Pub Date : 2019-11-01DOI: 10.1109/SMART46866.2019.9117385
S. M. S. I. Badhon, Md. Habibur Rahaman, Farea Rehnuma Rupon
Does thicker vocal folds produce sounds with longer wavelength? And can they produce higher pitches to human ears? We address these types of questions and try to identify the difference between male and female voices. By using Machine learning algorithm it's possible to identify the gender from voices. And for that we extract voice signal's MFCCs features by calculating Discrete Fourier Transform, Mel-spaced filter-bank and log filter-bank energies. Identify gender from natural voice can be one of the most important part of voice recognition. In normal voice to text conversion it's not important to detect the voices gender. But when we use this voice recognition for real life applications, it will be densely needed to identify the voices gender. Gender identifying from voice is a field of Natural language processing which is a branch of artificial intelligence. We followed a simple working sequence for getting the ultimate result. The sequence is, Input-audio-file, Pre-works, Feature Extraction, Creating CSV file with features, Train the model and finally test with test data. For feature extraction we used Mel-frequency cepstral coefficient (MFCC). And for mapping and selection we used Logistic Regression, Random Forest and Gradient Boosting. After all this work we get 99.13% accuracy on the dataset that containing 1652 data of more than 250 speakers and tested them with 400 male and 400 female voices.
{"title":"A Machine Learning Approach to Automating Bengali Voice Based Gender Classification","authors":"S. M. S. I. Badhon, Md. Habibur Rahaman, Farea Rehnuma Rupon","doi":"10.1109/SMART46866.2019.9117385","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117385","url":null,"abstract":"Does thicker vocal folds produce sounds with longer wavelength? And can they produce higher pitches to human ears? We address these types of questions and try to identify the difference between male and female voices. By using Machine learning algorithm it's possible to identify the gender from voices. And for that we extract voice signal's MFCCs features by calculating Discrete Fourier Transform, Mel-spaced filter-bank and log filter-bank energies. Identify gender from natural voice can be one of the most important part of voice recognition. In normal voice to text conversion it's not important to detect the voices gender. But when we use this voice recognition for real life applications, it will be densely needed to identify the voices gender. Gender identifying from voice is a field of Natural language processing which is a branch of artificial intelligence. We followed a simple working sequence for getting the ultimate result. The sequence is, Input-audio-file, Pre-works, Feature Extraction, Creating CSV file with features, Train the model and finally test with test data. For feature extraction we used Mel-frequency cepstral coefficient (MFCC). And for mapping and selection we used Logistic Regression, Random Forest and Gradient Boosting. After all this work we get 99.13% accuracy on the dataset that containing 1652 data of more than 250 speakers and tested them with 400 male and 400 female voices.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123610819","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117501
Tameem Ahmad, Nesar Ahmad
Natural Language Database Query (NLDQ) Processing is to make the system able to understand queries in natural language like in English, French or any other language sentence, which is to be interpreted by the system and a corresponding action triggered on the underlying database. Asking queries or questions to databases in natural language provides the ease to the user to access and retrieve data, especially for those who are not comfortable with formal query language such as SQL. This paper presents a model that allows users to interact with the database in natural language (in English language) and retrieve information from the relational database. The method is based on the literals of the sentence. This proposed interface allows users to ask queries or questions in natural language (English), which will be transformed into formal query by the system itself, i.e. SQL, which will fire over the underlying Database. The task of NLDQ is to transform the natural language query or question into formal Query Language Statement for information access and retrieval. This task requires the parsing of the input with syntactic understanding by the system. Then the parsed data with syntactic comprehension can be combined with relational database theories for extract the contextual meaning from the query and transforming it into formal database query statement that returns the required information from the associated database. This proposed method does not require all language specifications and grammar rules in the input query.
