检索结果-内蒙古大学图书馆

IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)

作者： Irene Anindaputri Iswanto Andry Chowanda Haryono Soeparno Widodo Budiharto Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350389692

ISBN: (纸本)9798350389708

In recent times, there has been considerable attention directed towards Facial Expression Recognition (FER) due to its extensive utility across diverse domains. However, the universality of facial expressions has been challenged by studies suggesting that cultural backgrounds significantly influence the perception and recognition of emotions. This paper addresses the need for culturally specific datasets in FER tasks, particularly in underrepresented regions like Indonesia. The study introduces dynamic images as an alternative input representation for facial expression recognition tasks, aiming to assess their efficacy using the Indonesian Mixed Emotions Dataset (IMED). Through experimentation using EfficientNet model, the performance of dynamic images is compared with static image and video inputs. Results indicate that dynamic images exhibit promising performance, with an accuracy of 94.28%. These results outperform static image datasets and nearly match the performance of video-based models, which achieved an accuracy of 97.93 %, despite using fewer data. Nonetheless, challenges such as data imbalance and the quality of generated dynamic images persist, suggesting avenues for further research and model refinement. This study provides valuable insights into methodological advancements in FER, particularly in limited dataset conditions, laying the groundwork for future developments in dynamic image-based facial expression recognition algorithms.

关键词： Emotion recognition Image recognition Accuracy Face recognition Heuristic algorithms Data models Cultural differences Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Facial Landmark Generation in Violin Performance using 3DCNN Network with Self Attention Model 48

Audio-Driven Facial Landmark Generation in Violin Performanc...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Lin, Ting-Wei Liu, Chao-Lin Su, Li Taiwan International Graduate Program Social Networks and Human-Centered Computing Taiwan Academia Sinica Institute of Information Science Taipei Taiwan National Chengchi University Department of Computer Science Taipei Taiwan

ISBN: (纸本)9781728163277

In a music scenario, both auditory and visual elements are essential to achieve an outstanding performance. Recent research has focused on the generation of body movements or fingering from audio in music performance. The audio-driven face generation technique in music performance is still deficient. In this paper, we compile a violin soundtrack and facial expression dataset (VSFE) for modeling facial expressions in violin performance. To our knowledge, this is the first dataset mapping the relationship between violin performance audio and musicians' facial expressions. We then propose a 3DCNN network with self-attention and residual blocks for audio-driven facial expression generation. In the experiments, we compare our methods with three baselines on talking face generation. The codes and dataset are available on the Github (https://***/kevinlin91/icassp-music2face). © 2023 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Powered Intent Classification for Indonesian E-Wallet Customer Service Chatbots

Artificial Intelligence-Powered Intent Classification for In...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Christopher Owen Derwin Suhartono 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)9798331506490

ISBN: (纸本)9798331506506

The rapid expansion of e-wallet services in Indonesia has significantly heightened the need for efficient customer service solutions, making chatbots an essential tool for user support. However, many providers continue to rely on rule-based chatbots, resulting in rigid interactions that struggle to meet diverse user needs or handle the linguistic complexities of the Indonesian language. This study addresses these limitations by developing an AI-powered intent classification model specifically tailored for Indonesian e-wallet customer service, aimed at delivering a more accurate, adaptive, and user-centered experience. A custom dataset was created from user comments on social media associated with Indonesia's top e-wallet providers, followed by data pre-processing and clustering using the BERTopic model. To improve interpretability, OpenAI's GPT-4 was employed for label refinement, resulting in enhanced clarity. Various models were tested, including IndoBERT, RoBERTa, and Convolutional Neural Network (CNN) architectures in both 2D and 3D configurations. The highest-performing model combined IndoBERT embeddings with a 3D CNN classifier, achieving an accuracy of 84.30%, precision of 84.33%, recall of 84.30%, and an F1-score of 84.24%. This study contributes a unique Indonesian-specific dataset and demonstrates the potential of AI to transform customer service interactions in Indonesia's e-wallet sector, offering a clear advancement over traditional rule-based approaches.

