Pub Date : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009213
Subba Reddy Meruva, B. Venkateswarlu
The most important phase in the discovery of common item-sets is identifying relationships between the items. Frequent-pattern growth (FP-growth), one of the traditional association mining techniques, excels at generating frequent item sets. For the purpose of eliminating item sets with high infrequency, both mining algorithms employ the support-confidence framework. Due to its inability to take into account the affected utility element, the support-confidence framework falls short in important applications including e-commerce, web mining, and healthcare. For circumvent the drawbacks of conventional algorithms, utility-based mining methods must be developed. Utility-based mining algorithms have recently developed with the significant advancements in association mining. For the purpose of performing active utility mining, the proposed technique is described. It employed the utility mining algorithms by tree structure building. The experimental section shows experimental findings from benchmark datasets and illustrates the effectiveness of the proposed methodology.
{"title":"A Fast and Effective Tree-based Mining Technique for Extraction of High Utility Itemsets","authors":"Subba Reddy Meruva, B. Venkateswarlu","doi":"10.1109/ICECA55336.2022.10009213","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009213","url":null,"abstract":"The most important phase in the discovery of common item-sets is identifying relationships between the items. Frequent-pattern growth (FP-growth), one of the traditional association mining techniques, excels at generating frequent item sets. For the purpose of eliminating item sets with high infrequency, both mining algorithms employ the support-confidence framework. Due to its inability to take into account the affected utility element, the support-confidence framework falls short in important applications including e-commerce, web mining, and healthcare. For circumvent the drawbacks of conventional algorithms, utility-based mining methods must be developed. Utility-based mining algorithms have recently developed with the significant advancements in association mining. For the purpose of performing active utility mining, the proposed technique is described. It employed the utility mining algorithms by tree structure building. The experimental section shows experimental findings from benchmark datasets and illustrates the effectiveness of the proposed methodology.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126704176","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009380
Riya Shah, Barkha M. Joshi, J. Shah, Milin M Patel, A. Rana, Ronak Roy
Unlike in some other parts of the world, speech recognition technology is legal in the West. It's not to the same degree that this happens in East Asian countries. It's possible that linguistic barriers are a major cause of this chasm. In addition, countries with many languages, such as India, must be taken into account if voice-based language identification is ever going to be practical. The challenge is in finding a technique to clearly and effectively identify the features that may differentiate across languages. The model processes audio data, creating spectrogram images from them before extracting features. Then, the Deep Learning (DL) is employed to streamline the output identification process by emphasizing the most crucial characteristics and attributes. Realizing that a person's vocal signal may be understood or observed was a major inspiration for the concept. This research work employ spectrograms (for visual data) and deep learning techniques to categorize Indic languages inside the IIITH Indic voice database. Finally, a model-based comparative analysis has been conducted by analyzing the accuracy, precision, recall, and f1-score to show that the proposed approach is more robust than existing models.
{"title":"Summary of Spoken Indian Languages Classification Using ML and DL","authors":"Riya Shah, Barkha M. Joshi, J. Shah, Milin M Patel, A. Rana, Ronak Roy","doi":"10.1109/ICECA55336.2022.10009380","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009380","url":null,"abstract":"Unlike in some other parts of the world, speech recognition technology is legal in the West. It's not to the same degree that this happens in East Asian countries. It's possible that linguistic barriers are a major cause of this chasm. In addition, countries with many languages, such as India, must be taken into account if voice-based language identification is ever going to be practical. The challenge is in finding a technique to clearly and effectively identify the features that may differentiate across languages. The model processes audio data, creating spectrogram images from them before extracting features. Then, the Deep Learning (DL) is employed to streamline the output identification process by emphasizing the most crucial characteristics and attributes. Realizing that a person's vocal signal may be understood or observed was a major inspiration for the concept. This research work employ spectrograms (for visual data) and deep learning techniques to categorize Indic languages inside the IIITH Indic voice database. Finally, a model-based comparative analysis has been conducted by analyzing the accuracy, precision, recall, and f1-score to show that the proposed approach is more robust than existing models.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126757344","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009231
E. Kirubakaran, K. Karthikeyan, S. Juliet, S. Shyam
Windmills are one of the finest and superior sources of electricity. Monitoring the working of windmill manually can be arduous. The ultra-wide band technology is exceptional for the purpose of monitoring and tracking of objects in complex environments. The proposed work proposes a windmill monitoring system by inculcating ultra-wide band tags and anchors. A conventional windmill consists of three blades. A minute UWB tag will be attached to each blades of the windmill followed by the attachment of a UWB anchor in the tower of the windmill. The pulses sent by the UWB tag will be received duly by the anchor present on the tower. The speed of the blade movement and deflection, along with their direction can be monitored from the frequency of the received pulses. Once received, the pulse are sent to the server for further algorithmic calculations. The monitoring system proposed promises to reduce the complexity in sensing the speed and movements in the deflection of blades and its current working status. An increase in accuracy and a nose dive in complexity can be witnessed using this sensing system.
