Objectives: In this study, a model was developed to predict the compressive strength of High Strength Concrete (HSC) mixed with silica fume using Response Surface Methodology (RSM). This study investigated the effects of cement, water, Silica Fume (SF), Coarse Aggregate (CA), and silica fume-cement ratio (SF/C) on the 28-day compressive strength of HSC. Silica fume is added with varying amounts of SF (5% to 25%) to cement content. Methods: Response surface methodology (RSM) was performed to investigate the influence of independent variables on the compressive strength of HSC. Findings: Analysis of the response surface plot reveals a remarkably low error percentage of less than 5%. This reveals a high degree of confidence (95%) in the model's accuracy. This study yielded a coefficient of determination (R2) of 0. 9968. It is observed negligible deviation between predicted and actual 28-day compressive strength values, indicating high model accuracy. Novelty: The predicted equation is reasonably predicting the compressive strength of high strength concrete. Keywords: High strength concrete, Response surface methodology, Silica fume, Compressive strength, Prediction model
{"title":"Prediction of Compressive Strength of Silica Fume Blended High Strength Concrete Using Response Surface Methodology Approach","authors":"D. Nirosha, C. Sashidhar, K. Narasimhulu","doi":"10.17485/ijst/v17i9.45","DOIUrl":"https://doi.org/10.17485/ijst/v17i9.45","url":null,"abstract":"Objectives: In this study, a model was developed to predict the compressive strength of High Strength Concrete (HSC) mixed with silica fume using Response Surface Methodology (RSM). This study investigated the effects of cement, water, Silica Fume (SF), Coarse Aggregate (CA), and silica fume-cement ratio (SF/C) on the 28-day compressive strength of HSC. Silica fume is added with varying amounts of SF (5% to 25%) to cement content. Methods: Response surface methodology (RSM) was performed to investigate the influence of independent variables on the compressive strength of HSC. Findings: Analysis of the response surface plot reveals a remarkably low error percentage of less than 5%. This reveals a high degree of confidence (95%) in the model's accuracy. This study yielded a coefficient of determination (R2) of 0. 9968. It is observed negligible deviation between predicted and actual 28-day compressive strength values, indicating high model accuracy. Novelty: The predicted equation is reasonably predicting the compressive strength of high strength concrete. Keywords: High strength concrete, Response surface methodology, Silica fume, Compressive strength, Prediction model","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"9 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140426682","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 : 2024-02-27DOI: 10.17485/ijst/v17i9.2938
Neha Garg, Anant Patel, Menakshi Pachori
Objectives: In this article, we addressed the problem of estimation of the finite population proportion under the Probability Proportional to Size (PPS) sampling technique, when the complete information is unavailable due to the presence of non-response. We developed calibrated estimators of the population proportion under PPS sampling in the presence of nonresponse based on the availability of auxiliary information. Methods: The expressions for the mean squared errors of the suggested estimators were developed to the first order of approximation. The developed estimators of the population proportion are compared with the design-based Horvitz-Thompson estimator and Horvitz-Thompson type calibration estimator which were obtained on the complete response units along with the design-based Hansen and Hurwitz type estimator in the presence of non-response. A Simulation study has also been conducted to support the performance of the developed estimators of population proportion with the help of two real datasets, by computing Percentage Absolute Relative Bias (%ARB) and Percentage Relative Root Mean Squared Error (%RRMSE) using R software. Findings: The simulation study supported the performance of the developed estimators of the finite population proportion based on %ARB and %RRMSE. The proposed calibration estimators of population proportion are more efficient than the other considered estimators in the presence of non-response. Novelty: The proposed new calibrated estimators have practical implications in the estimation of finite population proportions. Keywords: Auxiliary information, Calibration Approach, Nonresponse, Population proportion, PPS sampling
