检索结果-内蒙古大学图书馆

Social Media Web Scraping using Social Media Developers API and Regex

Procedia computer science 2019年 157卷 444-449页

作者： Lusiana Citra Dewi Meiliana Alvin Chandra Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Nowadays many information can be easily accessed through the internet. Some of social media web applications, such as Facebook, Twitter and Instagram, even provide user with an easy information sharing features. However, the information is presented in the form of a timeline or a feed, which is sometimes not relevant to the user or quite hard to accessed by user because of the redundancy of the information. This situation can be resolved with a Web Scraping method proposed in this paper, that able to search information, combine and present it in a better way according to user preferences. A system is developed to implement the proposed method by using an API that Facebook Developers and Twitter Developers provided. In addition, regular expression (or Regex) which is a language construction that can be used for matching text by using some patterns. Based on experiment conducted in this research, overload information could be suppressed into structure data that store in a database, less redundancy information is presented, and information relevancy could be adjusted to user preferences.

关键词： Web Scraping Regex Facebook Developers API Twitter Developers API Social Media

来源：评论

学校读者我要写书评

暂无评论

Increase The Interest In Learning By Implementing Augmented Reality: Case studies studying rail transportation.

引用

Procedia computer science 2019年 157卷 506-513页

作者： Hady Pranoto Francisco Maruli Panggabean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Learn a subject, for some people, might be an uninteresting and boring activity, especially when the subject to learn are difficult subjects to understand. Many methods used to change learning activities become more enjoyable and interested. This study proposed a new method in learning activities, by applied augmented reality technology in the learning process. The case study used in this paper are implementation the augmented reality in studied subjects related to train technology. In this study, author implement augmented reality on learning material, combines real and virtual things in one media, in this case a mobile device. The impact of implementation of augmented studied, at the end of experiment, author can conclude when implement augmented reality technology in learning material helps the learning process and increasing the impressive and fun factor in learning process and make the learning process more interested. Implementation of Augmented Reality in learning material gives more information about the object being studied, information about on shapes, textures, and provide more visualization for the object.

关键词： Augmented Reality learning method rail transportation

来源：评论

学校读者我要写书评

暂无评论

Mobile Financial Management Application using Google Cloud Vision API

引用

Procedia computer science 2019年 157卷 596-604页

作者： Kurniawan Dwi Saputra Della Anggi Rahmaastri Karina Setiawan Dewi Suryani Yudy Purnama Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Money is the main potential conflict in every individual life. Inability to understand financial concepts and risks may lead to wrong decision making then further worsen someone’s financial condition. Therefore financial literacy became significant knowledge to have. This financial literacy should be supported by some mechanism to record, monitor, and control an individual financial activity. This study observed the potential value of an mobile-based application “Manage on Money (MoM)” to solve those problem. MoM has three main features for each of those problems. First, “Add Income” and “Add Expense” menu, which is implemented using Google Vision Cloud API Optical Character Recognition (OCR). This menu helps the user record their income and expenses. Second, “Buy or Bye” menu, which is utilizing 50/20/30 budgetting rule. This menu helps the user control their budget usage. Third, “Recurring Transaction” menu, which is implemented using OneSignal API. This menu helps the user monitor their regularly expense and notify them during the due date. Overall score of over than 3 out of 4 was given by the respondent as evaluation of Manage on Money performances and usefulness.

