Pub Date : 2016-03-03DOI: 10.1109/ICEEOT.2016.7755359
Adidela Daveedu Raju, M. N. Sri, G. L. Devi
The discovery of knowledge from the huge available data is the highest mount setback in practical pattern classification and knowledge discovery problem. The preprocessing of data plays a major role in knowledge discovery as it consequently improves the accuracy of the classifier. One of the preprocessing techniques, attribute subset selection has major importance as the selection leads to better performance of the classifier and the cost of the classification is sensitive to the choice of attributes that used to construct the classifier. This paper proposes a new attribute subset selection method named as Mixed Weighting Mean Classification (MWM-C) method. It evaluates the weights of the available attributes by using 5 major weighting functions such as information gain, information gain ratio, gini index, correlation, chi squared statistic. The five methods are chosen to bias the results of one another. The proposed method is examined on soybean data set and conferred satisfactory results.
{"title":"Attribute subset selection by mixed weighting mean classification method","authors":"Adidela Daveedu Raju, M. N. Sri, G. L. Devi","doi":"10.1109/ICEEOT.2016.7755359","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7755359","url":null,"abstract":"The discovery of knowledge from the huge available data is the highest mount setback in practical pattern classification and knowledge discovery problem. The preprocessing of data plays a major role in knowledge discovery as it consequently improves the accuracy of the classifier. One of the preprocessing techniques, attribute subset selection has major importance as the selection leads to better performance of the classifier and the cost of the classification is sensitive to the choice of attributes that used to construct the classifier. This paper proposes a new attribute subset selection method named as Mixed Weighting Mean Classification (MWM-C) method. It evaluates the weights of the available attributes by using 5 major weighting functions such as information gain, information gain ratio, gini index, correlation, chi squared statistic. The five methods are chosen to bias the results of one another. The proposed method is examined on soybean data set and conferred satisfactory results.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129699927","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7755476
M. Yadav, Ankur Soni
In this paper we are discussing about a FACTS device named as UPFC (unified power flow controller). Its special features are to control active and reactive power course in a transmission line and to adjust the voltage at the bus at which it is situated. This device gives great quality flow on power system stability; these features even more considerable and perceptive that the unified power flow controller can be apply to the transmission line with in their limits and enhancing the power to flow through the preferred path. So this device gives unique control on the power flow and voltage stability. In this paper the working of UPFC is in the field of control flow of power in transmission-line. This research regarding the 6-bus power system to control the active and reactive power in the course of transmission line by keeping this controller at the sending end by simulation tools. When there is no FACTs device (UPFC) the active power, reactive power and voltage through the transmission line cannot be controlled. The circuit model for UPFC is developed using rectifier and inverter circuits. In this thesis, the power system simulation models are made on MATLAB version 7.13. By making the power system simulation model, we are getting result without and with using UPFC and after that these results are compared in form of real and reactive power in the transmission line. On the basis of simulation results and to analyze the performance of UPFC, we can conclude that UPFC is ideal controller for performing such parameters.
{"title":"Improvement of power flow and voltage stability using unified power flow controller","authors":"M. Yadav, Ankur Soni","doi":"10.1109/ICEEOT.2016.7755476","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7755476","url":null,"abstract":"In this paper we are discussing about a FACTS device named as UPFC (unified power flow controller). Its special features are to control active and reactive power course in a transmission line and to adjust the voltage at the bus at which it is situated. This device gives great quality flow on power system stability; these features even more considerable and perceptive that the unified power flow controller can be apply to the transmission line with in their limits and enhancing the power to flow through the preferred path. So this device gives unique control on the power flow and voltage stability. In this paper the working of UPFC is in the field of control flow of power in transmission-line. This research regarding the 6-bus power system to control the active and reactive power in the course of transmission line by keeping this controller at the sending end by simulation tools. When there is no FACTs device (UPFC) the active power, reactive power and voltage through the transmission line cannot be controlled. The circuit model for UPFC is developed using rectifier and inverter circuits. In this thesis, the power system simulation models are made on MATLAB version 7.13. By making the power system simulation model, we are getting result without and with using UPFC and after that these results are compared in form of real and reactive power in the transmission line. On the basis of simulation results and to analyze the performance of UPFC, we can conclude that UPFC is ideal controller for performing such parameters.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129112275","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7754739
W. P. Newman, J. Rebman
Several studies [6,7,8] have found that sunlight has a stress-reducing effect on those who are exposed to it. An innovative new design of artificial lighting known as RaLight is proposed to reflect light with a color rendering index (CRI) nearly identical to natural sunlight. This study will examine the relationship between exposure to RaLight (as a substitute for sunlight) and levels of stress. RaLight is predicted to decrease levels of stress in test subjects. In a commercial call center setting, test subjects will consist of an estimated 50 employees both male and female with ages ranging from 18 to 30 years. The initial control condition will be the common indoor environment which exposes patients to standard fluorescent lighting. Replacing light fixtures with RaLight will then establish both the second phase of the experiment and the independent variable. Throughout each phase, questionnaires, modified from the peer reviewed Wakefield Self-Report Questionnaire, regarding the overall well-being of employees will be completed to assess potential deviations in stress and depression levels. Analysis of the results showed a significant correlation between increased CRI and stress and depression.
