17results about How to "Avoid selectivity" patented technology

The invention discloses an intelligent driving environment sensing method and system based on multi-modal data fusion, and relates to the technical field of automatic driving, and the method comprises the steps: firstly obtaining the position information of a vehicle through a GPS, and starting an auxiliary positioning mechanism if the GPS signal is weak; multi-modal data acquisition and preprocessing: after an auxiliary positioning mechanism is started, a vehicle acquires surrounding environment information through an RGB camera, a laser radar and an IMU sensor; performing feature extraction on the RGB image by using an improved deep convolutional neural network, and generating a high-precision 3D bounding box through a region suggestion network; and multi-modal information is fused through a constructed efficient image reasoning framework. Based on multi-modal data fusion and an environment perception result, the method not only can carry out accurate target identification on the surrounding environment in the automatic driving process, but also can carry out global and local path planning.

The invention relates to the technical field of image processing, and provides a brain network analysis method and system based on adaptive graph collaborative contrast learning. The method comprises the following steps: dividing a brain into a plurality of brain regions, extracting an average time sequence of each brain region, and calculating a Pearson's correlation coefficient between every two brain regions; according to the Pearson's correlation coefficient, selecting edges meeting requirements, and constructing a brain map by taking the brain region as a node; performing learnable attribute augmentation on each brain graph by adopting a graph attribute augmentation device to obtain two attribute augmentation views and an attribute augmentation probability matrix; a graph structure augmentation device is adopted to carry out learnable structure augmentation on each brain graph, and two structure augmentation views and a structure augmentation probability matrix are obtained; training a feature extractor, a graph attribute augmentor, a graph structure augmentor and a classifier by utilizing graph collaborative contrast learning; based on the brain map, a trained feature extractor is adopted to extract brain map features, and then a trained classifier is adopted to carry out brain disease classification on the brain map features.

The invention is suitable for the technical field of vehicle diagnosis, and provides a remote diagnosis method and system of a vehicle, a storage medium and electronic equipment. The remote diagnosis method of the vehicle comprises the steps of obtaining vehicle bus data of the vehicle; based on a target prediction model obtained through pre-training, the adaptation probability of the vehicle bus data and the multiple alternative bus configuration files is determined, the target prediction model is obtained by training an initial neural network model based on multiple pieces of historical vehicle diagnosis data, and each piece of historical vehicle diagnosis data comprises the historical vehicle bus data and the multiple alternative bus configuration files; the bus configuration file is matched with the historical vehicle bus data; determining a target configuration file adapted to the vehicle bus data in the plurality of alternative bus configuration files according to the adaptation probability of the vehicle bus data and the plurality of alternative bus configuration files; and performing remote diagnosis on the vehicle according to the target configuration file. The technical problem that an existing vehicle remote diagnosis method is inaccurate in configuration file adaptation is solved.

The invention provides a field self-adaption method, a field self-adaption assembly, electronic equipment and a readable medium, and belongs to the technical field of computers. The method may be applied to a pre-trained initial model obtained by training on a first sample derived from a synthetic domain. Obtaining a first feature extracted from a second sample by a first feature extraction module in the initial model, wherein the second sample is derived from a natural domain and a synthetic domain; the source domain of the second sample can be judged according to the first feature, the antagonism loss absolute value of the first feature is determined based on the source domain, and the first feature extraction module is updated through gradient inversion in the reverse process with the purpose of maximizing the antagonism loss absolute value. On the basis, the method can realize the domain self-adaption of feature extraction, reduces the requirements on the number of natural domain samples and feature tags, can flexibly cope with the domain self-adaption requirements of a complex model, and can be flexibly applied in a plug-and-play mode.

The application discloses a kind of multi-level control mode adaptive switching method and system based on task constraint, different task type identification and corresponding task constraint strategy information are issued by remote control center for different task types, nest side edge computing controller continuously acquires network, task and unmanned aerial vehicle state in task start preparation stage and task execution process, dynamically determines the most suitable target control mode, and when target control mode is inconsistent with current control mode, control right handover, state synchronization and instruction semantic level switching are performed, to realize the coordinated and consistent adjustment of control mode, control right attribution, task state machine and instruction semantics.The application improves the task execution continuity, safety and stability of unmanned aerial vehicle system under different network conditions and task constraints.

