Screw turbine-type micro-hydro power plants are still controlled manually by humans when there is a change in the electrical load on the generator output. If there is a change in the electrical load, the generator output voltage will change, thus affecting the rotation of the turbine being used. In this case, humans are needed to manually regulate the flow of water entering the turbine to maintain the stability of the generator output voltage by controlling the sluice gate. The water discharge entering the screw turbine will rotate the generator through a belt/gearbox pulley transmission, thus producing an electrical voltage at the generator output. To maintain the stability of the generator output voltage, it is necessary to control the water discharge entering the screw turbine. The expected goal of this research is to design a control system for a screw turbine type microhydro power plant to stabilize the generator output voltage and monitor the output of a screw turbine type generator using a SCADA (Supervisory Control, and Data Aquisition) system. The method used is the research and development method, namely the system design stage based on secondary data that has been collected, where the system design includes hardware design and software design, followed by making hardware such as control panels and devices. Software, which includes display design and leader diagrams and testing, is carried out by testing the system on software, hardware, and overall system testing. From the results of the discussion and analysis, the screw turbine type microhydro power plant control design system was created, a load control system consisting of 6 groups and sluice gate opening control that uses an ultrasonic sensor to determine the water level. With the results of controlling the sluice gate at a door opening of 30 mm, the generator voltage is 18.42 Volts DC, DC current is 0.0 Ampere at a load of 0 watts, when the load is 30 watts the generator voltage decreases by 18.40 volts, current is 1.37 Ampere. Through the on-line monitoring system, electrical parameters are obtained which are displayed on the SCADA system by looking in real-time at the history of DC voltage and DC current, DC power, and DC energy generated by the screw turbine-type DC generator. The voltage read is 18. 57 volts, current 1.37 Amperes, DC electrical power is 25.4 watts with a DC light load of 30 watts.
{"title":"SCADA implementation in microhydro power plant control and monitoring systems of screw turbine type","authors":"","doi":"10.59018/032449","DOIUrl":"https://doi.org/10.59018/032449","url":null,"abstract":"Screw turbine-type micro-hydro power plants are still controlled manually by humans when there is a change in\u0000the electrical load on the generator output. If there is a change in the electrical load, the generator output voltage will\u0000change, thus affecting the rotation of the turbine being used. In this case, humans are needed to manually regulate the flow\u0000of water entering the turbine to maintain the stability of the generator output voltage by controlling the sluice gate. The\u0000water discharge entering the screw turbine will rotate the generator through a belt/gearbox pulley transmission, thus\u0000producing an electrical voltage at the generator output. To maintain the stability of the generator output voltage, it is\u0000necessary to control the water discharge entering the screw turbine. The expected goal of this research is to design a control\u0000system for a screw turbine type microhydro power plant to stabilize the generator output voltage and monitor the output of\u0000a screw turbine type generator using a SCADA (Supervisory Control, and Data Aquisition) system. The method used is the\u0000research and development method, namely the system design stage based on secondary data that has been collected, where\u0000the system design includes hardware design and software design, followed by making hardware such as control panels and\u0000devices. Software, which includes display design and leader diagrams and testing, is carried out by testing the system on\u0000software, hardware, and overall system testing. From the results of the discussion and analysis, the screw turbine type\u0000microhydro power plant control design system was created, a load control system consisting of 6 groups and sluice gate\u0000opening control that uses an ultrasonic sensor to determine the water level. With the results of controlling the sluice gate at\u0000a door opening of 30 mm, the generator voltage is 18.42 Volts DC, DC current is 0.0 Ampere at a load of 0 watts, when the\u0000load is 30 watts the generator voltage decreases by 18.40 volts, current is 1.37 Ampere. Through the on-line monitoring\u0000system, electrical parameters are obtained which are displayed on the SCADA system by looking in real-time at the history\u0000of DC voltage and DC current, DC power, and DC energy generated by the screw turbine-type DC generator. The voltage\u0000read is 18. 57 volts, current 1.37 Amperes, DC electrical power is 25.4 watts with a DC light load of 30 watts.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141127935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) is an emerging technology that covers various domains and has become an essential part of the upcoming technological revolution. IoT applications include healthcare, smart-cities, smart-cars, industries, quality of life, and several other fields. IoT typically consists of lightweight sensor devices that facilitate procedures such as automation, real-time trackable data collection, and data-driven decisions. However, securing IoT networks is an accessible research area for several reasons. The main security challenges are limited resources that are incapable of dealing with complex and advanced security tools; and lack of required data for training the security systems like Intrusion detection systems as a result of their heterogeneous nature. This research proposed a Few-shot learning IoT intrusion detection system model based on a Siamese network to overcome the above limitation. The model aims to classify and distinguish normal and attacked traffic. The experiment utilized an IoT dataset in different scenarios to analyze and validate the behavior with three categories with different numbers of data in each. The performance result achieves more than 99% accuracy and shows an efficient detection ability using only less than 1% of the dataset.