{"title":"Wind Mill Monitoring System using Ultra Wide Band Technology","authors":"E. Kirubakaran, K. Karthikeyan, S. Juliet, S. Shyam","doi":"10.1109/ICECA55336.2022.10009231","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009231","url":null,"abstract":"Windmills are one of the finest and superior sources of electricity. Monitoring the working of windmill manually can be arduous. The ultra-wide band technology is exceptional for the purpose of monitoring and tracking of objects in complex environments. The proposed work proposes a windmill monitoring system by inculcating ultra-wide band tags and anchors. A conventional windmill consists of three blades. A minute UWB tag will be attached to each blades of the windmill followed by the attachment of a UWB anchor in the tower of the windmill. The pulses sent by the UWB tag will be received duly by the anchor present on the tower. The speed of the blade movement and deflection, along with their direction can be monitored from the frequency of the received pulses. Once received, the pulse are sent to the server for further algorithmic calculations. The monitoring system proposed promises to reduce the complexity in sensing the speed and movements in the deflection of blades and its current working status. An increase in accuracy and a nose dive in complexity can be witnessed using this sensing system.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127353085","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009280
N. G. Croos, Sophinia R, Afkar Ahamedh, Dirushan J., U. Rajapaksha, Buddika Harshanath
Agriculture is the primary sector that supports Sri Lanka's economy. The introduction of novel technologies into agricultural practices will be of great assistance to farmers. The soil's pH and moisture content play a crucial part in the monitoring of soil fertility, irrigation level, and plant growth. Sometimes farmers were unsuccessful in selecting the appropriate crops to grow based on the conditions of the soil, the planting season, and the geographic location. Soil fertility is an important aspect in agriculture to determine the soil's quality. Soil nutrients are depleted after each harvest and must be replenished. The Irrigation system needs to control flood levels and adapt to paddy development. Water is necessary for the preparation of the ground, the planting of the crop, and crop upkeep throughout the growing-to-harvest cycle. The occurrence of paddy plant diseases and the presence of pests are two key factors that influence the production and quality of rice. One of the industry's biggest problems is the lack of a reliable method for determining paddy field soil nutrient levels, identifying the suitable crop, knowing the level of irrigation, and identifying the pest. This leads to farmers taking their own lives, leaving the agricultural industry, and moving to urban areas in search of work. This research has proposed a system to assist farmers in crop selection, fertilizer recommendation, irrigation, and pest detection by taking into account all of the relevant factors such as soil nutrient level, soil fertility, moisture level, PH, Temperature, and pest images. A mobile application and an intelligent method that is adapted to the requirements of the crop in each field can provide the farmer with information about the suitable crop, fertility of the soil, suitable fertilizer, irrigation level, and identified pest which will increase crop yield.
