Dental X-ray images are important and useful for dentists to diagnose dental diseases. Utilizing deep learning in dental X-ray images can help dentists quickly and accurately identify common dental diseases such as periodontitis and dental caries. This paper applies image processing and deep learning technologies to dental X-ray images to propose a simultaneous recognition method for periodontitis and dental caries. The single-tooth X-ray image is detected by the YOLOv7 object detection technique and cropped from the periapical X-ray image. Then, it is processed through contrast-limited adaptive histogram equalization to enhance the local contrast, and bilateral filtering to eliminate noise while preserving the edge. The deep learning architecture for classification comprises a pre-trained EfficientNet-B0 and fully connected layers that output two labels by the sigmoid activation function for the classification task. The average precision of tooth detection using YOLOv7 is 97.1%. For the recognition of periodontitis, the area under the curve (AUC) of the receiver operating characteristic (ROC) curve is 98.67%, and the AUC of the precision-recall (PR) curve is 98.38%. For the recognition of dental caries, the AUC of the ROC curve is 98.31%, and the AUC of the PR curve is 97.55%. Different from the conventional deep learning-based methods for a single disease such as periodontitis or dental caries, the proposed approach can provide the recognition of both periodontitis and dental caries simultaneously. This recognition method presents good performance in the identification of periodontitis and dental caries, thus facilitating dental diagnosis.

To examine the accuracy of machine learning to relate particulate matter (PM) 2.5 and PM10 concentrations to upper respiratory tract infections (URIs). Daily nationwide and regional outdoor PM2.5 and PM10 concentrations collected over 30 consecutive days obtained from the Taiwan Environment Protection Administration were the inputs for machine learning, using multilayer perceptron (MLP), to relate to the subsequent one-week outpatient visits for URIs. The URI data were obtained from the Centers for Disease Control datasets in Taiwan between 2009 and 2016. The testing used the middle month dataset of each season (January, April, July and October), and the training used the other months' datasets. The weekly URI cases were classified by tertile as high, moderate, and low volumes. Both PM concentrations and URI cases peak in winter and spring. In the nationwide data analysis, MLP machine learning can accurately relate the URI volumes of the elderly (89.05% and 88.32%, respectively) and the overall population (81.75% and 83.21%, respectively) with the PM2.5 and PM10 concentrations. In the regional data analyses, greater accuracy is found for PM2.5 than for PM10 for the elderly, particularly in the Central region (78.10% and 74.45%, respectively), whereas greater accuracy is found for PM10 than for PM2.5 for the overall population, particularly in the Northern region (73.19% and 63.04%, respectively). Short-term PM2.5 and PM10 concentrations were accurately related to the subsequent occurrence of URIs by using machine learning. Our findings suggested that the effects of PM2.5 and PM10 on URI may differ by age, and the mechanism needs further evaluation.

Multiscale entropy (MSE) of physiological signals may reflect cardiovascular health in diabetes. The classic MSE (cMSE) algorithm requires more than 750 signals for the calculations. The modified short-time MSE (sMSE) may have inconsistent outcomes compared with the cMSE at large time scales and in a disease status. Therefore, we compared the cMSE of 1500 (cMSE₁₅₀₀) consecutive and 1000 photoplethysmographic (PPG) pulse amplitudes with the sMSE of 500 PPG (sMSE₅₀₀) pulse amplitudes of bilateral fingertips among middle- to old-aged individuals with or without type 2 diabetes. We discovered that cMSE₁₅₀₀ had the smallest value across scale factors 1–10, followed by cMSE₁₀₀₀, and then sMSE₅₀₀ in both hands. The cMSE₁₅₀₀, cMSE₁₀₀₀ and sMSE₅₀₀ did not differ at each scale factor in both hands of persons without diabetes and in the dominant hand of those with diabetes. In contrast, the sMSE₅₀₀ differed at all scales 1–10 in the non-dominant hand with diabetes. In conclusion, autonomic dysfunction, prevalent in the non-dominant hand which had a low local physical activity in the person with diabetes, might be imprecisely evaluated by the sMSE; therefore, using more PPG signal numbers for the cMSE is preferred in such a situation.

Multiscale cross-approximate entropy (MC-ApEn) between two different physiological signals could evaluate cardiovascular health in diabetes. Whether MC-ApEn analysis between two similar signals such as photoplethysmographic (PPG) pulse amplitudes of bilateral fingertips can reflect diabetes status is unknown. From a middle-to-old-aged population free of prior cardiovascular disease, we selected the unaffected (no type 2 diabetes, n = 36), the well-controlled diabetes (glycated hemoglobin (HbA1c) < 8%, n = 30), and the poorly- controlled diabetes (HbA1c ≥ 8%, n = 26) groups. MC-ApEn indexes were calculated from simultaneous consecutive 1500 PPG pulse amplitudes signals of bilateral index fingertips. The average of scale factors 1–5 (MC-ApEn_SS) and of scale factors 6–10 (MC-ApEn_LS) were defined as the small- and large-scales MC-ApEn, respectively. The MC-ApEn_LS index was highest in the unaffected, followed by the well-controlled diabetes, and then the poorly-controlled diabetes (0.70, 0.62, and 0.53; all paired p-values were <0.05); in contrast, the MC-ApEn_SS index did not differ between groups. Our findings suggested that the bilateral fingertips large-scale MC-ApEn_LS index of PPG pulse amplitudes might be able to evaluate the glycemic status and detect subtle vascular disease in type 2 diabetes.

Trend prediction of influenza and the associated pneumonia can provide the information for taking preventive actions for public health. This paper uses meteorological and pollution parameters, and acute upper respiratory infection (AVRI) outpatient number as input to multilayer perceptron (MLP) to predict the patient number of influenza and the associated pneumonia in the following week. The meteorological parameters in use are temperature and relative humidity, air pollution parameters are Particulate Matter 2.5 (PM 2.5) and Carbon Monoxide (CO), and the patient prediction includes both outpatients and inpatients. Patients are classified by tertiles into three categories: high, moderate, and low volumes. In the nationwide data analysis, the proposed method using MLP machine learning can reach the accuracy of 81.16% for the elderly population and 77.54% for overall population in Taiwan. The regional data analyses with various age groups are also provided in this paper.

In the era of inclusive education, students with attention deficits are integrated into the general classroom. To ensure a seamless transition of students’ focus towards the teacher’s instruction throughout the course and to align with the teaching pace, this paper proposes a continuous recognition algorithm for capturing teachers’ dynamic gesture signals. This algorithm aims to offer instructional attention cues for students with attention deficits. According to the body landmarks of the teacher’s skeleton by using vision and machine learning-based MediaPipe BlazePose, the proposed method uses simple rules to detect the teacher’s hand signals dynamically and provides three kinds of attention cues (Pointing to left, Pointing to right, and Non-pointing) during the class. Experimental results show the average accuracy, sensitivity, specificity, precision, and F₁ score achieved 88.31%, 91.03%, 93.99%, 86.32%, and 88.03%, respectively. By analyzing non-verbal behavior, our method of competent performance can replace verbal reminders from the teacher and be helpful for students with attention deficits in inclusive education.