Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Low detectability" patented technology

A method and system for simultaneous analysis of multiple indicators of blood lipids in fingertip peripheral blood

PendingCN122081442ARealize synchronous detectionlow detectabilityMicrobiological testing/measurementColor/spectral properties measurementsVenous bloodBlood lipids
This invention discloses a method and system for simultaneous analysis of multiple lipid indicators in fingertip capillary blood, relating to the field of chemical analysis. The method includes S1: micro-sample pretreatment of fingertip blood; S1.5: sample matrix interference pretreatment; S2: multi-channel parallel specific reaction; S3: multi-band spectral synchronous detection; S4: machine learning intelligent calibration and analysis; and S5: result output and quality control verification. This method and system achieves simultaneous detection of five core lipid indicators in fingertip blood samples in a short time, with low deviation and cross-interference rates between the detection results and venous blood biochemical detection, and high matrix interference inhibition rate. It also possesses advantages of portability, speed, and accuracy, solving the problems of low detection efficiency, limited applicability, and matrix interference affecting accuracy in existing technologies.
Owner:SHENZHEN DONGYI MEDICAL LAB

A method and system for detecting abnormal driver states based on multimodal information fusion

PendingCN122313442AReduce the amount of parametersReduce computational overheadPattern recognitionDriver/operator
This invention provides a method and system for detecting abnormal driver states based on multimodal information fusion. The method includes: Step 1, acquiring real-time facial video images of the driver using an in-vehicle camera; and simultaneously acquiring the driver's voice signal using an in-vehicle microphone; Step 2, detecting driver fatigue abnormal states based on the facial video images acquired in Step 1 to obtain a fatigue probability; Step 3, preprocessing the voice signal, extracting Mel-frequency cepstral coefficients as voice features, and using a time-aware bidirectional multi-scale network for voice emotion recognition to obtain an anger probability; Step 4, adaptively weighting and fusing the fatigue probability and the anger probability to calculate a fusion risk value. This invention achieves non-contact, highly robust driver abnormal state detection, with a lightweight model and fast detection speed, making it suitable for deployment on in-vehicle edge devices.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY