For any business, it is essential to predict the sales of future months for proper stock maintenance. Especially, in the pharmaceutical drug business, it is crucial to restrict the wastage of drugs due to expiry dates. As of now, most pharmacists and drug sellers predict future drug sales manually on their own sales experience. However, artificial intelligence and machine learning can play a vital role here by predicting drug sales using past sales records. In this study, we are employing machine learning algorithms such as Linear Regression, Random Forest, Support Vector Machine, and XGBoost on the sales data to predict future sales and compare the accuracy of different algorithms on some specific kinds of most used drugs globally. The dataset which was used consisted of drug sales from various drugs such as antipyretics, antihistamines, etc. The dataset consisted of hourly, weekly, monthly, and yearly sales data. After pre-processing the data, the four machine learning algorithms were used to predict future sales. According to our findings, The XGboost Model performed well compared to the other three models used to predict sales. The results are shown using graphs and tables.
{"title":"Comparative Study of Various Machine Learning Algorithms for Pharmaceutical Drug Sales Prediction","authors":"Asmita Manna, Kavita Kolpe, Aniket Mhalungekar, Sainath Pattewar, Pushpak Kaloge, Ruturaj Patil","doi":"10.1109/IConSCEPT57958.2023.10169964","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10169964","url":null,"abstract":"For any business, it is essential to predict the sales of future months for proper stock maintenance. Especially, in the pharmaceutical drug business, it is crucial to restrict the wastage of drugs due to expiry dates. As of now, most pharmacists and drug sellers predict future drug sales manually on their own sales experience. However, artificial intelligence and machine learning can play a vital role here by predicting drug sales using past sales records. In this study, we are employing machine learning algorithms such as Linear Regression, Random Forest, Support Vector Machine, and XGBoost on the sales data to predict future sales and compare the accuracy of different algorithms on some specific kinds of most used drugs globally. The dataset which was used consisted of drug sales from various drugs such as antipyretics, antihistamines, etc. The dataset consisted of hourly, weekly, monthly, and yearly sales data. After pre-processing the data, the four machine learning algorithms were used to predict future sales. According to our findings, The XGboost Model performed well compared to the other three models used to predict sales. The results are shown using graphs and tables.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"245 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116142621","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170395
Abirami Srinivasan, Murugan Mahalingam, P. Raju
An emerging technology called the Internet of Things (IoT) connects number of different things with the three aspects of anything, anyplace, and anytime. Energy efficiency is a major necessity for this technology because of the large number of IoT gadgets and their close proximity to people. In general, Green IoT is achieved by concentrating on energy competency across several IoT platforms which lowers costs while lowering risks to human health. The Green Internet of Things (GIoT) is a method that uses substantially less energy than is required. Unquestionably, green networks in the Internet of Things (IoT) with sustainable architecture would use less electricity and have reduced operational expenses.
{"title":"An Exploration About Frameworks Based On Green Internet Of Things","authors":"Abirami Srinivasan, Murugan Mahalingam, P. Raju","doi":"10.1109/IConSCEPT57958.2023.10170395","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170395","url":null,"abstract":"An emerging technology called the Internet of Things (IoT) connects number of different things with the three aspects of anything, anyplace, and anytime. Energy efficiency is a major necessity for this technology because of the large number of IoT gadgets and their close proximity to people. In general, Green IoT is achieved by concentrating on energy competency across several IoT platforms which lowers costs while lowering risks to human health. The Green Internet of Things (GIoT) is a method that uses substantially less energy than is required. Unquestionably, green networks in the Internet of Things (IoT) with sustainable architecture would use less electricity and have reduced operational expenses.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122918634","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170717
C. Kumar, Guduru Pallavi, K. V. Kumar, Alikatti Mani Shankar, Manyam Sri Varun Raj
Inverters convert direct current or battery power into an alternating current. A multilevel inverter is more powerful than a conventional inverter. Multilevel Inverter has been developed to handle high and medium voltage applications. Multilevel Inverters are commercially used. Conventional Inverter produces a square waveform as output. Multilevel Inverters are used to produce almost equal to a sinusoidal waveform. Compared to the conventional inverter, the 9-level inverter has less harmonic distortion, lower electromagnetic interference, larger DC link voltages, significantly better output power quality, Minimum switching losses, etc. Multilevel Inverters use a reduced number of switches and generate output nearly sinusoidal output. This method uses ten switches to produce 9 levels of output. As this method requires less number of switches this reduces the complexity of the circuit. Based on the observational values like rms voltage, rms current, average voltage, and average current in MATLAB simulations, power loss analysis and efficiency of modified 9-level reduced switch symmetrical inverter parameters are analyzed.
