Pub Date : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10032038
C. C. You, Joi San Tan, Seng Poh Lim, Seng Chee Lim, Chen Kang Lee
Surface reconstruction becomes a difficult task in reverse engineering when the data obtained during the data acquisition process is unstructured. The unstructured data do not contain the connectivity information required to represent the surface correctly with the least error. Hence, it should be organised to obtain the connectivity information. Various types of Self-Organising Map (SOM) models are utilised in the previous works to organise the unstructured data and represent the surface. However, the performance of the SOM models is affected when different topologies are involved in the organising process. Therefore, the purposes of this experiment are to evaluate the performance of the SOM models with different topologies and to determine the limitation of the various SOM models. The SOM models involved are 2-D SOM, 3-D SOM, Cube Kohonen (CK) SOM, and Spherical SOM (SSOM). Three 3-D unstructured closed surface data sets are applied in this experiment to evaluate the models. The experimental results show that the CKSOM and SSOM models can represent the closed surface correctly with a medium speed. Overall, the CKSOM model performs better than the SSOM model as its grid size can be tuned and it achieved 9 out of 9 minimum error in presenting the surface.
{"title":"Performance Evaluation of Self-Organising Map Model in Organising the Unstructured Data","authors":"C. C. You, Joi San Tan, Seng Poh Lim, Seng Chee Lim, Chen Kang Lee","doi":"10.1109/ICOCO56118.2022.10032038","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10032038","url":null,"abstract":"Surface reconstruction becomes a difficult task in reverse engineering when the data obtained during the data acquisition process is unstructured. The unstructured data do not contain the connectivity information required to represent the surface correctly with the least error. Hence, it should be organised to obtain the connectivity information. Various types of Self-Organising Map (SOM) models are utilised in the previous works to organise the unstructured data and represent the surface. However, the performance of the SOM models is affected when different topologies are involved in the organising process. Therefore, the purposes of this experiment are to evaluate the performance of the SOM models with different topologies and to determine the limitation of the various SOM models. The SOM models involved are 2-D SOM, 3-D SOM, Cube Kohonen (CK) SOM, and Spherical SOM (SSOM). Three 3-D unstructured closed surface data sets are applied in this experiment to evaluate the models. The experimental results show that the CKSOM and SSOM models can represent the closed surface correctly with a medium speed. Overall, the CKSOM model performs better than the SSOM model as its grid size can be tuned and it achieved 9 out of 9 minimum error in presenting the surface.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"162 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129151080","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031931
Nor Haziqah Mohd Yusri, Nur Amalina binti Shafie, N. A. M. Ghani
Rice is a staple food in Malaysia. There are three leading crops consumed by humans which include rice, wheat, and maize. Among these three crops, rice is by far the most important for people in low and low-middle-income countries. Thus, rice has a pivotal role as a source of nutrition for most Malaysians and a principal source of income for farmers. In this study, a data set of monthly rice prices in Malaysia from January 2013 to December 2021 is used from IndexMundi. A total of108 observations were examined by using the Box-Jenkins method which is Autoregressive Integrated Moving Average (ARIMA). This study found that the ARIMA(2,1,1) is the best model using the data based on Akaike’s Information Criterion (AIC) and Bayesian Information Criterion (BIC) value. This research aimed to identify the behavior, the best fit model, and forecast the future value of rice prices in Malaysia.
