Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134410
M. R. Thanka, Shalem Preetham Gandu, B. Manaswini, Thirumal Reddy Bala Snehitha, Manukonda Narmada Reddy, Kalle Nandini
Arrhythmias are irregular and possibly deadly heartbeats. To reduce mortality and morbidity, the patient must receive the proper treatment. Recent techniques in the field of machine learning and signal processing have been applied to the detection and classification of arrhythmias. However, they face several challenges in accurately detecting arrhythmias. One major challenge is the class imbalance in the training data, which can lead to overfitting or underfitting of the models. Another challenge is the variability in ECG signals due to factors such as noise, artifacts, and variations in electrode placement. The proposed objective is to develop an effective ensemble model with a network-in-network architecture based on CNN and LSTM to accurately detect arrhythmias in ECG signals. On the MIT-BH dataset, it was trained and validated to recognize five different kinds of arrhythmias. Prior to that, resampling was done to balance the data in order to prevent the model from being under- or overfit. The ensembled model performs excellent on the validation data. The outcome of the trial show that the suggested model performed remarkably well, with 100% and 99.72% accuracy in the training and testing datasets, respectively. On validation data the CNN and LSTM performed with 98.6% and 98.4% individually. The proposed method outperformed the existing methods in accuracy, proving that the ensemble model is the most effective.
{"title":"An Ensemble Approach for Cardiac Arrhythmia Detection using Multimodal Deep Learning","authors":"M. R. Thanka, Shalem Preetham Gandu, B. Manaswini, Thirumal Reddy Bala Snehitha, Manukonda Narmada Reddy, Kalle Nandini","doi":"10.1109/ICICT57646.2023.10134410","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134410","url":null,"abstract":"Arrhythmias are irregular and possibly deadly heartbeats. To reduce mortality and morbidity, the patient must receive the proper treatment. Recent techniques in the field of machine learning and signal processing have been applied to the detection and classification of arrhythmias. However, they face several challenges in accurately detecting arrhythmias. One major challenge is the class imbalance in the training data, which can lead to overfitting or underfitting of the models. Another challenge is the variability in ECG signals due to factors such as noise, artifacts, and variations in electrode placement. The proposed objective is to develop an effective ensemble model with a network-in-network architecture based on CNN and LSTM to accurately detect arrhythmias in ECG signals. On the MIT-BH dataset, it was trained and validated to recognize five different kinds of arrhythmias. Prior to that, resampling was done to balance the data in order to prevent the model from being under- or overfit. The ensembled model performs excellent on the validation data. The outcome of the trial show that the suggested model performed remarkably well, with 100% and 99.72% accuracy in the training and testing datasets, respectively. On validation data the CNN and LSTM performed with 98.6% and 98.4% individually. The proposed method outperformed the existing methods in accuracy, proving that the ensemble model is the most effective.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127560881","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}
The approach described in this research study uses parse trees to transform ambiguous syntax into unambiguous grammar. There is no algorithm that can detect whether a grammar is ambiguous or not. The steps that will be considered in the proposed system to convert an ambiguous grammar into unambiguous are: Precedence of operators and the Associativity rule. Multiple interpretations of a statement might result from ambiguous grammar, making it challenging for natural language processing systems to recognize and respond to the intended meaning. The proposed approach entails creating a parse tree for the input text and utilizing it to locate and eliminate ambiguity sources. Experiments on a dataset of phrases with unclear syntax are used to assess the method's efficacy, indicating the potential for enhanced performance in natural language processing systems.
