Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.1543
The Brain Computing Interface (BCI) is a technology that has resulted in the advancement of Neuro-Prosthetics applications. BCI establishes a connection between the brain and a computer system, primarily focusing on assisting, enhancing, or restoring human cognitive and sensory - motor functions. BCI technology enables the acquisition of Electroencephalography (EEG) signals from the human brain. This research concentrates on analyzing the articulatory aspects, including Wernicke's and Broca's areas, for Silent Speech Recognition. Silent Speech Interfaces (SSI) offers an alternative to conventional speech interfaces that rely on acoustic signals. Silent Speech refers to the process of communicating speech in the absence of audible and intelligible acoustic signals. The primary objective of this study is to propose a classifier model for phoneme classification. The input signal undergoes preprocessing, and feature extraction is carried out using traditional methods such as Mel Frequency Cepstrum Coefficients (MFCC), Mel Frequency Spectral Coefficients (MFSC), and Linear Predictive Coding (LPC). The selection of the best features is based on classification accuracy for a subject and is implemented using the Integrated Stacking Classifier. The Integrated Stacking Classifier outperforms other traditional classifiers, achieving an average accuracy of 75% for both thinking and speaking states on the KaraOne dataset and approximately 86.2% and 84.09% for thinking and speaking states on the Fourteen Channel EEG for Imagined Speech (FEIS) dataset.
{"title":"A A Novel BCI - based Silent Speech Recognition using Hybrid Feature Extraction Techniques and Integrated Stacking Classifier","authors":"","doi":"10.56042/jsir.v82i11.1543","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.1543","url":null,"abstract":"The Brain Computing Interface (BCI) is a technology that has resulted in the advancement of Neuro-Prosthetics applications. BCI establishes a connection between the brain and a computer system, primarily focusing on assisting, enhancing, or restoring human cognitive and sensory - motor functions. BCI technology enables the acquisition of Electroencephalography (EEG) signals from the human brain. This research concentrates on analyzing the articulatory aspects, including Wernicke's and Broca's areas, for Silent Speech Recognition. Silent Speech Interfaces (SSI) offers an alternative to conventional speech interfaces that rely on acoustic signals. Silent Speech refers to the process of communicating speech in the absence of audible and intelligible acoustic signals. The primary objective of this study is to propose a classifier model for phoneme classification. The input signal undergoes preprocessing, and feature extraction is carried out using traditional methods such as Mel Frequency Cepstrum Coefficients (MFCC), Mel Frequency Spectral Coefficients (MFSC), and Linear Predictive Coding (LPC). The selection of the best features is based on classification accuracy for a subject and is implemented using the Integrated Stacking Classifier. The Integrated Stacking Classifier outperforms other traditional classifiers, achieving an average accuracy of 75% for both thinking and speaking states on the KaraOne dataset and approximately 86.2% and 84.09% for thinking and speaking states on the Fourteen Channel EEG for Imagined Speech (FEIS) dataset.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135565601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.3367
Every day, a multitude of mobile apps are released or updated, resulting in millions of daily downloads, usage, and views. This creates a fascinating phenomenon of user community acceptance and rating of these apps. Some apps are well-received by users due to factors such as performance, compatibility, and cost. This study has examined eleven factors that affect the performance of mobile banking apps like Google Pay, Phone Pay, and Paytm. Factors are identified by conducting a literature survey, analysing user reviews, and seeking expert opinions. It is worth noting that users tend to reject or dislike apps that pose challenges to them due to issues in the apps. Furthermore, the authors have utilized an Interpretive Structure Modeling (ISM) approach to develop a hierarchical structure for improvement of individual factors, along with MICMAC (Matrice d'Impacts Croisés Multiplication Appliquée á un Classment) analysis, to categorize the identified issues into four groups. Numerous studies have addressed issues related to mobile apps, but the classification or grouping of these issues has often been inadequate. In divergence, this particular research delivers a well-organized classification of issues associated with mobile banking applications. The issues are grouped into appropriate categories.
{"title":"Uncovering Issues Impacting Mobile Banking Performance using ISM-MICMAC Approach","authors":"","doi":"10.56042/jsir.v82i11.3367","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.3367","url":null,"abstract":"Every day, a multitude of mobile apps are released or updated, resulting in millions of daily downloads, usage, and views. This creates a fascinating phenomenon of user community acceptance and rating of these apps. Some apps are well-received by users due to factors such as performance, compatibility, and cost. This study has examined eleven factors that affect the performance of mobile banking apps like Google Pay, Phone Pay, and Paytm. Factors are identified by conducting a literature survey, analysing user reviews, and seeking expert opinions. It is worth noting that users tend to reject or dislike apps that pose challenges to them due to issues in the apps. Furthermore, the authors have utilized an Interpretive Structure Modeling (ISM) approach to develop a hierarchical structure for improvement of individual factors, along with MICMAC (Matrice d'Impacts Croisés Multiplication Appliquée á un Classment) analysis, to categorize the identified issues into four groups. Numerous studies have addressed issues related to mobile apps, but the classification or grouping of these issues has often been inadequate. In divergence, this particular research delivers a well-organized classification of issues associated with mobile banking applications. The issues are grouped into appropriate categories.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135565600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.3175
The Ropar Wetland is a significant freshwater ecosystem located in Punjab, India. In the recent years, this wetland has witnessed significant changes owing to anthropogenic and natural factors. In this study, the land use and land cover changes are analyzed around the Ropar Wetland using remote sensing techniques by utilizing Landsat images and GIS software. The results showed a significant increase in agricultural land from 19% in 2000 to 37% in 2010, followed by a decrease to 28% in 2020. Barren, urban, and fallow land also showed a continuous increase from 20% in 2000 to 44% in 2020. The forest cover decreased from 47% in 2000 to 17% in 2020 and water bodies decreased slightly from 14% in 2000 to 10% in both 2010 and 2020. The pictorial representation of LULC (Land Use Land Change) changes over the years, including the area of the Ropar Wetland, provided insight into the shifting patterns of land use and cover. Results from NDWI (Normalized Difference Water Index) show a small decrease in water body area in the wetland over the years, with some fluctuations in the total area. MNDWI (Modified Normalized Difference Water Index) shows the sparse water area around the wetland. Natural processes including erosion and accretion have affected the wetland region around the river, causing a net loss of 55 hectares of land, over the past two decades. The findings of this study suggest that there is a need to implement effective management practices that recognize the complex interrelationships between land use, hydrology, and ecological processes to protect the Ropar Wetland's ecological and hydrological functions. Ongoing monitoring and assessing land use and cover changes are crucial for conserving wetland ecosystems.
罗帕湿地是位于印度旁遮普的重要淡水生态系统。近年来，由于人为和自然因素的影响，该湿地发生了明显的变化。本研究利用Landsat影像和GIS软件，利用遥感技术对罗帕湿地周边土地利用和土地覆被变化进行分析。结果表明，农业用地比例从2000年的19%上升到2010年的37%，随后下降到2020年的28%。荒地、城市和休耕地也从2000年的20%持续增加到2020年的44%。森林覆盖率从2000年的47%下降到2020年的17%，水体从2000年的14%下降到2010年和2020年的10%。土地利用土地变化(LULC)多年来的变化，包括罗帕尔湿地的面积，提供了对土地利用和覆盖变化模式的深入了解。NDWI(归一化差水指数)结果显示，多年来湿地水体面积减少幅度较小，总面积有一定波动。MNDWI (Modified Normalized Difference Water Index)表示湿地周围的稀疏水域面积。在过去的二十年里，包括侵蚀和增生在内的自然过程影响了河流周围的湿地区域，造成了55公顷土地的净损失。本研究的结果表明，有必要实施有效的管理措施，认识到土地利用、水文和生态过程之间复杂的相互关系，以保护罗帕湿地的生态和水文功能。持续监测和评估土地利用和覆盖变化对保护湿地生态系统至关重要。
{"title":"Integrating NDWI, MNDWI, and Erosion Modeling to Analyze Wetland Changes and Impacts of Land Use Activities in Ropar Wetland, India","authors":"","doi":"10.56042/jsir.v82i11.3175","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.3175","url":null,"abstract":"The Ropar Wetland is a significant freshwater ecosystem located in Punjab, India. In the recent years, this wetland has witnessed significant changes owing to anthropogenic and natural factors. In this study, the land use and land cover changes are analyzed around the Ropar Wetland using remote sensing techniques by utilizing Landsat images and GIS software. The results showed a significant increase in agricultural land from 19% in 2000 to 37% in 2010, followed by a decrease to 28% in 2020. Barren, urban, and fallow land also showed a continuous increase from 20% in 2000 to 44% in 2020. The forest cover decreased from 47% in 2000 to 17% in 2020 and water bodies decreased slightly from 14% in 2000 to 10% in both 2010 and 2020. The pictorial representation of LULC (Land Use Land Change) changes over the years, including the area of the Ropar Wetland, provided insight into the shifting patterns of land use and cover. Results from NDWI (Normalized Difference Water Index) show a small decrease in water body area in the wetland over the years, with some fluctuations in the total area. MNDWI (Modified Normalized Difference Water Index) shows the sparse water area around the wetland. Natural processes including erosion and accretion have affected the wetland region around the river, causing a net loss of 55 hectares of land, over the past two decades. The findings of this study suggest that there is a need to implement effective management practices that recognize the complex interrelationships between land use, hydrology, and ecological processes to protect the Ropar Wetland's ecological and hydrological functions. Ongoing monitoring and assessing land use and cover changes are crucial for conserving wetland ecosystems.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135566711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Predicting student performance is the major problem for enhancing the educational procedures. A level of student’s performance may be influenced by several factors like job of parents, sexual category and average scores obtained in prior years. Student’s performance prediction is a challenging chore, which can help educational staffs and students of educational institutions to follow the progress of students in their academic activities. Student performance enhancement and progress in educational quality are the most vital part of educational organizations. Presently, it is essential for an educational organization to predict the performance of students. Existing methods utilized only previous student performances for prediction without including other significant behaviors of students. For addressing such problems, a proficient model is proposed for prediction of student performance utilizing proposed Adaptive Aquila Optimization-allied Deep Convolution Neural Network (DCNN). In this process, data transformation is initiated using the Yeo-Johnson transformation method. Subsequently, feature selection is performed using Fisher Score to identify the most relevant features. Following feature selection, data augmentation techniques are applied to enhance the dataset. Finally, student performance is predicted through the utilization of a DCNN, with a focus on fine-tuning the network parameters for optimal performance. This fine-tuning is achieved through the use of the Adaptive Aquila Optimizer (AAO), ensuring the network is poised to deliver the best possible results in predicting student outcomes. Proposed AAO-based DCNN has achieved minimal error values of Mean Square Error, Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, Mean Absolute Relative Error, Mean Squared Relative Error, and Root Mean Squared Relative Error, respectively.
{"title":"Predicting Student Performance with Adaptive Aquila Optimization-based Deep Convolution Neural Network","authors":"","doi":"10.56042/jsir.v82i11.40","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.40","url":null,"abstract":"Predicting student performance is the major problem for enhancing the educational procedures. A level of student’s performance may be influenced by several factors like job of parents, sexual category and average scores obtained in prior years. Student’s performance prediction is a challenging chore, which can help educational staffs and students of educational institutions to follow the progress of students in their academic activities. Student performance enhancement and progress in educational quality are the most vital part of educational organizations. Presently, it is essential for an educational organization to predict the performance of students. Existing methods utilized only previous student performances for prediction without including other significant behaviors of students. For addressing such problems, a proficient model is proposed for prediction of student performance utilizing proposed Adaptive Aquila Optimization-allied Deep Convolution Neural Network (DCNN). In this process, data transformation is initiated using the Yeo-Johnson transformation method. Subsequently, feature selection is performed using Fisher Score to identify the most relevant features. Following feature selection, data augmentation techniques are applied to enhance the dataset. Finally, student performance is predicted through the utilization of a DCNN, with a focus on fine-tuning the network parameters for optimal performance. This fine-tuning is achieved through the use of the Adaptive Aquila Optimizer (AAO), ensuring the network is poised to deliver the best possible results in predicting student outcomes. Proposed AAO-based DCNN has achieved minimal error values of Mean Square Error, Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, Mean Absolute Relative Error, Mean Squared Relative Error, and Root Mean Squared Relative Error, respectively.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135566706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.3127
A library of 170 fungicidal molecules of different functional moieties were subjected to in-silico assessment of their relative potential to inhibit ten vital targets of the Fusarium fujikuroi, bakanae disease causative pathogen in rice. Targets chosen were tubulin proteins (α-, β- and γ-tubulin) and NRPS31 gene cluster (FFUJ_00005, FFUJ_00006, FFUJ_00007, FFUJ_00008, FFUJ_00010, FFUJ_00011, FFUJ_00013). In-silico findings were validated with the help of in vitro analysis of the molecules to predict the most effective compound(s) relative to carbendazim (positive control). Most effective molecules were selected based on their chemical characteristics and Lipinski’s rule. One each of the natural and synthetic origin molecules was selected for the molecular dynamics and in-vitro analysis. β-Caryophyllene came out as the most potential molecule followed by flusilazole. The extent of inhibition of α-tubulin by these two molecules was significantly higher than by carbendazim. In-vitro bioassay validated the in-silico findings with LC50 values of 3.29, 64.12, and 178.77 μg/mL for β-caryophyllene, flusilazole and carbendazim, respectively. Further, molecular dynamics also revealed the selected molecular complex as highly effective with time when analyzed using Root Mean Square Deviation (RMSD) and Radius of Gyration (Rg).
