Pub Date : 2021-11-24DOI: 10.1109/citisia53721.2021.9719907
Himanshi Babbar, Shalli Rani, Sardar M. N. Islam, S. Iyer
An innovative QoS based security architecture for software-defined wireless sensor networking is developed in this paper. Conventional networks are constrained by hardware limitations and rigid architectural design, limiting research and innovation. Software-Defined Networking (SDN) is a networking breakthrough that allows administrators to control and customize their entire network from a central location. SDN makes network management more manageable and more effective. SDN model can deliver versatile routing and help the various communication patterns found in Wireless Sensor Networks (WSN). However, adopting this model to resource- constrained networks is difficult, particularly when security services are required. Current Software-Defined Networking- based Wireless Sensor Networks (SDN-WSN) methods have developed over time to meet resource-constrained needs. In this paper, the authors have discussed security architecture, its challenges and solutions. Further, the comparative analysis of various security algorithms (SEC-SDWSN, Genetic, Routing optimization for cross-domain preservation (ROCDP)) in SDN- WSN is carried out. The SEC-SDWSN achieved the better results based on the Quality of Service (QoS) metrics (packet delivery ratio, data transmission, response time and energy consumed parameters) which shows packet delivery ratio in SEC-SDWSN is 4% better than Genetic and ROCDP; data transmission rate in SEC-SDWSN is 15Kbps better than Genetic; and response time in SEC-SDWSN is 5% better than Genetic. Therefore, an original contribution to the literature and practices of network security architecture is made in this paper by developing an innovative QoS based security architecture for software-defined wireless sensor networking.
提出了一种创新的基于QoS的软件定义无线传感器网络安全体系结构。传统的网络受到硬件限制和僵化的架构设计的限制,限制了研究和创新。软件定义网络(SDN)是一项突破性的网络技术,它允许管理员从一个中心位置控制和定制整个网络。SDN使网络管理更易于管理,更有效。SDN模型可以提供多用途路由,并支持无线传感器网络(WSN)中的各种通信模式。然而,在资源受限的网络中采用这种模型是困难的,特别是当需要安全服务时。当前基于软件定义网络的无线传感器网络(SDN-WSN)方法是随着时间的推移而发展的,以满足资源受限的需求。在本文中,作者讨论了安全架构,其挑战和解决方案。进一步,对SDN- WSN中各种安全算法(SEC-SDWSN、Genetic、Routing optimization for cross-domain preservation (ROCDP))进行了比较分析。基于服务质量(QoS)指标(分组传送率、数据传输、响应时间和能耗参数),SEC-SDWSN的分组传送率比Genetic和ROCDP高4%;SEC-SDWSN的数据传输率比Genetic提高了15Kbps;与遗传算法相比,SEC-SDWSN的响应时间提高了5%。因此,本文通过为软件定义无线传感器网络开发一种创新的基于QoS的安全架构,对网络安全架构的文献和实践做出了原创性的贡献。
{"title":"QoS based Security Architecture for Software- Defined Wireless Sensor Networking","authors":"Himanshi Babbar, Shalli Rani, Sardar M. N. Islam, S. Iyer","doi":"10.1109/citisia53721.2021.9719907","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719907","url":null,"abstract":"An innovative QoS based security architecture for software-defined wireless sensor networking is developed in this paper. Conventional networks are constrained by hardware limitations and rigid architectural design, limiting research and innovation. Software-Defined Networking (SDN) is a networking breakthrough that allows administrators to control and customize their entire network from a central location. SDN makes network management more manageable and more effective. SDN model can deliver versatile routing and help the various communication patterns found in Wireless Sensor Networks (WSN). However, adopting this model to resource- constrained networks is difficult, particularly when security services are required. Current Software-Defined Networking- based Wireless Sensor Networks (SDN-WSN) methods have developed over time to meet resource-constrained needs. In this paper, the authors have discussed security architecture, its challenges and solutions. Further, the comparative analysis of various security algorithms (SEC-SDWSN, Genetic, Routing optimization for cross-domain preservation (ROCDP)) in SDN- WSN is carried out. The SEC-SDWSN achieved the better results based on the Quality of Service (QoS) metrics (packet delivery ratio, data transmission, response time and energy consumed parameters) which shows packet delivery ratio in SEC-SDWSN is 4% better than Genetic and ROCDP; data transmission rate in SEC-SDWSN is 15Kbps better than Genetic; and response time in SEC-SDWSN is 5% better than Genetic. Therefore, an original contribution to the literature and practices of network security architecture is made in this paper by developing an innovative QoS based security architecture for software-defined wireless sensor networking.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129749652","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719924
Abhiyan Gurung
