Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200084
N. Neelima, Aruru Sai Kumar, A. Jayanth, K. K. Mahitha, A. Dilip, K. Reddy
The basic elements of an electronic system are arithmetic operations. Arithmetic operations are the building block of any electronic application and algorithm is a sequence of instructions used to carry out calculations or solve problems. In spite of the fact that addition, subtraction, multiplication, and division are fundamental components of arithmetic implementation in the electronic system, the implementation of division has received far less attention than the implementation of the other arithmetic operations. The process of dividing two numbers using the method results in the production of a quotient in addition to a remainder. The implementation of division operations is highly challenging; thus, in this scenario, a complex method is employed to ensure successful implementation. To be successful, a system has to have a solid performance in the division circuit. In this body of work, the Restoring division and Non-restoring division algorithms, which fall under the category of Digit Recurrence Class, have been developed for unsigned integers with data sizes of 8 bit, 16 bit, and 32 bit using the Verilog HDL programming language. These algorithms are applicable to unsigned integers with data values of 8, 16, and 32 bits respectively. In each of these algorithms, the calculation takes place in one of three registers designated by the letters A, Q, or M.
{"title":"Implementation of Efficient Digit Recurrence Class of Division Algorithms","authors":"N. Neelima, Aruru Sai Kumar, A. Jayanth, K. K. Mahitha, A. Dilip, K. Reddy","doi":"10.1109/ACCESS57397.2023.10200084","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200084","url":null,"abstract":"The basic elements of an electronic system are arithmetic operations. Arithmetic operations are the building block of any electronic application and algorithm is a sequence of instructions used to carry out calculations or solve problems. In spite of the fact that addition, subtraction, multiplication, and division are fundamental components of arithmetic implementation in the electronic system, the implementation of division has received far less attention than the implementation of the other arithmetic operations. The process of dividing two numbers using the method results in the production of a quotient in addition to a remainder. The implementation of division operations is highly challenging; thus, in this scenario, a complex method is employed to ensure successful implementation. To be successful, a system has to have a solid performance in the division circuit. In this body of work, the Restoring division and Non-restoring division algorithms, which fall under the category of Digit Recurrence Class, have been developed for unsigned integers with data sizes of 8 bit, 16 bit, and 32 bit using the Verilog HDL programming language. These algorithms are applicable to unsigned integers with data values of 8, 16, and 32 bits respectively. In each of these algorithms, the calculation takes place in one of three registers designated by the letters A, Q, or M.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115672207","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10201193
Neethu Subash, Dr B Nithya, R. Bangar, Vipul Patel
AIMD (Additive Increase Multiplicative Decrease) and CUBIC (Cubic Congestion Control) are the two commonly used algorithms for network congestion control in the UAV (Unmanned Aerial Vehicle). AIMD and CUBIC can control the data transfer rate between the UAV and the ground station or other UAVs in a swarmed network. This is particularly important for real-time applications using flying adhoc networks (FANET), such as surveillance or monitoring, where timely data delivery is critical. Multiptah TCP utilizes individual subflows to implement congestion control. Nevertheless, the default congestion management mechanism for subflows in an MPTCP connection uses a linked increase adaptation technique to prevent the congestion window from rapidly expanding due to subflows independently developing their own congestion windows. The throughput of MPTCP connections may decline if fast algorithms like CUBIC TCP are employed in high speed congested network. This work proposes mpQUAD, a novel CUBIC TCP-based high-speed congestion management technique for MPTCP. It exposes specific control parameters of the algorithm to tweak the systems TCP congestion control behavior. The sender’s congestion window can be controlled by changing the multiplicative factor and the rate at which it grows, by the user. The throughputs of MPTCP flows decrease in the conventional congestion control algorithms. The limited bandwidth and high mobility of FANETs can cause significant delay, which the proposed congestion control algorithm mpQUAD can mitigate.
