Pub Date : 2023-12-07DOI: 10.30534/ijatcse/2023/021262023
The rapid progress and evolution of the Internet of Things (IoT) have led to a significant increase in the occurrence of security gaps. Pinpointing the source of network traffic coming from IoT devices can be challenging, but doing so can reduce security risks. This study proposes a network traffic source identification mechanism that leverages machine learning (ML) techniques to accurately determine the source of network traffic. The study utilizes a diverse dataset obtained from a purpose-built IoT/IIoT testbed and employs feature extraction, model development, and evaluation techniques. By utilizing network traffic features, a range of classifiers, including LGBMClassifier (LGBM), CatBoostClassifier (CB), RandomForestClassifier (RF), ExtraTreesClassifier (ET), KneighborsClassifier (KNN), and DecisionTreeClassifier (DT), were trained and evaluated. The results demonstrate exceptional performance across the classifiers, with high accuracy, precision, recall, and F1 scores achieved in identifying the source of network traffic. Among the classifier models, LGBM achieved the best accuracy value of 0.99999857, precision value of 0.99999859, and F1 score of 0.999998803, with CB achieving the best recall of 0.999997875. Some of these results are novel, and others performed better than existing systems. The findings of this study contribute to source identification, ensure the accountability of IoT network users, and provide insights into developing better defenses against security threats in the IoT domain
{"title":"Network Source Identification Mechanism for IoT Devices Using Machine Learning Techniques","authors":"","doi":"10.30534/ijatcse/2023/021262023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/021262023","url":null,"abstract":"The rapid progress and evolution of the Internet of Things (IoT) have led to a significant increase in the occurrence of security gaps. Pinpointing the source of network traffic coming from IoT devices can be challenging, but doing so can reduce security risks. This study proposes a network traffic source identification mechanism that leverages machine learning (ML) techniques to accurately determine the source of network traffic. The study utilizes a diverse dataset obtained from a purpose-built IoT/IIoT testbed and employs feature extraction, model development, and evaluation techniques. By utilizing network traffic features, a range of classifiers, including LGBMClassifier (LGBM), CatBoostClassifier (CB), RandomForestClassifier (RF), ExtraTreesClassifier (ET), KneighborsClassifier (KNN), and DecisionTreeClassifier (DT), were trained and evaluated. The results demonstrate exceptional performance across the classifiers, with high accuracy, precision, recall, and F1 scores achieved in identifying the source of network traffic. Among the classifier models, LGBM achieved the best accuracy value of 0.99999857, precision value of 0.99999859, and F1 score of 0.999998803, with CB achieving the best recall of 0.999997875. Some of these results are novel, and others performed better than existing systems. The findings of this study contribute to source identification, ensure the accountability of IoT network users, and provide insights into developing better defenses against security threats in the IoT domain","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"54 50","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138593206","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 : 2023-12-07DOI: 10.30534/ijatcse/2023/031262023
The Internet of Things (IoT) refers to a network of interconnected smart devices. The growth of IoT devices has increased the vulnerability of the network to attacks, such as Denial of Service (DoS) and Distributed Denial of Service (DDoS). Denial-of-Service (DoS) attacks are malicious activities aimed at rendering a computer network, system, or online service unavailable to legitimate users. This research addresses the growing vulnerability of IoT networks to DoS/DDoS attacks by developing a hybrid intrusion detection model to detect these attacks. The model integrates Kalman Filter (KF) with Artificial Neural Network (KF-ANN), Random Forest (KF-RF), Support Vector Machine (KF-SVM) and K-Nearest Neighbor (KF-KNN) machine learning models. The Kalman filter is an efficient tool for estimating the state of a system especially in the midst of uncertainty. Kalman filter was used to estimate the state of the system while the machine learning models were used to make predictions based on the estimated state to detect attacks in IoT. The model was tested using the DoS/DDoS Message Queueing Telemetry Protocol (MQTT) IoT dataset. Results shows Receiver Operative Curve Area Under the Curve (ROC-AUC) of 0.99% for KF-ANN and KF-RF, 0.98% and 0.97% for KF-KNN and KF-SVM. Detection accuracy of approximately 0.96%, 0.94% and 93% for KF-RF and KF-ANN, KF-KNN and KF-SVM respectively
