An electronic odor discrimination system had been developed by using four quartz resonator-sensitive membranes basic-resonance frequencies at 10 MHz as a sensor and analyzed the measurement data through a back propagation (BP) as the pattern recognition system. The developed system showed high recognition probability to discriminate various single odors to its high generality properties; however, the system had a limitation in recognizing the fragrances mixture. This system also had other disadvantages, such as classifying the unknown category of odor as the known category of odor. In order to improve the performance of the proposed system, development of the sensor and other neural networks (NNs) are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from four quartz resonator-basic resonance frequencies at 10 MHz with new 16 quartz resonator-basic resonance frequencies at 20 MHz, but also by replacing the pattern classifier from BP NNs with the variance of BP, probabilistic NNs, and fuzzy-neuro learning vector quantization (FNLVQ). Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, to become FNLVQ-MSA neural systems in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the fragrance mixtures, in addition to recognizing the unknown fragrance mixtures. The use of new sensing systems and FNLVQ-MSA has produced higher capability, compared to the previously mentioned system.Index Terms-Fuzzy-neuro learning vector quantization (FNLVQ), matrix similarity analysis (MSA), multiple quartz-resonator sensors, neural networks (NNs), odor discrimination system.
We have developed a novel catheter system, an intelligent catheter system, which is able to control a catheter by an externally-placed controller This system has made from master-slave mechanism and has following three components; 1) a joy stick as a master (for operators) 2) a catheter controller as a slave (for a patient), 3) a micro force sensor as a sensing device. This catheter tele-guiding system has abilities to perform intravascular procedures from the distant places. It may help to reduce the radiation exposures to the operators and also to help train young doctors.
We propose an interconnected suspension mechanism that is applicable to rough terrain mobile robots for construction sites. All wheels can follow on uneven ground by moving mutually with an interconnected suspension mechanism. And, it is possible to control the posture of the robot simply using the mechanism. In this paper, the structural and mechanical characteristics of the mechanism are discussed and the ground contact loads of wheels are analyzed. It was confirmed the mechanism has enough ability for moving on an uneven floor and posture control through experiments with an experimental rough terrain moving robot.
A template matching is a popular method for visual recognition. It costs much time to detect target objects. We have applied a Fuzzy and Neural Network algorithm to solve this problem. However, the problem to mistake recognizing the target object is not solved. Hence, in this paper, we propose a robust visual recognition algorithm for the autonomous robot navigation. The proposing algorithm employs a fuzzy template matching with the target object as well as the similar objects in the environment. As a result, the robot verifies the tentative recognition by comparing the likelihood of plus elements (target objects) with that of minus elements (similar objects). To integrate this algorithm into the robot navigation system, we propose a hierarchical control architecture. The validity of the proposing navigation system is shown with experimental results.
Human sensory test is often used for obtaining the sensory quantities of odors; however, the fluctuation of results due to the expert's condition can cause discrepancies among panelist. Artificial odor discrimination system is constructed to overcome the limitation of the already existing sensory test systems. Authors have developed an electronic odor discrimination system by using 4 quartz-resonator sensitive membranes as the sensors and had fundamental resonance frequencies 10 MHz. In recognizing and classifying the output pattern, the system used Back Propagation (BP) neural network as the pattern recognizer. This system can recognize the limited odor mixtures. The capability of the system can be amended by improving the hardware and changing the software of pattern classifier. This paper proposes a new sensing system using 16 multiple quartz resonator sensors array and basic resonance frequencies 20 MHz. Also modify various neural network called Probabilistic Neural Network (PNN) and Fuzzy-Neuro Learning Vector Quantization (FLVQ) as the automated pattern recognition system. The purpose of the recent study is to construct an artificial odor discrimination system for recognizing the fragrance mixtures. It is found out that the using of new sensing system as in PNN and FLVQ produces higher capability compare to the conventional sensing system with Back Propagation (BP) neural network.
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.