{"title":"Calibration Estimation of Population Proportion in Probability Proportional to Size Sampling in the Presence of Non-Response","authors":"Neha Garg, Anant Patel, Menakshi Pachori","doi":"10.17485/ijst/v17i9.2938","DOIUrl":"https://doi.org/10.17485/ijst/v17i9.2938","url":null,"abstract":"Objectives: In this article, we addressed the problem of estimation of the finite population proportion under the Probability Proportional to Size (PPS) sampling technique, when the complete information is unavailable due to the presence of non-response. We developed calibrated estimators of the population proportion under PPS sampling in the presence of nonresponse based on the availability of auxiliary information. Methods: The expressions for the mean squared errors of the suggested estimators were developed to the first order of approximation. The developed estimators of the population proportion are compared with the design-based Horvitz-Thompson estimator and Horvitz-Thompson type calibration estimator which were obtained on the complete response units along with the design-based Hansen and Hurwitz type estimator in the presence of non-response. A Simulation study has also been conducted to support the performance of the developed estimators of population proportion with the help of two real datasets, by computing Percentage Absolute Relative Bias (%ARB) and Percentage Relative Root Mean Squared Error (%RRMSE) using R software. Findings: The simulation study supported the performance of the developed estimators of the finite population proportion based on %ARB and %RRMSE. The proposed calibration estimators of population proportion are more efficient than the other considered estimators in the presence of non-response. Novelty: The proposed new calibrated estimators have practical implications in the estimation of finite population proportions. Keywords: Auxiliary information, Calibration Approach, Nonresponse, Population proportion, PPS sampling","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"281 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140427864","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}
Objectives: The present work examines the viability of using industrial solid waste, like cinder, to create lightweight aggregate concrete. Utilizing cinder aggregate as a substitute material for coarse aggregate in producing concrete not only helps in the conservation of natural resource but also provides a feasible solution for solid waste management. Method: The mechanical characteristics of cinder based lightweight concrete were improved by the inclusion of polypropylene fibre as micro-reinforcement, in volume proportions of 0.1%, 0.2%, 0.3%, and 0.4%. The laboratory tests that were conducted on the polypropylene fibre reinforced cinder based lightweight concrete included compressive strength test on cube specimen and cylinder specimen, flexural strength test on prism specimen and modulus of elasticity test on cylinder specimen. Findings: The findings show that cinder aggregate can be satisfactorily utilized as an alternate material to coarse aggregate in the production of lightweight concrete. It has been found that 0.3% of polypropylene fibre was the ideal dosage of micro-reinforcement that can be incorporated in lightweight concrete. Novelty: Further, a multiple linear regression (MLR) model was suggested to evaluate the performance parameters of the fibre-reinforced lightweight concrete, providing an alternative to the time and material consuming experimental works. Scatter plots and Statistical indicators such as R2, RMSE and MAPE indicated that the model demonstrated a strong correlation between the predicted values and the experimental results. Keywords: Cinder aggregate, Lightweight concrete, Mechanical characteristics, Micro reinforcement, Regression model
{"title":"Material Performance Evaluation of Cinder Based Light Weight Concrete with Micro-reinforcement","authors":"K. Sadhana, K. Suguna, P. Raghunath","doi":"10.17485/ijst/v17i9.84","DOIUrl":"https://doi.org/10.17485/ijst/v17i9.84","url":null,"abstract":"Objectives: The present work examines the viability of using industrial solid waste, like cinder, to create lightweight aggregate concrete. Utilizing cinder aggregate as a substitute material for coarse aggregate in producing concrete not only helps in the conservation of natural resource but also provides a feasible solution for solid waste management. Method: The mechanical characteristics of cinder based lightweight concrete were improved by the inclusion of polypropylene fibre as micro-reinforcement, in volume proportions of 0.1%, 0.2%, 0.3%, and 0.4%. The laboratory tests that were conducted on the polypropylene fibre reinforced cinder based lightweight concrete included compressive strength test on cube specimen and cylinder specimen, flexural strength test on prism specimen and modulus of elasticity test on cylinder specimen. Findings: The findings show that cinder aggregate can be satisfactorily utilized as an alternate material to coarse aggregate in the production of lightweight concrete. It has been found that 0.3% of polypropylene fibre was the ideal dosage of micro-reinforcement that can be incorporated in lightweight concrete. Novelty: Further, a multiple linear regression (MLR) model was suggested to evaluate the performance parameters of the fibre-reinforced lightweight concrete, providing an alternative to the time and material consuming experimental works. Scatter plots and Statistical indicators such as R2, RMSE and MAPE indicated that the model demonstrated a strong correlation between the predicted values and the experimental results. Keywords: Cinder aggregate, Lightweight concrete, Mechanical characteristics, Micro reinforcement, Regression model","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"2 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140424986","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}
