Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures.

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power system can be carried out; these inspections can be automated using computer vision techniques based on deep neural networks. Based on this need, this paper proposes the Semi-ProtoPNet deep learning model to classify defective structures in the power distribution networks. The Semi-ProtoPNet deep neural network does not perform convex optimization of its last dense layer to maintain the impact of the negative reasoning process on image classification. The negative reasoning process rejects the incorrect classes of an input image; for this reason, it is possible to carry out an analysis with a low number of images that have different backgrounds, which is one of the challenges of this type of analysis. Semi-ProtoPNet achieves an accuracy of 97.22%, being superior to VGG-13, VGG-16, VGG-19, ResNet-34, ResNet-50, ResNet-152, DenseNet-121, DenseNet-161, DenseNet-201, and also models of the same class such as ProtoPNet, NP-ProtoPNet, Gen-ProtoPNet, and Ps-ProtoPNet.

Abnormal Event Detection and Localization via Adversarial Event Prediction.

We present adversarial event prediction (AEP), a novel approach to detecting abnormal events through an event prediction setting. Given normal event samples, AEP derives the prediction model, which can discover the correlation between the present and future of events in the training step. In obtaining the prediction model, we propose adversarial learning for the past and future of events. The proposed adversarial learning enforces AEP to learn the representation for predicting future events and restricts the representation learning for the past of events. By exploiting the proposed adversarial learning, AEP can produce the discriminative model to detect an anomaly of events without complementary information, such as optical flow and explicit abnormal event samples in the training step. We demonstrate the efficiency of AEP for detecting anomalies of events using the UCSD-Ped, CUHK Avenue, Subway, and UCF-Crime data sets. Experiments include the performance analysis depending on hyperparameter settings and the comparison with existing state-of-the-art methods. The experimental results show that the proposed adversarial learning can assist in deriving a better model for normal events on AEP, and AEP trained by the proposed adversarial learning can surpass the existing state-of-the-art methods.

Object or Background: An Interpretable Deep Learning Model for COVID-19 Detection from CT-Scan Images.

The new strains of the pandemic COVID-19 are still looming. It is important to develop multiple approaches for timely and accurate detection of COVID-19 and its variants. Deep learning techniques are well proved for their efficiency in providing solutions to many social and economic problems. However, the transparency of the reasoning process of a deep learning model related to a high stake decision is a necessity. In this work, we propose an interpretable deep learning model Ps-ProtoPNet to detect COVID-19 from the medical images. Ps-ProtoPNet classifies the images by recognizing the objects rather than their background in the images. We demonstrate our model on the dataset of the chest CT-scan images. The highest accuracy that our model achieves is 99.29%.

An Interpretable Deep Learning Model for Covid-19 Detection With Chest X-Ray Images.

Timely and accurate detection of an epidemic/pandemic is always desired to prevent its spread. For the detection of any disease, there can be more than one approach including deep learning models. However, transparency/interpretability of the reasoning process of a deep learning model related to health science is a necessity. Thus, we introduce an interpretable deep learning model: Gen-ProtoPNet. Gen-ProtoPNet is closely related to two interpretable deep learning models: ProtoPNet and NP-ProtoPNet The latter two models use prototypes of spacial dimension [Formula: see text] and the distance function [Formula: see text]. In our model, we use a generalized version of the distance function [Formula: see text] that enables us to use prototypes of any type of spacial dimensions, that is, square spacial dimensions and rectangular spacial dimensions to classify an input image. The accuracy and precision that our model receives is on par with the best performing non-interpretable deep learning models when we tested the models on the dataset of [Formula: see text]-ray images. Our model attains the highest accuracy of 87.27% on classification of three classes of images, that is close to the accuracy of 88.42% attained by a non-interpretable model on the classification of the given dataset.

Image-based quantitative analysis of tear film lipid layer thickness for meibomian gland evaluation.

BACKGROUND: Dry eye syndrome is one of the most common ocular diseases, and meibomian gland dysfunction (MGD) is the leading cause of evaporative dry eye syndrome. When the tear film lipid layer becomes thin due to obstructive or hyposecretory meibomian gland dysfunction, the excessive evaporation of the aqueous layer can occur, and this causes evaporative dry eye syndrome. Thus, measuring the lipid layer thickness (LLT) is essential for accurate diagnosis and proper treatment of evaporative dry eye syndrome. METHODS: We used a white LED panel with a slit lamp microscope to obtain videos of the lipid layer interference patterns on the cornea. To quantitatively analyze the LLT from interference colors, we developed a novel algorithm that can automatically perform the following processes on an image frame: determining the radius of the iris, locating the center of the pupil, defining region of interest (ROI), tracking the ROI, compensating for the color of iris and illumination, and producing comprehensive analysis output. A group of dry eye syndrome patients with hyposecretory MGD, dry eye syndrome without MGD, hypersecretory MGD, and healthy volunteers were recruited. Their LLTs were analyzed and statistical information-mean and standard deviation, the relative frequency of LLT at each time point, and graphical LLT visualization-were produced. RESULTS: Using our algorithm, we processed the lipid layer interference pattern and automatically analyzed the LLT distribution of images from patients. The LLT of hyposecretory MGD was thinner (45.2 ± 11.6 nm) than that of dry eye syndrome without MGD (69.0 ± 9.4 nm) and healthy volunteers (68.3 ± 13.7 nm) while the LLT of hypersecretory MGD was thicker (93.5 ± 12.6 nm) than that of dry eye syndrome without MGD. Patients' LLTs were statistically analyzed over time, visualized with 3D surface plots, and displayed using 3D scatter plots of image pixel data for comprehensive assessment. CONCLUSIONS: We developed an image-based algorithm for quantitative measurement as well as statistical analysis of the LLT despite fluctuation and eye movement. This pilot study demonstrates that the quantitative LLT analysis of patients is consistent with the functions of meibomian glands clinically evaluated by an ophthalmologist. This approach is a significant step forward in developing a fully automated instrument for evaluating dry eye syndrome and for providing proper guidance of treatment.

A Fully Automatic Method for Gridding Bright Field Images of Bead-Based Microarrays.

In this paper, a fully automatic method for gridding bright field images of bead-based microarrays is proposed. There have been numerous techniques developed for gridding fluorescence images of traditional spotted microarrays but to our best knowledge, no algorithm has yet been developed for gridding bright field images of bead-based microarrays. The proposed gridding method is designed for automatic quality control during fabrication and assembly of bead-based microarrays. The method begins by estimating the grid parameters using an evolutionary algorithm. This is followed by a grid-fitting step that rigidly aligns an ideal grid with the image. Finally, a grid refinement step deforms the ideal grid to better fit the image. The grid fitting and refinement are performed locally and the final grid is a nonlinear (piecewise affine) grid. To deal with extreme corruptions in the image, the initial grid parameter estimation and grid-fitting steps employ robust search techniques. The proposed method does not have any free parameters that need tuning. The method is capable of identifying the grid structure even in the presence of extreme amounts of artifacts and distortions. Evaluation results on a variety of images are presented.