Pub Date : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088309
C. Kumar, S. Ajmera, B. Kumar, D. Srikar, S. Prasad, J. R. Datta
One of the essential and important roles in a country's protection is performed with the aid of the navy squaddies. Every year squaddies get strayed or injured and it's time consuming to do seek and rescue operations. In this paper, we present a WSN-primarily based environmental and fitness tracking technique wherein sensor information is processed using sturdy and solid algorithm carried out in controller. The observed data or information is shared to control room or base station using Internet of Think (IoT) technology. The developed mythologies are worked with excellent feaster using some peripheral devices like as tiny wearable psychological devices, sensors and transmission modules. Using these peripheral gadgets, it is viable to put into effect a low- cost mechanism to guard precious human life on the battlefield.
{"title":"Real-time Embedded Electronics using Wireless Connection for Soldier Security","authors":"C. Kumar, S. Ajmera, B. Kumar, D. Srikar, S. Prasad, J. R. Datta","doi":"10.1109/ASSIC55218.2022.10088309","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088309","url":null,"abstract":"One of the essential and important roles in a country's protection is performed with the aid of the navy squaddies. Every year squaddies get strayed or injured and it's time consuming to do seek and rescue operations. In this paper, we present a WSN-primarily based environmental and fitness tracking technique wherein sensor information is processed using sturdy and solid algorithm carried out in controller. The observed data or information is shared to control room or base station using Internet of Think (IoT) technology. The developed mythologies are worked with excellent feaster using some peripheral devices like as tiny wearable psychological devices, sensors and transmission modules. Using these peripheral gadgets, it is viable to put into effect a low- cost mechanism to guard precious human life on the battlefield.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114774709","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088362
Prachi Vijayeeta, Parthasarathi Pattnayak
The preceding decade has brought huge development in voice assistants. The speech recognition system along with cognitive and linguistic system are interdisciplinary areas that contribute to the field of speech construction and auditory observation. This study aims at developing a speech recognition system with the help of Recurrence Neural Network (RNN), a deep learning model for identifying the voice signals. This mechanism reduces the use of input devices and hardly requires more knowledge on feature selection. The hidden layers monitor the time sequence of audio signals between the transformation from one layer to another. The word error rate is the metric used to evaluate the efficiency of the model based on the number pf epochs and the input size.
{"title":"An Enhanced Voice Assistance using Recurrent Neural Network","authors":"Prachi Vijayeeta, Parthasarathi Pattnayak","doi":"10.1109/ASSIC55218.2022.10088362","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088362","url":null,"abstract":"The preceding decade has brought huge development in voice assistants. The speech recognition system along with cognitive and linguistic system are interdisciplinary areas that contribute to the field of speech construction and auditory observation. This study aims at developing a speech recognition system with the help of Recurrence Neural Network (RNN), a deep learning model for identifying the voice signals. This mechanism reduces the use of input devices and hardly requires more knowledge on feature selection. The hidden layers monitor the time sequence of audio signals between the transformation from one layer to another. The word error rate is the metric used to evaluate the efficiency of the model based on the number pf epochs and the input size.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125457705","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}
Sentiment Analysis a subset of Affective Computing is often categorized as a Natural Language Processing task and is restricted to the textual modality. Since the world around us is multimodal, i.e., we see things, listen to sounds, and feel the various textures of objects, sentiment analysis must be applied to the different modalities present in our daily lives. In this paper, we have implemented sentiment analysis on the following two modalities - text and image. The study compares the performance of individual single-modal models to the performance of a multimodal model for the task of sentiment analysis. This study employs the use of a functional RNN model for textual sentiment analysis and a functional CNN model for visual sentiment analysis. Multimodality is achieved by performing fusion. Additionally, a comparison of two types of fusion is explored, namely Intermediate fusion and Late fusion. There is an improvement from previous studies that is evident from the experimental results where our fusion model gives an accuracy of 79.63%. The promising results from the study will prove to be helpful for budding researchers in exploring prospects in the field of multimodality and affective domain.
