• The Journal of the Acoustical Society of Korea
• /
• v.10 no.4
• /
• pp.38-47
• /
• 1991

The frequency variation among speakers is one of problems in the speech recognition. This paper applies fuzzy theory to solve the variation problem of frequency features. Reference patterns are expressed by fuzzified patterns which are produced by the peak frequency and the peak energy extracted from codebooks which are generated from training words uttered by several speakers, as they should include common features of speech signals. Words are recognized by fuzzy inference which uses the certainty factor between the reference patterns and the test fuzzified patterns which are produced by the peak frequency and the peak energy extracted from the power spectrum of input speech signals. Practically, in computing the certainty factor, to reduce memory capacity and computation requirements we propose a new equation which calculates the improved certainty factor using only the difference between two fuzzy values. As a result of experiments to test this word recognition method by fuzzy interence with Korean digits, it is shown that this word recognition method using the new equation presented in this paper, can solve the variation problem of frequency features and that the memory capacity and computation requirements are reduced.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.2
• /
• pp.11-17
• /
• 1999

This paper proposes an observation probability smoothing technique for the robustness of a discrete hidden Markov(DHMM) model based speech recognizer. Also, an appropriate noise robust processing in car environment is suggested from experimental results. The noisy speech is often mislabeled during the vector quantization process. To reduce the effects of such mislabelings, the proposed technique increases the observation probability of similar codewords. For the noise robust processing in car environment, the liftering on the distance measure of feature vectors, the high pass filtering, and the spectral subtraction methods are examined. Recognition experiments on the 14-isolated words consists of the Korean digits and command words were performed. The database was recorded in a stopping car and a running car environments. The recognition rates of the baseline recognizer were 97.4% in a stopping situation and 59.1% in a running situation. Using the proposed observation probability smoothing technique, the liftering, the high pass filtering, and the spectral subtraction the recognition rates were enhanced to 98.3% in a stopping situation and to 88.6% in a running situation.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.44-51
• /
• 1999

The HMM-Net is a neural network architecture that implements the computation of output probabilities of a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.1
• /
• pp.110-114
• /
• 1995

Hypertrophic osteoarthropathy(HOA) is a systemic disorder primary affecting the bones, joints, and soft tissues and characterized by several(or all) of the followings ; 1) Clubbing of digits, 2) Persistent new bone formation particulary involving long bones of the distal extremites, 3) Symmetric arthritis-like changes in the joints and periarticular tissue, most commonly the ankles, knees, wrist, and elbows, 4) Increased thickness of the subcutaneous soft tissues in the distal one-third of the arms and legs, and 5) Neurovascular changes of the hands and feet, including chronic erythema, paresthesis, and increase sweating. Most of cases of HOA are secondary to intrathoracic neoplasms, while the remaining few cases are secondary to other disease in the chest or elsewhere. We experienced a case of HOA in association with lung abscess in 26-yr-old male and reported with a review of literatures.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.201-207
• /
• 2012

A RAM-based neural network is a weightless neural network based on binary neural network(BNN) which is efficient neural network with a one-shot learning. RAM-based neural network has multiful information bits and store counts of training in BNN. Supervised learning based on the RAM-based neural network has the excellent performance in pattern recognition but in pattern categorization with unsupervised learning as unsuitable. In this paper, we propose a unsupervised learning algorithm in the RAM-based neural network to perform pattern categorization. By the proposed unsupervised learning algorithm, RAM-based neural network create categories depending on the input pattern by itself. Therefore, RAM-based neural network for supervised learning and unsupervised learning should proof of all possible complex models. The training data for experiments provided by the MNIST offline handwritten digits which is consist of 0 to 9 multi-pattern.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2004.08a
• /
• pp.139-145
• /
• 2004

It is well known that human errors is involved in most of maritime accidents. For the purpose of reducing the influence of human elements on maritime activities, it is necessary to identify the human unsafe acts in those activities. The commonly used methods in identification of human unsafe acts are maritime accident statistics or case analysis. With the statistics data, people could roughly identify what kinds of unsafe acts or human errors have played active role in the accident, however, they often neglected some active unsafe acts while overestimated some mini-unsafe acts because of the inherent shortcoming of the methods. There should be some more accurate approaches for human error identification in maritime accidents. In this paper, the application of technique called grey relational analysis (GRA) into the identification of human unsafe acts is presented. GRA is used to examine the extent of connections between two digits by applying the, methodology of departing and scattering measurement to actual distance measurement. Based on the statistics data of maritime accidents occurred in Chinese waters in last 10years, the relationship between the happening times of maritime accidents and that of unsafe acts are established with GRA. In accordance with the value of grey relational grade, the identified main human unsafe acts involved in maritime accidents are ranked in following orders: improper lookout, improper use of radar and equivalent equipment, error of judgment, act not in time, improper communication, improper shiphandling, use of unsafe speed, violating the rule and ignorance of good seamanship. The result shows that GRA is an effective and practical technique in improving the accuracy of human unsafe acts identification.

