检索结果-内蒙古大学图书馆

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Sulistyawan, Jason Sebastian Nugroho, Kuncahyo Setyo Isnan, Mahmud Pardamean, Bens Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Gastrointestinal diseases are significant health concerns that mostly affect the digestive and biliary tracts. These can only be observed internally through endoscopy, or a modern approach named Wireless Capsule Endoscopy. Though the approach has proven to work, the process relies heavily on medical experts, which is prone to error when given a considerably large load. The use of deep learning in detecting diseases with images has been proven to work in various cases and can be implemented for gastrointestinal diseases. This study compared four deep learning models based on Convolutional Neural Network architectures consisting of the VGG16, ResNet152V2, InceptionV3, and Xception for classifying colon disease images. The experiment showed that the ResNet152V2 performed the best, compared to the other three with a testing accuracy score of 0.9837. On the other hand, the VGG16 had the lowest performance with around accuracy score of 0.89 while the Xception and InceptionV3models yielded similar accuracy scores of 0.9587 and 0.9549, respectively. The results highlight the effectiveness of ResNet152V2 in handling the complexity of colon disease detection © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mobile Based Brand and Car Type Detection Using Convolutional Neural Network 8

Mobile Based Brand and Car Type Detection Using Convolutiona...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Ramadhan, Cahaya Saputra, Hasta Ragil Dewi, Ratna Sari Suharjito Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Although the parking lot is equipped with CCTV surveillance, car theft incidents still occur occasionally. These thieves exploit a loophole in the system that prevents the identification of the car's brand and model upon entering and exiting the parking lot using the same ticket. Therefore, the aim of this research is to develop a system capable of detecting the brand and model of cars. The study utilizes convolutional neural network technology and specifically focuses on the EfficientNet, MobileNet, and MobileNetV2 architectures due to their low resource requirements. Training images for the study are sourced from an online marketplace for used cars, with each of the 20 car brand and model variations consisting of 100 photographs. creates a model after being processed. For the prototype, the approach is put into practice through a mobile application. This study compares EfficientNet, MobileNetV1, and MobileNetV2 as the end result. EfficientNet scored 74%, MobileNetV1 74%, and MobileNetV2 66% on the test of accuracy. The accuracy increases to 80% after the EfficientNet has been tuned. © 2023 The Authors. Published by Elsevier B.V.

关键词： Convolutional Neural Network EfficientNet MobileNet V2 MobileNetV1 Parking system Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

An Object Driven Fuzzy Decision Model for Sugarcane Yield Prediction in Indonesia’s Sugar Industry

An Object Driven Fuzzy Decision Model for Sugarcane Yield Pr...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Ditdit Nugeraha Utama Muhammad Asrol Suharjito Christian Harito Napthaleni Muhammad Syafrudin Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul South Korea

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

A sugarcane yield of one plantation area depends on several independent variables. Practically it is challenging to predict accurately by using conventional methods. This study aims to develop a decision model based on a combination of fuzzy logic and object-oriented methods to predict sugarcane yield. The research is conducted in four main stages, employing object-oriented methods for model design and fuzzy logic for model construction. Object and activity diagrams are used for the object-oriented model design. The fuzzy membership functions employed are a combination of trapezoidal and triangular shapes. The resulting decision model can simulate 2,225 data from plantation areas in Indonesia. Based on the 10 examples of plantation area data in Indonesia, plantation number one obtained the largest sugarcane yield, which was 4.79%, with a similarity value of 0.90 (when compared to manual calculations as its ground truth). This similarity value is a higher value when compared to the average similarity value, which is 0.89.

