Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157514
J. Rajasekhar, T. Hemanth, Anjuman Sk
Short messaging service (SMS) spam is the unwanted messages delivered to the inbox of mobile devices from spammers. Service providers are worried about these spam messages as their clients get dissatisfied with services due to the spam data reaching on their mobile phone. There are most of the service providers has given facility Do Not Disturb (DND) activation for their clients to save them from most of the spam messages. Even though the spam messages are not controlled fully, the delivery of such messages are unstoppable. To overcome this issue extensive research has been done. Artificial intelligence made it possible with extensive learning model and accuracy of detection. This paper is proposed to classify short messages as spam or ham based on a deep learning model. In this paper, the spam detection through Recurrent Neural Network (RNN) model, in specific Long Short Term Memory (LSTM) model is used. The dataset used for this study is extracted from Grumbletext website and it has a total 425 short messages with ‘Ham’ and ‘spam’. The LSTM model classified the SMS dataset effectively with the learning model. Experimental study showed that the model has achieved an accuracy of 88.33% accuracy on SMS spam classification with the LSTM model.
{"title":"SMS Spam Classification and Through Recurrent Neural Network (LSTM) model","authors":"J. Rajasekhar, T. Hemanth, Anjuman Sk","doi":"10.1109/ICEEICT56924.2023.10157514","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157514","url":null,"abstract":"Short messaging service (SMS) spam is the unwanted messages delivered to the inbox of mobile devices from spammers. Service providers are worried about these spam messages as their clients get dissatisfied with services due to the spam data reaching on their mobile phone. There are most of the service providers has given facility Do Not Disturb (DND) activation for their clients to save them from most of the spam messages. Even though the spam messages are not controlled fully, the delivery of such messages are unstoppable. To overcome this issue extensive research has been done. Artificial intelligence made it possible with extensive learning model and accuracy of detection. This paper is proposed to classify short messages as spam or ham based on a deep learning model. In this paper, the spam detection through Recurrent Neural Network (RNN) model, in specific Long Short Term Memory (LSTM) model is used. The dataset used for this study is extracted from Grumbletext website and it has a total 425 short messages with ‘Ham’ and ‘spam’. The LSTM model classified the SMS dataset effectively with the learning model. Experimental study showed that the model has achieved an accuracy of 88.33% accuracy on SMS spam classification with the LSTM model.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116577825","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157043
G. Shanmugapriya, Nikale Vasant Muralidhar, Ravindra R Solankce, Subash Ranjan Kabat, R. Jeevalatha, Pandit S. Patil
Several factors contribute to the gradual decrease in energy production from Photovoltaic (PV) systems. Partial shading is a key contributing element. Clouds and the presence of structures like buildings and tall trees cast partial shadows. Shade can reduce the quantity of energy generated by a photovoltaic system. Even in shady situations, it must be propped up to live. By removing the load from the PV array and taking a look at the open-circuit and short- circuit currents and voltages partial shading may be determined in the traditional manner. However, the suggested solution uses a regular camera to identify the partial shadowing without disconnecting the PV array from the load. There is a higher degree of sensitivity to variations in system performance using this approach. Photographs of the PV array are taken using a digital camera, and then partial shading is determined using standard image processing methods. During times of partial shadowing, the suggested technology reconfigures the electrical current in order to maximize power production by using the relay circuit. Partial shading data is used to create the control signals for the relays. The suggested approach involves interfacing a camera with MATLAB and immediately processing the collected pictures to identify the error or partial shading. The PV array is reconfigured for increased output power generation after reconfiguring signals are sent from a computer using a MATLAB-Arduino connection to the switch circuits in the array. The proposed approach has been tested in a solar PV system with a power output of 80 W, with results showing a 15 percent increase in output. It works well for 1-5-kilowatt solar photovoltaic power systems.
