http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 마렌드라 (검색결과 6 건)
- 무료
- 기관 내 무료
- 유료
-
Predicting Employment Earning using Deep Convolutional Neural Networks
마렌드라,김나랑,최형림,Ramadhani, Adyan Marendra,Kim, Na-Rang,Choi, Hyung-Rim The Society of Digital Policy and Management 2018 디지털융복합연구 Vol.16 No.6
소득은 경제생활에서 중요하다. 소득을 예측할 수 있으면, 사람들은 음식, 집세와 같은 생활비를 지불 할 수 있는 예산을 세울 수 있을 뿐 아니라, 다른 재화 또는 비상사태를 위한 돈을 별도로 저축 할 수 있다. 또한 소득수준은 은행, 상점 및 서비스 회사에서 마케팅 목적 및 충성도가 높은 고객을 유치하는 데 활용 된다. 이는 소득이 다양한 고객 접점에서 사용되는 중요한 인구 통계 요소이기 때문이다. 따라서 기존 고객 및 잠재 고객에 대한 수입 예측이 필요하다. 이 연구에서는 소득을 예측하기 위해 SVM (Support Vector Machines), Gaussian, 의사 결정 트리, DCNN (Deep Convolutional Neural Networks)과 같은 기계 학습 기법을 사용하였다. 분석 결과 DCNN 방법이 본 연구에서 사용 된 다른 기계 학습 기법에 비해 최적의 결과(88%)를 제공하는 것으로 나타났다. 향후 PCA 같이 데이터 크기를 향상 시킨다면 더 좋은 연구 결과를 제시할 수 있을 것이다. Income is a vital aspect of economic life. Knowing what their income will help people create budgets that allow them to pay for their living expenses. Income data is used by banks, stores, and service companies for marketing purposes and for retaining loyal customers; it is a crucial demographic element used at a wide variety of customer touch points. Therefore, it is essential to be able to make income predictions for existing and potential customers. This paper aims to predict employment earnings or income based on history, and uses machine learning techniques such as SVMs (Support Vector Machines), Gaussian, decision tree and DCNNs (Deep Convolutional Neural Networks) for predicting employment earnings. The results show that the DCNN method provides optimum results with 88% compared to other machine learning techniques used in this paper. Improvement of the data length such PCA has the potential to provide more optimum result.
-
Korean and English Sentiment Analysis Using the Deep Learning
마렌드라,최형림,임성배,Ramadhani, Adyan Marendra,Choi, Hyung Rim,Lim, Seong Bae Korea Society of Industrial Information Systems 2018 한국산업정보학회논문지 Vol.23 No.3
Social media has immense popularity among all services today. Data from social network services (SNSs) can be used for various objectives, such as text prediction or sentiment analysis. There is a great deal of Korean and English data on social media that can be used for sentiment analysis, but handling such huge amounts of unstructured data presents a difficult task. Machine learning is needed to handle such huge amounts of data. This research focuses on predicting Korean and English sentiment using deep forward neural network with a deep learning architecture and compares it with other methods, such as LDA MLP and GENSIM, using logistic regression. The research findings indicate an approximately 75% accuracy rate when predicting sentiments using DNN, with a latent Dirichelet allocation (LDA) prediction accuracy rate of approximately 81%, with the corpus being approximately 64% accurate between English and Korean.
-
A Study on the Conceptual Model of an E-Voting System based on Blockchain
마렌드라,홍순구,김나랑,유승의 한국인터넷전자상거래학회 2019 인터넷전자상거래연구 Vol.19 No.2
Voting is an activity that involves choosing a preferred candidate in an election. There are several potential problems in the voting process, including cheating and security failures. The development of a secure electronic voting system that offers the fairness and privacy of existing voting schemes while simultaneously providing the transparency and flexibility offered by electronic systems has been a challenge for some time. To prevent problems in the voting process, we propose a robust technique that includes blockchain and machine learning. Blockchain employs a technique and concept similar to that used by digital currencies to secure transactions. Blockchain voter data is then used to predict votes based on past votes using a machine learning method. The purpose of this research was to provide a conceptual model for an e-voting system based on blockchain technology and machine learning(support vector machines, Gaussian Naive Bayes, and decision trees) to predict votes and provide vote security. The machine learning techniques used in this study predicted votes based on previous voter data with an average of 98% accuracy, while the blockchain improved and tightened e-voting system security using private networks and structures. This study contributes to the literature on e-voting by proposing improvements to vote security and prediction by combining blockchain technology and machine learning techniques. Its primary limitation is that this method has only been replicated on small-scale networks, such as school networks.
