检索结果-内蒙古大学图书馆

Detection Traffic Congestion Based on Twitter Data using Machine Learning

Procedia computer science 2019年 157卷 118-124页

作者： Muhammad Taufiq Zulfikar Suharjito Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Twitter is one of the social media with text and image information that can be used as a source of information to detect traffic congestion in real-time. This study developed a system to detect traffic congestion in Indonesia, especially DKI Jakarta. The system displays the direction of the street according to the name of the street being passed and from each of the names of the streets, resulting in a tweet from the classification. The proposed method uses the Support Vector Machine (SVM) classification with the sigmoid kernel. This study shows that the SVM classification with the sigmoid kernel (libSVM) has an accuracy rate of 96.24% and that was increased by 2.68% when compared to SVM dot (mySVM). Based on the evaluation result of the proposed system compare to google maps application on detecting traffic congestion, the system could find a similar condition as many as 17 times from 25 of testing.

关键词： Traffic Congestion Text Classification Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A Blockchain Technology-Based for University Student Enrollment Process

A Blockchain Technology-Based for University Student Enrollm...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Meyliana Surjandy Erick Fernando Cadelina Cassandra Henry Antonius Eka Widjaja Yakob Utama Chandra Harjanto Prabowo School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

University in Indonesia contemporary is looking for a solution to improve the university documentation such as certificate and transcript. But fake diploma certificate and transcript is an issue reported in several articles recently. The new technology called Blockchain has been elaborate and predicted can be used to solve the issue because of blockchain characteristics which are immutable, secure, tamperproof and unchangeable. The enrollment process is one of the vital process for university before the document can be made. Therefore, the research tries to elaborate deeply to create a model of the university student enrollment process. The research question of this research is how Blockchain Technology can be merge in the enrollment process? The model has been validated by several universities in Indonesia. Forum Group Discussion had been performed to discuss for enrollment process. In the end, many benefits come up from blockchain technology utilization to produce a reliable document such as diploma certificate and transcripts.

关键词： Government Blockchain Documentation Companies Forgery Reliability

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Prediction Methods for Credit Default on Peer to Peer Lending using Machine Learning

引用

Procedia computer science 2019年 157卷 38-45页

作者： Netty Setiawan Suharjito Diana Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Social lending or peer to peer lending (p2p lending) has emerged as a viable digital platform where lenders and borrowers can do business without the involvement of financial institutions. P2p lending has gained significant momentum recently, with some platform has reached billion-dollar loan circulation. However, p2p lending platforms are not free from any form of risks. A higher return on investment for investor comes with a risk of the loan and interest not being repaid. For this purpose, this research proposes a tree-based classification method for predicting whether a loan will go bad or default before the loan is approved. The high dimensionality of the dataset needs to be processed and chosen carefully. This paper proposes a Binary PSO with SVM to perform feature selection for the dataset and Extremely Randomized Tree (ERT) and Random Forest (RF) as the classifiers. In this research, BPSOSVM-ERT and BPSOSVM-RF are compared with several performance metrics. The experimental results show BPSOSVM can produce subset of features without decreasing the performance from the original features and ERT can outperform RF in several performance metrics.

关键词： P2P lending Random forest Extremely randomized tree PSO BPSO

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology Open Problems and Impact to Supply Chain Management in Automotive Component Industry

Blockchain Technology Open Problems and Impact to Supply Cha...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Surjandy Meyliana Hareco Leslie Hendric Spits Warnars Edi Abdurachman School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

The study of the adoption of Blockchain Technology (BT) of the Supply Chain Management System (SCMS) automotive components industry still in infancy. BT's previous research topic mostly in virtual currency, security, and IoT. However, the automotive market's significant development causes several issues in the SCMS automotive components industry, such as fake components. Blockchain Technology (BT), as identified, might be possible as a way out for the development of SCMS automotive components. There are several research questions in this research, such as how BT can facilitate SCMS open issues? What is the BT impact in the SCM area? The study method used the systematic literature review (SLR) method to gather all information from 12 publishers and an international index journal. Seven open issues identified in this study and SCM's core operational aspect, such as supplier, logistics, manufacturer, distribution, and customer, have been identified impact with BT.