{"title":"The effects of increased color rendering index on stress and depression","authors":"W. P. Newman, J. Rebman","doi":"10.1109/ICEEOT.2016.7754739","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7754739","url":null,"abstract":"Several studies [6,7,8] have found that sunlight has a stress-reducing effect on those who are exposed to it. An innovative new design of artificial lighting known as RaLight is proposed to reflect light with a color rendering index (CRI) nearly identical to natural sunlight. This study will examine the relationship between exposure to RaLight (as a substitute for sunlight) and levels of stress. RaLight is predicted to decrease levels of stress in test subjects. In a commercial call center setting, test subjects will consist of an estimated 50 employees both male and female with ages ranging from 18 to 30 years. The initial control condition will be the common indoor environment which exposes patients to standard fluorescent lighting. Replacing light fixtures with RaLight will then establish both the second phase of the experiment and the independent variable. Throughout each phase, questionnaires, modified from the peer reviewed Wakefield Self-Report Questionnaire, regarding the overall well-being of employees will be completed to assess potential deviations in stress and depression levels. Analysis of the results showed a significant correlation between increased CRI and stress and depression.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130607274","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7755016
V. Garud, S. Lakade, Sanjiwan Bhoite, S. More, S. Ingale, Nilesh Gaikwad, K. Gavhane
Earth-moving machines are exposed to the repeated fluctuating stresses which cause fatigue cracks at the toe and throat of welded joints due to the metallurgical imperfections. So welding joints is the weak region for the components of all earth-moving machines and acts as a determining factor of expected life of earth-moving machines. Also due to this, welded joints must be fully understood to improve the fatigue and service life of the earth-moving machines. Here failure at throat can be minimized by achieving optimum strength but problem of weld toe cracking only be eliminated by reducing stress concentration at weld toe. To do this, R & D work has been initiated by preparing set of five T-joint weld samples having 8mm (sample F to J) throat thickness with one as-welded sample i.e. J (without post weld toe treatment) for benchmarking purpose has been prepared using GMAW welding process. For the toe grinding of samples F to J post weld toe grinding treatment as per IIW guidelines with cylindrical & hemispherical burr tool, cutter (A24PBF) and flap disc grinder respectively has been applied to reduce the stress concentration at weld toe by making smooth transition at weld toe with undercut of 1mm. Using UG NX 7.5, solid models of T-Joint shaped with sample size of 170 × 192 × 8mm has been created from the images of etched weld toe profile. Post weld toe treated with hemispherical burr tool has given maximum optimization in fatigue life of 76% as compared to as-welded samples i.e. J and validated by hardness testing at Heat affected zone (HAZ) of etched samples which shows that graph of alternating stress and fatigue limit shows almost parallel trend and differs by proportionality constant.
