检索结果-内蒙古大学图书馆

Journalist system using named entity recognition based on Twitter location extraction

AIP Conference Proceedings 2023年第1期2691卷

作者： Abba Suganda Girsang Sani Muhamad Isa Raditya Fajar BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

Interactions that occur on Twitter social media are easier to do and can easily reach all levels of society, as well as conversations tweeted by users. They can easily spread information or issues that are developing. Based on this, the use of conversational data on the Twitter platform can get an overview of issues that are developing and even those that are just being formed from community conversations on this Twitter platform. Still related to previous research, which researched to implement the Twitter social media monitoring system to provide access to additional information for journalists. This study aligns with its predecessors but comes with a richer data collection mechanism, so it can gather more conversations. The difficulty to be answered in this study is the difficulty of journalist determining a bunch of location of an incident on a Twitter conversation, which describes the name of a place or contains the address of a location in it. Also in this study, there are additional modifications to extract location names using the NER model, which has been customized according to the structure of naming location names in Indonesia. So from the text of the Twitter conversation, whether it's an address name or a description of a location name, it can get a location name that refers to the name of a place where it could be the location where an event occurred. The results of an Indonesian language location NER model, with an accuracy score of 97.67%, with a precision value of 90.57%, recall 59.30% and f1-score 71.67%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with Greedy Layer-Wise Compound Scaling for Temperature and Humidity Prediction in Solar Dryer Dome

SSRN

引用

SSRN 2022年

作者： Cenggoro, Tjeng Wawan Elwirehardja, Gregorius Natanael Dominic, Nicholas Setiawan, Karli Eka Rahutomo, Reza Djuana, Endang Gunawan, Fergyanto E. Budiman, Arief S. Romeli, Sugiarto Pardamean, Bens Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States PT. Impack Pratama Industri Jakarta Indonesia

Drying has been an eco-friendly and cost-efficient method to reduce post-harvest losses of agricultural crops. In various countries, the technique has been widely utilized in the form of Solar Dryer Dome (SDD) buildings. Accurate indoor microclimate forecasting is very important to implement smart control systems in SDDs that can maintain the ideal conditions, as the availability of solar energy is limited only at daytimes and the temperature may drop significantly during nighttimes in remote areas. The microclimate variables that play an important role in maintaining ideal environmental conditions include temperature and relative humidity. © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluation Model of Urban Regional Knowledge Management Systems in Indonesia for Natural Disaster Mitigation

Evaluation Model of Urban Regional Knowledge Management Syst...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Wahyu Sardjono Maryani Astari Retnowardhani Erma Lusia Muhammad Zarlis Widhilaga Gia Perdana 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 Tourism Department Faculty of Economics & Communication Bina Nusantara University Jakarta Indonesia Post Graduate Program of Management Science State University of Jakarta Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Nearly the whole Indonesian Archipelago is threatened by earthquake hazards, both on a small and large scale. This indicates Indonesia's susceptibility to earthquakes, tsunamis, volcanic eruptions, and other geological calamities. With the assistance of other pertinent ministries and institutions, the National Disaster Management Agency (BNPB) in Indonesia is in charge of carrying out disaster management at the national level. In order for mitigation to function effectively and efficiently, this research is vital since it is based on the establishment of an evaluation model for an urban knowledge management system in Indonesia. The goal of the project is to create an assessment model for Indonesian urban knowledge management systems that can be applied to the deployment of autonomous socialization programs for disaster mitigation. Factor analysis and regression analysis are the primary techniques used in this work. Regression analysis is used to create a model that can represent the current state of mitigation socialization and be used to develop implementation strategies in the future. Factor analysis is used to identify dominant factors in the implementation of knowledge management systems that support independent socialization.