{"title":"An Innovative Method for Optimizing Photovoltaic Array Design in Partially Shaded Environments","authors":"G. Shanmugapriya, Nikale Vasant Muralidhar, Ravindra R Solankce, Subash Ranjan Kabat, R. Jeevalatha, Pandit S. Patil","doi":"10.1109/ICEEICT56924.2023.10157043","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157043","url":null,"abstract":"Several factors contribute to the gradual decrease in energy production from Photovoltaic (PV) systems. Partial shading is a key contributing element. Clouds and the presence of structures like buildings and tall trees cast partial shadows. Shade can reduce the quantity of energy generated by a photovoltaic system. Even in shady situations, it must be propped up to live. By removing the load from the PV array and taking a look at the open-circuit and short- circuit currents and voltages partial shading may be determined in the traditional manner. However, the suggested solution uses a regular camera to identify the partial shadowing without disconnecting the PV array from the load. There is a higher degree of sensitivity to variations in system performance using this approach. Photographs of the PV array are taken using a digital camera, and then partial shading is determined using standard image processing methods. During times of partial shadowing, the suggested technology reconfigures the electrical current in order to maximize power production by using the relay circuit. Partial shading data is used to create the control signals for the relays. The suggested approach involves interfacing a camera with MATLAB and immediately processing the collected pictures to identify the error or partial shading. The PV array is reconfigured for increased output power generation after reconfiguring signals are sent from a computer using a MATLAB-Arduino connection to the switch circuits in the array. The proposed approach has been tested in a solar PV system with a power output of 80 W, with results showing a 15 percent increase in output. It works well for 1-5-kilowatt solar photovoltaic power systems.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131408053","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157595
A. Vijayalakshmi, E. Abishek B, Abdulsamath G, S. N, Mohamed Absar M, Arul Stephen. C
Existing cellular communications and future communication networks requires very low latency, high reliability standards, increased capacity, enhanced security, and efficient user communication. The ability to accommodate several independent devices is a feature that mobile operators are seeking for a programmable solution, comparable functional networks technical foundation. Through the use of the Network Slicing concept, 5G networks enable end-to-end deployment of network resources (NS). Due to the surge in traffic and the acceleration of 5G network performance, emerging communication networks will demand data-driven strategic planning. This paper has to implement machine learning based network slicing algorithm to divide 5G network IoT devices into effective network slices such as eMBB, mMTC, URLLC for the traffic. The GNB and B-GNB algorithms are used to classify the usecase devices under the three network slices. This work developed bagging integrated with GNB algorithm and its performance metrics have been analysed. The B-GNB algorithm works well for prediction of best slice and strategic recommendations even there is network interruption, be able to predict the best network slice and implement strategic recommendations. The performance metrics such as sensitivity, F-score, precision and accuracy have also been analyzed. The comparative analysis shows B-GNB classify the slices with 86% of accuracy.
{"title":"5G Network Slicing Algorithm Development using Bagging based-Gaussian Naive Bayes","authors":"A. Vijayalakshmi, E. Abishek B, Abdulsamath G, S. N, Mohamed Absar M, Arul Stephen. C","doi":"10.1109/ICEEICT56924.2023.10157595","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157595","url":null,"abstract":"Existing cellular communications and future communication networks requires very low latency, high reliability standards, increased capacity, enhanced security, and efficient user communication. The ability to accommodate several independent devices is a feature that mobile operators are seeking for a programmable solution, comparable functional networks technical foundation. Through the use of the Network Slicing concept, 5G networks enable end-to-end deployment of network resources (NS). Due to the surge in traffic and the acceleration of 5G network performance, emerging communication networks will demand data-driven strategic planning. This paper has to implement machine learning based network slicing algorithm to divide 5G network IoT devices into effective network slices such as eMBB, mMTC, URLLC for the traffic. The GNB and B-GNB algorithms are used to classify the usecase devices under the three network slices. This work developed bagging integrated with GNB algorithm and its performance metrics have been analysed. The B-GNB algorithm works well for prediction of best slice and strategic recommendations even there is network interruption, be able to predict the best network slice and implement strategic recommendations. The performance metrics such as sensitivity, F-score, precision and accuracy have also been analyzed. The comparative analysis shows B-GNB classify the slices with 86% of accuracy.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132495460","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157149
A. Manuel, Madhukumar S, B. Pramanick
Biosensors have a high potential for openly acknowl-edging and analyzing various anomalies related to the human body, particularly diseases like cancer. Lung cancer (LC) rates as a significant cause of mortality and a major obstacle to raising life expectancy in every nation. The death rate may be decreased to some extent by earlier detection as most LC patients are diagnosed at the advanced stages.LC can be treated using a variety of techniques used to screen for cancer based on tumor size. The available methods are expensive and not suitable for widespread screening as they are time-consuming and have a high rate of false-positive results. Therefore, it is required to design a simple, cost-effective, early detection platform to improve clinical prognosis and survival rates. Molecular biomarkers (BM) come into the picture, acetone, pentane, ethanol, and isoprene are the four carbonyl volatile organic compounds (VOCs) associated with LC, and depending on the kind of cancer, different concentration ranges exist. In contrast to healthy people, LC patients must have distinct metabolic pathways that lead to VOC production or metabolism. Compared to Gold (Au) interdigitated electrodes (IDE), TiO2 with the Glassy carbon sensing layer exhibits significant deflection in the change of resistance with the aid of Glassy carbon IDE. This combination including glassy carbon IDE provides a broad range of use in creating biosensors.
