检索结果-内蒙古大学图书馆

Automatic question generation for bahasa indonesia examination using copynet

Procedia Computer Science 2024年 245卷 953-962页

作者： Matthew Martianus Henry Gregorius Natanael Elwirehardja Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 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

In educational institutions, an educator is responsible for assessing the student's knowledge grasp through examination. Creating exam questions, even the low-level factoid questions, is time-consuming, especially for inexperienced educators. Therefore, this study aims to create a sequence-to-sequence model using CopyNet by exploiting its copying mechanism advantage to automatically generate Bahasa Indonesia factoid questions to ease the educator's burden. Indonesian records in the TyDi QA dataset are used as the model input. GRU and Bi-GRU are employed as the CopyNet encoder, while LSTM is used as the CopyNet decoder. The model that utilizes GRU as the encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.28, 0.19, 0.14, 0.1, and 0.32, respectively. Bi-GRU utilization as the model encoder achieves BLEU1, BLEU2, BLEU3, BLEU4, and ROUGE-L scores of 0.26, 0.17, 0.12, 0.09, and 0.30, respectively. Models using either encoder still achieve low scores. However, compared with the previous work, the result is still on par regarding the BLEU score. Further examination found that the generated questions do not adhere to semantic and syntactical correctness. Adding more records to the dataset and utilizing a more advanced architecture like CopyBERT are encouraged to improve the model performance in future work. Despite the result, this study has shown that CopyNet, primarily designed for text summarization or single-turn dialogue, can be tailored for factoid question generation.

关键词： Automatic question generation Bahasa Indonesia Copying mechanism Natural language generation Sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks for Scops Owl Sound Classification

引用

Procedia Computer Science 2021年 179卷 81-87页

作者： Alam Ahmad Hidayat Tjeng Wawan Cenggoro Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 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

Adopting a deep learning model into bird sound classification tasks becomes a common practice in order to construct a robust automated bird sound detection system. In this paper, we employ a four-layer Convolutional Neural Network (CNN) formulated to classify different species of Indonesia scops owls based on their vocal sounds. Two widely used representations of an acoustic signal: log-scaled mel-spectrogram and Mel Frequency Cepstral Coefficient (MFCC) are extracted from each sound file and fed into the network separately to compare the model performance with different inputs. A more complex CNN that can simultaneously process the two extracted acoustic representations is proposed to provide a direct comparison with the baseline model. The dual-input network is the well-performing model in our experiment that achieves 97.55% Mean Average Precision (MAP). Meanwhile, the baseline model achieves a MAP score of 94.36% for the mel-spectrogram input and 96.08% for the MFCC input.

关键词： acoustic features bird sound classification convolutional neural network mean average precision scops owl

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network-based Ancient Sundanese Character Classifier with Data Augmentation

引用

Procedia Computer Science 2021年 179卷 195-201页

作者： Alam Ahmad Hidayat Kartika Purwandari Tjeng Wawan Cenggoro Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 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

With an increasing interest in the digitization effort of ancient manuscripts, ancient character recognition becomes one of the most important areas in the automated document image analysis. In this regard, we propose a Convolutional Neural Network (CNN)-based classifier to recognize the ancient Sundanese characters obtained from a digital collection of Southeast Asian palm leaf manuscripts. In this work, we utilize two different preprocessing techniques for the dataset. The first technique involves the use of geometric transformations, noise background addition, and brightness adjustment to augment the imbalanced samples to be fed into the classifier. The second technique makes use of the Otsu’s threshold method to binarize the characters and only uses the usual geometric transformations for the data augmentation. The proposed network with different data augmentation processes is trained on the training set and tested on the testing set. Image binarization from the second technique can outperform the performance of the CNN-based classifier upon the first technique by achieving a testing accuracy of 97.74%.