{"title":"A Hybrid Intrusion Detection Model to Alleviate Denial of Service and Distributed Denial of Service Attacks in Internet of Things","authors":"","doi":"10.30534/ijatcse/2023/031262023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/031262023","url":null,"abstract":"The Internet of Things (IoT) refers to a network of interconnected smart devices. The growth of IoT devices has increased the vulnerability of the network to attacks, such as Denial of Service (DoS) and Distributed Denial of Service (DDoS). Denial-of-Service (DoS) attacks are malicious activities aimed at rendering a computer network, system, or online service unavailable to legitimate users. This research addresses the growing vulnerability of IoT networks to DoS/DDoS attacks by developing a hybrid intrusion detection model to detect these attacks. The model integrates Kalman Filter (KF) with Artificial Neural Network (KF-ANN), Random Forest (KF-RF), Support Vector Machine (KF-SVM) and K-Nearest Neighbor (KF-KNN) machine learning models. The Kalman filter is an efficient tool for estimating the state of a system especially in the midst of uncertainty. Kalman filter was used to estimate the state of the system while the machine learning models were used to make predictions based on the estimated state to detect attacks in IoT. The model was tested using the DoS/DDoS Message Queueing Telemetry Protocol (MQTT) IoT dataset. Results shows Receiver Operative Curve Area Under the Curve (ROC-AUC) of 0.99% for KF-ANN and KF-RF, 0.98% and 0.97% for KF-KNN and KF-SVM. Detection accuracy of approximately 0.96%, 0.94% and 93% for KF-RF and KF-ANN, KF-KNN and KF-SVM respectively","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"31 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138594410","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 : 2023-12-07DOI: 10.30534/ijatcse/2023/011262023
The growing concern over plastic pollution and its adverse impact on the environment has prompted the development of innovative solutions to address the issue effectively. Improper disposal of plastic bottles leads to environmental pollution. This paper presents the design and implementation of a prototype of smart plastic bottle recycle machine, integrating the Internet of Things (IoT). The Arduino board is used to control the machine. The smart plastic bottle recycling machine incorporates the ESP8266 and a Wi-Fi enabled system-on-chip (SoC) module used to develop IoT embedded applications. The utilization of IoT technology enables seamless real-time data transmission, allowing for efficient communication with the central system and simpliying remote monitoring and management processes. The IoT-enabled sensors and cameras capture information about the plastic bottles, such as their material, size, and condition. Thus, it makes recycling easy and satisfying, which motivates people to get involved in recycling activities. Moreover, implementing a point system that rewards individuals for their recycling efforts not only serves as an extra motivation for users, but also encourages them to actively participate in the preservation of the environment. Therefore, this prototype demonstrates the potential to foster sustainable recycling practices, which is a promising first step towards a future that prioritizes environmental consciousness
{"title":"A Prototype of Smart Plastic Bottle Recycle Machine Using IoT","authors":"","doi":"10.30534/ijatcse/2023/011262023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/011262023","url":null,"abstract":"The growing concern over plastic pollution and its adverse impact on the environment has prompted the development of innovative solutions to address the issue effectively. Improper disposal of plastic bottles leads to environmental pollution. This paper presents the design and implementation of a prototype of smart plastic bottle recycle machine, integrating the Internet of Things (IoT). The Arduino board is used to control the machine. The smart plastic bottle recycling machine incorporates the ESP8266 and a Wi-Fi enabled system-on-chip (SoC) module used to develop IoT embedded applications. The utilization of IoT technology enables seamless real-time data transmission, allowing for efficient communication with the central system and simpliying remote monitoring and management processes. The IoT-enabled sensors and cameras capture information about the plastic bottles, such as their material, size, and condition. Thus, it makes recycling easy and satisfying, which motivates people to get involved in recycling activities. Moreover, implementing a point system that rewards individuals for their recycling efforts not only serves as an extra motivation for users, but also encourages them to actively participate in the preservation of the environment. Therefore, this prototype demonstrates the potential to foster sustainable recycling practices, which is a promising first step towards a future that prioritizes environmental consciousness","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"5 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138591295","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 : 2023-10-15DOI: 10.30534/ijatcse/2023/061252023
