检索结果-内蒙古大学图书馆

Text Normalization Algorithm on Twitter in Complaint Category

Procedia computer science 2017年 116卷 20-26页

作者： Novita Hanafiah Alexander Kevin Charles Sutanto Fiona Yulyani Arifin Jaka Hartanto Computer Science Department School of Computer Science Bina Nusantara University Jl. K.H Syahdan No.9 DKI Jakarta 11480 Indonesia

Many people use microblog to express complaint or criticism. However, the limitation of the length that can be written is about 160 characters and the text is in unstructured sentence. It becomes the biggest obstacle to process the information. Those unstructured sentences cause a difficulty for preprocessing in text processing tools. Therefore, normalization is needed to make the unstructured sentences can be more understandable by a machine. We proposed a normalization of Indonesian language method which adopting some ideas of normalization from other researchers and adjust to the problem of Indonesian characteristic in unstructured sentence. The experiment exploits Twitter data which use Indonesian language in complaint category. The process is divided into three stages, which are cleaning process, OOV detection and word replacement. List of Basic words and Slang dictionary are used in the OOV detection. On the other hand, Context dictionary is built to solve the ambiguity problem. The algorithm can reaches the accuracy about 90% in a complaint category.

关键词： normalization microbolog Indonesian language Twitter language processing

来源：评论

学校读者我要写书评

暂无评论

Service Desk Implementation with Information Technology Infrastructure Library Framework (Study Case Financial Company)

引用

Journal of Physics: Conference Series 2018年第1期1090卷

作者： Dwi Handoko Abba Suganda Girsang Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

This paper proposes a service desk to handle two important issues in financial company using the Information Technology Infrastructure Library (ITIL) Framework, i.e. Single Point of Contact (SPOC) and Service Level Agreement (SLA) issues. SPOC is a gateway to information needs of both users and company staff, particularly the IT staff, while SLA defines the responsibilities of the parties where such services work and provides coverage for services provided to the client to achieve client satisfaction. The service desk is built by focusing in service operation. A service desk has been successfully built in this study to make user's problem controllable. The result also shows that the user's problem can be solved faster in many cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Face recognition system Using Deep Neural Network with Convolutional Neural Networks

引用

Journal of Physics: Conference Series 2019年第1期1235卷

作者： Erick Fernando Denny Andwiyan Dina Fitria Murad Derist Touriano Muhamad Irsan Information System Department School of Information Systems Bina Nusantara University Indonesia Universitas Islam Syekh Yusup (UNIS) School of Information Technology Indonesia Information System Department Binus Online Learning Bina Nusantara University Indonesia Information Technology Department Faculty of computer science and engineering University of Adi Wangsa Indonesia

Face recognition has long been a hot topic and challenging research point in areas such as image processing, pattern recognition, and machine vision. The face is a biometric feature with the intrinsic nature of a human. So that the face has self-stability, deep individual differences and can be an ideal basis for verification of an identity. In this research use, Deep Learning Network method uses to perform detection or face recognition. In this study, we present a framework that can be used to detect faces. This research is also able to present a DNN model that is used to study data sources from the data stream in sequence. The most important part of this study is able to adjust the capacity of the model from the simple one. This research uses experimental design method. The first step is a collection of face image data. Then the architecture design starts from the determination of the depth of the network, layout layers, and the selection of layer types that will be used to get the model based on input dataset and label name index.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mobile Smart Travelling Application For Indonesia Tourism

引用

Procedia computer science 2017年 116卷 556-563页

作者： Meiliana Devita Irmanti Mochamad Rizal Hidayat Nur Viani Amalina Dewi Suryani Computer Science Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 DKI Jakarta 11480 Indonesia