Objectives: This study mainly focuses on different steel fibres content behaviour, when exposed to various temperature. Methods: In this experimental investigation, the prism specimen of size 500 x 100 x 100 mm with steel fibre content of 0% and 1.5% were exposed to temperature of 100 °C, 300ºC, 500 °C and 700 °C. The Temperature-Time graph was obtained as an outcome of the experiment. Color change and weight loss of specimens at different temperatures was assessed. Findings: The RSM weight loss prediction model has been proposed for specimen before and after exposure of temperature. Color changes at 100 °C, 300 °C, 500 °C and 700 °C was observed to be no color change, red, grey and whitish grey respectively. Mass loss of 0% steel fibre concrete prism at 100 °C, 300 °C, 500 °C and 700 °C was found to be 2.17%, 4.33%, 4.24% and 6.55% respectively. Mass loss of 0% steel fibre concrete prism at 100 °C, 300 °C, 500 °C and 700 °C was found to be 0.61%, 4.51%, 5.66%, and 6.27% respectively. Novelty: Very few studies have been conducted on the combination of color change and weight loss of the specimen. Weight loss prediction model is the novelty of this study. The RSM prediction model clearly indicates that the response values are 97.21% and 96.12%, where the model is fit for weight of specimen before and after exposure to temperature respectively. Keywords: SFRC, Color change, weight loss, RSM, Temperature
{"title":"Experimental Investigation on Color Change and Weight Loss of Steel Fibre Reinforced Concrete when Exposed to Elevated Temperature","authors":"J. Jessie, K. K. Gaayathri, R. Sivaji, N. Lavanya","doi":"10.17485/ijst/v17i9.47","DOIUrl":"https://doi.org/10.17485/ijst/v17i9.47","url":null,"abstract":"Objectives: This study mainly focuses on different steel fibres content behaviour, when exposed to various temperature. Methods: In this experimental investigation, the prism specimen of size 500 x 100 x 100 mm with steel fibre content of 0% and 1.5% were exposed to temperature of 100 °C, 300ºC, 500 °C and 700 °C. The Temperature-Time graph was obtained as an outcome of the experiment. Color change and weight loss of specimens at different temperatures was assessed. Findings: The RSM weight loss prediction model has been proposed for specimen before and after exposure of temperature. Color changes at 100 °C, 300 °C, 500 °C and 700 °C was observed to be no color change, red, grey and whitish grey respectively. Mass loss of 0% steel fibre concrete prism at 100 °C, 300 °C, 500 °C and 700 °C was found to be 2.17%, 4.33%, 4.24% and 6.55% respectively. Mass loss of 0% steel fibre concrete prism at 100 °C, 300 °C, 500 °C and 700 °C was found to be 0.61%, 4.51%, 5.66%, and 6.27% respectively. Novelty: Very few studies have been conducted on the combination of color change and weight loss of the specimen. Weight loss prediction model is the novelty of this study. The RSM prediction model clearly indicates that the response values are 97.21% and 96.12%, where the model is fit for weight of specimen before and after exposure to temperature respectively. Keywords: SFRC, Color change, weight loss, RSM, Temperature","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"26 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140426453","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 : 2024-02-15DOI: 10.17485/ijst/v17i7.3017
Radha Krishna Jana, Dharmpal Singh, Saikat Maity, Hrithik Paul
Objectives: The objective of this study is to introduce a hybrid model for analyzing the people sentiment on covid-19 tweets. Methods: We used a total no. of 27,500 datasets, 70% of the data sets for training and reserved the other 30% for testing. Due to this separation 19,250 samples are used for training, the remaining 8,250 were used to evaluate the accuracy of the test. This paper proposes a technique for sentiment analysis that integrates deep learning, genetic algorithms (GA), and social media sentiment. For more accuracy and performance, we here suggested a hybrid genetic algorithm-based model. A hybrid model is created by assembling the LSTM model and providing it to the genetic algorithm architecture. Findings: LSTM with a genetic model better than LSTM without genetic model. The accuracy of our suggested model is 96.40%. Novelty : The accuracy of the LSTM model for sentiment analysis is 91%. The accuracy of the proposed model is 96.40%. The proposed model is more accurate for sentiment prediction. Keywords: Social network perception, Crossover, Mutation, LSTM, NLP, GA
