Pub Date : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126228
Sushmitha Ramaneedi, P. Pati
Error creeps into text in various ways. Typing error may come due to either mis-typing or due to poor language expertise. Similarly, recognition technologies while converting textual images and speech into text may generate error due to their limitations. Irrespective of the channel of error induction, presence of error poses a huge challenge for downstream consumption of such textual content. Additionally, error present in Indian language textual documents come with their own set of issues. This necessitates focused study on the textual errors in Indian language documents and the various technologies which may be employed to eliminate them.This work proposes to employ mT5, a very popular deep learning based multi-lingual language model, to eliminate errors present in Kannada, an Indian Language, text. A pretrained model of mT5 is enhanced with transfer learning for a Kannada dataset. The ability of the enhanced mT5 model to reduce error is studied at various levels of noise. Character Error Rate (CER) is employed as the metric. It’s observed that the enhanced mT5 model is effectively able to reduce noise by 12% for input text with 25% CER.
{"title":"Kannada Textual Error Correction Using T5 Model","authors":"Sushmitha Ramaneedi, P. Pati","doi":"10.1109/I2CT57861.2023.10126228","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126228","url":null,"abstract":"Error creeps into text in various ways. Typing error may come due to either mis-typing or due to poor language expertise. Similarly, recognition technologies while converting textual images and speech into text may generate error due to their limitations. Irrespective of the channel of error induction, presence of error poses a huge challenge for downstream consumption of such textual content. Additionally, error present in Indian language textual documents come with their own set of issues. This necessitates focused study on the textual errors in Indian language documents and the various technologies which may be employed to eliminate them.This work proposes to employ mT5, a very popular deep learning based multi-lingual language model, to eliminate errors present in Kannada, an Indian Language, text. A pretrained model of mT5 is enhanced with transfer learning for a Kannada dataset. The ability of the enhanced mT5 model to reduce error is studied at various levels of noise. Character Error Rate (CER) is employed as the metric. It’s observed that the enhanced mT5 model is effectively able to reduce noise by 12% for input text with 25% CER.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129875693","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126170
Dr. Prabira Kumar Sethy, J. Nayak, M. Bhargavi, Himanshu Sekhar Maharana, S. Behera, S. Rathore
The disease known as monkeypox is caused by an Orthopoxvirus, a zoonotic virus. As a zoonotic virus, it can be transmitted from animals to people. Furthermore, it can be transmitted between people and can also be picked up from the environment and transferred to people. This makes early detection vital to preventing broad population transmission. This study suggests a method for early diagnosis of monkeypox utilising Improved Darknet 19, which is simple, compact, and computationally affordable. The accuracy of the proposed model was measured using a publicly available dataset (https://github.com/mahsan2/Monkeypox-dataset-2022). There was an increase in accuracy to 85.49 percent with the new and upgraded Darknet 19 model.
{"title":"Detection of Monkeypox Based on Improved Darknet19","authors":"Dr. Prabira Kumar Sethy, J. Nayak, M. Bhargavi, Himanshu Sekhar Maharana, S. Behera, S. Rathore","doi":"10.1109/I2CT57861.2023.10126170","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126170","url":null,"abstract":"The disease known as monkeypox is caused by an Orthopoxvirus, a zoonotic virus. As a zoonotic virus, it can be transmitted from animals to people. Furthermore, it can be transmitted between people and can also be picked up from the environment and transferred to people. This makes early detection vital to preventing broad population transmission. This study suggests a method for early diagnosis of monkeypox utilising Improved Darknet 19, which is simple, compact, and computationally affordable. The accuracy of the proposed model was measured using a publicly available dataset (https://github.com/mahsan2/Monkeypox-dataset-2022). There was an increase in accuracy to 85.49 percent with the new and upgraded Darknet 19 model.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129905260","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126211
N. Narmada, P. Pati
To evaluate a learner’s knowledge of programming language skills, assessments are given. Grading of these is usually done manually which not only is tedious but prone to error due to repetition and fatigue. In this work, we employ pre-trained language models to perform automated grading of "C" programming language. Embeddings from different transformers on pre-assessed codes are used as feature vectors to train a wide range of regressors for the scoring task. Root-mean-square error (RMSE) is the metric utilized to compare the scores of these regressors. It’s observed that embeddings from T5-model with CatBoost regressor gives the least error around 15%.
