Abstract: An auxiliary diagnosis method for Parkinson's disease (PD) based on static and dynamic features of facial expressions is provided. Video data of various facial expressions performed by a to-be-tested patient is acquired and pre-processed to extract a plurality of optimal facial expression images corresponding to the various facial expressions. A similarity discrimination is performed on a synthesized happy facial expression image of the to-be-tested patient in a healthy state and an extracted happy facial expression image to obtain similarity features. Distances between multiple facial key points in the various facial expression images are calculated to obtain multiple key features, which are spliced with the plurality of key features to form static features. Coordinate change degrees of multiple facial key points of eyelids and mouth are calculated to obtain dynamic features. A classification prediction result of PD is output based on the spliced features.

Abstract: The present disclosure may provide a method and a system for visual data analysis and interaction. The method includes: displaying a visualization region in a user interface, the visualization region including a set of data; generating a data graph based on the set of data; in response to receiving a first operation instruction from a user, obtaining a data processing result by processing at least a portion of the set of data based on the data graph; and in response to receiving a second operation instruction from the user, displaying the data processing result and updating a display state of the visualization region.

Abstract: A fuzzy cloud-based risk assessment method for reservoir operation schemes, including: collecting basic data of target reservoirs; constructing optimal operation model of conventional reservoirs to obtain model calculation results; acquiring change process of operation characteristics during whole operating period according to model calculation results, and constructing multi-level reservoir multi-dimensional risk assessment index system; dividing different risk level intervals according to multi-level reservoir multi-dimensional risk assessment index system; obtaining large number of sample data xij of reservoir risk index under corresponding working conditions by multiple parallel calculations to conduct risk assessment; calculating cloud digital features of different indexes by inverse cloud generator; and weighting indexes in index layer and criterion layer by Analytic Hierarchy Process to obtain multi-dimensional risk assessment results.

Abstract: Examples provide a system and method for identifying unpaid items in real-time using computer vision object detection and recognition models. Images of a cart are selected based on proximity of the cart to one or more anchor points. The object detection and recognition models analyze the image data and identify a set of items in the selected cart. An e-receipt including a set of paid items is selected from a plurality of active electronic receipts based on matching the set of identified items to the set of paid items. Any unmatched items are added to a set of predicted unpaid items. When a receipt corresponding to the selected e-receipt is scanned, a notification identifying the set of predicted unpaid items is provided to a user device for display, enabling a user to identify any unpaid items in a basket of items quickly and accurately in real-time at store exit.

Abstract: A method for early diagnosis of Parkinson's disease based on multimodal deep learning is provided. Audio-visual data of a to-be-diagnosed subject while performing a speech task is acquired. The audio-visual data are preprocessed to extract a plurality of audio segments and a plurality of video segments. A face image sequence is extracted from each of the plurality of video segments. A Mel-spectrogram of each of the plurality of audio segments is calculated. The face image sequence and the Mel-spectrogram are input into a multimodal deep learning model to output a classification result for Parkinson's disease early diagnosis of the to-be-diagnosed subject. A system for early diagnosis of Parkinson's disease based on multimodal deep learning is also provided.

Abstract: A method for collaborative heave compensation control of a dual ship-mounted hoisting arm system including two vertical hoisting arms and two horizontal hoisting arms is provided, in which a dynamic model of the hoisting arm system is constructed based on hoisting arm position and velocity and an attitude angle of a load of the hoisting arm system; and based on the dynamic model, an optimal control strategy is obtained according to a control objective and an optimization objective under multiple constraint conditions to control the hoisting arm action, where the control objective is to track a hoisting arm reference compensation trajectory during the heave motion, the optimization objective is to minimize a tracking error, and the constraint conditions include a hoisting arm action constraint, and a position and velocity constraint of each hoisting arm after action. A system for implementing such method is also provided.

Abstract: In some embodiments, provided is soft grippers, methods of making the same, systems and methods of controlling the same. In one embodiment, the soft gripper comprises a main body comprising a suction cup portion and a neck portion; and a contact membrane, wherein the neck portion comprises a neck chamber and the suction cup portion comprises a suction cup chamber therein, together form a main chamber that is configured to be in gas communication with a first pneumatic source and to receive a jamming material, and wherein the neck portion comprises at least one assisted chambers therein disposed around the neck chamber and configured to be in gas communication with a second pneumatic source. Other example embodiments are described herein. In certain embodiments, provided soft grippers enable seamless transformation between suction gripper configuration and jamming gripper configuration, thereby enhanced grasping capability and versatility.

Abstract: A transmission driver for serial communication includes first multiplexing circuitry configured to partially serialize a data group into data subgroups based on an in-phase clock, and to delay a quadrature clock corresponding to the in-phase clock. The delay is based on latency of the partial serialization. The transmission driver also includes second multiplexing circuitry having a source-series terminated (SST) driver configured to serialize the data subgroups into a serial data stream based on the delayed quadrature clock. The first multiplexing circuitry may be configured to partially serialize the data group into the data subgroups by arranging a four-bit data group into a pair of two-bit data groups, and the second multiplexing circuitry may be configured to serialize the data subgroups into the serial data stream by arranging the pair of two-bit data groups into the serial data stream.

Abstract: The invention provides a multi-dimensional broad-spectrum clinical in-situ testing equipment designed to evaluate the material properties of plantar soft tissue. The equipment comprises the following features: 1. A testing table with a designated area corresponding to the sole of the foot; 2. A vertical reciprocating stress-strain testing unit mounted on the testing table, for applying vertical tensile and compressive stresses to the plantar and measuring the stress-strain responses; 3. A shear stress-strain testing unit, mounted on the testing table, for applying shear stresses to the plantar and measuring the stress-strain responses; 4. A torque stress-strain detection unit, positioned on the testing stage, for applying torque to the plantar and measuring the stress-strain responses; 5. A lifting mechanism that facilitates the vertical movement of the three testing units.