关键词： Fuzzy logic Seminars Shape Object oriented modeling Plantations Manuals Predictive models Sugar industry Intelligent systems Information technology

来源：评论

学校读者我要写书评

暂无评论

Indonesian Automatic Speech Recognition with XLSR-53

arXiv

引用

arXiv 2023年

作者： Arisaputra, Panji Zahra, Amalia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

This study focuses on the development of Indonesian Automatic Speech Recognition (ASR) using the XLSR-53 pre-trained model, the XLSR stands for cross-lingual speech representations. The use of this XLSR-53 pre-trained model is to significantly reduce the amount of training data in non-English languages required to achieve a competitive Word Error Rate (WER). The total amount of data used in this study is 24 hours, 18 minutes, and 1 second: (1) TITML-IDN 14 hours and 31 minutes;(2) Magic Data 3 hours and 33 minutes;and (3) Common Voice 6 hours, 14 minutes, and 1 second. With a WER of 20%, the model built in this study can compete with similar models using the Common Voice dataset split test. WER can be decreased by around 8% using a language model, resulted in WER from 20% to 12%. Thus, the results of this study have succeeded in perfecting previous research in contributing to the creation of a better Indonesian ASR with a smaller amount of data. © 2023, CC BY-SA.

关键词： Statistical tests

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

Automatic Multiple Choice Question Generation: A Systematic Literature Review 9

Automatic Multiple Choice Question Generation: A Systematic ...

引用

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Isnan, Mahmud Nugroho, Kuncahyo Setyo Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, especially for educators. As a starting point for further development, a Systematic Literature Review (SLR) is conducted to uncover current trends, future challenges, and opportunities in automatic MCQ generation. Previously, an SLR was conducted, but it lacks coverage of the utilization of transformer-based models. This SLR covers the development of automatic MCQ generation using either traditional or advanced approaches such as Transformers. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used to gather the data from Scopus, IEEE Xplore, SpringerLink, arXiv, and Semantic Scholar. The included articles must be open-access computer science conference papers or journal articles and written in English less than five years ago. Four independent reviewers analyzed the research workflow, evaluation metric, and dataset used in each study. There are 18 included studies, where 17% (n = 3) studies are from 2024, 33% (n = 6) studies are from 2023, 22% (n = 4) studies are from 2022, 11% (n = 2) studies are from 2021, and 17% (n = 3) studies are from 2020. There are 33% (n = 6) of the studies used the traditional feature-based engineering approach, 39% (n = 7) of the studies used the Transformer-based model fine-tuning approach, and the remaining used novel approaches. The study found that BERT variants are the most utilized Transformer-based model in automatic MCQ. The research notes some challenges, but also open various opportunities for further research, including Large Language Model (LLM) utilization for automatic MCQ generation, the utilization BERT-based models for standardized machine-learned evaluation metrics, and the initiative for the creation of an MCQ dataset benchmark. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Perfomance Improvement of mpdCNN as Ensemble Learning Model on Low Resolution Image-Face Recognition System 8

Perfomance Improvement of mpdCNN as Ensemble Learning Model ...

引用

8th International Conference on Electronics, Materials Engineering and Nano-Technology, IEMENTech 2025

作者： Wangean, Daniel Anando Suhartono, Derwin Bina Nusantara University Master of Computer Science Binus Graduate Program Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331520762

Low resolution image-face recognition system is one of the challenging aspects of face recognition models' development. From machine learning, deep learning, and into ensemble learning are implemented to develop face recognition models. Including mpdCNN that published by Mishra in a journal article. This mpdCNN already achieved 88.6% accuracy score on SCFace dataset while published. Based on literature review, ensemble learning model can be improved by modifying parallel layers. The purpose of this research is to improve mpdCNN's performance by implementing some modifications include adding parallel layers, alternating the fusion layers, expanding the layers, and adding residual connections. Some modifications were successfully improved mpdCNN's accuracy score. By adding parallel layers and residual connections into mpdCNN's architecture, the modified mpdCNN that proposed in this research achieved 92.33% accuracy score, measured by Rank-k evaluation metric. © 2025 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Implementation of Face Patterns and Smile Recognition for Intelligent Class Attendance Systems 6

Implementation of Face Patterns and Smile Recognition for In...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Miftakhurrokhmat Suparyanto, Teddy Elwirehardja, Gregorius Natanael Karimah, Shofiyati Nur Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Department of Informatics Yogyakarta Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350345162