关键词： ancient sundanese characters convolutional neural network data augmentation document image analysis Otsu’s threshold method

来源：评论

学校读者我要写书评

暂无评论

Systematic Evaluation of Cross Population Polygenic Risk Score on Colorectal Cancer

引用

Procedia Computer Science 2021年 179卷 344-351页

作者： Bharuno Mahesworo Arif Budiarto Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 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

The number of findings in cancer genomics research has grown rapidly in the last decade due to the decline in the cost of human sequencing and genotyping. However, the majority of the reported significant marker associated with cancer traits are based on European and East Asian population. Large population such as South Asian and South-East Asian population are under-represented in genomics research. In this study, we explored the possibility of computing a Polygenic Risk Score (PRS) of colorectal cancer on our test sample based on reported significant Single Nucleotide Polymorphism (SNP). The SNPs used to compute the risk score were collected from GWAS Central and GWAS Catalog. Significant SNPs from IC3 study were used as a benchmark. The result shows that calculating colorectal cancer risk score using reported significant marker from different population group is possible. The p-value of our statistic model shows significant differences between case and control group risk score.

关键词： Polygenic Risk Score Cross Population Colorectal Cancer

来源：评论

学校读者我要写书评

暂无评论

Repurposing transfer learning strategy of computer vision for owl sound classification

引用

Procedia Computer Science 2023年 216卷 424-430页

作者： Kevin William Gunawan Alam Ahmad Hidayat Tjeng Wawan Cenggoro Bens Pardamean Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

Accurately predicting an owl species based on its sound can be helpful for owl conservation. To build an accurate model for owl sound classification, deep learning is currently the most preferred algorithm, due to its excellent performance for modeling audio data. However, deep learning is generally underperformed for a small dataset, which is the case for recognizing scops owl sound. To overcome the issue, we proposed a transfer learning strategy, which is common for computer vision tasks, that can alleviate overfitting in a deep learning model for the owl sound classification. In our approach, we propose a neural network architecture consisting of the backbone of a EfficientNet model pre-trained on the massive ImageNet database. The model takes the sound input that has been converted as two image representations: Spectrogram and Mel Frequency Cepstral Coefficients. Our strategy enables the use of a relatively small size of pre-trained image classification model, which is widely available, for transfer learning in owl sound classification. Deploying the lightweight model in an automatic sound classifier provides a fast and accurate tool for various owl conservation purposes.

关键词： acoustics deep learning bird sound species detection transfer learning

来源：评论

学校读者我要写书评

暂无评论

Ten-Year Compilation of #SaveKPK Twitter Dataset

Ten-Year Compilation of #SaveKPK Twitter Dataset

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Reza Rahutomo Arif Budiarto Kartika Purwandari Anzaludin Samsinga Perbangsa Tjeng Wawan Cenggoro Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Politic is one of the most favorite topics to discuss in social media for people in Indonesia. It was proven when a people movement to support the Commission of Corruption Eradication (KPK) named #SaveKPK has been enlived for ten years and become a trending topic on Twitter for several times. In this research, all tweets contain `#SaveKPK' are crawled and compiled using an alternative algorithm to get twitter historical data instead of using Twitter API. The result described the characteristic of the dataset statistically, from the most frequently used words to the most active users. A clustering algorithm named Latent Dirichlet Allocation (LDA) was run over the gathered text dataset to discover most relevant keywords using unsupervised learning approach.

关键词： Twitter Computer science Resource management Natural language processing Information management Databases

来源：评论

学校读者我要写书评

暂无评论

Database Management System Design with Time Series Modification for Child Growth and Malnutrition Monitoring in The Regency of Serdang Bedagai

Database Management System Design with Time Series Modificat...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Reza Rahutomo Ika Nurlaila Anzaludin Samsinga Perbangsa Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia BINUS Online Learning Bina Nusantara University Jakarta Indonesia School of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

A poor data management has led zero stunting strategy in Indonesia moved nowhere. Some justifications on the demography and numbers of affected children remain a matter of plain assumptions without a clear supporting data. We hence develop a database system which enables time series monitoring on the expected increment of children's physical growth. At this initial step, our database system will be implemented at Public Health Office (Dinas Kesehatan) of Serdang Bedagai, South Celebes. This is a modification from Connoly and Begg's principles. Our database was built through 3-steps design started with conceptual followed by logical and at final step was normalizations-enriched physical design. By implementing this proposed system, the assigned healthcare workers will be able record every bit of superficial growth increase. Information obtained in the study is of essence for the efficient and effective intervention formula to achieve national zero stunting goal.

