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 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: 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: 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 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.