检索结果-内蒙古大学图书馆

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

In general, the hospitality industry has been acknowledged as a major sector that gives a high contribution to economic development in many countries including Indonesia. For that reason, many initiatives have been implemented to help the growth of the hospitality industry in many countries including Indonesia to rebound from the harsh impact of the Covid-19 Pandemic. One such initiative is improving restaurant services as the main sector of the hospitality industry. This paper presents empirical results of sentiment analysis as a means to assess the quality of restaurant services as the first step to improving service quality. In particular, this study explores the aspect-based sentiment analysis method to identify some aspects of restaurant service which need improvement by learning the polarity of customers toward the restaurant services without having to meet the customers directly. By using the aspect-based sentiment analysis method, the customer sentiments comprising opinions, sentiments, evaluations, attitudes, and emotions from restaurant service can be analyzed using customers' online reviews as input. The main experiment findings showed that the Long Short-term Memory model can achieve high performance in predicting aspect polarization in restaurant service reviews. Other findings suggest that Sigmoid as an activation function achieved 0.97 average training accuracy and 0.69 average testing accuracy giving a better performance to the model in comparison to ReLU, Tanh, and ELU activation functions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Comparing the Effect of Attention Mechanism and Aspect Embedding on the Performance of Long Short-term Memory Model for Aspect-Based Sentiment Analysis

Comparing the Effect of Attention Mechanism and Aspect Embed...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The attention mechanism is one of the key enablers which have positioned transformer models as the state-of-the-art models in Natural Language Processing. By having the attention mechanism, the first version (vanilla) transformer model can retrieve the hidden state but at the same time can maintain a low requirement on the context vector dimension by selectively choosing to which encoder hidden states to give priority attention. The objective of this study is to evaluate the effect of modified Long Short-term Memory models architecture on the model performance as a predictive model. The first model is modified by adding an attention mechanism to its architecture;whilst, the second model is modified by adding additional input to its architecture. The performance of both models is compared by assigning each model the same task: to address the aspect-based sentiment analysis task. The experiment results show that adding an attention mechanism is not significantly increase the performance of the Long Short-term Memory model in comparison to adding input to the same model. In particular, the average training accuracy of the former model is 0.885;whilst, the average training accuracy of the latter model is 0.942. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Restaurant Customer Feedback Sentiment Analysis using Aspect Embedding Long Short-term Memory Model

Restaurant Customer Feedback Sentiment Analysis using Aspect...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

ISBN: (纸本)9798350320954

In the past ten years, there has been a proliferation of unstructured textual data from a variety of fields, allowing for the analysis of the sentiment polarity of the text authors in each of those datasets. To analyze sentiment polarity from unstructured data, machine learning tasks such as aspect-based sentiment analysis are used. The public dataset of restaurant patron feedback was used as the input for this study's empirical results of aspect-based sentiment analysis utilizing the Aspect Embedding Long Short-Term Memory model. The primary experiment's results show that the aspect embedding long short-term memory model can predict aspect sentiment polarization from customer feedback to restaurant service and aspect text representation (aspect text embedding) as input with excellent performance. For example, the Aspect Embedding Long Short-term Memory model, which uses ReLU as its activation function in the Dense layer tends to achieve higher performance (0.97 average accuracies) than the same model equipped with Sigmoid, and Tanh functions which achieve 0.954 and 0.956 average training accuracy respectively. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effect of Activation Function on Transformer Model Performance for Official Announcement Translator from Indonesian to Sundanese Languages

Exploring the Effect of Activation Function on Transformer M...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Wijanarko, Bambang Dwi Fitria Murad, Dina Heryadi, Yaya Tho, Cuk Hashimoto, Kiyota BINUS Online Learning Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Jakarta11480 Indonesia BINUS Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket Campus Phuket83120 Thailand

ISBN: (纸本)9798350320954

Automated language translation involving low-resource language has gained wide interest from many research communities in the past decade. One lesson learned from the past COVID-19 pandemic, particularly in Indonesia, is that many local Governments have to release regular public announcements to keep people following health protocol especially when they are in public areas. Many studies showed some evidence that rural people in Indonesia which covers a large proportion of Indonesia's population, feel more convenience receiving official announcements in their local language. However, translating official announcement from the national language to many local languages in Indonesia require many experienced bilingual translators and time. This paper presents exploration results in developing an automated language translator model to translate texts in Bahasa Indonesia to the Sundanese language. In particular, this study aims to explore the effect of ReLU, Sigmoid, and Tanh activation functions of the Vanilla Transformer Model on its translation performance. The experiment results showed that the activation function under study gives similar training accuracy (0.98). However, ReLU achieves better performance than Tanh in terms of validation accuracy, training loss, and validation loss. © 2023 IEEE.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Network-based Models as Bahasa Indonesia-Sundanese Language Neural Machine Translator