Despite the exponential growth of cloud infrastructure over several years, data protection and reliable computing are still major obstacles for modern cloud computing applications. In order to address this issue, several researchers have done a lot of work on this and have suggested a variety of models, including data integrity checking and stable multi-party estimates. Vehicle ad-hoc networks (VANETs) have been diagnosed with several security issues, such as confidentiality, safe authorization/authentication, and system stability. Nevertheless, almost all these alternatives face challenges like over-computational complexity or absence of scalability. This paper explores the usage of blockchain technologies in order to strengthen this scenario. Blockchain is collaborative modern framework for distributed computation. Applying blockchain technologies to cloud infrastructure, leveraging the former encryption framework to boost the efficiency of data storage and decentralized computation, is an exciting research area. A system of message verification for the privacy and decentralization of knowledge utilizing blockchain technologies is proposed in this paper. This is where we add message authentication code (MAC) and public-private key for stable authentication. In this document, we follow consensus algorithms for computing blockchain structures such as proof of work (PoW) and Practical Byzantine Fault Tolerance (PBFT) in the proposed authorization method. Finally, it is shown that the suggested approach is secure from threats that require the impersonation of the internal intruder as well as the usual threats.
{"title":"Data security and privacy in cloud computing focused on transportation sector with the aid of block chain approach","authors":"Abhiyan Gurung","doi":"10.1109/citisia53721.2021.9719924","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719924","url":null,"abstract":"Despite the exponential growth of cloud infrastructure over several years, data protection and reliable computing are still major obstacles for modern cloud computing applications. In order to address this issue, several researchers have done a lot of work on this and have suggested a variety of models, including data integrity checking and stable multi-party estimates. Vehicle ad-hoc networks (VANETs) have been diagnosed with several security issues, such as confidentiality, safe authorization/authentication, and system stability. Nevertheless, almost all these alternatives face challenges like over-computational complexity or absence of scalability. This paper explores the usage of blockchain technologies in order to strengthen this scenario. Blockchain is collaborative modern framework for distributed computation. Applying blockchain technologies to cloud infrastructure, leveraging the former encryption framework to boost the efficiency of data storage and decentralized computation, is an exciting research area. A system of message verification for the privacy and decentralization of knowledge utilizing blockchain technologies is proposed in this paper. This is where we add message authentication code (MAC) and public-private key for stable authentication. In this document, we follow consensus algorithms for computing blockchain structures such as proof of work (PoW) and Practical Byzantine Fault Tolerance (PBFT) in the proposed authorization method. Finally, it is shown that the suggested approach is secure from threats that require the impersonation of the internal intruder as well as the usual threats.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124680552","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 : 2021-11-24DOI: 10.1109/CITISIA53721.2021.9719978
D. T. Sulaga, Angelika Maag, Indra Seher, Amr Elchouemi
Deep learning (DL) is an emerging technology that is being used in many areas due to its effectiveness. One of its major applications is attack detection and prevention of backdoor attacks. Sampling-based measurement approaches in the software-defined network of an Internet of Things (IoT) network often result in low accuracy, high overhead, higher memory consumption, and low attack detection. This study aims to review and analyse papers on DL-based network prediction techniques against the problem of Distributed Denial of service attack (DDoS) in a secure software network. Techniques and approaches have been studied, that can effectively predict network traffic and detect DDoS attacks. Based on this review, major components are identified in each work from which an overall system architecture is suggested showing the basic processes needed. Major findings are that the DL is effective against DDoS attacks more than other state of the art approaches.