Indonesia is a country that has seventeen thousand islands and located in a very strategic location. That reason makes Indonesia becoming a place that is interesting to be visited by many tourists either local or international. Every year the number of tourists who visited Indonesia has greatly increased 1,2 and transformed the tourism to be an important sector for Indonesia economical. The rapid development of tourism sector in Indonesia must be equilibrated by the evolution of technology and the supported facilities. Now, the usage of a smartphone technology is one of the important things and a part of modern people daily activities. By taking the advantages of a smartphone, this study is conducted to develop an android application that is named Smart Travelling. Smart travelling has many features that can facilitate every tourist who visited Indonesia, such as recognizes any tourist attractions, shows any events that nearby visited attractions, displays the nearest police station and hospital for an emergency case, and saves the history of the recognized objects. The main idea of the tourist attractions recognition here is to implement an image recognition using landmark detection feature from Google Cloud Vision Application program Interface (API) 3 technology which helps the tourist to easily remember and access any information regarding the visited attractions. In this study, the result is a completed application which is evaluated using questionnaires to 35 randomly selected participants. Based on the evaluation, the smart travelling achieves positive inputs and mostly the participants agree that the image recognition feature is really helping them. Furthermore, we also obtained a significant result for the scan landmark testing, which is 86% for the accuracy.

关键词： Image Recognition Android application Google Cloud Vision Tourism

来源：评论

学校读者我要写书评

暂无评论

Offline Signature Recognition and Verification System using Efficient Fuzzy Kohonen Clustering Network (EFKCN) Algorithm

引用

Procedia computer science 2017年 116卷 621-628页

作者： Dewi Suryani Edy Irwansyah Ricki Chindra Computer Science Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 DKI Jakarta 11480 Indonesia

Research on offline signature recognition still has not shown satisfactory results as the results of recent research. Therefore this study aims to proposed an offline signature recognition and verification system which employed an efficient fuzzy Kohonen clustering networks (EFKCN) 1 algorithm. The proposed recognition system and signature verification system consist of five stages including data acquisition, image processing, data normalization, clustering, and evaluation. The recognition of signature patterns using the clustering method with the EFKCN algorithm shows relatively better result with 70% accuracy compared to the accuracy of previous research results 2 which is 53%, and a good signature recognition result can be developed to assist the verification system as well as the personal data verification system as made in this study.

关键词： Signature Recognition Verification System EFKCN

来源：评论

学校读者我要写书评

暂无评论

Overcome Acrophobia with the Help of Virtual Reality and Kinect Technology

引用

Procedia computer science 2017年 116卷 476-483页

作者： Erick Marchelino Suyanto Denny Angkasa Harfondy Turaga Rhio Sutoyo Computer Science Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 Kemanggisan Jakarta 11480 Indonesia

There are many people in this world who are feared of high places. In general, there are two types of people: the prior one is people that are afraid of height and the latter one is people who really cannot handle high places (i.e. acrophobia). The purpose of this research is to reduce acrophobia level of people. The methodology which is used in this research is experiment with the help of virtual reality to simulate virtual world of high places environment as the reality in the imagination of the user. The virtual environment helps the sufferer to reduce their fear of height in a safe and controllable environment. This research shows that virtual reality is able to mimic real high places and train the users to overcome their anxiety of high places. With virtual world, the users are able to confront their fear gradually based on the level progression in the virtual world. Thus, it gives the users more experience to handle their fear in the secured environment and gradually decrease their anxiety level of acrophobia.

关键词： virtual reality kinect acrophobia afraid of height anxiety

来源：评论

学校读者我要写书评

暂无评论

Personality Prediction System from Facebook Users

引用

Procedia computer science 2017年 116卷 604-611页

作者： Tommy Tandera Hendro Derwin Suhartono Rini Wongso Yen Lina Prasetio Computer Science Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 Kemanggisan Jakarta 11480 Indonesia

The use of social networks is increasing rapidly. Various informations are shared widely through social media, i.e. Facebook. Information about users and what they expressed through status updates are such important assets for research in the field of behavioral learning and human personality. Similar researches have been conducted in this field and it grows continually till now. This study attempts to build a system that can predict a person’s personality based on Facebook user information. Personality model used in this research is Big Five Model Personality. While other previous researches used older machine learning algorithm in building their models, this research tries to implement some deep learning architectures to see the comparison by doing comprehensive analysis method through the accuracy result. The results succeeded to outperform the accuracy of previous similar research with the average accuracy of 74.17%.