{"title":"Evaluation of Fusion Techniques for Multi-modal Sentiment Analysis","authors":"Rishabh Shinde, Pallavi Udatewar, Amruta Nandargi, Siddarth Mohan, Ranjana Agrawal, Pankaj Nirale","doi":"10.1109/ASSIC55218.2022.10088291","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088291","url":null,"abstract":"Sentiment Analysis a subset of Affective Computing is often categorized as a Natural Language Processing task and is restricted to the textual modality. Since the world around us is multimodal, i.e., we see things, listen to sounds, and feel the various textures of objects, sentiment analysis must be applied to the different modalities present in our daily lives. In this paper, we have implemented sentiment analysis on the following two modalities - text and image. The study compares the performance of individual single-modal models to the performance of a multimodal model for the task of sentiment analysis. This study employs the use of a functional RNN model for textual sentiment analysis and a functional CNN model for visual sentiment analysis. Multimodality is achieved by performing fusion. Additionally, a comparison of two types of fusion is explored, namely Intermediate fusion and Late fusion. There is an improvement from previous studies that is evident from the experimental results where our fusion model gives an accuracy of 79.63%. The promising results from the study will prove to be helpful for budding researchers in exploring prospects in the field of multimodality and affective domain.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125963391","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 social media platforms are tremendously used nowadays. A huge amount of realistic data are being created everyday. The data are mainly feelings, emotions, mood of a person. The innovative research from these online users data are to predict levels posts such as negative or positive. The blogging sites like twitter, facebook, instagram have become so popular places to express online users thoughts and feelings. The data can be extensively filtered and used for the purpose of analyzing the depression levels. This can be a great platform for deep learning research. The social media tweets and comments are utilized. The two models simple BI-LSTM along with hybrid model of BERT CNN BI-LSTM is implemented. The hybrid model of BERT CNN BI-LSTM which achieves a higher accuracy than other deep learning models and the BERT Model is efficiently handles the different types of social media users data.
{"title":"Novel depression detection technique using Bert on social media","authors":"Asheema Pandey, Subhasis Mohapatra, Jibitesh Mishra, Ritesh Kumar Sinha","doi":"10.1109/ASSIC55218.2022.10088304","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088304","url":null,"abstract":"The social media platforms are tremendously used nowadays. A huge amount of realistic data are being created everyday. The data are mainly feelings, emotions, mood of a person. The innovative research from these online users data are to predict levels posts such as negative or positive. The blogging sites like twitter, facebook, instagram have become so popular places to express online users thoughts and feelings. The data can be extensively filtered and used for the purpose of analyzing the depression levels. This can be a great platform for deep learning research. The social media tweets and comments are utilized. The two models simple BI-LSTM along with hybrid model of BERT CNN BI-LSTM is implemented. The hybrid model of BERT CNN BI-LSTM which achieves a higher accuracy than other deep learning models and the BERT Model is efficiently handles the different types of social media users data.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131461823","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088414
Venkata Sai Praveen Gunda, Harshavardhan Gulla, Vishalteja Kosana, Shivani Janapati
This study proposes a deep learning-based framework for recognizing cows based on images of their muzzle, and faces. This method works well when dealing with missing or false insurance claims. This study proposes a hybrid multi-stage framework consisting of different phases such as augmentation, denoising, enhancement, and classification. The proposed framework is developed by hybridizing convolutional denoising autoencoders (CDAE), least squares generative adversarial network (LS-GAN), Xception feature extractor, and a convolutional neural network (CNN). CDAE is used to initiate the process of denoising noisy images. LS-GAN is used to improve the characteristics of denoised images by enhancing the image by elimination of the residual noise. The Xception is utilised to extract significant and optimal features, and CNN is then used for classification. Various comparative methodologies are used to assess the proposed approach at different phases through several statistical measures. The proposed framework achieved 97.27% accuracy using the test datasets, which is higher than the comparative approaches.
