{"title":"Visually Similar Handwritten Chinese Character Recognition with Convolutional Neural Network","authors":"Wei Liu, Kian Ming Lim, C. Lee","doi":"10.1109/ICoICT52021.2021.9527449","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527449","url":null,"abstract":"Computer vision has penetrated many domains, for instance, security, sports, health and medicine, agriculture, transportation, manufacturing, retail, and so like. One of the computer vision tasks is character recognition. In this work, a visually similar handwritten Chinese character dataset is collected. Subsequently, an enhanced convolutional neural network is proposed for the recognition of visually similar handwritten Chinese characters. The convolutional neural network is enhanced by the dropout regularization and early stopping mechanism to reduce the overfitting problem. The Adam optimizer is also leveraged to accelerate and optimize the training process of the convolutional neural network. The empirical results demonstrate that the enhanced convolutional neural network achieves a 97% accuracy, thus corroborate it has better discriminating power in visually similar handwritten Chinese character recognition.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129626768","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}
{"title":"Aspect Term Extraction Using Deep Learning-Based Approach on Indonesian Restaurant Reviews","authors":"Rachmansyah Adhi Widhianto, A. Romadhony","doi":"10.1109/ICoICT52021.2021.9527472","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527472","url":null,"abstract":"Aspect term extraction is a fundamental process in aspect-based sentiment analysis. Aspect term extraction aims to identify the review text span that contains the aspect mentions. In this paper, we present our work on aspect term extraction for Indonesian restaurant reviews, using a deep learning-based approach. We collected and annotated an Indonesian restaurant reviews dataset, obtained from a restaurant review website. We performed the annotation at a token-level and used the following aspect labels to annotate the reviews: FOOD, PRICE, AMBIENCE, SERVICE, and MISCELLANEOUS. This paper treats aspect extraction as a token-level classification. We employed a Convolutional Neural Network (CNN) model and Long Short-Term Memory (LSTM) model for the classification. The experimental result showed that the LSTM method gives the best performance, with the micro average F1-score is 55,1%.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126263051","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}
{"title":"FN-Net: A Deep Convolutional Neural Network for Fake News Detection","authors":"Kian Long Tan, Chin Poo Lee, K. Lim","doi":"10.1109/ICoICT52021.2021.9527500","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527500","url":null,"abstract":"Information and communication technology has evolved rapidly over the past decades, with a substantial development being the emergence of social media. It is the new norm that people share their information instantly and massively through social media platforms. The downside of this is that fake news also spread more rapidly and diffuse deeper than before. This has caused a devastating impact on people who are misled by fake news. In the interest of mitigating this problem, fake news detection is crucial to help people differentiate the authenticity of the news. In this research, an enhanced convolutional neural network (CNN) model, referred to as Fake News Net (FN-Net) is devised for fake news detection. The FN-Net consists of more pairs of convolution and max pooling layers to better encode the high-level features at different granularities. Besides that, two regularization techniques are incorporated into the FN-Net to address the overfitting problem. The gradient descent process of FN-Net is also accelerated by the Adam optimizer. The empirical studies on four datasets demonstrate that FN-Net outshines the original CNN model.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"282 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122950551","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}
{"title":"4G LTE Cellular Network Coverage Planning and Simulation on Mandalay Area with Propagation Model Cost-Hatta","authors":"A. Idris, S. Rahmatia, M. Ismail","doi":"10.1109/ICoICT52021.2021.9527455","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527455","url":null,"abstract":"Cellular networking technology is undeniably an expensive field, especially on the infrastructure side. To achieve maximum resource efficiency and effectiveness, a plan is needed. To estimate the most appropriate cell throughput, to decrease the number of equipment used, to answer the need for traffic analysis, and to get the most optimal capacity, network planning and simulation are required. Cellular Network Planning can be defined as a process that involves series of activities to determine a cost-effective and optimal network design plan.. This simulation was made for Mandalay region, located in Myanmar. With a total computational size zone of 656,198 km2, the aim is to have a better understanding of planning and doing a simulation on the said region. With Cost- Hatta model propagation, CVVPX310R1 antenna type, and E- UTRA Band 3 - 20MHz frequency band, 58 LTE transmitter are placed. After a simulation that consists of manual and automatic planning, several planning parameters: RSRP, RSRQ, SINR, best serving, and throughput are calculated. The results are then served to show the effects of plans made before. While this research might not be particularly special, author hoped that this might become helpful for those who come across similar research.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123348957","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}
{"title":"Sustainability And Aptness Of Game Elements In A Gamified Learning Environment","authors":"M. Sanmugam","doi":"10.1109/ICoICT52021.2021.9527499","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527499","url":null,"abstract":"Sustaining the interest level of students in any form of technology-based learning poses a significant challenge. Infusion of any tech-based elements into learning may not be sufficient for Generation-Z students, whose lives revolve around technology. Although gamification, game elements in non-gaming contexts are more comfortable being implemented by ordinary people with no tech-based knowledge. Nevertheless, in the context of learning, the sustainability of the game elements needs to be identified. Therefore, mixed-method research was conducted on 28 students aged 13 years old from an urban school in Malaysia for 14 weeks. The students were introduced to a gamified learning method that infused gamification elements in the traditional classroom and the online classroom. The game elements tested were points, badges, and leader boards. Students were taught two separate topics in the Malaysian Science syllabus using gamified learning to ensure the students' continuity effects. Upon completion, the game elements' final tally was assessed and supported by the interview feedback from the top 3 students from each game element. Based on the findings, gamified learning with game elements helped reduced boredom and using technology made learning fun. Although some respondents shared the fear of complacency of using games in learning, the mixed response was reported to the preferred type of game elements or type of learning that suits the game elements.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115543873","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}
