Pub Date : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085131
Nema Salem, Jameelh Asiri
In 2020, nearly all Saudi Arabia’s electricity generation was fueled by natural gas (61%) and crude oil (39%). As part of Saudi Arabia’s vision 2030, the Saudi government plans to diversify fuels to increase crude oil exports and reduce carbon dioxide emissions. In Saudi Arabia, the solar irradiance averages 5.2 kWh/m2/day, photovoltaic (PV) technology is being embraced to achieve green growth and increase power generation. As a result of the technology’s proximity to the point of consumption, it ensures a continuous supply of energy while reducing the country’s transmission and distribution losses. A key parameter affecting the performance of PV panels in a photovoltaic system is the solar radiation incident on the panel. The tilt and azimuth angles of PV modules are two important factors in designing the PV system for the best performance. This study starts by utilizing Excel software to calculate the azimuth angle for the best adjustment of solar modules. Then, PVSyst software is used to design and simulate a grid-connected PV system for the Admission and Registration Building (AR) at Effat University in Jeddah. The study compares the solar system’s performance for mono-crystalline, poly-crystalline, and thin-film photovoltaic modules. The simulation results showed the effectiveness of the design in terms of the produced energy, meeting the estimated needs of the AR building, the save CO2, and the annual savings using Saudi Arabia’s current electricity tariffs.
{"title":"Design and Performance Analysis of a Grid-Connected Solar Power System for Energy Efficient AR Building","authors":"Nema Salem, Jameelh Asiri","doi":"10.1109/ICAISC56366.2023.10085131","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085131","url":null,"abstract":"In 2020, nearly all Saudi Arabia’s electricity generation was fueled by natural gas (61%) and crude oil (39%). As part of Saudi Arabia’s vision 2030, the Saudi government plans to diversify fuels to increase crude oil exports and reduce carbon dioxide emissions. In Saudi Arabia, the solar irradiance averages 5.2 kWh/m2/day, photovoltaic (PV) technology is being embraced to achieve green growth and increase power generation. As a result of the technology’s proximity to the point of consumption, it ensures a continuous supply of energy while reducing the country’s transmission and distribution losses. A key parameter affecting the performance of PV panels in a photovoltaic system is the solar radiation incident on the panel. The tilt and azimuth angles of PV modules are two important factors in designing the PV system for the best performance. This study starts by utilizing Excel software to calculate the azimuth angle for the best adjustment of solar modules. Then, PVSyst software is used to design and simulate a grid-connected PV system for the Admission and Registration Building (AR) at Effat University in Jeddah. The study compares the solar system’s performance for mono-crystalline, poly-crystalline, and thin-film photovoltaic modules. The simulation results showed the effectiveness of the design in terms of the produced energy, meeting the estimated needs of the AR building, the save CO2, and the annual savings using Saudi Arabia’s current electricity tariffs.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126547","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085183
Ashish Sharma, Prafullit Shukla, Mahendra Kumar Gourisaria, B. Sharma, I. Dhaou
With the increase in the Telecom industry, service providers are more attentive toward the action of becoming larger or more extensive to the subscriber base. For surviving in telecom companies, the continued possession of holding customers must be a big challenge. According to consideration in the telecom environment, the market price of obtaining the new purchaser is more than holding the existing purchaser. Through collecting knowledge from the telecom industry to analyze the association of the customer whether will leave or not the company. Such types of the Decision tree and Logistic regression model have been compared on the 3334 instances of the dataset. The classification model derived from logistic regression has an accuracy of 80% and the decision tree classifier with an accuracy of 97%.