{"title":"Agro-Engineering: IoT and Image processing based agriculture monitoring and recommendation system","authors":"N. G. Croos, Sophinia R, Afkar Ahamedh, Dirushan J., U. Rajapaksha, Buddika Harshanath","doi":"10.1109/ICECA55336.2022.10009280","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009280","url":null,"abstract":"Agriculture is the primary sector that supports Sri Lanka's economy. The introduction of novel technologies into agricultural practices will be of great assistance to farmers. The soil's pH and moisture content play a crucial part in the monitoring of soil fertility, irrigation level, and plant growth. Sometimes farmers were unsuccessful in selecting the appropriate crops to grow based on the conditions of the soil, the planting season, and the geographic location. Soil fertility is an important aspect in agriculture to determine the soil's quality. Soil nutrients are depleted after each harvest and must be replenished. The Irrigation system needs to control flood levels and adapt to paddy development. Water is necessary for the preparation of the ground, the planting of the crop, and crop upkeep throughout the growing-to-harvest cycle. The occurrence of paddy plant diseases and the presence of pests are two key factors that influence the production and quality of rice. One of the industry's biggest problems is the lack of a reliable method for determining paddy field soil nutrient levels, identifying the suitable crop, knowing the level of irrigation, and identifying the pest. This leads to farmers taking their own lives, leaving the agricultural industry, and moving to urban areas in search of work. This research has proposed a system to assist farmers in crop selection, fertilizer recommendation, irrigation, and pest detection by taking into account all of the relevant factors such as soil nutrient level, soil fertility, moisture level, PH, Temperature, and pest images. A mobile application and an intelligent method that is adapted to the requirements of the crop in each field can provide the farmer with information about the suitable crop, fertility of the soil, suitable fertilizer, irrigation level, and identified pest which will increase crop yield.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404595","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009293
Ankeshit Srivastava, Ayaz Ahmad, Sunny Kumar, Md Arman Ahmad
The air to sustain life on Earth is a crucial ingredient. Consumption of fossil fuels, other nonrenewable energy sources, and environmental changes caused by industrial processes contribute significantly to the growth of air pollution. In order to maintain the health and success of all species living on Earth, the air quality must be continuously monitored. This work details the implementation and strategy of AI-based air pollution monitoring and forecasting based on Internet of Things (IoT). In addition, a web-based dashboard using Google's cloud platform and the ‘firebase’ API tracks air pollution levels in real-time, both here and now and in the future. The air's purity can find by some components like carbon monoxide (CO), ammonia (NH4), and ozone. These components are calculated by using different types of sensors. Sensors are placed in various places in Vijayawada's surroundings. To calculate the air pollution in respective areas, using other techniques based on the time series modelling process and by integrating the Auto regression model to the moving Average Model. In this process, input parameters are training data sets collected concerning time series. These input parameters are found by using innovative technology. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are two examples of performance indices used to verify the efficacy of different Time Series models (RMSE). Raspberry Pi-3 computer learning algorithm blinked. It is a node at the network's periphery. An online dashboard built on the open-source Google cloud firebase tracks air pollution readings and predictions for the next four hours.
{"title":"Air Pollution Data and Forecasting Data Monitored through Google Cloud Services by using Artificial Intelligence and Machine Learning","authors":"Ankeshit Srivastava, Ayaz Ahmad, Sunny Kumar, Md Arman Ahmad","doi":"10.1109/ICECA55336.2022.10009293","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009293","url":null,"abstract":"The air to sustain life on Earth is a crucial ingredient. Consumption of fossil fuels, other nonrenewable energy sources, and environmental changes caused by industrial processes contribute significantly to the growth of air pollution. In order to maintain the health and success of all species living on Earth, the air quality must be continuously monitored. This work details the implementation and strategy of AI-based air pollution monitoring and forecasting based on Internet of Things (IoT). In addition, a web-based dashboard using Google's cloud platform and the ‘firebase’ API tracks air pollution levels in real-time, both here and now and in the future. The air's purity can find by some components like carbon monoxide (CO), ammonia (NH4), and ozone. These components are calculated by using different types of sensors. Sensors are placed in various places in Vijayawada's surroundings. To calculate the air pollution in respective areas, using other techniques based on the time series modelling process and by integrating the Auto regression model to the moving Average Model. In this process, input parameters are training data sets collected concerning time series. These input parameters are found by using innovative technology. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are two examples of performance indices used to verify the efficacy of different Time Series models (RMSE). Raspberry Pi-3 computer learning algorithm blinked. It is a node at the network's periphery. An online dashboard built on the open-source Google cloud firebase tracks air pollution readings and predictions for the next four hours.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122596845","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009152
R. Siddthan, P. Shanthi
In many places in the world, groundwater nitrate pollution is a major issue. Close to the livestock waste disposal site (LWDS), coprostanol and nitrate concentrations in the soil were altered by livestock manure. There was a considerable correlation between the nitrate contents in the groundwater and soil. There was evidence that nitrates were carried downstream in both soil and groundwater. It is, however, difficult to identify the main nitrate sources because of the diffuse and widespread spatial overlap of multiple non-point pollution sources. This research study presents a comprehensive survey and evaluation of various convolutional neural network (CNN) models for the assessment of groundwater nitrate contamination. The survey provides the accuracy of various models of CNN method that records the prediction accuracy of groundwater nitrate contamination. The model provides an accuracy evaluation with the proposed method on nitrate concentration and shows how well the proposed method archives better accuracy than other CNN models.