{"title":"Using Deep learning for network traffic prediction to secure Software networks against DDoS attacks","authors":"D. T. Sulaga, Angelika Maag, Indra Seher, Amr Elchouemi","doi":"10.1109/CITISIA53721.2021.9719978","DOIUrl":"https://doi.org/10.1109/CITISIA53721.2021.9719978","url":null,"abstract":"Deep learning (DL) is an emerging technology that is being used in many areas due to its effectiveness. One of its major applications is attack detection and prevention of backdoor attacks. Sampling-based measurement approaches in the software-defined network of an Internet of Things (IoT) network often result in low accuracy, high overhead, higher memory consumption, and low attack detection. This study aims to review and analyse papers on DL-based network prediction techniques against the problem of Distributed Denial of service attack (DDoS) in a secure software network. Techniques and approaches have been studied, that can effectively predict network traffic and detect DDoS attacks. Based on this review, major components are identified in each work from which an overall system architecture is suggested showing the basic processes needed. Major findings are that the DL is effective against DDoS attacks more than other state of the art approaches.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121859158","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719908
Suman Sansanwal, Nitin Jain
Cloud computing has earned lot of awarenes in the Information Technology and now appeared as the next level in the evolution of Internet. But now it has been observed that the Load balancing (LB) is one among various challenges in cloud computing that needs to be resolved to perform the accurate operations on cloud and also to obtain the rapid development in the the sphere of cloud computing. The demand of various customers all over the world for the services used to increase the load rapidly. Therefore load balancing required to equally distribute the workload over each and every virtual machine in the cloud system hence as a result the throughput increases and the response time minimizes. The aim of load balancing is to build the client satisfaction, resource utilization maximisation and improvement in the cloud system performance leads to reduction in energy consumption and heat dissipation. In the present paper, the standard Grey Wolf Optimisation algorithm for load balancing is demonstrated for the cloud environment. Also the other versions of Grey wolf optimisation has been studied to know the issues related to them and additional functionality required by them to achieve the higher system performance. Furthermore, according to the surveyed research papers it has been seen that now the performance of the proposed hybrid Grey Wolf Optimisation algorithms is simulated by using Cloudsim simulator on the basis of different parameters such as throughput and response time etc.
{"title":"Review of existing variants of Grey Wolf Optimization algorithm handling Load Balancing in Clouds","authors":"Suman Sansanwal, Nitin Jain","doi":"10.1109/citisia53721.2021.9719908","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719908","url":null,"abstract":"Cloud computing has earned lot of awarenes in the Information Technology and now appeared as the next level in the evolution of Internet. But now it has been observed that the Load balancing (LB) is one among various challenges in cloud computing that needs to be resolved to perform the accurate operations on cloud and also to obtain the rapid development in the the sphere of cloud computing. The demand of various customers all over the world for the services used to increase the load rapidly. Therefore load balancing required to equally distribute the workload over each and every virtual machine in the cloud system hence as a result the throughput increases and the response time minimizes. The aim of load balancing is to build the client satisfaction, resource utilization maximisation and improvement in the cloud system performance leads to reduction in energy consumption and heat dissipation. In the present paper, the standard Grey Wolf Optimisation algorithm for load balancing is demonstrated for the cloud environment. Also the other versions of Grey wolf optimisation has been studied to know the issues related to them and additional functionality required by them to achieve the higher system performance. Furthermore, according to the surveyed research papers it has been seen that now the performance of the proposed hybrid Grey Wolf Optimisation algorithms is simulated by using Cloudsim simulator on the basis of different parameters such as throughput and response time etc.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130096024","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719882
{"title":"Conference Committee for CITISIA 2021","authors":"","doi":"10.1109/citisia53721.2021.9719882","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719882","url":null,"abstract":"","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130715257","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719953
A. Aanchal, P. Prasad
The review study was based on the integrated network and the secured protocols and blockchain technology to detect security issues and protect the user’s data storage. The study aims to review the recently published research articles that state the data storage techniques and blockchain technology for the IIoT to manage data confidentiality. The method opted here was the literature review for the collections and knowledge of the data management. Moreover, a secondary research method was selected in which the currently published research article was gathering to review the literature. The research paper's expected finding was that data storage and data management are the two crucial factors that had been used within the industry for allocation and work management. It had helped in enhancing industrial performance. The research work's contribution is in data collection from different libraries based on data storage techniques. This work plays a huge contributory role in investigating the currently available solutions dependent on blockchain technology and data storage technique for managing the data effectively and delivering valuable insights for data storage capabilities. The review study included different factors and attributes classified by considering different instances as per the author’s interest. The major component was also evaluated in this study through a different segment, including error rate and accuracy matrix that shows the system validation. The study verifies the system by considering different terms and their related frequency in the last segment, which justifies system accuracy.
