检索结果-内蒙古大学图书馆

Research Square 2020年

作者： Azwar, Azika Syahputra Suharjito Computer Science Department Binus Graduate Program Master Computer Science Bina Nusantara University Jakarta11480 Indonesia

Sarcasm is often used to express a negative opinion using positive or intensified positive words in social media. This intentional ambiguity makes sarcasm detection, an important task of sentiment analysis. Detecting a sarcastic tone in natural language hinders the performance of sentiment analysis tasks. The majority of the studies on automatic sarcasm detection emphasize on the use of lexical, syntactic, or pragmatic features that are often unequivocally expressed through figurative literary devices such as words, emoticons, and exclamation marks. In this paper, we introduce a multi-channel attention-based bidirectional long-short memory (MCAB-BLSTM) network to detect sarcastic headline on the news. Multi-channel attention-based bidirectional long-short memory (MCAB-BLSTM) proposed model was evaluated on the news headline dataset, and the results-compared to the CNN-LSTM and Hybrid Neural Network were excellent. © 2020, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting User Preferences with XGBoost Learning to Rank Method 3

Predicting User Preferences with XGBoost Learning to Rank Me...

引用

3rd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2020

作者： Qomariyah, Nunung Nurul Kazakov, Dimitar Fajar, Ahmad Nurul Bina Nusantara University Faculty of Computing and Media Computer Science Department Jakarta11480 Indonesia University of York Computer Science Department York United Kingdom Binus Graduate Program-Master of Information Systems Management Bina Nusantara University Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781728184067

Learning user preferences become very important as the personalization systems grow rapidly in this current era. Offering special and personal services can be an added value for the companies to maintain their customer loyalty. Building a personalized recommendation requires a good machine learning model to understand the individual preferences. Every user can be presented with a list of items sorted by its score learned from the individual preferences. So the first couple items shown will be the most liked items by the user. We can borrow the Learning to Rank algorithm from Information Retrieval to solve this problem. In this paper, we present the implementation of user preferences learning by using XGBoost Learning to Rank method in movie domain. We show the evaluation of three different approaches in Learning to Rank according to their Normalized Discounted Cumulative Gain (NDCG) score. We can conclude that in our case study, the pairwise approach appears to be the best solution to produce a personalized list of recommendation. © 2020 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

User Preference Modelling from Movie Database 7

User Preference Modelling from Movie Database

引用

7th International Conference on ICT for Smart Society, ICISS 2020

作者： Qomariyah, Nunung Nurul Kazakov, Dimitar Fajar, Ahmad Nurul Bina Nusantara University Faculty of Computing and Media Computer Science Department Jakarta11480 Indonesia University of York Computer Science Department York United Kingdom Bina Nusantara University BINUS Graduate Program-Master of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665404228

Film industry becomes one of the largest amongst the other economic sectors worldwide nowadays. This industry also has a significant impact in the global economic market. Many movies have been produced each year. However, some movies still fail to reach break-even points every year. Players in this industry need to think carefully when spending most of their money to make a great and successful movie in the market. Several attempts also need to be made to estimate the success performance before a movie can be released. On the audience side, there is an indicator that we can use to decide that a movie is good by looking to its ratings. The industry can use this rating systems as a factor to be considered when evaluating the past movie performances to make better movie for the next production. This study aims to predict the movie ratings and find the most important features which correlate to the ratings. We performed an experiment on IMDb dataset which contains 5,043 movie metadata on four models of machine learning, Linear Regression (LR), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbor (KNN). From the experiment, Random Forest achieves the best performance amongst the four models. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

ERP System Integration with Mobile Applications Using Service Oriented Architecture 4

ERP System Integration with Mobile Applications Using Servic...

引用

4th International Conference on Information Management and Technology, ICIMTech 2019

作者： Erdiyana, Hikmat Fauzy Suharjito Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

a furniture rental service multinational company has a mobile application that is used by the salesperson to make sales transactions. Currently the mobile application gets data from the ERP system by importing and exporting it so that the data used is not real-time. To support the creation of real-time data communication between ERP systems and mobile applications, a replacement method for the export and import process is needed. Therefore, this study makes several web services that can be used to replace the export and import processes through the integration of Enterprise Resource Planning (ERP) with mobile applications using Service Oriented Architecture (SOA). Web services are made using RESTful and have passed several stages of testing using the QOS standard. Based on the results of testing using Jmeter with a simulation of 20 users obtained latency on the web service is 3 seconds and 4 seconds load time with an average data size of 2599 bytes so it can be concluded that this quality is quite good in terms of performance and accessibility. Test results using vooky show no bugs, but there are still shortcomings in security, which are caused by the lack of security in the header. With the results of these tests, the webservice can be used to replace the export and import process that have been used by the salesperson, so the data communication between ERP and mobile applications becomes real-time. © 2019 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

GOROdsm: Local Wisdom Inspired socioDSM for Reconstructing Public Facility 7

GOROdsm: Local Wisdom Inspired socioDSM for Reconstructing P...

引用

7th International Conference on Cyber and IT Service Management, CITSM 2019

作者： Utama, Ditdit Nugeraha Suharjito BINUS Graduate Program Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728129099

Gotong royong (GORO) is an impressive cultural spirit of Indonesia. It means practically 'working together' without considering their dissimilarities and disparities to solve a problem. Specifically in public facility construction, at some time the citizen have to work together to do so with their own capital and resources through donation activity. It occurs century by century. Based on that unique phenomenon, this paper proposes a decision support model (DSM) that fundamentally created based on the GORO spirit to reconstruct the damage. The model is able to suggest the most objective damaged public facility that should be rehabilitated first. The method fuzzy logic is the main method operated in this work. The object-oriented method was used to design and develop a model. The simulated-annealing was functioned as an optimization method to optimize a selected decision. Finally, the model was tested by using experimental data to see its running. © 2019 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Reporting and Decision Support Using Data Warehouse for E-Commerce top-up Cell-phone Credit Transaction 7

Reporting and Decision Support Using Data Warehouse for E-Co...