{"title":"Design and Analysis of Glassy Carbon Material towards the Development of Biosensors for EarlyDetection of Lung Cancer","authors":"A. Manuel, Madhukumar S, B. Pramanick","doi":"10.1109/ICEEICT56924.2023.10157149","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157149","url":null,"abstract":"Biosensors have a high potential for openly acknowl-edging and analyzing various anomalies related to the human body, particularly diseases like cancer. Lung cancer (LC) rates as a significant cause of mortality and a major obstacle to raising life expectancy in every nation. The death rate may be decreased to some extent by earlier detection as most LC patients are diagnosed at the advanced stages.LC can be treated using a variety of techniques used to screen for cancer based on tumor size. The available methods are expensive and not suitable for widespread screening as they are time-consuming and have a high rate of false-positive results. Therefore, it is required to design a simple, cost-effective, early detection platform to improve clinical prognosis and survival rates. Molecular biomarkers (BM) come into the picture, acetone, pentane, ethanol, and isoprene are the four carbonyl volatile organic compounds (VOCs) associated with LC, and depending on the kind of cancer, different concentration ranges exist. In contrast to healthy people, LC patients must have distinct metabolic pathways that lead to VOC production or metabolism. Compared to Gold (Au) interdigitated electrodes (IDE), TiO2 with the Glassy carbon sensing layer exhibits significant deflection in the change of resistance with the aid of Glassy carbon IDE. This combination including glassy carbon IDE provides a broad range of use in creating biosensors.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131673712","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157499
Malhar Bangdiwala, Sakshi Mahadik, Yashvi Mehta, A. Salunke
This paper discusses the increasing use of machine learning (ML) models in the retail industry to improve the shopping experience of customers. The focus is on virtual trial rooms, self-checkout, and personalized recommendations. Virtual trial rooms allow customers to try on clothes virtually, while self-checkout provides a faster and more convenient checkout process. Personalized recommendations based on customers' purchase history and preferences can also improve the overall shopping experience. The paper reviews literature on the use of ML models and mentions advanced models that map clothes correctly to customers' pictures and use geolocation in barcode scanners to avoid long waiting queues.
{"title":"ML-Based Retail Innovations: Virtual Fitting, Scanning and Recommendations","authors":"Malhar Bangdiwala, Sakshi Mahadik, Yashvi Mehta, A. Salunke","doi":"10.1109/ICEEICT56924.2023.10157499","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157499","url":null,"abstract":"This paper discusses the increasing use of machine learning (ML) models in the retail industry to improve the shopping experience of customers. The focus is on virtual trial rooms, self-checkout, and personalized recommendations. Virtual trial rooms allow customers to try on clothes virtually, while self-checkout provides a faster and more convenient checkout process. Personalized recommendations based on customers' purchase history and preferences can also improve the overall shopping experience. The paper reviews literature on the use of ML models and mentions advanced models that map clothes correctly to customers' pictures and use geolocation in barcode scanners to avoid long waiting queues.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132136780","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157066
A. Barveen, S. Geetha, Mohamad Faizal
Memes are a socially interactive way to communicate online. Memes are used by users to communicate with one another on social networking sites and other forums. Memes essentially focus on speech recognition and image macros. While a meme is being created, it focuses on the semiotic type of resources that the internet community interprets with other resources, which facilitates the interaction among the internet and meme creators. Memes recreate based on various approaches, which fall under various acts such as existing speech acts. Based on the expressive face with captioned short texts, even the short text is exaggerated. Every year, meme mimicking applications are created that allow users to use the imitated meme expressions. Memes represent the shared texts of the younger generations on various social platforms. The classifications of sentiment based on the various memetic expressions are the most efficient way to analyse those feelings and emotions. HOG feature extraction allows the images to be segmented into blocks of smaller size by using a single feature vector for dimension, which characterizes the local object appearances to characterize the meme classification. The existence of specific characteristics, including such edges, angles, or patterns, is then analyzed by combining HOG features using multi-feature analysis on patches. Based upon the classification methodology, it classifies the sentiments, which tend to improve the learning process in an efficient manner. By combining a deep learning approach with a recurrent neural network, the extended LSTM-RNN can identify subtle nuances in memes, allowing for more accurate and detailed meme classification. This proposed method effectively evaluates several classification techniques, including CNN and Extended LSTM-RNN for meme image characterization. Through training and validation, Extended LSTM-RNN achieved 0.98% accuracy with better performance than CNN.
