Pub Date : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251869
S. K. Sonbhadra, Sonali Agarwal, M. Syafrullah, K. Adiyarta
Monitoring and tracking of any target in a surveillance system is an important task. When these targets are human then this problem comes under person identification and tracking. At present, large scale smart video surveillance system is an essential component for any commercial or public campus. Since field of view (FOV) of a camera is limited; for large area monitoring, multiple cameras are needed at different locations. This paper proposes a novel model for tracking a person under multiple non-overlapping cameras. It builds the reference signature of the person at the beginning of the tracking system to match with the upcoming signatures captured by other cameras within the specified area of observation with the help of trained support vector machine (SVM) between two cameras. For experiments, wide area re-identification dataset (WARD) and a real-time scenario have been used with color, shape and texture features for person's re-identification.
{"title":"Person tracking with non-overlapping multiple cameras","authors":"S. K. Sonbhadra, Sonali Agarwal, M. Syafrullah, K. Adiyarta","doi":"10.23919/EECSI50503.2020.9251869","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251869","url":null,"abstract":"Monitoring and tracking of any target in a surveillance system is an important task. When these targets are human then this problem comes under person identification and tracking. At present, large scale smart video surveillance system is an essential component for any commercial or public campus. Since field of view (FOV) of a camera is limited; for large area monitoring, multiple cameras are needed at different locations. This paper proposes a novel model for tracking a person under multiple non-overlapping cameras. It builds the reference signature of the person at the beginning of the tracking system to match with the upcoming signatures captured by other cameras within the specified area of observation with the help of trained support vector machine (SVM) between two cameras. For experiments, wide area re-identification dataset (WARD) and a real-time scenario have been used with color, shape and texture features for person's re-identification.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"06 1","pages":"137-143"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77102737","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251887
D. K. Agustika, S. Hidayat, K. Triyana, D. Iliescu, M. Leeson
Feature extraction of electronic nose (e-nose) output response aims to reduce information redundancy so that the e-nose performance can be improved. The use of different sensor types and sample targets can affect the optimization of feature extraction. This research used six types of metal oxide sensors, TGS 813, 822, 825, 826, 2620, and 2611 in an e-nose system to detect three types of herbal drink. Five kinds of feature extraction methods on the original response curve in a steady-state response were used, namely, baseline difference, logarithmic difference, local normalization, global normalization, and global autoscaling. The results of feature extraction were fed into a Principal Component Analysis (PCA) system. As a result, global autoscaling and normalization had the highest total sum of the first and second principal components of 96.96%, followed by local normalization (90.18%), logarithm, and baseline difference (88.92% and 79.26%, respectively). The validation of PCA results was performed using a Backpropagation Neural Network (BPNN). The highest accuracy, 97.44%, was obtained from the global autoscaling method, followed by global normalization, local normalization, logarithm, and baseline difference, with an accuracy level of 94.87%, 92.31 %, 89.74%, and 82.05%, respectively. This demonstrates that the selection of the feature extraction method can affect the classification results and improve e-nose performance.
{"title":"Steady-state response feature extraction optimization to enhance electronic nose performance","authors":"D. K. Agustika, S. Hidayat, K. Triyana, D. Iliescu, M. Leeson","doi":"10.23919/EECSI50503.2020.9251887","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251887","url":null,"abstract":"Feature extraction of electronic nose (e-nose) output response aims to reduce information redundancy so that the e-nose performance can be improved. The use of different sensor types and sample targets can affect the optimization of feature extraction. This research used six types of metal oxide sensors, TGS 813, 822, 825, 826, 2620, and 2611 in an e-nose system to detect three types of herbal drink. Five kinds of feature extraction methods on the original response curve in a steady-state response were used, namely, baseline difference, logarithmic difference, local normalization, global normalization, and global autoscaling. The results of feature extraction were fed into a Principal Component Analysis (PCA) system. As a result, global autoscaling and normalization had the highest total sum of the first and second principal components of 96.96%, followed by local normalization (90.18%), logarithm, and baseline difference (88.92% and 79.26%, respectively). The validation of PCA results was performed using a Backpropagation Neural Network (BPNN). The highest accuracy, 97.44%, was obtained from the global autoscaling method, followed by global normalization, local normalization, logarithm, and baseline difference, with an accuracy level of 94.87%, 92.31 %, 89.74%, and 82.05%, respectively. This demonstrates that the selection of the feature extraction method can affect the classification results and improve e-nose performance.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"26 1","pages":"144-149"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83031021","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251303
A. Permana, R. Taufiq, Salsabila Ramadhina
Hydroponics is one of the effective farming methods to apply in big cities because it does not require extensive agricultural land. In addition, hydroponic products are cleaner, higher quality and free from pesticides. However, the development of hydroponic products in Indonesia is relatively slow. One of the factors causing the slow development of hydroponic agribusiness is that online sales media for hydroponic products are still limited, especially android-based e-marketplace application. Hydrolite is present as an e-marketplace that specifically sells vegetables grown using the hydroponic method, and sells all the equipment needed to farm hydroponically. Hydrolite is a prototype e-marketplace application designed using the Marvelapp platform. Further, Marvelapp is one of the best prototyping tools to support application development on mobile devices.
