• Nutrition Research and Practice
• /
• v.9 no.3
• /
• pp.268-277
• /
• 2015

BACKGROUND/OBJECTIVES: Although it is crucial to identify those children likely to be treated in an appropriate nutrition rehabilitation programme and discharge them at the appropriate time, there is no golden standard for such identification. The current study examined the appropriateness of using Mid-Upper Arm Circumference for the identification, follow-up and discharge of malnourished children. We also assessed its discrepancy with the Weight-for-Height based diagnosis, the rate of recovery, and the discharge criteria of the children during nutrition rehabilitation. SUBJECTS/METHODS: The study present findings from 156 children (aged 6-59 months) attending a supplementary feeding programme at Makadara and Jericho Health Centres, Eastern District of Nairobi, Kenya. Records of age, weight, height and mid-upper arm circumference were selected at three stages of nutrition rehabilitation: admission, follow-up and discharge. The values obtained were then used to calculate z-scores as defined by WHO Anthro while estimating different diagnostic indices. RESULTS: Mid-upper arm circumference single cut-off (< 12.5 cm) was found to exhibit high values of sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio at both admission and discharge. Besides, children recorded higher rate of recovery at 86 days, an average increment of 0.98 cm at the rate of 0.14mm/day, and a weight gain of 13.49gm/day, albeit higher in female than their male counterparts. Nevertheless, children admitted on basis of low MUAC had a significantly higher MUAC gain than WH at 0.19mm/day and 0.13mm/day respectively. CONCLUSIONS: Mid-upper arm circumference can be an appropriate tool for identifying malnourished children for admission to nutrition rehabilitation programs. Our results confirm the appropriateness of this tool for monitoring recovery trends and discharging the children thereafter. In principle the tool has potential to minimize nutrition rehabilitation costs, particularly in community therapeutic centres in developing countries.

• Phonetics and Speech Sciences
• /
• v.14 no.4
• /
• pp.35-43
• /
• 2022

This paper studies how to improve the identification rate of laryngeal disability speech data by convolutional neural network (CNN) and machine learning ensemble learning methods. In general, the number of laryngeal dysfunction speech data is small, so even if identifiers are constructed by statistical methods, the phenomenon caused by overfitting depending on the training method can lead to a decrease the identification rate when exposed to external data. In this work, we try to combine results derived from CNN models and machine learning models with various accuracy in a multi-voting manner to ensure improved classification efficiency compared to the original trained models. The Pusan National University Hospital (PNUH) dataset was used to train and validate algorithms. The dataset contains normal voice and voice data of benign and malignant tumors. In the experiment, an attempt was made to distinguish between normal and benign tumors and malignant tumors. As a result of the experiment, the random forest method was found to be the best ensemble method and showed an identification rate of 85%.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.85-94
• /
• 2023

In the face of the serious security situation with the increasing threat from North Korea, Korean Army is pursuing a reduction in troops through the performance improvement project of the GOP science-based border security system, which utilizes advanced technology. In order for the GOP science-based border security system to be an effective alternative to the decrease in military resources due to the population decline, it must guarantee a high detection and identification rate and minimize troop intervention by dramatically improving the false detection rate. Recently introduced in Korean Army, the GOP science-based border security system is known to ensure a relatively high detection and identification rate in good weather conditions, but its performance in harsh weather conditions such as rain and fog is somewhat lacking. As an alternative to overcoming this, a radar-based border security system that can detect objects even in bad weather has been proposed. This paper proves the effectiveness of the AI-based scientific border security system based on radar that is being currently tested at the 00th Division through the 2021 Rapid Acquisition Program, and suggests the direction of development for the GOP scientific border security system.

• Phonetics and Speech Sciences
• /
• v.4 no.3
• /
• pp.95-101
• /
• 2012

In this paper, we introduce the automatic speaker identification system 'SPO(Supreme Prosecutors Office) Verifier'. SPO Verifier is a GMM(Gaussian mixture model)-UBM(universal background model) based automatic speaker recognition system and has been developed using Korean speakers' utterances. This system uses a channel compensation algorithm to compensate recording device characteristics. The system can give the users the ability to manage reference models with utterances from various environments to get more accurate recognition results. To evaluate the performance of SPO Verifier on Korean speakers, we compared this system with one of the most widely used commercial systems in the forensic field. The results showed that SPO Verifier shows lower EER(equal error rate) than that of the commercial system.

• Speech Sciences
• /
• v.14 no.1
• /
• pp.163-174
• /
• 2007

All observation has uncertainty due to noise or channel characteristics. This uncertainty should be counted in the modeling of observation. In this paper we propose a modified optimization object function of a GMM training considering inexact observation. The object function is modified by introducing the concept of observation confidence as a weighting factor of probabilities. The optimization of the proposed criterion is solved using a common EM algorithm. To verify the proposed method we apply it to the speaker recognition domain. The experimental results of text-independent speaker identification with VidTimit DB show that the error rate is reduced from 14.8% to 11.7% by the modified GMM training.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2011

In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including 'without compensation') and five feature enhancement methods (including 'without enhancement'). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.199-202
• /
• 1996

In this paper, we used the maximum likelihood method for 2-point aerodynamic model to determine the parameters of the ChangGong-91. Since the estimation from the flight test of real aircraft is the most reliable, we performed the flight test of ChangGong-91 to get the parameters such as velocity, height, 3 axis acceleration, 3 axis angular rate, pitch angle, angle of attack, temperature and so on. We recorded the flight test data in S-VHS tapes and stored them to personal computer using A/D(analog to digital) converter. Flight test was done in stall motion, and the acquired data was be processed with parameter identification method.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.1
• /
• pp.35-41
• /
• 1992

A speaker identification scheme using the speaker-based VQ codecook of a sustained vowel is proposed and tested. With the pitch synchronous LPC vector of the sustained vowel /i/ as a feature vector, a VQ codebook size of 4 was found to be suitable to characterize each speaker's feature space. For 40 normal speakers (20 males, 20 females), we achieved the correct identification rate of 99.4% with a training data set, and 89.4% with a test data set with speech samples of only 50 pitch periods.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• Journal of Sensor Science and Technology
• /
• v.20 no.3
• /
• pp.193-198
• /
• 2011

In this paper, we used optoelectronic feedback to generate the carrier frequency for the ASK modulation of a lighting LED. A solar cell was used for photo-detector in the feedback circuit, and the LED light was ASK modulated by controlling the ON/OFF state of the switch that is installed in the feedback loop. The oscillation frequency of the optoelectronic feedback loop was about 50 kHz and the data rate of the ASK modulation was 9.6 kbps. In experiments, the optoelectronic feedback circuit was used for the ASK modulation of a lighting LED in the transponder of a visible light identification system, and data exchange between the transponder and the reader was successfully carried out.