Pub Date : 2017-08-01DOI: 10.1109/INTERCON.2017.8079637
H. Nieto-Chaupis
From a sample of 20 type 2 diabetes patients with evidence of exhibiting nonlinear behavior of glucose, we have proposed a mathematical model based on the convolution of the so-called step-function and a full nonlinear function. For this end, we have performed successive measurements of glucose in order to construct the histograms as function of time. With this statistics we have applied a 5-parameters fitting in order to identify the parameters characterized with a high sensitivity on the morphology of the curves of glucose. Data have exhibited abnormal behavior in their glucose's evolution for a period of 60 days. Thus, we have identified the curve pattern so that a 5-parameters fitting was performed. The fit function has turned out to have the morphology of the so-called step-function roughly. However, data exhibits also disturbs which can be attributed to the patient's behavior mainly related to their alimentary habits or others psychological factors. Under the assumption that the patients are exhibiting a certain unpredictable policy of alimentary habits and are not following a strict policy of pharmacology, the model has yielded predictions in a confidence of order of 85% ± 10%, where at least one of 5 patients of the sample (20 patients) might acquire a disorder in their glucose's evolutions for subsequent 10 weeks.
{"title":"Modeling the nonlinear behavior of glucose by using the nonlinear step-functions","authors":"H. Nieto-Chaupis","doi":"10.1109/INTERCON.2017.8079637","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079637","url":null,"abstract":"From a sample of 20 type 2 diabetes patients with evidence of exhibiting nonlinear behavior of glucose, we have proposed a mathematical model based on the convolution of the so-called step-function and a full nonlinear function. For this end, we have performed successive measurements of glucose in order to construct the histograms as function of time. With this statistics we have applied a 5-parameters fitting in order to identify the parameters characterized with a high sensitivity on the morphology of the curves of glucose. Data have exhibited abnormal behavior in their glucose's evolution for a period of 60 days. Thus, we have identified the curve pattern so that a 5-parameters fitting was performed. The fit function has turned out to have the morphology of the so-called step-function roughly. However, data exhibits also disturbs which can be attributed to the patient's behavior mainly related to their alimentary habits or others psychological factors. Under the assumption that the patients are exhibiting a certain unpredictable policy of alimentary habits and are not following a strict policy of pharmacology, the model has yielded predictions in a confidence of order of 85% ± 10%, where at least one of 5 patients of the sample (20 patients) might acquire a disorder in their glucose's evolutions for subsequent 10 weeks.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123334054","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079688
David Zabala-Blanco, G. Campuzano, César A. Azurdia-Meza
It is well known that the performance of orthogonal frequency division multiplexing is highly sensitive to frequency offset. In this paper, we present theoretical results to assess the intercarrier interference reduction using general pulse shaping filters in digital video broadcasting over cable (DVB-C) systems. These pulses are characterized by only one design parameter, known as the roll-off factor. We found that for the DVB standard, which employs a raised cosine (RC) function, double-jump 1 (DJ1) filter outperforms the RC pulse as well as the rest of pulses in terms of both the bit error rate and the signal-to-interference ratio power. This is because the DJ1 pulse spectra presents the smallest lateral lobes and a broad main lobe.
{"title":"General nyquist-I pulses to mitigate carrier frequency offset in DVB-C-OFDM systems","authors":"David Zabala-Blanco, G. Campuzano, César A. Azurdia-Meza","doi":"10.1109/INTERCON.2017.8079688","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079688","url":null,"abstract":"It is well known that the performance of orthogonal frequency division multiplexing is highly sensitive to frequency offset. In this paper, we present theoretical results to assess the intercarrier interference reduction using general pulse shaping filters in digital video broadcasting over cable (DVB-C) systems. These pulses are characterized by only one design parameter, known as the roll-off factor. We found that for the DVB standard, which employs a raised cosine (RC) function, double-jump 1 (DJ1) filter outperforms the RC pulse as well as the rest of pulses in terms of both the bit error rate and the signal-to-interference ratio power. This is because the DJ1 pulse spectra presents the smallest lateral lobes and a broad main lobe.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"438 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115920139","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079649
J. Zeceña, Vivian Lucía Orozco Molina
Supervisory Control and Data Acquisition (SCADA) systems are used in many industries, particularly in the control of nationwide electric grids. These systems may by law, technical obsolescence, or failure, need to be replaced by newer ones. However, the testing and handing over of functions from the old SCADA to the new one (i.e., switchover) has to be done with minimum risk and maximum continuity of operations. Several vendors offer partial solutions to this problem, but they usually imply downtime or incomplete testing. We have developed a communications multiplexing system, Hydra, that allows for several Master Terminal Units (MTU) to poll telemetry data from the same set of Remote Terminal Units (RTU) using the DNP3 over TCP/IP protocol without requiring their reconfiguration. This system multiplexes DNP3 traffic so that MTUs share access to the same network of RTUs which allows for complete testing of functionality prior to commissioning with virtually no downtime, therefore addressing the main issues of concern when transitioning between SCADA systems. This paper deals with the motivation, architecture and implementation of Hydra.