The present invention discloses a compound of formula I, a composition including the same and use thereof, wherein A, X, Y, L, M and Ware as defined herein. The compound disclosed in the present invention can be used for treating diseases related to over-activation or over-expression of JAK3 kinase, such as autoimmune diseases, lung injury, and organ transplant rejection. In vitro experiments show that this series of compounds have a good inhibitory activity on the JAK3 kinase and have good application prospects in the field of medicine.

This invention proposes a method for denoising vibration signals from structural health monitoring based on a hybrid neural network. This method, implemented according to embodiments of the invention, eliminates the need for prior signal knowledge and manual parameter settings. It effectively removes various noise types from structural health monitoring vibration signals, significantly improves the signal-to-noise ratio, and reduces the root mean square error, achieving efficient and automated noise reduction of vibration signals.

The invention discloses a device and a method for separating reaction products from an o-cresol device, which are characterized in that non-condensable gas, light components and heavy components of reaction products from a reaction unit are separated in a flash evaporation unit, methanol, anisole and part of water are separated from the light components through a methanol removal unit, anisole is separated from high-concentration anisole, methanol and water through an extraction unit, and the high-concentration anisole is separated from the methanol and the water through a flash evaporation unit. Carrying out phenol and water separation on a phenol and water mixture discharged from the bottom of the methanol removal tower in an azeotropic dehydration unit; and heavy components discharged from the flash evaporation unit are subjected to phenol recovery through a phenol recovery unit, and phenol-free mixed phenol is further separated into an o-cresol product and a 2, 6-xylenol product in an o-cresol separation unit. By adopting a method of combining rectification, azeotropic distillation and liquid-liquid extraction, the phenol-methanol alkyl reaction product can be efficiently separated, the byproduct anisole is effectively separated, the influence of the byproduct on the reaction selectivity is reduced, the mass fraction of the o-cresol product is greater than or equal to 99.5%, the discharge of phenol-containing wastewater is avoided through azeotropic distillation, and the production cost is reduced. The energy consumption and the cost are reduced.

This invention relates to a method and system for suppressing baseline drift in electrocardiogram (ECG) signals based on cascaded singular spectrum analysis (SSA). The method includes: acquiring ECG signal data affected by baseline drift, setting the number of layers i = 1; and extracting baseline drift noise n from the ECG signal data affected by baseline drift using SSA with a window length of 2. i With ECG signal components o i Its central electrical signal ECG i Obtained through a formula; calculate baseline drift noise n. i With electrocardiogram (ECG) signal i inner product IP i Determine if the inner product has reached its minimum value. If the inner product has reached its minimum value, output the ECG signal of the current layer. i As a final result of suppressing baseline drift, otherwise, the baseline drift noise n i Using ECG signal data affected by baseline drift and incrementing the layer number i by 1, repeat the above extraction and calculation operations until the inner product reaches its minimum value, then output the ECG signal of the current layer. i .

The present invention relates to the technical field of transport path planning, and in particular to a transport path planning system for a material storage center, comprising an order generation module, an in-warehouse path analysis module, an out-warehouse path analysis module, an in-warehouse path planning module, an out-warehouse path planning module, a server, a data communication module, a processor and a display terminal; the present invention obtains the outbound order of the material storage center, extracts the storage location information and the destination location information of the material, and sends it to the server for storage, and then performs real-time monitoring and analysis on the in-warehouse path and out-warehouse path parameters of the target transport vehicle, generates a comprehensive evaluation coefficient of the in-warehouse path and the out-warehouse path, and dynamically plans the optimal in-warehouse and out-of-warehouse passage path based on the comprehensive evaluation coefficient, thereby achieving not only reducing the ineffective driving of vehicles in the warehouse, but also optimizing the external transport path in real time, effectively improving the transport efficiency and reducing the logistics cost.

This invention discloses a multi-level control mode adaptive switching method and system based on task constraints. For different task types, the remote control center issues different task type identifiers and corresponding task constraint strategy information. During the task initiation preparation phase and task execution, the nest-side edge computing controller continuously collects network, task, and UAV status data, dynamically determines the most suitable target control mode, and performs control handover, state synchronization, and instruction semantic level switching when the target control mode is inconsistent with the current control mode. This achieves coordinated and consistent adjustment of control mode, control ownership, task state machine, and instruction semantics. This invention improves the continuity, security, and stability of UAV system task execution under different network conditions and task constraints.

