Pub Date : 2022-06-30DOI: 10.1109/eeae53789.2022.9831239
Yordan Kalmukov, B. Evstatiev
Remote sensing and counting of animals is important for both livestock farming and wildlife population management. Traditional surveying methods for manual onsite counting are hard to accomplish, time-consuming, expensive and could be even dangerous. In contrast, remote detection and counting is safe, cost-effective and could be easily and frequently repeated, providing prompt information about animals’ population size and location. This paper reviews some of the most promising potential methods for automated remote detection and counting of animals, ranging from simple computer vision operations like spatial filtering, edge detection, binarization and image subtraction, to more complex machine learning and AI approaches for object detection and recognition. Many scientists worldwide are working on automation of farming and livestock management, and their experimental results really prove the great potential of computer vision and artificial intelligence for achieving that.
{"title":"Methods for Automated Remote Sensing and Counting of Animals","authors":"Yordan Kalmukov, B. Evstatiev","doi":"10.1109/eeae53789.2022.9831239","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831239","url":null,"abstract":"Remote sensing and counting of animals is important for both livestock farming and wildlife population management. Traditional surveying methods for manual onsite counting are hard to accomplish, time-consuming, expensive and could be even dangerous. In contrast, remote detection and counting is safe, cost-effective and could be easily and frequently repeated, providing prompt information about animals’ population size and location. This paper reviews some of the most promising potential methods for automated remote detection and counting of animals, ranging from simple computer vision operations like spatial filtering, edge detection, binarization and image subtraction, to more complex machine learning and AI approaches for object detection and recognition. Many scientists worldwide are working on automation of farming and livestock management, and their experimental results really prove the great potential of computer vision and artificial intelligence for achieving that.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126066279","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831419
K. Koev
A photovoltaic system installed on the roof of an industrial site has been studied. The total maximal installed power of the system is 117.24 kWp. Poly- and mono-crystalline photovoltaic modules have been used. The energy efficiency of the system has been studied through the changes of the performance ratio (PR) and of the energy efficiency coefficient (efficiency) for a period of 8 years and 9 months (105 months - from January 2009 to and including September 2017). It has been found out that the changes in the values of PR and efficiency over the years are insignificant. Studies on photovoltaic modules in operational conditions show that polycrystalline ones are more efficient than mono-crystalline ones during the summer periods when the minimal values of efficiency and PR are observed. Their differences for the two types of modules remain almost constant over the years and are respectively 4% and 0.1.
{"title":"An Investigation of the Energy Efficiency of a Grid Connected Photovoltaic System","authors":"K. Koev","doi":"10.1109/eeae53789.2022.9831419","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831419","url":null,"abstract":"A photovoltaic system installed on the roof of an industrial site has been studied. The total maximal installed power of the system is 117.24 kWp. Poly- and mono-crystalline photovoltaic modules have been used. The energy efficiency of the system has been studied through the changes of the performance ratio (PR) and of the energy efficiency coefficient (efficiency) for a period of 8 years and 9 months (105 months - from January 2009 to and including September 2017). It has been found out that the changes in the values of PR and efficiency over the years are insignificant. Studies on photovoltaic modules in operational conditions show that polycrystalline ones are more efficient than mono-crystalline ones during the summer periods when the minimal values of efficiency and PR are observed. Their differences for the two types of modules remain almost constant over the years and are respectively 4% and 0.1.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121745044","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831368
P. Veleva, M. Todorova, Stanislava Atanasova, Tsvetelina Georgieva, Dimitar Yorgov, S. Atanassova
Leaf chlorophyll is a key indicator of physiological condition of plants. The aim of the present study was to investigate the relationships between different vegetation indices and chlorophyll content index values (CCI) in strawberry leaves from two varieties Asia and Alba. Twenty- four different vegetative indices were calculated using measured reflectance spectra of leaves in visible and short-wave near-infrared region. It was found that CARI, MCARI, mNDVI, Clred edge, Clgreen, REI1, REI2, and REI3 indices are more sensitive to leave's chlorophyll content. Linear, quadratic, logarithmic and compound predictive regression models, defining the relations between the CCI and the investigated vegetation indices for both varieties of strawberries, were calculated. The Compound model based on calculated vegetative indices for the Alba variety has the best fit for all tested indices. The highest coefficient of determination of 0.743 was found for CARI index. Quadratic model best describes the relationship between CCI and the investigated vegetation indices for the Asia strawberry variety. The best fit was found for REI2 index – the obtained coefficient of determination was 0.842. The results of the study show that it is possible to use different vegetative indices obtained by nondestructive remote sensing methods to estimate the chlorophyll content in strawberry leaves.