{"title":"A Hybrid Approach to Analyse the Public Sentiment on Covid-19 Tweets","authors":"Radha Krishna Jana, Dharmpal Singh, Saikat Maity, Hrithik Paul","doi":"10.17485/ijst/v17i7.3017","DOIUrl":"https://doi.org/10.17485/ijst/v17i7.3017","url":null,"abstract":"Objectives: The objective of this study is to introduce a hybrid model for analyzing the people sentiment on covid-19 tweets. Methods: We used a total no. of 27,500 datasets, 70% of the data sets for training and reserved the other 30% for testing. Due to this separation 19,250 samples are used for training, the remaining 8,250 were used to evaluate the accuracy of the test. This paper proposes a technique for sentiment analysis that integrates deep learning, genetic algorithms (GA), and social media sentiment. For more accuracy and performance, we here suggested a hybrid genetic algorithm-based model. A hybrid model is created by assembling the LSTM model and providing it to the genetic algorithm architecture. Findings: LSTM with a genetic model better than LSTM without genetic model. The accuracy of our suggested model is 96.40%. Novelty : The accuracy of the LSTM model for sentiment analysis is 91%. The accuracy of the proposed model is 96.40%. The proposed model is more accurate for sentiment prediction. Keywords: Social network perception, Crossover, Mutation, LSTM, NLP, GA","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"12 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139776408","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 : 2024-02-15DOI: 10.17485/ijst/v17i7.2670
Rinkal Shah, Jyoti Pareek
Objectives: To develop a deep learning method using camera images that can effectively detect the preliminary phase of oral cancer, which has a high rate of morbidity and mortality and is a significant public health concern. If left untreated, it can result in severe deformities and negatively affect the patient's quality of life, both physically and mentally. Early detection is crucial owing to the rapid spread of the disease, where biopsy is the only option left. Therefore, it is essential to identify malignancies swiftly to prevent disease progression non-invasively. Methods: Three different scenarios are used in this study to analyze samples: CNN architecture, stratified K-fold validation, and transfer learning. For automated disease identification on binary datasets (normal vs. ulcer) and multiclass datasets (normal vs. ulcer vs. Leukoplakia), camera images are pre-processed with data augmentation. As a feature extractor in the model, transfer learning is used with pre-defined networks such as VGG19, InceptionNET, EfficientNET, and MobileNET weights. Findings: Using the proposed CNN architecture, the F1 score for image classification was 78% and 74% for photos showing hygienic mouths or ulcers, and 83%, 87%, and 84% for images showing normal mouths, ulcers, and leukoplakia. Using stratified 3-fold validation, the results were improved to 97%, and an EfficientNET achieves the highest results in a binary F1 score of 98% and a classification with multiple classes F1 scores of 98%, 87%, and 91%, respectively. Novelty: Previous studies have mostly concentrated on differentiating oral potentially malignant diseases (OPMD) from oral squamous cell carcinoma (OSCC) or on discriminating between cancerous and non-cancerous tissues. The objective is to diagnose patients with non-invasive procedures to classify ulcers, healthy mouths, or precancerous type "Leukoplakia" without requiring them to visit a doctor. Keywords: CNN, Transfer Learning, Oral Cancer, Ulcer, Leukoplakia, Stratified K-fold validation
目的开发一种利用摄像头图像的深度学习方法，该方法可有效检测口腔癌的初期阶段，口腔癌的发病率和死亡率都很高，是一个重大的公共卫生问题。如果不及时治疗，口腔癌会导致严重畸形，并对患者的身心生活质量造成负面影响。由于疾病传播迅速，活检是唯一的选择，因此早期发现至关重要。因此，必须迅速识别恶性肿瘤，以非侵入性的方式防止疾病恶化。方法：本研究采用了三种不同的方案来分析样本：CNN 架构、分层 K 折验证和迁移学习。为了在二元数据集（正常 vs. 溃疡）和多类数据集（正常 vs. 溃疡 vs. 白斑病）上自动识别疾病，对摄像头图像进行了数据增强预处理。作为模型中的特征提取器，迁移学习使用了预先定义的网络，如 VGG19、InceptionNET、EfficientNET 和 MobileNET 权重。研究结果使用提出的 CNN 架构，对显示卫生口腔或溃疡的照片进行图像分类的 F1 分数分别为 78% 和 74%，对显示正常口腔、溃疡和白斑病的图像进行分类的 F1 分数分别为 83%、87% 和 84%。通过分层 3 倍验证，结果提高到 97%，EfficientNET 的二元 F1 得分达到 98%，多类分类 F1 得分分别为 98%、87% 和 91%，取得了最高成绩。新颖性：以往的研究大多集中于区分口腔潜在恶性疾病（OPMD）和口腔鳞状细胞癌（OSCC），或区分癌组织和非癌组织。本研究的目的是通过非侵入性程序对患者进行诊断，对溃疡、健康口腔或癌前病变类型 "白斑病 "进行分类，而无需患者就医。关键词CNN、迁移学习、口腔癌、溃疡、白斑病、分层 K 倍验证