{"title":"Prototype Design of Mobile Application ‘Hydrolite’ for Hydroponics Marketplace","authors":"A. Permana, R. Taufiq, Salsabila Ramadhina","doi":"10.23919/EECSI50503.2020.9251303","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251303","url":null,"abstract":"Hydroponics is one of the effective farming methods to apply in big cities because it does not require extensive agricultural land. In addition, hydroponic products are cleaner, higher quality and free from pesticides. However, the development of hydroponic products in Indonesia is relatively slow. One of the factors causing the slow development of hydroponic agribusiness is that online sales media for hydroponic products are still limited, especially android-based e-marketplace application. Hydrolite is present as an e-marketplace that specifically sells vegetables grown using the hydroponic method, and sells all the equipment needed to farm hydroponically. Hydrolite is a prototype e-marketplace application designed using the Marvelapp platform. Further, Marvelapp is one of the best prototyping tools to support application development on mobile devices.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"23 1","pages":"45-48"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85506516","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251908
Sunaryo, A. Putra, Arief Marwanto, Muhamad Haddin
The consumption of electricity that increase anytime also increases CO2 emissions in the air as a result of coal combustion flue gas at the power plant. The operation of supercritical boilers on the power plant will lead to higher thermal efficiency compared to subcritical boilers. Higher steam pressure boiler will increase the thermal efficiency and automatically reduce CO2 emissions due to a reduction in fuel consumption at the same boiler efficiency and heating value of coal. At 166.9 bar subcritical steam boiler thermal efficiency was 45.47 % and CO2 emissions were 602.2 tons while at supercritical pressure 240 bar, efficiency increased to 47.12 % with a reduction in CO2 emissions of 20.9 tons to 581.3 tons.
{"title":"Potential for Reducing CO2 Emissions in the Operation of Subcritical Power Plants into Supercritical","authors":"Sunaryo, A. Putra, Arief Marwanto, Muhamad Haddin","doi":"10.23919/EECSI50503.2020.9251908","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251908","url":null,"abstract":"The consumption of electricity that increase anytime also increases CO2 emissions in the air as a result of coal combustion flue gas at the power plant. The operation of supercritical boilers on the power plant will lead to higher thermal efficiency compared to subcritical boilers. Higher steam pressure boiler will increase the thermal efficiency and automatically reduce CO2 emissions due to a reduction in fuel consumption at the same boiler efficiency and heating value of coal. At 166.9 bar subcritical steam boiler thermal efficiency was 45.47 % and CO2 emissions were 602.2 tons while at supercritical pressure 240 bar, efficiency increased to 47.12 % with a reduction in CO2 emissions of 20.9 tons to 581.3 tons.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"9 1","pages":"100-104"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87795672","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251297
Muhammad Nor Arif Sulaiman, T. Adiono
Digital image processing is a processing of digital frames using digital computation. Image processing has been used in many sectors such as military, biomedics, and in this paper, the authors will implement it in the civil aviation sector by introducing a new method to monitor an aviation navigation equipment. It can be used on all LED-based Built-in Monitor navigation equipment, despite it is a low-cost system. The image processing of this research is done by doing perspective correction and then continue with BLOB detection in a segmentation stage. The final result will be displayed on a web page. Compared to its predecessor, this method gives better flexibility which does not need to be electrically connected with monitored equipment and not limited to certain brands.
