2023 [Vol 2 Issue 2]
|
Brahmbhatt, Hiren; N, Thangadurai A NOVEL TECHNIQUE FOR DYNAMIC COLLECTOR VOLTAGE & CURRENT CLAMPING METHOD FOR DRIVING HIGH POWER SEMICONDUCTOR TO ENHANCE AVAILABILITY OF HIGH-POWER CONVERTERS IN EV (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 1-7, 2023. @article{nokey,
title = {A NOVEL TECHNIQUE FOR DYNAMIC COLLECTOR VOLTAGE & CURRENT CLAMPING METHOD FOR DRIVING HIGH POWER SEMICONDUCTOR TO ENHANCE AVAILABILITY OF HIGH-POWER CONVERTERS IN EV},
author = {Hiren Brahmbhatt and Thangadurai N},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-1-7.pdf},
year = {2023},
date = {2023-12-26},
urldate = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {1-7},
abstract = {The electric drive and the batteries are the two primary parts of an electric vehicle (EV). In order to increase the availability and dependability of the semiconductors used in traction converters, this research focuses on a new approach of semiconductor (IGBT) protection. The IGBT spike voltage during a short circuit situation was successfully reduced by a newly created active voltage and current clamping circuit. This innovative method restricts IGBT’s collector-emitter voltage during the turn-off event. As soon as the collector-emitter voltage of the IGBT crosses a predetermined threshold, the IGBT is partially turned on. The IGBT is then kept operating linearly, minimizing the rate at which the collector current falls and, consequently, and the collector-emitter over voltage. Simultaneously, during the short circuit, the current is monitored by a high precision hall-effect sensor allegro make IC, which detects over current and provides a fault output within 1 second. As a result of the combination of current and voltage monitoring, the likelihood of the IGBT failure is reduced.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The electric drive and the batteries are the two primary parts of an electric vehicle (EV). In order to increase the availability and dependability of the semiconductors used in traction converters, this research focuses on a new approach of semiconductor (IGBT) protection. The IGBT spike voltage during a short circuit situation was successfully reduced by a newly created active voltage and current clamping circuit. This innovative method restricts IGBT’s collector-emitter voltage during the turn-off event. As soon as the collector-emitter voltage of the IGBT crosses a predetermined threshold, the IGBT is partially turned on. The IGBT is then kept operating linearly, minimizing the rate at which the collector current falls and, consequently, and the collector-emitter over voltage. Simultaneously, during the short circuit, the current is monitored by a high precision hall-effect sensor allegro make IC, which detects over current and provides a fault output within 1 second. As a result of the combination of current and voltage monitoring, the likelihood of the IGBT failure is reduced. |
Ajay Kotalwar Sanket Mendhe Allur Shivprasad Rao, Meenakshi Thalor ANALYSIS OF MONOLITHIC AND MICROSERVICES SYSTEM ARCHITECTURES FOR AN E-COMMERCE WEB APPLICATION (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 8-21 2023. @article{nokey,
title = {ANALYSIS OF MONOLITHIC AND MICROSERVICES SYSTEM ARCHITECTURES FOR AN E-COMMERCE WEB APPLICATION},
author = {Allur Shivprasad Rao, Ajay Kotalwar
Sanket Mendhe, Meenakshi Thalor
},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-8-21.pdf},
year = {2023},
date = {2023-12-26},
urldate = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
abstract = {This research paper explores the relative merits of monolithic and microservices architecture for E-Commerce web applications, using Express JS and Node JS as the primary technologies. The study provides a comprehensive examination of the two architecture patterns and employs a practical approach to demonstrate the differences. The architecture is compared based on metrics such as latency, throughput, response-time, error percentage and cost. The findings indicate that when it comes to large and complex applications, microservices architecture outperforms monolithic architecture in terms of scalability and reliability. On the other hand, monolithic architecture offers a simpler and more straightforward approach for small-scale applications. Moreover, monolithic architecture also provides better results for a small-scale approach whereas microservices architecture would be an expensive approach. In the experiment, we found that monolithic architecture gives satisfactory results compared to microservices architecture while having low traffic. However, the error percentage of monolithic architecture is extremely high while having heavy traffic whereas microservices architecture handles heavy traffic with a very low error percentage. In the paper we conclude that the appropriate choice of architecture pattern should be determined by the unique needs of the project. The objective of this research is to evaluate the monolithic and microservices architectures for an ecommerce use case, and to propose guidelines for small and large scale enterprises on which architecture to implement. This is a generic use case that does not account for any specific conditions or constraints.