Background: Diabetic retinopathy (DR) produces bleeding, exudation, and new blood vessel formation conditions. DR can damage the retinal blood vessels and cause vision loss or even blindness. If DR is detected early, ophthalmologists can use lasers to create tiny burns around the retinal tears to inhibit bleeding and prevent the formation of new blood vessels, in order to prevent deterioration of the disease. The rapid improvement of deep learning has made image recognition an effective technology; it can avoid misjudgments caused by different doctors’ evaluations and help doctors to predict the condition quickly. The aim of this paper is to adopt visualization and preprocessing in the ResNet-50 model to improve module calibration, to enable the model to predict DR accurately.Results: This study compared the performance of the proposed method with other common CNNs models (Xception, AlexNet, VggNet-s, VggNet-16 and ResNet-50). In examining said models, the results alluded to an over-fitting phenomenon, and the outcome of the work demonstrates that the performance of the revised ResNet-50 (Train accuracy: 0.8395 and Test accuracy: 0.7432) is better than other common CNNs (that is, the revised structure of ResNet-50 could avoid the overfitting problem, decease the loss value, and reduce the fluctuation problem).Conclusions: This study proposed two approaches to designing the DR grading system: a standard operation procedure (SOP) for preprocessing the fundus image, and a revised structure of ResNet-50, including an adaptive learning rating to adjust the weight of layers, regularization and change the structure of ResNet-50, which was selected for its suitable features. It is worth noting that the purpose of this study was not to design the most accurate DR screening network, but to demonstrate the effect of the SOP of DR and the visualization of the revised ResNet-50 model. The results provided an insight to revise the structure of CNNs using the visualization tool.
According to the Ten Leading Causes of Death Statistics Report by the Ministry of Health and Welfare in 2021, cancer ranks as the leading cause of mortality. Among them, pleomorphic glioblastoma is a common type of brain cancer. Brain cancer often occurs in the brain with unclear boundaries from normal brain tissue, necessitating assistance from experienced doctors to distinguish brain tumors before surgical resection to avoid damaging critical neural structures. In recent years, with the advancement of deep learning (DL) technology, artificial intelligence (AI) plays a vital role in disease diagnosis, especially in the field of image segmentation. This technology can aid doctors in locating and measuring brain tumors, while significantly reducing manpower and time costs. Currently, U-Net is one of the primary image segmentation techniques. It utilizes skip connections to combine high-level and low-level feature information, leading to significant improvements in segmentation accuracy. To further enhance the model’s performance, this study explores the feasibility of using EfficientNetV2 as an encoder in combination with U-net. Experimental results indicate that employing EfficientNetV2 as an encoder together with U-net can improve the segmentation model’s Dice score (loss = 0.0866, accuracy = 0.9977, and Dice similarity coefficient (DSC) = 0.9133).
Motor imagery (MI) can produce a specific brain pattern when the subject imagines performing a particular action without any actual body movements. According to related previous research, the improvement of the training of MI brainwaves can be adopted by feedback methods in which the analysis of brainwave characteristics is very important. The aim of this study was to improve the subject's MI and the accuracy of classification. In order to ameliorate the accuracy of the MI of the left and right hand, the present study designed static and dynamic visual stimuli in experiments so as to evaluate which one can improve subjects' imagination training. Additionally, the filter bank common spatial pattern (FBCSP) method was used to divide the frequency band range of the brainwaves into multiple segments, following which linear discriminant analysis (LDA) was adopted for classification. The results revealed that the averaged false positive rate (FPR) under FBCSP-LDA in the dynamic MI experiment was the lowest FPR (23.76%). As such, this study suggested that a combination of the dynamic MI experiment and the FBCSP-LDA method improved the overall prediction error rate and ameliorated the performance of the MI brain-computer interface.
Rotating machinery is the fundamental component of almost all industrial frameworks. Therefore, prognostics and health management (PHM) have emerged as crucial requirements for effectively managing and sustaining various systems in a timely manner. The unbalanced fault has been recognized as a significant contributing factor in the development of faults in rotor-bearing systems, eventually causing failure. Thus, it is essential to monitor the unbalance and maintain it within acceptable bounds in order to guarantee the system’s proper operation. Most approaches to the rotor’s unbalance monitoring are model-based instead of data-driven due to the shortage of faulted data. In a derived model-based approach, proper identification of the model’s parameters, e.g., bearing parameters, always plays a very crucial role. Nonetheless, the identified model’s parameters in their initial state would inevitably degenerate during a long-term operation because of aging or environmental changes, such that they are no longer well representative of the real system. In this context, this paper offers an adaptive model-based approach for the assessment of unbalance faults developing over days in a rotor-bearing model. The model is adaptive in the sense that it automatically adjusts its parameters so that they are more closely aligned with the real system. A particle swarm optimization (PSO) scheme is utilized in the parameter identification process. The residual serves as the index for initiating the adaptive process when it is greater than a preset percentage. Individual feature errors work as a gauge to determine which bearing parameters need to be reevaluated. A set of 16-month operational data from a local petrochemical company is used to validate the approach. The unbalanced deterioration trend is evaluated, and results from the adaptive methodology are assessed to show its superiority over the original one. It is also observed that the model’s capacity to anticipate unbalance is greatly enhanced by the adaptive strategy. Finally, future unbalances are explored to show its capacity for continuous monitoring-based maintenance solutions.
Diabetic retinopathy (DR) is a severe complication of diabetes, causing damage to retinal blood vessels due to high blood sugar levels. Early detection is crucial but often requires significant time and expertise from ophthalmologists. While artificial intelligence (AI) and image recognition hold promise for DR detection, inconsistent image quality poses a challenge. Our study presents a novel technique that integrates pixel color amplification and EfficientNetV2 to enhance fundus image attributes, aiming to address issues related to image quality and achieving superior performance in DR detection. Leveraging EfficientNetV2, an advanced convolutional neural network (CNN) architecture, we achieve 84% multiclass accuracy and 99% binary accuracy, surpassing various other CNN models, including VGG16-fc1, VGG16-fc2, NASNet, Xception, Inception ResNetV2, EfficientNet, InceptionV3, MobileNet, and ResNet50. Our research tackles the critical challenge of early detection of DR, essential for preventing vision loss. This advancement holds the potential to enhance the efficiency and accuracy of DR classification, potentially alleviating the burden on medical professionals and ultimately improving the quality of life for individuals at risk of vision loss.
The aim of this study was to develop a real-time automatic attendance system (AAS) based on Internet of Things (IoT) technology and facial recognition. A Raspberry Pi camera built into a Raspberry Pi 3B is used to transfer facial images to a cloud server. Face detection and recognition libraries are implemented on this cloud server, which thus can handle all the processes involved with the automatic recording of student attendance. In addition, this study proposes the application of data serialization processing and adaptive tolerance vis-à-vis Euclidean distance. The facial features encountered are processed using data serialization before they are saved in the SQLite database; such serialized data can easily be written and then read back from the database. When examining the differences between the facial features already stored in the SQLite databases and any new facial features, the proposed adaptive tolerance system can improve the performance of the facial recognition method applying Euclidean distance. The results of this study show that the proposed AAS can recognize multiple faces and so record attendance automatically. The AAS proposed in this study can assist in the detection of students who attempt to skip classes without the knowledge of their teachers. The problem of students being unintentionally marked present, though absent, and the problem of proxies is also resolved.