{"title":"Smart Navigation Equipment Monitoring System","authors":"Muhammad Nor Arif Sulaiman, T. Adiono","doi":"10.23919/EECSI50503.2020.9251297","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251297","url":null,"abstract":"Digital image processing is a processing of digital frames using digital computation. Image processing has been used in many sectors such as military, biomedics, and in this paper, the authors will implement it in the civil aviation sector by introducing a new method to monitor an aviation navigation equipment. It can be used on all LED-based Built-in Monitor navigation equipment, despite it is a low-cost system. The image processing of this research is done by doing perspective correction and then continue with BLOB detection in a segmentation stage. The final result will be displayed on a web page. Compared to its predecessor, this method gives better flexibility which does not need to be electrically connected with monitored equipment and not limited to certain brands.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"98 1","pages":"198-202"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90650348","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251906
Kurniandha Sukma Yunastrian, Saiful Akbar, F. Arifiansyah
Spreadsheet is one of the tools that can be used to learn data analysis. Data analysis in spreadsheet can be done using formula. Spreadsheet tools can also be used for exams. For the assessment, there is a problem when the number of answers that need to be checked is large, that is it takes a long time to check all the answers. For this reason, an automatic grading system (autograder) that can evaluate formula in spreadsheet is needed. The method used in developing the autograder system is matching the answer key formula with the student's answer formula. The autograder system assesses the answer by calculating the similarity of the student's answer formula with the answer key formula. This paper explains how to build an autograder system that can evaluate the formula. At the end, an autograder system has been built successfully. It has been tested with 43 testcases and all of them are passed.
{"title":"Automatic Grading System for Spreadsheet Formula","authors":"Kurniandha Sukma Yunastrian, Saiful Akbar, F. Arifiansyah","doi":"10.23919/EECSI50503.2020.9251906","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251906","url":null,"abstract":"Spreadsheet is one of the tools that can be used to learn data analysis. Data analysis in spreadsheet can be done using formula. Spreadsheet tools can also be used for exams. For the assessment, there is a problem when the number of answers that need to be checked is large, that is it takes a long time to check all the answers. For this reason, an automatic grading system (autograder) that can evaluate formula in spreadsheet is needed. The method used in developing the autograder system is matching the answer key formula with the student's answer formula. The autograder system assesses the answer by calculating the similarity of the student's answer formula with the answer key formula. This paper explains how to build an autograder system that can evaluate the formula. At the end, an autograder system has been built successfully. It has been tested with 43 testcases and all of them are passed.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"1 1","pages":"49-53"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75683407","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251877
Mega Apriani, Diwandaru Rousstia, Fajar Achmad Rifai, R. Harwahyu, R. F. Sari
Work from Home (WFH) is an activity carrying out official duties, completing outputs, coordination, meetings, and other tasks from the residence of employees. Implement WFH many users use the zoom application has vulnerabilities. The network architecture used refers to the simple experiment network. In Secure WFH there are 3 offices connected through a router. Each client in each office is connected to the router via a Virtual Private Network (VPN) on a peer-to-peer (P2P). That architecture has 18 nodes that will be simulated. Secure WFH simulation with blockchain combines secure WFH with a bitcoin code simulator from Arthur Gervais's. Implementation of blockchain on secure WFH can increase security but the resulting speed decreases. The decrease in speed when implementing secure WFH is due to the generate block process and the verification process.