{"title":"Non-invasive Primary Screening of Oral Lesions into Binary and Multi Class using Convolutional Neural Network, Stratified K-fold Validation and Transfer Learning","authors":"Rinkal Shah, Jyoti Pareek","doi":"10.17485/ijst/v17i7.2670","DOIUrl":"https://doi.org/10.17485/ijst/v17i7.2670","url":null,"abstract":"Objectives: To develop a deep learning method using camera images that can effectively detect the preliminary phase of oral cancer, which has a high rate of morbidity and mortality and is a significant public health concern. If left untreated, it can result in severe deformities and negatively affect the patient's quality of life, both physically and mentally. Early detection is crucial owing to the rapid spread of the disease, where biopsy is the only option left. Therefore, it is essential to identify malignancies swiftly to prevent disease progression non-invasively. Methods: Three different scenarios are used in this study to analyze samples: CNN architecture, stratified K-fold validation, and transfer learning. For automated disease identification on binary datasets (normal vs. ulcer) and multiclass datasets (normal vs. ulcer vs. Leukoplakia), camera images are pre-processed with data augmentation. As a feature extractor in the model, transfer learning is used with pre-defined networks such as VGG19, InceptionNET, EfficientNET, and MobileNET weights. Findings: Using the proposed CNN architecture, the F1 score for image classification was 78% and 74% for photos showing hygienic mouths or ulcers, and 83%, 87%, and 84% for images showing normal mouths, ulcers, and leukoplakia. Using stratified 3-fold validation, the results were improved to 97%, and an EfficientNET achieves the highest results in a binary F1 score of 98% and a classification with multiple classes F1 scores of 98%, 87%, and 91%, respectively. Novelty: Previous studies have mostly concentrated on differentiating oral potentially malignant diseases (OPMD) from oral squamous cell carcinoma (OSCC) or on discriminating between cancerous and non-cancerous tissues. The objective is to diagnose patients with non-invasive procedures to classify ulcers, healthy mouths, or precancerous type \"Leukoplakia\" without requiring them to visit a doctor. Keywords: CNN, Transfer Learning, Oral Cancer, Ulcer, Leukoplakia, Stratified K-fold validation","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"36 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139776023","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 : 2024-02-15DOI: 10.17485/ijst/v17i7.3076
Abhilipsa Sahoo, Kaushika Patel
Objectives: To develop an inverse design model for transistors, utilizing machine learning algorithms to predict key design parameters specifically, the length and width based on specified gain and bandwidth requirements. And to conduct a comprehensive comparative analysis with existing literature, evaluating the efficacy and novelty of the proposed model in the context of semiconductor engineering challenges and methodologies. Methods: The comprehensive dataset, comprising 30,000 values generated through LTspice simulations, forms the basis for training the machine learning model. Utilizing a Random Forest regressor as the base model and a multi-output regressor as the main model, the project involves extensive data analysis, model development, and iterative fine-tuning. Findings: The outcomes demonstrate the efficacy of the developed model in accurately predicting transistor dimensions. Performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared, highlight the precision of the model in fulfilling the specified objectives. Novelty: This study introduces a novel approach to semiconductor device design optimization, showcasing the potential of machine learning to streamline the inverse design process. The use of a multi-output regressor, feature engineering, and fine-tuning through log transformation contribute to the innovative nature of the developed model. Keywords: Machine Learning (ML) model, Random Forest regressor, multioutput regressor, Feature engineering, Finetuning
目标：开发晶体管反向设计模型，利用机器学习算法预测关键设计参数，特别是基于指定增益和带宽要求的长度和宽度。并与现有文献进行全面的比较分析，根据半导体工程面临的挑战和方法，评估所提出模型的有效性和新颖性。研究方法由 LTspice 仿真生成的 30,000 个值组成的综合数据集是训练机器学习模型的基础。利用随机森林回归器作为基础模型，多输出回归器作为主要模型，该项目涉及广泛的数据分析、模型开发和迭代微调。研究结果结果表明，所开发的模型在准确预测晶体管尺寸方面非常有效。包括平均绝对误差 (MAE)、平均平方误差 (MSE) 和 R 平方在内的性能指标突出显示了模型在实现特定目标方面的精确性。新颖性：这项研究为半导体器件设计优化引入了一种新方法，展示了机器学习简化反向设计过程的潜力。多输出回归器、特征工程和通过对数变换进行微调等方法的使用为所开发模型的创新性做出了贡献。关键词机器学习（ML）模型、随机森林回归器、多输出回归器、特征工程、微调
{"title":"Machine Learning-based Inverse Design Model of a Transistor","authors":"Abhilipsa Sahoo, Kaushika Patel","doi":"10.17485/ijst/v17i7.3076","DOIUrl":"https://doi.org/10.17485/ijst/v17i7.3076","url":null,"abstract":"Objectives: To develop an inverse design model for transistors, utilizing machine learning algorithms to predict key design parameters specifically, the length and width based on specified gain and bandwidth requirements. And to conduct a comprehensive comparative analysis with existing literature, evaluating the efficacy and novelty of the proposed model in the context of semiconductor engineering challenges and methodologies. Methods: The comprehensive dataset, comprising 30,000 values generated through LTspice simulations, forms the basis for training the machine learning model. Utilizing a Random Forest regressor as the base model and a multi-output regressor as the main model, the project involves extensive data analysis, model development, and