Prior to the implementation of digitisation processes, the handwritten signature in an attendance sheet was the preferred way to prove the presence of each student in a classroom. The method is still preferred, for example, for short courses or places where other methods are not implemented. However, human verification of handwritten signatures is a tedious process. The present work describes two methods for classifying signatures in an attendance sheet as valid or not. One method based on Optical Mark Recognition is general but determines only the presence or absence of a signature. The other method uses a multiclass convolutional neural network inspired by the AlexNet architecture and, after training with a few pieces of genuine training data, shows over 85% of precision and recall recognizing the author of the signatures. The use of data augmentation and a larger number of genuine signatures ensures higher accuracy in validating the signatures.
Counting objects in video images has been an active area of computer vision for decades. For precise counting, it is necessary to detect objects and follow them through consecutive frames. Deep neural networks have allowed great improvements in this area. Nonetheless, this task is still a challenge for edge computing, especially when low-power edge AI devices must be used. The present work describes an application where an edge device is used to run a YOLO network and V-IOU tracker to count people and bicycles in real time. A selective frame-downsampling algorithm is used to allow a larger frame rate when necessary while optimizing memory usage and energy consumption. In the experiments, the system was able to detect and count the objects with 18 counting errors in 525 objects and a mean inference time of 112.82 ms per frame. With the selective downsampling algorithm, it was also capable of recovering and reduce memory usage while maintaining its precision.
Objectives: This clinical study aimed to evaluate and compare the diagnostic accuracy of intraoral periapical radiography (PR) and cone beam computed tomography (CBCT) in detecting external apical root resorption (EARR) in orthodontic patients during the retention phase. Methods: The research involved 41 Caucasian patients who had undergone comprehensive orthodontic treatment, with a total of 328 teeth analyzed. The Kappa values for inter- and intra-examiner agreement were high for both PR and CBCT, indicating a robust level of agreement among examiners. The study used a four-point scale for classifying EARR. Results: This study showed comparable accuracy, sensitivity, and specificity between PR and CBCT when using the most stringent criterion of “Definitely present”. The data suggested that CBCT outperformed PR when using a less stringent criterion (“Definitely present” or “Probably present”), particularly for maxillary incisors. However, overall diagnostic performance, as measured by the area under the ROC curve, showed only a slight advantage for CBCT over PR. Areas under the ROC curve range between 0.85 and 0.90 for PR and between 0.89 and 0.92 for CBCT. According to DeLong’s test, there is no evidence to conclude that the area under the ROC curve is different for PR and CBCT. Conclusions: Both PR and CBCT are accurate diagnostic tools for identifying EARR, with PR being deemed more suitable for routine clinical use due to its cost-effectiveness and lower radiation exposure. The findings emphasize the importance of considering the risk-benefit ratio when deciding on imaging modalities for monitoring EARR in orthodontic patients.
Background: Prediction of susceptibility to Orthodontically Induced External Apical Root Resorption (OIEARR) has been hampered by the complex architecture of this multifactorial phenotype. The aim of this study was to analyze the impact of the interaction of multiple variables in the susceptibility to OIEARR. Methods: The study evaluated 195 patients requiring orthodontic treatment. Nine clinical and treatment variables, single nucleotide polymorphisms (SNPs) from five genes and variables interactions were analyzed as risk factors for OIEARR using a multiple linear regression model. Results: The model explained 29% of OIEARR variability (ANOVA: p < 0.01). Duration of treatment was the most important predictor and gender was the second, closely followed by premolar extraction. For genes encoding osteoprotegerin (OPG), the receptor activator of nuclear factor κ B (RANK) and the IL1 receptor antagonist (IL1RN), the effect of analyzed variants changed from protective to deleterious depending on the duration of treatment and the age of the patient. Conclusions: This work shows that in OIEARR the impact of genetic susceptibility factors is dynamic changing according to clinical variables.
Predictive maintenance has gained importance due to industrialization. Harnessing advanced technologies like sensors and data analytics enables proactive interventions, preventing unplanned downtime, reducing costs, and enhancing workplace safety. They play a crucial role in optimizing industrial operations, ensuring the efficiency, reliability, and longevity of equipment, which have become increasingly vital in the context of industrialization. The analysis of time series’ stationarity is a powerful and agnostic approach to studying variations and trends that may indicate imminent failures in equipment, thus contributing to the effectiveness of predictive maintenance in industrial environments. The present paper explores the use of the Augmented Dickey–Fuller p-value temporal variation as a possible method for determining trends in sensor time series and thus anticipating possible failures of a wood chip pump in the paper industry.