{"title":"The relationships between different vegetation indices and chlorophyll content index values (CCI) in strawberry leaves","authors":"P. Veleva, M. Todorova, Stanislava Atanasova, Tsvetelina Georgieva, Dimitar Yorgov, S. Atanassova","doi":"10.1109/eeae53789.2022.9831368","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831368","url":null,"abstract":"Leaf chlorophyll is a key indicator of physiological condition of plants. The aim of the present study was to investigate the relationships between different vegetation indices and chlorophyll content index values (CCI) in strawberry leaves from two varieties Asia and Alba. Twenty- four different vegetative indices were calculated using measured reflectance spectra of leaves in visible and short-wave near-infrared region. It was found that CARI, MCARI, mNDVI, Clred edge, Clgreen, REI1, REI2, and REI3 indices are more sensitive to leave's chlorophyll content. Linear, quadratic, logarithmic and compound predictive regression models, defining the relations between the CCI and the investigated vegetation indices for both varieties of strawberries, were calculated. The Compound model based on calculated vegetative indices for the Alba variety has the best fit for all tested indices. The highest coefficient of determination of 0.743 was found for CARI index. Quadratic model best describes the relationship between CCI and the investigated vegetation indices for the Asia strawberry variety. The best fit was found for REI2 index – the obtained coefficient of determination was 0.842. The results of the study show that it is possible to use different vegetative indices obtained by nondestructive remote sensing methods to estimate the chlorophyll content in strawberry leaves.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124840538","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831271
K. Sirakov, Miroslav Mihaylov
The possibilities were studied for pre-sowing electromagnetic treatment of maize seeds, with or without prior fungicidal disinfection, at different fill levels of the space between the electrodes with seed material.It was established that the pre-sowing electromagnetic treatment of maize seeds should be performed after their disinfection with fungicide. Following that, by applying a voltage of 1,65 kV between the electrodes for a duration of treatment 10 s, an increase in the number and weight of the harvested cobs of up to 6,0%, and 9,9%, respectively, was achieved as compared to the reference specimen.
{"title":"Influence of Pre-Sowing Electromagnetic and Chemical Treatment on Sowing Qualities of Maize Seeds","authors":"K. Sirakov, Miroslav Mihaylov","doi":"10.1109/eeae53789.2022.9831271","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831271","url":null,"abstract":"The possibilities were studied for pre-sowing electromagnetic treatment of maize seeds, with or without prior fungicidal disinfection, at different fill levels of the space between the electrodes with seed material.It was established that the pre-sowing electromagnetic treatment of maize seeds should be performed after their disinfection with fungicide. Following that, by applying a voltage of 1,65 kV between the electrodes for a duration of treatment 10 s, an increase in the number and weight of the harvested cobs of up to 6,0%, and 9,9%, respectively, was achieved as compared to the reference specimen.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125032702","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831246
I. Damyanov, K. Dimitrov, Tsvetan Valkovski
This article is a continuation of our study of pasture research using aerial photography, focusing on seasonal differences in infrared thermal imaging in order to obtain a large database and relationships between different seasons and pasture quality.