{"title":"Rice Price Prediction in Malaysia","authors":"Nor Haziqah Mohd Yusri, Nur Amalina binti Shafie, N. A. M. Ghani","doi":"10.1109/ICOCO56118.2022.10031931","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031931","url":null,"abstract":"Rice is a staple food in Malaysia. There are three leading crops consumed by humans which include rice, wheat, and maize. Among these three crops, rice is by far the most important for people in low and low-middle-income countries. Thus, rice has a pivotal role as a source of nutrition for most Malaysians and a principal source of income for farmers. In this study, a data set of monthly rice prices in Malaysia from January 2013 to December 2021 is used from IndexMundi. A total of108 observations were examined by using the Box-Jenkins method which is Autoregressive Integrated Moving Average (ARIMA). This study found that the ARIMA(2,1,1) is the best model using the data based on Akaike’s Information Criterion (AIC) and Bayesian Information Criterion (BIC) value. This research aimed to identify the behavior, the best fit model, and forecast the future value of rice prices in Malaysia.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115890066","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031735
D. Truong, H. Nguyen, Sang Vu, Vuong T. Pham, Diem Nguyen
E-learning is an online educational system using technological and electronic devices through the internet. Using e-learning educational systems, learners can refer to documents and communicate directly with teachers to effectuate the acquisition of knowledge. In this paper, the method for creating an intelligent querying system for e-learning is proposed. The knowledge base of this system is organized based on the integrating of ontology and the structure of database. Some searching issues for knowledge content, such as studying and resolving knowledge searches based on classification of knowledge, are studied and solved. This method is applied to build an intelligent querying system on the course of Database Foundation in Information Technology (IT) curriculum at university. This system aims to support students to review lessons and understand more the knowledge of courses by their self-learning. The experimental results show that it would be expected to contribute in supporting online-based learning facilities for students.
{"title":"Construct an Intelligent Querying System in Education based on Ontology Integration","authors":"D. Truong, H. Nguyen, Sang Vu, Vuong T. Pham, Diem Nguyen","doi":"10.1109/ICOCO56118.2022.10031735","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031735","url":null,"abstract":"E-learning is an online educational system using technological and electronic devices through the internet. Using e-learning educational systems, learners can refer to documents and communicate directly with teachers to effectuate the acquisition of knowledge. In this paper, the method for creating an intelligent querying system for e-learning is proposed. The knowledge base of this system is organized based on the integrating of ontology and the structure of database. Some searching issues for knowledge content, such as studying and resolving knowledge searches based on classification of knowledge, are studied and solved. This method is applied to build an intelligent querying system on the course of Database Foundation in Information Technology (IT) curriculum at university. This system aims to support students to review lessons and understand more the knowledge of courses by their self-learning. The experimental results show that it would be expected to contribute in supporting online-based learning facilities for students.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"32 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125731820","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}
Reports of cyber attacks are increasing every year. Although many companies, groups, and organizations have taken various measures against cyber attacks, such as security education and attack detection systems. However, it is still practically challenging to prevent security incidents completely and proactively. In addition, attackers continue to attack internally after their initial intrusion. In other words, it is essential to prevent the attacker’s intrusion and quickly identify and stop the damage after the intrusion. However, it takes time and effort to quickly identify the infection status from a large number of logs. The purpose of this research is to identify the infection status of an organization quickly. We hypothesized that the behavior of the initially infected device and the secondary one by lateral movement would be similar. To put it differently, we thought it was possible to detect laterally moved devices based on the similarity between an initially infected device and a secondary one. In this research, we propose a method to find a device secondarily infected by lateral movement. We determine the similarity between the initially infected device and the secondary one by embodying the device’s behavior in terms of MITRE ATT&CK’s Technique. Our experiment results show a substantial similarity between the initially infected device and the secondary one by lateral movement.