{"title":"Towards intrusion detection in IoT using Few-shot learning","authors":"","doi":"10.59018/032454","DOIUrl":"https://doi.org/10.59018/032454","url":null,"abstract":"The Internet of Things (IoT) is an emerging technology that covers various domains and has become an essential\u0000part of the upcoming technological revolution. IoT applications include healthcare, smart-cities, smart-cars, industries,\u0000quality of life, and several other fields. IoT typically consists of lightweight sensor devices that facilitate procedures such\u0000as automation, real-time trackable data collection, and data-driven decisions. However, securing IoT networks is an\u0000accessible research area for several reasons. The main security challenges are limited resources that are incapable of\u0000dealing with complex and advanced security tools; and lack of required data for training the security systems like Intrusion\u0000detection systems as a result of their heterogeneous nature. This research proposed a Few-shot learning IoT intrusion\u0000detection system model based on a Siamese network to overcome the above limitation. The model aims to classify and\u0000distinguish normal and attacked traffic. The experiment utilized an IoT dataset in different scenarios to analyze and\u0000validate the behavior with three categories with different numbers of data in each. The performance result achieves more\u0000than 99% accuracy and shows an efficient detection ability using only less than 1% of the dataset.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141127740","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}
A native design of the Indonesian high-speed train has been developed as an improvement of the previous medium-speed train model. As the design speed is proposed to be increased from 160 km/h to 250 km/h, the nose shape and nose length of the train head were modified into a sharper and longer nose. In this study, numerical simulation of computational fluid dynamics was used to investigate the aerodynamic phenomena and flow behavior around the modified train head and carbodies. The CFD simulation was used as the verification of the shape design and a tool for rapid design changes and optimization. The model configuration is three cars on a real scale by ignoring other parts like the train window and door, pantograph, and train connecting. A k-ε turbulence model was used in the simulation. From this investigation, it is found that the coefficient of drag on the model is calculated to be 0.34. Meanwhile, an experimental wind tunnel test validates the result with a coefficient drag is 0.38 or 10% divergence from the numerical method.
{"title":"Numerical study of aerodynamics drag and flow characteristics of the high-speed train head design","authors":"","doi":"10.59018/032448","DOIUrl":"https://doi.org/10.59018/032448","url":null,"abstract":"A native design of the Indonesian high-speed train has been developed as an improvement of the previous\u0000medium-speed train model. As the design speed is proposed to be increased from 160 km/h to 250 km/h, the nose shape\u0000and nose length of the train head were modified into a sharper and longer nose. In this study, numerical simulation of\u0000computational fluid dynamics was used to investigate the aerodynamic phenomena and flow behavior around the modified\u0000train head and carbodies. The CFD simulation was used as the verification of the shape design and a tool for rapid design\u0000changes and optimization. The model configuration is three cars on a real scale by ignoring other parts like the train\u0000window and door, pantograph, and train connecting. A k-ε turbulence model was used in the simulation. From this\u0000investigation, it is found that the coefficient of drag on the model is calculated to be 0.34. Meanwhile, an experimental\u0000wind tunnel test validates the result with a coefficient drag is 0.38 or 10% divergence from the numerical method.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141127927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rehabilitation of the subsidence phenomenon in Jatikurung sub-village, Jatirunggo village, Pringapus Subdistrict, Semarang Regency, Central Java, has been carried out for a long time however, it has never been successful. Every time an embankment is made, it is only a matter of time before another subsidence occurs. This research aims to investigate the subsurface structure of the subsidence sites. It is proposed to be used as a reference for structural planning in the treatment of road subsidence. Subsurface information is very useful in addressing the subsidence problem more effectively and precisely. The method used was by recording microtremor data and analyzing shear wave velocity and Poisson ratio as parameters to determine the type of subsurface layer. The obtained results are in the form of clay layers to bedrock layers at a depth of 35m. The movement occurred because of the soft or loose soil below and at the edge of the road above the impermeable clay layer. In addition, to the north side of the collapse point is a fairly deep cliff, which is a burden on the bedrock. When it was raining, the soil filled with water and there was even a flow of water in the soil deposits (piping) resulting in the ground movement toward the lower part.
