Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743334
J. E. Vera, S. Mora, J. A. Torres, J. Avendano
To improve the characteristics of images taken by the IDEAM, the results obtained applying two algorithms to Synthetic Aperture Radar images or SAR images in regions of Colombia affected by natural disasters are discussed and compared. Two techniques of digital image processing were used, pyramidal fusion Morphological and the Discrete Wavelet Transform. An analysis of the responses obtained by each method was performed for determining which method is suitable according to pixellevel image fusion, for testing purposes and compare the two techniques, data about of entropy and correlation was calculated in MATLAB®. The results obtained show that the morphological fusion method presents a high performance in the SAR image processing, significantly improving the grouping of points on the test image.
{"title":"Analysis of images SAR to flood prevention implementing fusion methods","authors":"J. E. Vera, S. Mora, J. A. Torres, J. Avendano","doi":"10.1109/STSIVA.2016.7743334","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743334","url":null,"abstract":"To improve the characteristics of images taken by the IDEAM, the results obtained applying two algorithms to Synthetic Aperture Radar images or SAR images in regions of Colombia affected by natural disasters are discussed and compared. Two techniques of digital image processing were used, pyramidal fusion Morphological and the Discrete Wavelet Transform. An analysis of the responses obtained by each method was performed for determining which method is suitable according to pixellevel image fusion, for testing purposes and compare the two techniques, data about of entropy and correlation was calculated in MATLAB®. The results obtained show that the morphological fusion method presents a high performance in the SAR image processing, significantly improving the grouping of points on the test image.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"19 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120902298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743348
M. Forero, Sammy A. Perdomo, M. Quimbaya
A new image processing method for cell detection in leaves of Arabidopsis thaliana is presented. Using complementary image processing techniques, we introduce a good way to obtain the original cell contour shapes, surpassing the limitations given by factors like noise, stomata, blurred edges, and non-uniform illumination. Preliminary results show this process minimizes considerably the time of cell detection in comparison with the traditional biology methods that include a tedious freehand path, and produces matching percentages of true borders over 80%. Experimental results are shown.
{"title":"New method for wall cells detection in Arabidopsis thaliana leaves","authors":"M. Forero, Sammy A. Perdomo, M. Quimbaya","doi":"10.1109/STSIVA.2016.7743348","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743348","url":null,"abstract":"A new image processing method for cell detection in leaves of Arabidopsis thaliana is presented. Using complementary image processing techniques, we introduce a good way to obtain the original cell contour shapes, surpassing the limitations given by factors like noise, stomata, blurred edges, and non-uniform illumination. Preliminary results show this process minimizes considerably the time of cell detection in comparison with the traditional biology methods that include a tedious freehand path, and produces matching percentages of true borders over 80%. Experimental results are shown.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128223220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743329
A. F. Torres-Monsalve, Jaime Velasco-Medina
Image and video processing algorithms implemented in software, require most computation time when the image size is increased. Also, some algorithms must be processed at high-speed, for example the image thresholding algorithms for high throughput real-time applications. Then, in order to overcome this requirement, the algorithms must be efficiently implemented in hardware. In this paper, we present the hardware architectures for ISODATA and Otsu thresholding algorithms comparing area, latency, throughput and power consumption. The designs are described using generic structural VHDL and synthesized on the FPGA EP4CE115F29C7N. The designed architectures were verified using Signal Tap and an image acquisition system based on the D5M camera and the DE2-115 development kit of Terasic.
{"title":"Hardware implementation of ISODATA and Otsu thresholding algorithms","authors":"A. F. Torres-Monsalve, Jaime Velasco-Medina","doi":"10.1109/STSIVA.2016.7743329","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743329","url":null,"abstract":"Image and video processing algorithms implemented in software, require most computation time when the image size is increased. Also, some algorithms must be processed at high-speed, for example the image thresholding algorithms for high throughput real-time applications. Then, in order to overcome this requirement, the algorithms must be efficiently implemented in hardware. In this paper, we present the hardware architectures for ISODATA and Otsu thresholding algorithms comparing area, latency, throughput and power consumption. The designs are described using generic structural VHDL and synthesized on the FPGA EP4CE115F29C7N. The designed architectures were verified using Signal Tap and an image acquisition system based on the D5M camera and the DE2-115 development kit of Terasic.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129462198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743335
Melissa Ramlrez, M. Sotaquirá, Alberto De La Cruz, Esther Maria, G. Avellaneda, Ana Ochoa
We present an automatic speech recognition (ASR) system which, along with a haptic interface, is aimed at helping preschool children to learn Braille. The ASR algorithm extracts a set of Mel-Frequency Cepstral Coefficients (MFCC) from the speech signal, followed by a Dynamic Time Warping (DTW) approach, thus allowing to recognize vowels pronounced by the user. The ASR algorithm was tested on 9 subjects and its sensitivity was measured in terms of the percentage of true positives. The highest accuracy values were obtained for the a, e, o and u vowels (with hit ratios of 88.8% in all cases), whereas the i vowel exhibited the lowest sensitivity (77.7%). Validation of user interaction with the haptic system is currently underway, and additional testing is needed to determine the potential benefits that this system offers in the context of preschool education in Colombia.
