检索结果-内蒙古大学图书馆

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Brian Wijaya Aqraldo Jessen Yuliet Sentoman Deven Markos Harco Leslie Hendric Spits Warnars School of Information System Bina Nusantara University Jakarta Indonesia BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728185194

ISBN: (纸本)9781728185200

We have often heard of cases of loss of animals in the world, the owners of these animals are very troubled in looking for lost animals, so often when the pet is lost, the owner leaves it or makes the news of the competition for who can find it. We strive to help these pet owners easily detect the presence of pets they have through a mobile application that we make, namely Detepet that can track all the pets you have, so you are not afraid of losing your pet. In this case, the user should register their pet and the tool GPS necklace will be attached to the pet and the pet will be under monitoring of the systems.

关键词： Heart rate Animals Tools Mobile applications Registers Informatics Monitoring

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

Deep learning performance in sentiment analysis 4

Deep learning performance in sentiment analysis

引用

4th International Conference on Electrical, Telecommunication and computer Engineering, ELTICOM 2020

作者： Manalu, Boy Utomo Tulus Efendi, Syahril Graduate Program of Computer Science Universitas Sumatera Utara Medan Indonesia Universitas Sumatera Utara Department of Mathematics Medan Indonesia Universitas Sumatera Utara Department of Computer Science Medan Indonesia

ISBN: (纸本)9781728188706

A problem of sentiment analysis is the text representation, that encodes text into a continuous vector by arranging projections from semantics to the points in high dimensional space. Deep learning methods have been widely used to solve various sentiment analysis problems. To improve the performance of deep learning in sentiment analysis requires a good method of text representation to be used as an embedding layer. In this study, we analyzed deep learning with the Recurrent Neural Network (RNN) method with Long Short-Term Memory (LSTM) variants in sentiment classification. We compare the performance of the LSTM network with Word2Vec to the network without Word2Vec as word embedding. Sentiment data used is derived from user-provided reviews of the applications in Google Play. The training process involves the Dropout layer and Early Stopping points to prevent overfitting. The results showed that the LSTM network using a word embedding Word2Vec is better than without Word2Vec. LSTM with Word2Vec 300 words dimension got a low error value of 0.3287 with an accuracy of 86.76%. While the LSTM testing results without Word2Vec get the lowest error of 0.3751 with an accuracy of 84.14%. © 2020 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

引用

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

来源：评论

学校读者我要写书评

暂无评论

CELL-E 2: translating proteins to pictures and back with a bidirectional text-to-image transformer 23

CELL-E 2: translating proteins to pictures and back with a b...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Emaad Khwaja Yun S. Songt Aaron Agarunov Bo Huang UC Berkeley - UCSF Joint Bioengineering Graduate Program and Computer Science Division UC Berkeley CA Department of Statistics UC Berkeley CA and Computer Science Division UC Berkeley CA Department of Pathology Memorial Sloan Kettering Cancer Center Department of Pharmaceutical Chemistry UCSF San Francisco CA and Department of Biochemistry and Biophysics UCSF San Francisco CA and Chan Zuckerberg Biohub - San Francisco San Francisco CA

We present CELL-E 2, a novel bidirectional transformer that can generate images depicting protein subcellular localization from the amino acid sequences (and vice versa). Protein localization is a challenging problem that requires integrating sequence and image information, which most existing methods ignore. CELL-E 2 extends the work of CELL-E, not only capturing the spatial complexity of protein localization and produce probability estimates of localization atop a nucleus image, but also being able to generate sequences from images, enabling de novo protein design. We train and finetune CELL-E 2 on two large-scale datasets of human proteins. We also demonstrate how to use CELL-E 2 to create hundreds of novel nuclear localization signals (NLS). Results and interactive demos are featured at https://***/CELL-E_2/.

关键词：

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

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

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

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

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：