关键词： Industries Supply chain management Manufacturing processes Systematics Blockchain Tools Security

来源：评论

学校读者我要写书评

暂无评论

Convolve4D: A Novelty Approach to Improve Convolutional Process

引用

IOP Conference Series: Earth and Environmental science 2021年第1期794卷

作者： Suryadiputra Liawatimena Edi Abdurahman Agung Trisetyarso Antoni Wibowo Wiedjaja Atmadja Fandy Effendi Ivan Sebastian Edbert Computer Science Department BINUS Graduate Program - Doctor ofComputer Science Bina Nusantara University Jakarta Indonesia 11480 ComputerEngineering Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia 11480 ComputerScience Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Convolutional neural networks (ConvNet or CNN) are deep learning algorithms that can process input images, assign meaning to various aspects or objects in the image (biases and learnable weight) and recognize one image from another. The bigger kernel size will take more time to process the *** present a novelty way to use a 4D rank tensor to improve a convolutional process. At the early stage of the Convolve4D development, the edge detection with 3×3 kernel and The Laplacian of Gaussian (LoG) with 5×5 kernel size was used to demonstrate the convolutional process improvement. The Convolve4D needs more elaboration to be used into a CNN algorithm. The advantage of convolve4D is only need 9 loops to calculate 81 outputs, whereas convolve2D need 9 × 9 × 3 × 1 × 7 × 7 = 11.907 loops. The result is 18.5% shorter when using a 5×5 kernel; it reduces from 0.54 seconds to 0.44 seconds for the edge detection convolution process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Blockchain Technology-Based for University Teaching and Learning Processes

A Blockchain Technology-Based for University Teaching and Le...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Meyliana Cadelina Cassandra Surjandy Henry Antonius Eka Widjaja Harjanto Prabowo Erick Fernando Yakob Utama Chandra School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Contemporary, Indonesia is looking for an innovative solution to securing diploma certificate and transcript from forgery. Several cases had been reported due to the usage of a fake transcript. One modus of using fake transcript is to enter a higher level of education and job promotion. The new technology found called Blockchain believes in solving the problem. Characteristics of Blockchain Technology such as secured, immutable, distributed, transparent seem to be matched with transcript document requirement. Therefore, the research tries to create a process model of the university teaching and learning process. Several studies have been done; however, no detailed process shown especially for teaching and learning activities. The research question is, how are teaching, and learning activities can be supported by Blockchain Technology? Qualitative method used in this research, focus group discussion with 9 reputable universities discussed the academic operation process and the result show that it is possible to adopt Blockchain Technology into the teaching and learning process to avoid forgery of university transcript documents.

关键词： Education Forgery Reliability Information management Contracts

来源：评论

学校读者我要写书评

暂无评论

Study of runway crosswind and tailwind potential for airport sustainability: A study of Soekarno Hatta airport, Cengkareng, Indonesia

引用

IOP Conference Series: Earth and Environmental science 2021年第1期729卷

作者： W Sardjono Zulkarnain H Kusnoputranto TEB Soesilo DN Utama J Sudirwan Information Systems Management Department BINUS Graduate Program - Master of Information Systems Management BINA NUSANTARA University Jakarta Indonesia 11480 Post Graduate Program School of Environmental Science University of Indonesia Jakarta Indonesia Faculty of Public Health University of Infonesia Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480 School of Information Systems Department BINUS Undergraduate Program Bina Nusantara University Jakarta Indonesia 11480

Airport runway designs must consider wind climatology to reduce the potential for crosswind and tailwind events that can cause accidents and aircraft delays. The large potential of crosswind and tailwind on a runway at the airport is very detrimental to aircraft passengers and airlines. Therefore, it is necessary to know the potential of crosswind and tailwind on the runway of Soekarno Hatta Airport and find the right parameters for the approximate direction and speed of the wind on the airport runway. Analysis was carried out using the direction and wind speed data from the Soekarno Hatta meteorological station in 2007-2017 to determine the potential for crosswind and tailwind on the runway of Soekarno Hatta airport and run a Weather Research and Forecasting (WRF) weather model to determine the parameterization of the right weather model for wind forecast at Soekarno Hatta airport. The highest maximum crosswind component in the 2007-2017 period occurred in August 30.53 knots, while the highest maximum tailwind of 25 knots occurred in January for a 250-degree runway and 24 knots occurred in August for a 070-degree runway. The potential for crosswind and tailwind is different every month. The scheme produces forecasts of wind direction and speed with a strong level of correlation with observations of wind direction and speed from the Soekarno Hatta meteorological station, the correlation value is 0.61. The most significant social impact of plane delays is time loss for passengers. While the economic impact on one of the crosswind events at Soekarno Hatta airport was an economic loss for one airline of US $ 43,392.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Innovation Architecture Smart Car Parking System with Wireless Sensor Networks

Innovation Architecture Smart Car Parking System with Wirele...