{"title":"Meme Expressive Classification in Multimodal State with Feature Extraction in Deep Learning","authors":"A. Barveen, S. Geetha, Mohamad Faizal","doi":"10.1109/ICEEICT56924.2023.10157066","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157066","url":null,"abstract":"Memes are a socially interactive way to communicate online. Memes are used by users to communicate with one another on social networking sites and other forums. Memes essentially focus on speech recognition and image macros. While a meme is being created, it focuses on the semiotic type of resources that the internet community interprets with other resources, which facilitates the interaction among the internet and meme creators. Memes recreate based on various approaches, which fall under various acts such as existing speech acts. Based on the expressive face with captioned short texts, even the short text is exaggerated. Every year, meme mimicking applications are created that allow users to use the imitated meme expressions. Memes represent the shared texts of the younger generations on various social platforms. The classifications of sentiment based on the various memetic expressions are the most efficient way to analyse those feelings and emotions. HOG feature extraction allows the images to be segmented into blocks of smaller size by using a single feature vector for dimension, which characterizes the local object appearances to characterize the meme classification. The existence of specific characteristics, including such edges, angles, or patterns, is then analyzed by combining HOG features using multi-feature analysis on patches. Based upon the classification methodology, it classifies the sentiments, which tend to improve the learning process in an efficient manner. By combining a deep learning approach with a recurrent neural network, the extended LSTM-RNN can identify subtle nuances in memes, allowing for more accurate and detailed meme classification. This proposed method effectively evaluates several classification techniques, including CNN and Extended LSTM-RNN for meme image characterization. Through training and validation, Extended LSTM-RNN achieved 0.98% accuracy with better performance than CNN.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132169549","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}
There has been a rapid increase in the traffic concentration in southeast Asian countries in the past decade. The impact of risky driving attitude on businesses is monumental both in terms of road safety and cost optimization. The purpose of this article was to identify potentially risky driving pattern and factors influencing them including geographical factors. We analyzed the telematics data generated by an In-Vehicle-Monitoring-System installed in vehicles operating in supply chain industries. With the findings we propose the framework of a Risk Management platform which can be used by fleet managers to provide constructive feedbacks to drivers. Telematics data gathered after the implementation of the RMP shows up to 20% decrease in one of the key harsh driving indicators i.e. Harsh Acceleration.
