Abstract: Embodiments of the disclosure provide a circuit, chip, system, and method for eliminating random perturbation. The circuit includes a weight calculating module for receiving digital signals and random perturbation digital quantity, using least mean square error algorithm to calculate weight deviation iteration coefficient based on digital signal and digital quantity, and updating perturbation weight in real-time according to weight deviation iteration coefficient; and a perturbation eliminating module for eliminating perturbation signal in output digital signal of quantizer according to perturbation weight updated in real-time and updating perturbation weight in real-time according to weight deviation iteration coefficient, and then calculating current perturbation weight in real time to realize self-calibration of perturbation weight.

Abstract: An interface circuit and an electronic apparatus, including: a programmable current array (1), generating a first current and a second current transmitted to a common mode and differential mode generation circuit (2) according to an input code, and a third current and a fourth current transmitted to a driving bias generation circuit (3) according to the input code; the common mode and differential mode generation circuit (2), generating a common mode voltage according to the first current, and generating a high level voltage and a low level voltage according to the second current and the common mode voltage; a driving bias generation circuit (3), simulating a load according to the third and fourth currents, and generating a bias voltage based on the load and the low and high level voltages; an output driving circuit (4), converting an input signal into a differential signal in which the common mode voltage and a differential mode amplitude are configurable.

Abstract: Among the various aspects of the present disclosure is the provision of methods and systems for segmenting images and expediting a contouring process for MRI-guided adaptive radiotherapy (MR-IGART) comprising applying a convolutional neural network (CNN), wherein the CNN accurately segments organs (e.g., the liver, kidneys, stomach, bowel, or duodenum) in 3D MR images.

Abstract: The disclosure relates to a modifier composition for polyolefin, a polyolefin for packaging and a flexible packaging film. The disclosure relates to a modifier composition for polyolefin, including: (A) nano-silicon dioxide; (B) polyvinyl alcohol; (C) acrylic copolymer; and (D) Ethylene-Vinyl Acetate (EVA) copolymer. The disclosure also relates to a polyolefin for packaging, including: a polyolefin resin and a modifier composition of the polyolefin provided by the disclosure. The disclosure also relates to a flexible packaging film, of which at least a part is made of the polyolefin for packaging of the disclosure. The modifier composition of the disclosure can obviously improve the performance in the aspect of reducing residue of solvent in the polyolefin flexible packaging film.

Abstract: The disclosure relates to a modifier composition for polyolefin, a polyolefin for packaging and a flexible packaging film. The disclosure relates to a modifier composition for polyolefin, including: (A) nano-silicon dioxide; (B) polyvinyl alcohol; (C) acrylic copolymer; and (D) Ethylene-Vinyl Acetate (EVA) copolymer. The disclosure also relates to a polyolefin for packaging, including: a polyolefin resin and a modifier composition of the polyolefin provided by the disclosure. The disclosure also relates to a flexible packaging film, of which at least a part is made of the polyolefin for packaging of the disclosure. The modifier composition of the disclosure can obviously improve the performance in the aspect of reducing residue of solvent in the polyolefin flexible packaging film.