A method and an apparatus for height-based cell selection or reselection in a wireless communication system are provided. A wireless device receives information regarding (i) a first cell reselection priority associated with a first altitude range and (ii) a second cell reselection priority associated with a second altitude range. A wireless device monitors a current height of the wireless device. The wireless device determines a cell reselection priority as a first cell reselection priority or a second cell reselection priority based on the current height. The wireless device performs cell reselection based on the determined cell reselection priority.

The utility model provides wet etching equipment for wafers and a feeding system of the wet etching equipment. The feeding system comprises a mixing device and a liquid silicon dioxide supply part, the mixing device comprises a mixed liquid storage part and a circulating mechanism; the mixed liquid storage part is connected with the liquid silicon dioxide supply part; the circulating mechanism comprises a circulating pipeline and a first pump, two ends of the circulating pipeline are respectively communicated with the mixed liquid storage part, and the first pump is arranged on the circulating pipeline. The mixed liquid storage part is used for accommodating a phosphoric acid solution and receiving liquid silicon dioxide from the liquid silicon dioxide supply part, and the liquid silicon dioxide and the phosphoric acid solution are uniformly mixed under the action of the first pump to form a uniform silicon dioxide-phosphoric acid solution. The feeding system is applied to the wet etching equipment for wafers so as to carry out acid exchange operation on the wet etching equipment, and the change of the etching rate and the selection ratio of SIN / SiO2 caused by the great reduction of the concentration of silicon ions in an etching tank due to acid exchange can be avoided.

A substituted triazinylmethylcycloalkylcarboxylic acid derivative having a structure as shown in formula (I). In addition, further disclosed are a pharmaceutically acceptable salt, a stereoisomer, a pharmaceutical composition and the use of the derivative. The compound has significant P2X3 inhibitory activity and selectivity, and is high in application value.

The invention discloses purification equipment based on natural gas catalytic cracking hydrogen production, and relates to the technical field of hydrogen purification, the purification equipment based on natural gas catalytic cracking hydrogen production comprises a separator, the bottom end of the separator is communicated with a filter pipe, the bottom end of the filter pipe is communicated with a first feeding pipe, the top end of the separator is communicated with a first discharging pipe, and the top end of the separator is communicated with a second discharging pipe; a second discharging pipe communicates with the outer surface of the separator, a cleaning box is fixedly connected to the outer surface of the separator, a fixing block is rotatably connected to the interior of the cleaning box, and a membrane is detachably connected to the interior of a mounting groove formed in the surface of the fixing block. According to the utility model, the hydrogen purification efficiency is improved, the membrane blockage or pollution caused by incomplete filtration is avoided, the production interruption caused by saturated adsorption is avoided, and the continuity of the purification process is ensured.

The present invention relates to substituted benzoxaboroles having the structure comprising formula (iii), wherein r3 is selected from –ch3, –ch2ch3, –ch2=ch2, –ch2ch2ch3, –ch(ch3)2, –ch2ch2=ch2, and a cyclopropyl, r1 and r2 are each independently selected from h, -ch3, -ch2ch3, –ch2ch2ch3, and –ch(ch3)2; compositions containing such compounds, their use in therapy, including their use as antimycobacterial agents, for example in the treatment of a mycobacterial infection in a mammal, and methods for preparing such compounds.

The invention discloses a method for systematically controlling mobile operation post noise. The method comprises the following steps: identifying and distinguishing noise sources of mobile operation points; determining the standard-exceeding contribution rate of each noise source of the mobile operation point to post noise, and taking the operation point noise source with the standard-exceeding contribution rate exceeding 10% as a treatment point; determining a noise abatement point location and a noise reduction target; arranging a sound insulation cover and other sound insulation facilities for the noise treatment point, determining a noise reduction material conforming to a noise reduction target, and calculating the actual sound insulation amount of the sound insulation cover; calculating the air volume required by ventilation of the acoustic shield; arranging silencers at the air inlet and the air outlet, and calculating the silencing amount; and simulating and evaluating a flow post noise control effect. According to the method, the problem of mobile post noise treatment is systematically and comprehensively solved from the aspects of source identification, treatment target determination, economic and effective selection of noise reduction materials, safe and stable operation of equipment and the like, and the problems of disorder, high cost, poor effect, secondary potential safety hazards and the like of post noise treatment are avoided.