{"title":"mpQUAD: Multipath Quad TCP Congestion Control in FANETs","authors":"Neethu Subash, Dr B Nithya, R. Bangar, Vipul Patel","doi":"10.1109/ACCESS57397.2023.10201193","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10201193","url":null,"abstract":"AIMD (Additive Increase Multiplicative Decrease) and CUBIC (Cubic Congestion Control) are the two commonly used algorithms for network congestion control in the UAV (Unmanned Aerial Vehicle). AIMD and CUBIC can control the data transfer rate between the UAV and the ground station or other UAVs in a swarmed network. This is particularly important for real-time applications using flying adhoc networks (FANET), such as surveillance or monitoring, where timely data delivery is critical. Multiptah TCP utilizes individual subflows to implement congestion control. Nevertheless, the default congestion management mechanism for subflows in an MPTCP connection uses a linked increase adaptation technique to prevent the congestion window from rapidly expanding due to subflows independently developing their own congestion windows. The throughput of MPTCP connections may decline if fast algorithms like CUBIC TCP are employed in high speed congested network. This work proposes mpQUAD, a novel CUBIC TCP-based high-speed congestion management technique for MPTCP. It exposes specific control parameters of the algorithm to tweak the systems TCP congestion control behavior. The sender’s congestion window can be controlled by changing the multiplicative factor and the rate at which it grows, by the user. The throughputs of MPTCP flows decrease in the conventional congestion control algorithms. The limited bandwidth and high mobility of FANETs can cause significant delay, which the proposed congestion control algorithm mpQUAD can mitigate.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121448100","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200900
Aparna P R, Libish T M
Liver tumors are one of the life-threatening cancers with the fastest-growth rates worldwide. Early detection of tumors may therefore reduce morbidity and increase the survival rate. The development of automated techniques for the precise segmentation of hepatic tumors is essential for assisting doctors in tumor diagnosis and preoperative planning for surgical treatment of the liver which reduces the risk of surgical resection. The classification and segmentation of hepatic tumors in Computerized Tomography (CT) scan pose a great challenge due to noise, unclear boundaries, heterogeneity, and variability in tumor tissue appearance, shape, size, and location. In this study, we describe a novel method for automatic segmentation and classification of hepatic tumors in CT scan images using Deep Convolutional Neural Networks. For tumor segmentation, we created a modified Dense U-net model. The classification framework is based on a novel deep CNN with a pre-trained VGG-16 network to distinguish between normal and malignant liver tumors. The proposed system was evaluated based on MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge dataset and obtained the best result with a Dice Score of 95.40%, Jaccard Index of 92%, and accuracy of 92.60% for segmentation and the classification model has achieved an accuracy of 96%, Sensitivity of 95.80%, Specificity of 96.20% and Precision of 95.80%.
{"title":"Automatic segmentation and classification of the liver tumor using deep learning algorithms","authors":"Aparna P R, Libish T M","doi":"10.1109/ACCESS57397.2023.10200900","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200900","url":null,"abstract":"Liver tumors are one of the life-threatening cancers with the fastest-growth rates worldwide. Early detection of tumors may therefore reduce morbidity and increase the survival rate. The development of automated techniques for the precise segmentation of hepatic tumors is essential for assisting doctors in tumor diagnosis and preoperative planning for surgical treatment of the liver which reduces the risk of surgical resection. The classification and segmentation of hepatic tumors in Computerized Tomography (CT) scan pose a great challenge due to noise, unclear boundaries, heterogeneity, and variability in tumor tissue appearance, shape, size, and location. In this study, we describe a novel method for automatic segmentation and classification of hepatic tumors in CT scan images using Deep Convolutional Neural Networks. For tumor segmentation, we created a modified Dense U-net model. The classification framework is based on a novel deep CNN with a pre-trained VGG-16 network to distinguish between normal and malignant liver tumors. The proposed system was evaluated based on MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge dataset and obtained the best result with a Dice Score of 95.40%, Jaccard Index of 92%, and accuracy of 92.60% for segmentation and the classification model has achieved an accuracy of 96%, Sensitivity of 95.80%, Specificity of 96.20% and Precision of 95.80%.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123618184","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199296
Vikas Khullar, Mohit Angurala, K. Singh, P. Prasant, V. Pabbi, Veeramanickam M.R. M
The class imbalanced datasets are major challenge for classification techniques. In this paper, the role and possibilities of handling of imbalanced classes in structured and tabular dataset have been experimentally discussed. In methodology, diverse over sampling and under sampling techniques were applied and analyzed on basis of parameters viz., accuracy, precision, recall, and f1-score. Haberman Breast Cancer, Pima Indian diabetes and synthetic datasets were considered for experimental study, unbalanced datasets were considered. All three are unbalanced datasets were analyzed through classification algorithms. Further, class balancing techniques were applied through over sampling and under sampling methods and then supervised classification algorithms were applied and analyzed on basis of metrics. The results reflected with best fit metrics for both under and over sampling methods. In conclusion a best technique out of implemented methods were identified and proposed for future use.