{"title":"Topic: Scoping review of Blockchain based data storage technique in industrial IoT data management","authors":"A. Aanchal, P. Prasad","doi":"10.1109/citisia53721.2021.9719953","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719953","url":null,"abstract":"The review study was based on the integrated network and the secured protocols and blockchain technology to detect security issues and protect the user’s data storage. The study aims to review the recently published research articles that state the data storage techniques and blockchain technology for the IIoT to manage data confidentiality. The method opted here was the literature review for the collections and knowledge of the data management. Moreover, a secondary research method was selected in which the currently published research article was gathering to review the literature. The research paper's expected finding was that data storage and data management are the two crucial factors that had been used within the industry for allocation and work management. It had helped in enhancing industrial performance. The research work's contribution is in data collection from different libraries based on data storage techniques. This work plays a huge contributory role in investigating the currently available solutions dependent on blockchain technology and data storage technique for managing the data effectively and delivering valuable insights for data storage capabilities. The review study included different factors and attributes classified by considering different instances as per the author’s interest. The major component was also evaluated in this study through a different segment, including error rate and accuracy matrix that shows the system validation. The study verifies the system by considering different terms and their related frequency in the last segment, which justifies system accuracy.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124250782","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719943
Amish Patel, Zhongyan Ge, Indra Seher, Van Luong Vo
Cloud computing is the type of technology preferred to maintain computing power, computer resources, and majorly used to handle the cloud storage process. Also, it helps to manage the data security process during different applications. The data encryption, data classification, and feature extraction approaches are majorly considered for increasing the data security process. The main aim of the work is to review the DNA based cloud computing process for improving data security. The main purpose of this work is to review the current research article focus on the data security and computing process. Further, taxonomy is introduced that helps in the evaluation and analysis process. The secondary research approach is used during review work. Further, the deep learning with sequencing and modification process is reviewed in the work to manage the security and sequence analysis process. In addition, the block-chain-based random technique is reviewed to manage data detection and probability rate. The data optimization and data indexing process with block-chain is preferred to enhance data security and handle the feasibility, accuracy, and transfer time. Moreover, the OPNET model, Dynamic and static model approach, and data access algorithms are used together for maintaining the data mining security process. The IoT network topology and attributes based encryption process are reviewed in developed methods for maintaining data optimization and data security process. These approaches and factors are analyzed with the help of current research articles in order to review the state of the art in the developed method.
{"title":"DNA based service data security in cloud computing environment","authors":"Amish Patel, Zhongyan Ge, Indra Seher, Van Luong Vo","doi":"10.1109/citisia53721.2021.9719943","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719943","url":null,"abstract":"Cloud computing is the type of technology preferred to maintain computing power, computer resources, and majorly used to handle the cloud storage process. Also, it helps to manage the data security process during different applications. The data encryption, data classification, and feature extraction approaches are majorly considered for increasing the data security process. The main aim of the work is to review the DNA based cloud computing process for improving data security. The main purpose of this work is to review the current research article focus on the data security and computing process. Further, taxonomy is introduced that helps in the evaluation and analysis process. The secondary research approach is used during review work. Further, the deep learning with sequencing and modification process is reviewed in the work to manage the security and sequence analysis process. In addition, the block-chain-based random technique is reviewed to manage data detection and probability rate. The data optimization and data indexing process with block-chain is preferred to enhance data security and handle the feasibility, accuracy, and transfer time. Moreover, the OPNET model, Dynamic and static model approach, and data access algorithms are used together for maintaining the data mining security process. The IoT network topology and attributes based encryption process are reviewed in developed methods for maintaining data optimization and data security process. These approaches and factors are analyzed with the help of current research articles in order to review the state of the art in the developed method.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"126 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124235902","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719992