{"title":"Mining of Potential Antifungal Molecules for Control of Fusarium fujikuroi in Rice using in silico and in vitro Analysis","authors":"","doi":"10.56042/jsir.v82i11.3127","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.3127","url":null,"abstract":"A library of 170 fungicidal molecules of different functional moieties were subjected to in-silico assessment of their relative potential to inhibit ten vital targets of the Fusarium fujikuroi, bakanae disease causative pathogen in rice. Targets chosen were tubulin proteins (α-, β- and γ-tubulin) and NRPS31 gene cluster (FFUJ_00005, FFUJ_00006, FFUJ_00007, FFUJ_00008, FFUJ_00010, FFUJ_00011, FFUJ_00013). In-silico findings were validated with the help of in vitro analysis of the molecules to predict the most effective compound(s) relative to carbendazim (positive control). Most effective molecules were selected based on their chemical characteristics and Lipinski’s rule. One each of the natural and synthetic origin molecules was selected for the molecular dynamics and in-vitro analysis. β-Caryophyllene came out as the most potential molecule followed by flusilazole. The extent of inhibition of α-tubulin by these two molecules was significantly higher than by carbendazim. In-vitro bioassay validated the in-silico findings with LC50 values of 3.29, 64.12, and 178.77 μg/mL for β-caryophyllene, flusilazole and carbendazim, respectively. Further, molecular dynamics also revealed the selected molecular complex as highly effective with time when analyzed using Root Mean Square Deviation (RMSD) and Radius of Gyration (Rg).","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135565598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.5322
This paper introduces one improved version of the Grey Wolf Optimization algorithm (GWO), one of the newly established nature-inspired metaheuristic algorithms, and the suggested approach is termed Chaotic Grey Wolf Optimization (CGWO). The newly suggested approach CGWO is premeditated by the integration of the chaos technique with the GWO algorithm, aiming to resolve global optimization problems by maintaining a proper balance between exploration and exploitation. In the proposed approach, CGWO is assessed over the classic 23 benchmark functions. The proficiency of the freshly suggested approach, CGWO is verified by comparing it with contemporary methods as well as examined through statistical analysis also. Further, the same CGWO is utilized to train neural networks (MLP) by considering benchmark datasets, for data classification and establishing a better classifier algorithm.
{"title":"Improved Chaotic Grey Wolf Optimization for Training Neural Networks","authors":"","doi":"10.56042/jsir.v82i11.5322","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.5322","url":null,"abstract":"This paper introduces one improved version of the Grey Wolf Optimization algorithm (GWO), one of the newly established nature-inspired metaheuristic algorithms, and the suggested approach is termed Chaotic Grey Wolf Optimization (CGWO). The newly suggested approach CGWO is premeditated by the integration of the chaos technique with the GWO algorithm, aiming to resolve global optimization problems by maintaining a proper balance between exploration and exploitation. In the proposed approach, CGWO is assessed over the classic 23 benchmark functions. The proficiency of the freshly suggested approach, CGWO is verified by comparing it with contemporary methods as well as examined through statistical analysis also. Further, the same CGWO is utilized to train neural networks (MLP) by considering benchmark datasets, for data classification and establishing a better classifier algorithm.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135566704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.3268
In modern Radar applications, optimal sequences have been used in many areas, such as communication systems, radar, and sonar, because of their minimal peak sidelobe level, which causes an increase in the signal-to-noise ratio with a good range resolution at the output. The literature survey shows various pulse compression techniques that are widely used to achieve superior range resolution and range detection performance. Several studies have been conducted on chaotic communication involving chaotic maps in recent years, producing promising results. These maps are used to generate different phase-coded sequences. The properties of the chaotic map sequences are almost random. The performance of these sequences has been studied with various optimization techniques in literature by employing a matched filter and a mismatched filter and is measured in terms of peak sidelobe ratio. But the performance has not improved significantly. This paper focused on improving performance using a new hybrid technique to design mismatched filters. This improvement is achieved by designing the coefficients of the mismatched filters using a combination of metaheuristic methods and an evolutionary algorithm for specializing in intensification and diversification. A significant improvement in the peak sidelobe ratio and range resolution is obtained when the mismatched filter is combined with adaptive filters at the output.