关键词： Adaptation models Solid modeling Three-dimensional displays Accuracy Online banking Intent recognition Customer services Transforms Chatbots Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep neural networks and weighted word embeddings for sentiment analysis of drug product reviews

引用

Procedia computer science 2023年 216卷 664-671页

作者： Derwin Suhartono Kartika Purwandari Nicholaus Hendrik Jeremy Samuel Philip Panji Arisaputra Ivan Halim Parmonangan Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

One of the major tasks of natural language processing is sentiment analysis. The web is a source of unstructured and rich informa-tion with thousands of opinions and reviews. Individuals, businesses, and governments can all benefit from recognizing sentiment. As part of this study, we propose a deep learning-based approach for sentiment analysis on drug product review data obtained from the UCI machine learning repository. As an alternative to deep learning models, this architecture integrates glove word embedding with convolutional neural networks (CNN). Word2vec and GloVe word embedding schemes have been evaluated empirically for their predictive performance in CNN architectures. Based on a comparison of the deep learning architecture with RoBERTa, itcan be seen that BERT architecture outperforms both of them in training and validation. However, CNN models using Glove word embedding provided superior results in testing.

关键词： transformers machine learning sentiment analysis weighted word embeddings

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Mixed Reality System in Machinery Vocational School: ICT Blueprint

Cloud-Based Mixed Reality System in Machinery Vocational Sch...

引用

2022 International Conference on science and Technology, ICOSTECH 2022

作者： Suryodiningrat, Satrio Pradono Gaol, Ford L. Supangkat, Suhono Harso Ranti, Benny Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University Faculty of Computing and Media Computer Science Department Jakarta Indonesia Bina Nusantara University Jakarta Doctor of Computer Science Graduate Program Jakarta Indonesia Smart City and Community Innovation Center Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9781665479851

Education is always the most important part of our lives. To make education make a significant impact on today's learners, teaching and learning must evolve to match with today's learner's profile. Any education including vocational education has an important role in economic development and one of the ways to maximize the contribution of vocational educations is strengthening the link and match with the world of work [1]. As the technology also keeps evolving and it is getting more and more advanced, one technology that has significant traction lately is the mixed reality system and is often used for education purposes. Most big ICT companies like Microsoft, and HTC are racing to develop mixed reality systems to help the teaching and learning process to be more effective and efficient. Where everything is cloud-based, having a cloud-based mixed reality system is just makes sense but will have a great challenge and considered as a big ICT project. One of the ways to make the ICT project successful is to make a blueprint before it is started. The objective of this paper is how to develop an ICT Blueprint for implementing a cloud-based mixed reality system for machinery vocational schools to make the project have a higher success rate. © 2022 IEEE.

关键词： Blueprints

来源：评论

学校读者我要写书评

暂无评论

Identification of Clustering Brisk Keypoint Feature in Grocery Product Using the Elbow Method

Identification of Clustering Brisk Keypoint Feature in Groce...

引用

IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT)

作者： Rissa Rahmania Maria Susan Anggreainy Iman Herwidiana Kartowisastro Widodo Budiharto Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350353464

ISBN: (纸本)9798350353471

In smart retail, the problem in grocery product image classification is fine-grained image representation. Product variants are characterized by differences in color, text, and size. However, while the process of image classification involves quite complex stages, there is still a misclassification of grocery products. This is because there are many areas of the image being calculated, which makes the models not optimally calculate the most important area. This paper aims to identify a number of patch image formations as an important area of the product by involving Binary Robust Invariant Scalable Keypoints (BRISK) as a feature descriptor, K-Means Clustering, and the elbow method. First, we experiment with the BRISK keypoint feature for grocery products with different categories of brands. Second, the keypoint features are clustered using K-Means clustering. Lastly, the number of clusters is analyzed using the elbow method to find the optimal number. The result shows that the number of clusters from 8 products has variations of 5, 5, and 6 clusters. Finally, each cluster represents an important area in forming patches to support fine-grained grocery product image classification.

关键词： Image color analysis Image representation Communications technology Pattern recognition Fourth Industrial Revolution Elbow Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Synonym Replacement Augmentation for Handling Data Imbalance in Personality Classification

Synonym Replacement Augmentation for Handling Data Imbalance...