{"title":"Telecom Churn Analysis using Machine Learning in Smart Cities","authors":"Ashish Sharma, Prafullit Shukla, Mahendra Kumar Gourisaria, B. Sharma, I. Dhaou","doi":"10.1109/ICAISC56366.2023.10085183","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085183","url":null,"abstract":"With the increase in the Telecom industry, service providers are more attentive toward the action of becoming larger or more extensive to the subscriber base. For surviving in telecom companies, the continued possession of holding customers must be a big challenge. According to consideration in the telecom environment, the market price of obtaining the new purchaser is more than holding the existing purchaser. Through collecting knowledge from the telecom industry to analyze the association of the customer whether will leave or not the company. Such types of the Decision tree and Logistic regression model have been compared on the 3334 instances of the dataset. The classification model derived from logistic regression has an accuracy of 80% and the decision tree classifier with an accuracy of 97%.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130587228","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085097
Amnah Al-Sulami, Miada Al-Masre, N. Al-Malki
Predicting learners’ final course achievement is most of the time based on the grades they get on their graded course activities. Thus, it is of great importance for both students and higher education institutions to detect risk instances which can be addressed by the academic institution to support students’ success and academic advancement. In this context, Learning Analytics (LA), which represents learners’ behavior inside Learning Management Systems (LMS), and Deep Learning (DL) techniques come into play as academic data, which can be used to predict learners’ future achievements. It is not surprising that at-risk profiling becomes necessary when there are large numbers of students taking a preparatory course online, for example, where instructors fail to monitor their progress in real-time. Thus, the proposed study aims to utilize neural networks (vRNN, LSTM, and GRU); to build models that predict students’ final grade by classifing them as pass or fail based on their assessment grades. In the training process, the three models, alongside a baseline Multilayer Perceptron (MLP) classifier, were trained on four datasets illustrating students’ LMS activity and final grade results in a two-module English preparatory course in King Abdulaziz University (KAU). The datasets were collected during the first and second semesters of 2021. Results indicate that though all of the three DL models performed better than the MLP baseline, the GRU model achieved the highest classification accuracy on three datasets: (ELIA 103-1, 103-2, and 104-1) with the accuracy values of 92.21%, 97.75%, and 94.34%, respectively. On ELIA 104-2 dataset, both vRNN and LSTM achieved 99.89% accuracy. Considering the prediction of at-risk students, the three DL models achieved high recall values ranging from 65.38% to 99.79. %
{"title":"Deep Learning to Predict At-Risk Students’ Achievement in a Preparatory-year English Courses","authors":"Amnah Al-Sulami, Miada Al-Masre, N. Al-Malki","doi":"10.1109/ICAISC56366.2023.10085097","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085097","url":null,"abstract":"Predicting learners’ final course achievement is most of the time based on the grades they get on their graded course activities. Thus, it is of great importance for both students and higher education institutions to detect risk instances which can be addressed by the academic institution to support students’ success and academic advancement. In this context, Learning Analytics (LA), which represents learners’ behavior inside Learning Management Systems (LMS), and Deep Learning (DL) techniques come into play as academic data, which can be used to predict learners’ future achievements. It is not surprising that at-risk profiling becomes necessary when there are large numbers of students taking a preparatory course online, for example, where instructors fail to monitor their progress in real-time. Thus, the proposed study aims to utilize neural networks (vRNN, LSTM, and GRU); to build models that predict students’ final grade by classifing them as pass or fail based on their assessment grades. In the training process, the three models, alongside a baseline Multilayer Perceptron (MLP) classifier, were trained on four datasets illustrating students’ LMS activity and final grade results in a two-module English preparatory course in King Abdulaziz University (KAU). The datasets were collected during the first and second semesters of 2021. Results indicate that though all of the three DL models performed better than the MLP baseline, the GRU model achieved the highest classification accuracy on three datasets: (ELIA 103-1, 103-2, and 104-1) with the accuracy values of 92.21%, 97.75%, and 94.34%, respectively. On ELIA 104-2 dataset, both vRNN and LSTM achieved 99.89% accuracy. Considering the prediction of at-risk students, the three DL models achieved high recall values ranging from 65.38% to 99.79. %","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116019594","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085238
V. Goswami, B. Sharma, S. Patra, Subrata Chowdhury, Rabindra Kumar Barik, I. Dhaou
In the current scenarios there is a lot of development in the networking sector. Additionally needed are quick operations and the capability to solve complex issues. From several technical angles, IoT is being promoted to meet these developments. Implementations of IoT confront difficulties in handling such enormous volume of data including issues with its Quality of Services (QoS) necessities, privacy with security and the variety of networking elements. In smart cities, a vast volume of data is generated through IoT devices. They need to be processed near the edge devices due to latency issues, especially in the case of critical data-sensitive applications. Fog computing, a new technological paradigm, delivers a collection of networking essential services nearer to the client than cloud computing does. Fog computing overrides the cloud computing in the areas such as networking infrastructure scalability, latency reduction, network service dependability, and network device security. The technical approach to provide the highest degree of computing service has advanced by contributing cloud-assisted network services nearer to the end user/customer level. Fog servers can malfunction in a variety of circumstances. In this study, we describe the fog system as a machine-repair problem, where repair work is performed at a certain pace as soon as the Virtual Machine (VM) malfunctions. To analyze the system, numerous numerical analyses have been conducted.