在家办公(Work from Home, WFH)是一种在员工住所执行公务、完成产出、协调、会议等任务的活动。实现WFH的许多用户使用的缩放应用程序存在漏洞。使用的网络架构为简单的实验网络。在安全WFH中，有3个办公室通过路由器连接。每个办公室的每个客户端都通过点对点的VPN (Virtual Private Network)连接到路由器。该架构有18个节点将被模拟。区块链的安全WFH模拟将安全WFH与Arthur Gervais的比特币代码模拟器结合在一起。在安全WFH上实施区块链可以提高安全性，但导致速度降低。在实现安全WFH时，速度的降低是由于生成块过程和验证过程。
{"title":"Implementation of Secure Work From Home System Based on Blockchain using NS3 Simulation","authors":"Mega Apriani, Diwandaru Rousstia, Fajar Achmad Rifai, R. Harwahyu, R. F. Sari","doi":"10.23919/EECSI50503.2020.9251877","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251877","url":null,"abstract":"Work from Home (WFH) is an activity carrying out official duties, completing outputs, coordination, meetings, and other tasks from the residence of employees. Implement WFH many users use the zoom application has vulnerabilities. The network architecture used refers to the simple experiment network. In Secure WFH there are 3 offices connected through a router. Each client in each office is connected to the router via a Virtual Private Network (VPN) on a peer-to-peer (P2P). That architecture has 18 nodes that will be simulated. Secure WFH simulation with blockchain combines secure WFH with a bitcoin code simulator from Arthur Gervais's. Implementation of blockchain on secure WFH can increase security but the resulting speed decreases. The decrease in speed when implementing secure WFH is due to the generate block process and the verification process.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"33 1","pages":"54-59"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79517013","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251886
A. Darmawan, D. Siahaan, T. D. Susanto, Hoiriyah Hoiriyah, B. Umam, Anwari Anwari
Currently, almost every country struggles to apply city management to the concept of intelligent cities. Several previous studies have modelled the success, maturity, and success of information systems to use smart city principles. However, there are significant differences between city and district definition in terms of governance frameworks, regional size, livelihood differences, population, socio-economic, and socio-cultural dimensions. Therefore, work on the Smart District IT assessment requires new and unique studies that can differ substantially from smart cities. This study aims to explore the determinants of the success of Smart Regency services with mobile technology. The model and approach are the TRUTAUT model, which combines the concepts for the TRI and the UTAUT model. Two hundred eighty-nine participants could collect data with a smart cellular district service system - data processing using the SmartPLS v.3.2.8 software. Recent findings indicate that the variables proposed in the TRUTAUT model are a positive and essential relation. This study helps to determine the success of the application of intelligent mobile regional services applications. This study confirms that policymakers pay more considerable attention to critical questions that affect the district's smart cellular services' success.
{"title":"Exploring Success Factor for Mobile based Smart Regency Service using TRUTAUT Model Approach","authors":"A. Darmawan, D. Siahaan, T. D. Susanto, Hoiriyah Hoiriyah, B. Umam, Anwari Anwari","doi":"10.23919/EECSI50503.2020.9251886","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251886","url":null,"abstract":"Currently, almost every country struggles to apply city management to the concept of intelligent cities. Several previous studies have modelled the success, maturity, and success of information systems to use smart city principles. However, there are significant differences between city and district definition in terms of governance frameworks, regional size, livelihood differences, population, socio-economic, and socio-cultural dimensions. Therefore, work on the Smart District IT assessment requires new and unique studies that can differ substantially from smart cities. This study aims to explore the determinants of the success of Smart Regency services with mobile technology. The model and approach are the TRUTAUT model, which combines the concepts for the TRI and the UTAUT model. Two hundred eighty-nine participants could collect data with a smart cellular district service system - data processing using the SmartPLS v.3.2.8 software. Recent findings indicate that the variables proposed in the TRUTAUT model are a positive and essential relation. This study helps to determine the success of the application of intelligent mobile regional services applications. This study confirms that policymakers pay more considerable attention to critical questions that affect the district's smart cellular services' success.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"37 1","pages":"250-256"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82444108","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251897
Agung Besti, Ridwan Ilyas, Fatan Kasyidi, E. C. Djamal
One development of Natural Language Processing is the semantic classification of sentences and documents. The challenge is finding relationships between words and between documents through a computational model. The development of machine learning makes it possible to try out various possibilities that provide classification capabilities. This paper proposes the semantic classification of sentence pairs using Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM). Each couple of sentences is turned into vectors using Word2Vec. Experiments carried out using CBOW and Skip-Gram to get the best combination. The results are obtained that word embedding using CBOW produces better than Skip-Gram, although it is still around 5%. However, CBOW slows slightly at the beginning of iteration but is stable towards convergence. Classification of all six classes, namely Equivalent, Similar, Specific, No Alignment, Related, and Opposite. As a result of the unbalanced data set, the retraining was conducted by eliminating a few classes member from the data set, thus providing an accuracy of 73 % for non-training data. The results showed that the Adam model gave a faster convergence at the start of training compared to the SGD model, and AdaDelta, which was built, gave 75% better accuracy with an F1-Score of 67%.
