An optimal tilt-angle control based on artificial intelligence (AI control) for tracking bifacial photovoltaic (BPV) systems is developed in this study, and its effectiveness and characteristics are examined by simulating a virtual system over five years. Using deep reinforcement learning (deep RL), the algorithm autonomously learns the control strategy in real time from when the system starts to operate. Even with limited deep RL input variables, such as global horizontal irradiance, time, tilt angle, and power, the proposed AI control successfully learns and achieves a 4.0–9.2% higher electrical-energy yield in high-albedo cases (0.5 and 0.8) as compared to traditional sun-tracking control; however, the energy yield of AI control is slightly lower in low-albedo cases (0.2). AI control also demonstrates a superior performance when there are seasonal changes in albedo. Moreover, AI control is robust against long-term system degradation by manipulating the database used for reward setting.

Deep learning is a subset of machine learning that can be employed to accurately predict biological transitions. Eliminating hepatitis B surface antigens (HBsAgs) is the final therapeutic endpoint for chronic hepatitis B. Reliable predictors of the disappearance or reduction in HBsAg levels have not been established. Accurate predictions are vital to successful treatment, and corresponding efforts are ongoing worldwide. Therefore, this study aimed to identify an optimal deep learning model to predict the changes in HBsAg levels in daily clinical practice for inactive carrier patients. We identified patients whose HBsAg levels were evaluated over 10 years. The results of routine liver biochemical function tests, including serum HBsAg levels for 1, 2, 5, and 10 years, and biometric information were obtained. Data of 90 patients were included for adaptive training. The predictive models were built based on algorithms set up by SONY Neural Network Console, and their accuracy was compared using statistical analysis. Multiple regression analysis revealed a mean absolute percentage error of 58%, and deep learning revealed a mean absolute percentage error of 15%; thus, deep learning is an accurate predictive discriminant tool. This study demonstrated the potential of deep learning algorithms to predict clinical outcomes.

Background/Objectives: This study aimed to investigate the prevalence of liver damage and its associated non-invasive markers and echocardiographic risk factors in patients who underwent surgery for congenital heart disease. Methods: This retrospective observational study was conducted at a single tertiary-care university hospital in Niigata, Japan. Of 142 patients (ventricular septal defect [VSD] n = 47, tetralogy of Fallot [TOF] n = 67, Fontan n = 28), 52.8% were male [median age: 22.7 years; VSD (24.3 years), TOF (24.0 years), and Fontan (12.5 years)]. Pediatric patients with liver diseases unrelated to congestive liver disease, such as viral hepatitis and alcoholic liver disease, were excluded. We compared non-invasive liver fibrosis age-invariant biomarkers, such as the aspartate aminotransferase-to-platelet ratio index (APRI), and various serum markers and echocardiographic parameters to assess the prevalence and predictors of hepatic fibrosis. Results: The Fontan circulation group had the highest APRI, followed by the TOF group, while the VSD group had a low risk of APRI elevation. Postoperative TOF patients required monitoring for cirrhosis progression. Inferior vena cava mobility was associated with echocardiographic parameters and fibrosis severity, along with a loss of respiratory variability. The limitations of other cardiac assessments were highlighted by poor anatomical measurements. Gamma-glutamyl transpeptidase (γ-GTP) demonstrated strong discriminatory ability. The optimal cutoff value was 53.0 U/L, suggesting its use as a clinical marker. Conclusions: Assessing fibrosis is crucial in CHD patients, especially those with late post-TOF repair findings. Non-invasive markers (APRI, γ-GTP, and B-type natriuretic peptide), along with echocardiographic findings, may help detect fibrosis early, enabling timely intervention and improving long-term outcomes. Clinical trial registration: 2020-0199.

For decades, if an accident occurs where a product may be at fault, the analysis of the accident has been extremely important to increase safety, and danger and harm investigations are conducted to address issues with the product and prevent future accidents. Therefore, many researchers have proposed collection and analysis methods for accident reports. Although most of the previous methods apply to numerical data, a large amount of text data exists in shape of accident reports which contains rich information, such as the events of each accident in detail. This is useful for classification of accident type, analysis of accident factor, and many other risk management analysis. Because of the scale of the data, in order to analyze it correctly, a framework and categorization scheme based on it are necessary. However, injury data tagging is usually done manually, and proves difficult for large databases of accident reports. To solve this issue, we proposed a classification method using text mining technology, Japanese grammar pattern and machine learning technology to automate the classification of injury data. The algorithm of our proposed method is vectorization of words and clustering. In this research, we used the product accident data with 260 injury data and 116 products in 970 accident reports provided by the National Institute of Technology and Evaluation (NITE). For the classification, we used five Mechanism codes based on the International Classification of External Causes of Injury (ICECI). For the clustering, the ratio of the correct classification for the Mechanism code based on ICECI of cluster 0, 1 and 2 exceeded 0.8, and we found many data can be classified into a type of Mechanism code of ICECI. We consider that the reason that the clusters with a high correct classification ratio was that it was able to extract the words necessary for the classification from the analysis reports. On the other hand, clusters with a low ratio of correct classification showed such a result because many words that are not necessary for classification were extracted and introduced noise for the word vector model.