{"title":"A hybrid deep learning based robust framework for cattle identification","authors":"Venkata Sai Praveen Gunda, Harshavardhan Gulla, Vishalteja Kosana, Shivani Janapati","doi":"10.1109/ASSIC55218.2022.10088414","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088414","url":null,"abstract":"This study proposes a deep learning-based framework for recognizing cows based on images of their muzzle, and faces. This method works well when dealing with missing or false insurance claims. This study proposes a hybrid multi-stage framework consisting of different phases such as augmentation, denoising, enhancement, and classification. The proposed framework is developed by hybridizing convolutional denoising autoencoders (CDAE), least squares generative adversarial network (LS-GAN), Xception feature extractor, and a convolutional neural network (CNN). CDAE is used to initiate the process of denoising noisy images. LS-GAN is used to improve the characteristics of denoised images by enhancing the image by elimination of the residual noise. The Xception is utilised to extract significant and optimal features, and CNN is then used for classification. Various comparative methodologies are used to assess the proposed approach at different phases through several statistical measures. The proposed framework achieved 97.27% accuracy using the test datasets, which is higher than the comparative approaches.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134160818","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088372
Sanjukta Mohanty, Satya Prakash Dwivedy, A. Acharya, Suvakanta Mohapatra, Shivam Swastik Sahoo, Sibadatta Samal, Smrutisrita Samal
Today our world experiences a large number of active social media users daily, twitter being one the most used platform for discussion on various topics like politics, sports, entertainment etc. It highly influences people's lives and therefore it is required to maintain a healthy environment in such places. Thus these places eventually become the epicenter of malicious activities, wherein someone tries to share hate or manipulate information as per their own interest. The common mass which comprises the most part of the user base having limited knowledge of such things, fall prey to these activities. At present millions of such automated accounts exist, also known as bots which are involved in malicious activities like spreading misinformation and manipulating public opinion. The work presented here is aimed at developing a framework by implementing ensemble machine learning approaches like Adaptive boosting, Gradient boost (GB) and Extreme Gradient boost (XGB) to detect these twitter bots. We have used a dataset that is publicly available from database community and evaluate our proposed approach to predict whether the user account is a bot or non-bot. Our experiment demonstrates that the estimator GB achieves highest accuracy in detecting the social bots.
{"title":"Enhancing the Detection of Social bots on Twitter using Ensemble machine Learning Technique","authors":"Sanjukta Mohanty, Satya Prakash Dwivedy, A. Acharya, Suvakanta Mohapatra, Shivam Swastik Sahoo, Sibadatta Samal, Smrutisrita Samal","doi":"10.1109/ASSIC55218.2022.10088372","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088372","url":null,"abstract":"Today our world experiences a large number of active social media users daily, twitter being one the most used platform for discussion on various topics like politics, sports, entertainment etc. It highly influences people's lives and therefore it is required to maintain a healthy environment in such places. Thus these places eventually become the epicenter of malicious activities, wherein someone tries to share hate or manipulate information as per their own interest. The common mass which comprises the most part of the user base having limited knowledge of such things, fall prey to these activities. At present millions of such automated accounts exist, also known as bots which are involved in malicious activities like spreading misinformation and manipulating public opinion. The work presented here is aimed at developing a framework by implementing ensemble machine learning approaches like Adaptive boosting, Gradient boost (GB) and Extreme Gradient boost (XGB) to detect these twitter bots. We have used a dataset that is publicly available from database community and evaluate our proposed approach to predict whether the user account is a bot or non-bot. Our experiment demonstrates that the estimator GB achieves highest accuracy in detecting the social bots.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"240 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133486932","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088396
Tridiv Swain, Sushruta Mishra
In recent years, autonomous vehicles have been a hot topic of debate. Several major automakers, including many worldwide companies, are attempting to be pioneers in autonomous vehicle technology. Google Waymo, and Aptiv, for example, are all working on self-driving car technology. Radar, Lidar, sonar, GPS, and odometer are some of the technologies utilized in the development of autonomous vehicles to recognize their surroundings. An automatic control system is used to control navigation based on the data collected from these sensors. This study will look at how the CNN deep learning algorithm can be used to recognize the surrounding environment and produce the automatic navigation required for self-driving cars. The designed system will generate and learn the data set ahead of time, then use the learning outputs in an open simulation environment. By analysing the settings of an autonomous car, this simulation displays a high level of accuracy in learning to control it. This not only focused on simulation but also focused on predicting a high accuracy model which will be more scalable.