{"title":"Conversion of Ambiguous Grammar to Unambiguous Grammar using Parse Tree","authors":"K. Vayadande, Prithviraj Sangle, Kunjal Agrawal, Atman Naik, Aslaan Mulla, Ayushi Khare","doi":"10.1109/ICICT57646.2023.10134096","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134096","url":null,"abstract":"The approach described in this research study uses parse trees to transform ambiguous syntax into unambiguous grammar. There is no algorithm that can detect whether a grammar is ambiguous or not. The steps that will be considered in the proposed system to convert an ambiguous grammar into unambiguous are: Precedence of operators and the Associativity rule. Multiple interpretations of a statement might result from ambiguous grammar, making it challenging for natural language processing systems to recognize and respond to the intended meaning. The proposed approach entails creating a parse tree for the input text and utilizing it to locate and eliminate ambiguity sources. Experiments on a dataset of phrases with unclear syntax are used to assess the method's efficacy, indicating the potential for enhanced performance in natural language processing systems.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132609070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134475
Kanakam Siva Rama Prasad, N. S. Rao, T. K. Babu, Pranav A, Gosu Bobby, Shaik Haribulla
Fire detection and recognition is an important aspect of fire safety, and the use of virtual reality video images and deep learning (DL) methods can help to optimize this process. Deep learning (DL) is the sub-field of machine learning (ML) which utilizes the artificial neural networks (ANN) to train and analyze predictions. These networks are more suitable for processing enormous amounts of data which is better for image recognition. Based on the fire status and immersive view, the detection and recognition of fire are detected. Deep learning algorithms can be trained using these images to recognize patterns and identify fires, smoke, and other indicators of fire. This paper introduced the new fire detection model which detects the fire from video footage and also images collected various online sources. The proposed model used the pre-trained model RESNET-50 to train the fire affected videos. To detect the fire affected region the feature extraction method Histogram of Oriented Gradients and Radial Basis Function Networks (RBFNs) used to detect the fire affected images.
{"title":"Deep Learning Model for Detection and Recognition of Fire based on Virtual Reality Video Images","authors":"Kanakam Siva Rama Prasad, N. S. Rao, T. K. Babu, Pranav A, Gosu Bobby, Shaik Haribulla","doi":"10.1109/ICICT57646.2023.10134475","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134475","url":null,"abstract":"Fire detection and recognition is an important aspect of fire safety, and the use of virtual reality video images and deep learning (DL) methods can help to optimize this process. Deep learning (DL) is the sub-field of machine learning (ML) which utilizes the artificial neural networks (ANN) to train and analyze predictions. These networks are more suitable for processing enormous amounts of data which is better for image recognition. Based on the fire status and immersive view, the detection and recognition of fire are detected. Deep learning algorithms can be trained using these images to recognize patterns and identify fires, smoke, and other indicators of fire. This paper introduced the new fire detection model which detects the fire from video footage and also images collected various online sources. The proposed model used the pre-trained model RESNET-50 to train the fire affected videos. To detect the fire affected region the feature extraction method Histogram of Oriented Gradients and Radial Basis Function Networks (RBFNs) used to detect the fire affected images.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132709582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134235
J. L. Eben, R. Jayasudha, S. Ramya, S. Kaliappan, Shobha Aswal, Khalid Ali Salem Al-Salehi
Diabetes mellitus is one of the most pressing health concerns because so many people are afflicted by its disabling symptoms. Factors such as age, excess body fat, insufficient physical activity, a history of diabetes in one's family, a sedentary lifestyle, an unhealthy diet, hypertension, etc., all increase the likelihood of developing diabetes mellitus. Health complications are more common in people with diabetes, including cardiovascular disease, renal failure, stroke, blindness, and nerve injury. To validate a diagnosis of diabetes, hospitals typically perform a battery of procedures on the patient. Big data analytics has many vital applications in the healthcare sector. Numerous large computer systems are used in the healthcare sector. With the help of big data analytics, researchers can sift through mountains of data in search of previously unseen patterns and insights. Current techniques have a poor degree of precision in classification and forecast. While previous research has focused on factors such as glucose, body mass index, age, insulin, etc., the proposed model takes these into account and also the other factors that may be more relevant to the development of diabetes. The newer sample is superior to the older one based on categorization accuracy. A workflow algorithm for diabetes prognosis is also required to improve the accuracy.