• Journal of Forest and Environmental Science
• /
• v.31 no.3
• /
• pp.214-224
• /
• 2015

The economy of India and so also of many Asian countries depends on bamboos and their uses are not only in domestic items but also in rural housing and raw materials to several industries and germplasm characterization is an important link between the conservation and utilization of plant genetic resources. Classical taxonomic studies of the bamboos are based on floral morphology and growth habit, which can cause problems in identification due to erratic flowering coupled with different biotic agencies and environmental factors. Identification and genetic relationships among accessions of Thamnocalamus falconeri were investigated using morphology and random amplified polymorphic DNAs (RAPD) technique. Analysis started by using 51 vegetative characters and forty two 10-mer primers that allowed us to distinguish different genotypes hailing from different eco- zones of Garhwal Himalayas (India). The selected primers (12) were used for identification and for establishing a profiling system to estimate genetic diversity. A total of 79.33% polymorphism was estimated by using 12 selected primers. The genetic similar analysis was conducted based on binary digits i.e. presence (1) or absence (0) of bands, which revealed a wide range of variability among the species whereas genetic relatedness was quite high based on vegetative characters. Cluster analysis clearly showed two major clusters for both of the markers viz. morphology and RAPD belonging to 10 accessions of T. falconeri. Two major clusters were further divided into minor clusters. Cluster based on RAPD marker showed grouping of accessions of closed locality whereas analogy was reported for vegetative traits. The RAPD technique has the potential for use in species identification and genetic relationships studies of bamboo for breeding program.

• Archives of Plastic Surgery
• /
• v.44 no.2
• /
• pp.144-149
• /
• 2017

Background The purpose of this study was to identify the epidemiologic characteristics of hand tendon injuries in children and to compare these with those of adults. Methods This retrospective study was conducted on acute traumatic tendon injuries of the hand treated at our institution from 2005 to 2013, based on medical records and X-ray findings. Age, sex, hand injured, mechanism of injury, tendons and zones injured, number of affected digits, and comorbidities and complications were analyzed. Patients were divided into 2 groups: a pediatric group (${\leq}15years$) and an adult group (>15 years). Results Over the 9-year study period, 533 patients were surgically treated for acute traumatic tendon injuries of the hand. In the pediatric group (n=76), being male, the right hand, the extensor tendon, complete rupture, the middle finger, and glass injury predominated in hand tendon injuries. In the adult group (n=457), results were similar, but injury to the index finger and knife injury were the most common. An accompanying fracture was more common in the adult group and complication rates were non-significantly different. Conclusions This comparative analysis revealed no significant epidemiologic intergroup differences. The belief that pediatric tendon injuries tend to be less severe is misplaced, and careful physical examination and exploration should be conducted in pediatric cases of hand injury.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.5-10
• /
• 1995

In this paper we present a clustering procedure based on the use of HMM in order to get multiple statistical models which can well absorb the variants of each speaker with different ways of saying words. The HMM-clustered models obtained from the developed technique are applied to the speaker independent isolated word recognition. The HMM clustering method splits off all observation sequences with poor likelihood scores which fall below threshold from the training set and create a new model out of the observation sequences in the new cluster. Clustering is iterated by classifying each observation sequence as belonging to the cluster whose model has the maximum likelihood score. If any clutter has changed from the previous iteration the model in that cluster is reestimated by using the Baum-Welch reestimation procedure. Therefore, this method is more efficient than the conventional template-based clustering technique due to the integration capability of the clustering procedure and the parameter estimation. Experimental data show that the HMM-based clustering procedure leads to $1.43\%$ performance improvements over the conventional template-based clustering method and $2.08\%$ improvements over the single HMM method for the case of recognition of the isolated korean digits.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.8
• /
• pp.12-18
• /
• 2001

In this paper, we propose the Recurrent Neural Predictive HMM (RNPHMM). The RNPHMM is the hybrid network of the recurrent neural network and HMM. The predictive recurrent neural network trained to predict the future vector based on several last feature vectors, and defined every state of HMM. This method uses the prediction value from the predictive recurrent neural network, which is dynamically changing due to the effects of the previous feature vectors instead of the stable average vectors. The models of the RNPHMM are Elman network prediction HMM and Jordan network prediction HMM. In the experiment, we compared the recognition abilities of the RNPHMM as we increased the state number, prediction order, and number of hidden nodes for the isolated digits. As a result of the experiments, Elman network prediction HMM and Jordan network prediction HMM have good recognition ability as 98.5% for test data, respectively.