{"title":"Comparison of seasonal differences in infrared thermal images captured through a intelligent pasture monitoring system","authors":"I. Damyanov, K. Dimitrov, Tsvetan Valkovski","doi":"10.1109/eeae53789.2022.9831246","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831246","url":null,"abstract":"This article is a continuation of our study of pasture research using aerial photography, focusing on seasonal differences in infrared thermal imaging in order to obtain a large database and relationships between different seasons and pasture quality.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127715668","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831357
L. Sitnik, Z. Ivanov, R. Wróbel, R. Dimitrov, Z. Sroka, V. Mihaylov, M. Andrych-Zalewska, D. Ivanov
The aim of the article is to share the problems of reducing CO2, NOx emissions and FSN from today's vehicles through solutions based on the use of bio components for fuel. An innovative idea is to first prepare a mixture of bio components so that it has the density of the fuel, and then add this mixture to the fuel in greater proportions - here 20% by volume. All this to support the transition to a low-carbon future and meet our global emissions targets under the United Nations Framework Convention on Climate Change, while also using bio-waste. The article is a review with the original results of own research in a case study with new (significantly expanded) analyzes that have an important review element regarding the research method and the analysis of its results, which may take the form of a critique of the current method of comparing results and drawing conclusions from them. The case study shows the applicability of the work in practically more regions of the world and provides information on a wider range of renewable and sustainable energy use. The work is particularly important for systems - carbon dioxide accounting in the Life Cycle Assessment (LCA) as it presents a method for the correct assessment of energy (fuel) demand and associated emissions.
{"title":"Bio Mix Diesel for Significant Lowering of CO2, NOx Emissions and FSN from CI Engine","authors":"L. Sitnik, Z. Ivanov, R. Wróbel, R. Dimitrov, Z. Sroka, V. Mihaylov, M. Andrych-Zalewska, D. Ivanov","doi":"10.1109/eeae53789.2022.9831357","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831357","url":null,"abstract":"The aim of the article is to share the problems of reducing CO2, NOx emissions and FSN from today's vehicles through solutions based on the use of bio components for fuel. An innovative idea is to first prepare a mixture of bio components so that it has the density of the fuel, and then add this mixture to the fuel in greater proportions - here 20% by volume. All this to support the transition to a low-carbon future and meet our global emissions targets under the United Nations Framework Convention on Climate Change, while also using bio-waste. The article is a review with the original results of own research in a case study with new (significantly expanded) analyzes that have an important review element regarding the research method and the analysis of its results, which may take the form of a critique of the current method of comparing results and drawing conclusions from them. The case study shows the applicability of the work in practically more regions of the world and provides information on a wider range of renewable and sustainable energy use. The work is particularly important for systems - carbon dioxide accounting in the Life Cycle Assessment (LCA) as it presents a method for the correct assessment of energy (fuel) demand and associated emissions.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129625411","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831418
B. Evstatiev, N. Evstatieva
In this study is presented a concept for an energy monitoring system, applicable in industrial enterprises. The architecture of the system includes one master device, numerous sensors and repeaters, as well as a gateway and a database. The communication between the master and the sensors is implemented using a wireless sensor network, while the communication between the master and the database could use any appropriate technology. The study also presents the algorithm, describing the behavior of the system, the format of the data packets and the algorithm for measuring the key energy characteristics of the network.
{"title":"Concept of an Electronic System for Energy Monitoring of Industrial Plants","authors":"B. Evstatiev, N. Evstatieva","doi":"10.1109/eeae53789.2022.9831418","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831418","url":null,"abstract":"In this study is presented a concept for an energy monitoring system, applicable in industrial enterprises. The architecture of the system includes one master device, numerous sensors and repeaters, as well as a gateway and a database. The communication between the master and the sensors is implemented using a wireless sensor network, while the communication between the master and the database could use any appropriate technology. The study also presents the algorithm, describing the behavior of the system, the format of the data packets and the algorithm for measuring the key energy characteristics of the network.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120961167","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831224
M. Laković, Milica Jovčevski, M. Mančić, F. Stojkovski
In this paper, analysis of thermal pollution from thermal power plants is carried out. This analysis is done with the use of numerical simulation. A two-dimensional numerical model was proposed and numerical results are obtained by using the Fluent software package. Four scenarios were considered, where scenario 1 represents a flow ratio of the discharge channel and the Sava River of 3% and scenario 4 a flow ratio of 12%. With the appearance of increasing droughts, the flow of rivers also decreases. As the river flow decreases, the ratio of discharge channel and river flow increases. The analysis will show that the higher this ratio, the greater the negative impact on the living world in the river. Namely, there is an increase in the heat load of the river. In the numerical simulations, the initial river temperature was taken as the arithmetic mean temperature in the summer months for the previous five years, before reaching the Nikola Tesla B thermal power plant itself. When scenario 1 is compared with the scenario 4, one can notice that by changing the flow of the Sava River and for the same inlet temperature, the river temperature is higher for the scenario 4 at distance of 2000m after the discharge.