Fahmi Adam Augusta, Ahmad Husin Lubis, A. Syahriar, Putri Wulandari
Fossil energy, especially petroleum, is the main energy source and a source of foreign exchange. Indonesia has a limited amount of fossil energy. Meanwhile, energy consumption continues to increase along with the economic and population growth. Thus natural resources such as oil, gas, and coal are becoming more depleted, because they are not renewable energy. Indonesia is a tropical country located on the equator, as an archipelago with varied geological contours, more than 100 mountains, and also beaches. One of the energies that might be utilized is wind energy with an affordable cost and free pollutant output. Wind Turbines have become one of the feasible power plants to replace fossil energy. The mechanism of wind turbine is that the wind blows against the blades of the wind turbine, and allows the blades to rotate as the axis and produces a valuable source of renewable energy by repetitive rotational motion. This research was focused on finding a suitable generator for Savonius Vertical Axis Wind Turbine (VAWT) that can produce a high voltage at low RPM. In this research, to replicate the real wind blow, two different fans are used: a. 71 cm diameter industrial fan with range of wind speed from 1 to 6 m/s; b. 31 cm fan with a range of wind speed from 1 to 4,5 m/s. From the result, it can be concluded that the direction of the wind affects the rotation of the rotor, so it must be ensured that the wind touches the tip of the blade to maximize the rotational speed. The maximum voltage output produced by VAWT is 4,8 V at 67 RPM on wind speed 6 m/s using the 1st Generator. For further development, the Vertical Axis Wind Turbine (VAWT) have to be remodelled so the ratio between rotor radius and rotor height is 1,2.
{"title":"The Implementation of Low RPM Generator on Small Scale Savonius Vertical Axis Wind Turbine (VAWT)","authors":"Fahmi Adam Augusta, Ahmad Husin Lubis, A. Syahriar, Putri Wulandari","doi":"10.1109/citisia53721.2021.9719992","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719992","url":null,"abstract":"Fossil energy, especially petroleum, is the main energy source and a source of foreign exchange. Indonesia has a limited amount of fossil energy. Meanwhile, energy consumption continues to increase along with the economic and population growth. Thus natural resources such as oil, gas, and coal are becoming more depleted, because they are not renewable energy. Indonesia is a tropical country located on the equator, as an archipelago with varied geological contours, more than 100 mountains, and also beaches. One of the energies that might be utilized is wind energy with an affordable cost and free pollutant output. Wind Turbines have become one of the feasible power plants to replace fossil energy. The mechanism of wind turbine is that the wind blows against the blades of the wind turbine, and allows the blades to rotate as the axis and produces a valuable source of renewable energy by repetitive rotational motion. This research was focused on finding a suitable generator for Savonius Vertical Axis Wind Turbine (VAWT) that can produce a high voltage at low RPM. In this research, to replicate the real wind blow, two different fans are used: a. 71 cm diameter industrial fan with range of wind speed from 1 to 6 m/s; b. 31 cm fan with a range of wind speed from 1 to 4,5 m/s. From the result, it can be concluded that the direction of the wind affects the rotation of the rotor, so it must be ensured that the wind touches the tip of the blade to maximize the rotational speed. The maximum voltage output produced by VAWT is 4,8 V at 67 RPM on wind speed 6 m/s using the 1st Generator. For further development, the Vertical Axis Wind Turbine (VAWT) have to be remodelled so the ratio between rotor radius and rotor height is 1,2.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129584271","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 : 2021-11-24DOI: 10.1109/CITISIA53721.2021.9719896
Khalid Alalawi, R. Chiong, R. Athauda
Predicting student performance and identifying under-performing students early is the first step towards helping students who might have difficulties in meeting learning outcomes of a course resulting in a failing grade. Early detection in this context allows educators to provide appropriate interventions sooner for students facing challenges, which could lead to a higher possibility of success. Machine learning (ML) algorithms can be utilized to create an early warning system that detects students who need assistance and informs both educators and learners about their performance. In this paper, we explore the performance of different ML algorithms for identifying under-performing students in the early stages of an academic term/semester for a selected undergraduate course. First, we attempted to identify students who might fail their course, as a binary classification problem (pass or fail), with several experiments at different times during the semester. Next, we introduced an additional group of students who are at the borderline of failing, resulting in a multiclass classification problem. We were able to identify under-performing students early in the semester using only the first assessment in the course with an accuracy of 95%, and borderline students with an accuracy of 84%. In addition, we introduce a student performance prediction system that allows academics to create ML models and identify under-performing students early on during the academic term.