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This research paper explores the relative merits of monolithic and microservices architecture for E-Commerce web applications, using Express JS and Node JS as the primary technologies. The study provides a comprehensive examination of the two architecture patterns and employs a practical approach to demonstrate the differences. The architecture is compared based on metrics such as latency, throughput, response-time, error percentage and cost. The findings indicate that when it comes to large and complex applications, microservices architecture outperforms monolithic architecture in terms of scalability and reliability. On the other hand, monolithic architecture offers a simpler and more straightforward approach for small-scale applications. Moreover, monolithic architecture also provides better results for a small-scale approach whereas microservices architecture would be an expensive approach. In the experiment, we found that monolithic architecture gives satisfactory results compared to microservices architecture while having low traffic. However, the error percentage of monolithic architecture is extremely high while having heavy traffic whereas microservices architecture handles heavy traffic with a very low error percentage. In the paper we conclude that the appropriate choice of architecture pattern should be determined by the unique needs of the project. The objective of this research is to evaluate the monolithic and microservices architectures for an ecommerce use case, and to propose guidelines for small and large scale enterprises on which architecture to implement. This is a generic use case that does not account for any specific conditions or constraints. |
Dr. Rajesh Patel, Dr. Kirit Modi; Patel, Prof. Mehul A LOAD BALANCE AND VIRTUAL MACHINES MIGRATION APPROACH USING QEMU-KVM FOR ENERGY EFFICIENT DATA CENTRE OF CLOUD COMPUTING (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 22-30, 2024. @article{nokey,
title = {A LOAD BALANCE AND VIRTUAL MACHINES MIGRATION APPROACH USING QEMU-KVM FOR ENERGY EFFICIENT DATA CENTRE OF CLOUD COMPUTING},
author = {Dr. Rajesh Patel, Dr.Kirit Modi and Prof. Mehul Patel},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-22-30.pdf},
year = {2024},
date = {2024-01-26},
urldate = {2024-01-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {22-30},
abstract = {Load balancing and virtual machine migration are particularly challenging jobs in a cloud data centre. Some virtual computers in a data centre have more workload than they can handle, while others have less. The workload must be balanced as a result, and efficient virtual machine migration promotes workload balance while minimising server power consumption in the data centre. This ultimately leads to the energy consumption of the data centre being lowered by turning off idle servers. In our study, virtual machine migration and load balancing are performed using the hypervisor KVM. This optimal machine movement and subsequent reduction in host server CPU use results in lower power consumption and improved energy efficiency of data centres in cloud computing.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Load balancing and virtual machine migration are particularly challenging jobs in a cloud data centre. Some virtual computers in a data centre have more workload than they can handle, while others have less. The workload must be balanced as a result, and efficient virtual machine migration promotes workload balance while minimising server power consumption in the data centre. This ultimately leads to the energy consumption of the data centre being lowered by turning off idle servers. In our study, virtual machine migration and load balancing are performed using the hypervisor KVM. This optimal machine movement and subsequent reduction in host server CPU use results in lower power consumption and improved energy efficiency of data centres in cloud computing. |
Neeraja s, George Mathew Restoring Image Clarity: Dual-GAN Framework for High-Quality Image Generation from Low-Resolution Blurred Inputs (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 31-39, 2023. @article{nokey,
title = {Restoring Image Clarity: Dual-GAN Framework for High-Quality Image Generation from Low-Resolution Blurred Inputs},
author = {Neeraja s, George Mathew},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-31-39.pdf},
year = {2023},
date = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {31-39},