{"title":"Analysis of subsidence zone of the village access road in Jatirunggo, Semarang Regency using microtremor data","authors":"","doi":"10.59018/032450","DOIUrl":"https://doi.org/10.59018/032450","url":null,"abstract":"The rehabilitation of the subsidence phenomenon in Jatikurung sub-village, Jatirunggo village, Pringapus\u0000Subdistrict, Semarang Regency, Central Java, has been carried out for a long time however, it has never been successful.\u0000Every time an embankment is made, it is only a matter of time before another subsidence occurs. This research aims to\u0000investigate the subsurface structure of the subsidence sites. It is proposed to be used as a reference for structural planning\u0000in the treatment of road subsidence. Subsurface information is very useful in addressing the subsidence problem more\u0000effectively and precisely. The method used was by recording microtremor data and analyzing shear wave velocity and\u0000Poisson ratio as parameters to determine the type of subsurface layer. The obtained results are in the form of clay layers to\u0000bedrock layers at a depth of 35m. The movement occurred because of the soft or loose soil below and at the edge of the\u0000road above the impermeable clay layer. In addition, to the north side of the collapse point is a fairly deep cliff, which is a\u0000burden on the bedrock. When it was raining, the soil filled with water and there was even a flow of water in the soil\u0000deposits (piping) resulting in the ground movement toward the lower part.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141128046","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}
Pedada leaves (Sonneratia caseolaris) are plants from tropical areas with relatively high antioxidant content. This research aims to make antiseptic soap with the addition of pedada leaves and see the quality of the antiseptic soap by SNI 03-3532-1994. This research includes the pre-treatment process, namely taking pedada leaf extract by maceration using ethanol and acetone solvents using a variety of evaporation tools in the form of a water bath and soxhlet, then making soap with coconut oil with variations used in the form of evaporation methods and the amount of extract used. This research analyzed water content, free alkali, and free fatty acids. The observations showed that using a water bath would produce a more significant amount of extract. The results of the soap-free alkali analysis produced ranged from 0.061% to 0.088%, which shows that the free alkali content is still below the limit determined by SNI. The lowest water content analysis results obtained were 11.30%.
{"title":"The effectiveness of adding antioxidant compounds from pedada leaves extract (Sonneratia Caseolaris) in antiseptic soap production","authors":"","doi":"10.59018/032453","DOIUrl":"https://doi.org/10.59018/032453","url":null,"abstract":"Pedada leaves (Sonneratia caseolaris) are plants from tropical areas with relatively high antioxidant content. This\u0000research aims to make antiseptic soap with the addition of pedada leaves and see the quality of the antiseptic soap by SNI\u000003-3532-1994. This research includes the pre-treatment process, namely taking pedada leaf extract by maceration using\u0000ethanol and acetone solvents using a variety of evaporation tools in the form of a water bath and soxhlet, then making soap\u0000with coconut oil with variations used in the form of evaporation methods and the amount of extract used. This research\u0000analyzed water content, free alkali, and free fatty acids. The observations showed that using a water bath would produce a\u0000more significant amount of extract. The results of the soap-free alkali analysis produced ranged from 0.061% to 0.088%,\u0000which shows that the free alkali content is still below the limit determined by SNI. The lowest water content analysis\u0000results obtained were 11.30%.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141127920","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}
This research aims to present a land use inspection technique that affects land surface temperature from satellite data by using Maha Sarakham province, Thailand as a case study. Procedures: 1) Analyze land use from Sentinel-2 Satellite data that can be divided into 4 categories such as water, agriculture, forest, and urban, 2) Analyze land surface temperature from Sentinel-3 Satellite data. The study results found that urban area has the highest average surface temperature followed by forest area, water area, and agricultural area respectively. The analyzed data from the satellite found the highest average surface temperature is 32.20°C. The result shows that this inspection technique can analyze land surface temperature in other areas of the countryThis research aims to present a land use inspection technique that affects land surface temperature from satellite data by using Maha Sarakham province, Thailand as a case study. Procedures: 1) Analyze land use from Sentinel-2 Satellite data that can be divided into 4 categories such as water, agriculture, forest, and urban, 2) Analyze land surface temperature from Sentinel-3 Satellite data. The study results found that urban area has the highest average surface temperature followed by forest area, water area, and agricultural area respectively. The analyzed data from the satellite found the highest average surface temperature is 32.20°C. The result shows that this inspection technique can analyze land surface temperature in other areas of the country.
