For a one-layered-feedback neural network e.g., a Hopfield net, containing discrete sign-function neurons, the nonlinear properties of this network can be studied very efficiently using simple discrete mathematics. Th...
详细信息
ISBN:
(纸本)0819444081
For a one-layered-feedback neural network e.g., a Hopfield net, containing discrete sign-function neurons, the nonlinear properties of this network can be studied very efficiently using simple discrete mathematics. This paper summarizes the discrete-formulation of the problem as a matrix difference equation, the simple iterative method of solving this difference equation and the derivation of the major anomalous properties of the system from the solutions. These anomalous properties include, eigen-state storage, associative storage, domain of attraction, content-addressable recall, fault-tolerant recall, capacity of storage, binary oscillating states, limit-cycles in the state space, and noise-sensitive input states. The physical origin and the systematic trend of the derivation of these properties are easily seen in the numerical examples given.
We propose the development of a functional system for diagnosing and measuring ocular refractive errors in the human eye (astigmatism, hypermetropia and myopia) by automatically analyzing images of the human ocular gl...
详细信息
ISBN:
(纸本)0819445541
We propose the development of a functional system for diagnosing and measuring ocular refractive errors in the human eye (astigmatism, hypermetropia and myopia) by automatically analyzing images of the human ocular globe acquired with the Hartmann-Shack (HS) technique. HS images are to be input into a system capable of recognizing the presence of a refractive error and outputting a measure of such an error. The system should preprocess an image supplied by the acquisition technique and then use artificialneuralnetworks combined with fuzzy logic to extract the necessary information and output an automated diagnosis of the refractive errors that may be present in the ocular globe under exam.
In this paper we study the applicability of Probabilistic neuralnetworks (PNNs) as core classifiers to medium scale speaker recognition over fixed telephone networks. In particular, banking applications with up to 40...
详细信息
ISBN:
(纸本)0780375033
In this paper we study the applicability of Probabilistic neuralnetworks (PNNs) as core classifiers to medium scale speaker recognition over fixed telephone networks. In particular, banking applications with up to 400 enrolled speakers and short training times are targeted. Two PNN-based open-set text-independent systems for Speaker Identification and Speaker Verification correspondingly are presented. The performance of these systems is studied with and without use of a supporting Gaussian Mixture Models classifier. Results from experiments carried out on the Polycost and SpeechDat(ii)-Greek corpus, with training times as short as 43 seconds, are reported.
As Internet-enabled computers become ubiquitous in homes, schools, and other publicly accessible locations, there are more people 'surfing the net' who would prefer not to be exposed to offensive material. The...
详细信息
ISBN:
(纸本)0819444081
As Internet-enabled computers become ubiquitous in homes, schools, and other publicly accessible locations, there are more people 'surfing the net' who would prefer not to be exposed to offensive material. There is a lot of material freely available on the Internet that we, as a responsible and caring society, would like to keep our children from viewing. Pornographic image content is one category of material over which we would like sonic control. We have been conducting experiments to determine the effectiveness of using characteristic feature vectors and neuralnetworks to identify semantic image content. This paper will describe our approach to identifying pornographic images using Gabor filters, Principal Component Analysis (PCA), Correllograms, and neuralnetworks. In brief, we used a set of 5,000 typical images available from the Internet, 20% of which were judged to be pornographic, to train a neural network. We then apply the trained neural network to feature vectors from images that had not been used in training. We measure our performance as Recall, how many of the verification images labeled pornographic were correctly identified, and Precision, how many images deemed pornographic by the neural network are in fact pornographic. The set of images that were used in the experiment described in this paper for its training and validation sets are freely available on the Internet. Freely available is an important qualifier, since high-resolution, studio-quality pornographic images are often protected by portals that charge members a fee to gain access to their material. Although this is not a hard and fast rule, many of the pornographic images that are available easily and without charge on the Internet are of low image quality. Some of these images are collages or contain textual elements or have had their resolution intentionally lowered to reduce their file size. These are the offensive images that a user, without a credit card, might inadvertently come acr
In the field of artificialneuralnetworks, large-scale classification problems are still challenging due to many, obstacles such as local minima state, long time computation, and the requirement of large amount of me...
