Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817326
M. Mamun, Afia Farjana, Miraz Al Mamun, Md Salim Ahammed
Lung cancers are malignant lung tumors resulting from uncontrolled growth of lung cells that metastasizes to other parts of the body and can cause death. Although lung cancer cannot be prevented, the risk of cancer development can be lowered. Early detection of lung cancer is essential for patient survival, and machine learning-based prediction models have potential use in predicting lung cancer. Ensemble techniques are compelling and powerful techniques in Machine Learning to improve the prediction accuracy as classifiers. This paper reviewed some research articles on lung cancer prediction models that used machine learning and ensemble learning techniques. Furthermore, we added our newly developed ensemble learning techniques to this paper which was developed based on a survey dataset of 309 people with or without lung cancer by oversampling SMOTE method. The ensemble techniques we used are XGBoost, LightGBM, Bagging, and AdaBoost by k-fold 10 cross-validation method and the attributes our lung cancer prediction models used are age, smoking, yellow fingers, anxiety, peer pressure, chronic disease, fatigue, allergy, wheezing, alcohol, coughing, shortness of breath, swallowing difficulty, and chest pain. Results: According to our analysis, the XGBoost technique performed better than other ensemble techniques and achieved an accuracy of 94.42 %, precision of 95.66%, recall of 94.46%, and AUC of 98.14%, respectively.
{"title":"Lung cancer prediction model using ensemble learning techniques and a systematic review analysis","authors":"M. Mamun, Afia Farjana, Miraz Al Mamun, Md Salim Ahammed","doi":"10.1109/aiiot54504.2022.9817326","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817326","url":null,"abstract":"Lung cancers are malignant lung tumors resulting from uncontrolled growth of lung cells that metastasizes to other parts of the body and can cause death. Although lung cancer cannot be prevented, the risk of cancer development can be lowered. Early detection of lung cancer is essential for patient survival, and machine learning-based prediction models have potential use in predicting lung cancer. Ensemble techniques are compelling and powerful techniques in Machine Learning to improve the prediction accuracy as classifiers. This paper reviewed some research articles on lung cancer prediction models that used machine learning and ensemble learning techniques. Furthermore, we added our newly developed ensemble learning techniques to this paper which was developed based on a survey dataset of 309 people with or without lung cancer by oversampling SMOTE method. The ensemble techniques we used are XGBoost, LightGBM, Bagging, and AdaBoost by k-fold 10 cross-validation method and the attributes our lung cancer prediction models used are age, smoking, yellow fingers, anxiety, peer pressure, chronic disease, fatigue, allergy, wheezing, alcohol, coughing, shortness of breath, swallowing difficulty, and chest pain. Results: According to our analysis, the XGBoost technique performed better than other ensemble techniques and achieved an accuracy of 94.42 %, precision of 95.66%, recall of 94.46%, and AUC of 98.14%, respectively.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123127870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817207
Brandon Wood, Khaled Slhoub
Customers of e-commerce platforms often rely on other customers' reviews to make purchasing decisions. On these e-commerce platforms, such as Amazon, sellers will sometimes use fake reviews, often created by bots, to boost ratings on their products. This can negatively affect customer purchase satisfaction. This research employs unsupervised learning algorithms K-Means, DBSCAN, and OPTICS to discover clusters of potential bot reviewer feature values. These clusters will then be analyzed and used for training multiple classifier networks to attempt to be able to detect bot reviewers using machine learning. The results of this research article point towards a direction that this is a possible future path given additional research and domain expertise.