{"title":"Exploring Methods for Dealing with Class Imbalances in Supervised Machine Learning Structured Datasets","authors":"Vikas Khullar, Mohit Angurala, K. Singh, P. Prasant, V. Pabbi, Veeramanickam M.R. M","doi":"10.1109/ACCESS57397.2023.10199296","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199296","url":null,"abstract":"The class imbalanced datasets are major challenge for classification techniques. In this paper, the role and possibilities of handling of imbalanced classes in structured and tabular dataset have been experimentally discussed. In methodology, diverse over sampling and under sampling techniques were applied and analyzed on basis of parameters viz., accuracy, precision, recall, and f1-score. Haberman Breast Cancer, Pima Indian diabetes and synthetic datasets were considered for experimental study, unbalanced datasets were considered. All three are unbalanced datasets were analyzed through classification algorithms. Further, class balancing techniques were applied through over sampling and under sampling methods and then supervised classification algorithms were applied and analyzed on basis of metrics. The results reflected with best fit metrics for both under and over sampling methods. In conclusion a best technique out of implemented methods were identified and proposed for future use.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127522968","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199711
Jayesh T P, Pandiaraj K, Arya Paul, Ranjeesh R Chandran, Prasanth P Menon
IIoT is the integration of conventional IoT principles into industrial operations. IIoT has a wide range of practical applications, including but not limited to supply chain management, connected cars, smart grids, smart cities, and smart homes. Regrettably, these systems are increasingly becoming the focus of cybercrime attacks. Machine learning is a promising technology for creating and implementing resilient security measures in IIoT networks. A new and innovative approach to detecting cyberattacks in the IIoT is proposed in this document, through the use of a hybrid machine classifier (HMC). The HMC model is a unique amalgamation of different ML models, such as K-nearest neighbor (KNN), extra trees (ET), gradient boosting (GB), AdaBoost (AB), linear discriminant analysis (LDA), ), naive Bayes (NB), support vector machine (SVM), random forest (RFlinear regression (LR), and classification and regression tree (CART). The DS2OS dataset is used to evaluate the proposed method's effectiveness. Several performance metrics, including recall, precision, accuracy, specificity, F1 score, detection rate, and ROC are used to evaluate the system's performance. The proposed model successfully distinguishes between normal and attack traffic, achieving an accuracy rate of 99.7% and 99.8%, respectively. To evaluate the effectiveness of the proposed method, its performance metrics were compared to those of other advanced attack detection algorithms. The outcomes demonstrated that the proposed model outperformed other ML and DL-based techniques
{"title":"A Hybrid Machine Learning Approach to Anomaly Detection in Industrial IoT","authors":"Jayesh T P, Pandiaraj K, Arya Paul, Ranjeesh R Chandran, Prasanth P Menon","doi":"10.1109/ACCESS57397.2023.10199711","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199711","url":null,"abstract":"IIoT is the integration of conventional IoT principles into industrial operations. IIoT has a wide range of practical applications, including but not limited to supply chain management, connected cars, smart grids, smart cities, and smart homes. Regrettably, these systems are increasingly becoming the focus of cybercrime attacks. Machine learning is a promising technology for creating and implementing resilient security measures in IIoT networks. A new and innovative approach to detecting cyberattacks in the IIoT is proposed in this document, through the use of a hybrid machine classifier (HMC). The HMC model is a unique amalgamation of different ML models, such as K-nearest neighbor (KNN), extra trees (ET), gradient boosting (GB), AdaBoost (AB), linear discriminant analysis (LDA), ), naive Bayes (NB), support vector machine (SVM), random forest (RFlinear regression (LR), and classification and regression tree (CART). The DS2OS dataset is used to evaluate the proposed method's effectiveness. Several performance metrics, including recall, precision, accuracy, specificity, F1 score, detection rate, and ROC are used to evaluate the system's performance. The proposed model successfully distinguishes between normal and attack traffic, achieving an accuracy rate of 99.7% and 99.8%, respectively. To evaluate the effectiveness of the proposed method, its performance metrics were compared to those of other advanced attack detection algorithms. The outcomes demonstrated that the proposed model outperformed other ML and DL-based techniques","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132972168","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199820
Aruru Sai Kumar, M. Deekshana, V. Sreenivasulu, N. Kumari, G. Shanthi
Moore’s law indicates that several technological developments are currently being digested. Since switching from a simple MOSFET built with a single control gate to one with numerous control gates, the device’s controllability has significantly enhanced. In this paper, the device-level simulation of vertically stacked GAA nanosheet FET is performed for which the various geometrical variations are calibrated. This research Paper examines the impact of these geometrical variations on the performance of the device. The most prominent parameters like ION, IOFF, SS, DIBL, switching ratio, and Threshold voltage values are analyzed. For the device to be considered to have better performance ION should be maximum, IOFF should be minimum. Hence to obtain this the thickness of the nanosheet is varied on the scale of 5nm to 9nm and the width is varied from 10nm to 50nm. The device simulation and analysis are performed using the Visual TCAD - 3D Cogenda tool.
