Pub Date : 2022-11-19DOI: 10.1109/ASSIC55218.2022.10088345
M. Sailaja, K. Harika, B. Sridhar, Rajan Singh, V. Charitha, Koppula Srinivas Rao
Over the last few years deep neural network made image captioning conceivable. Image caption generator provides an appropriate title for an applied input image based on the dataset. The present work proposes a model based on deep learning and utilizes it to generate caption for the input image. The model takes an image as input and frame the sentence related to the given input image by using some algorithms like CNN and LSTM. This CNN model is used to identify the objects that are present in the image and Long Short-Term Memory (LSTM) model will not only generate the sentence but summarize the text and generate the caption that is suitable for the project. So, the proposed model mainly focuses on identify the objects and generating the most appropriate title for the input images.
{"title":"Image Caption Generator using Deep Learning","authors":"M. Sailaja, K. Harika, B. Sridhar, Rajan Singh, V. Charitha, Koppula Srinivas Rao","doi":"10.1109/ASSIC55218.2022.10088345","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088345","url":null,"abstract":"Over the last few years deep neural network made image captioning conceivable. Image caption generator provides an appropriate title for an applied input image based on the dataset. The present work proposes a model based on deep learning and utilizes it to generate caption for the input image. The model takes an image as input and frame the sentence related to the given input image by using some algorithms like CNN and LSTM. This CNN model is used to identify the objects that are present in the image and Long Short-Term Memory (LSTM) model will not only generate the sentence but summarize the text and generate the caption that is suitable for the project. So, the proposed model mainly focuses on identify the objects and generating the most appropriate title for the input images.","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":"129911214","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/ASSIC55218.2022.10088406
Ravi Shankar Jha, P. R. Sahoo, Shaktimaya Mohapatra
In the fast-moving era of the Industrial Revolution (Industry 4.0), digitally fueled devices and technologies are paramount for driving innovation and creating values across a myriad of industries. A case in point is - Healthcare Industry. Healthcare insurance companies, hospitals, and other providers around the world are belligerently leveraging digital tools and technologies such as Big Data analytics, Lake, Machine Learning, Artificial Intelligence, Internet of Things (IoT), Natural Language Processing, smart sensors, and the Internet of Things (IoT), for improving the overall quality of care and overall process efficiency and effectiveness. The Healthcare industry has been a center of discussion for embracing Big Data practice across the value chain for the past couple of decades due to the prodigious potential that is concealed in it. With so much abundant information, there have been numerous provocations related to the apiece stage of maneuvering big data that can only be amplified by leveraging high-end computer science results for big data analytics, as mentioned above. Well-organized healthcare ecosystem, analysis, and magnification of big data can influence the course of the game by opening new paths in terms of offering unique yet innovative products and services for the modern age technology-propelled healthcare value chain. This paper emphasizes the impetus of Big Data across the healthcare value chain, which involves the amalgamation of technology, data, and business, yielding better decisions and improving the experience across all touch points.