{"title":"Early Detection of Under-Performing Students Using Machine Learning Algorithms","authors":"Khalid Alalawi, R. Chiong, R. Athauda","doi":"10.1109/CITISIA53721.2021.9719896","DOIUrl":"https://doi.org/10.1109/CITISIA53721.2021.9719896","url":null,"abstract":"Predicting student performance and identifying under-performing students early is the first step towards helping students who might have difficulties in meeting learning outcomes of a course resulting in a failing grade. Early detection in this context allows educators to provide appropriate interventions sooner for students facing challenges, which could lead to a higher possibility of success. Machine learning (ML) algorithms can be utilized to create an early warning system that detects students who need assistance and informs both educators and learners about their performance. In this paper, we explore the performance of different ML algorithms for identifying under-performing students in the early stages of an academic term/semester for a selected undergraduate course. First, we attempted to identify students who might fail their course, as a binary classification problem (pass or fail), with several experiments at different times during the semester. Next, we introduced an additional group of students who are at the borderline of failing, resulting in a multiclass classification problem. We were able to identify under-performing students early in the semester using only the first assessment in the course with an accuracy of 95%, and borderline students with an accuracy of 84%. In addition, we introduce a student performance prediction system that allows academics to create ML models and identify under-performing students early on during the academic term.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129898360","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 : 2021-11-24DOI: 10.1109/citisia53721.2021.9719914
Abdul B. Maqsood, Angelica Maag, Indra Seher, Md Sayfullah
Natural language processing (NLP) is the a types of artificial intelligence approach used to maintain the decision making and data interaction process with high accuracy and reliability rate. It is also used to maintain the computer-human interaction for better understanding and result. The aim of this work is to review the data extraction techniques with NLP for a better business and user analysis process. For data analysis and user experience analysis process data analytic, K-neighbor techniques are used that are obtained using the method a lLiterature review. This process aims to review the current research articles that are focused on data extraction and analytic techniques. Besides, it is focused on NLP techniques for improving the analysis and extraction process. The Factorization, FCMA, and soft computing algorithms with NLP are reviewed that maintain precision and accuracy rate. Different tools, such as visualization, decision-making, consumer identification, and behavior analysis, are considered during the review process. In this review process, PRM and embedding matrix approaches are considered for an accurate analysis process. The data extraction, feature extraction, and machine learning model with data extraction techniques are reviewed to manage consumer experience and error estimation. This study introduces customer behavior data, Natural processing-based data extraction, e-commerce business effectiveness and evaluation as the major factors of this work.
{"title":"Customer data extraction techniques based on natural language processing for e-commerce business analytics","authors":"Abdul B. Maqsood, Angelica Maag, Indra Seher, Md Sayfullah","doi":"10.1109/citisia53721.2021.9719914","DOIUrl":"https://doi.org/10.1109/citisia53721.2021.9719914","url":null,"abstract":"Natural language processing (NLP) is the a types of artificial intelligence approach used to maintain the decision making and data interaction process with high accuracy and reliability rate. It is also used to maintain the computer-human interaction for better understanding and result. The aim of this work is to review the data extraction techniques with NLP for a better business and user analysis process. For data analysis and user experience analysis process data analytic, K-neighbor techniques are used that are obtained using the method a lLiterature review. This process aims to review the current research articles that are focused on data extraction and analytic techniques. Besides, it is focused on NLP techniques for improving the analysis and extraction process. The Factorization, FCMA, and soft computing algorithms with NLP are reviewed that maintain precision and accuracy rate. Different tools, such as visualization, decision-making, consumer identification, and behavior analysis, are considered during the review process. In this review process, PRM and embedding matrix approaches are considered for an accurate analysis process. The data extraction, feature extraction, and machine learning model with data extraction techniques are reviewed to manage consumer experience and error estimation. This study introduces customer behavior data, Natural processing-based data extraction, e-commerce business effectiveness and evaluation as the major factors of this work.","PeriodicalId":252063,"journal":{"name":"2021 6th International Conference on Innovative Technology in Intelligent System and Industrial Applications (CITISIA)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116200144","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}