Abstract: A computer-implemented method for generating anti-noise using an anti-noise generator to suppress noise from a noise source in an environment comprises processing a sound signal, which is representative of ambient sound including noise, anti-noise and propagation noise from the environment, using a deep learning algorithm configured to generate an anti-noise signal to form anti-noise. The deep learning algorithm comprises a convolution layer; after the convolution layer, a series of atrous scaled convolution modules, wherein each of the atrous scaled convolution modules comprises an atrous convolution, a nonlinear activation function after the atrous convolution, and a pointwise convolution after the nonlinear activation function; after the series of atrous scaled convolution modules, a recurrent neural network; and after the recurrent neural network, a plurality of fully connected layers.

Abstract: A method for generating anti-noise comprises receiving a sound signal representative of ambient sound including noise from a noise source, anti-noise from an anti-noise generator, and propagation noise from environment; processing the sound signal using a deep learning algorithm configured to generate an anti-noise signal to form anti-noise; and outputting the anti-noise signal to the anti-noise generator. The deep learning algorithm features an iterative encoder module forming plural feature maps; an attention module generating plural attention maps respectively based on the feature maps; a recurrent neural network (RNN), with long short-term memory layers receiving the feature map of the final iteration of the encoder module, predicting a future portion of the sound signal and modelling temporal features of the feature map of the final encoder module iteration; and an iterative decoder module mapping the output of the RNN to the anti-noise signal having common dimensions as the sound signal.

Abstract: Provided is a composition for the prevention or treatment of Hutchinson-Gilford Progeria syndrome (HGPS) using gene editing, which contains sgRNA that hybridizes to mRNA encoding progerin, which causes HGPS, and a gene encoding Cas13 protein acting on the same. When introduced into the cell of a subject to be treated and only the mRNA encoding progerin is selectively cut. There is no need for co-prescribing with other therapies and fewer side effects occur than traditional farnesyltransferase inhibitors (FTIs). The efficiency is higher than when treated using homologous recombination (HR) at the DNA level, treatment using composition can be made reversibly, and the composition can be applied specifically compared to targeted treatment using RNAi (RNA interference), and has fewer side effects. Compared to treatment using CRISPR/Cas9, which directly acts on DNA and produces irreversible results, treatment using composition is reversible and selectively cut only mRNA encoding progerin, thereby ensuring safety.

Abstract: An apparatus for assembling a capacitor assembly and a method for assembling the capacitor assembly using the same according to the present disclosure includes: a processing module mechanically, electrically coupling a capacitor to a bracket to assemble to a capacitor assembly, a test module testing whether the assembled capacitor assembly normally operates, and a conveyor module in which the capacitor assembly is arranged to sequentially perform the processing and test processes while moving in one direction, and it is possible to precisely detect whether the capacitor assembly is defective through two or more tests, and if many mechanical defects occur, it is possible to reduce the possibility of occurrence of the mechanical defect by controlling and adjusting some of the processing modules and improve productivity.

Abstract: A computer-implemented method of analyzing an image to segment an article of interest in the image comprises (i) receiving the image having a width of n1 pixels, a height of n2 pixels and a depth of d channels; (ii) processing the image using a machine learning algorithm configured to segment the article of interest, the machine learning algorithm comprising a convolutional neural network including: at least one convolution layer; after said at least one convolution layer, at least one separable convolution module comprising a series of separable convolutions, each separable convolution comprising a depthwise convolution and a pointwise convolution; after said at least one separable convolution module, a pooling module; and a decoder module after the pooling module; and (iii) displaying the image with location of the article of interest being indicated if determined to be present by the machine learning algorithm.

Abstract: A computer-implemented method for analyzing a thermographic image to detect an article of interest (AOI) comprises processing the image using a machine learning algorithm configured to detect the AOI and comprising a convolutional neural network (CNN); and displaying the image with location of the AOI being indicated if determined to be present. The CNN features a series pair of convolution modules configured to receive the image and form a reduced size feature map; an in-depth module thereafter and configured to learn correlations and contextual features of the image; and a superficial module after a first of the series convolution module pair and configured to extract features relevant to the AOI. Also, a computer-implemented method for generating synthetic training data based on authentic training data comprises a first neural network configured to generate the synthetic data and a second neural network configured to compare it to the authentic data to determine closeness.