{"title":"An Insight into the Performance of Chaotic Sequences using Cascaded Mismatched Filters with Adaptive Performance of Radar Sequences using Adaptive Mismatched Filter","authors":"","doi":"10.56042/jsir.v82i11.3268","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.3268","url":null,"abstract":"In modern Radar applications, optimal sequences have been used in many areas, such as communication systems, radar, and sonar, because of their minimal peak sidelobe level, which causes an increase in the signal-to-noise ratio with a good range resolution at the output. The literature survey shows various pulse compression techniques that are widely used to achieve superior range resolution and range detection performance. Several studies have been conducted on chaotic communication involving chaotic maps in recent years, producing promising results. These maps are used to generate different phase-coded sequences. The properties of the chaotic map sequences are almost random. The performance of these sequences has been studied with various optimization techniques in literature by employing a matched filter and a mismatched filter and is measured in terms of peak sidelobe ratio. But the performance has not improved significantly. This paper focused on improving performance using a new hybrid technique to design mismatched filters. This improvement is achieved by designing the coefficients of the mismatched filters using a combination of metaheuristic methods and an evolutionary algorithm for specializing in intensification and diversification. A significant improvement in the peak sidelobe ratio and range resolution is obtained when the mismatched filter is combined with adaptive filters at the output.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135566709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.1978
The sensor response of the metal oxide based gas sensor has been simulated using Deep Neural Network (DNN) model. The neural network designed for the modelling of the sensor has single input layer, three hidden layers and single output layer. The linear regression algorithm has been used to compute the electrical conductance of the sensor at given temperature and pressure. The data generated through modified Wolkenstein method has been used for training, validation and testing of the developed network. The data for materials Tin (IV) oxide (SnO2), Tin (II) oxide (SnO) and Copper (I) oxide (Cu2O) with different Eg values has been utilized. The other input parameters like Temperature, ND, NC, NV, EF−ESSand ECS−EF are varied for the specific range to collect a variety of data for calculation of electrical conductance of the sensor. The total data used for training, validation and testing was 1,90,512 data points. The plots for training, validation and testing phase have been plotted. The sensor response computed through the proposed model is validated with the results of already published mathematical model. The sensor response shows steep change when the gas concentration of the target gas reaches above 10−8 atm. The proposed model can be retrained or transfer learning can be applied for using the same model for other types of materials for gas sensing applications.
{"title":"Deep Neural Network Based Modelling of Chemisorption Process on Surface of Oxide Based Gas Sensors","authors":"","doi":"10.56042/jsir.v82i11.1978","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.1978","url":null,"abstract":"The sensor response of the metal oxide based gas sensor has been simulated using Deep Neural Network (DNN) model. The neural network designed for the modelling of the sensor has single input layer, three hidden layers and single output layer. The linear regression algorithm has been used to compute the electrical conductance of the sensor at given temperature and pressure. The data generated through modified Wolkenstein method has been used for training, validation and testing of the developed network. The data for materials Tin (IV) oxide (SnO2), Tin (II) oxide (SnO) and Copper (I) oxide (Cu2O) with different Eg values has been utilized. The other input parameters like Temperature, ND, NC, NV, EF−ESSand ECS−EF are varied for the specific range to collect a variety of data for calculation of electrical conductance of the sensor. The total data used for training, validation and testing was 1,90,512 data points. The plots for training, validation and testing phase have been plotted. The sensor response computed through the proposed model is validated with the results of already published mathematical model. The sensor response shows steep change when the gas concentration of the target gas reaches above 10−8 atm. The proposed model can be retrained or transfer learning can be applied for using the same model for other types of materials for gas sensing applications.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135566712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-01DOI: 10.56042/jsir.v82i11.5506
The objective of this study is to compare the stress shielding effect of various conventional as well as modified additive manufactured porous materials used for spinal cages. A finite element study was performed by changing the design (fully porous and hybrid) and the materials (PEEK, CFR-PEEK, Titanium) of spinal cages. All the models were simulated under uniaxial compression, to study the stress shielding effect. The Finite Element Analysis results showed that the hybrid spinal cage transfers more stress to its adjacent vertebrae than the other design configurations under uniaxial compression. The hybrid titanium cage was most effective in reducing the stress shielding effect. The hybrid cage is stronger than PEEK & CFR-PEEK cages, however, due to the porous structure reduced stress shielding was observed.