摩尔定律表明，目前有几种技术发展正在被消化。由于从具有单个控制栅极的简单MOSFET切换到具有多个控制栅极的MOSFET，该器件的可控性显着增强。本文对垂直堆叠的GAA纳米片场效应管进行了器件级模拟，并对各种几何变化进行了校准。本研究论文考察了这些几何变化对器件性能的影响。分析了离子、IOFF、SS、DIBL、开关比和阈值电压等最重要的参数。对于被认为具有较好性能的设备，ION应该是最大的，IOFF应该是最小的。因此，为了获得这一点，纳米片的厚度在5nm到9nm之间变化，宽度在10nm到50nm之间变化。利用visualtcad - 3D Cogenda工具对器件进行仿真和分析。
{"title":"Device Analysis of Vertically Stacked GAA Nanosheet FET at Advanced Technology Node","authors":"Aruru Sai Kumar, M. Deekshana, V. Sreenivasulu, N. Kumari, G. Shanthi","doi":"10.1109/ACCESS57397.2023.10199820","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199820","url":null,"abstract":"Moore’s law indicates that several technological developments are currently being digested. Since switching from a simple MOSFET built with a single control gate to one with numerous control gates, the device’s controllability has significantly enhanced. In this paper, the device-level simulation of vertically stacked GAA nanosheet FET is performed for which the various geometrical variations are calibrated. This research Paper examines the impact of these geometrical variations on the performance of the device. The most prominent parameters like ION, IOFF, SS, DIBL, switching ratio, and Threshold voltage values are analyzed. For the device to be considered to have better performance ION should be maximum, IOFF should be minimum. Hence to obtain this the thickness of the nanosheet is varied on the scale of 5nm to 9nm and the width is varied from 10nm to 50nm. The device simulation and analysis are performed using the Visual TCAD - 3D Cogenda tool.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133509128","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10201037
Diwaker, Kriti, Jyoti Rawat
Over past few decades Breast cancer (BC) has become more common and affecting females in early age, which is an alarming and challenging situation for researchers to provide methods to identify the disease in their early stage. This is the deadliest cancer among women and is alarming female fraternity becoming second leading cause of deaths. If the disease gets identified in their early stage it may leads to reduction in mortality rate. It may occur in cells that produce milk (lobules) or in the passages responsible for carrying milk (milk ducts). This paper presents the performance comparison of various pre-processing techniques based on the BreakHis dataset. The dataset used contains 1980 breast histopathological images including 625 benign and 1355 malignant cases. Initially the histopathological images have been pre-processed using techniques including contrast limited adaptive histogram equalization (CLAHE), contrast stretching (CS), histogram equalization (HE), and unsharp masking (UM) followed by feature extraction using 2D Gabor Wavelet Transform to obtain texture feature from both the categories like original and preprocessed images. Finally, support vector machine (SVM) classifies the images in two categories namely benign and malignant. The experiments results show that texture features computed using UM as pre-processing tool outperformed for making difference between benign and malignant images using breast histopathological images with a classification accuracy of 84.1 %.
