. Therefore, forecasting consumer bankruptcy risk has received increasing scientific and public attention. Purpose of the article: This study proposes artificial intelligence solutions to address the increased importance of the personal bankruptcy phenomenon and the growing need for reliable forecasting models. The objective of this paper is to develop six models for forecasting personal bankruptcies in Poland and Taiwan with the use of three soft-computing techniques. Methods: Six models were developed to forecast the risk of insolvency: three for Polish households and three for Taiwanese consumers, using fuzzy sets, genetic algorithms, and artificial neural networks. This research relied on four samples. Two were learning samples (one for each country), and two were testing samples, also one for each country separately. Both testing samples contain 500 bankrupt and 500 nonbankrupt households, while each learning sample consists of 100 insolvent and 100 solvent natural persons. Findings & value added: This study presents a solution for effective bankruptcy risk forecasting by implementing both highly effective and usable methods and proposes a new type of ratios that combine the evaluated consumers' financial and demographic characteristics. The usage of such ratios also improves the versatility of the presented models, as they are not denominated in monetary value or strictly in demographic units. This would be limited to use in only one country but can be widely used in other regions of the world. [ABSTRACT FROM AUTHOR]

Liquefaction is one of the disasters caused due to earthquake. In 1999, Chi-Chi, Taiwan, earthquake is an example of liquefaction prone disasters induced due to Mw 7.6 earthquake. This becomes major cause for prediction of the liquefaction in the soil with respect to geotechnical property. In this paper, we have use Artificial Neural Networks (ANN) model based on Resilient Back propagation (Rprop), Decision tree model (DT) and classifier are C 4.5 and Random Forest is done for comparing the performance and evaluation of liquefaction potential based on the obtained field CPT data (Juang et al. [1]) consisting 125 datasets over the simplified procedures that are being traditionally use for the classification of liquefaction of the soil by different researchers. It is observe that Resilient Back propagation Algorithm prediction is 100% whereas C 4.5 algorithm and Random forest Algorithm are 97.6% and 98.4% accurate for the evaluation of seismic soil liquefaction potential. [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]

Objective. The Fugl-Meyer assessment for upper extremity (FMA-UE) is a measure for assessing upper extremity motor function in patients with stroke. However, the considerable administration time of the assessment decreases its feasibility. This study aimed to develop an accumulative assessment system of upper extremity motor function (AAS-UE) based on the FMA-UE to improve administrative efficiency while retaining sufficient psychometric properties. Methods. The study used secondary data from 3 previous studies having FMA-UE datasets, including 2 follow-up studies for subacute stroke individuals and 1 test-retest study for individuals with chronic stroke. The AAS-UE adopted deep learning algorithms to use patients' prior information (ie, the FMA-UE scores in previous assessments, time interval of adjacent assessments, and chronicity of stroke) to select a short and personalized item set for the following assessment items and reproduce their FMA-UE scores. Results. Our data included a total of 682 patients after stroke. The AAS-UE administered 10 different items for each patient. The AAS-UE demonstrated good concurrent validity (r =0.97-0.99 with the FMA-UE), high test-retest reliability (intra-class correlation coefficient=0.96), low random measurement error (percentage of minimal detectable change=15.6%), good group-level responsiveness (standardized response mean=0.65-1.07), and good individual-level responsiveness (30.5%-53.2% of patients showed significant improvement). These psychometric properties were comparable to those of the FMA-UE. Conclusion. The AAS-UE uses an innovative assessment method, which makes good use of patients' prior information to achieve administrative efficiency with good psychometric properties. Impact. This study demonstrates a new assessment method to improve administrative efficiency while retaining psychometric properties, especially individual-level responsiveness and random measurement error, by making good use of patients' basic information and medical records. [ABSTRACT FROM AUTHOR]