{"title":"A Simple Guide to Implement Data Retrieval through Natural Language Database Query Interface (NLDQ)","authors":"Tameem Ahmad, Nesar Ahmad","doi":"10.1109/SMART46866.2019.9117501","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117501","url":null,"abstract":"Natural Language Database Query (NLDQ) Processing is to make the system able to understand queries in natural language like in English, French or any other language sentence, which is to be interpreted by the system and a corresponding action triggered on the underlying database. Asking queries or questions to databases in natural language provides the ease to the user to access and retrieve data, especially for those who are not comfortable with formal query language such as SQL. This paper presents a model that allows users to interact with the database in natural language (in English language) and retrieve information from the relational database. The method is based on the literals of the sentence. This proposed interface allows users to ask queries or questions in natural language (English), which will be transformed into formal query by the system itself, i.e. SQL, which will fire over the underlying Database. The task of NLDQ is to transform the natural language query or question into formal Query Language Statement for information access and retrieval. This task requires the parsing of the input with syntactic understanding by the system. Then the parsed data with syntactic comprehension can be combined with relational database theories for extract the contextual meaning from the query and transforming it into formal database query statement that returns the required information from the associated database. This proposed method does not require all language specifications and grammar rules in the input query.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117193390","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117538
R. K. Megalingam, Balla Tanmayi, G. R. Sree, T. Indumathi, G. Mallika
Charity is one of the noblest humanitarian services that a person can render. We are all familiar with people asking for charitable donations. We are also familiar with boxes, placed at strategic locations, in shops and malls, with quotes written on them saying “please help the poor”. But usually, the boxes are unnoticed by many people. This paper reviews the design of an intelligent donation box, capacitated to request for charity. This scheme is anticipated to be even more effective than merely placing a donation box in a conspicuous location or a human directly asking for charity. The voice-empowered box speaks out when it detects an obstacle. When a person approaches or passes by the front of the box within a range of 90 cm, it outputs a verbal request., simulating a human voice., in six languages: English., Hindi., Telugu., Malayalam., Tamil., and Kannada. The existing technique of integrating object detection and voice synthesis is not yet implemented in the form of a donation box for charity., which is discussed in this research work. Empirical results validate the efficacy., speed., and reliability of the donation box that can be used to raise funds for the welfare of the needy.
{"title":"Voice Enabled Donation Box","authors":"R. K. Megalingam, Balla Tanmayi, G. R. Sree, T. Indumathi, G. Mallika","doi":"10.1109/SMART46866.2019.9117538","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117538","url":null,"abstract":"Charity is one of the noblest humanitarian services that a person can render. We are all familiar with people asking for charitable donations. We are also familiar with boxes, placed at strategic locations, in shops and malls, with quotes written on them saying “please help the poor”. But usually, the boxes are unnoticed by many people. This paper reviews the design of an intelligent donation box, capacitated to request for charity. This scheme is anticipated to be even more effective than merely placing a donation box in a conspicuous location or a human directly asking for charity. The voice-empowered box speaks out when it detects an obstacle. When a person approaches or passes by the front of the box within a range of 90 cm, it outputs a verbal request., simulating a human voice., in six languages: English., Hindi., Telugu., Malayalam., Tamil., and Kannada. The existing technique of integrating object detection and voice synthesis is not yet implemented in the form of a donation box for charity., which is discussed in this research work. Empirical results validate the efficacy., speed., and reliability of the donation box that can be used to raise funds for the welfare of the needy.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128589134","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117422
H. S. kanyal, Surender Rahamatkar, Birender Kr. Sharma
A full-fledged Target Tracking System (TTS) construction is the greatest challenge in networking. In place of this, an improvised enhanced strategic system would be definitely more feasible. The minimum expectation out of a secured protocol is to include mechanisms against known attack types and also new security features that can be used for future use. Our focus is on the recognition of MANET routing protocol attacks. There are various target tracking techniques for cooperation of MANET nodes that are selected as the security factors including WatchDog and Pathrater approach. This paper aims in proposing Reputation Based Schemes in which Reputation of each node is calculated and circulated to every node in the network. Contribution of entities to network operation is better defined as Reputation. Some of the schemes that include CORE, CONFIDANT and OCEAN are analyzed and compared based on several simulation parameters
