• 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.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.3
• /
• pp.72-78
• /
• 2000

In this study, we propose a model verification algorithm based on DCT and neural network for ATM security system. We construct database about facial images after capturing thirty persons facial images in the same lumination and distance. To simulate model verification, we capture four learning images and test images per a man. After detecting edge in facial images, we detect a characteristic area of square shape using edge distribution in facial images. Characteristic area contains eye bows, eyes, nose, mouth and cheek. We extract characteristic vectors to calculate diagonally coefficients sum after obtaining DCT coefficients about characteristic area. Characteristic vectors is normalized between +1 and -1, and then used for input vectors of neural networks. Not considering passwords, simulations results showed 100% verification rate when facial images were learned and 92% verification rate when facial images weren't learned. But considering passwords, the proposed algorithm showed 100% verification rate in case of two simulations.

• Korean Journal of Clinical Laboratory Science
• /
• v.52 no.4
• /
• pp.364-371
• /
• 2020

The Korea Centers for Disease Control and Prevention is conducting surveillance of climate change vectors across all regions in Korea to counteract the spread of these vectors. As a part of this surveillance project, wild rodents were captured using traps to investigate the spread of chigger mites, the vector of Tsutsugamushi disease, across Jeonbuk, Jinan region, and to conduct studies on pathogens. Twenty samplers were used to sample chigger mites weekly from September to November in four different locations. Six hundred and eleven chigger mites of eight varying types were captured. The largest number of captured chigger mites was N. tamiyai, with 434 samples (71.0%). With the addition of 66 wild rodents captured from traps, 3,050 chigger mites were sampled, which yielded a Chigger index of 46.2. The monthly Chigger index was highest in November with a value of 206.1. the result of the test conducted in the presence of pathogens showed two positive results, each from May and September, out of all 85 pools. This result was aligned with the increased frequency in tsutsugamushi disease cases in spring and fall seasons.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.11
• /
• pp.42-48
• /
• 1990

In this paper robust test generation for stuck-open faults in CMOS circuits is proposed. By obtaining initialization patterns and test patterns using the relationship of bit position and Hamming weight among input vectors for CMOS circuit test generation time for stuck-open faults can be reduced, and the problem of input transition skew which make fault detection difficult is solved, and the number of test sequences are minimized. Also the number of test sequences is reduced by arranging test sequences using Hamming distance between initialization patterns and test patterns for circuit.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.8
• /
• pp.1185-1194
• /
• 2004

Virtual images for PIV are produced for the construction of a benchmark test tool of PTV systems, Camera parameters obtained by an actual experiment are used to construct the virtual images, LES(Large Eddy Simulation) data sets of a channel flow are used for generation of the virtual images, Using the virtual images and the camera's parameters. three-dimensional velocity vectors are obtained for a channel flow. The capabilities of a 3D-PTV algorithm are investigated by comparing the results obtained by the virtual images and those by an actual measurement for the channel flow.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.37-41
• /
• 2014

The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.85-94
• /
• 2017

Conventional speaker verification systems using time delay neural network, identity vector and probabilistic linear discriminant analysis (TDNN-Ivector-PLDA) are known to be very effective for verifying long-duration speech utterances. However, when test utterances are of short duration, duration mismatch between enrollment and test utterances significantly degrades the performance of TDNN-Ivector-PLDA systems. To compensate for the I-vector mismatch between long and short utterances, this paper proposes to use probabilistic linear discriminant analysis (PLDA) model adaptation with augmented data. A PLDA model is trained on vast amount of speech data, most of which have long duration. Then, the PLDA model is adapted with the I-vectors obtained from short-utterance data which are augmented by using vocal tract length perturbation (VTLP). In computer experiments using the NIST SRE 2008 database, the proposed method is shown to achieve significantly better performance than the conventional TDNN-Ivector-PLDA systems when there exists duration mismatch between enrollment and test utterances.

• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.813-820
• /
• 2018

This paper proposes new frame rate up-conversion algorithms. Adaptive motion estimation based on block complexity information are used to obtain more accurate motion vectors. Because the information on block complexity is extracted from the motion estimation prediction size from the original frame, additional computational complexity is not imparted. In experimental results, the proposed algorithms provide robust frame interpolation performance for whole test sequences. Also, the computational complexity of the proposed algorithm is reduced to a benchmark algorithm.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.12
• /
• pp.1906-1915
• /
• 1990

A synthesis system generating sequential circuits from a high-level hardware descdription language CHDL, modelling language for Thor functional/behavioral simulator, is developed. In this paper, we describe the semantic analysis process, state minimization and state assignment algorithms. proposed assignment algorithm generates optimal state vectors using constraint matrix and similarity graph. Expremental results for MCNC benchmarks, standard test circuits, show that the system inplementing the proposed algorithms can be a viable tool for designing large finite state machines.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.12
• /
• pp.150-157
• /
• 2002

This paper presents an effective cutting force model that enable us to predict the instantaneous cutting force in face milling from a knowledge of the work material properties and cutting conditions. The development of the model is based on the orthogonal machining theory with the effective rake angle which is defined in the plane containing the cutting velocity and chip flow vectors. Face milling testes are performed at different feeds and, a fairly good agreement is shown between the predicted cutting forces and test results.