引用

International Conference on Information Technology, computer and Electrical Engineering (ICITACEE)

作者： Erick Fernando Harco Leslie Hendric Spits Warnars School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728172262

ISBN: (纸本)9781728172279

Nowadays, the number of cars is increasing every year, with the number of cars increasing, the parking areas will be limited. If parking areas can take more space in a town/place, it will be good for the town itself because nowadays the problem is either no parking space or too much parking space which is not suitable for human space. Moreover, because our population keeps going up and space is reducing even, we have to cut the forest to make space for parking lots, which is not suitable for our ecosystem. The number of cars itself also increasing each year, which is so problematic in road and infrastructure management. To fix this, we need to have a sound management system for maximizing the use of available space in town and minimizing the traffic in the road. The problem nowadays is a roaming car that searching for parking space and making road traffic and making massive pollution for the town. When a car searching for a parking slot inside a building that is crowded, it will go around the parking lot, and there will be traffic inside the parking lot because many cars will queue searching for empty parking slots. This means that the driver will also waste many fuels, which is not suitable for the ecosystem. Since this problem has not been fixed yet and the population is increasing each year, and a new way of driving and parking system is required, we want to propose a new system that uses the processor board, wireless sensor network to fix the problem.

关键词： Wireless sensor networks Roads Sociology Automobiles Fuels Statistics Vehicles

来源：评论

学校读者我要写书评

暂无评论

Saint-Venant Model Analysis of Trapezoidal Open Channel Water Flow using Finite Difference Method

引用

Procedia computer science 2019年 157卷 6-15页

作者： Gracia Natasha Suharjito Viska Noviantri Mathemathics Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

This study aims to compare the flow characteristics in rectangular and trapezoidal open channel by investigating the effects of Manning coefficient, channel bottom slope, channel width, and channel side slope which represented by modified Saint-Venant equation according to the channel cross section, which are rectangular and trapezoidal, and the slope of channel friction using the Manning coefficient. The equation is solved numerically by using finite difference methods with Forward Time Backward Space approach. The model is simulated by using python-based desktop application to show the flow characteristics. Computational results are displayed in the form of summaries, tables, two-dimensional graphics, and three-dimensional graphics. Validation is done by comparing computational results data with data from the other studies that have been done before and concluded that the simulation results have been valid and indicate compliance with the prior studies. The simulation results show that trapezoidal channel is better at minimizing the risk of flooding than rectangular channel in consideration of smaller discharge, smaller velocity, and lower water level.

关键词： Channel Water Flow Simulation Saint-Venant Equation Finite Difference Method

来源：评论

学校读者我要写书评

暂无评论

An Agile Implementation Model for ERP 4

An Agile Implementation Model for ERP

引用

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

作者： Wijaya, Santo Fernandi Prabowo, Harjanto Kosala, Raymondus Raymond Meyliana Information Systems Department Computer Science Department Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Management Department Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

The growing impact of industrial dynamics will be a challenge to increase productivity. Productivity is a demand for improving organizational performance. ERP systems are a way to increase productivity. Therefore, ERP implementation is important to ensure that ERP runs well. Critical factors in ERP implementation must get serious attention to project management. Even so, the reality of ERP implementation is slowly, even tends to experience failure, resulting in highly expensive. The previous research that carried out ERP implementation showed that the failure reached 40%, and the achievement of the benefits of ERP implementation in Indonesia is still not optimal. It can be said that ERP implementation is a complexity project. For this reason, it is necessary to consider other implementation methods that can overcome the problem in implementing ERP. An agile method is a proactive and reactive alternative to handle the problem in implementing of ERP. The development of an agile ERP model is one way to achieve success in ERP implementation. This research methodology is a survey approach to the study of literature. This research will propose an agile ERP model which will be used as an effective guide for achieving the success of ERP implementation. © 2019 IEEE.

关键词： Productivity

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：