详细信息
ISBN:
(纸本)9810475241
In the field of artificialneuralnetworks, large-scale classification problems are still challenging due to many, obstacles such as local minima state, long time computation, and the requirement of large amount of memory. The large-scale network CombNET-ii overcomes the local minima state and proves to give good recognition rate in many applications. However CombNET-ii still requires a large amount of memory used for the training database and feature space. Here we propose a revised version of CombNET-ii with a considerably lower memory requirement, which make the problem of large-scale classification more tractable. The memory reduction is achieved by adding a preprocessing stage at the input of each branch network. The purpose of this stage is to select the different features that have the most classification power for each subspace generated by the stem network. Testing our proposed model using Japanese kanji characters shows that the required memory might be reduced by almost 50% without significant decrease in the recognition rate.
Solid waste recycling is more and more increasing according to the need to realize dismantled material recovery and to reduce overall environmental pollution. When a recycling strategy is applied sorting strategies ha...
详细信息
ISBN:
(纸本)0819444081
Solid waste recycling is more and more increasing according to the need to realize dismantled material recovery and to reduce overall environmental pollution. When a recycling strategy is applied sorting strategies have to be developed and implemented. Such an approach ca be considered as the second logical step of the process that is, after that the attributes (physical, chemical, morphological, morphometrical, textural, etc.) of the materials resulting from classical processing (comminution, classification, separation, etc.) are detected and numerically modeled. The resulting feature vector need to be "handled" by a software architecture performing the required recognition/classification procedure and defining the quality of the investigated products. From the results further "feed-back" or "feed-forward" control strategies can be applied in order to improve equipment or processing architectures performances. In this paper are analyzed and described neural network based sorting strategies applied with reference to fluff (light fraction of the materials resulting from car dismantling) recognition.
In this paper(1), we investigate several fusion techniques for designing a composite classifier to improve the performance (probability of correct classification) of FLIR ATR. The motivation behind the fusion of ATR a...
详细信息
ISBN:
(纸本)0819444081
In this paper(1), we investigate several fusion techniques for designing a composite classifier to improve the performance (probability of correct classification) of FLIR ATR. The motivation behind the fusion of ATR algorithms is that if each contributing technique in a fusion algorithm (composite classifier) emphasizes on learning at least some features of the targets that are not learned by other contributing techniques for making a classification decision, a fusion of ATR algorithms may improve overall probability of correct classification of the composite classifier. In this research, we propose to use four ATR algorithms for fusion. We propose to use averaged Bayes classifier, committee of experts, stacked-generalization, winner-takes-all, and ranking-based fusion techniques for designing the composite classifiers. The experimental results show an improvement of more than 5 % over the best individual performance.
Many studies for computer-based chromosome analysis using artificialneural network (ANN) have shown that it is possible to classify chromosomes into 24 subgroups. It is important to select optimum features for traini...
详细信息
ISBN:
(纸本)0819444081
Many studies for computer-based chromosome analysis using artificialneural network (ANN) have shown that it is possible to classify chromosomes into 24 subgroups. It is important to select optimum features for training the ANN. Our purpose was to select features that had the low classification error and the best ability for human chromosome classification. We applied the medial axis transformation for the medial line, extended the line to the boundary and obtained relative length, relative area and centromeric index. The Giemsa-stained human chromosome has a sequence of banding pattern that is perpendicular to the medial axis of the chromosome. Density profile is a one-dimensional graph of the banding pattern property of the chromosome computed at a sequence of points along the possibly curved chromosome medial axis. Some studied used relative length, centromeric index and 62 density profile as features, but we prepared two data sets as features that one set was relative length, centromeric index and 80 density profile considered No. I chromosome's length and the other was relative length, centromeric index, the 80 density profile and relative area and compared classification error of each set. We found that the classification error showed to be decreased by adding relative area to the other features.
The proceedings contains 70 papers. Topics discussed include machine learning, data mining and knowledge discovery, constraint satisfaction, intelligent information retrieval, planning and scheduling, intelligent real...
详细信息
The proceedings contains 70 papers. Topics discussed include machine learning, data mining and knowledge discovery, constraint satisfaction, intelligent information retrieval, planning and scheduling, intelligent real time systems, logic and reasoning, natural language processing, multimedia and imageprocessing, internet software, multi-agents, neuralnetworks and applications and software engineering and knowledge sharing.
The performance of face verification systems has steadily improved over the last few Years, mainly focusing on models rather than on feature processing. State-of-the-art methods often use the gray-scale face image as ...
详细信息
ISBN:
(纸本)076951695X
The performance of face verification systems has steadily improved over the last few Years, mainly focusing on models rather than on feature processing. State-of-the-art methods often use the gray-scale face image as input. In this paper, we propose to use an additional feature to the face image: the skin color The new feature set is tested on a benchmark database, namely XM2VTS, using a simple discriminant artificialneural network. Results show that the skin color information improves the performance.
暂无评论