{"title":"Detecting Amazon Bot Reviewers Using Unsupervised and Supervised Learning","authors":"Brandon Wood, Khaled Slhoub","doi":"10.1109/aiiot54504.2022.9817207","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817207","url":null,"abstract":"Customers of e-commerce platforms often rely on other customers' reviews to make purchasing decisions. On these e-commerce platforms, such as Amazon, sellers will sometimes use fake reviews, often created by bots, to boost ratings on their products. This can negatively affect customer purchase satisfaction. This research employs unsupervised learning algorithms K-Means, DBSCAN, and OPTICS to discover clusters of potential bot reviewer feature values. These clusters will then be analyzed and used for training multiple classifier networks to attempt to be able to detect bot reviewers using machine learning. The results of this research article point towards a direction that this is a possible future path given additional research and domain expertise.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123632320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817202
Christopher Le, Alvaro Martin Grande, AJ Carmine, J. Thompson, Tauheed Khan Mohd
When designing Operating Systems, security is one of the most critical factors to consider. Given the popularity and high usage of Raspberry Pi, Raspbian OS vulnerabilities may cause users serious security issues. Frequently, software developers spend long periods of time testing and analyzing their systems. Throughout this paper, certain vulnerabilities of the Raspbian OS will be addressed and reviewed. The most prominent security issue is the default username and password combination set upon installation. Others include various software and hardware bugs, and shortcomings present in multiple different releases of the Raspbian OS such as Stretch or Wheezy. Additionally, secure shell keys are another prominent area of attacks against Raspbian OS, with connections becoming insecure and vulnerable to attackers and malware. Throughout this paper, potential fixes to these problems will be explored in greater depth.
{"title":"Analysis of Various Vulnerabilities in the Raspbian Operating System and Solutions","authors":"Christopher Le, Alvaro Martin Grande, AJ Carmine, J. Thompson, Tauheed Khan Mohd","doi":"10.1109/aiiot54504.2022.9817202","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817202","url":null,"abstract":"When designing Operating Systems, security is one of the most critical factors to consider. Given the popularity and high usage of Raspberry Pi, Raspbian OS vulnerabilities may cause users serious security issues. Frequently, software developers spend long periods of time testing and analyzing their systems. Throughout this paper, certain vulnerabilities of the Raspbian OS will be addressed and reviewed. The most prominent security issue is the default username and password combination set upon installation. Others include various software and hardware bugs, and shortcomings present in multiple different releases of the Raspbian OS such as Stretch or Wheezy. Additionally, secure shell keys are another prominent area of attacks against Raspbian OS, with connections becoming insecure and vulnerable to attackers and malware. Throughout this paper, potential fixes to these problems will be explored in greater depth.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129568905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817213
Chukwuemeka Duru, J. Ladeji-Osias, K. Wandji, Otily Toutsop, Rachida Kone
Security and trust of Information Systems are critical in its design as they directly influence users' view and acceptance of such systems. Security can be said to be a contextual and dynamic term as there has not been a holistic, universal, and eternal security measure to date. Recent years have seen a lot of confidential and sensitive information being sent, received, and analyzed on the Internet, and a plethora of investigations on ways of developing comprehensive security solutions like encryptions, pattern recognition, and anomaly detection. This work reviews the human inspired algorithms that are particularly employed in pattern recognition and anomaly detection problems. The work discusses the components of the immune system that inspired the artificial Immune System (AIS) based algorithms for pattern and intrusion detection (IDS) problems. A detailed comparison is made between negative selection, clonal selection, and dendritic cell algorithms (danger theory) which are the three major AIS algorithms. AIS is ubiquitous in computer and information security because it is based on the theories developed through years of study and understanding of the human immune system by immunologist. The strengths and weaknesses of these algorithms are also discussed, and possible improvement suggested.