abstract = {A key task in computer vision is image restoration, which aims to recover high-quality images from blurry or degraded inputs. In this research, we provide a novel method for restoring high-quality images by combining the advantages of DeblurGAN and ESRGAN (Enhanced Super-Resolution GAN). While ESRGAN focuses on super-resolution and fine detail recovery, DeblurGAN focuses on eliminating blurring artefacts and increasing image details. We take advantage of the complementary strengths of these two architectures and produce a synergistic outcome by combining them in a multi-stage refining process. The suggested method starts by using DeblurGAN to deblur the input photos and improve their clarity and sharpness. Enhance super-resolution GAN is then used to further enhance the deblurred images with a focus on high-frequency detail recovery and super-resolution. The input photos can be fully restored using this multi-stage refinement procedure, which improves visual quality and resolution. Numerous tests show that this method performs better in eliminating blurring artefacts and retrieving fine details. Deblur-GAN and ESRGAN are combined to improve visual quality, resolution, and detail recovery through a multi-stage refinement process. The method effectively addresses the picture restoration issues, showing potential for applications in digital photography, surveillance, and medical imaging.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
A key task in computer vision is image restoration, which aims to recover high-quality images from blurry or degraded inputs. In this research, we provide a novel method for restoring high-quality images by combining the advantages of DeblurGAN and ESRGAN (Enhanced Super-Resolution GAN). While ESRGAN focuses on super-resolution and fine detail recovery, DeblurGAN focuses on eliminating blurring artefacts and increasing image details. We take advantage of the complementary strengths of these two architectures and produce a synergistic outcome by combining them in a multi-stage refining process. The suggested method starts by using DeblurGAN to deblur the input photos and improve their clarity and sharpness. Enhance super-resolution GAN is then used to further enhance the deblurred images with a focus on high-frequency detail recovery and super-resolution. The input photos can be fully restored using this multi-stage refinement procedure, which improves visual quality and resolution. Numerous tests show that this method performs better in eliminating blurring artefacts and retrieving fine details. Deblur-GAN and ESRGAN are combined to improve visual quality, resolution, and detail recovery through a multi-stage refinement process. The method effectively addresses the picture restoration issues, showing potential for applications in digital photography, surveillance, and medical imaging. |
Ashvini k. Butani, Ravirajsinh s. Vaghela A LITERATURE REVIEW ON CLOUD COMPUTING SECURITY (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 40-49, 2023. @article{nokey,
title = {A LITERATURE REVIEW ON CLOUD COMPUTING SECURITY},
author = {Ashvini k. Butani, Ravirajsinh s.Vaghela},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-40-49.pdf},
year = {2023},
date = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {40-49},
abstract = {Cloud computing most trending technology nowadays because this pandemic situation all works from home small village to megacity, government sector to private sector and company, school,hospital,all home utility whole worlds depending on cloud base technology so it is on-demand technology that provides all over a solution like software, storage, or platforms and give a huge infrastructure over the internet with minimal cost. hence cloud needs more protection about user data to need more protection and secure framework from internal and external attacks like botnets, viruses, and worms, web application threats, dos attacks. So this paper gives an analysis and discusses about the cloud computing security working with different Algoritham,Ai and machine learning with different authentication control block chain analysis and discusses the review of cloud computing security in three different layer SaaS(Software as a Service), PaaS (Platform as a Service), Iaas (Infrastructure as a Service), and its deployment models private, public, hybrid, and community cloud.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Cloud computing most trending technology nowadays because this pandemic situation all works from home small village to megacity, government sector to private sector and company, school,hospital,all home utility whole worlds depending on cloud base technology so it is on-demand technology that provides all over a solution like software, storage, or platforms and give a huge infrastructure over the internet with minimal cost. hence cloud needs more protection about user data to need more protection and secure framework from internal and external attacks like botnets, viruses, and worms, web application threats, dos attacks. So this paper gives an analysis and discusses about the cloud computing security working with different Algoritham,Ai and machine learning with different authentication control block chain analysis and discusses the review of cloud computing security in three different layer SaaS(Software as a Service), PaaS (Platform as a Service), Iaas (Infrastructure as a Service), and its deployment models private, public, hybrid, and community cloud. |