{"title":"IoT-Fog Computing Sustainable System for Smart Cities: A Queueing-based Approach","authors":"V. Goswami, B. Sharma, S. Patra, Subrata Chowdhury, Rabindra Kumar Barik, I. Dhaou","doi":"10.1109/ICAISC56366.2023.10085238","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085238","url":null,"abstract":"In the current scenarios there is a lot of development in the networking sector. Additionally needed are quick operations and the capability to solve complex issues. From several technical angles, IoT is being promoted to meet these developments. Implementations of IoT confront difficulties in handling such enormous volume of data including issues with its Quality of Services (QoS) necessities, privacy with security and the variety of networking elements. In smart cities, a vast volume of data is generated through IoT devices. They need to be processed near the edge devices due to latency issues, especially in the case of critical data-sensitive applications. Fog computing, a new technological paradigm, delivers a collection of networking essential services nearer to the client than cloud computing does. Fog computing overrides the cloud computing in the areas such as networking infrastructure scalability, latency reduction, network service dependability, and network device security. The technical approach to provide the highest degree of computing service has advanced by contributing cloud-assisted network services nearer to the end user/customer level. Fog servers can malfunction in a variety of circumstances. In this study, we describe the fog system as a machine-repair problem, where repair work is performed at a certain pace as soon as the Virtual Machine (VM) malfunctions. To analyze the system, numerous numerical analyses have been conducted.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129011744","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085192
Lukman Adewale Ajao, S. T. Apeh
The advent of a smart city-based industrial Internet of Things (IIoT) is confidently built on the combined protocols of a virtual IPv6 addressing scheme and the fifth generation (5G) mobile network. For better network service and to achieve Quality of Experience (QoE) in the architecture. But this intelligent city architecture is vulnerable to several cyber-attack and malicious actors at the different layers which make it exposed to the same attacks as in the conventional IPv4 wireless sensor networks. However, this work aims to develop a blockchain-based machine learning (BML) security framework that secures the fog computing layer vulnerability in the smart city’s sustainability. The machine learning approach is firstly implemented between the edge layer and fog server nodes of the city architecture for the variants of intrusion detection using different ML algorithms for the attack’s discovery and classification. While the augmented blockchain technology is implemented between the fog layer and cloud computing to enhance the privacy and confidentiality of packet traffic broadcast to the public. The results obtained from ML-IDS show high-performance detection accuracy and low processing time. While the blockchain framework is also evaluated based on the certmcate generation, and retrieval size in bytes and time in milliseconds.
{"title":"Blockchain Integration with Machine Learning for Securing Fog Computing Vulnerability in Smart City Sustainability","authors":"Lukman Adewale Ajao, S. T. Apeh","doi":"10.1109/ICAISC56366.2023.10085192","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085192","url":null,"abstract":"The advent of a smart city-based industrial Internet of Things (IIoT) is confidently built on the combined protocols of a virtual IPv6 addressing scheme and the fifth generation (5G) mobile network. For better network service and to achieve Quality of Experience (QoE) in the architecture. But this intelligent city architecture is vulnerable to several cyber-attack and malicious actors at the different layers which make it exposed to the same attacks as in the conventional IPv4 wireless sensor networks. However, this work aims to develop a blockchain-based machine learning (BML) security framework that secures the fog computing layer vulnerability in the smart city’s sustainability. The machine learning approach is firstly implemented between the edge layer and fog server nodes of the city architecture for the variants of intrusion detection using different ML algorithms for the attack’s discovery and classification. While the augmented blockchain technology is implemented between the fog layer and cloud computing to enhance the privacy and confidentiality of packet traffic broadcast to the public. The results obtained from ML-IDS show high-performance detection accuracy and low processing time. While the blockchain framework is also evaluated based on the certmcate generation, and retrieval size in bytes and time in milliseconds.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114895491","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085673
A. Riaz, Muhammad Jawad Ikram, Najmussaba Asadullah
A Blockchain network contains a distributed ledger that is used to store a secure and permanent record of transactions among multiple parties. As the registries of land records are historically stored in the form of paper documentation where, there might arise the issue of losing, destroying, and modifying needed documents. This land registration process is complicated and time-consuming and required a lot of effort to transfer ownership of the land registry or change any information. For this purpose, various contributions have been made by different researchers to overcome the problem of the classical land registration process by using blockchain technology. In this survey, we shed light on some advantages (reduce time and effort, security, permanency, etc.) of blockchain to identify some early problems in the paper-based land registration process.