{"title":"Burr grinder: Advanced & effective post weld toe treatment to optimize fatigue life of welded structures","authors":"V. Garud, S. Lakade, Sanjiwan Bhoite, S. More, S. Ingale, Nilesh Gaikwad, K. Gavhane","doi":"10.1109/ICEEOT.2016.7755016","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7755016","url":null,"abstract":"Earth-moving machines are exposed to the repeated fluctuating stresses which cause fatigue cracks at the toe and throat of welded joints due to the metallurgical imperfections. So welding joints is the weak region for the components of all earth-moving machines and acts as a determining factor of expected life of earth-moving machines. Also due to this, welded joints must be fully understood to improve the fatigue and service life of the earth-moving machines. Here failure at throat can be minimized by achieving optimum strength but problem of weld toe cracking only be eliminated by reducing stress concentration at weld toe. To do this, R & D work has been initiated by preparing set of five T-joint weld samples having 8mm (sample F to J) throat thickness with one as-welded sample i.e. J (without post weld toe treatment) for benchmarking purpose has been prepared using GMAW welding process. For the toe grinding of samples F to J post weld toe grinding treatment as per IIW guidelines with cylindrical & hemispherical burr tool, cutter (A24PBF) and flap disc grinder respectively has been applied to reduce the stress concentration at weld toe by making smooth transition at weld toe with undercut of 1mm. Using UG NX 7.5, solid models of T-Joint shaped with sample size of 170 × 192 × 8mm has been created from the images of etched weld toe profile. Post weld toe treated with hemispherical burr tool has given maximum optimization in fatigue life of 76% as compared to as-welded samples i.e. J and validated by hardness testing at Heat affected zone (HAZ) of etched samples which shows that graph of alternating stress and fatigue limit shows almost parallel trend and differs by proportionality constant.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116301401","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7754973
Isashri Padhi, H. Palo, S. Mishra, M. Mohanty
To characterize any speech signal, features plays an important role as a parameter to best describe a particular speaker from his/her voice. In emotional speech recognition system prosodic and spectral features provide a significant detecting parameter in differentiating various classes of emotions as these features closely resembles human vocal tract system. The statistical properties of these features vary with different emotional speech utterances and due to change in ascent, speaking style and language of the speaker. In this paper, an attempt is made taking into account these facts to categorize various classes of emotional speech. The result is promising in detecting four classes of emotions as angry, fear, sad and surprise of children database generated by us.
{"title":"Statistical feature based child emotion analysis","authors":"Isashri Padhi, H. Palo, S. Mishra, M. Mohanty","doi":"10.1109/ICEEOT.2016.7754973","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7754973","url":null,"abstract":"To characterize any speech signal, features plays an important role as a parameter to best describe a particular speaker from his/her voice. In emotional speech recognition system prosodic and spectral features provide a significant detecting parameter in differentiating various classes of emotions as these features closely resembles human vocal tract system. The statistical properties of these features vary with different emotional speech utterances and due to change in ascent, speaking style and language of the speaker. In this paper, an attempt is made taking into account these facts to categorize various classes of emotional speech. The result is promising in detecting four classes of emotions as angry, fear, sad and surprise of children database generated by us.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126423856","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7755387
J. Vinodhini, R. Babu, J. A. Glenn
In electric traction application electrical energy used was: 1.direct current and 2.alternating current. In this world already a constant voltage constant frequency single phase and three phase AC readily available. For some applications it is needed to have variable voltage and variable frequency for this conversions need between dc and ac sources, and this conversion can be carried out by power converters. For converting AC-AC cycloconverter are widely used as a converter. The ns of alternating current drives relates with the frequency (f) and number of poles (p) present in the induction motor. It is not feasible by changing the poles of a motor under running processes, so the only one way during running condition the frequency can be varied. In the absence of direct current (DC) link with constant voltage constant frequency alternating current to variable voltage variable frequency alternating current is needed to run the electric traction applications, so the cycloconverter will make this as possible with reliable and economical. This work explains how to control the speed of single phase induction motor and single phase to single phase Cycloconverter using different frequency conversions with R Load was carried out using MATLAB / Simulink.
{"title":"Single phase to single phase step-down cycloconverter for electric traction applications","authors":"J. Vinodhini, R. Babu, J. A. Glenn","doi":"10.1109/ICEEOT.2016.7755387","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7755387","url":null,"abstract":"In electric traction application electrical energy used was: 1.direct current and 2.alternating current. In this world already a constant voltage constant frequency single phase and three phase AC readily available. For some applications it is needed to have variable voltage and variable frequency for this conversions need between dc and ac sources, and this conversion can be carried out by power converters. For converting AC-AC cycloconverter are widely used as a converter. The ns of alternating current drives relates with the frequency (f) and number of poles (p) present in the induction motor. It is not feasible by changing the poles of a motor under running processes, so the only one way during running condition the frequency can be varied. In the absence of direct current (DC) link with constant voltage constant frequency alternating current to variable voltage variable frequency alternating current is needed to run the electric traction applications, so the cycloconverter will make this as possible with reliable and economical. This work explains how to control the speed of single phase induction motor and single phase to single phase Cycloconverter using different frequency conversions with R Load was carried out using MATLAB / Simulink.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128051759","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7755567
D. Ilcev
This paper describes the steering and mount systems of Airborne Satellite Antenna (ASA) as a most important and sensitive part of both Aeronautical Mobile Satellite Communication (AMSA) and Aeronautical Mobile Satellite Broadcasting (AMSB) systems. In general, most of ASA solutions are small and easy to install onboard aircraft such as Low Gain Antenna (LGA). However, in particular, some of ASA systems are quite complex, relatively large and heavy, especially airborne High Gain Antenna (HGA) for Aircraft Earth Stations (AES), such as Inmarsat-H, High Speed Data (HSD), Swift64, SwiftBroadband and Digital Video Broadcasting-Return Channel via Satellite (DVB-RCS) antennas, so they need sophisticated steering and mounting systems. Over the past decade are developed the steering ASA broadband system, which main components are reduced considerably in both physical size and weight. These reductions are presented in this research that brings greater Effective Isotropic Radiated Power (EIRP) from satellite transponders coupled with GaAs-FET technology at the front end the satellite receiver. In this paper are also introduced existing types of mechanical, electrical, combined and other mount systems of ASA steering system. The ASA has to be always pointed towards the satellite in spite of aircraft motions. At this point, the mount airborne satellite system as one of the main requirements in designing the mobile satellite antenna systems from the technical and rational viewpoints is discussed.