{"title":"A Review of Human Immune Inspired Algorithms for Intrusion Detection Systems","authors":"Chukwuemeka Duru, J. Ladeji-Osias, K. Wandji, Otily Toutsop, Rachida Kone","doi":"10.1109/aiiot54504.2022.9817213","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817213","url":null,"abstract":"Security and trust of Information Systems are critical in its design as they directly influence users' view and acceptance of such systems. Security can be said to be a contextual and dynamic term as there has not been a holistic, universal, and eternal security measure to date. Recent years have seen a lot of confidential and sensitive information being sent, received, and analyzed on the Internet, and a plethora of investigations on ways of developing comprehensive security solutions like encryptions, pattern recognition, and anomaly detection. This work reviews the human inspired algorithms that are particularly employed in pattern recognition and anomaly detection problems. The work discusses the components of the immune system that inspired the artificial Immune System (AIS) based algorithms for pattern and intrusion detection (IDS) problems. A detailed comparison is made between negative selection, clonal selection, and dendritic cell algorithms (danger theory) which are the three major AIS algorithms. AIS is ubiquitous in computer and information security because it is based on the theories developed through years of study and understanding of the human immune system by immunologist. The strengths and weaknesses of these algorithms are also discussed, and possible improvement suggested.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130141739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817186
Patrick Kopacz, M. Chowdhury
Cloud computing has grown tremendously over the past few years. It creates new ways for information to be stored and processed which bring the growing problem of security. The question at hand is what makes the cloud safe and secure as well as the challenges involved in the process. As modern technology emerges so do the new challenges and issues that come along with this progression. For now, the cloud is highly reliable, provides incredible scalability, and an easy-to-use system. This paper will discuss what cloud computing is, how information is stored, the security behind the scenes, any improvements that can be made, and what the cloud's future looks like.
{"title":"Cloud Computing Security and Future","authors":"Patrick Kopacz, M. Chowdhury","doi":"10.1109/aiiot54504.2022.9817186","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817186","url":null,"abstract":"Cloud computing has grown tremendously over the past few years. It creates new ways for information to be stored and processed which bring the growing problem of security. The question at hand is what makes the cloud safe and secure as well as the challenges involved in the process. As modern technology emerges so do the new challenges and issues that come along with this progression. For now, the cloud is highly reliable, provides incredible scalability, and an easy-to-use system. This paper will discuss what cloud computing is, how information is stored, the security behind the scenes, any improvements that can be made, and what the cloud's future looks like.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125498406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817195
Nandang Sunandar, A. Hidayanto
Data quality is closely related to the quality of information. Low data quality leads to inaccurate information and leads to a decrease in business performance. PT BPI as a company that serves the management of local government financial data needs to control and maintain data quality to remain good. The quality of the data produced is very important to note. This needs to be done to maintain the credibility and capability of PT BPI. This scientific writing aims to provide recommendations for improving data quality management. This scientific writing uses qualitative methods with document studies and several interview sessions. The models used in this scientific writing are Data Quality Management Maturity from Loshin and Data Management Body of Knowledge (DMBOK). The results of measuring the maturity level of data quality management at PT BPI using the D'Lhosin model shows that the organization is still at level one. This indicates that PT BPI does not yet have adequate and thorough basic knowledge about data quality management. PT BPI cannot meet the eight measurement characteristics at level two. Based on the resulting maturity measurement to reach level two, the writer made recommendations from eight unmet characteristics based on DMBOK.
{"title":"Data Quality Management Improvement: Case Studi PT BPI","authors":"Nandang Sunandar, A. Hidayanto","doi":"10.1109/aiiot54504.2022.9817195","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817195","url":null,"abstract":"Data quality is closely related to the quality of information. Low data quality leads to inaccurate information and leads to a decrease in business performance. PT BPI as a company that serves the management of local government financial data needs to control and maintain data quality to remain good. The quality of the data produced is very important to note. This needs to be done to maintain the credibility and capability of PT BPI. This scientific writing aims to provide recommendations for improving data quality management. This scientific writing uses qualitative methods with document studies and several interview sessions. The models used in this scientific writing are Data Quality Management Maturity from Loshin and Data Management Body of Knowledge (DMBOK). The results of measuring the maturity level of data quality management at PT BPI using the D'Lhosin model shows that the organization is still at level one. This indicates that PT BPI does not yet have adequate and thorough basic knowledge about data quality management. PT BPI cannot meet the eight measurement characteristics at level two. Based on the resulting maturity measurement to reach level two, the writer made recommendations from eight unmet characteristics based on DMBOK.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125501732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817254
Outi-Marja Latvala, Ivo Emanuilov, Tatu Niskanen, Pia Raitio, J. Salonen, Diogo Santos, K. Yordanova
Trust is a key ingredient in collaboration between security operations centers (SOCs). The collaboration can enhance defense and preparedness against cyberattacks, but it is also important to limit the attacker's ability to infer their potential for success from the communication between SOCs. This paper presents a proof-of-concept for a granular information sharing scheme. The information about a security incident is encrypted and the SOCs can decide with great precision which users or user groups can access it. The information is presented in a web-based dasboard visualization, and a user can communicate with other SOCs in order to access relevant incident information.