{"title":"Land use inspection technique affects land surface temperature from satellite data","authors":"","doi":"10.59018/032451","DOIUrl":"https://doi.org/10.59018/032451","url":null,"abstract":"This research aims to present a land use inspection technique that affects land surface temperature from satellite\u0000data by using Maha Sarakham province, Thailand as a case study. Procedures: 1) Analyze land use from Sentinel-2\u0000Satellite data that can be divided into 4 categories such as water, agriculture, forest, and urban, 2) Analyze land surface\u0000temperature from Sentinel-3 Satellite data. The study results found that urban area has the highest average surface\u0000temperature followed by forest area, water area, and agricultural area respectively. The analyzed data from the satellite\u0000found the highest average surface temperature is 32.20°C. The result shows that this inspection technique can analyze land\u0000surface temperature in other areas of the countryThis research aims to present a land use inspection technique that affects land surface temperature from satellite\u0000data by using Maha Sarakham province, Thailand as a case study. Procedures: 1) Analyze land use from Sentinel-2\u0000Satellite data that can be divided into 4 categories such as water, agriculture, forest, and urban, 2) Analyze land surface\u0000temperature from Sentinel-3 Satellite data. The study results found that urban area has the highest average surface\u0000temperature followed by forest area, water area, and agricultural area respectively. The analyzed data from the satellite\u0000found the highest average surface temperature is 32.20°C. The result shows that this inspection technique can analyze land\u0000surface temperature in other areas of the country.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141127769","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}
Technology, specifically computers play an important role in modern society. People who are new to computers can determine what type of RAM they have, which can be used to avoid confusion on what type of RAM their computer needs with the help of an Android device. For this study, a powerful computer with a Graphics Processing Unit (GPU) needed to be used to shorten the amount of time that the deep learning process takes. The study gathered images of 4 types of Random Access Memory for a RAM classification system. There were 1000 images in total for DDR1, DDR2, DDR3, and DDR4 RAM. The study utilized transfer learning to RAM type classification with pre-trained models such as VGG16, VGG19, Inception V3, and Xception. The data that was gathered showed that Xception is the best classifier with an initial average accuracy of 85.034% and a 100% Val_Accuracy even though the model had the longest loading time with 12 seconds.
{"title":"Classification of different types of DDR RAM using transfer learning in convolutional learning networks","authors":"","doi":"10.59018/022434","DOIUrl":"https://doi.org/10.59018/022434","url":null,"abstract":"Technology, specifically computers play an important role in modern society. People who are new to computers can determine what type of RAM they have, which can be used to avoid confusion on what type of RAM their computer needs with the help of an Android device. For this study, a powerful computer with a Graphics Processing Unit (GPU) needed to be used to shorten the amount of time that the deep learning process takes. The study gathered images of 4 types of Random Access Memory for a RAM classification system. There were 1000 images in total for DDR1, DDR2, DDR3, and DDR4 RAM. The study utilized transfer learning to RAM type classification with pre-trained models such as VGG16, VGG19, Inception V3, and Xception. The data that was gathered showed that Xception is the best classifier with an initial average accuracy of 85.034% and a 100% Val_Accuracy even though the model had the longest loading time with 12 seconds.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140702991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The electrical properties of thin films made of polyethylene oxide (PEO) dispersed with dopants fixed amount of iodine (0.1 wt. %) were studied using the AC impedance technique. The films were prepared by electrically casting method. In this present work, the variation of AC electrical conductivity with temperatures ranging from 30 oC to 55 oC at a frequency of 200 kHz for (PEO) film doped with 0.1wt. % iodine and undoped (PEO) film were studied. Physical quantities and parameters such as AC conductivity, impedance, dielectric constant, and dielectric loss, were determined. The observed values of the impedance (Z), dielectric constant ('), dielectric loss ("), and AC-conductivity (σAC) showed temperature dependence. It was found that the dielectric constant and the dielectric loss of the prepared thin films increased with doped (0.1wt. %) iodine complexes and also increased with the increase of temperature according to the polarization processes.