Recurrent Neural Network-based Models as Bahasa Indonesia-Su...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Wijanarko, Bambang Dwi Heryadi, Yaya Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Online Learning Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Sequential data are available in many domains including weather observation data, stock price, gene sequence, and many others. Sequential data processing is very instrumental as a solution to a variety of downstream tasks in Natural Language Processing such as language translation. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, language translation is not an easy computation task when there is a language-resource gap. This paper presents some empirical results from the exploration of the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU), the Long Short-term Memory (LSTM), and the Bidirectional Long Short-term Memory (Bi-LSTM) models as machine translation models from Bahasa Indonesia to the Sundanese language. These empirical results show that the Bi-LSTM achieved the highest performance (0.95 average training accuracy and 0.92 average testings BLEU score) compared to the RNN (0.93 average training accuracy and 0.91 average testings BLEU score), the GRU (0.88 average training accuracy and 0.89 average testings BLEU score), and the LSTM (0.92 average training accuracy and 0.91 average testings BLEU score) models. These results validate some previously reported studies that claim the Bi-LSTM model potentially outperforms the other recurrent neural network-based models when it is used to process sequence datasets. © 2023 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

Neural Machine Translation Approach for Low-resource Languages using Long Short-term Memory Model

Neural Machine Translation Approach for Low-resource Languag...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota Bina Nusantara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Communication is a form of translation that human learns naturally since early childhood. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. One example of high-impact language translation is translating health protocols from the World Health Organization to many national languages to prevent the spread of the Covid-19 virus. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of the Long Short-term Memory model as a machine translation involving Bahasa Indonesia and the Sundanese languages. Performance of the Sundanese language to Indonesian language translation is 0.93 average training and validation accuracy and 0.91 average testings BLEU score. Whilst, Indonesian language to Sundanese language translation is 0.92 average training and validation accuracy and 0.88 average testings BLEU score. Both models achieve 0.39 average training loss and 0.38 average validation loss. © 2023 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Revalidating the Encoder-Decoder Depths and Activation Function to Find Optimum Vanilla Transformer Model

Revalidating the Encoder-Decoder Depths and Activation Funct...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota Bina Nusantara University Graduate Program- Computer Science Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University Online Learning Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The transformer model has become a state-of-the-art model in Natural Language Processing. The initial transformer model, known as the vanilla transformer model, is designed to improve some prominent models in sequence modeling and transduction problems such as language modeling and machine translation. The initial transformer model has 6 stacks of identical encoder-decoder layers with an attention mechanism whose aim is to push limitations of common recurrent language models and encoder-decoder architectures. Its outstanding performance has inspired many researchers to extend the architecture to improve its performance and computation efficiency. Despite many extensions to the vanilla transformer, there is no clear explanation of the encoder-decoder set out depth in the vanilla transformer model. This paper presents exploration results on the effect of combination encoder-decoder layer depth and activation function in the feed-forward layer of the vanilla transformer model on its performance. The model is tested to address a downstream task: text translation from Bahasa Indonesia to the Sundanese language. Although the value difference is not significantly large, the empirical results show that the combination of depth = 2 with Sigmoid, Tanh, and ReLU activation function;and d = 6 with ReLU activation shows the highest average training accuracy. Interestingly, d = 6 and ReLU show the lowest average training and validation loss. However, statistically, there is no significant difference between depth and activation functions. © 2023 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Indonesian-Sundanese Language Machine Translation using Bidirectional Long Short-term Memory Model

Indonesian-Sundanese Language Machine Translation using Bidi...

引用

2023 International Conference on Computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of two models: the Long Short-term Memory and the Bidirectional Long Short-term Memory models as machine language translation models involving Bahasa Indonesia and the Sundanese language. The empiric results showed that the Bidirectional Long Short-term Memory model achieves higher performance as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.95 and 0.95 average training accuracy respectively;and 0.90 and 0.89 average testing BLEU scores respectively) than the Long Short-term Memory model as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.93 and 0.92 average training accuracy respectively;and 0.91 and 0.88 average testing BLEU scores). These results validate some previously reported studies that claim the Bidirectional Long Short-term Memory model potentially outperform the Long Short-term Memory model when it is used to process a sequence dataset. © 2023 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Simulation of large plausible tsunami scenarios associated with the 2019 Durres (Albania) earthquake source and adjacent seismogenic zones