{"title":"Using Blockchain to Overcome the Issues in Land Registry Management: A Systematic Review","authors":"A. Riaz, Muhammad Jawad Ikram, Najmussaba Asadullah","doi":"10.1109/ICAISC56366.2023.10085673","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085673","url":null,"abstract":"A Blockchain network contains a distributed ledger that is used to store a secure and permanent record of transactions among multiple parties. As the registries of land records are historically stored in the form of paper documentation where, there might arise the issue of losing, destroying, and modifying needed documents. This land registration process is complicated and time-consuming and required a lot of effort to transfer ownership of the land registry or change any information. For this purpose, various contributions have been made by different researchers to overcome the problem of the classical land registration process by using blockchain technology. In this survey, we shed light on some advantages (reduce time and effort, security, permanency, etc.) of blockchain to identify some early problems in the paper-based land registration process.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133346806","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085121
Safia Nahhas
In the last period, realizing the smart cities vision has required utilizing many technologies, such as internet of things and others. Our investigation in this study reveals that semantic internet of things technologies have a vital role in addressing essential issues in smart cities, primarily interoperability issues. Hence, in this paper we extrapolate and highlight the potentials of semantic internet of things in smart cities based on examining many sample cases. Additionally, this paper provides a general roadmap and an abstract architecture to facilitate exploiting semantic internet of things in smart cities. Common frameworks, ontologies, standards, and tools that are used in many sample cases are extracted and accentuated. The study also pinpoints the most frequent quality attributes that are considered in semantic internet of things in smart cities’ field. Finally, the paper identifies the ongoing issues that still require improvement regarding the semantic internet of things in smart cities.
{"title":"Potentials of semantic internet of things in smart cities: an overview and roadmap","authors":"Safia Nahhas","doi":"10.1109/ICAISC56366.2023.10085121","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085121","url":null,"abstract":"In the last period, realizing the smart cities vision has required utilizing many technologies, such as internet of things and others. Our investigation in this study reveals that semantic internet of things technologies have a vital role in addressing essential issues in smart cities, primarily interoperability issues. Hence, in this paper we extrapolate and highlight the potentials of semantic internet of things in smart cities based on examining many sample cases. Additionally, this paper provides a general roadmap and an abstract architecture to facilitate exploiting semantic internet of things in smart cities. Common frameworks, ontologies, standards, and tools that are used in many sample cases are extracted and accentuated. The study also pinpoints the most frequent quality attributes that are considered in semantic internet of things in smart cities’ field. Finally, the paper identifies the ongoing issues that still require improvement regarding the semantic internet of things in smart cities.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124058250","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085538
Saleh Ateeq Almutairi
Highway congestion is a major obstacle to Saudi Arabia’s modernization and economic diversification initiatives. Intelligent transportation systems (ITS) have recently become a practical investment choice. Vehicular Ad Hoc Networks (VANET) allow for transportation system enhancements. In addition, the technology to harness solar power can be considered a viable renewable energy option. Since photovoltaic (PV) panels can produce electricity at scales ranging from microwatts to megawatts; they represent a promising option. Besides, academics and business executives have recently received more attention to distributed computing paradigms. As a result, implementing ITS in KSA necessitates using green technology and distributed computing methods. Therefore, the primary goal of this research is to present a standard design for an Internet of Things (IoT)- Fog computing-based PV system, including Solar photovoltaic panels, batteries, an MPPT charger, LED drivers, a microcontroller (MCU), IoT devices, and distributed computing approaches.
