National Electronic and Computer Technology Center

Pathum Thani, Thailand

National Electronic and Computer Technology Center

Pathum Thani, Thailand
Time filter
Source Type

Viriyavit W.,Thammasat University | Sornlertlamvanich V.,Thammasat University | Kongprawechnon W.,Thammasat University | Pongpaibool P.,National Electronic and Computer Technology Center | Isshiki T.,Tokyo Institute of Technology
2017 8th International Conference on Information and Communication Technology for Embedded Systems, IC-ICTES 2017 - Proceedings | Year: 2017

This paper describes bed posture classification by using a Neural Network model for elderly care. Data collected from a sensor panel (composed of piezoelectric sensors and pressure sensors), which is placed under a mattress in the thoracic area, we use Neural Network for posture classification. Bayesian approach is used for estimating the likelihood of consecutive postures. The sensing data are normalized into a range of 0 to 1 by the unity-based normalization (or feature scaling) method for eliminating the bias between the different types of sensors. Also, the accumulated signal data in one second time slots (120-inputs set) can improve the coverage of the trained model. The results from Neural Network and Bayesian network estimation are combined by the weighted arithmetic mean. Our proposed technique is applied to elderly patient data with five different postures i.e., out of bed, sitting, lying down, lying left, and lying right. This resulted in 91.50% accuracy when the proportion of coefficient for Neural Network and Bayesian probability is 0.3 and 0.7 respectively. © 2017 IEEE.

Oros C.,University of Arts | Wisitsoraat A.,National Electronic and Computer Technology Center | Horprathum M.,National Electronic and Computer Technology Center
Key Engineering Materials | Year: 2016

In this work, the nanorod structure of Tin oxide (SnO2) prepared by glancing angle deposition (GLAD) technique with different O2 flow rate from 12 to 48 sccm. The surface and Crystal structure of SnO2 thin films were characterized by scanning electron microscopy (SEM), X-raydiffraction (XRD) and tested toward ethanol gas sensing. Structural characterization showed that the morphological of all SnO2 thin films prepared with different O2 flow rates consists of columnar nanorod structures and the nanorod size which is likely to decrease as the O2 flow rate increases. As the O2 flow rate increases from 12 to 48 sccm, the crystal structure of SnO2 nanorods changes from amorphous to crystalline and the crystallinity is improved by increasing O2 flow rate. Gas sensing performances of SnO2 nanorods have been characterized toward ethanol sensing. It was found that SnO2 nanorods exhibit n-type conductivity with decreased resistance when exposed to ethanol, which is reducing gas. In addition, sensitivity to ethanol tend to improve as O2 flow rate increases. Furthermore, the SnO2 nanorods prepared at O2 flow rates 48 sccm are detecting ethanol gas at concentrations lower than 50 ppm at operating temperature 250 °C. © 2016 Trans Tech Publications, Switzerland.

Lokavee S.,Mahidol University | Puntheeranurak T.,Mahidol University | Kerdcharoen T.,Mahidol University | Watthanwisuth N.,National Electronic and Computer Technology Center | Tuantranont A.,National Electronic and Computer Technology Center
Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics | Year: 2012

In this paper, we have developed a low-cost sleep monitoring system for patient based on polysomnography which will be useful for patient communication with healthcare personals and/or relatives. In particular, we have presented the sensor pillow and bed sheet system that employs wireless networks based on low-cost ZigBee technology and a sensor array of force sensitive resistors (FSR) based on polymer thick film (PTF) device, for classifying and specifically verifying the respiration rate during sleep. This paper also proposes a simple motion model that explains the change of head and body pressure distribution. In addition, we can detect some physiological parameters during the sleep stages and wakefulness as well as record respiration rate as related to different physiological factors. The integration of this sensor system and wireless technology with computer software could make this healthcare monitoring system a commercial product valuable for point-of-care applications. © 2012 IEEE.