iterative fine-tuning. Findings: The outcomes demonstrate the efficacy of the developed model in accurately predicting transistor dimensions. Performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-squared, highlight the precision of the model in fulfilling the specified objectives. Novelty: This study introduces a novel approach to semiconductor device design optimization, showcasing the potential of machine learning to streamline the inverse design process. The use of a multi-output regressor, feature engineering, and fine-tuning through log transformation contribute to the innovative nature of the developed model. Keywords: Machine Learning (ML) model, Random Forest regressor, multioutput regressor, Feature engineering, Finetuning","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"115 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139834907","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 : 2024-02-15DOI: 10.17485/ijst/v17i7.2836
B. V. Poornima, S. Srinath
Objectives: The objective of this paper is to introduce and demonstrate an innovative approach for the recognition of Indian sign language gestures, with a focus on bridging communication gap between the deaf and hearing communities. The goal is to contribute to the development of effective tools and technologies that facilitate seamless communication between individuals using sign language and the people with no knowledge about sign language. Methods: The methodology consists of three key steps. First, data pre-processing involves resizing and contours extraction. Next, feature extraction employs Fourier descriptors for frequency domain analysis and gray-level-co-occurrence matrix for spatial domain analysis. Finally, various machine learning models including SVM, Random Forest, Logistic Regression, K-Nearest Neighbor and Naive Bayes are trained on a standard dataset. Findings: In our controlled experimental setup, we applied a diverse set of machine learning classifiers to evaluate the proposed approach for gesture recognition. Among the classifiers tested, K-Nearest Neighbors demonstrated the highest accuracy, achieving 99.82%. To validate the robustness of our approach, we employed k-fold cross-validation with 5 folds. Novelty: This study presents an innovative method for sign language recognition by employing a dual-domain fusion strategy that prominently emphasizes the frequency domain. Through the integration of Fourier descriptors, the research conducts a detailed frequency domain analysis to characterize the contour shapes of sign language gestures. The synergy with gray-level co-occurrence matrix texture features in the spatial domain analysis, contributes to the creation of a comprehensive feature vector. The proposed approach ensures a thorough exploration of gesture features, there by advancing the precision and efficacy of sign language recognition. Keywords: Indian Sign Language (ISL), Sign Language Recognition (SLR), Frequency domain, Spatial domain, Fourier descriptors, Gray level cooccurrence matrix (GLCM), K Fold
{"title":"Frequency and Spatial Domain-Based Approaches for Recognition of Indian Sign Language Gestures","authors":"B. V. Poornima, S. Srinath","doi":"10.17485/ijst/v17i7.2836","DOIUrl":"https://doi.org/10.17485/ijst/v17i7.2836","url":null,"abstract":"Objectives: The objective of this paper is to introduce and demonstrate an innovative approach for the recognition of Indian sign language gestures, with a focus on bridging communication gap between the deaf and hearing communities. The goal is to contribute to the development of effective tools and technologies that facilitate seamless communication between individuals using sign language and the people with no knowledge about sign language. Methods: The methodology consists of three key steps. First, data pre-processing involves resizing and contours extraction. Next, feature extraction employs Fourier descriptors for frequency domain analysis and gray-level-co-occurrence matrix for spatial domain analysis. Finally, various machine learning models including SVM, Random Forest, Logistic Regression, K-Nearest Neighbor and Naive Bayes are trained on a standard dataset. Findings: In our controlled experimental setup, we applied a diverse set of machine learning classifiers to evaluate the proposed approach for gesture recognition. Among the classifiers tested, K-Nearest Neighbors demonstrated the highest accuracy, achieving 99.82%. To validate the robustness of our approach, we employed k-fold cross-validation with 5 folds. Novelty: This study presents an innovative method for sign language recognition by employing a dual-domain fusion strategy that prominently emphasizes the frequency domain. Through the integration of Fourier descriptors, the research conducts a detailed frequency domain analysis to characterize the contour shapes of sign language gestures. The synergy with gray-level co-occurrence matrix texture features in the spatial domain analysis, contributes to the creation of a comprehensive feature vector. The proposed approach ensures a thorough exploration of gesture features, there by advancing the precision and efficacy of sign language recognition. Keywords: Indian Sign Language (ISL), Sign Language Recognition (SLR), Frequency domain, Spatial domain, Fourier descriptors, Gray level cooccurrence matrix (GLCM), K Fold","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"210 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139833536","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 : 2024-02-15DOI: 10.17485/ijst/v17i7.2828