Every project has its own risks associated with it. The more complex the project, the higher risks embedded within the project. Whenever the risk is not identified and mitigated properly, it will disrupt the project implementation. The article takes case study of a state-owned energy company, XYZ, that build electricity transmission system around Indonesia area. The transmission project requires various expertise that involves using multiple contractors with their subcontractors. Using the chain of contractors/subcontractors is a common thing in transmission project, so the project owner should ensure all risks within the chain should be properly managed. The article proposes the use of ISO 31000 risk assessment method to identify and mitigate all possible risks that may disrupt the project. The use of ISO 31000 method enables to lower the risk of project achievements from 79.74% success rates to more than 90%. The outcome of the article is expected to be used as a reference for project owner of transmission projects in Indonesia to manage the risks associated with the use of chain contractors and subcontractors.
{"title":"Optimizing Subcontractor Work through ISO 31000 Risk Assessment Method","authors":"","doi":"10.30534/ijatcse/2023/061252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/061252023","url":null,"abstract":"Every project has its own risks associated with it. The more complex the project, the higher risks embedded within the project. Whenever the risk is not identified and mitigated properly, it will disrupt the project implementation. The article takes case study of a state-owned energy company, XYZ, that build electricity transmission system around Indonesia area. The transmission project requires various expertise that involves using multiple contractors with their subcontractors. Using the chain of contractors/subcontractors is a common thing in transmission project, so the project owner should ensure all risks within the chain should be properly managed. The article proposes the use of ISO 31000 risk assessment method to identify and mitigate all possible risks that may disrupt the project. The use of ISO 31000 method enables to lower the risk of project achievements from 79.74% success rates to more than 90%. The outcome of the article is expected to be used as a reference for project owner of transmission projects in Indonesia to manage the risks associated with the use of chain contractors and subcontractors.","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"56 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135766044","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 : 2023-10-08DOI: 10.30534/ijatcse/2023/041252023
This study presents a machine learning-based approach to enhance the classification and optimization of students’ academic performance within Nigeria’s polytechnic education system. The polytechnic system is pivotal in providing technical and vocational education, but challenges persist in nurturing students’ academic achievement. This article explores the complexities influencing academic performance and proposes strategies for improvement using machine learning algorithms. The research utilizes linear and support vector regression models to predict students’ cumulative grade point averages (CGPA). A dataset from Akwa Ibom State Polytechnic, Ikot Osurua, comprising total courses, credit units, department, and previous grade point average (GPA), is employed for model development and evaluation. Both models achieve similar predictive performance, but linear regression slightly outperforms support vector regression. The results highlight the significant role of variables like total courses, the type of academic department, and previous GPA in predicting CGPA. This study offers a valuable tool for assessing and improving students’ academic performance in Nigeria’s polytechnic education system, with potential for broader applications in higher education. Further research involves expanding the dataset and considering additional factors beyond result records to enhance the model’s robustness and applicability.