{"title":"Proof-of-Concept for a Granular Incident Management Information Sharing Scheme","authors":"Outi-Marja Latvala, Ivo Emanuilov, Tatu Niskanen, Pia Raitio, J. Salonen, Diogo Santos, K. Yordanova","doi":"10.1109/aiiot54504.2022.9817254","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817254","url":null,"abstract":"Trust is a key ingredient in collaboration between security operations centers (SOCs). The collaboration can enhance defense and preparedness against cyberattacks, but it is also important to limit the attacker's ability to infer their potential for success from the communication between SOCs. This paper presents a proof-of-concept for a granular information sharing scheme. The information about a security incident is encrypted and the SOCs can decide with great precision which users or user groups can access it. The information is presented in a web-based dasboard visualization, and a user can communicate with other SOCs in order to access relevant incident information.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128548651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817155
Calum McCormack, Christopher Wallace, P. Barrie, G. Morison
We describe the investigation and testing of univariate forecasting techniques on IoT hardware for application at “the Edge” using power demand forecasting. An evaluation of common forecasting techniques is presented, tested using the Morocco Buildings Electricity Consumption Datasets. An architecture is described for the Edge system that would enable 1-day forward forecasts of power demand for use in provisioning power in a hybrid power system. Several of the configurations examined in this study performed comparably with current trends in forecasting methods and are suitable for this application at the Edge, providing a balance of performance and accuracy. A Long Short-Term Memory (LSTM) Neural Network configuration provided the most effective balance of performance, accuracy and simplicity of deployment that is desirable for an application at the Edge.
{"title":"Day ahead Power Demand Forecasting for Hybrid Power at the Edge","authors":"Calum McCormack, Christopher Wallace, P. Barrie, G. Morison","doi":"10.1109/aiiot54504.2022.9817155","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817155","url":null,"abstract":"We describe the investigation and testing of univariate forecasting techniques on IoT hardware for application at “the Edge” using power demand forecasting. An evaluation of common forecasting techniques is presented, tested using the Morocco Buildings Electricity Consumption Datasets. An architecture is described for the Edge system that would enable 1-day forward forecasts of power demand for use in provisioning power in a hybrid power system. Several of the configurations examined in this study performed comparably with current trends in forecasting methods and are suitable for this application at the Edge, providing a balance of performance and accuracy. A Long Short-Term Memory (LSTM) Neural Network configuration provided the most effective balance of performance, accuracy and simplicity of deployment that is desirable for an application at the Edge.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"31 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129938695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817278
K. Adhikari
This paper frames the estimation of directions of arrival of plane waves impinging on an array of sensors as a classification problem using convolutional neural networks (CNNs). We propose a methodology to impose the shift-invariant structure inherent in data to CNNs. We use several methods to pre-process the data collected from sensor arrays and feed the pre-processed data as inputs to CNNs. For all CNNs, data sets corresponding to different signal-to-noise ratio (SNR) levels are generated. The data sets associated with the lowest SNR level are used for training while the other data sets are used for validation. Comparison of the accuracy of the shift-invariant structure-imposed CNNs with those of CNNs that are based on raw data, sample covariance matrices, and principal eigenvectors is provided. The simulations show that shift-invariant structure can be efficiently and most accurately imposed using the optimal signal subspace basis estimates as CNN inputs.