引用

International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)

作者： Rilo Chandra Pradana Derwin Suhartono 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)9798350368970

ISBN: (纸本)9798350368987

The Myers-Briggs Type Indicator (MBTI) classification is a widely utilized instrument for personality assessment. However, it frequently encounters challenges due to imbalanced data distributions across personality dimensions. It is paramount to address this issue to enhance the accuracy and reliability of personality predictions. Most current research in this field is focused on data balancing techniques, such as oversampling and undersampling, which have been demonstrated to enhance model performance. Nevertheless, there is a dearth of research exploring text augmentation methods, particularly synonym replacement, for this purpose. This study examines the efficacy of synonym replacement as a data augmentation technique for MBTI classification. Experiments are conducted with varying levels of synonym replacement (10%, 30%, 50%, 70%, and 90%) to assess its impact on model accuracy and F1 scores across the four MBTI dimensions. Our findings indicate that low levels of synonym replacement, particularly at 10% to 50%, can enhance the performance of the model in predicting MBTI dimensions. On the other hand, a higher number of replaced words in the synonym replacement augmentation can harm the model's performance. These observations suggest that synonym replacement can effectively address data imbalance in MBTI classification, although its application must be tailored to specific personality dimensions.

关键词： Training Electrical engineering Accuracy Instruments Predictive models Data augmentation Data models Reliability Information technology Information systems

来源：评论

学校读者我要写书评

暂无评论

Recommendation News for Joumalist Based on Twitter Data Using CNN 6

Recommendation News for Joumalist Based on Twitter Data Usin...

引用

6th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2022

作者： Harvy, Ikrar Girsang, Abba Suganda Saragih, Melva Hermayanty Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350399615

Getting the update news fast is important for journalist. This study uses Twitter data which is fast and rich information for get the update news and useful for journalist. This study starts from collecting data from Twitter, then predicting the category of tweet using convolution neural network (CNN) algorithm. With convolution neural network data, Twitter can categorize 10 news categories that mention news to official Twitter media on Twitter social media. Scenario data in predicting news by dividing the data based on 70% training, 15% validation, and 15% testing. Then the data is converted into vector form where the convolution neural network predicts the data in vector form. The results show that, the convolution neural network is able to conduct the good performance based on the values of accuracy, precision, recall and f1 score. It also compares by the other methods. © 2022 IEEE.

关键词： classification news convolution neural network deep learning journalist Social media

来源：评论

学校读者我要写书评

暂无评论

Input Representation on Text Data for E-Commerce Product Review Summarization Using Graph Convolutional Network

Input Representation on Text Data for E-Commerce Product Rev...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Azani Cempaka Sari Yaya Heryadi Iman Herwidiana Kartowisastro Widodo Budiharto Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

This paper investigates recent advancements and methodologies in Automatic Text Summarization, a field that has garnered significant attention for its ability to condense lengthy documents into concise summaries while preserving key information and themes. The study examines the development of Automatic Text Summarization models, including both extractive and abstractive approaches. Additionally, the research delves into the use of graph convolutional networks for text representation in e-commerce product review summarization. The study employs an e-commerce dataset in conjunction with a graph convolutional network model, covering stages from preprocessing and tokenization to constructing graph-based data representation. The expected outcome is a graph-structured representation of input text data derived from Indonesian-language e-commerce product reviews.

关键词： Sentiment analysis Graph convolutional networks Reviews Text summarization Tokenization Multilingual Electronic commerce Meteors Recommender systems Postal services

来源：评论

学校读者我要写书评

暂无评论

Light Wasserstein Generative Adversarial Network with Gradient Penalty (LWGAN-GP) for Batik Nitik Synthetic

Light Wasserstein Generative Adversarial Network with Gradie...

引用

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

作者： Almuzhidul Mujhid Antoni Wibowo Ricky Reynardo Siswanto Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The development of research in the field of image generation can now be one of the tools to introduce a country's artistic culture. Indonesia is known as one of the countries with cultural diversity. Batik is one of Indonesia's most iconic cultural arts. GAN studies on batik have produced good images but still have a long training process. Several GAN techniques have been developed to create synthetic batik, one of the pioneering ones is BATIK-GAN which proposes a double flow model. Several GAN techniques have been developed to create good images, one of the best known and most widely used as a model is DCGAN due to its lightweight training and ability to produce good synthetic images. In this research we propose the Light Wasserstein Generative Adversarial Network model with Gradient penalty (LWGAN-GP) to be able to generate batik motif images. This model is proposed to produce a model that can perform a faster training process but can still produce good images. The experimental results of LWGAN-GP compared with DCGAN show that the computation time of DCGAN is faster than that of LWGAN-GP but LWGAN-GP is superior to the variety of images produced and is able to remain stable (without collapse mode).

关键词： Training Seminars Art Image synthesis Computational modeling Generative adversarial networks Data models Cultural differences Intelligent systems Information technology

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：