{"title":"Performance and Analysis of Target Tracking System (TTS) Based on Local Reputation Scheme","authors":"H. S. kanyal, Surender Rahamatkar, Birender Kr. Sharma","doi":"10.1109/SMART46866.2019.9117422","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117422","url":null,"abstract":"A full-fledged Target Tracking System (TTS) construction is the greatest challenge in networking. In place of this, an improvised enhanced strategic system would be definitely more feasible. The minimum expectation out of a secured protocol is to include mechanisms against known attack types and also new security features that can be used for future use. Our focus is on the recognition of MANET routing protocol attacks. There are various target tracking techniques for cooperation of MANET nodes that are selected as the security factors including WatchDog and Pathrater approach. This paper aims in proposing Reputation Based Schemes in which Reputation of each node is calculated and circulated to every node in the network. Contribution of entities to network operation is better defined as Reputation. Some of the schemes that include CORE, CONFIDANT and OCEAN are analyzed and compared based on several simulation parameters","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133481138","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117395
Md. Ariful Islam Arif, Saiful Islam Sany, Faiza Islam Nahin, AKM SHAHARIAR AZAD RABBY
The key to success in today's business is controlling the retails supply chain. Predicting customer demand is very essential for supply chain management. The perfect prediction has an effective impact on earning a profit., storage., lost profit., sales amount and consumer attraction. This article will produce a new method-using machine learning that will help for accurate prediction. This method collects the previous data of a store and analyze those data. Gathering the important information process those data and get prepared for using in method. Applying related algorithms towards the process data. We know K-Nearest Neighbor, Support Vector Machine, Gaussian Nave Bayes, Random Forest, Decision Tree Classifier and regressions have recently used an algorithm for prediction. We collect real-life data from the market. This paper made with the combination of shop position, month and occasion on that month and other related data. Our country's geographical area has an impact on prediction, which we discuss in our research. Our model produces a tentative demand for a particular product. This estimation helps retails and their businesses. After making a data set and apply appropriate algorithms, we will find different results and accuracy of different used algorithms. Compare them with others, we find out Gaussian Nave Bayes has the best accuracy. This helps to estimate the accurate product demand for a shop.
{"title":"Comparison Study: Product Demand Forecasting with Machine Learning for Shop","authors":"Md. Ariful Islam Arif, Saiful Islam Sany, Faiza Islam Nahin, AKM SHAHARIAR AZAD RABBY","doi":"10.1109/SMART46866.2019.9117395","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117395","url":null,"abstract":"The key to success in today's business is controlling the retails supply chain. Predicting customer demand is very essential for supply chain management. The perfect prediction has an effective impact on earning a profit., storage., lost profit., sales amount and consumer attraction. This article will produce a new method-using machine learning that will help for accurate prediction. This method collects the previous data of a store and analyze those data. Gathering the important information process those data and get prepared for using in method. Applying related algorithms towards the process data. We know K-Nearest Neighbor, Support Vector Machine, Gaussian Nave Bayes, Random Forest, Decision Tree Classifier and regressions have recently used an algorithm for prediction. We collect real-life data from the market. This paper made with the combination of shop position, month and occasion on that month and other related data. Our country's geographical area has an impact on prediction, which we discuss in our research. Our model produces a tentative demand for a particular product. This estimation helps retails and their businesses. After making a data set and apply appropriate algorithms, we will find different results and accuracy of different used algorithms. Compare them with others, we find out Gaussian Nave Bayes has the best accuracy. This helps to estimate the accurate product demand for a shop.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134422826","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117218
R. Narayanan, K. Radhika, C. L. Priya, S. Laxmipriya, B. Krishnakumari
Characteristic nature of groundwater along the Pondicherry beachfront area is under worry because of overexploitation. The examination models the excess concentration of EC levels to assess the impacts on the coastal region. Field data included in the model are electrical conductivity, water table, depth, pump test, elevation/ topography of the area, annual precipitation, aquifer thickness, their porosity, permeability, specific storage and specific yield, the lithological cross-section of exploratory/ observatory bore wells, etc. The visual MODFLOW modeller (MT3DMS) is employed to predict the concentration of EC μS/cm for the actual pumping rate and at an annual recharge of 40% together with the DL (longitudinal dispersion) value of 10 m to characterize changing salt-cloud. The model encompasses the highest coefficient of correlation of more top than 94% for the initial twenty years, and so reduced to 85% for the subsequent twenty years. The model results with saltwater intrusion (~14 km) along the SW Pondicherry coast.