{"title":"Numerical analysis of thermal pollution caused by coal-fired power plant","authors":"M. Laković, Milica Jovčevski, M. Mančić, F. Stojkovski","doi":"10.1109/eeae53789.2022.9831224","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831224","url":null,"abstract":"In this paper, analysis of thermal pollution from thermal power plants is carried out. This analysis is done with the use of numerical simulation. A two-dimensional numerical model was proposed and numerical results are obtained by using the Fluent software package. Four scenarios were considered, where scenario 1 represents a flow ratio of the discharge channel and the Sava River of 3% and scenario 4 a flow ratio of 12%. With the appearance of increasing droughts, the flow of rivers also decreases. As the river flow decreases, the ratio of discharge channel and river flow increases. The analysis will show that the higher this ratio, the greater the negative impact on the living world in the river. Namely, there is an increase in the heat load of the river. In the numerical simulations, the initial river temperature was taken as the arithmetic mean temperature in the summer months for the previous five years, before reaching the Nikola Tesla B thermal power plant itself. When scenario 1 is compared with the scenario 4, one can notice that by changing the flow of the Sava River and for the same inlet temperature, the river temperature is higher for the scenario 4 at distance of 2000m after the discharge.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124434767","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831228
L. Mihaescu, G. Lăzăroiu, R. Grigoriu, L. Stănescu, Mihai Dragne, G. Negreanu, I. Balcu, C. Panait
The purpose of the paper targets the development of a mathematic model that encompasses the phenomena of decarbonization through methanation processes, aided by the use of a nickel / alumina catalyst. Emphasis was placed on the impact pressure and temperature ranges have on the process. A nickel catalyst, type NKM – 4A was considered in a temperature range of 220-260 °C in order to highlight the influence of the pressure of CO2and H2reactants. The model used in numerical simulations is derived from the Langmuir - Hinshelwood mechanism, admitting dissociative adsorption of CO2 and O (atomic oxygen), after which methane is formed. The numerical simulations were validated experimentally, concluding in an optimal ratio of hydrogen pressureto carbon dioxide pressure in therangefrom 3 to 4, with further experimental data extending the range up to 5. The experimental base from the Maritime University of Constanța was also presented, a base equipped with a methane generator and a methaniser. The researches (in incipient phase) performed only the conversion of pure carbon dioxide with the ratio hydrogen to carbon dioxide equal to 4. They will be extended to the flue gases of an internal combustion engine driving an electric generator.