{"title":"An automatic speech recognition system for helping visually impaired children to learn Braille","authors":"Melissa Ramlrez, M. Sotaquirá, Alberto De La Cruz, Esther Maria, G. Avellaneda, Ana Ochoa","doi":"10.1109/STSIVA.2016.7743335","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743335","url":null,"abstract":"We present an automatic speech recognition (ASR) system which, along with a haptic interface, is aimed at helping preschool children to learn Braille. The ASR algorithm extracts a set of Mel-Frequency Cepstral Coefficients (MFCC) from the speech signal, followed by a Dynamic Time Warping (DTW) approach, thus allowing to recognize vowels pronounced by the user. The ASR algorithm was tested on 9 subjects and its sensitivity was measured in terms of the percentage of true positives. The highest accuracy values were obtained for the a, e, o and u vowels (with hit ratios of 88.8% in all cases), whereas the i vowel exhibited the lowest sensitivity (77.7%). Validation of user interaction with the haptic system is currently underway, and additional testing is needed to determine the potential benefits that this system offers in the context of preschool education in Colombia.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129682191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743357
Keider Hoyos-Osorio, Jairo Castaneda-Gonzaiez, G. Daza-Santacoloma
The epilepsy is a common neurological disease caused by a neuronal electric activity imbalance in any side of the brain, named epileptic focus. The epilepsy is characterized by recurrent and sudden seizures. Recently, researchers found that approximately 50% of epileptic patients feel auras (subjective phenomenon which precedes and indicates an epileptic seizure onset) associated to a physiological anomaly. In this research, a non-invasive seizure prediction methodology is developed in order to improve the quality of life of the patients with epilepsy, alerting them about potential seizure and avoiding falls, injuries, wounds or even death. The research addresses the recognition of patterns in electroencephalographic (EEG) and electrocardiographic (ECG) signals taken from 7 patients with focal epilepsy whom are treated at the Instituto de Epilepsia y Parkinson del Eje Cafetero-NEUROCENTRO-. The biosignals were independently analyzed, at least 15 minutes before the seizure onset and in periods with no seizure were considered. The methodology considers the generation of features computed over the discrete wavelet transform of the EEG signal and others related to the heart rate variability in the ECG signal. Using feature selection techniques such as Sequential Forward Selection (SFS) with classification algorithms as cost functions (linear-Bayes and k-nearest neighbors classifier), we found which features have the most relevant information about pre-ictal state and which of them are the most appropriated for seizure forecasting, therefore we found that ECG signal could be a potential resource for predicting epileptic seizures, and we concluded that there are patterns in EEG and ECG signals that, via machine learning algorithms, can predict the epileptic seizure onset.