Students 'attendance in class is one important success parameter in face-to-face learning processes. Conventional attendance systems, such as paper-based attendance sheets or identity card systems, require a long time in the manual recapitulation process. Without additional verifications, even computer vision-based methods are prone to fraudulent practices by the students instead of gaining their excitement and attention in a class. To stimulate students' attention in a class, this work designs an intelligent class attendance system, in which facial pattern and smile recognition are implemented by using the latter as an additional task-based verification to reduce the risks of fake attendance. For the face recognition module, this pilot study used FaceNet as a feature extractor combined with SVM for classification, whereas the Haar cascade algorithm is used for recognizing smiles. This face recognition pipeline was implemented as a service installed on minicomputers or Internet of Things (IoT) devices in each classroom and connected to an IP camera. Every recorded attendance will be sent as a notification to a mobile application for students that requires their active participation to confirm it with a smiling self-photo. The proposed pipeline obtained 92.86% accuracy on the test data, and 66.67% accuracy when evaluated in a real-life simulation setting through the implemented system. The lower accuracy in the simulation indicated that further improvements are indispensable, especially since the model obtained 28.57% False Negative Rate. Future studies will need to acquire more data and experiment with more efficient methods of attendance verification. © 2023 IEEE.

关键词： class attendance convolutional neural network deep learning face recognition smile

来源：评论

学校读者我要写书评

暂无评论

Data Mining for the Global Multiplex Weekly Average Income Analysis

引用

Procedia computer science 2023年 219卷 52-59页

作者： Nicholas Dominic Gregorius Natanael Elwirehardja Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

The box office (BO) income had significantly declined up to 80% in 2020, as the COVID-19 pandemic emerged. To minimize further financial risks, multiplex (multiple cinema complexes) owners need to analyze their potential income for each movie, each week. Therefore, we developed a proper data mining strategy that allows multiplex owners to analyze and discover insights on how successfully produced movies could be. The methodology comprises (1) data loading and exploration, (2) data cleaning, (3) data selection, integration, and transformation using Pentaho, (4) data mining in which the results were stored in the MySQL database, and (5) pattern evaluation and presentation using Qlik Sense as the Business Intelligence (BI) dashboard. Based on our data mining methodology, we revealed that drama, comedy, action, and thriller are favorite genres. We also found that DreamWorks Animation and Pixar Animation Studios are both the most popular production houses, even Apatow Productions and Escape Artists still have the biggest revenue on average.

关键词： movie multiplex income data mining Business Intelligence dashboard

来源：评论

学校读者我要写书评

暂无评论

Using CNN and Transformer Model for Unimodal Speech Emotion Recognition on MELD and IEMOCAP

Using CNN and Transformer Model for Unimodal Speech Emotion ...

引用

Advancement in Data science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Clarence Aurelio Andry Chowanda Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Emotion Recognition is one field that is taking the world by storm in this current age. Multimodal emotion recognition has shown promising results however, previous studies shows that recognition using speech is a field has not performed that greatly. Previous research used popular methods such as CNN, RNN, and other machine learning methods has been used to achieved good results with the help of other modality, where if speech were to be used alone the results won't be as good. A factor that contributes to the result of the speech modality not performing as well is the fact of the dataset and the way it was processed. Therefore, this research looks into what makes speech one of the lowest performing modalities by preprocessing the dataset using a different method than previous researches as well as using a CNN model paired with a Transformer model. Results achieved from this research showed an improvement when using IEMOCAP by 8.09% and MELD by 1.06%. A comparison results of using the pre-processed data with previous studies model was also done to compare the results. In conclusion, this research has explored a different preprocessing method and deep learning model that has achieved results better than previous works with the same dataset.

关键词： Deep learning Hands Emotion recognition Storms Speech recognition Transformers Data models Mel frequency cepstral coefficient Speech processing Information systems

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：