{"title":"Autograding of Programming Skills","authors":"N. Narmada, P. Pati","doi":"10.1109/I2CT57861.2023.10126211","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126211","url":null,"abstract":"To evaluate a learner’s knowledge of programming language skills, assessments are given. Grading of these is usually done manually which not only is tedious but prone to error due to repetition and fatigue. In this work, we employ pre-trained language models to perform automated grading of \"C\" programming language. Embeddings from different transformers on pre-assessed codes are used as feature vectors to train a wide range of regressors for the scoring task. Root-mean-square error (RMSE) is the metric utilized to compare the scores of these regressors. It’s observed that embeddings from T5-model with CatBoost regressor gives the least error around 15%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127203437","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126283
Tarun Kumar, Samli, Dilip Kumar
Wireless sensor network (WSN) technology is the amalgamation of numerous sensors exploited for monitoring and controlling the physical climate conditions. The integration of WSN technology in greenhouse farming has offered a new direction towards the production of crops. Greenhouse presents a protected environment for the plants/crops and facilitates the farmers in boosting their production. The paper presents a real-time greenhouse monitoring and controlling system. Humidity-Temperature sensor (DHT11), Soil Moisture sensor and Light sensor (LDR) are explored to measure the climate parameters accurately. To collect the real-time monitoring data from these sensors and transmit the data to the Firebase Cloud, the Wi-Fi module ESP8266 is attached to Arduino UNO. Further, an android application is developed for monitoring and controlling climate parameters via smart devices. The proposed model is efficient in terms of services and cost. The proposed automatic greenhouse monitoring and control system can facilitate the farmers in monitoring and controlling the climate conditions automatically as well as manually if the need arises. The developed application is user-friendly and can be efficiently utilized by farmers.
{"title":"Greenhouse Monitoring and Controlling using Cloud-Based Android Application","authors":"Tarun Kumar, Samli, Dilip Kumar","doi":"10.1109/I2CT57861.2023.10126283","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126283","url":null,"abstract":"Wireless sensor network (WSN) technology is the amalgamation of numerous sensors exploited for monitoring and controlling the physical climate conditions. The integration of WSN technology in greenhouse farming has offered a new direction towards the production of crops. Greenhouse presents a protected environment for the plants/crops and facilitates the farmers in boosting their production. The paper presents a real-time greenhouse monitoring and controlling system. Humidity-Temperature sensor (DHT11), Soil Moisture sensor and Light sensor (LDR) are explored to measure the climate parameters accurately. To collect the real-time monitoring data from these sensors and transmit the data to the Firebase Cloud, the Wi-Fi module ESP8266 is attached to Arduino UNO. Further, an android application is developed for monitoring and controlling climate parameters via smart devices. The proposed model is efficient in terms of services and cost. The proposed automatic greenhouse monitoring and control system can facilitate the farmers in monitoring and controlling the climate conditions automatically as well as manually if the need arises. The developed application is user-friendly and can be efficiently utilized by farmers.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127371611","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126365
Shireesha Gorre, Palash Mishra, M. Agrawal, A. Paramane, S. Chatterjee
Room temperature vulcanized (RTV) silicon rubber (SiR) is widely employed as the coating material for ceramic based insulating bushings of power transformers because of its excellent hydrophobicity and dielectric properties. However, due to oil leaks, transformer oil may seriously impair the performance of RTV silicon rubber coverings. The purpose of this study is to examine the decay of silicon rubber (SiR) when aged in transformer oil. Therefore, pure SiR, SiR + 40% micro Aluminium Tri Hydrate (ATH), SiR + 4% nano Silica (SiO2) and SiR + 10% micro ATH + 5% nano SiO2 blends were prepared. The degradation dynamics of all the samples post transformer oil ageing was studied using several physiochemical and electrical techniques studies viz. moisture diffusion, surface hydrophobicity, leakage current, corona inception voltage and shore A hardness measurements. In the end, based on the experimental outcomes best composite formulation is reported.