{"title":"Semantic Classification of Scientific Sentence Pair Using Recurrent Neural Network","authors":"Agung Besti, Ridwan Ilyas, Fatan Kasyidi, E. C. Djamal","doi":"10.23919/EECSI50503.2020.9251897","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251897","url":null,"abstract":"One development of Natural Language Processing is the semantic classification of sentences and documents. The challenge is finding relationships between words and between documents through a computational model. The development of machine learning makes it possible to try out various possibilities that provide classification capabilities. This paper proposes the semantic classification of sentence pairs using Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM). Each couple of sentences is turned into vectors using Word2Vec. Experiments carried out using CBOW and Skip-Gram to get the best combination. The results are obtained that word embedding using CBOW produces better than Skip-Gram, although it is still around 5%. However, CBOW slows slightly at the beginning of iteration but is stable towards convergence. Classification of all six classes, namely Equivalent, Similar, Specific, No Alignment, Related, and Opposite. As a result of the unbalanced data set, the retraining was conducted by eliminating a few classes member from the data set, thus providing an accuracy of 73 % for non-training data. The results showed that the Adam model gave a faster convergence at the start of training compared to the SGD model, and AdaDelta, which was built, gave 75% better accuracy with an F1-Score of 67%.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"36 1","pages":"150-155"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81431100","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 : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251872
Kurniabudi, A. Harris, Albertus Edward Mintaria, Darmawijoyo, D. Stiawan, Mohd Yazid Bin Idris, R. Budiarto
The feature selection techniques are used to find the most important and relevant features in a dataset. Therefore, in this study feature selection technique was used to improve the performance of Anomaly Detection. Many feature selection techniques have been developed and implemented on the NSL-KDD dataset. However, with the rapid growth of traffic on a network where more applications, devices, and protocols participate, the traffic data is complex and heterogeneous contribute to security issues. This makes the NSL-KDD dataset no longer reliable for it. The detection model must also be able to recognize the type of novel attack on complex network datasets. So, a robust analysis technique for a more complex and larger dataset is required, to overcome the increase of security issues in a big data network. This study proposes particle swarm optimization (PSO) Search methods as a feature selection method. As contribute to feature analysis knowledge, In the experiment a combination of particle swarm optimization (PSO) Search methods with other search methods are examined. To overcome the limitation NSL-KDD dataset, in the experiments the CICIDS2017 dataset used. To validate the selected features from the proposed technique J48 classification algorithm used in this study. The detection performance of the combination PSO Search method with J48 examined and compare with other feature selection and previous study. The proposed technique successfully finds the important features of the dataset, which improve detection performance with 99.89% accuracy. Compared with the previous study the proposed technique has better accuracy, TPR, and FPR.
{"title":"Improving the Anomaly Detection by Combining PSO Search Methods and J48 Algorithm","authors":"Kurniabudi, A. Harris, Albertus Edward Mintaria, Darmawijoyo, D. Stiawan, Mohd Yazid Bin Idris, R. Budiarto","doi":"10.23919/EECSI50503.2020.9251872","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251872","url":null,"abstract":"The feature selection techniques are used to find the most important and relevant features in a dataset. Therefore, in this study feature selection technique was used to improve the performance of Anomaly Detection. Many feature selection techniques have been developed and implemented on the NSL-KDD dataset. However, with the rapid growth of traffic on a network where more applications, devices, and protocols participate, the traffic data is complex and heterogeneous contribute to security issues. This makes the NSL-KDD dataset no longer reliable for it. The detection model must also be able to recognize the type of novel attack on complex network datasets. So, a robust analysis technique for a more complex and larger dataset is required, to overcome the increase of security issues in a big data network. This study proposes particle swarm optimization (PSO) Search methods as a feature selection method. As contribute to feature analysis knowledge, In the experiment a combination of particle swarm optimization (PSO) Search methods with other search methods are examined. To overcome the limitation NSL-KDD dataset, in the experiments the CICIDS2017 dataset used. To validate the selected features from the proposed technique J48 classification algorithm used in this study. The detection performance of the combination PSO Search method with J48 examined and compare with other feature selection and previous study. The proposed technique successfully finds the important features of the dataset, which improve detection performance with 99.89% accuracy. Compared with the previous study the proposed technique has better accuracy, TPR, and FPR.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"44 1","pages":"119-126"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73389994","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：