{"title":"Diabetes Prediction Model for Better Clarification by using Machine Learning","authors":"J. L. Eben, R. Jayasudha, S. Ramya, S. Kaliappan, Shobha Aswal, Khalid Ali Salem Al-Salehi","doi":"10.1109/ICICT57646.2023.10134235","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134235","url":null,"abstract":"Diabetes mellitus is one of the most pressing health concerns because so many people are afflicted by its disabling symptoms. Factors such as age, excess body fat, insufficient physical activity, a history of diabetes in one's family, a sedentary lifestyle, an unhealthy diet, hypertension, etc., all increase the likelihood of developing diabetes mellitus. Health complications are more common in people with diabetes, including cardiovascular disease, renal failure, stroke, blindness, and nerve injury. To validate a diagnosis of diabetes, hospitals typically perform a battery of procedures on the patient. Big data analytics has many vital applications in the healthcare sector. Numerous large computer systems are used in the healthcare sector. With the help of big data analytics, researchers can sift through mountains of data in search of previously unseen patterns and insights. Current techniques have a poor degree of precision in classification and forecast. While previous research has focused on factors such as glucose, body mass index, age, insulin, etc., the proposed model takes these into account and also the other factors that may be more relevant to the development of diabetes. The newer sample is superior to the older one based on categorization accuracy. A workflow algorithm for diabetes prognosis is also required to improve the accuracy.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115465785","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}
This research study presents an automated real-time background face recognition system for a large dataset of human faces. This is very difficult because background subtraction is still an issue in live images. Addition to this there are huge features in human face image in terms of eye, nose, head, lip, etc. The proposed system simplifies many of the facial recognition features. It utilizes AdaBoost with cascade to detect human faces in real-time. The matched face is then used to Identify a person. The real-time security and automation system is based on human face recognition, and it uses a simple and fast algorithm that achieves high accuracy. We have accuracy of 92% by using Adaboost Algorithm.
{"title":"A Real-time Person Identity Detection System Using Machine Learning","authors":"Anushka Vilas Wagh, Priti Prem Ghodke, Prit Ujjawal Patil, Prashant Dinanath Chauhan, Prachi Gurav","doi":"10.1109/ICICT57646.2023.10134404","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134404","url":null,"abstract":"This research study presents an automated real-time background face recognition system for a large dataset of human faces. This is very difficult because background subtraction is still an issue in live images. Addition to this there are huge features in human face image in terms of eye, nose, head, lip, etc. The proposed system simplifies many of the facial recognition features. It utilizes AdaBoost with cascade to detect human faces in real-time. The matched face is then used to Identify a person. The real-time security and automation system is based on human face recognition, and it uses a simple and fast algorithm that achieves high accuracy. We have accuracy of 92% by using Adaboost Algorithm.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115597565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134211
V. Mounika, Y. Charitha
The identity of emotional speech is a significant topic within the discipline of interactions between humans and computers. Many strategies of figuring out emotions in human speech had been introduced and installed through diverse researchers. To identify noises in audio documents is the purpose of one of these versions. Together with gender recognition and YouTube video will be played depending on mood, this suggested computer also features speech emotion detection, which listens for sentiments like happiness, rage, and sadness in audio cues. This output is sent as input to YouTube, which plays song within the user's mind, resulting in the person's temper to stabilize fast. Using the CNN characteristic extraction approach, the function sizes vector become processed with NumPy, and the audio class became carried out in MFCC. This research study mainly uses two programs: RAVDESS and SAVEE. Using the acquired datasets, a new version of the look was produced in-depth. The device area is the platform where the Google Colab is used to perform code execution.
{"title":"Mood -Enhancing Music Recommendation System based on Audio Signals and Emotions","authors":"V. Mounika, Y. Charitha","doi":"10.1109/ICICT57646.2023.10134211","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134211","url":null,"abstract":"The identity of emotional speech is a significant topic within the discipline of interactions between humans and computers. Many strategies of figuring out emotions in human speech had been introduced and installed through diverse researchers. To identify noises in audio documents is the purpose of one of these versions. Together with gender recognition and YouTube video will be played depending on mood, this suggested computer also features speech emotion detection, which listens for sentiments like happiness, rage, and sadness in audio cues. This output is sent as input to YouTube, which plays song within the user's mind, resulting in the person's temper to stabilize fast. Using the CNN characteristic extraction approach, the function sizes vector become processed with NumPy, and the audio class became carried out in MFCC. This research study mainly uses two programs: RAVDESS and SAVEE. Using the acquired datasets, a new version of the look was produced in-depth. The device area is the platform where the Google Colab is used to perform code execution.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114304322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134427
M. Keerthiga, D. Abisha, P. Kalaiselvi, S. Shenbagalakshmi
In today's environment, young people frequently use social media platforms to communicate emotions. They post about their feelings on social media, which can help us understand how they feel at the time. As a reaction to the critical need for early detection tools, this research study uses sentiment analysis techniques to examine user contributions to social networks to help detect potential depression at an early stage. The research describes different methods for predicting sadness from user posts. The dataset is vectorised using count vectoriser and TF-IDFvectorizer, and features like post sentiment is retrieved. In our project, the model is divided into training and test datasets and trained using the Naive Bayes, Support Vector Machine, Decision Trees, Random Forest, and K-Nearest Neighbors machine learning techniques. The measures that are assessed are recall and accuracy. The Instagram API is applied to mine Instagram posts to create the dataset for the model. Each comment will undergo pre processing; each word will be processed through a lexicon to determine if it is positive or negative. This research study presents a new feature vector for classifying the texts as positive or negative. Each comment generates a score value from the lexicon to signify the degree of positivity, negativity, and other factors. A CSV file containing around 6,300 posts has been preprocessed. The distinctive characters and extraneous characters are eliminated using regular expressions. The data quality is then enhanced using stop words, Lemmatization, and tokenization. The best method for this approach yields an accuracy of 90.19% and a recall of 89.85% utilizing a decision tree model using a count vectorizer.