{"title":"Towards Green and Computing Approaches to Establish Intelligent Transportation Systems (ITS) in KSA","authors":"Saleh Ateeq Almutairi","doi":"10.1109/ICAISC56366.2023.10085538","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085538","url":null,"abstract":"Highway congestion is a major obstacle to Saudi Arabia’s modernization and economic diversification initiatives. Intelligent transportation systems (ITS) have recently become a practical investment choice. Vehicular Ad Hoc Networks (VANET) allow for transportation system enhancements. In addition, the technology to harness solar power can be considered a viable renewable energy option. Since photovoltaic (PV) panels can produce electricity at scales ranging from microwatts to megawatts; they represent a promising option. Besides, academics and business executives have recently received more attention to distributed computing paradigms. As a result, implementing ITS in KSA necessitates using green technology and distributed computing methods. Therefore, the primary goal of this research is to present a standard design for an Internet of Things (IoT)- Fog computing-based PV system, including Solar photovoltaic panels, batteries, an MPPT charger, LED drivers, a microcontroller (MCU), IoT devices, and distributed computing approaches.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129330452","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 : 2023-01-23DOI: 10.1109/ICAISC56366.2023.10085369
K. Garg, Manik Gupta, B. Sharma, I. Dhaou
The expansion of the internet of things (IoT) and Big Data are two factors that have contributed to the rise in popularity of smart cities. The ability to anticipate the quality of the air in an area with precision and efficiency is one of the fundamental building blocks of a smart city. The amount of polluted air found in smart cities throughout the world has been gradually growing. Because of this, there has been a rise in the concentration of several air pollutants in the environment, including particulate matter (PM 10), sulphur dioxide (SO2), and PM 2.5, amongst others. Because of the possibility of uncontrollable repercussions, such as an increase in the severity of asthma and cardiovascular disease, this situation poses a risk to the country and to the people who live in it. Heavy industry and vehicle exhaust have been major contributors to the growth of air pollution in smart cities such as New Delhi, Bombay, Chandigarh, and Bengaluru in India. The purpose of this investigation is to compare and contrast the efficiency of a variety of machine learning methods in order to assess the precision of the air quality index (AQI) projection of PM 2.5 in Chandigarh, India. Models for predicting AQI are trained and tested using a variety of statistical techniques like Linear regression, Lasso regression, KNN regression, and Random Forest regression This Root Mean Square Error (RMSE) found for Linear regression, Lasso regression, KNN regression, and Random Forest regression are 31.01, 29,45, 37.09 and 28.3. From all four models, random forest regression was more accurate than the other three regression models in estimating PM 2.5 levels in India’s smart city.
{"title":"A Comparison of Regression Techniques for Prediction of Air Quality in Smart Cities","authors":"K. Garg, Manik Gupta, B. Sharma, I. Dhaou","doi":"10.1109/ICAISC56366.2023.10085369","DOIUrl":"https://doi.org/10.1109/ICAISC56366.2023.10085369","url":null,"abstract":"The expansion of the internet of things (IoT) and Big Data are two factors that have contributed to the rise in popularity of smart cities. The ability to anticipate the quality of the air in an area with precision and efficiency is one of the fundamental building blocks of a smart city. The amount of polluted air found in smart cities throughout the world has been gradually growing. Because of this, there has been a rise in the concentration of several air pollutants in the environment, including particulate matter (PM 10), sulphur dioxide (SO2), and PM 2.5, amongst others. Because of the possibility of uncontrollable repercussions, such as an increase in the severity of asthma and cardiovascular disease, this situation poses a risk to the country and to the people who live in it. Heavy industry and vehicle exhaust have been major contributors to the growth of air pollution in smart cities such as New Delhi, Bombay, Chandigarh, and Bengaluru in India. The purpose of this investigation is to compare and contrast the efficiency of a variety of machine learning methods in order to assess the precision of the air quality index (AQI) projection of PM 2.5 in Chandigarh, India. Models for predicting AQI are trained and tested using a variety of statistical techniques like Linear regression, Lasso regression, KNN regression, and Random Forest regression This Root Mean Square Error (RMSE) found for Linear regression, Lasso regression, KNN regression, and Random Forest regression are 31.01, 29,45, 37.09 and 28.3. From all four models, random forest regression was more accurate than the other three regression models in estimating PM 2.5 levels in India’s smart city.","PeriodicalId":422888,"journal":{"name":"2023 1st International Conference on Advanced Innovations in Smart Cities (ICAISC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115567419","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：