检索结果-内蒙古大学图书馆

Research Square 2021年

作者： Wongso, Wilson Lucky, Henry Suhartono, Derwin Computer Science Department School of Computer Science Bina Nusantara University Jakarta11840 Indonesia

The Sundanese language has over 32 million speakers worldwide, but the language has reaped little to no benefits from the recent advances in natural language understanding. Like other low-resource languages, the only alternative is to fine-tune existing multilingual models. In this paper, we pre-trained three monolingual Transformer-based language models on Sundanese data. When evaluated on a downstream text classification task, we found that most of our monolingual models outperformed larger multilingual models despite the smaller overall pre-training data. In the subsequent analyses, our models benefited strongly from the Sundanese pre-training corpus size and do not exhibit socially biased behavior. We released our models for other researchers and practitioners to use. © 2021, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Separable Convolutional Neural Networks For Facial Expressions Recognition

Research Square

引用

Research Square 2021年

作者： Chowanda, Andry Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Social interactions are important for us, human, as social creatures. Emotions play an important part in social interactions. They usually express meanings along with the spoken utterances to the interlocutors. Automatic facial expressions recognition is one technique to automatically capture, recognise, and understand emotions from the interlocutor. Many techniques proposed to increase the accuracy of emotions recognition from facial cues. Architecture such as convolutional neural networks demonstrates promising results for emotions recognition. However, most of the current models of convolutional neural networks require an enormous computational power to train and process emotional recognition. This research aims to build compact networks with depthwise separable layers while also maintaining performance. Three datasets and three other similar architectures were used to be compared to the proposed architecture. The results show that the proposed architecture performed the best among the other architectures. It achieved up to 13% better accuracy and 6-71 % smaller and more compact than the other architectures. The best testing accuracy achieved by the architecture was 99.4%. © 2021, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Traffic Lights Analysis and Simulation Using Fuzzy Inference System of Mamdani on Three-Signaled Intersections.

引用

Procedia computer science 2021年 179卷 268-280页

作者： Siti Komsiyah Evelyn Desvania Mathematics Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

As one of the main characters at road intersections, traffic lights have lost its limelight and functions as of late. The unbalanced timing on its green light/green time duration settings with less to no regard to actual traffic in each lane becomes one of its main problems. Therefore in this paper, the author will formulate a more dynamic green time setting system by using Fuzzy Inference System type Mamdani. To help with the analyzing process, a desktop-based application is designed to simulate the green light duration setting for the traffic light based on the previously conducted analysis. The green light/green time output obtained during the implementation of this application will be further compared to the data obtained from transportation office of DKI Jakarta (Dinas Perhubungan Provinsi DKI Jakarta). From this comparison, it can be deduced that the output results from the implementation of this methods show a more dynamic value.

关键词： Fuzzy Inference System Mamdan traffic lights simulation green time

来源：评论

学校读者我要写书评

暂无评论

Development of Key Performance Indicators in e-Learning Implementation in Higher Education Institutions

Development of Key Performance Indicators in e-Learning Impl...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Wahyu Sardjono Desi Maya Kristin Gustian Rama Putra Information Systems Management Department BINUS Graduate Program - Master of Information Systems Management Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Study Program Faculty of Mathematics & Natural Sciences Pakuan University Bogor Indonesia

Companies or organizations usually use key performance indicators (KPI) as indicators to determine their performance. The company's performance achievements are reflected in the set indicators that will describe the overall performance, as well as higher education institutions can also set key performance indicators, to see their performance achievements. The use of e-learning as a tool to support teaching and learning processes to be more effective and efficient is an example of which performance needs to be measured. This article discusses how the process of developing key performance indicators is carried out through the stages of designing questionnaires and distributing questionnaires to students, data is processed using the method of factor analysis to obtain the main indicators determining performance and the method of regression analysis is also used to build performance models. obtain KPI determinants, and then develop KPI models. The results show that there are indicators of sharing knowledge, managing knowledge, understanding knowledge, and utilization knowledge as performance measurement indicators.

关键词：

来源：评论

学校读者我要写书评

暂无评论

My trackmap: Web-based application for tracking employees

引用

AIP Conference Proceedings 2024年第1期2982卷

作者： Evan Edbert Eko Setyo Purwanto Rinda Nariswari I. Gusti Agung Anom Yudistira Samsul Arifin Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Statistics Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

ESRI is a company that provides application services in the field of Geographic Information System. The main problem in this company is that there is no tracking process for sales employees who are working outside. On the other hand, the manual tracking process is also a concern. In this research, the author makes My Trackmap, a web-based application to track salesmen in a company. This application is also developed for two hardware, Desktop, and Mobile. Where the Desktop version is used as an admin to check salesmen at ESRI, and the Mobile version is developed to be used by salesmen. In developing this application, we use the help of the JAVAScript API and Larave.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model of Customer Relationship Management Systems Evaluation Using Factor Analysis

Model of Customer Relationship Management Systems Evaluation...