关键词： Financial Mobile Android Google Vision Cloud API Optical Character Recognition 50/20/30 Rule Notification OneSignal API

来源：评论

学校读者我要写书评

暂无评论

Implementation of Optical Character Recognition using Tesseract with the Javanese Script Target in Android Application

引用

Procedia computer science 2019年 157卷 499-505页

作者： G. Abdul Robby Antonia Tandra Imelda Susanto Jeklin Harefa Andry Chowanda Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Recognising characters from text have been a popular topic in the computer vision area. The application can benefit to many problems in the world. For example: recognising text in documents, classifying the text or scripts of documents, plate recognition, etc. Many researchers have been developed the methods for recognising characters in by using Optical Character Recognition methods. Although text recognition problem using Optical Character Recognition has been more or less solved, most of the Optical Character Recognition problem explored is belong to Latin alphabet texts. Meanwhile, there are several languages have non-Latin scripts as the written text. Recognising a non-Latin script is quite challenging as the contour and shape of the text are relatively different with a Latin script text. This research aims to collect datasets for OCR in Javanese characters. A total of 5880 characters were collected and trained with several methods with Tesseract OCR tools. The models then be implemented to a mobile phone (Android based). The highest accuracy (97,50%) achieved by the model was achieved by combining single boundary box for the whole parts of the character and the separate boundary boxes in main body and sandangan parts.

关键词： OCR Non-Latin Script Javanese Script Tesseract Android

来源：评论

学校读者我要写书评

暂无评论

Music Recommender System Based on Genre using Convolutional Recurrent Neural Networks

引用

Procedia computer science 2019年 157卷 99-109页

作者： Adiyansjah Alexander A S Gunawan Derwin Suhartono Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

With commercial music streaming service which can be accessed from mobile devices, the availability of digital music currently is abundant compared to previous era. Sorting out all this digital music is a very time-consuming and causes information fatigue. Therefore, it is very useful to develop a music recommender system that can search in the music libraries automatically and suggest suitable songs to users. By using music recommender system, the music provider can predict and then offer the appropriate songs to their users based on the characteristics of the music that has been heard previously. Our research would like to develop a music recommender system that can give recommendations based on similarity of features on audio signal. This study uses convolutional recurrent neural network (CRNN) for feature extraction and similarity distance to look similarity between features. The results of this study indicate that users prefer recommendations that consider music genres compared to recommendations based solely on similarity.

关键词： Music Recommender System Convolutional Recurrent Neural Network Similarity Distance

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Visual Indonesian Place Classification with Convolutional Neural Networks

引用

Procedia computer science 2019年 157卷 436-443页

作者： Andry Chowanda Rhio Sutoyo Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Places classification is one of the points of discussion in the computer vision and robotics community. Some renowned techniques such as local-invariant feature extractors (e.g. Scale-invariant feature transform SIFT, Speeded Up Robust Features SURF), as well as Visual BoW approach were used in place classification problems. Nowadays, deep learning methods such as Convolutional Neural Networks (CNNs) have the advantages towards computer vision problems including place classification problem. Albeit, there are several renowned datasets existed to help the community to learn the models, there is no publicly exists in places dataset for specifically places in Indonesia. This paper presents methodology to collect data of visual places in Indonesia, learn deep features from the data, and classify visual places in Indonesia. We aims to contribute a large dataset as well as deep learning models of places in Indonesian. There are more than 16K images collected and augmented to build the places (specifically places in Indonesia) dataset. The highest accuracy score achieved by the models is 92%.

关键词： Visual Place Classification Convolutional Neural Networks Deep Learning Dataset Collection

来源：评论

学校读者我要写书评

暂无评论

MobileNet Convolutional Neural Networks and Support Vector Machines for Palmprint Recognition

引用

Procedia computer science 2019年 157卷 110-117页

作者： Aurelia Michele Vincent Colin Diaz D. Santika Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Due to the ease of handling with low resolution images, low cost hardware and high recognition accuracy, palmprint recognition has been attracting in the recent years. Many different features extracted of the palmprint image have been employed to perform the recognition tasks. Most of the recognition efforts consequently has been put on the designing and obtaining a relevant set of effective hand-crafted features which is considered to be the drawback of the traditional image based biometric recognition systems. To overcome the aforementioned problem, in this paper we explore the applicability of MobileNet V2 deep convolutional neural networks on palmprint recognition by fine-tuning a pretrained MobileNet neural networks. We also explore the performance of dropout support vector machines (SVM) by training them on the deep features of the similar pretrained networks. The experiments are carried out using datasets provided by Hong Kong Polytechnic University of science and Technology. The dataset consists of 6000 grayscale images of 128x128 pixels from 500 different palms. It is demonstrated that the proposed schemes exhibit state-of-the-art performance on the datasets. The second scheme, MobileNet V2 based features with SVM classifier, is able to achieve best average testing and validation accuracy rate of 100% outperforming the best previous reported results.