引用

7th International Conference on Cyber and IT Service Management, CITSM 2019

作者： Vincentdo, Vito Pratama, Andhika Rizky Girsang, Abba Suganda Suwandi, Rizaldi Andrean, Yosefina Pricilia BINUS Graduate Program-Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728129099

As e-commerce that covered all Indonesia, needs a fast reporting system to analyze the business to make the best decision. This paper provides methods to fasten the reporting process by making a data warehouse using Kimball and ross method. Data warehouse consists of 9 step methodology designed by Kimball and Ross. This paper devoted for business processes in e-commerce especially for online cellphone balance top-up transactions. Furthermore, data can be displayed in a form such as a dashboard, and also in a simple, informative and effective report. © 2019 IEEE.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

An Enhanced-BLCA for Assessing Performance of Company's Growth 7

An Enhanced-BLCA for Assessing Performance of Company's Grow...

引用

7th International Conference on Cyber and IT Service Management, CITSM 2019

作者： Utama, Ditdit Nugeraha BINUS Graduate Program Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728129099

This paper purposes an improved algorithm of the butterfly lifecycle for calculating the performance of the company's growth. Three types of change for the better are regarding mathematical model, conception in calculating the growth performance parameters, and also data operated practically for testing the proposed algorithm. Three simple stages of study conducted are previous study-re-analyzing and re-reviewing, mathematical model constructing, and model testing. Here, roulette-wheel technique was technically functioned to generate probability of positive and negative factor values;that influence the performance of artificial butterfly's metamorphoses process (also could affect the quality of butterfly finally). Nineteen mathematical equations successfully produced are able to perfect the previous algorithm, particularly in the detailed calculation of performance in every single stage of metamorphoses. Conclusively, a balanced scorecard approach adopted as conception in calculating the company's internal aspect performance that benefited from testing the new improved algorithm. Similar to the previous study, the company's external factors considered as well in stage of model testing. © 2019 IEEE.

关键词： Wheels

来源：评论

学校读者我要写书评

暂无评论

Business Intelligent in an E-Commerce Industry 6

Business Intelligent in an E-Commerce Industry

引用

Joint Conference of the 6th Annual Conference of Industrial and System Engineering 2019, ACISE 2019 and 1st International Conference on Risk Management as an Interdisciplinary Approach 2019, ICRMIA 2019

作者： Purnamasari, A.M. Pah, C.E.A. Yoga, M.D.I. Girsang, A.S. Isa, S.M. Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Usantara University Jakarta11480 Indonesia

According to a survey from *** about in 2017, retail e-commerce sales worldwide amounted to 2.3 trillion US dollars and e-retail revenues are projected to grow to 4.88 trillion US dollars in 2021. Each year, e-commerce business increasingly popular. Some retail companies finally decided to focus on internet-based sales to get more customers. Along with transactions that continue to be carried out from year to year, transaction data continues to be stored and stacked and of course space consuming. So after years, Business Intelligence is finally appeared and offer great data processing. Without a business intelligence, these stacked big data are useless and wait to be removed because of poor knowledge. Business intelligence turns on the poor knowledge data into rich knowledge data visualization. This paper proposed a data warehouse that can be used to build a business intelligent with utilize information obtained from the history of transactions. To build up this business intelligent, authors uses methodology steps by Kimball which consists 4 steps of dimensional design process. Furthermore, data analysis will be presented in a dashboard using Power BI. © Published under licence by IOP Publishing Ltd.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Extended-RSA for Encryption Process to Improve Application Server Availability 6

Extended-RSA for Encryption Process to Improve Application S...

引用

作者： Susanto, A. Herman Putranto, M.I. Utama, D.N. Wibowo, A. Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Every enterprise stores and operates its transactions confidentially, therefore it has to encrypt the transaction to protect it from data intruders. Technically, most encryption processes are ranging from hundreds of milliseconds. If there is a lot of encrypting process, then the performance will be getting bottleneck and the transaction's speed is being slowed down. In this paper, a promising scheme by adding GZIP compression on the former RSA encryption method to increase speed is proposed;thus every transaction is going to require less times, therefore the number of failed transactions or requests will be reduced. Hence, this way makes the transaction easier for customers to do. The result of little experimental test shows that using XOR to stream cipher-text to replace the absent of padding into specific bytes shows a lot of performance increase resulting other factors such as availability also affected without sacrificing the security level. © Published under licence by IOP Publishing Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Realtime Vehicle Counting Method Using Haar Cascade Classifier Model

Realtime Vehicle Counting Method Using Haar Cascade Classifi...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Prasetyo Mimboro Yaya Heryadi Lukas Wayan Suparta Antoni Wibowo Doctor of Computer Science Graduate Program Faculty of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Atma Jaya University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665499705

The proliferation of digital camera technology has provided many digital images for object detection and counting in public places. This paper presents an experiment on the realtime vehicle counting method to be implemented in a single board computer. The proposed design's objective is to detect and count vehicles entering and exiting at entrances using haar cascade classifier algorithms and other automatic open and close door systems controlled by a single board computer (SBC). The proposed system was tested using raspberry pi 4 model B with a 4GB RAM platform. The empiric results using 3-minute video as input with a total of 113 passing vehicles the proposed method achieve of 91.2 % of average accuracy.

关键词： Mechatronics Automation Computational modeling Digital images Random access memory Object detection Logic gates

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：