{"title":"Machine Learning-based Depression Prediction using Social Media Feeds","authors":"M. Keerthiga, D. Abisha, P. Kalaiselvi, S. Shenbagalakshmi","doi":"10.1109/ICICT57646.2023.10134427","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134427","url":null,"abstract":"In today's environment, young people frequently use social media platforms to communicate emotions. They post about their feelings on social media, which can help us understand how they feel at the time. As a reaction to the critical need for early detection tools, this research study uses sentiment analysis techniques to examine user contributions to social networks to help detect potential depression at an early stage. The research describes different methods for predicting sadness from user posts. The dataset is vectorised using count vectoriser and TF-IDFvectorizer, and features like post sentiment is retrieved. In our project, the model is divided into training and test datasets and trained using the Naive Bayes, Support Vector Machine, Decision Trees, Random Forest, and K-Nearest Neighbors machine learning techniques. The measures that are assessed are recall and accuracy. The Instagram API is applied to mine Instagram posts to create the dataset for the model. Each comment will undergo pre processing; each word will be processed through a lexicon to determine if it is positive or negative. This research study presents a new feature vector for classifying the texts as positive or negative. Each comment generates a score value from the lexicon to signify the degree of positivity, negativity, and other factors. A CSV file containing around 6,300 posts has been preprocessed. The distinctive characters and extraneous characters are eliminated using regular expressions. The data quality is then enhanced using stop words, Lemmatization, and tokenization. The best method for this approach yields an accuracy of 90.19% and a recall of 89.85% utilizing a decision tree model using a count vectorizer.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134366
Vandana Rawat, Neelam Singh, Rahul Bijalwan, P. Verma
Internet of things (IoT) is a fast and conforming technology, having a standard emergence primarily connected to the wireless communication between actuators, gadgets, and electrical services all in general referred to as instructions. Developmental services refer to the activities and services promoting community development and are considered as an integral part of developmental services, which include seamless and coherent experience. It is a phenomenon rich in technical skills and broader experiences consisting of mechanical frameworks and platforms, which aim towards selecting the most efficient and cost-effective tools. The collection of valuable information and relaying on them accurately are the two most important features provided by the efficient IoT services.
{"title":"Application of Developmental Services based on IoT Efficiency","authors":"Vandana Rawat, Neelam Singh, Rahul Bijalwan, P. Verma","doi":"10.1109/ICICT57646.2023.10134366","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134366","url":null,"abstract":"Internet of things (IoT) is a fast and conforming technology, having a standard emergence primarily connected to the wireless communication between actuators, gadgets, and electrical services all in general referred to as instructions. Developmental services refer to the activities and services promoting community development and are considered as an integral part of developmental services, which include seamless and coherent experience. It is a phenomenon rich in technical skills and broader experiences consisting of mechanical frameworks and platforms, which aim towards selecting the most efficient and cost-effective tools. The collection of valuable information and relaying on them accurately are the two most important features provided by the efficient IoT services.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114514961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134162
P. Kalaivani, A. Dhivya, G. Dharani, S. Bharathi, C. Rajan
Early detection of pneumonia disease and COVID-19 can increase the survival rate of patients with lung infections. While the signs and symptoms of COVID-19 and pneumonia are quite similar, a chest X-ray can distinguish between the two to identify and diagnose each condition. A trained radiologist may find it challenging to distinguish between pneumonia and COVID-19 from CXR pictures since manual mistakes are quite likely to occur. The classification of images for use in medical imaging and other fields benefits greatly from deep learning techniques. The problem statement is that it is difficult to distinguish COVID-19 infection from pneumonia using chest X-rays since they both have similar symptoms. Here the work depicts by comparing various CNN models and detects the differences in chest X-rays for the identification of diseases, with high accuracies. A new approach to the multi-classification method is accomplished. Preprocessing techniques such as histogram equalization and bilateral filtering are used to enhance the quality of chest X-ray images [1]. The proposed system is experienced with the CNN architectures such as VGG16 and InceptionV3 which are used for multiclassification. It is noted that InceptionV3 is less expensive. The comparison is done between both the models, and the accuracies are compared to identify the best model. VGG16 attained an accuracy of 88%, and InceptionV3 attained the highest accuracy with 93%. All architecture performances are compared using various classification metrics forestimating the performance of DL techniques.