{"title":"Effect of Transformer oil on Silicon Rubber Nano-Micro Composites","authors":"Shireesha Gorre, Palash Mishra, M. Agrawal, A. Paramane, S. Chatterjee","doi":"10.1109/I2CT57861.2023.10126365","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126365","url":null,"abstract":"Room temperature vulcanized (RTV) silicon rubber (SiR) is widely employed as the coating material for ceramic based insulating bushings of power transformers because of its excellent hydrophobicity and dielectric properties. However, due to oil leaks, transformer oil may seriously impair the performance of RTV silicon rubber coverings. The purpose of this study is to examine the decay of silicon rubber (SiR) when aged in transformer oil. Therefore, pure SiR, SiR + 40% micro Aluminium Tri Hydrate (ATH), SiR + 4% nano Silica (SiO2) and SiR + 10% micro ATH + 5% nano SiO2 blends were prepared. The degradation dynamics of all the samples post transformer oil ageing was studied using several physiochemical and electrical techniques studies viz. moisture diffusion, surface hydrophobicity, leakage current, corona inception voltage and shore A hardness measurements. In the end, based on the experimental outcomes best composite formulation is reported.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127475008","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126269
Uppin Rashmi, Tripty Singh, Sateesh Ambesange
Alzheimer's is one of the causes of dementia, which causes memory loss, problem-solving disability, speaking, and a lot more difficulties in day-to-day life. Generally, dementia is a loss of memory, problem-solving ability, language fluency, and other thinking abilities that severely affect day-to-day life. Alzheimer's creates a huge impact on family life, the economy, and finally, the country as a whole is affected. According to statistics every 3 seconds, one person develops dementia in the world and the estimates say that by 2030, 78 million people will be affected, and by 2050 139 million people will have dementia. Estimates say that the economic impact due to dementia by 2030 in the US will be $2.8 Trillion which causes a huge loss and needs to be avoided.Alzheimer's can be diagnosed at various stages, with different datasets like Magnetic Resonance Imaging (MRI) Test images, Speech Tests, Symptoms, genes, and other data. Several models are developed to diagnose, but doctors expect proper insights about results apart from diagnosis, so the paper explains the results using various explainable methods like SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME).Data Sets used are MRI Features data extracted with generic information, Cross-sectional MRI data, and Longitudinal MRI Data. The step-by-step data processing includes data balancing using SMOTEENN, and then data transferred, using Quantile Transformer and PCA dimension reduction technique for 6 features, and Meta machine learning model, first level six key machine learning methods and finally voting classifier with hyperparameter tuning to get performance, 97.6 %, Precision 95.8%, recall 97.9% and finally F1 Score 96.8%.