关键词： Biometric Palmprint recognition Support vector machine Deep convolutional neural networks MobileNets model

来源：评论

学校读者我要写书评

暂无评论

Gender Demography Classification on Instagram based on User’s Comments Section

引用

Procedia computer science 2019年 157卷 64-71页

作者： N. Reynaldo Goenawan William Chanrico Derwin Suhartono Fredy Purnomo Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Social media has become an integral part of the society. This created a rising demand on social media marketing. New breakthroughs in the field of artificial intelligence have enabled brand owners to boost social media marketing by knowing their target’s demography. This study presents a model to predict gender of social media users based on comments section on Instagram profile by using AdaBoost, XGBoost, Support Vector Machine, and Naive Bayes Classifier combined with a grid search and K- Fold validation. The model was trained with 40,000 comments and managed to get 78.64% on Naive Bayes, 73.41% on XGBoost, 74.56% on AdaBoost and 76.07% on SVM which are generally higher than related studies on this subject. This result shows that Naive Bayes produces higher accuracy on short text classification and has possibilities to help social media marketing.

关键词： Gender prediction Short text classification Instagram

来源：评论

学校读者我要写书评

暂无评论

Automotive Security with Authorization and Tracking via GPS

引用

Procedia computer science 2019年 157卷 72-78页

作者： Arko Wirarespati Zulfany Erlisa Rasjid Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

With the ever progressing technology in Indonesia, Information and Technology has rooted and integrates itself with most of today’s daily aspect. The automotive industry today is reaching out to wider range of users, being accessible in various shapes, sizes and range of mobility. However, the still ongoing vehicular thefts and the fact that it’s also difficult at times to report to authorities in regards of the matter has brought forth several problems, such as lack of necessary means to reclaim vehicles, expensive GPS tracker prices, all while having the aforementioned tools that are not quite user-friendly. Using research and experiments on Arduino micro-controllers, and mobile development using Android Studio SDK, such a system was developed. From this system, which was tested by various ranges of age and occupation, it has been concluded and proven that a creation of fair-priced, user-friendly, and functional tracking system is very much possible. This system also operates offline, which is very useful when users are lacking internet connections.

关键词： GPS User-friendly Micro-controllers Arduino Android

来源：评论

学校读者我要写书评

暂无评论

Designing an Emotionally Realistic Chatbot Framework to Enhance Its Believability with AIML and Information States

引用

Procedia computer science 2019年 157卷 621-628页

作者： Rhio Sutoyo Andry Chowanda Agnes Kurniati Rini Wongso Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Chatbot program has been empirically proven help to improve the engagement with users. Moreover, the implementation of a chat-bot program in the industry helps the company to reduce their operational costs in engaging with their customers and employees. There are still quite a number of problems existed in order to build a human-like chatbot program. Understanding a natural conversation and replying back to the conversation the interlocutors, keeping the conversation flowing naturally is a cumbersome task for a computer. This research aims to design an emotionally realistic chatbot system to enhance the believability of the chatbot using Artificial Intelligence Markup Language (AIML) and Information State. The results show that there is a statistically significant improvement to the chatbot believability in the system that has emotions variables induced compare to the one without emotions. Moreover, 63,33% of the respondents perceived Aero and Iris as two different individuals. The future work of this research is to deploy and have an exploration of the chatbot system to other cases.

关键词： Chatbot Emotions Model Believability AIML Information State

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：