{"title":"Deep Learning with Multi-Class Classification for Detection of Covid-19 and Pneumonia","authors":"P. Kalaivani, A. Dhivya, G. Dharani, S. Bharathi, C. Rajan","doi":"10.1109/ICICT57646.2023.10134162","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134162","url":null,"abstract":"Early detection of pneumonia disease and COVID-19 can increase the survival rate of patients with lung infections. While the signs and symptoms of COVID-19 and pneumonia are quite similar, a chest X-ray can distinguish between the two to identify and diagnose each condition. A trained radiologist may find it challenging to distinguish between pneumonia and COVID-19 from CXR pictures since manual mistakes are quite likely to occur. The classification of images for use in medical imaging and other fields benefits greatly from deep learning techniques. The problem statement is that it is difficult to distinguish COVID-19 infection from pneumonia using chest X-rays since they both have similar symptoms. Here the work depicts by comparing various CNN models and detects the differences in chest X-rays for the identification of diseases, with high accuracies. A new approach to the multi-classification method is accomplished. Preprocessing techniques such as histogram equalization and bilateral filtering are used to enhance the quality of chest X-ray images [1]. The proposed system is experienced with the CNN architectures such as VGG16 and InceptionV3 which are used for multiclassification. It is noted that InceptionV3 is less expensive. The comparison is done between both the models, and the accuracies are compared to identify the best model. VGG16 attained an accuracy of 88%, and InceptionV3 attained the highest accuracy with 93%. All architecture performances are compared using various classification metrics forestimating the performance of DL techniques.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117065250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-26DOI: 10.1109/ICICT57646.2023.10134056
Y. P. G. Reedy, K. Jagadeesh, A. Pravin
Air pollution has a negative impact on our ability to do daily tasks and on our standard of living. Ecosystems and human well-being are under danger. Recent years have seen a notable increase in heavy industry, leaving it even more important to monitor air quality. When it comes to air quality, individuals must be aware of how much control they have. This study proposes a network of sensors to track changes in the air. The Arduino was employed as the platform's microcontroller. The purpose of the air pollution surveillance systems is to continuously track and record data on the state of the air around a certain location and upload that information to a central server for safekeeping and online access. Parts-per-million measures used to quantify pollution levels, and the results were evaluated in Microsoft Excel. The system's ability to monitor air quality as planned worked as intended. The results were displayed on the bespoke hardware's ui and were also stored in the cloud, where they could be accessed by anybody with a smartphone.
{"title":"Air Quality Evaluator using Arduino","authors":"Y. P. G. Reedy, K. Jagadeesh, A. Pravin","doi":"10.1109/ICICT57646.2023.10134056","DOIUrl":"https://doi.org/10.1109/ICICT57646.2023.10134056","url":null,"abstract":"Air pollution has a negative impact on our ability to do daily tasks and on our standard of living. Ecosystems and human well-being are under danger. Recent years have seen a notable increase in heavy industry, leaving it even more important to monitor air quality. When it comes to air quality, individuals must be aware of how much control they have. This study proposes a network of sensors to track changes in the air. The Arduino was employed as the platform's microcontroller. The purpose of the air pollution surveillance systems is to continuously track and record data on the state of the air around a certain location and upload that information to a central server for safekeeping and online access. Parts-per-million measures used to quantify pollution levels, and the results were evaluated in Microsoft Excel. The system's ability to monitor air quality as planned worked as intended. The results were displayed on the bespoke hardware's ui and were also stored in the cloud, where they could be accessed by anybody with a smartphone.","PeriodicalId":126489,"journal":{"name":"2023 International Conference on Inventive Computation Technologies (ICICT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117157506","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：