Based on information produced by a 200 kHz ultrasonic echo device developed for robotics and other industrial purposes, a method for object identification was developed and is presented in this paper. Interpretation o...
详细信息
Based on information produced by a 200 kHz ultrasonic echo device developed for robotics and other industrial purposes, a method for object identification was developed and is presented in this paper. Interpretation of the echos from the reflecting objects, complexity analysis and information extraction were made by system identification methods such as impulse response analysis and state-space realization. A clustering-type discrimination of different objects based on the echo identification result was made in a subsequent step using the least-squares method. Experimental evaluation showed that the method is effective for object recognition.
This paper describes the evaluation of an application of the ARTMAP neural network model to the diagnosis of cancer from fine-needle aspirates of the breast. The network has previously demonstrated very high performan...
详细信息
ISBN:
(纸本)3540600256
This paper describes the evaluation of an application of the ARTMAP neural network model to the diagnosis of cancer from fine-needle aspirates of the breast. The network has previously demonstrated very high performance when used with high-quality data provided by an expert pathologist. New performance results are provided for its use with "noisy" data provided by an inexperienced pathologist. Additionally, ARTMAP supports the extraction of symbolic rules from a trained network and the validity of these autonomously-acquired rules is discussed. It is concluded that the symbolic rules provide an appropriate mapping of input features to category classes in the domain. However, the network in its present form is only suitable for use as a decision-support tool by a senior pathologist, since its performance deteriorated greatly with poor-quality data provided by a junior pathologist. The implications of the findings are discussed.
An application of the ARTMAP neural network model to the early diagnosis of acute myocardial infarction is described. Performance results are given for 10 individual ARTMAP networks, and for combinations of the networ...
详细信息
ISBN:
(纸本)3540600256
An application of the ARTMAP neural network model to the early diagnosis of acute myocardial infarction is described. Performance results are given for 10 individual ARTMAP networks, and for combinations of the networks using "pooled" decision making (the so-called voting strategy). Category nodes are pruned from the trained networks in different ways so as to improve accuracy, sensitivity and specificity respectively. The differently pruned networks are employed in a novel "cascaded" variation of the voting strategy. This allows a partitioning of the test data into predictions with a high and a lower certainty of being correct, providing the diagnosing clinician with an indication of the reliability of an individual prediction.
The aim of this paper is to do a survey of the resource allocation conditions for deadlock avoidance, as a primary condition of FMS design, and then to present the advantages of simulation methods for layout and opera...
详细信息
The aim of this paper is to do a survey of the resource allocation conditions for deadlock avoidance, as a primary condition of FMS design, and then to present the advantages of simulation methods for layout and operation optimization. Based on the layout of a demonstrator manufacturing cell, that is generally used in education and research activities, a case study is considered. Different design solutions of allocating the system resources, throughout discrete event simulation using GPSS/H language, are analyzed. The conclusions of the paper emphasize the benefits of the simulation method.
Intelligent manufacturing processes require intelligent sensor integration. For automated assembly this means integration of three-dimensional scene perception. Existing approaches use or to reconstruct the 3-D object...
详细信息
Intelligent manufacturing processes require intelligent sensor integration. For automated assembly this means integration of three-dimensional scene perception. Existing approaches use or to reconstruct the 3-D objects. In this paper the 3-D objects are reconstructed by their planar surfaces. The extraction of these surfaces is done using a with . The object planes are estimated by intersecting the generating cones for the projected disks and the image ellipses. The new method is especially addressed to problems arising in robotics and assembly tasks, where it is necessary to recognize a priori known objects and to estimate their pose.
By a hybrid system we mean a discrete controller in interaction with a physical environment. This paper discusses methodologies for incorporating physically grounded models in representations of hybrid systems. To thi...
详细信息
Most speech recognition systems are unable to cope with data from high-resolution pre-processors (such as auditory models and high-resolution spectral estimates) for two reasons. One is due to the inappropriateness of...
详细信息
Most speech recognition systems are unable to cope with data from high-resolution pre-processors (such as auditory models and high-resolution spectral estimates) for two reasons. One is due to the inappropriateness of measures related to the Euclidean distance. The other is somewhat less obvious, but is due to the non-ergodic nature of short-term parameterisations of speech sounds. This aspect of speech variability is addressed. The authors show how a linear, but nonstationary, vector predictor, based on the concept of 'acoustic flow', can be used to estimate the redundancy in speech data, paving the way for an improvement in recognition performance.< >
Describes an experimental implementation of a multivariable adaptive control to the regulation of temperatures in an industrial multizone reheating furnace operating in a tube drawing plant at Podbrezova (middle Slova...
Describes an experimental implementation of a multivariable adaptive control to the regulation of temperatures in an industrial multizone reheating furnace operating in a tube drawing plant at Podbrezova (middle Slovakia). The motivation for the experiments was to test the practical possibilities of the adaptive control algorithms in the reduction of fuel consumption in comparison to existing digital PID control of the furnace temperatures.
The problem of correctness and timing of reactions of an agent in interaction with a physical environment is addressed. To this end, a method based on composition of separate models of the software and the environment...
详细信息
This paper is concerned with introducing a genetic-based algorithm for the minimum-time trajectory planning of articulated robotic manipulators. The planning procedure is performed in the configuration space and respe...
详细信息
This paper is concerned with introducing a genetic-based algorithm for the minimum-time trajectory planning of articulated robotic manipulators. The planning procedure is performed in the configuration space and respects all physical constraints imposed on the manipulator design, including the limits on the torque values applied to the motor of each joint of the arm; consequently, the complete nonlinear dynamic robot model is incorporated in the formulation.< >
暂无评论