Introduction: This study used artificial intelligence and strategic management to predict sports industry development in Taiwan. Through public government information, we aimed to determine the dynamics of the sports industry and analyze the current situation of domestic sports industries and sports industry sectors. We also explored national sports policies and development issues to construct a Taiwan Sports Industry Gross Domestic Product Forecasting Model that aligns with the requirements of government agencies and the sports industry. Methods: This study explored time series data for 12 sports industries and 40 sports industry sectors from 2009 to 2018. We used artificial neural networks to predict future gross domestic product (GDP). We also used the moving average method to calculate the trend direction and used strategic management and brand positioning analysis to analyze industry positioning and trend development. Results: Only one sports industry, Sports Venue or Facility Construction, had an optimistic forecast for growth, while the GDP of the remaining 11 sports industries was predicted to decline. The average GDP forecasting accuracy for the sports industry was 94% in 2017 and 97.2% in 2018. Among the 40 sports industry sectors, eight had growth forecasts, while the GDP of the other 32 sectors was predicted to decline. The average GDP forecasting accuracy for sports industry sectors was 99.5% in 2017 and 99.4% in 2018. In the strategic matrix analysis, all 12 sports industries showed a growth trend. All sports industries showed a consistent upward trend in the GDP time series, indicating overall continuous growth in the sports industry. Similarly, among the 40 sports industry sectors, the Star and Cash Cow sectors showed growth trends and trend lines in the strategic positioning matrix and GDP time series. In contrast, the Question Marks and Dogs sectors showed declining trends and trend lines. Conclusion: This study makes six specific recommendations: (1) Seek solutions for the sports industry through prediction and estimation, (2) use strategic management to chart the course for developing the sports industry, (3) explore and propose future trends in the sports industry, (4) explore and propose future trends in the various sports industry sectors, (5) define the scope of the sports industry and address significant data management and its implications, and (6) foster research and development in technology management and its academic applications. These recommendations aim to provide valuable insights and guidance for the advancement and strategic planning of the sports industry, considering future trends and technological advances. [ABSTRACT FROM AUTHOR]

This study presents a novel financial performance forecasting method that combines the threshold technique with Artificial Neural Networks (ANN). It applies the threshold regression method to identify the factors within the board of directors that influence the financial performance of traditional industries in Taiwan. The findings indicate that the ANN method effectively predicts financial performance by using relevant board structure data. Furthermore, the empirical results suggest that boards with more members demonstrate increased profitability. Additionally, a more significant presence of board members with accounting expertise contributes to more consistent profits. In contrast, an increased presence of members with financial expertise has a more pronounced impact on profitability. [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]

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]

Storm surges are one of the most devastating coastal disasters. Numerous efforts have continuously been made to achieve better prediction of storm surge variation. In this paper, we propose a parametric cyclone and neural network hybrid model for accurate, long lead-time storm surge prediction. The model was applied to the northeastern coastal region of Taiwan, i.e., Longdong station. A total of 14 historical typhoon events were used for model training and validation, and the results and questions associated with this hybrid approach carefully discussed. Overall, the proposed method reduced the complexity of network structure while retaining the important typhoon indicators. In particular, local pressure and winds estimated from the storm parameters through physically-based parametric cyclone models allow for inferring the possible future influence of a typhoon, unlike the simple collection and direct usage of observation data from local stations in earlier works. Meanwhile, the error-tolerance capability of the neural network alleviated some discrepancy in the model inputs and enabled good surge prediction. Further, the proposed method showed better and faster convergence thanks to the retention of storm information and the reduced dimensions of the search space. The hybrid model presented excellent performance or maintained reasonable capability for short lead-time and long lead-time storm surge prediction. Compared with the pure neural network model under the same network dimensions, the present model demonstrated great improvement in accuracy as the prediction lead time increased to 8 h, e.g., 33–40% (13–21%) and 32–37% (18–29%) RMSE and CE, respectively, in the training/validation phase. [ABSTRACT FROM AUTHOR]

This paper aims to develop a stochastic model (SM_EID_IOT) for estimating the inundation depths and associated 95% confidence intervals at the specific locations of the roadside water-level gauges, i.e., Internet of Things (IoT) sensors under the observed water levels/rainfalls and the precipitation forecasts given. The proposed SM_EID_IOT model is an ANN-derived one, a modified artificial neural network model (i.e., the ANN_GA-SA_MTF) in which the associated ANN weights are calibrated via a modified genetic algorithm with a variety of transfer functions considered. To enhance the reliability and accuracy of the proposed SM_EID_IOT model in the estimations of the inundation depths at the IoT sensors, a great number of the rainfall induced flood events as the training and validation datasets are simulated by the 2D hydraulic dynamic (SOBEK) model with the simulated rain fields via the stochastic generation model for the short-term gridded rainstorms. According to the results of model demonstration, Nankon catchment, located in northern Taiwan, the proposed SM_EID_IOT model can estimate the inundation depths at the various lead times with high reliability in capturing the validation datasets. Moreover, through the integrated real-time error correction method integrated with the proposed SM_EID_IOT model, the resulting corrected inundation-depth estimates exhibit a good agreement with the validated ones in time under an acceptable bias. [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]