{"title":"Predictive Modeling for Enhancing Academic Performance in Nigerian Polytechnic Education","authors":"","doi":"10.30534/ijatcse/2023/041252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/041252023","url":null,"abstract":"This study presents a machine learning-based approach to enhance the classification and optimization of students’ academic performance within Nigeria’s polytechnic education system. The polytechnic system is pivotal in providing technical and vocational education, but challenges persist in nurturing students’ academic achievement. This article explores the complexities influencing academic performance and proposes strategies for improvement using machine learning algorithms. The research utilizes linear and support vector regression models to predict students’ cumulative grade point averages (CGPA). A dataset from Akwa Ibom State Polytechnic, Ikot Osurua, comprising total courses, credit units, department, and previous grade point average (GPA), is employed for model development and evaluation. Both models achieve similar predictive performance, but linear regression slightly outperforms support vector regression. The results highlight the significant role of variables like total courses, the type of academic department, and previous GPA in predicting CGPA. This study offers a valuable tool for assessing and improving students’ academic performance in Nigeria’s polytechnic education system, with potential for broader applications in higher education. Further research involves expanding the dataset and considering additional factors beyond result records to enhance the model’s robustness and applicability.","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135198253","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 : 2023-10-08DOI: 10.30534/ijatcse/2023/051252023
The process through which a computer can identify spoken words is termed as speech recognition. After analysis and finding of features of the speech sound, one can go towards the recognition of the speech. The extraction of feature vector is known as the feature extraction process or the front-end process. This front-end process is considered as the 1st stage of speech recognition. Pattern matching process is the 2nd stage or final stage of speech recognition where actual search is carried out to decode the spoken utterances by matching the sequence of feature vectors against the acoustic and language models stored in the recognizer. To reduce this problem, clustering technique is used. Clustering makes it possible to look at properties of whole clusters instead of individual objects - a simplification that might be useful when handling large volume of data. Clustering is nothing but the assignment of a set of observations into subsets so that the observations in the same cluster are similar in some sense.
{"title":"Clustering of Feature Vectors and Recognition of Bodo Phoneme Using MLP Technique","authors":"","doi":"10.30534/ijatcse/2023/051252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/051252023","url":null,"abstract":"The process through which a computer can identify spoken words is termed as speech recognition. After analysis and finding of features of the speech sound, one can go towards the recognition of the speech. The extraction of feature vector is known as the feature extraction process or the front-end process. This front-end process is considered as the 1st stage of speech recognition. Pattern matching process is the 2nd stage or final stage of speech recognition where actual search is carried out to decode the spoken utterances by matching the sequence of feature vectors against the acoustic and language models stored in the recognizer. To reduce this problem, clustering technique is used. Clustering makes it possible to look at properties of whole clusters instead of individual objects - a simplification that might be useful when handling large volume of data. Clustering is nothing but the assignment of a set of observations into subsets so that the observations in the same cluster are similar in some sense.","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135197843","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 : 2023-10-08DOI: 10.30534/ijatcse/2023/021252023
It is essential for universities to accredit their programs to be recognized locally and globally and to maintain the quality and credibility of educational programs. For programs to become accredited, they must meet predefined quality standards for the intended accreditation institution. These quality standards are applied to program courses, and each course covers some requirements from the accreditation requirements, such as Student and Course Learning Outcomes, based on their specific accreditation commission. As programs and courses are added frequently at university programs, information about accreditation mapped to each course syllabus and program description is becoming more complicated. It must be maintained automatically since program accreditation must be renewed on a regular basis to guarantee the program's quality. In addition, supporting Curriculum Designers in finding gaps and imbalances in the proposed programs and courses is becoming necessary to alleviate the management of accreditation related tasks. In this paper, we propose a knowledge graph-based system that supports the development of balanced educational programs and helps detecting gaps and redundancies within the same university programs. The system provides an attractive graphical user interface that visualizes the curriculum components and accreditation requirements as interactive graphs. The system has been implemented using the graph database Neo4j and the results are analyzed using the Cypher query language