{"title":"Simulation and Modeling of Seawater Intrusion Around Pondicherry Coastal Aquifer-India","authors":"R. Narayanan, K. Radhika, C. L. Priya, S. Laxmipriya, B. Krishnakumari","doi":"10.1109/SMART46866.2019.9117218","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117218","url":null,"abstract":"Characteristic nature of groundwater along the Pondicherry beachfront area is under worry because of overexploitation. The examination models the excess concentration of EC levels to assess the impacts on the coastal region. Field data included in the model are electrical conductivity, water table, depth, pump test, elevation/ topography of the area, annual precipitation, aquifer thickness, their porosity, permeability, specific storage and specific yield, the lithological cross-section of exploratory/ observatory bore wells, etc. The visual MODFLOW modeller (MT3DMS) is employed to predict the concentration of EC μS/cm for the actual pumping rate and at an annual recharge of 40% together with the DL (longitudinal dispersion) value of 10 m to characterize changing salt-cloud. The model encompasses the highest coefficient of correlation of more top than 94% for the initial twenty years, and so reduced to 85% for the subsequent twenty years. The model results with saltwater intrusion (~14 km) along the SW Pondicherry coast.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134518392","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117555
Nilendu Das, Vaibhav Kumar, Ankit Tewari, A. K. Agnihotri, Shivam, S. Gaur, A. Ohri
Rivers are the lifeline of human civilization from ancient times and almost all the human settlements had evolved around it. In this present era, human population has grown at a rapid pace and the anthropogenic activities have grown along with it. Pollution levels of rivers are increasing day by day due to increase in anthropogenic activities, as huge amount of waste gets disposed into it. Several kinds of waste including domestic and industrial waste have been a major source of pollution for the rivers. These pollutants have severely affected the aquatic ecosystem. To keep a check with the increasing pollution levels in the rivers, periodic monitoring of river water quality is essential. In this paper, we present a low cost sensor system model which comprises Arduino, designed and developed for the periodic monitoring of river Ganga. Water quality parameters like turbidity, Dissolved Oxygen (DO), pH and temperature are measured on periodic basis. Recorded sensor data can be transferred to the computer system and still processed further.
{"title":"Periodic Monitoring of Rivers Using Portable Sensor System","authors":"Nilendu Das, Vaibhav Kumar, Ankit Tewari, A. K. Agnihotri, Shivam, S. Gaur, A. Ohri","doi":"10.1109/SMART46866.2019.9117555","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117555","url":null,"abstract":"Rivers are the lifeline of human civilization from ancient times and almost all the human settlements had evolved around it. In this present era, human population has grown at a rapid pace and the anthropogenic activities have grown along with it. Pollution levels of rivers are increasing day by day due to increase in anthropogenic activities, as huge amount of waste gets disposed into it. Several kinds of waste including domestic and industrial waste have been a major source of pollution for the rivers. These pollutants have severely affected the aquatic ecosystem. To keep a check with the increasing pollution levels in the rivers, periodic monitoring of river water quality is essential. In this paper, we present a low cost sensor system model which comprises Arduino, designed and developed for the periodic monitoring of river Ganga. Water quality parameters like turbidity, Dissolved Oxygen (DO), pH and temperature are measured on periodic basis. Recorded sensor data can be transferred to the computer system and still processed further.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129892636","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117377
Md. Sanzidul Islam
The Autonomous machineries are changing our thinking level day by day. Autonomous driving system is a field of likelihood of computer vision research. The flourished countries has already come to the fore and using semi autonomous driving vehicle. They constructed the driving model as their eco-friendly and with their road traffic data. But in Indian sub-continent countries like Bangladesh, there has a little research work and implementation on it. In our research we have made a full size vehicle where we can set up our sensors, cameras and other hardwares to collect the visual training data to train any kind of vision based autonomous vehicle algorithms. We also proposed a CNN model to classify the real-time objects with our dataset. Finally, tested the trained model using the vehicle in real environment and got expected output. Here we used a rickshaw (Bangladeshi traditional three wheeler) as our base vehicle and use some custom made hardware to full-fill our purpose.