M Anil Kumar, V. Srinivasan, P. R. Raju
Objectives: The aim of this study is to examine the mechanical and microstructural properties of functionally graded material (FGM) composites based on magnesium (Mg). Magnesium alloys are commonly employed in the development of biomaterials for implant applications owing to their favorable corrosion properties. The research objective is to study the microstructural and mechanical properties and produce Zn/Mo reinforced functionally graded magnesium composites using the centrifugal casting. Methods: A triple layered cylindrical shaped Mg based functionally graded material (FGM) was fabricated through a centrifugal process from (Mg (80%) +Zn (10%) + Mo (10%) alloy. The developed FGMs have been analyzed for their mechanical and microstructural characteristics. The microstructure was analyzed via the OM AND SEM microscope. It is identified that denser particle molybdenum (Mo) have influenced the mechanical and microstructural characteristics. Findings: Results recommend that, all the three layered testing’s, Mg (80%) +Zn (10%) + Mo (10%) composite exhibited favorable mechanical and microstructural properties. It is identified that denser particle of Mo which is influenced the microstructural characteristics. The alteration in micro hardness in the direction of centrifugal force is observed, and it is perceived that top surface has higher hardness as compared to the middle and bottom region. The flexural strength of top surface sample is 254 MPa, which is 10% greater than middle surface sample and 12.36% greater than bottom surface sample. Compressive strength of 385 MPa, surpassing the middle surface sample by 17.11% and the bottom surface sample by 19.36%. Novelty: In this study, a novel three-layered centrifugal casting technique was devised. Owing to its rapid degradability, the anticipated duration of the implants within the human body is significantly shorter in comparison to alternative biomaterials such as Titanium and Stainless steel. Furthermore, the findings from the conducted tests strongly advocate for the utilization of this technique in biomedical implantations. Keywords: Functionally graded material (FGM), Centrifugal casting, Mechanical properties, Microstructural behavior and bioimplants
{"title":"Microstructural and Mechanical Characterization of the Mg Based Functionally Graded Material Fabricated through Centrifugal Casting Process","authors":"M Anil Kumar, V. Srinivasan, P. R. Raju","doi":"10.17485/ijst/v17i7.2828","DOIUrl":"https://doi.org/10.17485/ijst/v17i7.2828","url":null,"abstract":"Objectives: The aim of this study is to examine the mechanical and microstructural properties of functionally graded material (FGM) composites based on magnesium (Mg). Magnesium alloys are commonly employed in the development of biomaterials for implant applications owing to their favorable corrosion properties. The research objective is to study the microstructural and mechanical properties and produce Zn/Mo reinforced functionally graded magnesium composites using the centrifugal casting. Methods: A triple layered cylindrical shaped Mg based functionally graded material (FGM) was fabricated through a centrifugal process from (Mg (80%) +Zn (10%) + Mo (10%) alloy. The developed FGMs have been analyzed for their mechanical and microstructural characteristics. The microstructure was analyzed via the OM AND SEM microscope. It is identified that denser particle molybdenum (Mo) have influenced the mechanical and microstructural characteristics. Findings: Results recommend that, all the three layered testing’s, Mg (80%) +Zn (10%) + Mo (10%) composite exhibited favorable mechanical and microstructural properties. It is identified that denser particle of Mo which is influenced the microstructural characteristics. The alteration in micro hardness in the direction of centrifugal force is observed, and it is perceived that top surface has higher hardness as compared to the middle and bottom region. The flexural strength of top surface sample is 254 MPa, which is 10% greater than middle surface sample and 12.36% greater than bottom surface sample. Compressive strength of 385 MPa, surpassing the middle surface sample by 17.11% and the bottom surface sample by 19.36%. Novelty: In this study, a novel three-layered centrifugal casting technique was devised. Owing to its rapid degradability, the anticipated duration of the implants within the human body is significantly shorter in comparison to alternative biomaterials such as Titanium and Stainless steel. Furthermore, the findings from the conducted tests strongly advocate for the utilization of this technique in biomedical implantations. Keywords: Functionally graded material (FGM), Centrifugal casting, Mechanical properties, Microstructural behavior and bioimplants","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"14 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139776420","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}