{"title":"Healthcare Industry: Embracing Potential of Big Data across Value Chain","authors":"Ravi Shankar Jha, P. R. Sahoo, Shaktimaya Mohapatra","doi":"10.1109/ASSIC55218.2022.10088406","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088406","url":null,"abstract":"In the fast-moving era of the Industrial Revolution (Industry 4.0), digitally fueled devices and technologies are paramount for driving innovation and creating values across a myriad of industries. A case in point is - Healthcare Industry. Healthcare insurance companies, hospitals, and other providers around the world are belligerently leveraging digital tools and technologies such as Big Data analytics, Lake, Machine Learning, Artificial Intelligence, Internet of Things (IoT), Natural Language Processing, smart sensors, and the Internet of Things (IoT), for improving the overall quality of care and overall process efficiency and effectiveness. The Healthcare industry has been a center of discussion for embracing Big Data practice across the value chain for the past couple of decades due to the prodigious potential that is concealed in it. With so much abundant information, there have been numerous provocations related to the apiece stage of maneuvering big data that can only be amplified by leveraging high-end computer science results for big data analytics, as mentioned above. Well-organized healthcare ecosystem, analysis, and magnification of big data can influence the course of the game by opening new paths in terms of offering unique yet innovative products and services for the modern age technology-propelled healthcare value chain. This paper emphasizes the impetus of Big Data across the healthcare value chain, which involves the amalgamation of technology, data, and business, yielding better decisions and improving the experience across all touch points.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"152 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":"133960298","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/ASSIC55218.2022.10088351
Raju Rollakanti, B. Naresh, Aruna Manjusha, Sudeep Sharma, U. Somanaidu, S. Prasad
The main goal of a coal mine safety system is to be built using things that speak as the data transmission channel. In coal mines, the system monitors and manages a variety of parameters, including light detection, gas leak detection, temperature and humidity conditions, and coal mine fire detection. These sensors are bundled together and put in coal mines. Thing Speak receives and analyses all sensor values in real-time. The gas is monitored regularly here, and if there are any concerns about the gas level, a bell is used to alert the workers. In this configuration, an LDR sensor detects the presence of light. The light comes on automatically and may be controlled using the LED button. An alert notification is sent to the authorized person's mailbox if a fire breaks out in a coal mine. Temperature and humidity levels are regularly checked and displayed on the serial monitor and the thing talk platform. The developed technology is primarily utilized to improve coal mine working conditions and protect workers' safety.
{"title":"Design of IOT based coal mine safety system using LoRa","authors":"Raju Rollakanti, B. Naresh, Aruna Manjusha, Sudeep Sharma, U. Somanaidu, S. Prasad","doi":"10.1109/ASSIC55218.2022.10088351","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088351","url":null,"abstract":"The main goal of a coal mine safety system is to be built using things that speak as the data transmission channel. In coal mines, the system monitors and manages a variety of parameters, including light detection, gas leak detection, temperature and humidity conditions, and coal mine fire detection. These sensors are bundled together and put in coal mines. Thing Speak receives and analyses all sensor values in real-time. The gas is monitored regularly here, and if there are any concerns about the gas level, a bell is used to alert the workers. In this configuration, an LDR sensor detects the presence of light. The light comes on automatically and may be controlled using the LED button. An alert notification is sent to the authorized person's mailbox if a fire breaks out in a coal mine. Temperature and humidity levels are regularly checked and displayed on the serial monitor and the thing talk platform. The developed technology is primarily utilized to improve coal mine working conditions and protect workers' safety.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"16 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":"125058152","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/ASSIC55218.2022.10088354
Binu P. K, Thejas Menon, Javed Harees
True random number generation is essential for modern and future security and cryptography. This paper surveys five existing methods of using audio and video to generate numbers, and compares their hardware, software, and randomness to find the best method for TRNG. The entropy of each method is compared, and the randomness of each method can be found. Each paper generates random numbers by utilizing the inherent noise created by transitioning analogue data to digital data, unlike other TRNG methods which use the conditions of internal hardware, erroneous data from wireless networks, or other non-noise-based methods.