{"title":"Automatic epileptic seizure prediction based on scalp EEG and ECG signals","authors":"Keider Hoyos-Osorio, Jairo Castaneda-Gonzaiez, G. Daza-Santacoloma","doi":"10.1109/STSIVA.2016.7743357","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743357","url":null,"abstract":"The epilepsy is a common neurological disease caused by a neuronal electric activity imbalance in any side of the brain, named epileptic focus. The epilepsy is characterized by recurrent and sudden seizures. Recently, researchers found that approximately 50% of epileptic patients feel auras (subjective phenomenon which precedes and indicates an epileptic seizure onset) associated to a physiological anomaly. In this research, a non-invasive seizure prediction methodology is developed in order to improve the quality of life of the patients with epilepsy, alerting them about potential seizure and avoiding falls, injuries, wounds or even death. The research addresses the recognition of patterns in electroencephalographic (EEG) and electrocardiographic (ECG) signals taken from 7 patients with focal epilepsy whom are treated at the Instituto de Epilepsia y Parkinson del Eje Cafetero-NEUROCENTRO-. The biosignals were independently analyzed, at least 15 minutes before the seizure onset and in periods with no seizure were considered. The methodology considers the generation of features computed over the discrete wavelet transform of the EEG signal and others related to the heart rate variability in the ECG signal. Using feature selection techniques such as Sequential Forward Selection (SFS) with classification algorithms as cost functions (linear-Bayes and k-nearest neighbors classifier), we found which features have the most relevant information about pre-ictal state and which of them are the most appropriated for seizure forecasting, therefore we found that ECG signal could be a potential resource for predicting epileptic seizures, and we concluded that there are patterns in EEG and ECG signals that, via machine learning algorithms, can predict the epileptic seizure onset.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743300
Luis Angel, J. Viola
A robotic system may be affected by external disturbances and parametric uncertainness, which change its dynamical behavior. One of the most common disturbances is the payload variation that affects the control system performance. If the payload variation is known, its negative effects can be minimized adjusting the control system parameters. However, when the payload variation is unknown, the control system parameters cannot be adjusted appropriately. This paper proposes a methodology for the payload variation estimation for a robotic system using unsupervised classification techniques. BSAS, MBSAS and Kmeans algorithms were employed as clustering techniques. The Silhouette index and the standard deviation were employed as performance indexes to compare the classification algorithms. Results showed that Kmeans algorithm has a better performance for the payload variation classification.
{"title":"Payload estimation for a robotic system using unsupervised classification","authors":"Luis Angel, J. Viola","doi":"10.1109/STSIVA.2016.7743300","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743300","url":null,"abstract":"A robotic system may be affected by external disturbances and parametric uncertainness, which change its dynamical behavior. One of the most common disturbances is the payload variation that affects the control system performance. If the payload variation is known, its negative effects can be minimized adjusting the control system parameters. However, when the payload variation is unknown, the control system parameters cannot be adjusted appropriately. This paper proposes a methodology for the payload variation estimation for a robotic system using unsupervised classification techniques. BSAS, MBSAS and Kmeans algorithms were employed as clustering techniques. The Silhouette index and the standard deviation were employed as performance indexes to compare the classification algorithms. Results showed that Kmeans algorithm has a better performance for the payload variation classification.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115504258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743337
L. Ángel, J. Viola, M. Vega, R. Restrepo
This paper presents a methodology for an autoclave sterilization process stages estimation using logistic regression models. The Autoclave sterilization process has four stages Pre-Vacuum, Rising Temperature, Sterilizing and Vacuum-Drying, which are classified employing the one vs all algorithm. The logistic regression model employed as variables the Autoclave absolute temperature and pressure. Data from 35 sterilization process were employed to find the logistic regression coefficients. As performance indexes, the precision, coverage and harmonic mean were employed. Results shown that the classification algorithm reached an efficiency of 81% to estimate the sterilization process stages.
{"title":"Sterilization process stages estimation for an autoclave using logistic regression models","authors":"L. Ángel, J. Viola, M. Vega, R. Restrepo","doi":"10.1109/STSIVA.2016.7743337","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743337","url":null,"abstract":"This paper presents a methodology for an autoclave sterilization process stages estimation using logistic regression models. The Autoclave sterilization process has four stages Pre-Vacuum, Rising Temperature, Sterilizing and Vacuum-Drying, which are classified employing the one vs all algorithm. The logistic regression model employed as variables the Autoclave absolute temperature and pressure. Data from 35 sterilization process were employed to find the logistic regression coefficients. As performance indexes, the precision, coverage and harmonic mean were employed. Results shown that the classification algorithm reached an efficiency of 81% to estimate the sterilization process stages.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121910039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743338
L. T. Molano, Y. M. Jiménez, J. Villamarín, Nylho A. Dorado, Munoz Fabian G. Munoz, L. F. Londoño
This paper presents the implementation of a quantitative system of assessment by ultrasound, which allows the acoustic characterization of animal blood plasma, with potential applications in hematic biometric techniques. The system comprises a unidimensional electronic controller with step size 1 mm which enables the acoustic inspection of blood samples using an ultrasonic field incident with central frequency of 5MHz in pulse echo mode. Additionally, the implemented system incorporates the development of computer algorithms in Matlab allowing digital signal processing of ultrasonic backscattered signals, based on the estimation of acoustic parameters such as speed of sound and spectral energy loss, using the logarithmic power spectral density subtraction in the bandwidth of the transducer (1MHz @ -3dB). Estimating acoustic parameters from blood samples centrifuged to 3398 rpm were correlated with density values, pH and concentration of platelets. The results showed that samples with densities between 1.040 g/ml-1.051 g/ml and variations of platelet concentrations between 45×103/mm3-138×103/mm3, showed variations in sound velocity between 1335 m/s-1572 m/s. Moreover, measurements showed a sound attenuation subtle difference variations between 0.21dB/cm to 2.73 dB/cm. Finally quantitative ultrasound system shows that the estimate of velocity profiles acoustic propagation enables infer variations of platelet concentration at room temperature with potential applications in the quality assessment of blood plasma.