Digambar Jadhav, Pankaj Kumar Payal Bhargava IMAGE SEGMENTATION FOR BRAIN TUMOR DIAGNOSIS: A POSSIBLE APPLICATION OF MACHINE LEARNING (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 50-65, 2023. @article{nokey,
title = {IMAGE SEGMENTATION FOR BRAIN TUMOR DIAGNOSIS: A POSSIBLE APPLICATION OF MACHINE LEARNING},
author = {Digambar Jadhav, Pankaj Kumar
Payal Bhargava
},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-50-65.pdf},
year = {2023},
date = {2023-12-26},
urldate = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {50-65},
abstract = {Image segmentation is essential for the prognosis of brain tumors. Accurate and quick MRI segmentation is crucial for the diagnosis, treatment, and prognosis of brain tumors. In this study, we provide a machine learning-based approach to the problem of segmenting brain tumors. Improved outcomes for patients with brain tumors may be expected as a consequence of the use of cutting-edge deep learning techniques with massive MRI datasets. Brain tumor segmentation in medical images is particularly challenging. An accurate method of dividing up brain tumors is needed. When it comes to image categorization, object identification, and semantic segmentation, deep learning algorithms have excelled. Segmentation methods for brain tumors based on deep learning show promise. Segmentation of brain tumors using deep learning is the topic of this essay. A total of 150 academic publications are reviewed, including topics like network architecture design, imbalanced segmentation, and multi-modality processes. Goal-setting conversations may be quite illuminating. Brain tumors are the result of unchecked cell proliferation. Brain tumors are diverse. Brain tumors may be either malignant or benign. This technique uses image segmentation and classification to automate the identification of brain tumors. Brain tumors can come in a wide range of sizes. Use deep neural networks with a lot of memory. Our methods are outlined below for your perusal. Kaggle data was used to evaluate the trained model. There are 5,000 images for segmentation and 8,000 for classification in this set of data. MRI scans may be broken up into patches. On test data, this method proved to be 95.6% accurate. We tried several configurations of neural network layers to settle on the best one. A glioma was identified via convolutional neural networks. Spectrum-based lilac cell glioma localization was achieved by means of deep and convolutional neural networks. Potentially, this framework can foretell the future.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Image segmentation is essential for the prognosis of brain tumors. Accurate and quick MRI segmentation is crucial for the diagnosis, treatment, and prognosis of brain tumors. In this study, we provide a machine learning-based approach to the problem of segmenting brain tumors. Improved outcomes for patients with brain tumors may be expected as a consequence of the use of cutting-edge deep learning techniques with massive MRI datasets. Brain tumor segmentation in medical images is particularly challenging. An accurate method of dividing up brain tumors is needed. When it comes to image categorization, object identification, and semantic segmentation, deep learning algorithms have excelled. Segmentation methods for brain tumors based on deep learning show promise. Segmentation of brain tumors using deep learning is the topic of this essay. A total of 150 academic publications are reviewed, including topics like network architecture design, imbalanced segmentation, and multi-modality processes. Goal-setting conversations may be quite illuminating. Brain tumors are the result of unchecked cell proliferation. Brain tumors are diverse. Brain tumors may be either malignant or benign. This technique uses image segmentation and classification to automate the identification of brain tumors. Brain tumors can come in a wide range of sizes. Use deep neural networks with a lot of memory. Our methods are outlined below for your perusal. Kaggle data was used to evaluate the trained model. There are 5,000 images for segmentation and 8,000 for classification in this set of data. MRI scans may be broken up into patches. On test data, this method proved to be 95.6% accurate. We tried several configurations of neural network layers to settle on the best one. A glioma was identified via convolutional neural networks. Spectrum-based lilac cell glioma localization was achieved by means of deep and convolutional neural networks. Potentially, this framework can foretell the future. |