{"title":"Airborne satellite antenna steering and mounting systems","authors":"D. Ilcev","doi":"10.1109/ICEEOT.2016.7755567","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7755567","url":null,"abstract":"This paper describes the steering and mount systems of Airborne Satellite Antenna (ASA) as a most important and sensitive part of both Aeronautical Mobile Satellite Communication (AMSA) and Aeronautical Mobile Satellite Broadcasting (AMSB) systems. In general, most of ASA solutions are small and easy to install onboard aircraft such as Low Gain Antenna (LGA). However, in particular, some of ASA systems are quite complex, relatively large and heavy, especially airborne High Gain Antenna (HGA) for Aircraft Earth Stations (AES), such as Inmarsat-H, High Speed Data (HSD), Swift64, SwiftBroadband and Digital Video Broadcasting-Return Channel via Satellite (DVB-RCS) antennas, so they need sophisticated steering and mounting systems. Over the past decade are developed the steering ASA broadband system, which main components are reduced considerably in both physical size and weight. These reductions are presented in this research that brings greater Effective Isotropic Radiated Power (EIRP) from satellite transponders coupled with GaAs-FET technology at the front end the satellite receiver. In this paper are also introduced existing types of mechanical, electrical, combined and other mount systems of ASA steering system. The ASA has to be always pointed towards the satellite in spite of aircraft motions. At this point, the mount airborne satellite system as one of the main requirements in designing the mobile satellite antenna systems from the technical and rational viewpoints is discussed.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134446884","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7754740
Sachin D. Daxini, G. Rohit, J. Prajapati
Meshfree Methods (MMs) have become popular as an alternative numerical simulation technique to handle problems of diverse engineering fields where conventional grid based methods are not suitable. Element Free Galerkin (EFG) method is a popular meshfree approach based on global weak form of governing differential equation and employs Moving Least Square (MLS) approximants to construct shape functions. While deriving solution with EFG, following selectable parameters affect solution accuracy and computational efforts: Order of monomial basis function and weight function selection in MLS approximants, size of influence domain, uniform and non-uniform node distribution, number of Gauss points in integration cells and the method of imposing essential boundary conditions. In the present paper, aforesaid significant parameters are studied individually to check its influence on solution accuracy in EFG and suggest near optimal selection. An axially loaded elastic bar problem is taken as case study for unambiguous presentation of results. Finally, when EFG results are compared with standard FEM solution, it is found that EFG displacements are more accurate than FEM and EFG stress results are continuous in the domain in contrast to discontinuous stress values in FEM at element boundaries.