{"title":"Power Loss Analysis Of Modified 9-Level Reduced Switch Symmetrical Inverter","authors":"C. Kumar, Guduru Pallavi, K. V. Kumar, Alikatti Mani Shankar, Manyam Sri Varun Raj","doi":"10.1109/IConSCEPT57958.2023.10170717","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170717","url":null,"abstract":"Inverters convert direct current or battery power into an alternating current. A multilevel inverter is more powerful than a conventional inverter. Multilevel Inverter has been developed to handle high and medium voltage applications. Multilevel Inverters are commercially used. Conventional Inverter produces a square waveform as output. Multilevel Inverters are used to produce almost equal to a sinusoidal waveform. Compared to the conventional inverter, the 9-level inverter has less harmonic distortion, lower electromagnetic interference, larger DC link voltages, significantly better output power quality, Minimum switching losses, etc. Multilevel Inverters use a reduced number of switches and generate output nearly sinusoidal output. This method uses ten switches to produce 9 levels of output. As this method requires less number of switches this reduces the complexity of the circuit. Based on the observational values like rms voltage, rms current, average voltage, and average current in MATLAB simulations, power loss analysis and efficiency of modified 9-level reduced switch symmetrical inverter parameters are analyzed.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116937178","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170016
P. Raju, S. Lakshmi Priya., S. Ksheeraja., B. Menaga., V. Ragul
Forests are one of the essential natural resources required to preserve the planet’s ecological equilibrium. This paper offers a technique for creating an extensive environmental monitoring system. Along with that, it keeps an check over illegal activities taking place nearby, such as invasion into reserved forest areas and natural calamities like forest fire. The datas will be captured, classified, and reported to the official by the device. This can be accomplished by interfacing various sensors like an flame sensor, an ultrasonic sensor, and a DHT sensor with Arduino Nano board. Additionally, it offers guidance on safety measures and has the capacity to forecast natural calamities. Results are compared to numerous cutting-edge methods for figuring out total performance. The concern of finite energy supplies, however, affects the sensor nodes used in such networks. Keeping this concern in mind, energy can be saved to a greater extend by implementing green IoT technologies. The continual changes in temperature and humidity may be observed using the Adafruit cloud platform. The internet connectivity that connects Arduino to the Adafruit platform is provided by Node MCU. Wi-Fi is the transmission technique used in this. Real-time application of Lora WAN technology is possible to link sensors to cloud platforms.
{"title":"Green IoT Framework for Deep Forest Surveillance","authors":"P. Raju, S. Lakshmi Priya., S. Ksheeraja., B. Menaga., V. Ragul","doi":"10.1109/IConSCEPT57958.2023.10170016","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170016","url":null,"abstract":"Forests are one of the essential natural resources required to preserve the planet’s ecological equilibrium. This paper offers a technique for creating an extensive environmental monitoring system. Along with that, it keeps an check over illegal activities taking place nearby, such as invasion into reserved forest areas and natural calamities like forest fire. The datas will be captured, classified, and reported to the official by the device. This can be accomplished by interfacing various sensors like an flame sensor, an ultrasonic sensor, and a DHT sensor with Arduino Nano board. Additionally, it offers guidance on safety measures and has the capacity to forecast natural calamities. Results are compared to numerous cutting-edge methods for figuring out total performance. The concern of finite energy supplies, however, affects the sensor nodes used in such networks. Keeping this concern in mind, energy can be saved to a greater extend by implementing green IoT technologies. The continual changes in temperature and humidity may be observed using the Adafruit cloud platform. The internet connectivity that connects Arduino to the Adafruit platform is provided by Node MCU. Wi-Fi is the transmission technique used in this. Real-time application of Lora WAN technology is possible to link sensors to cloud platforms.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127612049","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170332
Narayana Darapaneni, B. Sudha, A. Reddy, Ab Abdul Karim, Dhanalakshmi Marothu, S. Kulkarni, Deepak Das Menon
The field of computer vision is constantly expanding and evolving, and it has seen tremendous growth in recent years. Computer vision includes image classification as a fundamental component. The critical components for making the best decisions are image categorization and interpretation. This study intends to examine several etiology clots labels, such as Cardiac Embolic and Large Artery Atherosclerosis (CE & LAA), for researchers and practitioners of medical image analysis (particularly of blood clot origin). An analysis of the accuracy and processing speed of various image classification methods using neural network topologies. This report also describes the available medical data set and explains the performance measures of the techniques that are currently accessible. Some of the Deep Learning architectures, including CNN, VGG-16, Efficient-Net, and Res-Net, are studied in the article and discuss the trends with challenges in the application of medical image analysis.