引用

Mediterranean Geoscience Reviews 2024年第3期6卷 197-217页

作者： Xhafaj, Edlira Hassan, Hany M. Scaini, Chiara Peresan, Antonella Taiwan International Graduate Program (TIGP)–Earth System Science Program Academia Sinica and National Central University Academia Sinica Taipei 11529 Taiwan Institute of Earth Sciences Academia Sinica Taipei 11529 Taiwan Earthquake-Disaster and Risk Evaluation and Management (E-DREaM) Center National Central University Taoyuan 32001 Taiwan National Institute of Oceanography and Applied Geophysics OGS Via Treviso 55 Udine 33100 Italy National Research Institute of Astronomy and Geophysics NRIAG 1 Marsd Street Cairo Helwan Egypt

We present an analysis of the hazards of potential earthquake-generated tsunamis along the Albanian–Adriatic coast. The study adopts a case study approach to model plausible tsunamigenic events associated with the 2019 Mw 6.4 Durres (Albania) earthquake source zone. The approach combines current findings on regional tectonics and scenario-based calculations of potential tsunami impacts. The study’s goal is to analyse the propagation of tsunami waves generated by identified seismogenic sources (namely ALCS002 [Lushnje] and ALCS018 [Shijak]) and determine the tsunami risk assessment for Durres City on the Albanian–Adriatic coast. The sources can generate earthquakes with maximum moment magnitudes of Mw 7.5 and Mw 6.8, which are likely to trigger tsunamis that could cause significant impacts in the region. The modelling is performed deterministically with the NAMI DANCE numerical code, including scenarios associated with the largest plausible earthquake. The model integrates bathymetry and topography datasets of large and medium resolutions. Each tsunami scenario simulation is based on the solution of the non-linear shallow water equations used to generate maximum positive wave amplitudes (water elevation), travel time, and tsunami inundation maps. In Durres City, modelling indicates that medium-sized waves could reach up to 2.5 m inland, posing a significant danger to the city’s low-lying areas. The most substantial tsunami waves are expected to impact the area within the first 10 to 20 min. Combining inundation maps and information on exposed assets allows for identifying areas where damages can be expected. In terms of human impact, a preliminary analysis shows that the study area is prone to tsunami threat, with more than 138,000 inhabitants living in vulnerable urban areas of Durres City by 2036. The model’s capacity to capture details related to the presence of buildings is limited due to constraints posed by the resolution of bathymetry and topography datasets a

关键词： Albania Durres Earthquake-generated tsunami Tsunami hazard scenarios Tsunami modelling

来源：评论

学校读者我要写书评

暂无评论

Official and unofficial data supporting disaster risk management in medium-sized cities

引用

Natural Hazards Research 2023年第1期3卷 89-96页

作者： Amaral, Gabriel Corrêa Ferreira, Adriano Mota Sardinha, Diego de Souza Menezes, Paulo Henrique Bretanha Junker Marchezini, Victor Tiezzi, Rafael de Oliveira Institute of Science and Technology Federal University of Alfenas (UNIFAL) MG Poços de Caldas Brazil Graduate Program on Disaster Science Institute of Science and Technology São Paulo State University (UNESP) SP São José dos Campos Brazil Cemaden (National Center for Monitoring and Early Warning of Natural Disasters) SP São José dos Campos Brazil Federal University of São Carlos (UFScar) Nature Science Center SP Buri Brazil Natural Hazards Center Institute of Behavioral Science University of Colorado Boulder Colorado United States

The disaster database enables managers to support prevention, preparedness, and mitigation actions, especially in Latin American countries, where disaster risk data are scarce. This article surveys and analyses a database of disasters in a medium-sized municipality, using official (civil defense) and unofficial (documentary research) sources. The methodology was based on data collection between 1970 and 2021, being classified according to the Brazilian disaster Codification (COBRADE) and subsequent spatialization of information. The results indicated that 71% of the hazard events were registered in the “natural group” (NG), mainly related to heavy rainfall, and 29% in the “technological group” (TG), mostly associated with urban fires. Based on spatial analysis, 20 locations (“hotspots”) with the largest occurrences were identified, representing approximately 64.30% of (NG) total records. The city's central zone was the location with the highest number of occurrences (133), followed by Jardim Kennedy (64), in the South zone, and Serra São Domingos (53), in the North. The methodology developed is an important tool to support urban planning and disaster risk management in medium-sized cities. © 2023 National Institute of Natural Hazards, Ministry of Emergency Management of China

关键词： Cities disaster risk reduction Fires Flooding Landslides Storms

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：