Supervised Contrastive Learning Framework and Hardware Implementation of Learned ResNet for Real-time Respiratory Sound Classification.

This paper presents a supervised contrastive learning (SCL) framework for respiratory sound classification and the hardware implementation of learned ResNet on field programmable gate array (FPGA) for real-time monitoring. At the algorithmic level, multiple techniques such as features augmentation and MixUp are combined holistically to mitigate the impact of data scarcity and imbalanced classes in the training dataset. Bayesian optimization further enhances the classification accuracy through parameter tuning in pre-processing and SCL.

Morphology genetic 3D hierarchical SnOmicrostructures constructed by Sub 5 nm nanocrystals for highly sensitive ethanol-sensor.

SnOis widely used for ethanol-sensing applications due to its excellent physicochemical properties, low toxicity and high sensitivity. However it is a challenge to construct 3D-hierarchical structures with sub 5 nm primary grain particle, which is the optimized size for ethanol sensor. Herein, genetic tri-level hierarchical SnOmicrostructures are synthesised by the genetic conversion of 3D hierarchical SnSflowers assembled by ultrathin nanosheets.

A hybrid intelligent multi-fault detection method for rotating machinery based on RSGWPT, KPCA and Twin SVM.

This paper proposes a hybrid intelligent method for multi-fault detection of rotating machinery, in which three methods, i.e. including the redundant second generation wavelet package transform (RSGWPT), the kernel principal component analysis (KPCA) and the twin support vector machine (TWSVM), are combined.

Novel Downhole Electromagnetic Flowmeter for Oil-Water Two-Phase Flow in High-Water-Cut Oil-Producing Wells.

First, the measuring principle, the weight function, and the magnetic field of the novel downhole inserted electromagnetic flowmeter (EMF) are described. Second, the basic design of the EMF is described. Third, the dynamic experiments of two EMFs in oil-water two-phase flow are carried out.

Manchester code telemetry system for well logging using quasi-parallel inductive-capacitive resonance.

In this paper, a quasi-parallel inductive-capacitive (LC) resonance method is proposed to improve the recovery of MIL-STD-1553 Manchester code with several frequency components from attenuated, distorted, and drifted signal for data telemetry in well logging, and corresponding telemetry system is developed. Required resonant frequency and quality factor are derived, and the quasi-parallel LC resonant circuit is established at the receiving end of the logging cable to suppress the low-pass filtering effect caused by the distributed capacitance of the cable and provide balanced pass for all the three frequency components of the Manchester code. The performance of the method for various encoding frequencies and cable lengths at different bit energy to noise density ratios (Eb/No) have been evaluated in the simulation.