{"title":"Variation of electrical properties with temperature for polyethylene oxide doped with 0.1 wt. % iodine","authors":"","doi":"10.59018/022432","DOIUrl":"https://doi.org/10.59018/022432","url":null,"abstract":"The electrical properties of thin films made of polyethylene oxide (PEO) dispersed with dopants fixed amount of iodine (0.1 wt. %) were studied using the AC impedance technique. The films were prepared by electrically casting method. In this present work, the variation of AC electrical conductivity with temperatures ranging from 30 oC to 55 oC at a frequency of 200 kHz for (PEO) film doped with 0.1wt. % iodine and undoped (PEO) film were studied. Physical quantities and parameters such as AC conductivity, impedance, dielectric constant, and dielectric loss, were determined. The observed values of the impedance (Z), dielectric constant ('), dielectric loss (\"), and AC-conductivity (σAC) showed temperature dependence. It was found that the dielectric constant and the dielectric loss of the prepared thin films increased with doped (0.1wt. %) iodine complexes and also increased with the increase of temperature according to the polarization processes.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140701376","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}
Gold has emerged as an extra famous and very beneficial commodity in phrases of investment. Gold has been considered, as a country wide reserved commodity for many years, which leads to very integral for the economy of any country. Most people and traders believe that gold is a protected investment from uncertainty and political chaos. The rate of motion of gold helps the buyers from the centre of attention in their investments; they make use of the year by year information from Indian Gold Council. The analysis of the data was taken from 1964 to 2020. This paper's motto is to analyze and summarize different algorithms for predicting the rate of gold. The procedures utilized to fit the data were from the Time Series analysis Auto Regressive Integrated Moving Average (ARIMA) and Neural Network models; Multi-Layer Perception (MLP) and Extreme Learning Machine (ELM). The test data were utilized for the analysis, and then the outcome was exhibited with the help of error parameters. ELM is best as compared to ARIMA and MLP. The error measures are RMSE (1634.975) and MAPE (3.002). The error measurements have been represented in the tables for ARIMA and MLP. The best prediction of Gold price was given by the ELM, which is be efficient and accurate model.
{"title":"Prediction of Gold price with comparison of forecasting methods","authors":"","doi":"10.59018/022436","DOIUrl":"https://doi.org/10.59018/022436","url":null,"abstract":"Gold has emerged as an extra famous and very beneficial commodity in phrases of investment. Gold has been considered, as a country wide reserved commodity for many years, which leads to very integral for the economy of any country. Most people and traders believe that gold is a protected investment from uncertainty and political chaos. The rate of motion of gold helps the buyers from the centre of attention in their investments; they make use of the year by year information from Indian Gold Council. The analysis of the data was taken from 1964 to 2020. This paper's motto is to analyze and summarize different algorithms for predicting the rate of gold. The procedures utilized to fit the data were from the Time Series analysis Auto Regressive Integrated Moving Average (ARIMA) and Neural Network models; Multi-Layer Perception (MLP) and Extreme Learning Machine (ELM). The test data were utilized for the analysis, and then the outcome was exhibited with the help of error parameters. ELM is best as compared to ARIMA and MLP. The error measures are RMSE (1634.975) and MAPE (3.002). The error measurements have been represented in the tables for ARIMA and MLP. The best prediction of Gold price was given by the ELM, which is be efficient and accurate model.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140703033","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}
Various ailments affect rice, a staple crop in India, across different stages of its growth. Identification of these diseases manually poses a significant challenge, especially for farmers lacking in-depth knowledge. Recently, there's been promising advancement in deep learning research through automated picture identification systems employing Convolutional Neural Network (CNN) models. To tackle the scarcity of rice leaf disease image datasets, we developed a deep learning model using Transfer Learning on a limited dataset. Our approach leverages VGG-16 to train and evaluate the proposed CNN architecture, drawing from rice field and internet datasets. Impressively, the model achieves a 95 percent accuracy rate. Key terms in this study include Deep Learning, Convolutional Neural Network (CNN), fine-tuning, and rice leaf diseases.
{"title":"A novel technique predicting the rice leaf diseases using Convolutional Neural Network","authors":"","doi":"10.59018/022437","DOIUrl":"https://doi.org/10.59018/022437","url":null,"abstract":"Various ailments affect rice, a staple crop in India, across different stages of its growth. Identification of these diseases manually poses a significant challenge, especially for farmers lacking in-depth knowledge. Recently, there's been promising advancement in deep learning research through automated picture identification systems employing Convolutional Neural Network (CNN) models. To tackle the scarcity of rice leaf disease image datasets, we developed a deep learning model using Transfer Learning on a limited dataset. Our approach leverages VGG-16 to train and evaluate the proposed CNN architecture, drawing from rice field and internet datasets. Impressively, the model achieves a 95 percent accuracy rate. Key terms in this study include Deep Learning, Convolutional Neural Network (CNN), fine-tuning, and rice leaf diseases.","PeriodicalId":38652,"journal":{"name":"ARPN Journal of Engineering and Applied Sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140702743","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：