Abstract: Described are techniques for machine learning library management. The techniques include generating a table including a plurality of machine learning libraries and their current versions that are used in a deployed machine learning platform (MLP) instance, a first available version upgrade for a first machine learning library of the plurality of machine learning libraries, a security indication associated with the first available version upgrade relative to a current version implemented by the first machine learning library, and a compatibility indication between the first available version upgrade and the current version of the first machine learning library. The techniques further include generating a recommendation related to upgrading the first machine learning library based on the security indication and the compatibility indication.

Abstract: This application discloses a semantic learning-based down-sampling method of point cloud data of an aircraft, including: (S1) constructing a multi-input encoder based on feature learning according to point cloud semantic learning principle; inputting the point cloud data of the aircraft and feature point data into the multi-input encoder for feature fusion followed by decoding using a decoder the multi-input feature fused data to obtain to-be-measured data; (S2) constructing and training a point cloud feature weight calculation network based on semantic learning to acquire a feature weight of each point in the to-be-measured data; and (S3) performing spatial weighted sampling on the feature weight of each point in the to-be-measured data followed by down-sampling based on Gaussian distribution-based spatial sampling principle.

Abstract: The present disclosure discloses a digital hydraulic assisted braking system with a high dynamic response and a control method thereof. The system includes a two-position two-way digital switch valve A, a controller, an electromagnetic two-position two-way proportional reversing valve, a two-position two-way digital switch valve B, a displacement detection system, and a pressure detection system. When a vehicle starts, a control system of the present disclosure maintains a preload state and responds to a braking at any time. During an emergency braking, the braking system is open. When the vehicle is shut down, the braking system is closed. Compared with an existing braking method, by implementing the braking method of the present disclosure, a braking response time is greatly shortened, a dynamic performance of a braking response period is improved, and a safety of vehicle braking is further guaranteed.

Abstract: A game controller for a mobile device, the game controller including a first handle, a second handle, a bridge, and a flat, flexible cable. The first handle is configured to contact and support a mobile device. The first handle includes a user-accessible, first hardware interface on a main body portion of the first handle that is configured to accept touch inputs. The second handle is configured to contact and support the mobile device. The second handle includes a user-accessible, second hardware interface on a main body portion of the second handle that is configured to accept touch inputs. The bridge couples the first handle to the second handle. The bridge is in sliding engagement with the first handle and the second handle. The flat, flexible cable is configured to conduct an electrical signal between the first handle and the second handle.

Abstract: A rotating cushioning and assisting mechanism comprises a rotating outward expanding member, an elastic return member, and an inner support heterogeneous member; the rotating outward expanding member comprises a first rotating member and a second rotating member, which enclose to form an expandable compartment; the elastic return member is connected to the free ends of the first rotating member and the second rotating member; and the inner support heterogeneous member is rotationally disposed in the expandable compartment. When an external force drives the inner support heterogeneous member to rotate in the expandable compartment, a work done by the force exerted by the inner support heterogeneous member is converted into elastic potential energy to be stored; when the external force is over, the elastic potential energy is released and converted into kinetic energy to help the free ends of the two rotating members to move close.

Abstract: Provided are a computer-implemented method, a system, and a computer program product. The method comprises extracting features from a plurality of base models in an ensemble model. The plurality of base models are configured to provide respective prediction results. The ensemble model is configured to provide an overall prediction result from the prediction results of the plurality of base models. The features are associated with time performance of the base models. The method further comprises clustering the plurality of base models into a plurality of clusters based on the extracted features. The method further comprises assigning the plurality of base models to a plurality of parallel computation units based on the plurality of clusters.

Abstract: A few-shot defect detection method based on metric learning, including: (S1) performing data enhancement on a to-be-detected few-shot defect data set through a G2-Generative adversarial network (G2-GAN); (S2) extracting features of a defect data set similar to the to-be-detected few-shot defect data set based on an adaptive convolution kernel-based convolutional neural network (SKM-CNN) to generate a pre-training model; and (S3) transferring the pre-training model to a few-shot defect detection network (S2D2N) based on metric learning; and performing target feature extraction and metric learning in sequence to realize rapid identification and location of defects.