{"title":"Image Classification of Stroke Blood Clot Origin","authors":"Narayana Darapaneni, B. Sudha, A. Reddy, Ab Abdul Karim, Dhanalakshmi Marothu, S. Kulkarni, Deepak Das Menon","doi":"10.1109/IConSCEPT57958.2023.10170332","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170332","url":null,"abstract":"The field of computer vision is constantly expanding and evolving, and it has seen tremendous growth in recent years. Computer vision includes image classification as a fundamental component. The critical components for making the best decisions are image categorization and interpretation. This study intends to examine several etiology clots labels, such as Cardiac Embolic and Large Artery Atherosclerosis (CE & LAA), for researchers and practitioners of medical image analysis (particularly of blood clot origin). An analysis of the accuracy and processing speed of various image classification methods using neural network topologies. This report also describes the available medical data set and explains the performance measures of the techniques that are currently accessible. Some of the Deep Learning architectures, including CNN, VGG-16, Efficient-Net, and Res-Net, are studied in the article and discuss the trends with challenges in the application of medical image analysis.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132257575","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170608
A. Punnoose
This paper discusses the experimental details of speech enhancement using variational autoencoders (VAE). A joint VAE architecture is formulated, and a training protocol that strikes a balance between speech enhancement and VAE correctness is defined. Extended short-term objective intelligibility (ESTOI) is used to measure the intelligibility of enhanced speech. The proposed approach is implemented using MFCC and STFT features on a benchmark dataset and we report, on an average, 2 times improvement in ESTOI for enhanced speech using MFCC over STFT features across all noise levels. Further, the proposed approach using MFCC features shows significant improvement in denoising very noisy speech, as opposed to marginal improvement on relatively clean speech.
{"title":"Speech Enhancement Using Variational Autoencoders","authors":"A. Punnoose","doi":"10.1109/IConSCEPT57958.2023.10170608","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170608","url":null,"abstract":"This paper discusses the experimental details of speech enhancement using variational autoencoders (VAE). A joint VAE architecture is formulated, and a training protocol that strikes a balance between speech enhancement and VAE correctness is defined. Extended short-term objective intelligibility (ESTOI) is used to measure the intelligibility of enhanced speech. The proposed approach is implemented using MFCC and STFT features on a benchmark dataset and we report, on an average, 2 times improvement in ESTOI for enhanced speech using MFCC over STFT features across all noise levels. Further, the proposed approach using MFCC features shows significant improvement in denoising very noisy speech, as opposed to marginal improvement on relatively clean speech.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132810010","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170335
S. Siva Suriya Narayanan, V. Yuvaraju, S. Thangavel
In the context of the Battery Management System (BMS) of an Electric Vehicle (EV), accurately predicting the terminal voltage of the battery is of utmost importance. However, this prediction model is dependent on the battery’s chemistry and its overall lifespan. To address this issue, this work presents a generalized procedure for implementing a Machine Learning (ML) based prediction model. Specifically, we compare the performance of five distinct regression techniques, namely, decision tree, ensemble boost and bagg, support vector machine, and neural network, using a supervised ML approach. The performance of the different regression techniques is evaluated by means of the Root Mean Square Error (RMSE). The proposed method of using ML techniques to develop an accurate prediction model for a specific task, as discussed in this work, has the potential to be implemented in various other regression tasks of engineering applications. Therefore, the approach presented in this work can serve as a blueprint for developing accurate prediction models in other engineering applications, provided that the relevant data and training are available.
{"title":"Regression Analysis in Electrical Engineering Applications: A Machine Learning Approach","authors":"S. Siva Suriya Narayanan, V. Yuvaraju, S. Thangavel","doi":"10.1109/IConSCEPT57958.2023.10170335","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170335","url":null,"abstract":"In the context of the Battery Management System (BMS) of an Electric Vehicle (EV), accurately predicting the terminal voltage of the battery is of utmost importance. However, this prediction model is dependent on the battery’s chemistry and its overall lifespan. To address this issue, this work presents a generalized procedure for implementing a Machine Learning (ML) based prediction model. Specifically, we compare the performance of five distinct regression techniques, namely, decision tree, ensemble boost and bagg, support vector machine, and neural network, using a supervised ML approach. The performance of the different regression techniques is evaluated by means of the Root Mean Square Error (RMSE). The proposed method of using ML techniques to develop an accurate prediction model for a specific task, as discussed in this work, has the potential to be implemented in various other regression tasks of engineering applications. Therefore, the approach presented in this work can serve as a blueprint for developing accurate prediction models in other engineering applications, provided that the relevant data and training are available.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132864357","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170458
M. C. Sekhar, G. Meghana, T. S. Varsha, K. S. Mohan, K. V. Reddy
The proposed design in this paper is a triangular microstrip patch antenna with inset feed with proper impedance matching without the addition of extra structure. This enhances the gain, and bandwidth of the antenna, and very low backward radiation also observed in the desired operating band. An elemental patch antenna is modeled on the substrate named FR4 with a height of 1.6mm and a dielectric constant of 4.4. The antenna was modeled using the High-Frequency Structure Simulator (HFSS) platform. This simulated model gives better performance and which is preferable for IoT Applications.