{"title":"MRI image based Ensemble Voting Classifier for Alzheimer's Disease Classification with Explainable AI Technique","authors":"Uppin Rashmi, Tripty Singh, Sateesh Ambesange","doi":"10.1109/I2CT57861.2023.10126269","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126269","url":null,"abstract":"Alzheimer's is one of the causes of dementia, which causes memory loss, problem-solving disability, speaking, and a lot more difficulties in day-to-day life. Generally, dementia is a loss of memory, problem-solving ability, language fluency, and other thinking abilities that severely affect day-to-day life. Alzheimer's creates a huge impact on family life, the economy, and finally, the country as a whole is affected. According to statistics every 3 seconds, one person develops dementia in the world and the estimates say that by 2030, 78 million people will be affected, and by 2050 139 million people will have dementia. Estimates say that the economic impact due to dementia by 2030 in the US will be $2.8 Trillion which causes a huge loss and needs to be avoided.Alzheimer's can be diagnosed at various stages, with different datasets like Magnetic Resonance Imaging (MRI) Test images, Speech Tests, Symptoms, genes, and other data. Several models are developed to diagnose, but doctors expect proper insights about results apart from diagnosis, so the paper explains the results using various explainable methods like SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME).Data Sets used are MRI Features data extracted with generic information, Cross-sectional MRI data, and Longitudinal MRI Data. The step-by-step data processing includes data balancing using SMOTEENN, and then data transferred, using Quantile Transformer and PCA dimension reduction technique for 6 features, and Meta machine learning model, first level six key machine learning methods and finally voting classifier with hyperparameter tuning to get performance, 97.6 %, Precision 95.8%, recall 97.9% and finally F1 Score 96.8%.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131354929","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126268
Kartik Patel, Sanjay Dasrao Deshmukh
With ever increasing demand and progress of telecommunication networks (4G, 5G and beyond) in industrial automation, smart cities, internet of things and vehicular communication, some of the key goals or challenges that need to be talked are capacity enhancement, better data rate, increased spectral efficiency, reduced latency and better Quality of Service (QoS) and Quality of Experience (QoE) to mobile users. The limitations of the 3G and 4G networks lies in the capacity because of the Orthogonal Multiple Access (OMA) they use in time, frequency, and code domain. To overcome this limitation 5G NR (New Radio) is developed by 3GPP. The multiple access technique used in 5G network is Non-Orthogonal Multiple Access (NOMA). This paper presents results of review and basic implementation of NOMA operations like superposition coding, Successive Interference Cancellation (SIC) and effect of it on bit error rate (BER) curve for two users and three users with different power weights. Authors have found that with large difference in the power weights assigned to user there is significant difference in the BER of users after decoding, also by changing the power weights assigned to users BER can be reduced at lower values of SNR.
{"title":"2S (Superposition Coding, Successive Interference Cancellation) Operations in NOMA Technology for 5G Networks: Review and Implementation","authors":"Kartik Patel, Sanjay Dasrao Deshmukh","doi":"10.1109/I2CT57861.2023.10126268","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126268","url":null,"abstract":"With ever increasing demand and progress of telecommunication networks (4G, 5G and beyond) in industrial automation, smart cities, internet of things and vehicular communication, some of the key goals or challenges that need to be talked are capacity enhancement, better data rate, increased spectral efficiency, reduced latency and better Quality of Service (QoS) and Quality of Experience (QoE) to mobile users. The limitations of the 3G and 4G networks lies in the capacity because of the Orthogonal Multiple Access (OMA) they use in time, frequency, and code domain. To overcome this limitation 5G NR (New Radio) is developed by 3GPP. The multiple access technique used in 5G network is Non-Orthogonal Multiple Access (NOMA). This paper presents results of review and basic implementation of NOMA operations like superposition coding, Successive Interference Cancellation (SIC) and effect of it on bit error rate (BER) curve for two users and three users with different power weights. Authors have found that with large difference in the power weights assigned to user there is significant difference in the BER of users after decoding, also by changing the power weights assigned to users BER can be reduced at lower values of SNR.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126294487","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126316
Yashal Railkar, Aditi Nasikkar, Sakshi Pawar, P. Patil, Rohini. G. Pise
Object detection has been studied by many researchers for important applications in the industry like detecting a road object for self-driving cars, medical research for detecting particular diseases, gesture control, etc. Object detection and recognition is incredibly very important wrt security purposes. As computers and models can work 24/7 it can watch for video surveillance in secure areas. Humans can quickly detect or make out what items are there in photos and photographs, where these images and pictures are located, and how they interact with systems when they see them. [1]. Object identification and tracking is a key challenge in CV systems and interactions, such as visual surveillance and human computer vision systems. Human visual systems are quick and precise, allowing them to handle complicated activities such as driving. Computers will be able to drive automobiles using improvised and speedy errorfree object identification algorithms, yet they will require specialized sensors and auxiliary gadgets to relay real-time scenarios. [1]Using exact object recognition and picture classification approaches, strategies, and methodologies, it is critical and essential for deciding autonomous driving in metropolitan situations. Many big companies are currently working on this and achieving their goals day by day. In this report a object detection system has been proposed which can detect various objects, in fact it can detect almost any object wrt. training given to the model. Proposed methodology for object detection in the report is You Look Only Once (YOLO).