-
Bitcoin Price Forecasting Using Neural Decomposition and Deep Learning
Adyan Marendra Ramadhani(마렌드라),Kim Na Rang(김나랑),Lee Tai Hun(이태헌),Ryu Seung Eui(유승의) 한국산업정보학회 2018 한국산업정보학회논문지 Vol.23 No.4
Bitcoin is a cryptographic digital currency and has been given a significant amount of attention in literature since it was first introduced by Satoshi Nakamoto in 2009. It has become an outstanding digital currency with a current market capitalization of approximately $60 billion. By 2019, it is expected to have over 5 million users. Nowadays, investing in Bitcoin is popular, and along with the advantages and disadvantages of Bitcoin, learning how to forecast is important for investors in their decision-making so that they are able to anticipate problems and earn a profit. However, most investors are reluctant to invest in bitcoin because it often fluctuates and is unpredictable, which may cost a lot of money. In this paper, we focus on solving the Bitcoin forecasting prediction problem based on deep learning structures and neural decomposition. First, we propose a deep learning-based framework for the bitcoin forecasting problem with deep feed forward neural network. Forecasting is a time-dependent data type; thus, to extract the information from the data requires decomposition as the feature extraction technique. Based on the results of the experiment, the use of neural decomposition and deep neural networks allows for accurate predictions of around 89%.
-
Korean and English Sentiment Analysis Using the Deep Learning
Adyan Marendra Ramadhani(마렌드라),Hyung Rim Choi(최형림),Seong Bae Lim(임성배) 한국산업정보학회 2018 한국산업정보학회논문지 Vol.23 No.3
Social media has immense popularity among all services today. Data from social network services (SNSs) can be used for various objectives, such as text prediction or sentiment analysis. There is a great deal of Korean and English data on social media that can be used for sentiment analysis, but handling such huge amounts of unstructured data presents a difficult task. Machine learning is needed to handle such huge amounts of data. This research focuses on predicting Korean and English sentiment using deep forward neural network with a deep learning architecture and compares it with other methods, such as LDA MLP and GENSIM, using logistic regression. The research findings indicate an approximately 75% accuracy rate when predicting sentiments using DNN, with a latent Dirichelet allocation (LDA) prediction accuracy rate of approximately 81%, with the corpus being approximately 64% accurate between English and Korean.
-
CNN과 Bidirectional LSTM을 활용한 부산시 민원 자동 분류 연구
김나랑,마렌드라 라마다니 한국전산회계학회 2019 電算會計硏究 Vol.17 No.2
온라인과 정보통신기술의 발달로 정부정책에 대한 시민의 참여 욕구는 높아지고 있다. 이에 따라 시민들은 민원을 인터넷과 모바일을 활용하여 전자 민원 게시판을 통해 접수하는 건수가 증가하고 있다. 폭발적으로 늘어나는 민원의 양에 비해 아직 수작업으로 분류 하여 오류가 발생하거나 신속한 대응이 이루어지지 않아 민원인들의 불만이 늘어나고 있다. 본 연구에서는 딥러닝 기법을 통해 담당 부서 분류를 자동화하기 위해 2017년도의 부산시 민원 데이터를 수집하고, 담당 부서를 확인 할 수 있는 부서명, 전화번호, 담당자명을 기준으로 레이블을 부여하였다. 그리고 딥러닝 중 대표적인 분류방법인 CNN과 최근 여러 분야에서 두각을 내고 있는 Bidirectional LSTM을 기반으로 상위 12개 범주에 대하여 지도학습을 실시하였다. 지도학습 결과 각각 73%, 77%의 정확도를 보여 안정적인 성능을 보여주었다. 본 연구의 민원 분류에 대한 지도학습 사례는 향후 다른 주제 및 지방자치단체 민원에 대한 텍스트 데이터의 분류에 이용될 수 있어 실무적인 공헌도와 함께 후속연구를 유발할 수 있다는 학문적 기여도가 있다.
ScienceON
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