{"title":"Survey On Using Audio Video for True Random Number Generation","authors":"Binu P. K, Thejas Menon, Javed Harees","doi":"10.1109/ASSIC55218.2022.10088354","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088354","url":null,"abstract":"True random number generation is essential for modern and future security and cryptography. This paper surveys five existing methods of using audio and video to generate numbers, and compares their hardware, software, and randomness to find the best method for TRNG. The entropy of each method is compared, and the randomness of each method can be found. Each paper generates random numbers by utilizing the inherent noise created by transitioning analogue data to digital data, unlike other TRNG methods which use the conditions of internal hardware, erroneous data from wireless networks, or other non-noise-based methods.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"16 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":"124541389","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/ASSIC55218.2022.10088312
Kanuri Naveen, Kiran Dasari, G. Swapnasri, R. Swetha, S. Nishitha, B. Anusha
The high speed 5G network requires the more gain, the micro strip patch antenna array is the better solution for the high speed data network system. The novel proposed antenna array has the 2x4 structure with the dimension of (28.3 mm x 30 mm) at 5 GHz simulated and the results observed as the gain of 17.6dB S11 reported that as - 24.7,radiation efficiency of 67%.directivity of 17.4801. This novel proposed design has the application of vehicle to vehicle communication and vehicle to other communication and internet of things and modern communication systems. This novel proposed 2x4 antenna array design overcome the above mentioned literature and the gain enhancement is achieved as 17.6dB
高速5G网络对增益的要求更高，微带贴片天线阵列是高速数据网络系统较好的解决方案。该天线阵列具有2x4结构，尺寸为(28.3 mm x 30 mm)，在5 GHz时进行仿真，结果显示增益为17.6dB, S11报道为- 24.7，辐射效率为67%。指向性为17.4801。本设计具有车对车通信、车对其他通信以及物联网和现代通信系统的应用。本文提出的2x4天线阵列设计克服了上述文献的缺陷，实现了17.6dB的增益增强
{"title":"Microstrip Patch Antenna Array With Gain Enhancement for WLAN Applications","authors":"Kanuri Naveen, Kiran Dasari, G. Swapnasri, R. Swetha, S. Nishitha, B. Anusha","doi":"10.1109/ASSIC55218.2022.10088312","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088312","url":null,"abstract":"The high speed 5G network requires the more gain, the micro strip patch antenna array is the better solution for the high speed data network system. The novel proposed antenna array has the 2x4 structure with the dimension of (28.3 mm x 30 mm) at 5 GHz simulated and the results observed as the gain of 17.6dB S11 reported that as - 24.7,radiation efficiency of 67%.directivity of 17.4801. This novel proposed design has the application of vehicle to vehicle communication and vehicle to other communication and internet of things and modern communication systems. This novel proposed 2x4 antenna array design overcome the above mentioned literature and the gain enhancement is achieved as 17.6dB","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"16 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":"127371519","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/ASSIC55218.2022.10088373
Debasis Prasad Sahoo, M. Rout, P. Mallick, Sasmita Rani Samanta
Deep learning is becoming more popular in practically every industry, but especially in medical imaging for better diagnostics of various deadly diseases. Deep learning is used to explain difficulties based on medical image processing as part of machine learning artificial intelligence. Most commonly used machine learning algorithm named Convolutional Neural Network (CNN) grasps a resilient position for image recognition tasks. In this paper, we compared the performance of basic CNN and three state of the art transfer-learning models namely, VGG-16, ResNet50 and GoogleNet (Inception-v3) by extracting features from pre-trained CNN architecture. Small datasets of three fatal diseases, which are brain tumor, breast cancer and skin cancer are used. The determination of this study is to discover the finest trade-off between accuracy.
{"title":"Comparative Analysis of Medical Images using Transfer Learning Based Deep Learning Models","authors":"Debasis Prasad Sahoo, M. Rout, P. Mallick, Sasmita Rani Samanta","doi":"10.1109/ASSIC55218.2022.10088373","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088373","url":null,"abstract":"Deep learning is becoming more popular in practically every industry, but especially in medical imaging for better diagnostics of various deadly diseases. Deep learning is used to explain difficulties based on medical image processing as part of machine learning artificial intelligence. Most commonly used machine learning algorithm named Convolutional Neural Network (CNN) grasps a resilient position for image recognition tasks. In this paper, we compared the performance of basic CNN and three state of the art transfer-learning models namely, VGG-16, ResNet50 and GoogleNet (Inception-v3) by extracting features from pre-trained CNN architecture. Small datasets of three fatal diseases, which are brain tumor, breast cancer and skin cancer are used. The determination of this study is to discover the finest trade-off between accuracy.","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":"127442487","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/ASSIC55218.2022.10088404
M. Kandpal, Chandramouli Das, C. Misra, Abhaya Kumar Sahoo, Jagannath Singh, R. K. Barik
Blockchain offers decentralized and immutable data storage. In recent years, logistics and supply chain management are slowly realizing Blockchain's impact. Leading-edge companies are trying to fight supply chain network complexity with block chain. Blockchain helps in enabling steady and cost-efficient delivery of products and improving traceability of products, coordination between the consumer's, partners, and financial aid. By considering this, the main objective of the proposed work is to merge decentralized behavior of blockchain with supply chain management to make it more protective, secure and transparent. For the implementation of the proposed framework, it uses Ganache, Metamask, MySQL, PHP, NodeJS, Solidity and JavaScript. Adding blockchain also helps in minimizing the interference of middle man attack in the processes. This technology helps in discarding forged products flowing in the marketplace. Hence, it overall maintains the integrity and authentication among all, the stages in between producer and consumer.