{"title":"A Comprehensive Survey on CNN Models on Assessment of Nitrate Contamination in Groundwater","authors":"R. Siddthan, P. Shanthi","doi":"10.1109/ICECA55336.2022.10009152","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009152","url":null,"abstract":"In many places in the world, groundwater nitrate pollution is a major issue. Close to the livestock waste disposal site (LWDS), coprostanol and nitrate concentrations in the soil were altered by livestock manure. There was a considerable correlation between the nitrate contents in the groundwater and soil. There was evidence that nitrates were carried downstream in both soil and groundwater. It is, however, difficult to identify the main nitrate sources because of the diffuse and widespread spatial overlap of multiple non-point pollution sources. This research study presents a comprehensive survey and evaluation of various convolutional neural network (CNN) models for the assessment of groundwater nitrate contamination. The survey provides the accuracy of various models of CNN method that records the prediction accuracy of groundwater nitrate contamination. The model provides an accuracy evaluation with the proposed method on nitrate concentration and shows how well the proposed method archives better accuracy than other CNN models.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123521691","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009445
M. Nisha, J. Jebathangam
This research work intends to classify the texts associated with bullying contents in social media, especially twitter by using the text mining process. A Multi-Modal Detection and classification of Cyberbullying media is developed in the study. This model integrates textual, and metadata to identify the cyberbullying media in case of social networks. The process involves two phases training and test the cyberbullying data, where natural language processing (NLP) is applied as the pre-processing tool and then particle swarm optimisation is used as feature selection process. Finally, the study applies decision tree classifier to classify the instances associated with cyberbullying and after classification, these features are combined with text instances to detect the performance of the proposed model. The simulation is conducted to test the detection rate of the classifier than the existing methods. The results show that the proposed method achieves higher rate of classification and detection accuracy than the existing methods.
{"title":"Detection and Classification of Cyberbullying in Social Media using Text Mining","authors":"M. Nisha, J. Jebathangam","doi":"10.1109/ICECA55336.2022.10009445","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009445","url":null,"abstract":"This research work intends to classify the texts associated with bullying contents in social media, especially twitter by using the text mining process. A Multi-Modal Detection and classification of Cyberbullying media is developed in the study. This model integrates textual, and metadata to identify the cyberbullying media in case of social networks. The process involves two phases training and test the cyberbullying data, where natural language processing (NLP) is applied as the pre-processing tool and then particle swarm optimisation is used as feature selection process. Finally, the study applies decision tree classifier to classify the instances associated with cyberbullying and after classification, these features are combined with text instances to detect the performance of the proposed model. The simulation is conducted to test the detection rate of the classifier than the existing methods. The results show that the proposed method achieves higher rate of classification and detection accuracy than the existing methods.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123529384","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009577
N. S. V. S. G. Bhavani, M. Vinodhini
A decrease in design complexity via approximate computation will increase performance and power of error-resilient applications. This paper presents a new approximation method for multipliers using the novel hybrid reverse carry propagate adder. In this case, the proposed hybrid Reverse Carry Propagate Adder (RCPA) is utilized to implement approximation method using two variables of a 8-bit multiplier. Reverse carry propagation adders propagate data from MSB to the LSB, which makes the input carrier more relevant than resulting carrier signal. According to probability statistics, the accumulation of altered partial products produces variable likelihood terms. This variation of logic complexity can be explained by altering partial products of the multiplier. Using the proposed Hybrid Reverse Carry Adder in the multiplier leads to an area improvement of 20%, delay and power improvement of 75.7% and 26% respectively. Compared to the ideal approximate reverse carry adder, this structure is more accurate.
{"title":"High Performance Accurate Multiplier using Hybrid Reverse Carry Propagate Adder","authors":"N. S. V. S. G. Bhavani, M. Vinodhini","doi":"10.1109/ICECA55336.2022.10009577","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009577","url":null,"abstract":"A decrease in design complexity via approximate computation will increase performance and power of error-resilient applications. This paper presents a new approximation method for multipliers using the novel hybrid reverse carry propagate adder. In this case, the proposed hybrid Reverse Carry Propagate Adder (RCPA) is utilized to implement approximation method using two variables of a 8-bit multiplier. Reverse carry propagation adders propagate data from MSB to the LSB, which makes the input carrier more relevant than resulting carrier signal. According to probability statistics, the accumulation of altered partial products produces variable likelihood terms. This variation of logic complexity can be explained by altering partial products of the multiplier. Using the proposed Hybrid Reverse Carry Adder in the multiplier leads to an area improvement of 20%, delay and power improvement of 75.7% and 26% respectively. Compared to the ideal approximate reverse carry adder, this structure is more accurate.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"29 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126299264","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009113
GK Yudheksha, Vijay Murugadoss, P. Reddy, T. Harshavardan, Shivram Sriramulu
Diabetes is one of the nation's primary causes of the spike in mortality rates. The surge in diabetes has been directly associated with an unhealthy lifestyle, urbanization, obesity/overweight, genetics, hormonal imbalance, poor diet, smoking, and alcoholism. Diabetes is very much harmful if left unidentified over the long term, which can lead to life- threatening difficulties like stroke and heart diseases. Through the application of Machine Learning algorithms to real-life problems, it is possible to come up with efficient, effective, and tailor-made solutions to detect diabetes at early stages. In this research paper, several ML models are compared and analyzed for early diabetes detection. The various categorization techniques used for our model development are SVM, DT, Random Forest, XGBoost, KNN, Logistic Regression. Through grid search, the hyperparameters of the models are tuned to achieve optimal performance. The proposed algorithm's performance is evaluated using various performance metrics like precision, Accuracy, Recall and F1-Score and ROC-AUC Curve.