{"title":"Driver Behavior Management in Supply Chain Industries across Southeast Asia","authors":"Anuradha Das, Sabarirajan K, Selvakuberan Karuppasamy, Subhashini Lakshminarayanan","doi":"10.1109/ICEEICT56924.2023.10157716","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157716","url":null,"abstract":"There has been a rapid increase in the traffic concentration in southeast Asian countries in the past decade. The impact of risky driving attitude on businesses is monumental both in terms of road safety and cost optimization. The purpose of this article was to identify potentially risky driving pattern and factors influencing them including geographical factors. We analyzed the telematics data generated by an In-Vehicle-Monitoring-System installed in vehicles operating in supply chain industries. With the findings we propose the framework of a Risk Management platform which can be used by fleet managers to provide constructive feedbacks to drivers. Telematics data gathered after the implementation of the RMP shows up to 20% decrease in one of the key harsh driving indicators i.e. Harsh Acceleration.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"42 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122854994","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157394
Prabhash Kumar Sonwani, A. Swarnkar, Gurpinder Singh, N. Gupta, K. R. Niazi
Non-intrusive load monitoring (NILM) is a technique for disaggregating the total energy consumption of a building into individual appliance-level energy consumption. Event detection is a critical component of NILM systems as it involves the identification and classification of different electrical events from the aggregate power signal. In this article an event detection method for NILM systems has been proposed that is based on the analysis of the statistical properties of the aggregate power signal. Specifically, we use a sliding window approach and K-Means clustering to detect number of devices from the power signal and then apply a threshold-based algorithm to detect electrical events. We evaluate the proposed method on a public dataset and demonstrate its effectiveness in accurately detecting electrical events. The proposed method has the potential to improve the accuracy with recall of 98.84% carried out on Pecan Street Datanort Inc.
非侵入式负荷监测(NILM)是一种将建筑物的总能耗分解为单个电器级能耗的技术。事件检测是NILM系统的关键组成部分，因为它涉及到从总功率信号中识别和分类不同的电气事件。本文提出了一种基于总功率信号统计特性分析的NILM系统事件检测方法。具体来说，我们使用滑动窗口方法和K-Means聚类从功率信号中检测设备数量，然后应用基于阈值的算法检测电事件。我们在一个公共数据集上评估了所提出的方法，并证明了它在准确检测电事件方面的有效性。该方法对Pecan Street Datanort Inc.的查全率达到98.84%，具有提高查全率的潜力。
{"title":"Energy Disaggregation of Residential House via Event Based Optimization Technique","authors":"Prabhash Kumar Sonwani, A. Swarnkar, Gurpinder Singh, N. Gupta, K. R. Niazi","doi":"10.1109/ICEEICT56924.2023.10157394","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157394","url":null,"abstract":"Non-intrusive load monitoring (NILM) is a technique for disaggregating the total energy consumption of a building into individual appliance-level energy consumption. Event detection is a critical component of NILM systems as it involves the identification and classification of different electrical events from the aggregate power signal. In this article an event detection method for NILM systems has been proposed that is based on the analysis of the statistical properties of the aggregate power signal. Specifically, we use a sliding window approach and K-Means clustering to detect number of devices from the power signal and then apply a threshold-based algorithm to detect electrical events. We evaluate the proposed method on a public dataset and demonstrate its effectiveness in accurately detecting electrical events. The proposed method has the potential to improve the accuracy with recall of 98.84% carried out on Pecan Street Datanort Inc.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128484705","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157261
S. Jayashree, Mohammad Nurul Hassan Reza, C. Malarvizhi, Mazni Binti Alias
Despite the increased interest in higher learning institutions (HLIs), research on big data analytics (BDA) focusing on sustainability in the education sector is still in its infancy. Therefore, this study proposes a BDA-centric framework, emphasizing sustainability in higher education by integrating the Technology, Organization, and Environment (TOE) theory and the Diffusion of Innovation (DOI) model. The framework will be tested to examine the impact of the factors on BDA adoption and sustainable education. It also aims to determine how BDA assists HLIs in attaining sustainability. Moreover, whether BDA mediates the relationship between the factors and sustainable education will also be tested. The study will employ a questionnaire-based survey to validate the model. Data will be collected from public and private universities located in various states in Malaysia. Structural Equation Modeling (SEM) will be employed to examine the model and proposed hypotheses. The study's findings offer essential insights for adopting BDA successfully in HLIs. This study may be helpful for educators, policymakers, and big data vendors in adopting big data successfully among HLIs to ensure sustainability in educational systems.
