检索结果-内蒙古大学图书馆

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

作者： Harvy, Ikrar Matitaputty, Gilbert Alessandro Girsang, Abba Suganda Michael, Steve Isa, Sani Muhamad BINUS Graduate Program-Master of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9781728129099

Data is the part that represents the evidence in presenting the state of the surrounding environment, obtained through research in the form of numbers, sources or scales. with data, conditions can be measured to produce the best solution. GIS Bookstore is one company that needs data every month to be analyzed. However, GIS Bookstore has constraints in processing large data with increasing time. for example GIS bookstore has problems in analyzing bestsellers because of the increasing number of authors and book publishers who work together. In this study, GIS Bookstore found a solution by implementing business intelligence that plays a role in the processing of raw data in large amounts of data into well-structured data information, the results are collected and processed in a data warehouse scheme. Targets stored in the data warehouse are data that will be processed based on the model design method (ERD) and star schema. This paper discusses the GIS Bookstore data warehouse with the aim of analyzing the sales of most books based on a certain time period. The method used in retrieving data uses Pentaho data integration tools, MySQL workbench, report designer, bi server and workbench schema. © 2019 IEEE.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

XSS Attack Detection With Machine Learning and n-Gram Methods

XSS Attack Detection With Machine Learning and n-Gram Method...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Gulit Habibi Nico Surantha BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Cross-Site Scripting (XSS) is an attack most often carried out by attackers to attack a website by inserting malicious scripts into a website. This attack will take the user to a webpage that has been specifically designed to retrieve user sessions and cookies. Nearly 68% of websites are vulnerable to XSS attacks. In this study, the authors conducted a study by evaluating several machine learning methods, namely Support Vector Machine (SVM), K-Nearest Neighbour (KNN), and Naïve Bayes (NB). The machine learning algorithm is then equipped with the n-gram method to each script feature to improve the detection performance of XSS attacks. The simulation results show that the SVM and n-gram method achieves the highest accuracy with 98%.

关键词： Machine learning Uniform resource locators Support vector machines Training data Cross-site scripting Machine learning algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Virtual Plant Computational Model of Green-Leaf Vegetable Plant Bok Choy (Brassica chinensis L.) for Investment Decision

引用

IOP Conference Series: Earth and Environmental science 2022年第1期998卷

作者： D. N. Utama A. Wibowo Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Plant computational modelling is a part of ecological informatics. It is a research domain that model the plant/s and is correlated to an environmental issue. A vegetable is one imperative plant. It has an important role in aspects of health, the environment, and also the economy. The study was performed to make a plant computational model of the green-leaf vegetable plant Bok Choy that can suggest the environment-oriented decision in agriculture investment. Two methods functional structural plant modelling (FSPM) and simple mathematics are operated respectively to model the Bok Choy plant morphologically and the decision recommendation. The study produced the morphological 3-dimension (3D) model of the forty-fve-day-age plant Bok Choy and investment decision to plant Bok Choy in a hydroponic system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fingermath - Arithmetic Hand Gesture Game to Improve Early Childhood Mathematics Learning 4

Fingermath - Arithmetic Hand Gesture Game to Improve Early C...

引用

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

作者： Yuliana, Dewi Suharjito Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

Teaching mathematics has received priority in schools, because mathematics is the basis for development in understanding mathematics as a whole at school. computer technology used in teaching and learning can help improve children's preferences and abilities to learn mathematics in class, and can change attitudes of early childhood who are more critical, creative, and innovative. Jarimagic method is one method for learning to count on the fingers, where early childhood often communicate with fingers in learning mathematics in the classroom. For this reason, research attempts learning methods with interactive games with hand movements using the Jarimajic method and tools scratch 2.0. In this study, evaluation of data obtained through 20 child respondents was carried out by testing before using the game and after using the game, using Pre-Test and Post-Test analysis, which was divided into 2 results based on the preferences and abilities of early childhood learning mathematics in the classroom. From the study, the game development was carried out using the System Development Life Cycle (SDLC) method by taking the model of implementation the waterfall model. then a game is designed to overcome this problem. After the game is made, the game will be tested again for early childhood, with T-Test statistical analysis as the final data obtained from research that shows whether early childhood likes and increases ability to learn mathematics after the game is implemented. The results of this study are the realization of interactive game-based learning methods for early childhood in learning to count mathematics. especially in learning additions and collection using the jarimajic method so that children have the ability and preference in learning mathematics. © 2019 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Sarcasm Detection Using Multi-Channel Attention Based BLSTM On News Headline