{"title":"Assessing the Effect of Pre-processing Techniques on Classification of Breast Cancer using Histopathological Images","authors":"Diwaker, Kriti, Jyoti Rawat","doi":"10.1109/ACCESS57397.2023.10201037","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10201037","url":null,"abstract":"Over past few decades Breast cancer (BC) has become more common and affecting females in early age, which is an alarming and challenging situation for researchers to provide methods to identify the disease in their early stage. This is the deadliest cancer among women and is alarming female fraternity becoming second leading cause of deaths. If the disease gets identified in their early stage it may leads to reduction in mortality rate. It may occur in cells that produce milk (lobules) or in the passages responsible for carrying milk (milk ducts). This paper presents the performance comparison of various pre-processing techniques based on the BreakHis dataset. The dataset used contains 1980 breast histopathological images including 625 benign and 1355 malignant cases. Initially the histopathological images have been pre-processed using techniques including contrast limited adaptive histogram equalization (CLAHE), contrast stretching (CS), histogram equalization (HE), and unsharp masking (UM) followed by feature extraction using 2D Gabor Wavelet Transform to obtain texture feature from both the categories like original and preprocessed images. Finally, support vector machine (SVM) classifies the images in two categories namely benign and malignant. The experiments results show that texture features computed using UM as pre-processing tool outperformed for making difference between benign and malignant images using breast histopathological images with a classification accuracy of 84.1 %.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126764603","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200446
D. Kumar, Y. Kumar, V. Kukreja, Ankit Bansal, Abhishek Bhattacherjee
A worldwide industry that provides food, business, and employment opportunities, agriculture is a key component of human life. Despite this, wheat is one of the most common armed crops and the production rate harms wheat yield every year. In this paper, a prediction method for wheat yield has been calculated with different environmental impact assessment parameters. Predictors of data are a predictive approach that helps to categorize the data based on the different grouping patterns. Exploratory data analysis (EDA) and Linear discriminant analysis (LDA) are very effective approaches for grouping the data. The main aim of this paper is to predict the wheat yield prediction through EDA, decision tree, random forest regressor, ensemble learning, and LDA to maximize accuracy. Different environmental impacts parameters such as average rainfall, average temperature, and pesticides have been used to predict the wheat yield. Also, ensemble learning has been used for the prediction and analysis of the model through the decision tree and random forest regressor. Moreover, the LDA has been used to classify the wheat yield dataset by applying a reduction approach of LDA. During wheat yield prediction, the decision tree achieves 0.025 losses in training time. Also, the performance of LDA and EDA has been calculated through squared error functions. During wheat yield prediction through EDA with environmental impact parameters, the Root means squared error (RMSE) is 18245.27 while the value of Mean absolute error (MAE) is 12334.75. Furthermore, the work of LDA has presented by supporting the data visualization through different graphs using pandas and Matplotlib library. This study provides the data reduction predictors approach to the wheat yield and explains the data-preprocessing technique used along with EDA and LDA for wheat yield prediction in different environmental impact parameters.
{"title":"High Performance EDA and LDA Analysis: An Application for Wheat Yield Estimation","authors":"D. Kumar, Y. Kumar, V. Kukreja, Ankit Bansal, Abhishek Bhattacherjee","doi":"10.1109/ACCESS57397.2023.10200446","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200446","url":null,"abstract":"A worldwide industry that provides food, business, and employment opportunities, agriculture is a key component of human life. Despite this, wheat is one of the most common armed crops and the production rate harms wheat yield every year. In this paper, a prediction method for wheat yield has been calculated with different environmental impact assessment parameters. Predictors of data are a predictive approach that helps to categorize the data based on the different grouping patterns. Exploratory data analysis (EDA) and Linear discriminant analysis (LDA) are very effective approaches for grouping the data. The main aim of this paper is to predict the wheat yield prediction through EDA, decision tree, random forest regressor, ensemble learning, and LDA to maximize accuracy. Different environmental impacts parameters such as average rainfall, average temperature, and pesticides have been used to predict the wheat yield. Also, ensemble learning has been used for the prediction and analysis of the model through the decision tree and random forest regressor. Moreover, the LDA has been used to classify the wheat yield dataset by applying a reduction approach of LDA. During wheat yield prediction, the decision tree achieves 0.025 losses in training time. Also, the performance of LDA and EDA has been calculated through squared error functions. During wheat yield prediction through EDA with environmental impact parameters, the Root means squared error (RMSE) is 18245.27 while the value of Mean absolute error (MAE) is 12334.75. Furthermore, the work of LDA has presented by supporting the data visualization through different graphs using pandas and Matplotlib library. This study provides the data reduction predictors approach to the wheat yield and explains the data-preprocessing technique used along with EDA and LDA for wheat yield prediction in different environmental impact parameters.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130832066","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200536
Rajasree R, C. Latha, Sujni Paul, Appu M, A. N
The scientific community has shown considerable interest in plant disease detection and classification based on deep learning. In order to address these research gaps, this study proposes an optimized, fine-tuned model for the detection of Cassava Brown Streak Diseases. Casѕava is a vital Thai manufacturing harvest. Thailand is a pioneer in cassava production; therefore, a lot of cassava has been produced and exported. But, caѕsava infection could be the key to cut back caѕsava creation and immediately has an effect on growers' earnings. This research is to develop a model using an effective deep learning algorithm for cassava leaf disease detection. We split the classification into two phases, with Model1 and Model2. First model is used to do the cassava disease classification and second model for identifying the Cassava Brown Streak Virus Disease using VGGNet, AlexNet and Faster R-CNN algorithm. Furthermore, data augmentation techniques are employed during network training to improve the performance of the proposed network. The proposed model has been evaluated its performance using accuracy and confusion matrix. The experimental results demonstrates that our approach can accurately classify Cassava Brown Streak Diseases with an accuracy of 96% using Faster R-CNN.