{"title":"Parametric study in Element Free Galerkin method for an elastic bar","authors":"Sachin D. Daxini, G. Rohit, J. Prajapati","doi":"10.1109/ICEEOT.2016.7754740","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7754740","url":null,"abstract":"Meshfree Methods (MMs) have become popular as an alternative numerical simulation technique to handle problems of diverse engineering fields where conventional grid based methods are not suitable. Element Free Galerkin (EFG) method is a popular meshfree approach based on global weak form of governing differential equation and employs Moving Least Square (MLS) approximants to construct shape functions. While deriving solution with EFG, following selectable parameters affect solution accuracy and computational efforts: Order of monomial basis function and weight function selection in MLS approximants, size of influence domain, uniform and non-uniform node distribution, number of Gauss points in integration cells and the method of imposing essential boundary conditions. In the present paper, aforesaid significant parameters are studied individually to check its influence on solution accuracy in EFG and suggest near optimal selection. An axially loaded elastic bar problem is taken as case study for unambiguous presentation of results. Finally, when EFG results are compared with standard FEM solution, it is found that EFG displacements are more accurate than FEM and EFG stress results are continuous in the domain in contrast to discontinuous stress values in FEM at element boundaries.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130999578","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7754748
A. Banerjee, Samiran Chattopadhyay, A. Mukhopadhyay, G. Gheorghe
Reliability optimization in Wireless Sensor Network (WSN) is obviously an important problem. The basic function of a WSN is to provide an adequate and quality data transmission as economically as possible with a reasonable level of reliability with minimum power consumption. To make the system more reliable, solar energy has been considered as energy harvesting strategy. In this paper, an algorithm aiming for reliability optimization in WSN systems is discussed. This algorithm is based on a modified Ant Colony Optimization (ACO) algorithm. The throughput obtained from Sensor Medium Access Control (SMAC) protocol considered as objective function with respect to different environmental constraints. For the input variables, fuzzy models with trapezoidal membership functions are used. The results obtained are compared with other approaches from literature and found satisfactory.
{"title":"A fuzzy-ACO algorithm to enhance reliability optimization through energy harvesting in WSN","authors":"A. Banerjee, Samiran Chattopadhyay, A. Mukhopadhyay, G. Gheorghe","doi":"10.1109/ICEEOT.2016.7754748","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7754748","url":null,"abstract":"Reliability optimization in Wireless Sensor Network (WSN) is obviously an important problem. The basic function of a WSN is to provide an adequate and quality data transmission as economically as possible with a reasonable level of reliability with minimum power consumption. To make the system more reliable, solar energy has been considered as energy harvesting strategy. In this paper, an algorithm aiming for reliability optimization in WSN systems is discussed. This algorithm is based on a modified Ant Colony Optimization (ACO) algorithm. The throughput obtained from Sensor Medium Access Control (SMAC) protocol considered as objective function with respect to different environmental constraints. For the input variables, fuzzy models with trapezoidal membership functions are used. The results obtained are compared with other approaches from literature and found satisfactory.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133435193","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 : 2016-03-03DOI: 10.1109/ICEEOT.2016.7754996
Subhrajit Mitra, P. Chattopadhyay
Artificial Neural Networks (ANN) provides a simple and efficient method to implement highly non-linear complex systems due to its “Universal Function Approximation” capabilities. However lack of a simple hardware design that is capable of adopting any changes in operating environment of the system limits the applicability of ANN in automotive and industrial environment. The most challenging task for implementation of ANN in embedded plat-form is realization of non-linear sigmoidal activation function. This paper aims to address various hardware implementation issues of ANN in terms of speed, accuracy and resource utilization. Inverse Definite Minimum Time (IDMT) characteristic has been realized and verified using XILINX Spartan-3AN FPGA with very simple ANN model. Sigmoid activation function played a very crucial role in designing and implementation of ANN. Among various techniques piece wise linear approximation (PLAN) has found to be the most optimized and hardware friendly methods for implementing of sigmoid function on reconfigurable FPGA platform.
{"title":"Challenges in implementation of ANN in embedded system","authors":"Subhrajit Mitra, P. Chattopadhyay","doi":"10.1109/ICEEOT.2016.7754996","DOIUrl":"https://doi.org/10.1109/ICEEOT.2016.7754996","url":null,"abstract":"Artificial Neural Networks (ANN) provides a simple and efficient method to implement highly non-linear complex systems due to its “Universal Function Approximation” capabilities. However lack of a simple hardware design that is capable of adopting any changes in operating environment of the system limits the applicability of ANN in automotive and industrial environment. The most challenging task for implementation of ANN in embedded plat-form is realization of non-linear sigmoidal activation function. This paper aims to address various hardware implementation issues of ANN in terms of speed, accuracy and resource utilization. Inverse Definite Minimum Time (IDMT) characteristic has been realized and verified using XILINX Spartan-3AN FPGA with very simple ANN model. Sigmoid activation function played a very crucial role in designing and implementation of ANN. Among various techniques piece wise linear approximation (PLAN) has found to be the most optimized and hardware friendly methods for implementing of sigmoid function on reconfigurable FPGA platform.","PeriodicalId":383674,"journal":{"name":"2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133212410","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：