Bharti Sahua, Dr. Bhagwan Phulpagar Digambar Jadhav PREDICTING THE GROWTH AND TREND OF THE COVID-19 VIRUS USING MACHINE LEARNING (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 66-76, 2023. @article{nokey,
title = {PREDICTING THE GROWTH AND TREND OF THE COVID-19 VIRUS USING MACHINE LEARNING},
author = {Bharti Sahua, Dr. Bhagwan Phulpagar
Digambar Jadhav},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-66-76.pdf},
year = {2023},
date = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {66-76},
abstract = {The global SARS-CoV-2 outbreak caused by the COVID-19 Coronavirus has been catastrophic. COVID-19's cumulative incidence is rising at an alarming rate. Tracking the disease, predicting its progress, and developing strategies and regulations to control the epidemic are all tasks that can greatly benefit from the use of Machine Learning (ML) and Cloud Computing. This research makes use of a sophisticated mathematical model to examine and predict the epidemic's progress. An improved model based on ML has been used to estimate the risk of COVID-19 in different nations. We show that iterative weighting for fitting may lead to a better fit when building a prediction framework using the Generalized Inverse Weibull distribution. This has been implemented on a cloud computing platform for improved and more timely prediction of the epidemic's development propensity. Proactive responses from both the government and the people can greatly benefit from a data-driven strategy with the level of precision shown here. Finally, we suggest a number of avenues for future study and actual implementation. From this review of the relevant literature, we were able to choose a group of prediction-friendly algorithms, including SVMs, RFs, and ANNs. The selected algorithms' performances are compared in order to determine which method provides the most accuracy. To determine the significance of each feature in the context of the forecast, importance values are calculated. The use of Machine Learning for COVID-19 prediction has the potential to increase the rate at which diseases are diagnosed, which in turn would reduce mortality rates. Based on the experimental data, it was determined that the artificial neural network outperformed the other algorithms.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The global SARS-CoV-2 outbreak caused by the COVID-19 Coronavirus has been catastrophic. COVID-19's cumulative incidence is rising at an alarming rate. Tracking the disease, predicting its progress, and developing strategies and regulations to control the epidemic are all tasks that can greatly benefit from the use of Machine Learning (ML) and Cloud Computing. This research makes use of a sophisticated mathematical model to examine and predict the epidemic's progress. An improved model based on ML has been used to estimate the risk of COVID-19 in different nations. We show that iterative weighting for fitting may lead to a better fit when building a prediction framework using the Generalized Inverse Weibull distribution. This has been implemented on a cloud computing platform for improved and more timely prediction of the epidemic's development propensity. Proactive responses from both the government and the people can greatly benefit from a data-driven strategy with the level of precision shown here. Finally, we suggest a number of avenues for future study and actual implementation. From this review of the relevant literature, we were able to choose a group of prediction-friendly algorithms, including SVMs, RFs, and ANNs. The selected algorithms' performances are compared in order to determine which method provides the most accuracy. To determine the significance of each feature in the context of the forecast, importance values are calculated. The use of Machine Learning for COVID-19 prediction has the potential to increase the rate at which diseases are diagnosed, which in turn would reduce mortality rates. Based on the experimental data, it was determined that the artificial neural network outperformed the other algorithms. |
Mili Dhar, Saikat Majumder A STUDY OF LATENCY AWARE CONTROLLER PLACEMENT PROBLEM IN SDN (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 77-85, 2023. @article{nokey,
title = {A STUDY OF LATENCY AWARE CONTROLLER PLACEMENT PROBLEM IN SDN},
author = {Mili Dhar, Saikat Majumder},
editor = {Dr. K. K. Patel},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-77-85.pdf},
year = {2023},
date = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {77-85},