关键词： Prevention and mitigation Disasters Evaluation models Earthquakes Tsunami Knowledge management Regulation Regression analysis Synchronization Monitoring

来源：评论

学校读者我要写书评

暂无评论

High-Performance and Resource-Efficient IoT-based Sleep Monitoring System

High-Performance and Resource-Efficient IoT-based Sleep Moni...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Nico Surantha Oei Kurniawan Utomo Sani Muhamad Isa Computer Science Department BINUS Graduate Program-Master of Computer Science Jakarta Indonesia

ISBN: (数字)9781728152073

ISBN: (纸本)9781728140537

Recently, the number of people who have trouble sleeping is on the rise. It results in an increase in the number of car accidents, lower productivity and a higher risk of chronic disease. Advancing wearable and contactless health sensors offers the possibility of daily sleep quality monitoring that can be done on a regular basis by patients in their homes. The goal of this research is to propose the design of an Internet-of-Things (IoT) sleep quality monitoring system that can be integrated with a wearable or contactless sensor. The proposed platform architecture is based on micro-services and is event-driven. The simulation results show that the implementation of the IoT sleep quality monitoring system based on the proposed design decreases the response time by 55.85 per cent while increasing the throughput by 34.76 per cent compared to the traditional approach. On the other hand, the rate of increase in memory usage per instance replication for proposed method is lower than the traditional method.

关键词： Monitoring Logic gates Time factors computer architecture Sensor systems Throughput

来源：评论

学校读者我要写书评

暂无评论

Contribution of Virtual Reality Technology to Increase Student Interest in Vocational High Schools

Contribution of Virtual Reality Technology to Increase Stude...

引用

2021 International Seminar on Intelligent Technology and Its Application, ISITIA 2021

作者： Maulana, Fairuz Iqbal Pangestu, Gusti Sano, Albert Verasius Dian Purnomo, Agung Rahmadika, Sandi Widartha, Vandha Pradwiyasma Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Business School Undergraduate Program Entrepreneurship Department Jakarta11480 Indonesia Graduate School Pknu Pukyong National University Interdisciplinary Program of Information Security Busan Korea Republic of Telkom University Information System of Industrial Engineering Faculty Bandung Indonesia

ISBN: (纸本)9781665428477

This research investigates the feasibility of school-based learning using Virtual Reality technology in Electric Power Generation learning during the COVID-19 pandemic. This research employs a qualitative approach. Vocational High School Nurul Jadid Paiton Probolinggo is the site of this study. Data was gathered through observation, literature review, and interviews. In the Electrical Engineering section, interviews were conducted with a teaching instructor. Triangulation was used to investigate the data's authenticity, in addition to further interviews with the curriculum staff and instructors at the school. The teacher's assessment of learning media using Virtual Reality application technology shows valid criteria with an average value of 3.6. In comparison, after using the Virtual Reality application learning media, the assessment of students obtained an average value of 3.77 compared to conventional assessments with an interval of 2.71. The use of Virtual Reality technology has proven that it can help and facilitate student learning. The use of technologies of Virtual Reality as a means of learning in classrooms will also be an alternate option for virtual laboratories during the COVID-19 pandemic. © 2021 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Autonomous car using CNN deep learning algorithm 2

Autonomous car using CNN deep learning algorithm

引用

2nd Annual Conference of science and Technology, ANCOSET 2020

作者： Sonata, I. Heryadi, Y. Lukas, L. Wibowo, A. Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Jl. Kyai H. Syahdan No.9 Jakarta11480 Indonesia Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Jl Jend. Sudirman No.51 Jakarta12930 Indonesia

Autonomous cars have become an interesting discussion in recent years. Several major automotive industries such as Tesla, GM and Nissan are trying to become pioneers in autonomous car technology. Giant technology companies such as Google Waymo, Baidu and Aptiv also developing autonomous car technology. Several technological approaches are carried out in implementing autonomous cars for recognizing surrounding situations, such as radar, lidar, sonar, GPS, and odometry. An automatic control system is used to control navigation based on the data obtained from these sensors. This paper will discuss the use of CNN deep learning algorithm for recognizing the surrounding environment in creating the automatic navigation required by autonomous cars. The system designed will create and learn the data set that will be taken in advance and the learning outcomes will be implemented in an open simulation system. This simulation shows high accuracy in learning to navigate the autonomous car by observing the surrounding environment. © Published under licence by IOP Publishing Ltd.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Quality Analysis the E-PASTI System to Determine the Condition of the System and Information Quality

Quality Analysis the E-PASTI System to Determine the Conditi...