{"title":"Blockchain assisted Supply Chain Management System for Secure Data Management","authors":"M. Kandpal, Chandramouli Das, C. Misra, Abhaya Kumar Sahoo, Jagannath Singh, R. K. Barik","doi":"10.1109/ASSIC55218.2022.10088404","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088404","url":null,"abstract":"Blockchain offers decentralized and immutable data storage. In recent years, logistics and supply chain management are slowly realizing Blockchain's impact. Leading-edge companies are trying to fight supply chain network complexity with block chain. Blockchain helps in enabling steady and cost-efficient delivery of products and improving traceability of products, coordination between the consumer's, partners, and financial aid. By considering this, the main objective of the proposed work is to merge decentralized behavior of blockchain with supply chain management to make it more protective, secure and transparent. For the implementation of the proposed framework, it uses Ganache, Metamask, MySQL, PHP, NodeJS, Solidity and JavaScript. Adding blockchain also helps in minimizing the interference of middle man attack in the processes. This technology helps in discarding forged products flowing in the marketplace. Hence, it overall maintains the integrity and authentication among all, the stages in between producer and consumer.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"109 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":"129322758","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/ASSIC55218.2022.10088410
Tridiv Swain, Suravi Sinha, Awantika Singh, Khushali Verma, S. Das
Human Pose Estimation is a method of capturing a collection of coordinates for each joint (arm, head, torso, etc.) that may be used to characterize a person's pose. The initial goal is to create a skeleton-like depiction of a human body, which will then be processed for task-specific applications. The ability to identify and estimate the position of a human body is valuable in a wide range of applications and conditions like action recognition, animation, gaming, and so on. It is a crucial first step toward understanding people through images and media. In this study, graph neural networks were utilised to predict human poses by modelling the human skeleton as an unordered list, greatly enhancing 3D human pose estimation. This paper describes the approach as an efficient way to determine the 3D posture of many persons in a picture. Our model gives a validation accuracy of 92%.
{"title":"Human Pose Estimation Using GNN","authors":"Tridiv Swain, Suravi Sinha, Awantika Singh, Khushali Verma, S. Das","doi":"10.1109/ASSIC55218.2022.10088410","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088410","url":null,"abstract":"Human Pose Estimation is a method of capturing a collection of coordinates for each joint (arm, head, torso, etc.) that may be used to characterize a person's pose. The initial goal is to create a skeleton-like depiction of a human body, which will then be processed for task-specific applications. The ability to identify and estimate the position of a human body is valuable in a wide range of applications and conditions like action recognition, animation, gaming, and so on. It is a crucial first step toward understanding people through images and media. In this study, graph neural networks were utilised to predict human poses by modelling the human skeleton as an unordered list, greatly enhancing 3D human pose estimation. This paper describes the approach as an efficient way to determine the 3D posture of many persons in a picture. Our model gives a validation accuracy of 92%.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"10 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":"125369295","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/ASSIC55218.2022.10088377
Mahesh Kumar Morampudi, Nagamani Gonthina, Dinesh Reddy, K. S. Rao
Programming Skills play a crucial role in any computer engineering student's life to apply the concepts in solving any real world problem as well to crack a secure job in the dream company. To achieve this they should assess their performance in programming, analyze and improve their skills regularly. Many students are even undergoing mental stress and depression and even attempting suicides out of the stress if the considered scores and performance are not met. With the help of analyzing the programming skills one can enhance their scores and performance on a regular basis, introspect and can deliberately practice for better improvement. This reduces the stress, anxiety and depression on students' minds in securing good scores in their academics and in building their career to achieve the goal. This analysis helps even professors to improvise the teaching and learning outcomes of students and increase their performance in whichever field they are working in. We made a comparison of different machine learning algorithms based on 200 classification instances. This analysis helped us in analyzing the statistics of students' performance.
