Deployment of a cloud pipeline for real-time visual inspection using fast streaming high-definition images

We investigate the challenges of building an end-to-end cloud pipeline for real-time intelligent visual inspection system for use in automotive manufacturing. Current methods of visual detection in automotive assembly are highly labor intensive, and thus prone to errors. An automated process is sought that can operate within the real-time constraints of the assembly line and can reduce errors. Components of the cloud pipeline include capture of a large set of high-definition images from a camera setup at the assembly location, transfer and storage of the images as needed, execution of object detection, and notification to a human operator when a fault is detected. The end-to-end execution must complete within a fixed time frame before the next car arrives in the assembly line. In this article, we report the design, development, and experimental evaluation of the tradeoffs of performance, accuracy, and scalability for a cloud system.     

On-line estimation of kinetic parameters in anaerobic digestion using observer-based estimators and multiwavelength fluorometry.

Observer-based estimators (OBE) were used for estimation of state variables and kinetic parameters in an anaerobic digestion (AD) process. A simplified first-order model with time-varying kinetic parameters was used to design an OBE for kinetic parameter estimation. This approach was validated on a laboratory-scale anaerobic reactor equipped with a multiwavelength fluorometer for on-line measurements of COD and VFA concentrations in the reactor effluent. The proposed estimators provide continuous adjustment of kinetic parameters and can be used for predictions of state variables between samples acquisition and during sensor failure.     

A note on the variance of rank-based selection strategies for genetic algorithms and genetic programming

This paper evaluates different forms of rank-based selection that are used with genetic algorithms and genetic programming. Many types of rank based selection have exactly the same expected value in terms of the sampling rate allocated to each member of the population. However, the variance associated with that sampling rate can vary depending on how selection is implemented. We examine two forms of tournament selection and compare these to linear rank-based selection using an explicit formula. Because selective pressure has a direct impact on population diversity, we also examine the interaction between selective pressure and different mutation strategies.     

Motion Perception Using Analog VLSI

Motion perception is arguably a fundamental mechanism used by natural species to accomplish a number of tasks, such as navigating freely in an unknown environment. Traditional motion perception methods tend to be computationally intensive, requiring powerful computers and large memories. However, by copying biological mechanisms, such as elementary motion discrimination at the early stages of the visual processing paths, it should be possible to build small and efficient motion perception systems. This paper describes the manner in which a simple motion perception model based on the insect visual system has been implemented using mixed analog/digital VLSI. The device has been fabricated in a 2 micron double metal, double polysilicon process, and comprises 61 photo-detectors, and associated analog and digital circuitry. While not entirely successful in that component mismatches hamper the detection of dark-to-bright changes in contrast, the results clearly show the feasibility of using such a device in autonomous control systems.     

Investigations of high-performance GaAs solar cells grown on Ge-Si/sub 1-x/Ge/sub x/-Si substrates

High-performance p/sup +//n GaAs solar cells were grown and processed on compositionally graded Ge-Si/sub 1-x/Ge/sub x/-Si (SiGe) substrates. Total area efficiencies of 18.1% under the AM1.5-G spectrum were measured for 0.0444 cm/sup 2/ solar cells. This high efficiency is attributed to the very high open-circuit voltages (980 mV (AM0) and 973 mV (AM1.5-G)) that were achieved by the reduction in threading dislocation density enabled by the SiGe buffers, and thus reduced carrier recombination losses. This is the highest independently confirmed efficiency and open-circuit voltage for a GaAs solar cell grown on a Si-based substrate to date. Larger area solar cells were also studied in order to examine the impact of device area on GaAs-on-SiGe solar cell performance; we found that an increase in device area from 0.36 to 4.0 cm/sup 2/ did not degrade the measured performance characteristics for cells processed on identical substrates. Moreover, the device performance uniformity for large area heteroepitaxial cells is consistent with that of homoepitaxial cells; thus, device growth and processing on SiGe substrates did not introduce added performance variations. These results demonstrate that using SiGe interlayers to produce "virtual" Ge substrates may provide a robust method for scaleable integration of high performance III-V photovoltaics devices with large area Si wafers.