Research Square

引用

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

Performance Evaluation of Queue Algorithms for Video-on-Demand Application

Performance Evaluation of Queue Algorithms for Video-on-Dema...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Yoni Irawan Nico Surantha BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Nowadays, there are real-time internet applications that require low latency and high bandwidth usage. In order to satisfy this requirement, many active queuing algorithms are offered, such as RED, BLUE, and controlled delay (CoDel). The number of publications aimed at evaluating the performance of the active queue management (AQM) algorithm is still limited by using a network simulator and only comparing two algorithms. The combination of AQM and connection types (fairness and no-fairness) in real network implementation has not been discussed much. In this paper, we offer a comparison of the performance of three queuing algorithms, namely DropTail, BLUE, and CoDel, with two types of connections, namely fairness and no-fairness using real network devices and internet video streaming access. Experiments carried out in the real network environment using Sandvine PL8840's bandwidth management device. The quality of services (QoS) parameters that will be compared are throughput, latency, and packet loss. The comparison results show that fairness connections on all queuing algorithms can maintain low latency values; throughput is smaller than no-fairness connections. The absence of packet loss in streaming video based on the TCP protocol does not guarantee that the video being played runs well because it depends on the available bandwidth capacity.

关键词： Bandwidth Delays Packet loss Throughput Streaming media Quality of service

来源：评论

学校读者我要写书评

暂无评论

Unsupervised News Topic Modelling with Doc2Vec and Spherical Clustering

引用

Procedia computer science 2021年 179卷 40-46页

作者： Arif Budiarto Reza Rahutomo Hendra Novyantara Putra Tjeng Wawan Cenggoro Muhamad Fitra Kacamarga Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Information System Department School of Information System Bina Nusantara University Jakarta Indonesia 11480 Eureka AI Singapore Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

In the digital and Internet era, companies are racing to profile their target users based on their online activities. One of the reliable sources is the news articles they read that can represent their interests. However, extracting latent information from the news articles is not an easy task for a human. In this paper, we introduced a practical model to automatically extract latent information from news articles with pre-determined topics. Our proposed model used unsupervised learning, thus alleviating the need for humans to label news items manually. Doc2vec was used to generate word vectors for each article. Afterward, a spectral clustering algorithm was applied to group the data based on the similarity. A supervised Long Short Term Memory (LSTM) model was built to compare the clustering performance. The best 1, best 3, and best 5 scores were used to evaluate our model. The result showed that our model could not outperformed LSTM model for the best 1 score. However, the best 5 score result indicated that our model was sufficiently robust to cluster the articles based on topic similarity. Additionally, the proposed unsupervised model was implemented in both an on-premise server, and a cloud server. Surprisingly, our proposed method could run faster in the cloud server despite its less number of CPU cores.

关键词： Topic Modelling Latent Information News Article Document Embedding Spherical Clustering

来源：评论

学校读者我要写书评

暂无评论

Model Decision Support System For Diagnosis COVID-19 Using Forward Chaining: A Case in Indonesia

Model Decision Support System For Diagnosis COVID-19 Using F...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Henderi Miftah Maulana Harco Leslie Hendrie S. Warnars Didik Setiyadi Taufik Qurrohman University of Raharja Tangerang Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Bina Insani University Bekasi Indonesia

ISBN: (数字)9781728177014

ISBN: (纸本)9781728177021

The government in Indonesia and its staff work together to make tactical steps to prevent the spread of COVID-19 in the community. From the ministerial level to the heads of the provinces, regencies, and even the government. Therefore, this study aims to make a model decision support system to diagnose patients exposed to Covid-19, such as people in control, patients in oversight, and those who are positive for the Covid-19 Virus. Model decision support system development aims to provide information about the development of COVID- 19 and help the community in diagnosing themselves related to COVID-19 infection. In this study, the authors use the forward chaining method in application to get conclusions from the symptoms of the Covid-19. This research resulted in an application that patients exposed to the Covid-19, and it's also provided a solution for healing from patients. And this could be a reference for patients before consulting further with the doctor.

关键词： COVID-19 History Expert systems Viruses (medical) Decision support systems Lung Informatics

来源：评论

学校读者我要写书评

暂无评论

Geometric verification method of best score increasing subsequence for object instance recognition 6

Geometric verification method of best score increasing subse...

引用

6th International Conference on Information Technology, computer and Electrical Engineering, ICITACEE 2019

作者： Kusuma, Gede Putra Harjono, Kristopher David Dwi Putra, Muhammad Taufik Bina Nusantara University BINUS Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728126890

Weighted Longest Increasing Subsequence (WLIS) and its improvement, Best Increasing Subsequence (BIS) are two methods that has been proposed for pair verification in object instance recognition using local features. Tested on the Stanford Mobile Visual Dataset (SMVS), the BIS achieves better performance than WLIS on most categories, except for the 'video frames' category. In this paper we propose several modifications to BIS which resulted in a better overall performance compared to the WLIS and the basic BIS approaches. On average, the proposed Best Score Increasing Subsequence (BSIS) performs 4.53% better than the BIS and 9.43% better than the WLIS. © 2019 IEEE.

关键词： Object recognition

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

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：