{"title":"Design of Linearly Polarized Triangular Microstrip Patch Antenna for IoT Applications","authors":"M. C. Sekhar, G. Meghana, T. S. Varsha, K. S. Mohan, K. V. Reddy","doi":"10.1109/IConSCEPT57958.2023.10170458","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170458","url":null,"abstract":"The proposed design in this paper is a triangular microstrip patch antenna with inset feed with proper impedance matching without the addition of extra structure. This enhances the gain, and bandwidth of the antenna, and very low backward radiation also observed in the desired operating band. An elemental patch antenna is modeled on the substrate named FR4 with a height of 1.6mm and a dielectric constant of 4.4. The antenna was modeled using the High-Frequency Structure Simulator (HFSS) platform. This simulated model gives better performance and which is preferable for IoT Applications.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133001147","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170207
Kota Ravi Kumar, R. Nakkeeran
Internet of Things (IoT) has achieved great recognition, in terms of identifying datasets through feature selection to increase the performance of the IoT network. In this situation, attacks will play a crucial role in choosing the performance of IoT networks. The Existing methodology like labeled transition could able to collect the data in such a way that the data can be accessed using a classification mechanism but with less feature selection. This may not lead to dimensionality reduction which may lead to a larger number of feature selections and thus making the system complex. The current research papers will focus on dimensionality reduction with less feature selection and retrieve the maximal contents of the datasets. This would assist the IoT users with a machine learning model to retrieve the data with fewer threats on the system. This is due to the maximal selection of the traits. This may lead to maximal DoS and minimal datasets feature selection.
{"title":"A Comprehensive Study on Denial of Service (DoS) Based on Feature Selection of a Given Set Datasets in Internet of Things (IoT)","authors":"Kota Ravi Kumar, R. Nakkeeran","doi":"10.1109/IConSCEPT57958.2023.10170207","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170207","url":null,"abstract":"Internet of Things (IoT) has achieved great recognition, in terms of identifying datasets through feature selection to increase the performance of the IoT network. In this situation, attacks will play a crucial role in choosing the performance of IoT networks. The Existing methodology like labeled transition could able to collect the data in such a way that the data can be accessed using a classification mechanism but with less feature selection. This may not lead to dimensionality reduction which may lead to a larger number of feature selections and thus making the system complex. The current research papers will focus on dimensionality reduction with less feature selection and retrieve the maximal contents of the datasets. This would assist the IoT users with a machine learning model to retrieve the data with fewer threats on the system. This is due to the maximal selection of the traits. This may lead to maximal DoS and minimal datasets feature selection.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130147286","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170073
Nomika Sree Kolla, Mythili Anumula, S. Sujana, M. Ratnababu
Nowadays managing the road garbage is essential. The waste disposal leads to pollution, climate change, water contamination etc. The major issue which is unresolved is dealing with the large amount of waste that is dumped in the environment rather than segregating properly. To overcome this problem, a deep learning algorithm is used to segregate the garbage which is beneficial for diminishing landfills, recycling etc. We use One MaxPool layer, one average pool layer, and 48 convolutional layers make up the 50-layer convolutional neural network known as ResNet50. The model that is used to categorise the items has already been trained. In the process of implementation certain stages are involved such as preprocessing, DataAugmentation, training, Finetuning and evaluation of the modal etc. This work aims to keep the environment safe and also helps the municipal corporations to collect garbage effectively in remote areas. The garbage dataset consists of 2,527 images of cardboard, plastic, paper, metal, glass and trash. We achieved an accuracy of 81%. Finally, Precision, Recall, f1 scores and Confusion matrix are calculated with respect to their classes.
{"title":"Road Garbage Classification Using ResNet50","authors":"Nomika Sree Kolla, Mythili Anumula, S. Sujana, M. Ratnababu","doi":"10.1109/IConSCEPT57958.2023.10170073","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170073","url":null,"abstract":"Nowadays managing the road garbage is essential. The waste disposal leads to pollution, climate change, water contamination etc. The major issue which is unresolved is dealing with the large amount of waste that is dumped in the environment rather than segregating properly. To overcome this problem, a deep learning algorithm is used to segregate the garbage which is beneficial for diminishing landfills, recycling etc. We use One MaxPool layer, one average pool layer, and 48 convolutional layers make up the 50-layer convolutional neural network known as ResNet50. The model that is used to categorise the items has already been trained. In the process of implementation certain stages are involved such as preprocessing, DataAugmentation, training, Finetuning and evaluation of the modal etc. This work aims to keep the environment safe and also helps the municipal corporations to collect garbage effectively in remote areas. The garbage dataset consists of 2,527 images of cardboard, plastic, paper, metal, glass and trash. We achieved an accuracy of 81%. Finally, Precision, Recall, f1 scores and Confusion matrix are calculated with respect to their classes.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134256092","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：