http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Comparative Study of Phishing Websites Classification Based on Classifier Ensembles
Bayu Adhi Tama,이경현 한국멀티미디어학회 2018 멀티미디어학회논문지 Vol.21 No.5
Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.
A Detailed Analysis of Classifier Ensembles for Intrusion Detection in Wireless Network
Bayu Adhi Tama,이경현 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.5
Intrusion detection systems (IDSs) are crucial in this overwhelming increase of attacks on the computinginfrastructure. It intelligently detects malicious and predicts future attack patterns based on the classificationanalysis using machine learning and data mining techniques. This paper is devoted to thoroughly evaluateclassifier ensembles for IDSs in IEEE 802.11 wireless network. Two ensemble techniques, i.e. voting andstacking are employed to combine the three base classifiers, i.e. decision tree (DT), random forest (RF), andsupport vector machine (SVM). We use area under ROC curve (AUC) value as a performance metric. Finally,we conduct two statistical significance tests to evaluate the performance differences among classifiers.
Bayu Adhi Tama,김도현,김규원,김수환,이승철 대한이비인후과학회 2020 Clinical and Experimental Otorhinolaryngology Vol.13 No.4
This study presents an up-to-date survey of the use of artificial intelligence (AI) in the field of otorhinolaryngology, considering opportunities, research challenges, and research directions. We searched PubMed, the Cochrane Central Register of Controlled Trials, Embase, and the Web of Science. We initially retrieved 458 articles. The exclusion of non-English publications and duplicates yielded a total of 90 remaining studies. These 90 studies were divided into those analyzing medical images, voice, medical devices, and clinical diagnoses and treatments. Most studies (42.2%, 38/90) used AI for image-based analysis, followed by clinical diagnoses and treatments (24 studies). Each of the remaining two subcategories included 14 studies. Machine learning and deep learning have been extensively applied in the field of otorhinolaryngology. However, the performance of AI models varies and research challenges remain.
Learning to Prevent Inactive Student of Indonesia Open University
( Bayu Adhi Tama ) 한국정보처리학회 2015 Journal of information processing systems Vol.11 No.2
The inactive student rate is becoming a major problem in most open universities worldwide. In Indonesia, roughly 36% of students were found to be inactive, in 2005. Data mining had been successfully employed to solve problems in many domains, such as for educational purposes. We are proposing a method for preventing inactive students by mining knowledge from student record systems with several state of the art ensemble methods, such as Bagging, AdaBoost, Random Subspace, Random Forest, and Rotation Forest. The most influential attributes, as well as demographic attributes (marital status and employment), were successfully obtained which were affecting student of being inactive. The complexity and accuracy of classification techniques were also compared and the experimental results show that Rotation Forest, with decision tree as the base-classifier, denotes the best performance compared to other classifiers.
Bayu Aji Aritejo,Widya Paramita,Sahid Susilo Nugroho 글로벌지식마케팅경영학회 2023 Global Marketing Conference Vol.2023 No.07
Although influencers establish their reputation and gain popularity by demonstrating expertise toward a specific topic, there is a huge potential to extend their market by tapping into different topics. Specifically, by promoting different types of product categories. However, previous studies tend to have different predictions about the success of this practice. Such that, according to the match-up hypothesis, it is unlikely that the influencer can successfully promote different product categories. On the other hand, Stereotype Content Model (SCM) suggests that influencers might be perceived as competence that overgeneralized to other domains. By conducting a survey to 302 online consumers in Indonesia, this study aims to test two competing routes toward influencer’s success in promoting product categories other than their initial expertise within the fashion context. The findings of this study revealed the primacy of match-up hypotheses, even when the influencers are perceived as competent, it does not mean that consumers are willing to follow their recommendation if it is outside their expertise domain. Only when there is an influencer-product fit, consumers are willing to accept their recommendation. However, perceived competence of the influencers can promote acceptance to follow recommendation on different product categories only when it established trust on the influencer.
