A Fully-Integrated Analog Machine Learning Classifier for Breast Cancer Classification

We propose a fully integrated common-source amplifier based analog artificial neural network (ANN). The performance of the proposed ANN with a custom non-linear activation function is demonstrated on the breast cancer classification task. A hardware-software co-design methodology is adopted to ensure good matching between the software AI model and hardware prototype. A 65 nm prototype of the proposed ANN is fabricated and characterized. The prototype ANN achieves 97% classification accuracy when operating from a 1.1 V supply with an energy consumption of 160 fJ/classification. The prototype consumes 50 μ W power and occupies 0.003 mm 2 die area.

Wave physics as an analog recurrent neural network

Analog machine learning hardware platforms promise to be faster and more energy efficient than their digital counterparts. Wave physics, as found in acoustics and optics, is a natural candidate for building analog processors for time-varying signals. Here, we identify a mapping between the dynamics of wave physics and the computation in recurrent neural networks. This mapping indicates that physical wave systems can be trained to learn complex features in temporal data, using standard training techniques for neural networks. As a demonstration, we show that an inverse-designed inhomogeneous medium can perform vowel classification on raw audio signals as their waveforms scatter and propagate through it, achieving performance comparable to a standard digital implementation of a recurrent neural network. These findings pave the way for a new class of analog machine learning platforms, capable of fast and efficient processing of information in its native domain.

Virtual Manufacturing and Simulation of Transplanting Mechanism with Non-Circular Gears

This article deploys an exploratory development of super rice High-performance transplanter transplanting mechanism with non-circular Gears by dint of rice transplanter transplanting mechanism analog machine accroding to pro/E software.This research is first to building a model of non-circular Gears designed by researcher before,and then assemble the whole to obtain the result of virtual manufacturing with non-circular Gears, and assemble it on the test machine of rice transplanter test machine ,also analysis the Kinematic Principle of Simulation result by pro/E software.Finally, make the motion trail conform to the agronomy requirement according to correcting and consummating the fember unqualified.

Automatic Measurement for Internal Resistance of Battery in Uninterruptible Power Source

Automatic Measurement for Internal Resistance of Battery in Uninterruptible Power SourceThis paper considers the approach to the measurement of internal resistance of the battery in the uninterruptible power sources (UPSs [1]). Advantages of the approach are the measurements in power supplies without switching-off the battery, simplicity in realization of algorithm.The basic expressions of the theory used in the method about internal resistance of the storage battery are considered.The function chart of construction of an analog part of the scheme, and also algorithm of action of the scheme of logic of decision-making are considered.Construction of the tracing generator of load, the important part in realization of the method is stated. The use of the analog machine for processing of the results of measurements and a differential method of measurement with the purpose of increase the accuracy of the method is offered.