许多研究人员已经研究了物体检测在工业中的重要应用，如自动驾驶汽车的道路物体检测，检测特定疾病的医学研究，手势控制等。目标检测和识别在安全方面是非常重要的。由于计算机和模型可以全天候工作，它可以在安全区域观看视频监控。人类可以快速检测或识别照片和照片中的物品，这些图像和照片位于何处，以及当他们看到它们时如何与系统交互。[1]。目标识别和跟踪是CV系统和交互中的一个关键挑战，例如视觉监控和人类计算机视觉系统。人类的视觉系统是快速和精确的，使他们能够处理复杂的活动，如驾驶。计算机将能够使用即兴的、快速无误的目标识别算法来驾驶汽车，但它们将需要专门的传感器和辅助设备来传递实时场景。[1]使用精确的目标识别和图像分类方法、策略和方法，对于在大都市情况下决定自动驾驶至关重要。许多大公司目前都在努力实现这一目标。本文提出了一种可以检测各种物体的目标检测系统，实际上它几乎可以检测任何物体。对模型进行训练。报告中提出的目标检测方法是You Look Only Once (YOLO)。
{"title":"Object Detection and Recognition System Using Deep Learning Method","authors":"Yashal Railkar, Aditi Nasikkar, Sakshi Pawar, P. Patil, Rohini. G. Pise","doi":"10.1109/I2CT57861.2023.10126316","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126316","url":null,"abstract":"Object detection has been studied by many researchers for important applications in the industry like detecting a road object for self-driving cars, medical research for detecting particular diseases, gesture control, etc. Object detection and recognition is incredibly very important wrt security purposes. As computers and models can work 24/7 it can watch for video surveillance in secure areas. Humans can quickly detect or make out what items are there in photos and photographs, where these images and pictures are located, and how they interact with systems when they see them. [1]. Object identification and tracking is a key challenge in CV systems and interactions, such as visual surveillance and human computer vision systems. Human visual systems are quick and precise, allowing them to handle complicated activities such as driving. Computers will be able to drive automobiles using improvised and speedy errorfree object identification algorithms, yet they will require specialized sensors and auxiliary gadgets to relay real-time scenarios. [1]Using exact object recognition and picture classification approaches, strategies, and methodologies, it is critical and essential for deciding autonomous driving in metropolitan situations. Many big companies are currently working on this and achieving their goals day by day. In this report a object detection system has been proposed which can detect various objects, in fact it can detect almost any object wrt. training given to the model. Proposed methodology for object detection in the report is You Look Only Once (YOLO).","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126405880","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126337
V. Mamatha, J. Kavitha
Manures, pesticides, agricultural chemicals, small and fragmented land holdings, and other problems plague agriculture in developing nations like India. Consumers is also demanding a healthier diet that is high in quality and free of agricultural chemicals and pesticides. The above mentioned difficulties and demands are met by using the system of hydroponics, which can be organic. This kind of agriculture could result in a high yield if properly controlled and monitored. A smart agriculture system based on web application is proposed for remote monitoring by combining an appropriate IoT platform with the necessary sensor network. The proposed system controls the necessary conditions for the plant to grow hydroponically, and cultivators can remotely control agriculture using IoT. Various sensors are deployed in the field to collect parameters such as temperature, humidity, pH and water content. The sensor data that has been collected and the external input data such as the District Name, Crop Name, Area in acres and the Type of Hydroponics system is then sent to microcontroller, which in turn processes the data and then acts on it. The data that has been collected is sent to the cloud, processed and the notifications are delivered to the farmers. The proposed web application provides the farmers with an estimate of how much crop yield will be produced based on the given sensor and user input. The crop yield prediction is provided in tones and is estimated using Random Forest algorithm.