{"title":"Evolution Of Machine Learning Algorithms For Enhancement Of Self-Driving Vehicles Security","authors":"Tridiv Swain, Sushruta Mishra","doi":"10.1109/ASSIC55218.2022.10088396","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088396","url":null,"abstract":"In recent years, autonomous vehicles have been a hot topic of debate. Several major automakers, including many worldwide companies, are attempting to be pioneers in autonomous vehicle technology. Google Waymo, and Aptiv, for example, are all working on self-driving car technology. Radar, Lidar, sonar, GPS, and odometer are some of the technologies utilized in the development of autonomous vehicles to recognize their surroundings. An automatic control system is used to control navigation based on the data collected from these sensors. This study will look at how the CNN deep learning algorithm can be used to recognize the surrounding environment and produce the automatic navigation required for self-driving cars. The designed system will generate and learn the data set ahead of time, then use the learning outputs in an open simulation environment. By analysing the settings of an autonomous car, this simulation displays a high level of accuracy in learning to control it. This not only focused on simulation but also focused on predicting a high accuracy model which will be more scalable.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":" 35","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132188569","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088321
Biswaranjan Bhola, Raghvendra Kumar
The Internet of Things (IoT) is now extensively used. Sensors, processors, and communication hardware are among the smart devices that make up this ecosystem. IoT hubs are used in traditional IoT systems to act as a bridge between tiny underlying sensors and the cloud, allowing applications to accumulate, send, and analyse collected data in real time. The IoT hub and sensors are two separate isolated layers in the traditional system, which makes the system complex and increases network dependency. The purpose of this presented paper is to analyse and modify the IoT architecture in order to design an autonomous and distributed IoT module for a water meter system that supports the internet and the LoRa network. The module incorporates M2M (Machine to Machine) communication to address the aforementioned issue while also increasing the scalability of IoT water meter devices. The designed meter reading module can be used as an IoT device, connecting to the network via Ethernet, Wi-Fi, or LoRa WAN and providing an interface for users (cloud servers, people, and devices) to communicate with one another. Furthermore, the proposed modules are self-contained and can easily interface with any programming language. Resource management and security of IoT systems have also been taken into account. As a result, the water meter system's performance could be improved.
{"title":"Improvement of the IoT Computing Platform for water meter network","authors":"Biswaranjan Bhola, Raghvendra Kumar","doi":"10.1109/ASSIC55218.2022.10088321","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088321","url":null,"abstract":"The Internet of Things (IoT) is now extensively used. Sensors, processors, and communication hardware are among the smart devices that make up this ecosystem. IoT hubs are used in traditional IoT systems to act as a bridge between tiny underlying sensors and the cloud, allowing applications to accumulate, send, and analyse collected data in real time. The IoT hub and sensors are two separate isolated layers in the traditional system, which makes the system complex and increases network dependency. The purpose of this presented paper is to analyse and modify the IoT architecture in order to design an autonomous and distributed IoT module for a water meter system that supports the internet and the LoRa network. The module incorporates M2M (Machine to Machine) communication to address the aforementioned issue while also increasing the scalability of IoT water meter devices. The designed meter reading module can be used as an IoT device, connecting to the network via Ethernet, Wi-Fi, or LoRa WAN and providing an interface for users (cloud servers, people, and devices) to communicate with one another. Furthermore, the proposed modules are self-contained and can easily interface with any programming language. Resource management and security of IoT systems have also been taken into account. As a result, the water meter system's performance could be improved.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127106823","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088409
Mishahira N, Gayathri Geetha Nair, Mohammad Talal Houkan, K. K. Sadasivuni, M. Geetha, S. Al-Máadeed, Asiya Albusaidi, Nandhini Subramanian, H. Yalcin, H. Ouakad, I. Bahadur
cardiovascular diseases are the major cause of death worldwide. Early detection of heart failure will assist patients and medical professionals in taking better precautions to reduce risks. The objective of this study is to find a technique that can reliably forecast the risk of cardiovascular illnesses. With the help of the training data we offer, deep learning algorithms like Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) make these predictions. Prediction accuracy will be reduced by a lack of medical data. As a part of our study, we examined DNN architectures to forecast cardiac failure. Over the training data, existing deep learning methods were employed. A new deep learning method that can predict heart failure using RR interval measurements is developed by comparing the accuracy performance of the proposed and existing models. The Physiobank NSR-RR and CHF-RR databases were used to compile the findings. The new model, which was based on experimental findings using these two free RR interval databases, attained a 94% accuracy rate compared to the existing model's 93.1% accuracy rate.