( Bayu Dwi Apri Nugroho ),( Chusnul Arif ) 한국농업기계학회 2018 한국농업기계학회 학술발표논문집 Vol.23 No.1
Although there have been many studies in system of rice intensification, but a little evidence in relationships with field monitoring system in Indonesia, especially in East Nusa Tenggara Province. East Nusa Tenggara (NTT) Province, a province with consists many islands, typical monsoon climate with low annual rainfall. The aim of this study is using Field Monitoring System (FMS) as an adaptation strategy of system of rice intensification (SRI) cultivation against regional climate change. For this study, field monitoring system was set up in the SRI and conventional field since 26 July 2016 in Kupang, NTT Province that is consisted of three main components, i.e., FieldRouter, Datalogger and the sensors. Here, there are several sensors that have been installed in the field, e.g., solar radiation, rain-gauge and soil moisture. In one planting season, we tried cultivated SRI and conventional rice farming. As the results, the IT field monitoring system showed good performance and reliable for adaptive climate change rice farming with SRI in East Nusa Tenggara. The actual field conditions were monitored well in term of image, numeric, and graphical data acquisition. Based on monitored data, plant growth can be well monitored. In addition, dynamic changes of environmental parameters can be monitored as well. Based on those data, we found that SRI rice farming was more efficient in water use than that conventional rice farming. The water use can be saved up to 12%. SRI also increased water and land productivities respectively were 5.12% and 16.36%. This results proven that SRI can be alternative rice farming that more adaptive to climate change.
Learning to Prevent Inactive Student of Indonesia Open University
Tama, Bayu Adhi Korea Information Processing Society 2015 Journal of information processing systems Vol.11 No.2
The inactive student rate is becoming a major problem in most open universities worldwide. In Indonesia, roughly 36% of students were found to be inactive, in 2005. Data mining had been successfully employed to solve problems in many domains, such as for educational purposes. We are proposing a method for preventing inactive students by mining knowledge from student record systems with several state of the art ensemble methods, such as Bagging, AdaBoost, Random Subspace, Random Forest, and Rotation Forest. The most influential attributes, as well as demographic attributes (marital status and employment), were successfully obtained which were affecting student of being inactive. The complexity and accuracy of classification techniques were also compared and the experimental results show that Rotation Forest, with decision tree as the base-classifier, denotes the best performance compared to other classifiers.
Surgical Perspective of T1799A BRAF Mutation Diagnostic Value in Papillary Thyroid Carcinoma
Brahma, Bayu,Yulian, Erwin Danil,Ramli, Muchlis,Setianingsih, Iswari,Gautama, Walta,Brahma, Putri,Sastroasmoro, Sudigdo,Harimurti, Kuntjoro Asian Pacific Journal of Cancer Prevention 2013 Asian Pacific journal of cancer prevention Vol.14 No.1
Background: Throughout Indonesia, thyroid cancer is one of the ten commonest malignancies, with papillary thyroid carcinoma (PTC) in our hospital accounting for about 60% of all thyroid nodules. Although fine needle aspiration biopsy (FNAB) is the most reliable diagnostic tool, some nodules are diagnosed as indeterminate and second surgery is common for PTC. The aim of this study was to establish the diagnostic value and feasibility of testing the BRAF T1799A mutation on FNA specimens for improving PTC diagnosis. Materials and Methods: This prospective study enrolled 95 patients with thyroid nodules and future surgery planned. Results of mutational status were compared with surgical pathology diagnosis. Results: Of the 70 cases included in the final analysis, 62.8% were PTC and the prevalence of BRAF mutation was 38.6%. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for BRAF mutation analysis were 36%, 100%, 100% and 48%, respectively. With other data findings, nodules with "onset less than 5 year" and "hard consistency" were proven as diagnostic determinants for BRAF mutation with a probability of 62.5%. This mutation was also a significant risk factor for extra-capsular extension. Conclusions: Molecular analysis of the BRAF T1799A mutation in FNAB specimens has high specificity and positive predictive value for PTC. It could be used in the selective patients with clinical characteristics to facilitate PTC diagnosis and for guidance regarding extent of thyroidectomy.