{"title":"Prediction of Infected Devices Using the Quantification Theory Type 3 Based on MITRE ATT&CK Technique","authors":"Yosuke Katano, Yukihiro Kozai, Satoshi Okada, Takuho Mitsunaga","doi":"10.1109/ICOCO56118.2022.10031822","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031822","url":null,"abstract":"Reports of cyber attacks are increasing every year. Although many companies, groups, and organizations have taken various measures against cyber attacks, such as security education and attack detection systems. However, it is still practically challenging to prevent security incidents completely and proactively. In addition, attackers continue to attack internally after their initial intrusion. In other words, it is essential to prevent the attacker’s intrusion and quickly identify and stop the damage after the intrusion. However, it takes time and effort to quickly identify the infection status from a large number of logs. The purpose of this research is to identify the infection status of an organization quickly. We hypothesized that the behavior of the initially infected device and the secondary one by lateral movement would be similar. To put it differently, we thought it was possible to detect laterally moved devices based on the similarity between an initially infected device and a secondary one. In this research, we propose a method to find a device secondarily infected by lateral movement. We determine the similarity between the initially infected device and the secondary one by embodying the device’s behavior in terms of MITRE ATT&CK’s Technique. Our experiment results show a substantial similarity between the initially infected device and the secondary one by lateral movement.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125771717","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}
Recently, remote work has become popular due to the widespread of infectious diseases. Many organizations and companies have turned to a Virtual Private Network (VPN) in an attempt to provide secure remote access to their on-premises infrastructure. However, intensive access to such VPN devices places a heavy burden on network performance, and there is also a high risk of cyber-attacks targeting them. Therefore, the demand for zero trust architecture without using VPN devices is increasing these days. However, it takes much time for organizations to introduce a zero trust architecture. Furthermore, it is difficult for some organizations to implement the so-called “ideal zero trust environment” because of some security problems and confidential information management. Thus, it is expected that a hybrid environment in which a zero trust architecture and a conventional on-premises environment coexist is introduced at first in many organizations. In this environment, access logs for each service are distributed in both cloud and on-premise servers. Thus, conventional log-based anomaly detection methods will not work well. In this paper, we propose a method for detecting unauthorized access to such a hybrid environment using machine learning and verify its effectiveness in a virtual environment. As a result, we detect abnormal behavior with high accuracy. Furthermore, based on the experimental results, we discuss how logs should be collected and what kind of log information is useful for anomaly detection in hybrid environments.
{"title":"ML Detection Method for Malicious Operation in Hybrid Zero Trust Architecture","authors":"Koshi Ishide, Satoshi Okada, Mariko Fujimoto, Takuho Mitsunaga","doi":"10.1109/ICOCO56118.2022.10031702","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031702","url":null,"abstract":"Recently, remote work has become popular due to the widespread of infectious diseases. Many organizations and companies have turned to a Virtual Private Network (VPN) in an attempt to provide secure remote access to their on-premises infrastructure. However, intensive access to such VPN devices places a heavy burden on network performance, and there is also a high risk of cyber-attacks targeting them. Therefore, the demand for zero trust architecture without using VPN devices is increasing these days. However, it takes much time for organizations to introduce a zero trust architecture. Furthermore, it is difficult for some organizations to implement the so-called “ideal zero trust environment” because of some security problems and confidential information management. Thus, it is expected that a hybrid environment in which a zero trust architecture and a conventional on-premises environment coexist is introduced at first in many organizations. In this environment, access logs for each service are distributed in both cloud and on-premise servers. Thus, conventional log-based anomaly detection methods will not work well. In this paper, we propose a method for detecting unauthorized access to such a hybrid environment using machine learning and verify its effectiveness in a virtual environment. As a result, we detect abnormal behavior with high accuracy. Furthermore, based on the experimental results, we discuss how logs should be collected and what kind of log information is useful for anomaly detection in hybrid environments.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123421020","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031922
A. Zakaria, A. Selamat, Lim Kok Cheng, O. Krejcar
Data mining is a knowledge discovery of the data that extracts and discovers patterns and relationships to predict outcomes. Class imbalance is one of the obstacles that can drive misclassification. The class imbalance affected the result of classification machine learning. The classification technique can divide the data into the given class target. This research focuses on four pre-processing methods: SMOTE, Spread Subsample, Class Balancer, and Resample. These methods can help to clean the data before undergoing the classification techniques. Resample shows the best result for solving the imbalance problem with 41.321 for Mean and Standard Deviation, 64.101. Besides, this research involves six classification techniques: Naïve Bayes, BayesNet, Random Forest, Random Tree, Logistics, and Multilayer Perceptron. Indeed, the combination of Resample and Random Forest has the best result of Precision, 0.941, and ROC Area is 0.983.