{"title":"Supporting Curriculum Designers in Developing Balanced Outcome-based Programs using Knowledge Graphs","authors":"","doi":"10.30534/ijatcse/2023/021252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/021252023","url":null,"abstract":"It is essential for universities to accredit their programs to be recognized locally and globally and to maintain the quality and credibility of educational programs. For programs to become accredited, they must meet predefined quality standards for the intended accreditation institution. These quality standards are applied to program courses, and each course covers some requirements from the accreditation requirements, such as Student and Course Learning Outcomes, based on their specific accreditation commission. As programs and courses are added frequently at university programs, information about accreditation mapped to each course syllabus and program description is becoming more complicated. It must be maintained automatically since program accreditation must be renewed on a regular basis to guarantee the program's quality. In addition, supporting Curriculum Designers in finding gaps and imbalances in the proposed programs and courses is becoming necessary to alleviate the management of accreditation related tasks. In this paper, we propose a knowledge graph-based system that supports the development of balanced educational programs and helps detecting gaps and redundancies within the same university programs. The system provides an attractive graphical user interface that visualizes the curriculum components and accreditation requirements as interactive graphs. The system has been implemented using the graph database Neo4j and the results are analyzed using the Cypher query language","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135198094","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 : 2023-10-08DOI: 10.30534/ijatcse/2023/011252023
Recently, deep learning has gotten progressively popular in the domain of security. However, Traditional machine learning models are not capable to discover zero-day botnet attacks with extraordinary privacy. For this purpose, researchers have utilized deep learning based computational framework for Botnet which can detect zero-day attacks, achieve data privacy and improve training time using machine learning techniques for the IoT-edge devices. However, it combines and integrates various models and contexts. As a result, the objective of this research was to incorporate the deep learning model which controls different operation of IoT devices and reduce the training time. In deep learning, there are numerous components that aspect the false positive rate of every detected attack type. These elements are F1 score, false-positive rate, and training time; reduce the time of detection, and Accuracy. Bashlite and Mirai are two examples of zero-day botnet attacks that pose a threat to IoT edge devices. The majority of cyber-attacks are executed by malware-infected devices that are remotely controlled by attackers. This malware is often referred to as a bot or botnet, and it enables attackers to control the device and perform malicious actions, such as spamming, stealing sensitive information, and launching DDoS attacks. The model was formulated in Python libraries and subsequently tested on real life data to assess whether the integrated model performs better than its counterparts. The outcomes show that the proposed model performs in a way that is better than existing models i.e. DDL, CDL and LDL as Botnet Attacks Intelligence (BAI) the purposed deep learning model.
{"title":"Botnet Threat Intelligence in IoT-Edge","authors":"","doi":"10.30534/ijatcse/2023/011252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/011252023","url":null,"abstract":"Recently, deep learning has gotten progressively popular in the domain of security. However, Traditional machine learning models are not capable to discover zero-day botnet attacks with extraordinary privacy. For this purpose, researchers have utilized deep learning based computational framework for Botnet which can detect zero-day attacks, achieve data privacy and improve training time using machine learning techniques for the IoT-edge devices. However, it combines and integrates various models and contexts. As a result, the objective of this research was to incorporate the deep learning model which controls different operation of IoT devices and reduce the training time. In deep learning, there are numerous components that aspect the false positive rate of every detected attack type. These elements are F1 score, false-positive rate, and training time; reduce the time of detection, and Accuracy. Bashlite and Mirai are two examples of zero-day botnet attacks that pose a threat to IoT edge devices. The majority of cyber-attacks are executed by malware-infected devices that are remotely controlled by attackers. This malware is often referred to as a bot or botnet, and it enables attackers to control the device and perform malicious actions, such as spamming, stealing sensitive information, and launching DDoS attacks. The model was formulated in Python libraries and subsequently tested on real life data to assess whether the integrated model performs better than its counterparts. The outcomes show that the proposed model performs in a way that is better than existing models i.e. DDL, CDL and LDL as Botnet Attacks Intelligence (BAI) the purposed deep learning model.","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135198255","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 : 2023-10-08DOI: 10.30534/ijatcse/2023/031252023