{"title":"Comparative Analysis of Porous Titanium Spinal Cage with Conventional Spinal Cages: A Finite Element Study","authors":"","doi":"10.56042/jsir.v82i11.5506","DOIUrl":"https://doi.org/10.56042/jsir.v82i11.5506","url":null,"abstract":"The objective of this study is to compare the stress shielding effect of various conventional as well as modified additive manufactured porous materials used for spinal cages. A finite element study was performed by changing the design (fully porous and hybrid) and the materials (PEEK, CFR-PEEK, Titanium) of spinal cages. All the models were simulated under uniaxial compression, to study the stress shielding effect. The Finite Element Analysis results showed that the hybrid spinal cage transfers more stress to its adjacent vertebrae than the other design configurations under uniaxial compression. The hybrid titanium cage was most effective in reducing the stress shielding effect. The hybrid cage is stronger than PEEK & CFR-PEEK cages, however, due to the porous structure reduced stress shielding was observed.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135565307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.56042/jsir.v82i10.2613
Accurate measurement of flow depth in an open channel on a real-time basis is the prime factor leading to more accurate quantification of discharge by the flow measuring device. The aim of present study was to evaluate the ultrasonic sensors (viz. HC-SR04 and JSN-SR04T) for depth of flow and corresponding discharge rate measurement in irrigation channel of canal command. The effect of ambient temperature on ultrasonic sensors was also investigated for irrigation channel hydraulic response measurement. It was observed that the performance of calibrated and temperature compensated sensors was better than the uncalibrated ones. Moreover, the performance of JSN-SR04T was better with mean absolute deviation (MAD: 0.21 ± 0.01cm), root mean square error (RMSE: 0.82 ± 0.01) and mean absolute percentage error (MAPE: 0.46 ± 0.09) compared to HC-SR04 sensor with MAD (0.36 ± 0.07), RMSE (0.43 ± 0.08) and MAPE (1.54 ± 0.82), respectively. Hence, JSN-SR04T ultrasonic sensor was used in the developed sensing system for the measurement of flow depth. It was observed that the system measured flow rate when compared with the observed flow resulted in prediction error estimate MAD (0.13 ± 0.05 lps), RMSE (0.16 ± 0.05) and MAPE (2.09 ± 1.16) and coefficient of determination (R2: 0.99) for flow rate ranging from 2 to 20 lps. Overall, the study resulted in the development of a novel and economically viable open channel digital flow sensing system to measure discharge rate passing through the flume. The developed sensing system will assist stakeholders in enhancing surface irrigation water use efficiency in canal commands.
{"title":"Evaluation of Ultrasonic Sensor for Flow Measurement in Open Channel","authors":"","doi":"10.56042/jsir.v82i10.2613","DOIUrl":"https://doi.org/10.56042/jsir.v82i10.2613","url":null,"abstract":"Accurate measurement of flow depth in an open channel on a real-time basis is the prime factor leading to more accurate quantification of discharge by the flow measuring device. The aim of present study was to evaluate the ultrasonic sensors (viz. HC-SR04 and JSN-SR04T) for depth of flow and corresponding discharge rate measurement in irrigation channel of canal command. The effect of ambient temperature on ultrasonic sensors was also investigated for irrigation channel hydraulic response measurement. It was observed that the performance of calibrated and temperature compensated sensors was better than the uncalibrated ones. Moreover, the performance of JSN-SR04T was better with mean absolute deviation (MAD: 0.21 ± 0.01cm), root mean square error (RMSE: 0.82 ± 0.01) and mean absolute percentage error (MAPE: 0.46 ± 0.09) compared to HC-SR04 sensor with MAD (0.36 ± 0.07), RMSE (0.43 ± 0.08) and MAPE (1.54 ± 0.82), respectively. Hence, JSN-SR04T ultrasonic sensor was used in the developed sensing system for the measurement of flow depth. It was observed that the system measured flow rate when compared with the observed flow resulted in prediction error estimate MAD (0.13 ± 0.05 lps), RMSE (0.16 ± 0.05) and MAPE (2.09 ± 1.16) and coefficient of determination (R2: 0.99) for flow rate ranging from 2 to 20 lps. Overall, the study resulted in the development of a novel and economically viable open channel digital flow sensing system to measure discharge rate passing through the flume. The developed sensing system will assist stakeholders in enhancing surface irrigation water use efficiency in canal commands.","PeriodicalId":17010,"journal":{"name":"Journal of Scientific & Industrial Research","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135763056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：