{"title":"Analyzing Student Performance in Programming Education Using Classification Techniques","authors":"Mahesh Kumar Morampudi, Nagamani Gonthina, Dinesh Reddy, K. S. Rao","doi":"10.1109/ASSIC55218.2022.10088377","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088377","url":null,"abstract":"Programming Skills play a crucial role in any computer engineering student's life to apply the concepts in solving any real world problem as well to crack a secure job in the dream company. To achieve this they should assess their performance in programming, analyze and improve their skills regularly. Many students are even undergoing mental stress and depression and even attempting suicides out of the stress if the considered scores and performance are not met. With the help of analyzing the programming skills one can enhance their scores and performance on a regular basis, introspect and can deliberately practice for better improvement. This reduces the stress, anxiety and depression on students' minds in securing good scores in their academics and in building their career to achieve the goal. This analysis helps even professors to improvise the teaching and learning outcomes of students and increase their performance in whichever field they are working in. We made a comparison of different machine learning algorithms based on 200 classification instances. This analysis helped us in analyzing the statistics of students' performance.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"76 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":"122611595","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/ASSIC55218.2022.10088353
Kwabena Appiah Ampofo, E. Owusu, J. K. Appati
Electricity consumption is an important economic index, and it plays a significant role in drawing up an energy development policy for every country. Thus, having reliable information regarding the prediction of electricity consumption in a country is imperative to policy and decision-makers to plan and schedule the operation of power systems. Studies have shown that the Long Short-Term Memory (LSTM) neural network model is capable of learning long term temporary dependencies and nonlinear characteristic of a time series phenomenon and it can be a better alternative to the traditional neural networks and statistical methods for predicting electricity consumption. The LSTM neural network model has many hyperparameters, and one of the important hyperparameters is the optimization method. The optimization method plays a significant role in the performance of an LSTM neural network model, but selecting it is not a trivial task to end-users as there is no particular approach for selecting an appropriate method for a particular task. In this study, the LSTM neural network model was used to predict long term electricity consumption using socioeconomic data as predictors to analyze six popular optimization methods that have been implemented in the Keras machine learning library. The motivation is to determine which optimization method will be most suitable for electricity consumption prediction using LSTM neural network model. The results of the study show that the Stochastic Gradient Descent (SGD) optimizer is the most outstanding optimization method.
{"title":"Performance Evaluation of LSTM Optimizers for Long-Term Electricity Consumption Prediction","authors":"Kwabena Appiah Ampofo, E. Owusu, J. K. Appati","doi":"10.1109/ASSIC55218.2022.10088353","DOIUrl":"https://doi.org/10.1109/ASSIC55218.2022.10088353","url":null,"abstract":"Electricity consumption is an important economic index, and it plays a significant role in drawing up an energy development policy for every country. Thus, having reliable information regarding the prediction of electricity consumption in a country is imperative to policy and decision-makers to plan and schedule the operation of power systems. Studies have shown that the Long Short-Term Memory (LSTM) neural network model is capable of learning long term temporary dependencies and nonlinear characteristic of a time series phenomenon and it can be a better alternative to the traditional neural networks and statistical methods for predicting electricity consumption. The LSTM neural network model has many hyperparameters, and one of the important hyperparameters is the optimization method. The optimization method plays a significant role in the performance of an LSTM neural network model, but selecting it is not a trivial task to end-users as there is no particular approach for selecting an appropriate method for a particular task. In this study, the LSTM neural network model was used to predict long term electricity consumption using socioeconomic data as predictors to analyze six popular optimization methods that have been implemented in the Keras machine learning library. The motivation is to determine which optimization method will be most suitable for electricity consumption prediction using LSTM neural network model. The results of the study show that the Stochastic Gradient Descent (SGD) optimizer is the most outstanding optimization method.","PeriodicalId":441406,"journal":{"name":"2022 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC)","volume":"23 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":"121921700","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：