Climate change is one of the important issues that face the world in this technological era. We have used data collected from the publicly available GISTEMP data, the Global Surface Temperature Change data distributed by the National Aeronautics and Space Administration Goddard Institute for Space Studies (NASA-GISS). The data consisted of the mean surface temperature change with respect to baseline climatology corresponding to the period 1951-1980. The data covers the time period of 1961-2019. We studied the change in temperature in the countries like Greenland and India using the regression models. All the regression graphs were plotted in the Spyder software using python. From the regression models we observed the significant rise in temperature in these countries caused due to global warming. These models will help us to predict the change in temperature in future
{"title":"The Magic of Environmental Detection and Future Prediction by Satellite","authors":"","doi":"10.30534/ijatcse/2023/031252023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/031252023","url":null,"abstract":"Climate change is one of the important issues that face the world in this technological era. We have used data collected from the publicly available GISTEMP data, the Global Surface Temperature Change data distributed by the National Aeronautics and Space Administration Goddard Institute for Space Studies (NASA-GISS). The data consisted of the mean surface temperature change with respect to baseline climatology corresponding to the period 1951-1980. The data covers the time period of 1961-2019. We studied the change in temperature in the countries like Greenland and India using the regression models. All the regression graphs were plotted in the Spyder software using python. From the regression models we observed the significant rise in temperature in these countries caused due to global warming. These models will help us to predict the change in temperature in future","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135197839","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 : 2023-08-10DOI: 10.30534/ijatcse/2023/081242023
Federated Learning (FL), a new private and secure Machine Learning (ML) approach, faces a big difficulty when it comes to sharing profits with data producers. Shapley Values (SV) have been proposed as a fair incentive system to remedy this, but it is challenging to determine the SV with accuracy. Therefore, SV calculation is problematic since the number of necessary federated models rises exponentially with the number of data sources. As a result, an effective approximation approach is required. The One Round Model Reconstruction (OR) and Truncated Monte Carlo Shapley (TMC) approaches for SV approximation in FL are being improved and combined in this study. The proposed approach, Adjusted OR-TMC, combines TMC principles with OR and achieves a comparable level of accuracy over a shorter period. Because of this, Adjusted OR-TMC is the perfect OR replacement. The performance outcomes and underlying causes are covered in the study.
联邦学习(FL)是一种新的私有和安全的机器学习(ML)方法，在与数据生产者分享利润时面临着很大的困难。沙普利值(Shapley Values, SV)被提议作为一种公平的激励机制来弥补这一缺陷，但要准确地确定SV是一项挑战。因此，SV计算是有问题的，因为必要的联邦模型的数量随着数据源的数量呈指数增长。因此，需要一种有效的近似方法。本研究对单轮模型重构(One Round Model Reconstruction, OR)和截断蒙特卡罗沙普利(Truncated Monte Carlo Shapley, TMC)方法进行了改进和结合。所提出的方法，调整OR-TMC，将TMC原则与OR相结合，并在较短的时间内达到相当的准确性水平。正因为如此，调整后的OR- tmc是完美的OR替代品。该研究涵盖了绩效结果和潜在原因。
{"title":"Fair Rewards in Federated Learning: A Novel Approach with Adjusted OR-TMC Shapley Value Approximation Algorithm","authors":"","doi":"10.30534/ijatcse/2023/081242023","DOIUrl":"https://doi.org/10.30534/ijatcse/2023/081242023","url":null,"abstract":"Federated Learning (FL), a new private and secure Machine Learning (ML) approach, faces a big difficulty when it comes to sharing profits with data producers. Shapley Values (SV) have been proposed as a fair incentive system to remedy this, but it is challenging to determine the SV with accuracy. Therefore, SV calculation is problematic since the number of necessary federated models rises exponentially with the number of data sources. As a result, an effective approximation approach is required. The One Round Model Reconstruction (OR) and Truncated Monte Carlo Shapley (TMC) approaches for SV approximation in FL are being improved and combined in this study. The proposed approach, Adjusted OR-TMC, combines TMC principles with OR and achieves a comparable level of accuracy over a shorter period. Because of this, Adjusted OR-TMC is the perfect OR replacement. The performance outcomes and underlying causes are covered in the study.","PeriodicalId":129636,"journal":{"name":"International Journal of Advanced Trends in Computer Science and Engineering","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856794","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：