Abstract: A computer-implemented method for generating anti-noise using an anti-noise generator to suppress noise from a noise source in an environment comprises processing a sound signal, which is representative of ambient sound including noise, anti-noise and propagation noise from the environment, using a deep learning algorithm configured to generate an anti-noise signal to form anti-noise. The deep learning algorithm comprises a convolution layer; after the convolution layer, a series of atrous scaled convolution modules, wherein each of the atrous scaled convolution modules comprises an atrous convolution, a nonlinear activation function after the atrous convolution, and a pointwise convolution after the nonlinear activation function; after the series of atrous scaled convolution modules, a recurrent neural network; and after the recurrent neural network, a plurality of fully connected layers.

Abstract: A computer-implemented method for analyzing an image to detect an article of interest (AOI) comprises processing the image using a machine learning algorithm configured to detect the AOI and comprising a convolutional neural network (CNN); and displaying the image with location of the AOI being indicated if determined to be present. The CNN comprises an input module configured to receive the image and comprising at least one convolutional layer, batch normalization and a nonlinear activation function; an encoder thereafter and configured to extract features indicative of a present AOI to form a feature map; a decoder thereafter and configured to discard features from the feature map that are not associated with the present AOI and to revert the feature map to a size matching an initial image size; and a concatenation module configured to link outputs of the input module, the encoder and the decoder for subsequent segmentation.

Abstract: A computer-implemented method of analyzing an image to segment an article of interest in the image comprises (i) receiving the image having a width of n1 pixels, a height of n2 pixels and a depth of d channels; (ii) processing the image using a machine learning algorithm configured to segment the article of interest, the machine learning algorithm comprising a convolutional neural network including: at least one convolution layer; after said at least one convolution layer, at least one separable convolution module comprising a series of separable convolutions, each separable convolution comprising a depthwise convolution and a pointwise convolution; after said at least one separable convolution module, a pooling module; and a decoder module after the pooling module; and (iii) displaying the image with location of the article of interest being indicated if determined to be present by the machine learning algorithm.

Abstract: Structure defect detection is performed using computer-implemented arrangements employing machine learning algorithms in the form of neural networks. In one arrangement, a convolutional neural network is trained using a database of images formed to optimize accuracy of the convolutional neural network to detect, for example, a crack in a concrete surface. A two-stage scanning process each performing a plurality of scans of a test image is incorporated in the foregoing arrangement of convolutional neural network, with the two-stages forming overlapping capture areas to reduce likelihood of a crack lying on a boundary of the individual scans going undetected. Also, region-based convolutional neural networks are trained to detect various types of defects.

Abstract: Structure defect detection is performed using computer-implemented arrangements employing machine learning algorithms in the form of neural networks. In one arrangement, a convolutional neural network is trained using a database of images formed to optimize accuracy of the convolutional neural network to detect, for example, a crack in a concrete surface. A two-stage scanning process each performing a plurality of scans of a test image is incorporated in the foregoing arrangement of convolutional neural network, with the two-stages forming overlapping capture areas to reduce likelihood of a crack lying on a boundary of the individual scans going undetected. Also, region-based convolutional neural networks are trained to detect various types of defects.

Abstract: A composite imaging apparatus for dental diagnosis, wherein dental diagnosis for teeth/periodontal diseases and orthodontics can be simply done even with an imaging apparatus, and a patient's head portion can be automatically rotated according to image taking directions so as to simplify radiography, save radiography time, and minimize X-ray exposure. The apparatus includes a rotary arm horizontally rotating in left and right directions in order to take an X-ray image of teeth, jawbone and alveolar bone of a patient; a support frame vertically moving with a proper range according to a height of the patient, supporting and enabling the rotary arm to be fixed and horizontally rotate; and an object moving device formed on the base so as to move up and down a for certain range, reciprocate in forward and backward directions, horizontally rotate in forward and reverse directions while the patient is sitting thereon, and facilitate radiography.