Thitipatanapong R.,National Electronic and Computer Technology Center | Dechanupaprittha S.,Kasetsart University
SAE Technical Papers | Year: 2013

Normally, the energy conversion efficiency in road vehicle was presented in term of amount of unit fuel per distance within specific condition where it could not be comparable in practice that the variations of dynamic traffic condition and driver behavior were impacted. To minimized energy consumption, the both traffic conditions and driver behavior needs to be managed. The traffic conditions improves as infrastructure development, but the driver behavior needs personal training with equipment In this study, the alternative practical indicator was proposed with applying specific positive kinetic energy concept to indicate the level of vehicle dynamic behavior which relate to the level of fuel consumption rate. Furthermore, the experimental were taken place in Pahonyothin Rd. (Bangkok, Thailand) including urban, sub-urban and highway with various traffic congestion level. In addition, the 2010-model Honda CRV 2.0l was selected as experimental vehicle with on-board combustion rate equipment for actual fuel consumption measurements. Therefore, from the analysis the specific positive kinetic energy (sPKE) per trip was proportional to the fuel consumption excluding idling. Moreover, the proposed methodology could be applied for rate the vehicle behavior Eco-route design, Eco-traffic management or Eco-driver training to minimize energy consumption in vehicle.

Yuenyong S.,Tokyo Institute of Technology | Nishihara A.,Tokyo Institute of Technology | Kongprawechnon W.,Thammasat University | Tungpimolrut K.,National Electronic and Computer Technology Center
BioMedical Engineering Online | Year: 2011

Background: A new framework for heart sound analysis is proposed. One of the most difficult processes in heart sound analysis is segmentation, due to interference form murmurs.Method: Equal number of cardiac cycles were extracted from heart sounds with different heart rates using information from envelopes of autocorrelation functions without the need to label individual fundamental heart sounds (FHS). The complete method consists of envelope detection, calculation of cardiac cycle lengths using auto-correlation of envelope signals, features extraction using discrete wavelet transform, principal component analysis, and classification using neural network bagging predictors.Result: The proposed method was tested on a set of heart sounds obtained from several on-line databases and recorded with an electronic stethoscope. Geometric mean was used as performance index. Average classification performance using ten-fold cross-validation was 0.92 for noise free case, 0.90 under white noise with 10 dB signal-to-noise ratio (SNR), and 0.90 under impulse noise up to 0.3 s duration.Conclusion: The proposed method showed promising results and high noise robustness to a wide range of heart sounds. However, more tests are needed to address any bias that may have been introduced by different sources of heart sounds in the current training set, and to concretely validate the method. Further work include building a new training set recorded from actual patients, then further evaluate the method based on this new training set. © 2011 Yuenyong et al; licensee BioMed Central Ltd.

Mongkolluksamee S.,National Electronic and Computer Technology Center | Fukuda K.,Japan National Institute of Information and Communications Technology | Pongpaibool P.,National Electronic and Computer Technology Center
IEEE International Conference on Communications | Year: 2012

With the prevalence of Network Address Translation (NAT), identifying a number of Internet users becomes a challenging task because many users share the same public IP address. This paper proposes a passive technique for estimating a number of Internet hosts sharing the same IP address, i.e., NATted hosts. Previous work by Bellovin [1] counted NATted hosts by observing a sequence of IPID fields in IP header. This technique only works on some operating systems with a global counter for the IPID sequence (e.g., Windows). Other operating systems that implement the IPID sequence on a per-flow or a random basis are not detected. The proposed technique overcomes this limitation by observing patterns of the TCP sequence number and the TCP source port, in addition to the IPID sequence. Our technique demonstrates more accurate estimate than the previous work in controlled experiments. Moreover, applying our technique on a collection of longitudinal traffic traces measured at a trans-Pacific link in 2001-2010, we find that the percentage of the NATted hosts is stably less than 2% over years. © 2012 IEEE.

Lorwongtragool P.,Mahidol University | Lorwongtragool P.,Rajamangala University of Technology at Suvarnabhumi | Wisitsoraat A.,National Electronic and Computer Technology Center | Kerdcharoen T.,Mahidol University
Journal of Nanoscience and Nanotechnology | Year: 2011