{"title":"Hydra - A DNP3 multiplexing platform for SCADA system switchover","authors":"J. Zeceña, Vivian Lucía Orozco Molina","doi":"10.1109/INTERCON.2017.8079649","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079649","url":null,"abstract":"Supervisory Control and Data Acquisition (SCADA) systems are used in many industries, particularly in the control of nationwide electric grids. These systems may by law, technical obsolescence, or failure, need to be replaced by newer ones. However, the testing and handing over of functions from the old SCADA to the new one (i.e., switchover) has to be done with minimum risk and maximum continuity of operations. Several vendors offer partial solutions to this problem, but they usually imply downtime or incomplete testing. We have developed a communications multiplexing system, Hydra, that allows for several Master Terminal Units (MTU) to poll telemetry data from the same set of Remote Terminal Units (RTU) using the DNP3 over TCP/IP protocol without requiring their reconfiguration. This system multiplexes DNP3 traffic so that MTUs share access to the same network of RTUs which allows for complete testing of functionality prior to commissioning with virtually no downtime, therefore addressing the main issues of concern when transitioning between SCADA systems. This paper deals with the motivation, architecture and implementation of Hydra.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131523183","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079651
Ricardo Yauri, M. Rios, J. Lezama
This paper presents a water quality monitoring system using low power hardware based in the Internet of Things. Six sensor nodes for water quality monitoring in pisciculture are installed in three region of the Peruvian amazon. The sensor node is a modular hardware composed by control, communication and sensor module that measure parameters such as pH, conductivity and temperature. All data information is managed by software platform designed using open source tools, data information allows to control water pollution and their effect in the pisciculture. Data acquired is used by the researchers of the Instituto de Investigaciones de la Amazonía Peruana to study the health and growing population of paiche fish.
{"title":"Water quality monitoring of Peruvian Amazon based in the Internet of Things","authors":"Ricardo Yauri, M. Rios, J. Lezama","doi":"10.1109/INTERCON.2017.8079651","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079651","url":null,"abstract":"This paper presents a water quality monitoring system using low power hardware based in the Internet of Things. Six sensor nodes for water quality monitoring in pisciculture are installed in three region of the Peruvian amazon. The sensor node is a modular hardware composed by control, communication and sensor module that measure parameters such as pH, conductivity and temperature. All data information is managed by software platform designed using open source tools, data information allows to control water pollution and their effect in the pisciculture. Data acquired is used by the researchers of the Instituto de Investigaciones de la Amazonía Peruana to study the health and growing population of paiche fish.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128450950","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079662
Alexi Delgado
Citizen criminality has become an important social problem in Lima city, due to the fact that the number of crimes has increased. In this study, we conducted a citizen criminality assessment using the grey clustering method, which is based on grey systems theory. The case study was conducted on 32 districts from Lima, Peru. Consequently, a map on the citizen criminality situation was obtained. The results revealed that the more insecure districts were San Juan de Lurigancho, Los Olivos, and Cercado de Lima; and the less insecure districts were Ancón, Surquillo, and Lince. The study results could help to the central and district government to make the best decision on the citizen criminality problem. The grey clustering method showed interesting results and could be applied to other social problems, as this method considers the uncertainty within its analysis.