关键词： personality prediction big five model personality facebook machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Development Game Chinese Language Learning with Gamification and Using Mnemonic Method

引用

Procedia computer science 2017年 116卷 61-67页

作者： Dicky Rawendy Yi Ying Yulyani Arifin Kelly Rosalin Game Application Technology Department School of Computer Science Bina Nusantara University Jl. K.H. Syahdan No. 9 Palmerah Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jl. K.H. Syahdan No. 9 Palmerah Jakarta 11480 Indonesia

In globalization era, many people interested to learn Chinese language. It caused by potential of China’s economic growth in the world. Chinese language has introduced to children in early age in Indonesia. But sometimes learn Chinese language was difficult to them, which will make them feel boring. This paper has purpose to help children learn Chinese language using gamification and mnemonic method into game content. Briefly, gamification is process that adopt game elements to apply into non-game context and mnemonic is strategy to increase memory with various ways. Both in gamification and mnemonic method have applied in previous paper which the conclusion showed positive result in learning environment. This game refers to primary school, which students in 6-12 years old. The conclusion in this paper show that the developed game by authors can interest children to learn Chinese language based by pre-test and post-test result.

关键词： Chinese Language Game Gamification Mobile Learning Mnemonic

来源：评论

学校读者我要写书评

暂无评论

It Takes Two To Tango: Modification of Siamese Long Short Term Memory Network with Attention Mechanism in Recognizing Argumentative Relations in Persuasive Essay

引用

Procedia computer science 2017年 116卷 449-459页

作者： Aryo Pradipta Gema Suhendro Winton Theodorus David Derwin Suhartono Muhsin Shodiq Wikaria Gazali Computer Science Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 Kemanggisan Jakarta 11480 Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jl. K. H. Syahdan No. 9 Kemanggisan Jakarta 11480 Indonesia

We propose a novel approach in a dataset of argumentation relations. This task is intended to analyze the presence of a support relation between two sentences. To be able to identify relations between two sentences or arguments, one is obliged to understand the nuance brought by both sentences. Our models are modification of siamese network architectures, in which we replace the feature extractor into Long Short Term Memory and implement cosine distance as the energy function. Our models take a pair of sentences as their input and try to identify whether there is a support relation between those two sentences or *** primary motivation of this research is to prove that a high degree of similarity between two sentences correlates to sentences supporting each other. This work will focus more on the modification of siamese network and the implementation of attention mechanism. Due to the difference in dataset setting, we cannot arbitrarily compare our results with the prior research results. Therefore, this work will not highlight the comparison between deep learning and traditional machine learning algorithm per se, but it will be more of an exploratory research. Our models are able to outperform the baseline score of accuracy with a margin of 17.33% (67.33%). By surpassing the baseline performance, we believe that our work can be a stepping stone for deep learning implementation in argumentation mining field.

关键词： Siamese Network Long Short Term Memory Attention Mechanism GloVe Cosine Distance

来源：评论

学校读者我要写书评

暂无评论

Automated Test Case Generation from UML Activity Diagram and Sequence Diagram using Depth First Search Algorithm

引用

Procedia computer science 2017年 116卷 629-637页

作者： Meiliana Irwandhi Septian Ricky Setiawan Alianto Daniel Ford Lumban Gaol Computer Science Department School of Computer Science - Bina Nusantara University Jl. K. H. Syahdan No. 9 DKI Jakarta 11480 Indonesia Doctor of Computer Science – Bina Nusantara University Jl. Kebon Jeruk Raya No.27 DKI Jakarta 11530 Indonesia

Software testing is an important and critical activity in software development that deals with software quality. However, the testing process is consuming activities that need to be automated to save a lot of resources. Towards automated testing, automating test cases generation as the first testing process is being highlighted. This research aims to generate test case automatically from UML diagram since model based testing that conducted on early phase of software development process show higher efficiency. UML diagrams used in this research are activity diagram, sequence diagram and SYTG as the combination graph. These three diagrams have been proved as the most compatible diagram to generate test case from previous research. Method proposed in this paper is Depth First Search algorithm that is modified to generate expected test cases. This paper proves that modified DFS algorithm applied to generate test case is provide accurate result, every node presented on the test case, include any condition (alt and opt). Comparison result from three different test cases generated shows that test cases from combined UML may not necessarily result in better test cases, due to the possibility of redundant test cases for some test cases. This paper also presenting an experiment result that proving sequence diagrams can produce better test cases.

关键词： test cases depth first search algorithm UML diagram software testing test cases generator

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：