• 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]

Total electron content (TEC) precursors of the Chi-Chi Earthquake, which occurred in Taiwan at 01:47:15 on September 21, 1999 (Taiwan Standard Time, TST), with its epicenter at 23.85° N and 120.82° E, a Richter magnitude (ML) of 7.3 (a moment magnitude (Mw) of 7.6), and a focal depth of 8.00 km, were detected 1, 3, and 4 days before the earthquake using two back-propagation neural network (BPNN) models. These results are consistent with the analysis results of Liu et al. (2001) and Lin (2010). Another TEC precursor was detected on May 13, 2003 (TST), 2 days before the earthquake on May 15, 2003 (TST), with an ML of 5.21. Their precursors might be induced by the variations of the geomagnetic and electric fields near their hypocenter. The two BPNN models were to be verified for stability and reliability after performing cross-validation and evaluating the variance in the learning process. For this, the result of the analyzed method can serve as a real-time TEC predicted system for giving any future time as inputs of the two BPNN models. Hence, an earthquake early warning (EEW) system is performable. [ABSTRACT FROM AUTHOR]

Construction projects are associated with risks, which influence projects' performance and quality. To ensure the on-time completion of construction projects, project managers often use risk assessment and management methods to reduce risks in the project life cycle. Identifying risk factors and the relationship between major risk factors and the quality of construction projects facilitates construction management. In this study, 948 project records of construction inspection from 1993 to 2020 were collected from the Public Construction Management Information System (PCMIS) of the Taiwan central government to conduct an expert survey to identify five risk dimensions and 19 major risk factors associated with Taiwanese construction projects. The hybrid analytic hierarchy process (AHP) and an artificial neural network (ANN) were employed to develop a model for predicting major risk factors and construction quality. The AHP was used to calculate the weight of major risk factors to verify their influence on construction. The ANN was adopted to extract the features of major risk factors to predict the quality of a construction project. The accuracy of the prediction model was 85%. The project managers can reference the prediction results obtained with the proposed method to perform effective risk management and devise decision-making strategies for construction management. [ABSTRACT FROM AUTHOR]

Manual titration of positive airway pressure (PAP) is a gold standard to provide an optimal pressure for the treatment of obstructive sleep apnea-hypopnea syndrome (OSAS). Since manual titration studies were costly and time-consuming, many statistical models for predicting effective PAPs were reported. However, the prediction accuracies of the models associated with nocturnal parameters still remain low. This study proposes a fuzzy neural prediction network (FNPN) with input candidate variables, selected among easily available measurements (e.g., body mass index (BMI), waist circumstance (WC), and body composition) and OSAS related questionnaires, to rapidly predict an optimal PAP. The FNPN comprises fuzzy rules and is characterized with the ability of automatic rule growing and pruning from training data. A total of 147 participants from April 2018 to April 2019 were enrolled in Taichung Veterans General Hospital, Taiwan. After two selection processes for feature extraction, WC and BMI were the significant variables for entering the FNPN to predict optimal PAP. Experimental results showed that the average successful prediction rate of the proposed method was 71.8%. This study also found that Epworth sleepiness scales (ESS) and body composition, such as visceral fat area and percent body fat, were excluded in the final prediction model. Compared with existing models, the proposed prediction approach provided a rapid prediction of optimal PAP with higher accuracy. [ABSTRACT FROM AUTHOR]

Defects on thin film transistor liquid crystal display (TFT-LCD) panel could be divided into either macro- or microdefects, depending on if they are easy to be detected by the naked eye or not. There have been abundant studies discussing the identification of macrodefects but very few on microones. This study proposed a multicategory classification model using a convolutional neural network model to work with automatic optical inspection (AOI) for identifying defective pixels on the TFT-LCD panel. Since the number of nondefective pixels outnumbered the defective ones, there exists a very serious class-imbalanced problem. To deal with that, this study designed a special training strategy that worked with data augmentation to increase the effectiveness of the proposed model. Actual panel images provided by a mobile manufacturer in Taiwan are used to demonstrate the efficiency and effectiveness of the proposed approach. After validation, the model constructed by this study had 98.9% total prediction accuracy and excellent specificity and sensitivity. The model could finish the detection and classification process automatically to replace the human inspection. [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]