引用

International Conference on Information Management and Technology (ICIMTech)

Relationship with customers is one of the most crucial factors in business continuity and development. Many current businesses have started delving into Customer Relationship Management (CRM) to establish and maintain their sales and customer relationships. This research was conducted on one retail company that implements CRM but experiencing a gap in their unit sales performance between their targeted sales and the realization. This study aims to analyze the gaps causing factors using Factor Analysis Method, constructing a suitable regression model, and proposing the company's necessary strategy. The research was conducted quantitatively using a questionnaire from 264 respondents. The result of this study showed that there are five causing factors which are CRM Reliability, Underutilization of CRM, CRM Capability, CRM Unpreparedness, and Customer Relation Quality, as well as forming a regression model of the company's CRM performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Lambda Distribution: Application on Financial Performance Data in the Indonesia Stock Exchange

Generalized Lambda Distribution: Application on Financial Pe...

引用

International Conference of computer science and Information Technology

作者： Prana Ugiana Gio Herman Mawengkang Muhammad Zarlis Saib Suwilo Graduate School of Mathematics Universitas Sumatera Utara Medan Indonesia Department of Mathematics Universitas Sumatera Utara Medan Indonesia Computer Science Department Bina Nusantara University Medan Indonesia

The generalized lambda distribution (GLD) is one of the statistical distributions that can be used for data matching. GLD is known to have a high level of flexibility so that it can create distributions with a variety of different forms. The aim of this study is to apply GLD to financial performance data of companies listed on the Indonesia Stock Exchange and also comparing the result with several probability distribution, such as normal, Weibull, lognormal and Gamma. The result shows that GLD gives the highest accuracy rather than other probability distributions in data matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scientometric Analysis of Artificial Intelligence Research in Agriculture

Scientometric Analysis of Artificial Intelligence Research i...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Fairuz Iqbal Maulana Andi Pramono Miftahul Hamim Sukeipah Yuli Prihatin Rahman Arifuddin Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Entrepreneurship Business Creation BINUS Business School Bina Nusantara University Jakarta Indonesia Informatics Study Program Politeknik Kota Malang Malang Indonesia Department of Electrical Engineering University of Merdeka Malang Malang Indonesia

ISBN: (纸本)9781665473286

Artificial Intelligence Research in Agriculture has grown so common, and the potential they provide is so revolutionary that it is considered essential for competitive growth. Until we conducted this research, only 1064 academic documents on Trends of Artificial Intelligence Research in Agriculture that we found from 2012 to 2021 were obtained by searching the Scopus database. This study uses bibliometric analysis methods to map scientific publications worldwide. We use an article selection process, the year limitation, then the database is exported to RIS and CSV format files. Researchers in the United States had the most published articles and were indexed by Scopus among the most prolific authors ( $\mathrm{N}=287$ ), followed by the United Kingdom at second ( $\mathrm{N}=139$ ) and Italy with 66 academic publications. Data analysis reveals an increasing trend in the number of Trends of Artificial Intelligence Research in Agriculture publications worldwide, as measured by the Scopus index.

关键词： Data analysis Databases Multimedia systems Bibliometrics Market research Agriculture Indexes

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Paid Road use for the Reduction of Traffic Congestion

Mobile Application for Paid Road use for the Reduction of Tr...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Muhammad Rizqiko Harliano Mohammad Afif Hafiz Ramadhani Tanto Harsono Iwan Rian Koswara Hareo Leslie Hendrie Spits Warnars School of Computer Science Bina Nusantara University Jakarta Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

Technology has evolved a lot in the last few years. E-toll becomes the only payment method available for highway roads, especially in Indonesia. This system of payment is expected to enhance the efficiency of payment from using the previous payment method. However, there are still some weaknesses addressed by the implementation of e-toll. It still takes time because the car's owner should tap the card first, and the sequence time between each person to tap is different. Thus, the queue results still long, and the traffic congestion on the highway road is not fully solved. This paper aims to address a better solution by adding a more efficient option of payment. So, traffic congestion is reduced and leads to better operation in toll gates. This research work has proposed a mobile application and route prediction model based on the Dijkstra Algorithm, where the price will be decided on which type of car will be passed by the gate, and the algorithm predicts the best possible routes based on the number of cars on the highway. Payment is conducted on the application using the balance from the application. This application eliminates time consumed during toll payment at any toll gate.

关键词： Online banking Roads Urban areas Logic gates Predictive models Prediction algorithms Modems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Classifying Public Opinions on Energy Sector IHSG Stocks on the Twitter Social Media Platform

Deep Learning Model for Classifying Public Opinions on Energ...

引用

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Bambang Sulistio Yaya Heryadi Lukas Wayan Suparta Ilvico Sonata Computer Science Department Binus Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

Capital market transactions provide an opportunity for investors to acquire ownership of company shares and capital gains, as well as dividends. However, alongside the benefits, there are risks of capital loss and liquidation, leading to stress and depression due to profit targets and decision-making errors. To mitigate the risk of decision-making errors in investment, data analysis is needed, including sentiment analysis, which influences stock prices. This study aims to develop a new deep learning model to classify Indonesian public opinion on JCI stocks, especially the Energy sector, obtained from the Twitter social media platform. The model will perform sentiment analysis and categorize opinions as negative, neutral, or positive. We created a dataset that was trained using Bidirectional Encoder Representations from Transformers (BERT) to summarize the analysis of public sentiment above so that it can assist investors in studying public sentiment as a reference for investing with a yield precision of 76%, Recall of 77%, and F1-score on 76%.

关键词： Deep learning Sentiment analysis Analytical models Social networking (online) Blogs Decision making Text categorization Bidirectional control Transformers Encoding

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：