{"title":"Big Data Analytics and Educational Sustainability-A Malaysian Scenario","authors":"S. Jayashree, Mohammad Nurul Hassan Reza, C. Malarvizhi, Mazni Binti Alias","doi":"10.1109/ICEEICT56924.2023.10157261","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157261","url":null,"abstract":"Despite the increased interest in higher learning institutions (HLIs), research on big data analytics (BDA) focusing on sustainability in the education sector is still in its infancy. Therefore, this study proposes a BDA-centric framework, emphasizing sustainability in higher education by integrating the Technology, Organization, and Environment (TOE) theory and the Diffusion of Innovation (DOI) model. The framework will be tested to examine the impact of the factors on BDA adoption and sustainable education. It also aims to determine how BDA assists HLIs in attaining sustainability. Moreover, whether BDA mediates the relationship between the factors and sustainable education will also be tested. The study will employ a questionnaire-based survey to validate the model. Data will be collected from public and private universities located in various states in Malaysia. Structural Equation Modeling (SEM) will be employed to examine the model and proposed hypotheses. The study's findings offer essential insights for adopting BDA successfully in HLIs. This study may be helpful for educators, policymakers, and big data vendors in adopting big data successfully among HLIs to ensure sustainability in educational systems.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117100253","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157072
M. Sangari, K. Thangaraj, U. Vanitha, N. Srikanth, J. Sathyamoorthy, K. Renu
Being at the nexus of robotics and ocean engineering, underwater robots have been a developing research area. They can be used for deep sea infrastructure inspections, oceanographic mapping, and environmental monitoring. Autonomous navigation skills are essential for doing these activities successfully, especially given the poor communication conditions in underwater locations. Autonomous navigation technologies, such as path planning and tracking, have been one of the fascinating but difficult issues in the field of study due to the extremely dynamic and three-dimensional settings. Due to their short detection ranges and poor visibility, cameras have not received much attention as an underwater sensor. However, using visual data from cameras is still a popular technique for underwater sensing, and it works particularly well for close-range detections. In this study, the enhancement of underwater vision is achieved by combining the max-RGB and shades of grey methods. Then, to solve the problem of poorly illuminated underwater images, a technique known as RCNN (Region-based Convolutional Neural Network) is proposed. This procedure tells the mapping relationship how to create the illumination map. Following image processing, an RCNN strategy for underwater detection and classification is recommended. Two improved strategies are then used to change the RCNN structure in accordance with the properties of underwater vision. In order to deal with the challenges of object tracking and detection in underwater communication, a correlation filter tracking algorithm (CFTA) method was created. The properties of the invariant moment and area were looked at after the object's region had been extracted using a threshold segment and morphological technique. The findings show that the suggested method is effective for underwater target tracking based on RCNN-CFTA in the aquatic environment. Simulated evaluation of these methods' performance demonstrates the potency of the suggested strategies.
{"title":"Deep learning-based Object Detection in Underwater Communications System","authors":"M. Sangari, K. Thangaraj, U. Vanitha, N. Srikanth, J. Sathyamoorthy, K. Renu","doi":"10.1109/ICEEICT56924.2023.10157072","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157072","url":null,"abstract":"Being at the nexus of robotics and ocean engineering, underwater robots have been a developing research area. They can be used for deep sea infrastructure inspections, oceanographic mapping, and environmental monitoring. Autonomous navigation skills are essential for doing these activities successfully, especially given the poor communication conditions in underwater locations. Autonomous navigation technologies, such as path planning and tracking, have been one of the fascinating but difficult issues in the field of study due to the extremely dynamic and three-dimensional settings. Due to their short detection ranges and poor visibility, cameras have not received much attention as an underwater sensor. However, using visual data from cameras is still a popular technique for underwater sensing, and it works particularly well for close-range detections. In this study, the enhancement of underwater vision is achieved by combining the max-RGB and shades of grey methods. Then, to solve the problem of poorly illuminated underwater images, a technique known as RCNN (Region-based Convolutional Neural Network) is proposed. This procedure tells the mapping relationship how to create the illumination map. Following image processing, an RCNN strategy for underwater detection and classification is recommended. Two improved strategies are then used to change the RCNN structure in accordance with the properties of underwater vision. In order to deal with the challenges of object tracking and detection in underwater communication, a correlation filter tracking algorithm (CFTA) method was created. The properties of the invariant moment and area were looked at after the object's region had been extracted using a threshold segment and morphological technique. The findings show that the suggested method is effective for underwater target tracking based on RCNN-CFTA in the aquatic environment. Simulated evaluation of these methods' performance demonstrates the potency of the suggested strategies.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117324327","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：