Abstract: This invention is in the field of medicinal chemistry. In particular, the invention relates to a new class of small-molecules having a piperazine or piperidine structure which function as either inhibitors of pan-T-type calcium channel activity (e.g., CaV3.1 voltage gated calcium channel activity) (e.g., CaV3.2 voltage gated calcium channel activity) (e.g., CaV3.3 voltage gated calcium channel activity) (e.g., depolarization-induced calcium influx) or specific inhibitors of CaV3.2 voltage gated calcium channel activity, and their use as therapeutics for the treatment and/or prevention of pan-T-type calcium channel related pain (e.g., CaV3.1 related pain) (e.g., CaV3.2 related pain) (e.g., CaV3.3 related pain) (e.g., HIV-associated peripheral sensory neuropathy, chemotherapy-induced peripheral neuropathy (CIPN), spinal nerve ligation (SNL) induced neuropathy) (e.g., tonic, neuropathic, and/or inflammatory pain) and related conditions.

Abstract: Disclosed are a computer-implemented method, a system and a computer program product for model exploration. Model feature importance of each model of a plurality of models can be obtained, the plurality of models can be grouped into a plurality of model clusters based on the model feature importance of each model, and the model feature importance can be presented by box-plot or confidence interval.

Abstract: The present disclosure provides a method and system for calculating water-land-forage-livestock balance in a family pasture by taking forage quality into account. The method takes a family pasture as a calculation unit and starts from a water circulation process, various types of groundwater recharges of the family pasture are calculated, and an available groundwater quantity is calculated by using an exploitable coefficient method, and undergoes water-land balance calculation with an irrigation water demand and a drinking water demand of people and livestock; and total digestible nutrients of various types of forage are used to convert each type of forage into standard hay for forage-livestock balance calculation, so as to determine a maximum supportable planting area of irrigated artificial grasslands and a maximum supportable quantity of livestock raised in the family pasture.

Abstract: The present invention discloses a method and an apparatus for controlling an air conditioner, and a computer storage medium, and relates to the technical field of intelligent household appliances. The method includes acquiring a current physical characteristic parameter of an air conditioner user in a current sampling timeframe; and adjusting either or both of a current set temperature and a current compressor frequency of the air conditioner according to the current physical characteristic parameter and current energy consumption of the air conditioner when the current physical characteristic parameter falls within a set range of parameters in sleep. Therefore, energy conservation and a comfortable user experience are compatible, thereby providing more functions for the control of the air conditioner in the sleep mode.

Abstract: The technology presented herein enables the use of a clustering algorithm to identify additional malicious domains based on known malicious domains. A domain identifier system identifies a first plurality of domain names associated with a malicious domain campaign and seeding a first clustering algorithm with the first plurality of domain names. After seeding the first clustering algorithm, the domain identifier system uses the first clustering algorithm to process passive domain name system (DNS) records to identify and group a second plurality of domain names associated with the malicious domain campaign.

Abstract: A computer-implemented system, platform, programing product, and/or method for improving transformation selection in an ensemble machine learning (ML) model that includes: providing all base ML models of the ensemble ML model; identifying all of a plurality of Derived Fields in all the base ML models; performing a Derived Field run prediction analysis for all the Derived Fields; computing the Derived Field Importance Weight for Field (DFIW4F) and the Derived Field Importance Weight for Model (DFIW4M) for all the Derived Fields; clustering all the Derived Fields into a plurality of Derived Field clusters, wherein each Derived Field cluster is based upon the DFIW4M and the DFIW4F for the Derived Field; sorting all the Derived Field clusters by best cluster based upon DFIW4M and DFIW4F; and running the base ML models based upon the Derived Fields in the best Derived Field cluster until sufficient base ML models have been run.

Abstract: The present disclosure relates to data transmission methods and apparatuses. In one example method, a receiving end obtains a transmission resource, and feeds back first information to a transmitting end based on the transmission resource. The first information is determined based on a channel state of a first channel, and the first information indicates whether retransmission is required or indicates whether a transmission mode is to be adjusted.

Abstract: The present disclosure relates to radar signal processing, and a harmonic radar based on a field programmable gate array (FPGA) and deep learning. Specifically, a signal processing module generates a baseband linear frequency modulation (LFM) signal, converts the baseband LFM signal into an analog signal, and mixes the analog signal with a local carrier frequency signal to obtain a radio frequency (RF) transmitting signal.

Abstract: A multicast service transmission method includes: a management device that receives a first message; the management device based on the first message, instructs a gateway device to send a data packet of the first multicast service to the terminal device or the access network device, or the management device instructs a gateway device to stop sending a data packet of the first multicast service to the terminal device or the access network device.