{"title":"Improving Class Imbalance Detection And Classification Performance: A New Potential of Combination Resample and Random Forest","authors":"A. Zakaria, A. Selamat, Lim Kok Cheng, O. Krejcar","doi":"10.1109/ICOCO56118.2022.10031922","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031922","url":null,"abstract":"Data mining is a knowledge discovery of the data that extracts and discovers patterns and relationships to predict outcomes. Class imbalance is one of the obstacles that can drive misclassification. The class imbalance affected the result of classification machine learning. The classification technique can divide the data into the given class target. This research focuses on four pre-processing methods: SMOTE, Spread Subsample, Class Balancer, and Resample. These methods can help to clean the data before undergoing the classification techniques. Resample shows the best result for solving the imbalance problem with 41.321 for Mean and Standard Deviation, 64.101. Besides, this research involves six classification techniques: Naïve Bayes, BayesNet, Random Forest, Random Tree, Logistics, and Multilayer Perceptron. Indeed, the combination of Resample and Random Forest has the best result of Precision, 0.941, and ROC Area is 0.983.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122285742","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 : 2022-11-14DOI: 10.1109/icoco56118.2022.10031974
{"title":"2022 IEEE Conference on Computing (ICOCO)","authors":"","doi":"10.1109/icoco56118.2022.10031974","DOIUrl":"https://doi.org/10.1109/icoco56118.2022.10031974","url":null,"abstract":"","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134050338","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031675
Al Mamun Mizan, Farah Aliah Nur Mansor, N. A. M. Ghani, A. Kamarudin, Mahayaudin M. Mansor, Siti Afiqah Muhamad Jamil, N. Ibrahim
Authorities have suggested emergency remote instruction to guarantee that students are not left idle during the pandemic due to the sudden closing of educational facilities. Then for the time being, traditional methods (face-to-face) have been replaced by Open and Distance Learning (ODL). Face-to-face learning was preferred by the majority of students over online learning since students were not able transit to online learning and lacked inspiration. Hence, this study focuses on perception towards ODL during COVID-19 among statistics’ students at FSKM UiTM Shah Alam based on some impeding factors such as social issue, lecturer issue, accessibility issue, academic issue, generic skills and learner intentions. The aim of this study is to investigate the perception of statistics’ students on ODL based on impeding factors and to identify the significant impeding factors effect on statistics students’ perception on ODL. There are 160 observations that are used in this study. The methods that are being used in this study are descriptive analysis and logistic regression. Overall, from the result obtained, students’ perception on ODL are approximately to agree for social issue, academic issue and learner intentions variables. Meanwhile, the significance impeding factors in this study are social issue and learner intentions. This study may help higher education institution to improve and make a better strategy to improve the existing teaching method that have been applied by all lecturers.
当局建议进行紧急远程教学，以确保学生在疫情期间不会因教育设施突然关闭而闲置。然后，就目前而言，传统的方法(面对面)已经被开放和远程学习(ODL)所取代。由于学生无法过渡到在线学习并且缺乏灵感，大多数学生更喜欢面对面学习而不是在线学习。因此，本研究基于社会问题、讲师问题、可及性问题、学术问题、通用技能和学习者意向等阻碍因素，重点研究FSKM Shah Alam统计专业学生在COVID-19期间对ODL的看法。本研究的目的是基于阻碍因素调查统计专业学生对ODL的感知，并找出显著的阻碍因素对统计专业学生ODL感知的影响。在这项研究中使用了160个观察结果。在本研究中使用的方法是描述性分析和逻辑回归。总体而言，从获得的结果来看，学生对ODL的感知在社会问题、学术问题和学习者意图变量上大致一致。同时，社会问题和学习者意向是本研究的显著性阻碍因素。本研究可以帮助高等教育机构改进和制定更好的策略来改进所有讲师所采用的现有教学方法。