{"title":"Shift-Invariant Structure-Imposed Convolutional Neural Networks for Direction of Arrival Estimation","authors":"K. Adhikari","doi":"10.1109/aiiot54504.2022.9817278","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817278","url":null,"abstract":"This paper frames the estimation of directions of arrival of plane waves impinging on an array of sensors as a classification problem using convolutional neural networks (CNNs). We propose a methodology to impose the shift-invariant structure inherent in data to CNNs. We use several methods to pre-process the data collected from sensor arrays and feed the pre-processed data as inputs to CNNs. For all CNNs, data sets corresponding to different signal-to-noise ratio (SNR) levels are generated. The data sets associated with the lowest SNR level are used for training while the other data sets are used for validation. Comparison of the accuracy of the shift-invariant structure-imposed CNNs with those of CNNs that are based on raw data, sample covariance matrices, and principal eigenvectors is provided. The simulations show that shift-invariant structure can be efficiently and most accurately imposed using the optimal signal subspace basis estimates as CNN inputs.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130290630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817193
Junifar Adam Pamungkas, Y. Priyadi, M. J. Alibasa
There are differences in perceptions between Clients and Developers regarding software requirements specifications therefore, research is needed to determine the perceived similarity between software requirements specifications and requirements elicitation results. The SRS document used in this study is called the Cinemaloka application. This document contains business processes and Requirements Specifications related to website-based cinema ticket reservations. This study aims to measure the suitability of perceptions between developers and clients regarding the specification of software requirements that will be or are being built. There are methods that are combined in this research, namely: determining the similarity of the requirement specification with the elicitation of requirements, analyzing the text contained in the elicitation results, Text Pre-processing, and validation through Gwet's AC1. The results of the measurement of the similarity between the elicitation of requirements and the requirement specification carried out in this study resulted in a match between the applications made and the wishes of potential users/clients. Through stages such as CountVectorizer, PorterStemmer, and Cosine Similarity, resulting in a match of 0.717144. Kappa Score from Gwet's AC1 formula using Python is -0.2222, which means “Less than Chance-agreement,” while the Kappa Score value using a questionnaire filled out by the Expert is 0.5378, which means “Moderate Aggregation.”.
{"title":"Measurement of Similarity Between Requirement Elicitation and Requirement Specification Using Text Pre-Processing in the Cinemaloka Application","authors":"Junifar Adam Pamungkas, Y. Priyadi, M. J. Alibasa","doi":"10.1109/aiiot54504.2022.9817193","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817193","url":null,"abstract":"There are differences in perceptions between Clients and Developers regarding software requirements specifications therefore, research is needed to determine the perceived similarity between software requirements specifications and requirements elicitation results. The SRS document used in this study is called the Cinemaloka application. This document contains business processes and Requirements Specifications related to website-based cinema ticket reservations. This study aims to measure the suitability of perceptions between developers and clients regarding the specification of software requirements that will be or are being built. There are methods that are combined in this research, namely: determining the similarity of the requirement specification with the elicitation of requirements, analyzing the text contained in the elicitation results, Text Pre-processing, and validation through Gwet's AC1. The results of the measurement of the similarity between the elicitation of requirements and the requirement specification carried out in this study resulted in a match between the applications made and the wishes of potential users/clients. Through stages such as CountVectorizer, PorterStemmer, and Cosine Similarity, resulting in a match of 0.717144. Kappa Score from Gwet's AC1 formula using Python is -0.2222, which means “Less than Chance-agreement,” while the Kappa Score value using a questionnaire filled out by the Expert is 0.5378, which means “Moderate Aggregation.”.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120956812","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：