An electronic nose (e-nose) system based on polymer/carboxylic- functionalized single-walled carbon nanotubes (SWNT-COOH) was developed for sensing various volatile amines. The SWNTCOOH dispersed in the matrix of different polymers; namely, polyvinyl chloride (PVC), cumene terminated polystyrene-co-maleic anhydride (cumene-PSMA), poly(styrenecomaleic acid) partial isobutyl/methyl mixed ester (PSE), and polyvinylpyrrolidon (PVP), were deposited on interdigitated gold electrodes to make the gas sensors. The response of these sensors to volatile amines was studied by both static and dynamic flow measurements. It was found that all sensors exhibited behaviors corresponding to Plateau-Bretano-Stevens law (R 2 = 0.81 to 0.99) as the response to volatile amines. Real-world application was demonstrated by applying this e-nose to monitor the odor of sun-dried snakeskin gourami that was pre-processed by salting-preservation. This electronic nose can discriminate sun-dried fish odors with different stored days using a simple pattern recognition based on the principal component analysis (PCA). Copyright © 2011 American Scientific Publishers All rights reserved.

Wongchoosuk C.,National Center for Nanosciences and Technology of China | Wisitsoraat A.,National Electronic and Computer Technology Center | Tuantranont A.,National Electronic and Computer Technology Center | Kerdcharoen T.,National Center for Nanosciences and Technology of China | Kerdcharoen T.,Mahidol University
Sensors and Actuators, B: Chemical | Year: 2010

In this paper, a portable electronic nose (E-nose) based on hybrid carbon nanotube-SnO2 gas sensors is described. The hybrid gas sensors were fabricated using electron beam (E-beam) evaporation by means of powder mixing. The instrument employs feature extraction techniques including integral and primary derivative, which lead to higher classification performance as compared to the classical features (ΔR and ΔR/R0). It was shown that doping of carbon nanotube (CNT) improves the sensitivity of hybrid gas sensors, while quantity of CNT has a direct effect on the selectivity to volatile organic compounds, i.e., methanol (MeOH) and ethanol (EtOH). The real-world applications of this E-nose were also demonstrated. Based on the proposed methods, this instrument can monitor and classify 1 vol% of MeOH contamination in whiskeys. © 2010 Elsevier B.V. All rights reserved.

Saiprasert C.,National Electronic and Computer Technology Center | Thajchayapong S.,National Electronic and Computer Technology Center
IEEE Communications Letters | Year: 2015

This letter proposes a driver identification algorithm developed for using minimal information transmitted in vehicle-to-vehicle (V2V) environment based on the assumption that each driver has his/her own unique driving behavior characteristics hidden in conventional driving behaviour signals. Performance evaluation using real-world data shows that the proposed algorithm accurately identifies three drivers in 15 trips using only two acceleration signals at a sampling rate much lower than the one used in previous study. Furthermore, it is shown that the proposed algorithm is able to perform driver identification within a small connectivity time in a scenario where driving behavior signals of are transmitted via a V2V communication environment in a streaming manner. © 1997-2012 IEEE.

Jolivot R.,National Electronic and Computer Technology Center | Benezeth Y.,University of Burgundy | Marzani F.,University of Burgundy
International Journal of Biomedical Imaging | Year: 2013

In vivo quantitative assessment of skin lesions is an important step in the evaluation of skin condition. An objective measurement device can help as a valuable tool for skin analysis. We propose an explorative new multispectral camera specifically developed for dermatology/cosmetology applications. The multispectral imaging system provides images of skin reflectance at different wavebands covering visible and near-infrared domain. It is coupled with a neural network-based algorithm for the reconstruction of reflectance cube of cutaneous data. This cube contains only skin optical reflectance spectrum in each pixel of the bidimensional spatial information. The reflectance cube is analyzed by an algorithm based on a Kubelka-Munk model combined with evolutionary algorithm. The technique allows quantitative measure of cutaneous tissue and retrieves five skin parameter maps: melanin concentration, epidermis/dermis thickness, haemoglobin concentration, and the oxygenated hemoglobin. The results retrieved on healthy participants by the algorithm are in good accordance with the data from the literature. The usefulness of the developed technique was proved during two experiments: a clinical study based on vitiligo and melasma skin lesions and a skin oxygenation experiment (induced ischemia) with healthy participant where normal tissues are recorded at normal state and when temporary ischemia is induced. © 2013 Romuald Jolivot et al.

Loading National Electronic and Computer Technology Center collaborators
Loading National Electronic and Computer Technology Center collaborators