{"title":"Logistic Regression Model for Measuring Perception on Open and Distance Learning (ODL) during COVID-19 Pandemic based on Impeding Factors among Students","authors":"Al Mamun Mizan, Farah Aliah Nur Mansor, N. A. M. Ghani, A. Kamarudin, Mahayaudin M. Mansor, Siti Afiqah Muhamad Jamil, N. Ibrahim","doi":"10.1109/ICOCO56118.2022.10031675","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031675","url":null,"abstract":"Authorities have suggested emergency remote instruction to guarantee that students are not left idle during the pandemic due to the sudden closing of educational facilities. Then for the time being, traditional methods (face-to-face) have been replaced by Open and Distance Learning (ODL). Face-to-face learning was preferred by the majority of students over online learning since students were not able transit to online learning and lacked inspiration. Hence, this study focuses on perception towards ODL during COVID-19 among statistics’ students at FSKM UiTM Shah Alam based on some impeding factors such as social issue, lecturer issue, accessibility issue, academic issue, generic skills and learner intentions. The aim of this study is to investigate the perception of statistics’ students on ODL based on impeding factors and to identify the significant impeding factors effect on statistics students’ perception on ODL. There are 160 observations that are used in this study. The methods that are being used in this study are descriptive analysis and logistic regression. Overall, from the result obtained, students’ perception on ODL are approximately to agree for social issue, academic issue and learner intentions variables. Meanwhile, the significance impeding factors in this study are social issue and learner intentions. This study may help higher education institution to improve and make a better strategy to improve the existing teaching method that have been applied by all lecturers.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133922133","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031756
Muhammad Syabil Azman, Farli Rossi, N. Zulkarnain, S. S. Mokri, Ashrani Aizzuddin Abd. Rahni, Nurul Fatihah Ali
Global Cancer Statistics 2020 states that there are 2.2 million lung cancer cases worldwide with 1.8 million deaths. At present, deep learning based CAD system for lung nodules classification has been extensively explored. However, this approach requires a great size of images which becomes an issue for medical images. Thus, Generative Advesarial Network (GAN) is introduced to ease this limitation by creating synthetic images. In this study, four GAN architectures namely Deep Convolutional (DCGAN), Deep Regret Analytic GAN (DRAGAN), Wasserstein GAN (WGAN) and Wasserstein GAN with Gradient Penalty (WGANGP) are used in generating synthetic medical images which are then used to classify the lung lesions into benign and malignant via ShuffleNet. The classification is assessed based on pecificity, accuracy, sensitivity, and values of AUC-ROC. Experimental results show that DRAGAN achieved the lowest Fréchet Inception Distance (FID) score of 137.48 of the new generated datasets followed by the WGAN-GP (158.86), WGAN (176.86) and DCGAN (172.56). However, due to the lack of diversity in datasets of DRAGAN, instead WGAN-GP ShuffleNet performed the best in the classification task achieving 98.87% of accuracy, 98.36% of specificity, 99.34% of sensitivity and highest AUC among others at 99.96%. Overall, both high quality and well diversed synthetic images are equally important for the lung nodules classification problem.
《2020年全球癌症统计》指出，全球有220万例肺癌病例，其中180万人死亡。目前，基于深度学习的肺结节分类CAD系统已经得到了广泛的探索。然而，这种方法需要大尺寸的图像，这成为医学图像的一个问题。因此，生成对抗网络(GAN)通过创建合成图像来缓解这一限制。本研究采用深度卷积GAN (Deep Convolutional GAN)、深度遗憾分析GAN (Deep Regret Analytic GAN (DRAGAN)、沃瑟斯坦GAN (WGAN)和Wasserstein GAN with Gradient Penalty (WGANGP)四种GAN架构生成合成医学图像，然后通过ShuffleNet将肺病变分类为良性和恶性。分类是根据特异性、准确性、敏感性和AUC-ROC值来评估的。实验结果表明，在新生成的数据集中，DRAGAN的fr起始距离(FID)得分最低，为137.48，其次是WGAN- gp(158.86)、WGAN(176.86)和DCGAN(172.56)。然而，由于DRAGAN数据集缺乏多样性，WGAN-GP ShuffleNet在分类任务中表现最好，准确率为98.87%，特异性为98.36%，灵敏度为99.34%，AUC最高，为99.96%。总之，高质量和多样化的合成图像对肺结节分类问题同样重要。
{"title":"Classification of Lung Nodule CT Images Using GAN Variants and CNN","authors":"Muhammad Syabil Azman, Farli Rossi, N. Zulkarnain, S. S. Mokri, Ashrani Aizzuddin Abd. Rahni, Nurul Fatihah Ali","doi":"10.1109/ICOCO56118.2022.10031756","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031756","url":null,"abstract":"Global Cancer Statistics 2020 states that there are 2.2 million lung cancer cases worldwide with 1.8 million deaths. At present, deep learning based CAD system for lung nodules classification has been extensively explored. However, this approach requires a great size of images which becomes an issue for medical images. Thus, Generative Advesarial Network (GAN) is introduced to ease this limitation by creating synthetic images. In this study, four GAN architectures namely