The training of a Multi-Layer Perceptron (MLP) classifier is considered as a Combinatorial Optimization task and solved using the Reactive Tabu Search (RTS) method. RTS needs only forward passes (no derivatives) and does not require high precision network parameters. TOTEM, a special-purpose VLSI chip, was developed to take advantage of the limited memory and processing requirements of RTS: the final system effects a very close match between hardware and training algorithm. The RTS algorithm and the design of TOTEM are discussed, together with the operational characteristics of the VLSI chip and some preliminary training and generalization tests on triggering tasks.
A miniaturized color camera module for disposable endoscopic applications and minimally invasive surgery has been designed and developed. The module consists of a Complementary Metal Oxide semiconductor (CMOS) sensor, miniaturized optics, a Light Emitting Diode (LED)-based illuminator and a connector on a single substrate. The compact size (5.0 mm × 8.2 mm × 7.0 mm), high-efficiency illumination, VGA resolution and good image quality allow it to be used in endoluminal procedures. A demonstration system has been built and tested in vivo. The module is connected through a 1.5-m long cable to a receiver board, which transfers the data stream to a Personal Computer (PC). A dedicated software controls the hardware setting and displays the image, after having performed various color and image processing tasks.
A custom CMOS image sensor designed for low power endoluminal applications is presented. The fabricated chip includes a 320 × 240 pixel array, a complete read-out channel, a 10-bit ADC converter, a series of DACs for internal references and digital blocks for chip control. The complete functionality of the chip is guaranteed through 7 signal pins, used for the I 2 C-like input and LVDS output interfaces. Prototypes were produced using UMC 0.18 m-CIS (CMOS Image Sensor) technology for both monochrome and colour-RGB versions. Due to its high sensitivity, a pinned photodiode was implemented. The imager was electrically and optically characterized and preliminary ex-vivo tests were performed. Characterization results show state-of-the-art performance in terms of power consumption (<40 mW for the core), which is less than half compared to off-the-shelf sensors, and light sensitivity (0.1 lux@555 nm for the monochrome imager), which makes sensor performance comparable to CCD technology performance for single chip endoluminal applications.
A CMOS pixel with linear-logarithmic response and programmable dynamic range (DR), based on a tunable transition point, has purposely been designed for endoscopic applications. A theoretical model of the pixel was developed and validated. A chip with a 100 × 100 pixel array and a 12-b digital output was fabricated in a 0.35-μm technology and was fully tested, thus demonstrating state-of-the-art performance in terms of DR and noise. Intraframe DR proved to be extendable to more than 110 dB through a logarithmic compression of the signal in the light irradiation power density (LIPD) range. The measured temporal noise (pixel noise) was less than 0.22% over the full range. The architecture presented limited fixed pattern noise (FPN) due to the scheme adopted, which allowed its correction over the full signal range: FPN was 0.83% (1.37%) in the linear (logarithmic) region. Although the test chip was designed mainly for endoscopic applications, the technology may also be applied to other fields, e.g., robotics, security and industrial automation, whenever high DR is a crucial feature.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.