{"title":"Quantitative ultrasound system for the characterization of animal blood plasma","authors":"L. T. Molano, Y. M. Jiménez, J. Villamarín, Nylho A. Dorado, Munoz Fabian G. Munoz, L. F. Londoño","doi":"10.1109/STSIVA.2016.7743338","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743338","url":null,"abstract":"This paper presents the implementation of a quantitative system of assessment by ultrasound, which allows the acoustic characterization of animal blood plasma, with potential applications in hematic biometric techniques. The system comprises a unidimensional electronic controller with step size 1 mm which enables the acoustic inspection of blood samples using an ultrasonic field incident with central frequency of 5MHz in pulse echo mode. Additionally, the implemented system incorporates the development of computer algorithms in Matlab allowing digital signal processing of ultrasonic backscattered signals, based on the estimation of acoustic parameters such as speed of sound and spectral energy loss, using the logarithmic power spectral density subtraction in the bandwidth of the transducer (1MHz @ -3dB). Estimating acoustic parameters from blood samples centrifuged to 3398 rpm were correlated with density values, pH and concentration of platelets. The results showed that samples with densities between 1.040 g/ml-1.051 g/ml and variations of platelet concentrations between 45×103/mm3-138×103/mm3, showed variations in sound velocity between 1335 m/s-1572 m/s. Moreover, measurements showed a sound attenuation subtle difference variations between 0.21dB/cm to 2.73 dB/cm. Finally quantitative ultrasound system shows that the estimate of velocity profiles acoustic propagation enables infer variations of platelet concentration at room temperature with potential applications in the quality assessment of blood plasma.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129468522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743355
E. Severeyn, J. Velásquez, Gilberto Perpiñan, H. Herrera, M. Pacheco, Sara Wong
Athletes usually start the training with normal body water content, and then they dehydrate during exercise. The water deficit may contribute to increased heart rate and therefore impaired heart rate variability (HRV) postexercise. This paper presents a protocol to study the dehydration from the electrocardiographic signal in athletes, which comprised three phases: (i) Rest (RE): before any physical activity, (ii) post-exercise (PE): athletes performed a physical activity by pedaling a stationary bike, iii) post-hydration (PH): the subjects drank water ad libitum. In each phase, an electrocardiographic acquisition and weight measure were performed. In RE phase height was measured and in PE phase subjective effort perception of Borg was performed. The protocol was carried out in the morning. The sample consisted of 17 male athletes. The study of HRV in each of the electrocardiographic signals was performed by obtaining time-domain parameters (RR, RMSSD, SDRR), frequency-domain parameters (LF, HF) and non-linear parameters (SD1, SD2, approximate entropy and scaled exponents: α1 and α2). The findings in this paper imply that parameters: RR, RMSSD, SDRR, LF, HF, α2, SD1 and SD2 from HRV, are able to differentiate between phases of hydration and dehydration in the individual athlete, which could be used in the early detection of dehydration using the ECG signal, that is readily available and also noninvasively measure.