{"title":"The First Full-size RC Vehicle: Collecting Bangladeshi Road-traffic Data and Doing Research on Autonomous Three Wheeler","authors":"Md. Sanzidul Islam","doi":"10.1109/SMART46866.2019.9117377","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117377","url":null,"abstract":"The Autonomous machineries are changing our thinking level day by day. Autonomous driving system is a field of likelihood of computer vision research. The flourished countries has already come to the fore and using semi autonomous driving vehicle. They constructed the driving model as their eco-friendly and with their road traffic data. But in Indian sub-continent countries like Bangladesh, there has a little research work and implementation on it. In our research we have made a full size vehicle where we can set up our sensors, cameras and other hardwares to collect the visual training data to train any kind of vision based autonomous vehicle algorithms. We also proposed a CNN model to classify the real-time objects with our dataset. Finally, tested the trained model using the vehicle in real environment and got expected output. Here we used a rickshaw (Bangladeshi traditional three wheeler) as our base vehicle and use some custom made hardware to full-fill our purpose.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122448081","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117283
Amit Sharma, Swaty Punia, Devesh Sharma
Thermodynamic and thermo physical properties of refrigerants are essential for the equipment designs used in refrigeration and air-conditioning systems. For accurate and fast representation of thermodynamic and thermo physical properties of refrigerants equation of state (EOS) is required. Because these properties are essential for the equipment designs. This work represents the cubical equation of state (EOS) model for HC-290. A promising refrigerant with zero ozone depletion potential and very low global warming potential conduct to be potential green refrigerant for the replacement of R-22. Vapour specific volume property is calculated in this work. Several two and three parameter based equation of states root mean square deviation has been presented. Berthelot, Harmens-Knapp, Redlich-Kwong and Schmidt-Wenzel state promising results for HC-290.
{"title":"Cubic Equation of State Model for HC-290","authors":"Amit Sharma, Swaty Punia, Devesh Sharma","doi":"10.1109/SMART46866.2019.9117283","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117283","url":null,"abstract":"Thermodynamic and thermo physical properties of refrigerants are essential for the equipment designs used in refrigeration and air-conditioning systems. For accurate and fast representation of thermodynamic and thermo physical properties of refrigerants equation of state (EOS) is required. Because these properties are essential for the equipment designs. This work represents the cubical equation of state (EOS) model for HC-290. A promising refrigerant with zero ozone depletion potential and very low global warming potential conduct to be potential green refrigerant for the replacement of R-22. Vapour specific volume property is calculated in this work. Several two and three parameter based equation of states root mean square deviation has been presented. Berthelot, Harmens-Knapp, Redlich-Kwong and Schmidt-Wenzel state promising results for HC-290.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121127300","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 : 2019-11-01DOI: 10.1109/SMART46866.2019.9117549
M. Jewel, Md. Ismail Hossain, Tamanna Haider Tonni
In this paper, we have demonstrated how to apply CNN (Convolutional Neural Network) structured model and transfer learning to identify the ethnicity of Bengali people and it's a systematic process of gender classification too. We also applied several models of transfer learning like VGG16, Mobilenet, Resnet50, etc. to find out which model is more convenient to get our desired accuracy. But problems arise because there are many Indian people who look like and get dressed up like Bengali since in India many Bengali dwell in when many of them speak Bangla as well! (people of Kolkata along with some other provinces). So, the Bengali people are not only found in Bangladesh but also elsewhere in the world. That's why our model is based on facial images along with the tradition of their costumes. We tried to build a sophisticated model using CNN and transfer learning for this purpose and we got some tremendous performances applying transfer learning.
{"title":"Bengali Ethnicity Recognition and Gender Classification using CNN & Transfer Learning","authors":"M. Jewel, Md. Ismail Hossain, Tamanna Haider Tonni","doi":"10.1109/SMART46866.2019.9117549","DOIUrl":"https://doi.org/10.1109/SMART46866.2019.9117549","url":null,"abstract":"In this paper, we have demonstrated how to apply CNN (Convolutional Neural Network) structured model and transfer learning to identify the ethnicity of Bengali people and it's a systematic process of gender classification too. We also applied several models of transfer learning like VGG16, Mobilenet, Resnet50, etc. to find out which model is more convenient to get our desired accuracy. But problems arise because there are many Indian people who look like and get dressed up like Bengali since in India many Bengali dwell in when many of them speak Bangla as well! (people of Kolkata along with some other provinces). So, the Bengali people are not only found in Bangladesh but also elsewhere in the world. That's why our model is based on facial images along with the tradition of their costumes. We tried to build a sophisticated model using CNN and transfer learning for this purpose and we got some tremendous performances applying transfer learning.","PeriodicalId":328124,"journal":{"name":"2019 8th International Conference System Modeling and Advancement in Research Trends (SMART)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126927276","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：