{"title":"A New Deep Learning Method for Accurate Cardiac Heart Failure Prediction from RR Interval Measurements","authors":"Mishahira N, Gayathri Geetha Nair, Mohammad Talal Houkan, K. K. Sadasivuni, M. Geetha, S. Al-Máadeed, Asiya Albusaidi, Nandhini Subramanian, H. Yalcin, H. Ouakad, I. Bahadur","doi":"10.1109/ASSIC55218.2022.10088409","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088409","url":null,"abstract":"cardiovascular diseases are the major cause of death worldwide. Early detection of heart failure will assist patients and medical professionals in taking better precautions to reduce risks. The objective of this study is to find a technique that can reliably forecast the risk of cardiovascular illnesses. With the help of the training data we offer, deep learning algorithms like Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) make these predictions. Prediction accuracy will be reduced by a lack of medical data. As a part of our study, we examined DNN architectures to forecast cardiac failure. Over the training data, existing deep learning methods were employed. A new deep learning method that can predict heart failure using RR interval measurements is developed by comparing the accuracy performance of the proposed and existing models. The Physiobank NSR-RR and CHF-RR databases were used to compile the findings. The new model, which was based on experimental findings using these two free RR interval databases, attained a 94% accuracy rate compared to the existing model's 93.1% accuracy rate.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130400811","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 : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088347
Vijaya Kumar Reddy Kokatam, A. Doss
India is mainly an agricultural country. Agriculture assumes an essential part in the Indian economy. More than 70% of the country family units rely upon agriculture. Despite growth in other sectors, agriculture's overall contribution of GDP has decreased from 19.2 percent to 17 percent in 2018–19. When the yield is affected by pets like insect/ fungal/bacteria/viral diseases the efficiency of the yield is decrease. This problem can be overcome by identifying diseases. The recent advances in the deep learning made the classification accurately. Using Plant Village dataset of 5,300 images of disease and healthy plant leaves were collected. The deep learning convolutional neural network i.e., VGG16 were trained to identify the 14 disease leaves of corn and tomato. After identifying the disease an intimation message sent to farmer mobile number using telegram bot channel. Based on the study it is found that the deep learning algorithm is 86% efficiency for disease classification.
{"title":"Prediction of Corn and Tomato Plant Diseases Using Deep Learning Algorithm","authors":"Vijaya Kumar Reddy Kokatam, A. Doss","doi":"10.1109/ASSIC55218.2022.10088347","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088347","url":null,"abstract":"India is mainly an agricultural country. Agriculture assumes an essential part in the Indian economy. More than 70% of the country family units rely upon agriculture. Despite growth in other sectors, agriculture's overall contribution of GDP has decreased from 19.2 percent to 17 percent in 2018–19. When the yield is affected by pets like insect/ fungal/bacteria/viral diseases the efficiency of the yield is decrease. This problem can be overcome by identifying diseases. The recent advances in the deep learning made the classification accurately. Using Plant Village dataset of 5,300 images of disease and healthy plant leaves were collected. The deep learning convolutional neural network i.e., VGG16 were trained to identify the 14 disease leaves of corn and tomato. After identifying the disease an intimation message sent to farmer mobile number using telegram bot channel. Based on the study it is found that the deep learning algorithm is 86% efficiency for disease classification.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123885568","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：