abstract = {In fast and rapidly growing technology where data handling is more important, a new promising paradigm has come into the picture called Software-Defined Network (SDN). A SDN is a software-based programmable network that detaches the control and data plane to overcome the shortcomings of traditional networks. This separation provides many advantages like network virtualization, flexibility, management, and so on. Apart from the advantages given by the SDN, it also brings some issues. The controller placement problem (CPP) is one of them. Depending on the controller location network performances can vary. Putting a controller in any of the accessible locations is also not a good idea, as it only increases the overhead delay. Hence, selecting an appropriate location to shorten the latency is a challenging task. Thus, in this article, we talk about the importance of latency in SDN and study some of the latency-aware techniques developed by other researchers to solve the CPP. These solutions have been divided into two categories according to the application scenarios which are data-center networks and Wide Area Networks (WANs). We've categorized latencies in the control plane and presented their mathematical formulation. We have also presented a comprehensive study in this review. Lastly, we outlined potential areas for future research that researchers can delve into further.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In fast and rapidly growing technology where data handling is more important, a new promising paradigm has come into the picture called Software-Defined Network (SDN). A SDN is a software-based programmable network that detaches the control and data plane to overcome the shortcomings of traditional networks. This separation provides many advantages like network virtualization, flexibility, management, and so on. Apart from the advantages given by the SDN, it also brings some issues. The controller placement problem (CPP) is one of them. Depending on the controller location network performances can vary. Putting a controller in any of the accessible locations is also not a good idea, as it only increases the overhead delay. Hence, selecting an appropriate location to shorten the latency is a challenging task. Thus, in this article, we talk about the importance of latency in SDN and study some of the latency-aware techniques developed by other researchers to solve the CPP. These solutions have been divided into two categories according to the application scenarios which are data-center networks and Wide Area Networks (WANs). We've categorized latencies in the control plane and presented their mathematical formulation. We have also presented a comprehensive study in this review. Lastly, we outlined potential areas for future research that researchers can delve into further. |
Bhavini K. Shah, Dr. Kamlendu S. Pandey A Comprehensive Review on AI Based Model for Rainfall Prediction (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 87-105, 2023. @article{nokey,
title = {A Comprehensive Review on AI Based Model for Rainfall Prediction},
author = {Bhavini K. Shah, Dr. Kamlendu S. Pandey},
editor = {Our nation’s economy is heavily dependent on agriculture and industries. To generate a profit, we should rely substantially on the availability of water. But the outcome is severely hampered by the irregularity of rainfall and the depletion of available water supplies. In 2014, India earned net $8 billion from $304 billion trade in commercial services. On the other hand, agricultural trade of $56 billion fetched as much as $18 billion in trade surplus. This is because while in services trade imports account for a lion’s share, in agriculture imports component is negligible since basic resources such as sunlight, land, water, labor etc. are all available in the country. Agriculture is not just important for feeding the local population but to gain foreign exchange. Sometime heavy rainfall can cause damage to farms and crops but if it is predicted earlier than early warning can help to reduce the damage of life and resources. This paper provides a systematic literature review of state of art machine learning and deep learning techniques proposed by various authors to predict the rainfall. This paper gives information about Ensemble Learning, Logistic Regression, various Linear Regression, Multiple Linear Regression, Artificial Neural Network, K-Nearest Neighbor, Support Vector Regression, Decision tree and other miscellaneous models.},
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-87-105.pdf},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {87-105},