{"title":"A Machine Learning based Approach to Detect Early Stage Diabetes Prediction","authors":"GK Yudheksha, Vijay Murugadoss, P. Reddy, T. Harshavardan, Shivram Sriramulu","doi":"10.1109/ICECA55336.2022.10009113","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009113","url":null,"abstract":"Diabetes is one of the nation's primary causes of the spike in mortality rates. The surge in diabetes has been directly associated with an unhealthy lifestyle, urbanization, obesity/overweight, genetics, hormonal imbalance, poor diet, smoking, and alcoholism. Diabetes is very much harmful if left unidentified over the long term, which can lead to life- threatening difficulties like stroke and heart diseases. Through the application of Machine Learning algorithms to real-life problems, it is possible to come up with efficient, effective, and tailor-made solutions to detect diabetes at early stages. In this research paper, several ML models are compared and analyzed for early diabetes detection. The various categorization techniques used for our model development are SVM, DT, Random Forest, XGBoost, KNN, Logistic Regression. Through grid search, the hyperparameters of the models are tuned to achieve optimal performance. The proposed algorithm's performance is evaluated using various performance metrics like precision, Accuracy, Recall and F1-Score and ROC-AUC Curve.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131832734","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 : 2022-12-01DOI: 10.1109/ICECA55336.2022.10009435
Eliyah Immanuel Thavaraj A, S. Juliet, Anila Sharon J
In the field of artificial intelligence, computer vision and natural language processing are used to automatically generate an image's contents. The regenerative neuronal model is developed and is dependent on machine translation and computer vision. Using this technique, natural phrases are produced that finally explain the image. This architecture also includes recurrent neural networks (RNN) and convolutional neural networks (CNN). The RNN is used to create phrases, whereas the CNN is used to extract characteristics from images. The model has been taught to produce captions that, when given an input image, almost exactly describe the image. The outcome of these algorithms is determined by several factors, including feature extraction, caption generation, and optimizer selection. Our goal is to conduct a comparative analysis of several optimizers to determine the optimizer that achieves highest accuracy for a deep learning model. The deep learning model is subsequently trained with various optimizers on the Flicker dataset. The accuracy of the results of the model using optimizers are achieved as follows: RMSprop optimizer has a 92% accuracy, SGD has a 12% accuracy, Adam optimizer has 53% accuracy, and Adadelta has a 12% per cent.
{"title":"A Comparative Study on Optimizers for Automatic Image Captioning","authors":"Eliyah Immanuel Thavaraj A, S. Juliet, Anila Sharon J","doi":"10.1109/ICECA55336.2022.10009435","DOIUrl":"https://doi.org/10.1109/ICECA55336.2022.10009435","url":null,"abstract":"In the field of artificial intelligence, computer vision and natural language processing are used to automatically generate an image's contents. The regenerative neuronal model is developed and is dependent on machine translation and computer vision. Using this technique, natural phrases are produced that finally explain the image. This architecture also includes recurrent neural networks (RNN) and convolutional neural networks (CNN). The RNN is used to create phrases, whereas the CNN is used to extract characteristics from images. The model has been taught to produce captions that, when given an input image, almost exactly describe the image. The outcome of these algorithms is determined by several factors, including feature extraction, caption generation, and optimizer selection. Our goal is to conduct a comparative analysis of several optimizers to determine the optimizer that achieves highest accuracy for a deep learning model. The deep learning model is subsequently trained with various optimizers on the Flicker dataset. The accuracy of the results of the model using optimizers are achieved as follows: RMSprop optimizer has a 92% accuracy, SGD has a 12% accuracy, Adam optimizer has 53% accuracy, and Adadelta has a 12% per cent.","PeriodicalId":356949,"journal":{"name":"2022 6th International Conference on Electronics, Communication and Aerospace Technology","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129964496","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：