{"title":"Remotely monitored Web based Smart Hydroponics System for Crop Yield Prediction using IoT","authors":"V. Mamatha, J. Kavitha","doi":"10.1109/I2CT57861.2023.10126337","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126337","url":null,"abstract":"Manures, pesticides, agricultural chemicals, small and fragmented land holdings, and other problems plague agriculture in developing nations like India. Consumers is also demanding a healthier diet that is high in quality and free of agricultural chemicals and pesticides. The above mentioned difficulties and demands are met by using the system of hydroponics, which can be organic. This kind of agriculture could result in a high yield if properly controlled and monitored. A smart agriculture system based on web application is proposed for remote monitoring by combining an appropriate IoT platform with the necessary sensor network. The proposed system controls the necessary conditions for the plant to grow hydroponically, and cultivators can remotely control agriculture using IoT. Various sensors are deployed in the field to collect parameters such as temperature, humidity, pH and water content. The sensor data that has been collected and the external input data such as the District Name, Crop Name, Area in acres and the Type of Hydroponics system is then sent to microcontroller, which in turn processes the data and then acts on it. The data that has been collected is sent to the cloud, processed and the notifications are delivered to the farmers. The proposed web application provides the farmers with an estimate of how much crop yield will be produced based on the given sensor and user input. The crop yield prediction is provided in tones and is estimated using Random Forest algorithm.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122341458","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 : 2023-04-07DOI: 10.1109/I2CT57861.2023.10126251
S. V, S. Koolagudi
Human beings have the ability to identify a particular event occurring in a surrounding based on sound cues even when no visual scenes are presented. Sound events are the auditory cues that are present in a surrounding. Sound event detection (SED) is the process of determining the beginning and end of sound events as well as a textual label for the event. The term sound source localization (SSL) refers to the process of identifying the spatial location of a sound occurrence in addition to the SED. The integrated task of SED and SSL is known as Sound Event Localization and Detection (SELD). In this proposed work, three different deep learning architectures are explored to perform SELD. The three deep learning architectures are SELDNet, D-SELDNet (Depthwise Convolution), and T-SELDNet (Transpose Convolution). Two sets of features are used to perform SED and Direction-of-Arrival (DOA) estimation tasks in this work. D-SELDNet uses a Depthwise convolution layer which helps reduce the model’s complexity in terms of computation time. T-SELDNet uses Transpose Convolution, which helps in learning better discriminative features by retaining the input size and not losing necessary information from the input. The proposed method is evaluated on the First-order Ambisonic (FOA) array format of the TAU-NIGENS Spatial Sound Events 2020 dataset. An improvement has been observed as compared to the existing SELD systems with the proposed T-SELDNet.
{"title":"A Transpose-SELDNet for Polyphonic Sound Event Localization and Detection","authors":"S. V, S. Koolagudi","doi":"10.1109/I2CT57861.2023.10126251","DOIUrl":"https://doi.org/10.1109/I2CT57861.2023.10126251","url":null,"abstract":"Human beings have the ability to identify a particular event occurring in a surrounding based on sound cues even when no visual scenes are presented. Sound events are the auditory cues that are present in a surrounding. Sound event detection (SED) is the process of determining the beginning and end of sound events as well as a textual label for the event. The term sound source localization (SSL) refers to the process of identifying the spatial location of a sound occurrence in addition to the SED. The integrated task of SED and SSL is known as Sound Event Localization and Detection (SELD). In this proposed work, three different deep learning architectures are explored to perform SELD. The three deep learning architectures are SELDNet, D-SELDNet (Depthwise Convolution), and T-SELDNet (Transpose Convolution). Two sets of features are used to perform SED and Direction-of-Arrival (DOA) estimation tasks in this work. D-SELDNet uses a Depthwise convolution layer which helps reduce the model’s complexity in terms of computation time. T-SELDNet uses Transpose Convolution, which helps in learning better discriminative features by retaining the input size and not losing necessary information from the input. The proposed method is evaluated on the First-order Ambisonic (FOA) array format of the TAU-NIGENS Spatial Sound Events 2020 dataset. An improvement has been observed as compared to the existing SELD systems with the proposed T-SELDNet.","PeriodicalId":150346,"journal":{"name":"2023 IEEE 8th International Conference for Convergence in Technology (I2CT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125275701","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：