{"title":"Heart rate variability analysis during a dehydration protocol on athletes","authors":"E. Severeyn, J. Velásquez, Gilberto Perpiñan, H. Herrera, M. Pacheco, Sara Wong","doi":"10.1109/STSIVA.2016.7743355","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743355","url":null,"abstract":"Athletes usually start the training with normal body water content, and then they dehydrate during exercise. The water deficit may contribute to increased heart rate and therefore impaired heart rate variability (HRV) postexercise. This paper presents a protocol to study the dehydration from the electrocardiographic signal in athletes, which comprised three phases: (i) Rest (RE): before any physical activity, (ii) post-exercise (PE): athletes performed a physical activity by pedaling a stationary bike, iii) post-hydration (PH): the subjects drank water ad libitum. In each phase, an electrocardiographic acquisition and weight measure were performed. In RE phase height was measured and in PE phase subjective effort perception of Borg was performed. The protocol was carried out in the morning. The sample consisted of 17 male athletes. The study of HRV in each of the electrocardiographic signals was performed by obtaining time-domain parameters (RR, RMSSD, SDRR), frequency-domain parameters (LF, HF) and non-linear parameters (SD1, SD2, approximate entropy and scaled exponents: α1 and α2). The findings in this paper imply that parameters: RR, RMSSD, SDRR, LF, HF, α2, SD1 and SD2 from HRV, are able to differentiate between phases of hydration and dehydration in the individual athlete, which could be used in the early detection of dehydration using the ECG signal, that is readily available and also noninvasively measure.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130658874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/STSIVA.2016.7743366
D. Márquez-Viloria, J. Botero-Valencia, J. Villegas-Ceballos
The consequences of the exploitation of natural resources are evident in the current bad environmental conditions. For this reason, governments have implemented realtime environmental measurement systems and they have applied strategies focused to restrict the physical activities and avoid futures health problem. Even, in critical cases, the governments take measures to stop the movement of motor vehicles when the threshold of World Health Organization (WHO) is exceeded. The governmental measurement systems are limited because of high cost and they are typically located in big cities with few points of measure losing a lot of information in the uncovered areas. This work presents the development and implementation of a low cost georeferenced air-pollution measurement system that offers information of particulate measurement PM1, PM2.5 y PM10 by scatter. In addition, the system measures the levels of ozone concentration, and atmospheric variables such as temperature, humidity and barometric pressure. The whole system is connected to a low cost microprocessor with integrated Wi-Fi allowing to send the data to the cloud in real-time using MQTTprotocol, and thus the data can be georeferenced and published on an open access platform, used to the Internet of Things (IoT), for the acquisition and visualization of the data. In this way, the information is public and the residents of a particular area can look for the nearest measure of the environmental conditions. This work proposes a simple and cheap way to implement a measurement system allowing it to be easily replicated. The consequences for the health because of exposition to pollutants are serious, it implies a public policy issues with direct effect in the economy and development of cities. Because of all this, the air-pollution measurement systems should be improved and available in many more points. Governments can make public policy decisions about the environment using the information from systems like the proposed in this work.
{"title":"A low cost georeferenced air-pollution measurement system used as early warning tool","authors":"D. Márquez-Viloria, J. Botero-Valencia, J. Villegas-Ceballos","doi":"10.1109/STSIVA.2016.7743366","DOIUrl":"https://doi.org/10.1109/STSIVA.2016.7743366","url":null,"abstract":"The consequences of the exploitation of natural resources are evident in the current bad environmental conditions. For this reason, governments have implemented realtime environmental measurement systems and they have applied strategies focused to restrict the physical activities and avoid futures health problem. Even, in critical cases, the governments take measures to stop the movement of motor vehicles when the threshold of World Health Organization (WHO) is exceeded. The governmental measurement systems are limited because of high cost and they are typically located in big cities with few points of measure losing a lot of information in the uncovered areas. This work presents the development and implementation of a low cost georeferenced air-pollution measurement system that offers information of particulate measurement PM1, PM2.5 y PM10 by scatter. In addition, the system measures the levels of ozone concentration, and atmospheric variables such as temperature, humidity and barometric pressure. The whole system is connected to a low cost microprocessor with integrated Wi-Fi allowing to send the data to the cloud in real-time using MQTTprotocol, and thus the data can be georeferenced and published on an open access platform, used to the Internet of Things (IoT), for the acquisition and visualization of the data. In this way, the information is public and the residents of a particular area can look for the nearest measure of the environmental conditions. This work proposes a simple and cheap way to implement a measurement system allowing it to be easily replicated. The consequences for the health because of exposition to pollutants are serious, it implies a public policy issues with direct effect in the economy and development of cities. Because of all this, the air-pollution measurement systems should be improved and available in many more points. Governments can make public policy decisions about the environment using the information from systems like the proposed in this work.","PeriodicalId":373420,"journal":{"name":"2016 XXI Symposium on Signal Processing, Images and Artificial Vision (STSIVA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132388069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：