Objective: This paper aims to investigate the impact of specified behavioral biases on investors' stock trading decisions in North India. It has been observed that most of the research works are based on financial theories, which affect investment decisions. But besides the theories nowadays, behavioral biases also play an important role in investment decisions, which was less focused in the previous literature. Methods: The study used primary data collected from a sample from North Indian States (Uttar Pradesh, Delhi, Haryana, and Punjab) through a structured questionnaire to analyze the impact of specified behavioral biases on investors' stock trading decisions. We used structural equation modelling to find out the significant impact of behavioral biases on stock trading and investment decisions. Findings: The investigation determined that the majority of the designated cognitive biases, such as the Overconfidence Bias, the Representativeness Bias, and the Herding Bias, exert a significant influence on the decisions about stock trading and investment made by investors. Novelty: The ample research in this domain has primarily occurred in various countries, with only a limited number of studies conducted specifically at the Indian level. Nevertheless, based on the literature review, it is evident that this study is groundbreaking in North India. The objective of this research is to enhance the effectiveness of financial advisors by gaining a deeper understanding of the psychological aspects of clients. This, in turn, will aid in developing portfolios tailored to individual behavior, aligning with client preferences. Recognizing and addressing behavioral biases is crucial for individual investors as they strive to make informed and successful financial decisions. Keywords: Behavioral Biases, Overconfidence (OC) bias, Representativeness Bias (RB), Herding Bias (HB), Structural Equation Modelling
{"title":"Impact of Behavioral Biases on Investors’ Stock Trading Decisions: A Comprehensive Quantitative Analysis","authors":"Anurag Shukla, Manish Dadhich, Dipesh Vaya, Anuj Goel","doi":"10.17485/ijst/v17i8.2845","DOIUrl":"https://doi.org/10.17485/ijst/v17i8.2845","url":null,"abstract":"Objective: This paper aims to investigate the impact of specified behavioral biases on investors' stock trading decisions in North India. It has been observed that most of the research works are based on financial theories, which affect investment decisions. But besides the theories nowadays, behavioral biases also play an important role in investment decisions, which was less focused in the previous literature. Methods: The study used primary data collected from a sample from North Indian States (Uttar Pradesh, Delhi, Haryana, and Punjab) through a structured questionnaire to analyze the impact of specified behavioral biases on investors' stock trading decisions. We used structural equation modelling to find out the significant impact of behavioral biases on stock trading and investment decisions. Findings: The investigation determined that the majority of the designated cognitive biases, such as the Overconfidence Bias, the Representativeness Bias, and the Herding Bias, exert a significant influence on the decisions about stock trading and investment made by investors. Novelty: The ample research in this domain has primarily occurred in various countries, with only a limited number of studies conducted specifically at the Indian level. Nevertheless, based on the literature review, it is evident that this study is groundbreaking in North India. The objective of this research is to enhance the effectiveness of financial advisors by gaining a deeper understanding of the psychological aspects of clients. This, in turn, will aid in developing portfolios tailored to individual behavior, aligning with client preferences. Recognizing and addressing behavioral biases is crucial for individual investors as they strive to make informed and successful financial decisions. Keywords: Behavioral Biases, Overconfidence (OC) bias, Representativeness Bias (RB), Herding Bias (HB), Structural Equation Modelling","PeriodicalId":508200,"journal":{"name":"Indian Journal Of Science And Technology","volume":"159 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140455918","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：