由于犯罪数量的增加，公民犯罪已经成为利马市一个重要的社会问题。本研究以灰色系统理论为基础，运用灰色聚类方法进行公民犯罪评估。案例研究是在秘鲁利马的32个地区进行的。因此，获得了关于公民犯罪情况的地图。结果显示，最不安全的地区是San Juan de Lurigancho、Los Olivos和Cercado de Lima;不太安全的地区是Ancón, Surquillo和Lince。研究结果可以帮助中央和地方政府对公民犯罪问题做出最佳决策。灰色聚类方法显示出有趣的结果，可以应用于其他社会问题，因为该方法在分析中考虑了不确定性。
{"title":"Citizen criminality assessment in lima city using the grey clustering method","authors":"Alexi Delgado","doi":"10.1109/INTERCON.2017.8079662","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079662","url":null,"abstract":"Citizen criminality has become an important social problem in Lima city, due to the fact that the number of crimes has increased. In this study, we conducted a citizen criminality assessment using the grey clustering method, which is based on grey systems theory. The case study was conducted on 32 districts from Lima, Peru. Consequently, a map on the citizen criminality situation was obtained. The results revealed that the more insecure districts were San Juan de Lurigancho, Los Olivos, and Cercado de Lima; and the less insecure districts were Ancón, Surquillo, and Lince. The study results could help to the central and district government to make the best decision on the citizen criminality problem. The grey clustering method showed interesting results and could be applied to other social problems, as this method considers the uncertainty within its analysis.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128180699","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079692
E. Carrera, Andrés González, R. Carrera
Diabetic retinopathy is a common eye disease in diabetic patients and is the main cause of blindness in the population. Early detection of diabetic retinopathy protects patients from losing their vision. Thus, this paper proposes a computer-assisted diagnosis based on the digital processing of retinal images in order to help people detecting diabetic retinopathy in advance. The main goal is to automatically classify the grade of non-proliferative diabetic retinopathy at any retinal image. For that, an initial image processing stage isolates blood vessels, microaneurysms and hard exudates in order to extract features that can be used by a support vector machine to figure out the retinopathy grade of each retinal image. This proposal has been tested on a database of 400 retinal images labeled according to a 4-grade scale of non-proliferative diabetic retinopathy. As a result, we obtained a maximum sensitivity of 95% and a predictive capacity of 94%. Robustness with respect to changes in the parameters of the algorithm has also been evaluated.
{"title":"Automated detection of diabetic retinopathy using SVM","authors":"E. Carrera, Andrés González, R. Carrera","doi":"10.1109/INTERCON.2017.8079692","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079692","url":null,"abstract":"Diabetic retinopathy is a common eye disease in diabetic patients and is the main cause of blindness in the population. Early detection of diabetic retinopathy protects patients from losing their vision. Thus, this paper proposes a computer-assisted diagnosis based on the digital processing of retinal images in order to help people detecting diabetic retinopathy in advance. The main goal is to automatically classify the grade of non-proliferative diabetic retinopathy at any retinal image. For that, an initial image processing stage isolates blood vessels, microaneurysms and hard exudates in order to extract features that can be used by a support vector machine to figure out the retinopathy grade of each retinal image. This proposal has been tested on a database of 400 retinal images labeled according to a 4-grade scale of non-proliferative diabetic retinopathy. As a result, we obtained a maximum sensitivity of 95% and a predictive capacity of 94%. Robustness with respect to changes in the parameters of the algorithm has also been evaluated.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115337757","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079697
Enzo Romero, R. Callupe, D. Elias
This paper presents the implementation of a Finger force detection platform capable to measure the exerted forces by the index, middle, ring and little finger in single-axis direction (flexion); and in dual-axis direction (flexion/adduction) by the thumb. It can be adapted to different sizes in both right or left hand. A test protocol is established. Also, a Graphical User Interface (GUI) is developed in order to assist the subject during the test. The results show the maximum forces developed by each finger among Peruvian participants.
{"title":"Implementation of a finger force detection platform with a graphical user interface","authors":"Enzo Romero, R. Callupe, D. Elias","doi":"10.1109/INTERCON.2017.8079697","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079697","url":null,"abstract":"This paper presents the implementation of a Finger force detection platform capable to measure the exerted forces by the index, middle, ring and little finger in single-axis direction (flexion); and in dual-axis direction (flexion/adduction) by the thumb. It can be adapted to different sizes in both right or left hand. A test protocol is established. Also, a Graphical User Interface (GUI) is developed in order to assist the subject during the test. The results show the maximum forces developed by each finger among Peruvian participants.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129931469","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}
The people that need rehabilitation have grown and have overwhelmed therapists therefore new technological advances are required to provide service to a larger population, also the cost is a factor to consider. Particularly, the people who has suffered and survive a stroke (cerebral sudden malfunction) usually need therapy to recover lost functions, such as neuromuscular coordination. In this work, we propose a mechatronic system to help patients to recover hand-eye coordination which requires movement of the whole arm. The preliminary results show that the system is ready to be validated with real patients, that is reliable and that can be replicated as needed.