Deep Convolutional (DCGAN), Deep Regret Analytic GAN (DRAGAN), Wasserstein GAN (WGAN) and Wasserstein GAN with Gradient Penalty (WGANGP) are used in generating synthetic medical images which are then used to classify the lung lesions into benign and malignant via ShuffleNet. The classification is assessed based on pecificity, accuracy, sensitivity, and values of AUC-ROC. Experimental results show that DRAGAN achieved the lowest Fréchet Inception Distance (FID) score of 137.48 of the new generated datasets followed by the WGAN-GP (158.86), WGAN (176.86) and DCGAN (172.56). However, due to the lack of diversity in datasets of DRAGAN, instead WGAN-GP ShuffleNet performed the best in the classification task achieving 98.87% of accuracy, 98.36% of specificity, 99.34% of sensitivity and highest AUC among others at 99.96%. Overall, both high quality and well diversed synthetic images are equally important for the lung nodules classification problem.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132765697","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 : 2022-11-14DOI: 10.1109/ICOCO56118.2022.10031725
Nik Aqil, Firdaus Afifi, Faiz Zaki, N. B. Anuar
The Internet of Things (IoT) has gained attention for its rapid growth in the past few years. IoT devices such as temperature and humidity sensors and voice controllers are implemented widely, from household appliances to industrial machines. However, with the rapid growth and benefits IoT offers, we are exposed to various security vulnerabilities, such as data breaches and IoT-specific malware. Researchers are using IoT device identification as a solution for IoT security issues. IoT device identification helps network administrators identify network traffic into its originating devices. However, researchers often overlook an important issue in IoT device identification, which is accuracy degradation over time. Thus, this paper explores the severity of accuracy degradation in IoT device identification on different traffic representation approaches, which are flow, sub-flow, and packet. This paper utilizes a private, and the UNSW IoT Traffic Traces public dataset. Based on the experimental findings, the sub-flow-based approach recorded the best overall performance, with only 8% degradation in the private dataset and 1% degradation in the public dataset. Meanwhile, even though the packet-based approach only degraded 5% on the private dataset, it recorded up to an 11% accuracy decrease in the public dataset.
{"title":"Preliminary Study on the Effect of Traffic Representation on Accuracy Degradation in Machine Learning-based IoT Device Identification","authors":"Nik Aqil, Firdaus Afifi, Faiz Zaki, N. B. Anuar","doi":"10.1109/ICOCO56118.2022.10031725","DOIUrl":"https://doi.org/10.1109/ICOCO56118.2022.10031725","url":null,"abstract":"The Internet of Things (IoT) has gained attention for its rapid growth in the past few years. IoT devices such as temperature and humidity sensors and voice controllers are implemented widely, from household appliances to industrial machines. However, with the rapid growth and benefits IoT offers, we are exposed to various security vulnerabilities, such as data breaches and IoT-specific malware. Researchers are using IoT device identification as a solution for IoT security issues. IoT device identification helps network administrators identify network traffic into its originating devices. However, researchers often overlook an important issue in IoT device identification, which is accuracy degradation over time. Thus, this paper explores the severity of accuracy degradation in IoT device identification on different traffic representation approaches, which are flow, sub-flow, and packet. This paper utilizes a private, and the UNSW IoT Traffic Traces public dataset. Based on the experimental findings, the sub-flow-based approach recorded the best overall performance, with only 8% degradation in the private dataset and 1% degradation in the public dataset. Meanwhile, even though the packet-based approach only degraded 5% on the private dataset, it recorded up to an 11% accuracy decrease in the public dataset.","PeriodicalId":319652,"journal":{"name":"2022 IEEE International Conference on Computing (ICOCO)","volume":"925 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113981878","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：