Abstract: A showerhead assembly may include a base member configured to be fluidly connected to a shower pipe, and defining a cavity in which a water filter is disposed. Magnet(s) may be positioned at a front wall opposite a wall that is proximate the shower pipe. A handheld showerhead may be fluidly connected to the base member. The handheld showerhead may include (i) a rear wall and (ii) a front face. Second magnet(s) may be positioned and arranged to be attracted to the first magnet(s). The handheld showerhead may be altered from a first elevation angle to a second elevation angle while magnetically retained by the base member.

Abstract: A method for collaborative heave compensation control of a dual ship-mounted hoisting arm system including two vertical hoisting arms and two horizontal hoisting arms is provided, in which a dynamic model of the hoisting arm system is constructed based on hoisting arm position and velocity and an attitude angle of a load of the hoisting arm system; and based on the dynamic model, an optimal control strategy is obtained according to a control objective and an optimization objective under multiple constraint conditions to control the hoisting arm action, where the control objective is to track a hoisting arm reference compensation trajectory during the heave motion, the optimization objective is to minimize a tracking error, and the constraint conditions include a hoisting arm action constraint, and a position and velocity constraint of each hoisting arm after action. A system for implementing such method is also provided.

Abstract: The disclosure belongs to the field of microorganisms, and in particular relates to a strain of Akkermansia muciniphila and a product and application thereof. The A. muciniphila is AKK PROBIO, with a preservation number of CGMCC No. 20955. AKK PROBIO of the disclosure has good tolerance, high safety, wide indications, and a good therapeutic effect, can prevent and treat diseases such as colitis, colorectal carcinoma, Alzheimer's disease, and gouty arthritis, and has very good clinical application prospects.

Abstract: An optimized method for identifying robot pouring regions based on hierarchical processing and connectivity maximization and a system thereof, wherein the optimized method includes: rough identification stage: identifying and positioning, according to working characteristics of mobile robot, target container through vision module when a distance from target region is relatively far, and generating information collection position of target container required for fine identification according to the positioning; fine identification stage: obtaining, by mobile robot, information of target container and source container, and generating corresponding connectable domains, then identifying and optimizing robot pouring region by using connectivity maximization method. It solves problems of autonomous identification of pouring region of the mobile robot, can be applied to most target containers and source containers, and enhances the generalization ability of robot pouring manipulation skills.

Abstract: The present disclosure relates to an excavator, a precise control method and system therefor, a vehicle terminal and a storage medium. The precise control method for the excavator comprises: presetting a plurality of work modes of the excavator, and an action rate and action coefficient corresponding to each working mode of the plurality of work modes; and performing work mode switching according to a handle input signal.

Abstract: An application of Bacillus coagulans in preparing a medication for improving functional decline of organisms caused by hyperglycemia and hyperlipidemia is provided in the present application, belonging to the technical field of microbial strains. A Bacillus coagulans is disclosed in the present application, and the Bacillus coagulans is preserved in the China General Microbiological Culture Collection Center (CGMCC), Institute of Microbiology Chinese Academy of Sciences on Nov. 10, 2021, with a preservation number of CGMCC No.23766 and a preservation address of Institute of Microbiology, Chinese Academy of Sciences, No.3, No.1 Beichen West Road, Chaoyang District, Beijing.

Abstract: A method and system for robotic multi-peg-in-hole assembly based on hierarchical reinforcement and distributed learning, including: establishing a master-control assembly-strategy model based on deep reinforcement learning by using data of states and actions of a robot; constructing a plurality of sub-process networks based on different assembly interaction environments, updating and training the master-control assembly-strategy model by using interaction data of the robot obtained by the constructed plurality of sub-process networks, and obtaining a trained master-control assembly-strategy model; and controlling and instructing the robot to execute an assembly task of a robotic multi-peg-in-hole assembly by using the trained master-control assembly-strategy model.

Abstract: A wireless charging apparatus is provided. The apparatus uses a multi-feed, multi-mode, and resonance coherent working mechanism and wirelessly charges an energy receiving apparatus through a focusing field, thereby effectively improving wireless charging efficiency and implementing miniaturization of an energy receiving antenna. The wireless charging apparatus includes a cavity (1) and a phased array antenna. The cavity (1) includes an even number of side faces (2). The even number of side faces (2) are parallel in pairs. Each side face (2) has a capability of reflecting an electromagnetic wave. The phased array antenna includes an antenna array. The antenna array includes a plurality of antennas (3). The plurality of antennas (3) are disposed on the even number of side faces (2) and are configured to emit electromagnetic waves to charge an energy receiving device (4) placed in the cavity (1).

Abstract: A water faucet filter assembly may include a horizontal orientation including a filter element viewable through a front cover of the filter assembly and an optional skin treatment element adapter that may receive a water-dissolvable, skin treatment element through which water filtered by the filter element passes before being dispensed to a user.

Abstract: A human balance sensor for assessing the risk of the user falling includes a transparent glass plate, a latex sheet located on the top surface of the glass plate, a light source located so as to inject light into edge of the glass plate and a high resolution camera located below the glass plate so as to capture light diffused from the glass plate when pressure is applied thereto by the user's foot. Based on the principle of Frustrated Total Internal Reflection (FTIR), when user stands with his feet on the glass plate a condition of total internal reflection is eliminated at pressure locations due to the pressure from the feet, and diffused light passes from the bottom surface of the glass plate and forms a haptic image of the contact area of the feet which can be analyzed over time to determine the user's ability to balance, and hence their risk of a fall.