Ryandy Djap, Charles Lim, Kalpin Erlangga Silaen, Andi Yusuf
{"title":"XB-Pot: Revealing Honeypot-based Attacker’s Behaviors","authors":"Ryandy Djap, Charles Lim, Kalpin Erlangga Silaen, Andi Yusuf","doi":"10.1109/ICoICT52021.2021.9527422","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527422","url":null,"abstract":"Since its introduction, the honeypot has been used by researchers to track and learn the cyber attack into organization infrastructures. With the continuous rise of cyberattacks, deception technology, i.e., honeypot, has been eyed by organizations as a prominent tool to provide early detection of attack capability and defense mechanism after learning from the interaction between the attacker and the tool. In this research, a new enhanced framework is introduced to categorize attacker behaviors detected through our honeypots. The framework provides a finer-grained result allowing representation of the actual attacker behaviors as he/she interacts with the honeypot. Complete threat categories both on high-volume and low-volume attack traffic are presented.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116022672","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}
{"title":"Tone Detection System Design for Targets with Frequency Drift","authors":"B. Comar","doi":"10.1109/ICoICT52021.2021.9527412","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527412","url":null,"abstract":"In this study, 3 methods of tone detection are investigated, the non-coherent averaging method, the power spectral method, and the cross-power spectral method. The target tones are simulated with frequency drift. Analysis is performed to find optimal FFT sizes and number of spectra to average. PD vs. PFA curves are then created and used to compare these methods. This analysis is particularly useful when using high sampling rate detectors to find tones produced with lower quality oscillators that experience frequency drift since using FFTs that are too large or averaging too many spectra may actually decrease detectability.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131258361","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}
{"title":"Comparative Analysis of Support Vector Machine (SVM) and Random Forest (RF) Classification for Cancer Detection using Microarray","authors":"Irawansyah, Adiwijaya, W. Astuti","doi":"10.1109/ICoICT52021.2021.9527458","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527458","url":null,"abstract":"Cancer is the second leading cause of death globally. According to the World Health Organization (WHO) in 2018, approximately 9.6 million deaths were caused by cancer. Globally, about 1 in 6 deaths are caused by cancer. One way to detect cancer is to use microarray data classification. Microarray technology is used to detect the expression of thousands of genes at the same time to analyze and diagnose cancer. However, microarray data have high dimensions because of its large features and low data distribution, which means that it has a small data samples, which causes low performance. To overcome this problem, dimension reduction is needed. Therefore, it is necessary to reduce the dimensions of microarray data with Random Projection (RP) to reduce the high dimensions and use the Support Vector Machine (SVM) and Random Forest (RF) as classification methods. The classification method will be compared and analyzed to determine which classification method produces the best performance by using Random Projection (RP) as a dimensional reduction method. Based on the system that has been built, the best accuracy for Colon Tumor is 69.23% with Random Projection (RP)-SVM, Lung Cancer is 100% for both methods classification, Ovarian Cancer is 100% for both methods classification, the prostate tumor is 95.12% for both methods classification and Central Nervous System is 66.66% for both methods classification.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123729522","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}
{"title":"Detection of Sinusoids with Frequency Drift in White Gaussian Noise","authors":"B. Comar","doi":"10.1109/ICoICT52021.2021.9527437","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527437","url":null,"abstract":"In this study, 4 methods of detecting sinusoid targets in white Gaussian noise are investigated. Averaging FFTs coherently and non-coherently is examined. A brute force method is introduced and investigated. Using a single large FFT spanning the observation window is also considered. Detection performance is studied on targets whose frequencies drift over time. It is determined that averaging non-coherent FFTs is a safe choice in a detection system. The preferred size of the FFT used for tone detection as well as the number of spectra to average is driven by the nature of the target tone frequency drift. This information is especially useful when high sample rate detectors are used to find tones from low quality transmitters because making FFTs too large or taking too many averages may hinder detection.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114800956","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}
Wishnu Dwi Herlambang, K. A. Laksitowening, I. Asror
{"title":"Prediction of Graduation with Naïve Bayes Algorithm and Principal Component Analysis (PCA) on Time Series Data","authors":"Wishnu Dwi Herlambang, K. A. Laksitowening, I. Asror","doi":"10.1109/ICoICT52021.2021.9527443","DOIUrl":"https://doi.org/10.1109/ICoICT52021.2021.9527443","url":null,"abstract":"The percentage of students who graduated on time can be predicted with data mining methods. This research aims to provide earlier information regarding students who are at risk of not graduating on time. Thus, the study program can take appropriate action before it is too late. Several classification methods can be used for prediction. Our research combines Naïve Bayes with Principal Component Analysis (PCA). PCA is used to simplify complex academic data. The PCA result has a more straightforward structure to be processed using Naive Bayes classification. This research uses four batches of student academic performance data in Informatics Study Program, Telkom University. The dataset is partitioned by academic year to obtain time-series data of each student. The combination of PCA and Naïve Bayes algorithms obtained better results than classification using Naïve Bayes only, with 6.04% higher accuracy on average.","PeriodicalId":191671,"journal":{"name":"2021 9th International Conference on Information and Communication Technology (ICoICT)","volume":"1021 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123120286","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}