关键词： Pediatrics Monitoring Database systems Dictionaries Drugs Public healthcare

来源：评论

学校读者我要写书评

暂无评论

RHC: A Dataset for In-Room and Out-Room Human Counting

引用

Procedia Computer Science 2021年 179卷 33-39页

作者： Bens Pardamean Hery Harjono Muljo Faizal Abid Herman Albert Susanto Tjeng Wawan Cenggoro Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Accounting Information Systems Program Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

In recent years, research in human counting from CCTV (Closed Circuit Television) images have found an increasing demand to be deployed in real-world applications. The applications have been implemented in various settings, both indoor and outdoor. In the case of indoor setting, we found a type of room setting that conveys a problem to human counting model if we need to count only humans inside a room. With this respect, we present RHC (Room Human Counting) dataset, which images are captured in the aforementioned setting. The dataset can be used to develop a robust model that can differentiate between humans inside and outside a room. The dataset is publicly available at https://***/datasets/vt5c8h6kmh/1.

关键词： dataset human counting crowd counting in-room out-room

来源：评论

学校读者我要写书评

暂无评论

Health Assistant Wearable-Based Data Science System Model: A Pilot Study 3

Health Assistant Wearable-Based Data Science System Model: A...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Budiarto, Arif Febriana, Trisna Suparyanto, Teddy Caraka, Rezzy Eko Pardamean, Bens Computer Science Department Bina Nusantara University School of Computer Science Jakarta11480 Indonesia Information Systems Department Bina Nusantara University School of Information Systems Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Indonesia Faculty of Science National University of Malaysia School of Mathematical Science Bangi43000 Malaysia Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9781538658215

The rapid development of Information and Communication Technology (ICT) has an impact on the innovation of new technology that gives benefits for health. One of its latest development is wearable device technology. Nowadays, the growth of this technology market is very positive. But unfortunately the growth of this technology is not followed by the availability of supporting applications that provide maximum benefits for users by utilizing personal health and activity data. This paper is intended to provide a report of our initial research in developing a health assistant solution that utilizes wearable device generated data. The whole research process is executed using Design Thinking approach that put the users as the main consideration. This initial research is started by designing a field research that can potentially gathered users' data generated from wearable device. A series of statistical and machine learning techniques are presented to analyze time series data to create a model. Finally, to implement the model, a mobile application prototype is also proposed. The outcomes from this initial research will be used to develop a fully working solution. © 2018 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Digitizing Farmers' Land Data Collection Systems in Indonesia with the Use of Tani Millenial Apps 4

Digitizing Farmers' Land Data Collection Systems in Indonesi...

引用

4th International Conference on Cybernetics and Intelligent System, ICORIS 2022

作者： Bimantio, Mohammad Prasanto Putra, Dian Pratama Suparyanto, Teddy Ferhat, Amallia Nugraha, Nanda Satya Hidayat, Alam Ahmad Pardamean, Bens Institute of Agriculture STIPER Department of Food and Agricultural Technology Yogyakarta Indonesia Institute of Agriculture STIPER Department of Agrotechnology Yogyakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Institute of Agriculture STIPER Department of Agricultural Socio-Economics Yogyakarta Indonesia Institute of Agriculture STIPER Department of Forestry Yogyakarta Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665453950

In this era of digital world information, farmers face challenges about information management of huge data and the complexity of processes in precision farming. The data collection carried out so far can cause several difficulties, especially if the data is needed by the government or academics to support decision-making. Agricultural data collection applications only cover 12% of the market share of Android-based agriculture-based applications. In this study, Tani Milenial application is present as an alternative to support agricultural data collection activities in Indonesia. This application encourages farmers to be active and contribute independently to their role as subjects of agricultural development and is accustomed to digitally recording their agricultural activities. In this developed application system, the community, especially farmers and farmer groups, will find it easier to get information about agricultural potential data around where they carry out agricultural activities and can access this information online. Tani Milenial works as a guide to help farmers and transform agriculture but still have some gaps which should be checked and removed. The data collected can be used by various parties for research and decision-making. The app can be further improved to develop new features related to education, market information, and goods. © 2022 IEEE.

关键词： Decision making

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：