引用

2019 International Conference of science and Information Technology in Smart Administration, ICSINTeSA 2019

作者： Nugraha, Bayu Marleny, Finki Dona Sfenrianto, Sfenrianto Edwina, Cinthya Information System Program Faculty of Science and Technology Sari Mulia University South Kalimantan Banjarmasin Indonesia Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia

The purpose of this study is to evaluate the quality of secretarial, financial and staffing information systems at the Directorate General of AHU, known as the E-PASTI system. There are two variables analysed, namely system quality and information quality. Data collection using questionnaires that distributed to 123 employees who used the E-PASTI system but returned 93 questionnaires. Data quality analyst uses descriptive quantitative method. The results of the study are several conditions related to the system and information quality of E-PASTI. The quality can be a reference for the AHU Directorate General to improve the quality of E-PASTI that suits the needs of employees. © Published under licence by IOP Publishing Ltd.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Downstream Task Performance of Pre-Trained Model For Outdoor Audio Event Classification

Downstream Task Performance of Pre-Trained Model For Outdoor...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

作者： Theresia Herlina Rochadiani Yaya Heryadi Ilvico Sonata Lukas Wawan Suparta BINUS Graduate Program- Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

Our surroundings’ auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (AEDC) systems has a great deal of potential applications in environmental monitoring, security, surveillance, and driverless cars. Even though AEDC has advanced significantly in indoor settings, difficulties still exist outside because of the variable and changing acoustic conditions brought on by elements like the weather, different sound sources, and ambient noise from traffic and industry. This study suggests an outdoor audio event categorization model based on convolutional neural networks (CNNs). The suggested model shows passable accuracy by utilizing adaptation to the downstream task using the ESC-50 dataset and transfer learning from a pre-trained model. The effectiveness of multi-class audio classification models in downstream tasks is analyzed in this paper, with an emphasis on the effect of an increasing number of output classes on accuracy. Three models—three, four, and five classes—with different output class configurations are used in the study, and their training and validation accuracies are assessed. Although the accuracy scores above 80% are commendable, the data show a discernible reduction in performance as the number of classes rises. Notably, the three-class model attains a validation accuracy exceeding 90%, whereas the four-class and five-class models exhibit reduced accuracies, falling below 90% and 85%, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction Using LSTM and Search Economics Optimization

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2020年第4期47卷 1-7页

作者： Girsang, Abba Suganda Lioexander, Fernando Tanjung, Daniel Computer Science Department BINUS Graduate Program-Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Long Short-Term Memory (LSTM) has been one of the most popular methods in time-series forecasting. Within the LSTM architecture, there are hyperparameters present that need to be optimized in order to achieve the optimum results. In order to optimize these hyperparameters, a metaheuristic optimization method was used. A metaheuristic algorithm was used as a way to reduce both time and computational complexity. We used the Search Economics algorithm because we found the algorithm quite interesting while being unpopular. The evaluation was carried out by using Root Mean Square Error (RMSE) as the primary metric used for the optimization. The dataset being used in this experiment is the stock price of one of the most well-known financial institutes in Indonesia. The SE-Optimized LSTM was able to create a prediction that did not overfit with RMSE of 538.92, which was great compared to the unoptimized LSTM model with RMSE of 661.041 and ARIMA model with RMSE of 2809.015. © 2020. All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming Algorithm using Furniture Industry 0/1 Knapsack Problem

Dynamic Programming Algorithm using Furniture Industry 0/1 K...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Mietha Anditta Natashya Amartya Laurens Spits Warnars Harco Leslie Hendric Spits Warnars Arief Ramadhan Teddy Siswanto Teddy Mantoro Nurulhuda Noordin Computer Science Departement School of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Departement School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Departement BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia PJJ Informatika Telkom University Bandung Indonesia Information Systems Department Trisakti University Jakarta Indonesia Faculty of Engineering and Technology Sampoerna University Jakarta Indonesia School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Malaysia

Dynamic programming is a fundamental algorithm that can be found in our daily lives easily. One of the dynamic programming algorithm implementations consists of solving the 0/1 knapsack problem. A 0/1 knapsack problem can be seen from industrial production cost. It is prevalent that a production cost has to be as efficient as possible, but the expectation is to get the proceeds of the products higher. Thus, the dynamic programming algorithm can be implemented to solve the diverse knapsack problem, one of which is the 0/1 knapsack problem, which would be the main focus of this paper. The implementation was implemented using C language. This paper was created as an early implementation algorithm using a Dynamic program algorithm applied to an Automatic Identification System (AIS) dataset.

关键词：

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：