{"title":"Mechatronic system for rehabilitation of patients after a stroke","authors":"Octavio Diaz-Hernández, Sandra Montserrat Garcia-Villalpando","doi":"10.1109/INTERCON.2017.8079654","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079654","url":null,"abstract":"The people that need rehabilitation have grown and have overwhelmed therapists therefore new technological advances are required to provide service to a larger population, also the cost is a factor to consider. Particularly, the people who has suffered and survive a stroke (cerebral sudden malfunction) usually need therapy to recover lost functions, such as neuromuscular coordination. In this work, we propose a mechatronic system to help patients to recover hand-eye coordination which requires movement of the whole arm. The preliminary results show that the system is ready to be validated with real patients, that is reliable and that can be replicated as needed.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128009505","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079713
M. Montalvo, Eduardo Calle-Ortiz
The present research describes the design and implementation of a programming by demonstration algorithm, where data is taken from a human narrator and then processed and imitated by the social robot Nao. This has been done by the use of artificial neural networks and inverse kinematics algorithms, resulting in a 7.25% trajectory difference when comparing the instructor movements with the robot learned movements. An exploratory study is also presented regarding recent advances in social robotics, affective computation, and human-machine interaction. These subjects are analyzed and an innovative way of integrating them as a tool for the narration and diffusion of legends and oral expressions in risk of disappearance is proposed. This work aims the new generations to renew their interest in traditional oral elements and actively involve them in the preservation and transmission of intangible cultural heritage.
{"title":"Programming by demonstration for the teaching and preservation of intangible cultural heritage","authors":"M. Montalvo, Eduardo Calle-Ortiz","doi":"10.1109/INTERCON.2017.8079713","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079713","url":null,"abstract":"The present research describes the design and implementation of a programming by demonstration algorithm, where data is taken from a human narrator and then processed and imitated by the social robot Nao. This has been done by the use of artificial neural networks and inverse kinematics algorithms, resulting in a 7.25% trajectory difference when comparing the instructor movements with the robot learned movements. An exploratory study is also presented regarding recent advances in social robotics, affective computation, and human-machine interaction. These subjects are analyzed and an innovative way of integrating them as a tool for the narration and diffusion of legends and oral expressions in risk of disappearance is proposed. This work aims the new generations to renew their interest in traditional oral elements and actively involve them in the preservation and transmission of intangible cultural heritage.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124281019","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 : 2017-08-01DOI: 10.1109/INTERCON.2017.8079727
C. Jose L. Flores, A. E. Gladys Cutipa, R. Lauro Enciso
The present work proposes to recognize the static hand gestures taken under invariations features as scale, rotation, translation, illumination, noise and background. We use the alphabet of sign language of Peru (LSP). For this purpose, digital image processing techniques are used to eliminate or reduce noise, to improve the contrast under a variant illumination, to separate the hand from the background of the image and finally detect and cut the region containing the hand gesture. We use of convolutional neural networks (CNN) to classify the 24 hand gestures. Two CNN architectures were developed with different amounts of layers and parameters per layer. The tests showed that the first CNN has an accuracy of 95.37% and the second CNN has an accuracy of 96.20% in terms of recognition of the 24 static hand gestures using the database developed. We compared the two architectures developed in accuracy level for each type of invariance presented in this paper. We compared the two architectures developed and usual techniques of machine learning in results of accuracy.
{"title":"Application of convolutional neural networks for static hand gestures recognition under different invariant features","authors":"C. Jose L. Flores, A. E. Gladys Cutipa, R. Lauro Enciso","doi":"10.1109/INTERCON.2017.8079727","DOIUrl":"https://doi.org/10.1109/INTERCON.2017.8079727","url":null,"abstract":"The present work proposes to recognize the static hand gestures taken under invariations features as scale, rotation, translation, illumination, noise and background. We use the alphabet of sign language of Peru (LSP). For this purpose, digital image processing techniques are used to eliminate or reduce noise, to improve the contrast under a variant illumination, to separate the hand from the background of the image and finally detect and cut the region containing the hand gesture. We use of convolutional neural networks (CNN) to classify the 24 hand gestures. Two CNN architectures were developed with different amounts of layers and parameters per layer. The tests showed that the first CNN has an accuracy of 95.37% and the second CNN has an accuracy of 96.20% in terms of recognition of the 24 static hand gestures using the database developed. We compared the two architectures developed in accuracy level for each type of invariance presented in this paper. We compared the two architectures developed and usual techniques of machine learning in results of accuracy.","PeriodicalId":229086,"journal":{"name":"2017 IEEE XXIV International Conference on Electronics, Electrical Engineering and Computing (INTERCON)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131081702","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：