{"title":"An optimized Faster R-CNN model for Cassava Brown Streak Disease Classification","authors":"Rajasree R, C. Latha, Sujni Paul, Appu M, A. N","doi":"10.1109/ACCESS57397.2023.10200536","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200536","url":null,"abstract":"The scientific community has shown considerable interest in plant disease detection and classification based on deep learning. In order to address these research gaps, this study proposes an optimized, fine-tuned model for the detection of Cassava Brown Streak Diseases. Casѕava is a vital Thai manufacturing harvest. Thailand is a pioneer in cassava production; therefore, a lot of cassava has been produced and exported. But, caѕsava infection could be the key to cut back caѕsava creation and immediately has an effect on growers' earnings. This research is to develop a model using an effective deep learning algorithm for cassava leaf disease detection. We split the classification into two phases, with Model1 and Model2. First model is used to do the cassava disease classification and second model for identifying the Cassava Brown Streak Virus Disease using VGGNet, AlexNet and Faster R-CNN algorithm. Furthermore, data augmentation techniques are employed during network training to improve the performance of the proposed network. The proposed model has been evaluated its performance using accuracy and confusion matrix. The experimental results demonstrates that our approach can accurately classify Cassava Brown Streak Diseases with an accuracy of 96% using Faster R-CNN.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121852263","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 : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200442
G. Shanthi, Aruru Sai Kumar, Md Masood Hasan, H. Tanuja, Ch. Yashwanth
Multiplication and Division Operations have been extensively used as basic elements when designing a system for advanced applications. In today’s digital Era speed and area are the main constraints while implementing the digital systems. A crucial part of the digital design is played by addition operations. Many processors use the Carry Select Adder (CSA), one of the faster adders. To improve the efficiency of the adder used in various applications different architectures can be adopted. It is well known that processors in the semiconductor industry perform millions of work functions per second. Performance speed must therefore be taken into account as one of the major requirements while developing a multiplier. In this paper, we offer a method for designing FIR filters that makes use of carry-select adders and compressor-based multipliers. The performance of the proposed FIR filter outperformed the power and delay compared with existed FIR filter.
{"title":"An Efficient and High Speed FIR Filter using BEC with MUX Technique","authors":"G. Shanthi, Aruru Sai Kumar, Md Masood Hasan, H. Tanuja, Ch. Yashwanth","doi":"10.1109/ACCESS57397.2023.10200442","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200442","url":null,"abstract":"Multiplication and Division Operations have been extensively used as basic elements when designing a system for advanced applications. In today’s digital Era speed and area are the main constraints while implementing the digital systems. A crucial part of the digital design is played by addition operations. Many processors use the Carry Select Adder (CSA), one of the faster adders. To improve the efficiency of the adder used in various applications different architectures can be adopted. It is well known that processors in the semiconductor industry perform millions of work functions per second. Performance speed must therefore be taken into account as one of the major requirements while developing a multiplier. In this paper, we offer a method for designing FIR filters that makes use of carry-select adders and compressor-based multipliers. The performance of the proposed FIR filter outperformed the power and delay compared with existed FIR filter.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124966182","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：