{"title":"An analysis of the efficiency of flue gases energy potential conversion through methanation","authors":"L. Mihaescu, G. Lăzăroiu, R. Grigoriu, L. Stănescu, Mihai Dragne, G. Negreanu, I. Balcu, C. Panait","doi":"10.1109/eeae53789.2022.9831228","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831228","url":null,"abstract":"The purpose of the paper targets the development of a mathematic model that encompasses the phenomena of decarbonization through methanation processes, aided by the use of a nickel / alumina catalyst. Emphasis was placed on the impact pressure and temperature ranges have on the process. A nickel catalyst, type NKM – 4A was considered in a temperature range of 220-260 °C in order to highlight the influence of the pressure of CO2and H2reactants. The model used in numerical simulations is derived from the Langmuir - Hinshelwood mechanism, admitting dissociative adsorption of CO2 and O (atomic oxygen), after which methane is formed. The numerical simulations were validated experimentally, concluding in an optimal ratio of hydrogen pressureto carbon dioxide pressure in therangefrom 3 to 4, with further experimental data extending the range up to 5. The experimental base from the Maritime University of Constanța was also presented, a base equipped with a methane generator and a methaniser. The researches (in incipient phase) performed only the conversion of pure carbon dioxide with the ratio hydrogen to carbon dioxide equal to 4. They will be extended to the flue gases of an internal combustion engine driving an electric generator.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122831038","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 : 2022-06-30DOI: 10.1109/eeae53789.2022.9831255
Martin Dejanov
Non-destructive applications for the detection of food quality, especially internal properties, are highly relevant for process control in the food industry. In this respect, visible and near-infrared spectroscopy (VIS and NIR) were evaluated and compared for their ability to predict β-carotene content in apricots. Two regions called VIS-NIR from 400–1000 nm and called NIR from 900–1700 nm regions were analyzed for prediction ability. In the paper two types of regression models that present the β-carotene content are used: partial least square regression (PLSR) and support vector machine regression (SVMR) developed in both spectrum ranges, with good results for coefficient of determination (R2) and standard errors of cross-validation (RMSECV). The best model performance for calibration and validation is obtained using SNV->SG pre-treatment with PLS and SVM regressions in the VIS-NIR range. The performance measurements are as follows: R2c=0.91 and RMSEC=20.1 for calibration and R2v=0.84 and RMSEV=27.1 for validation. On the other hand Support Vector Machine Regression (SVMR) has the following results: R2c=0.92 and RMSEC=19.2 for calibration and R2v=0.84 and RMSEV=26.7 for validation. When using second derivative Savitzky-Golay (SG’’) both models showed a poor performance. On the basis of the developed models the polynomial linear regression and equations are developed to evaluate the β-carotene content during the apricots drying process. The results show that the both ranges VIS-NIR and NIR can be used for non-destructive and reliable determination of β-carotene content in apricots using different kinds of predictive models. In this study the best model is obtained in the VIS-NIR range. The conclusion is that there is a work to be done for improving the prediction. The variance of the drying process model is still large. Despite the closeness between the reference values and the predicted ones, the error in estimating the concentration is still not satisfactory.
{"title":"Evaluation of β-carotene content in apricots during the drying process using visual and near-infrared spectroscopy","authors":"Martin Dejanov","doi":"10.1109/eeae53789.2022.9831255","DOIUrl":"https://doi.org/10.1109/eeae53789.2022.9831255","url":null,"abstract":"Non-destructive applications for the detection of food quality, especially internal properties, are highly relevant for process control in the food industry. In this respect, visible and near-infrared spectroscopy (VIS and NIR) were evaluated and compared for their ability to predict β-carotene content in apricots. Two regions called VIS-NIR from 400–1000 nm and called NIR from 900–1700 nm regions were analyzed for prediction ability. In the paper two types of regression models that present the β-carotene content are used: partial least square regression (PLSR) and support vector machine regression (SVMR) developed in both spectrum ranges, with good results for coefficient of determination (R2) and standard errors of cross-validation (RMSECV). The best model performance for calibration and validation is obtained using SNV->SG pre-treatment with PLS and SVM regressions in the VIS-NIR range. The performance measurements are as follows: R2c=0.91 and RMSEC=20.1 for calibration and R2v=0.84 and RMSEV=27.1 for validation. On the other hand Support Vector Machine Regression (SVMR) has the following results: R2c=0.92 and RMSEC=19.2 for calibration and R2v=0.84 and RMSEV=26.7 for validation. When using second derivative Savitzky-Golay (SG’’) both models showed a poor performance. On the basis of the developed models the polynomial linear regression and equations are developed to evaluate the β-carotene content during the apricots drying process. The results show that the both ranges VIS-NIR and NIR can be used for non-destructive and reliable determination of β-carotene content in apricots using different kinds of predictive models. In this study the best model is obtained in the VIS-NIR range. The conclusion is that there is a work to be done for improving the prediction. The variance of the drying process model is still large. Despite the closeness between the reference values and the predicted ones, the error in estimating the concentration is still not satisfactory.","PeriodicalId":441906,"journal":{"name":"2022 8th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE)","volume":"449 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123018177","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：