abstract = {Our nation’s economy is heavily dependent on agriculture and industries. To generate a profit, we should rely substantially on the availability of water. But the outcome is severely hampered by the irregularity of rainfall and the depletion of available water supplies. In 2014, India earned net $8 billion from $304 billion trade in commercial services. On the other hand, agricultural trade of $56 billion fetched as much as $18 billion in trade surplus. This is because while in services trade imports account for a lion’s share, in agriculture imports component is negligible since basic resources such as sunlight, land, water, labor etc. are all available in the country. Agriculture is not just important for feeding the local population but to gain foreign exchange. Sometime heavy rainfall can cause damage to farms and crops but if it is predicted earlier than early warning can help to reduce the damage of life and resources. This paper provides a systematic literature review of state of art machine learning and deep learning techniques proposed by various authors to predict the rainfall. This paper gives information about Ensemble Learning, Logistic Regression, various Linear Regression, Multiple Linear Regression, Artificial Neural Network, K-Nearest Neighbor, Support Vector Regression, Decision tree and other miscellaneous models.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Our nation’s economy is heavily dependent on agriculture and industries. To generate a profit, we should rely substantially on the availability of water. But the outcome is severely hampered by the irregularity of rainfall and the depletion of available water supplies. In 2014, India earned net $8 billion from $304 billion trade in commercial services. On the other hand, agricultural trade of $56 billion fetched as much as $18 billion in trade surplus. This is because while in services trade imports account for a lion’s share, in agriculture imports component is negligible since basic resources such as sunlight, land, water, labor etc. are all available in the country. Agriculture is not just important for feeding the local population but to gain foreign exchange. Sometime heavy rainfall can cause damage to farms and crops but if it is predicted earlier than early warning can help to reduce the damage of life and resources. This paper provides a systematic literature review of state of art machine learning and deep learning techniques proposed by various authors to predict the rainfall. This paper gives information about Ensemble Learning, Logistic Regression, various Linear Regression, Multiple Linear Regression, Artificial Neural Network, K-Nearest Neighbor, Support Vector Regression, Decision tree and other miscellaneous models. |
R. Ragunath, R. Rathipriya AGRICULTURAL COMMODITY PRICE FORECASTING WITH COMPETITIVE ENSEMBLE REGRESSION TECHNIQUE (Journal Article) In: International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS), vol. 02, iss. 02, pp. 106-118, 2023. @article{nokey,
title = {AGRICULTURAL COMMODITY PRICE FORECASTING WITH COMPETITIVE ENSEMBLE REGRESSION TECHNIQUE},
author = {R. Ragunath, R. Rathipriya},
editor = {Dr. K. K. Patel },
url = {https://sciencetransactions.com/ijascis/uploads/2024/01/d23-106-118.pdf},
year = {2023},
date = {2023-12-26},
journal = {International Journal of Advances in Soft Computing and Intelligent Systems (IJASCIS)},
volume = {02},
issue = {02},
pages = {106-118},
abstract = {This research study focuses on introducing a novel ensemble learning-based strategy using regression models to enhance the accuracy of forecasting Agricultural Commodity Price (ACP) trends. The main objective is to give farmers and traders better accurate pricing forecasts. The study uses data from India's rainfall data and the Wholesale Pricing Index (WPI) for essential commodities to test a variety of regression models, including ensemble regression models. The empirical results highlight the competitive ensemble approach's greater accuracy in capturing directional shifts in agricultural commodity pricing when compared to conventional regression models. As a result, this strategy has a lot of potential for assisting decision-making in the food and financial industries.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This research study focuses on introducing a novel ensemble learning-based strategy using regression models to enhance the accuracy of forecasting Agricultural Commodity Price (ACP) trends. The main objective is to give farmers and traders better accurate pricing forecasts. The study uses data from India's rainfall data and the Wholesale Pricing Index (WPI) for essential commodities to test a variety of regression models, including ensemble regression models. The empirical results highlight the competitive ensemble approach's greater accuracy in capturing directional shifts in agricultural commodity pricing when compared to conventional regression models. As a result, this strategy has a lot of potential for assisting decision-making in the food and financial industries. |