检索结果-内蒙古大学图书馆

Speed Bump Detection Through Inertial Sensors and Deep Learning in a Multi-contextual Analysis

SN computer science 2023年第1期4卷 18页

作者： Menegazzo, Jeferson von Wangenheim, Aldo Graduate Program in Computer Science (PPGCC) Image Processing and Computer Graphics Lab (LAPIX) Brazilian National Institute for Digital Convergence (INCoD) Department of Informatics and Statistics (INE) Federal University of Santa Catarina (UFSC)-Florianópolis Santa Catarina Brazil

Speed bumps are vertical raisings of the road pavement used to force drivers to slow down to ensure greater safety in traffic. However, these obstacles have disadvantages in terms of efficiency and safety, where the presence of speed bumps can affect travel time and fuel consumption, cause traffic jams, delay emergency vehicles, and cause vehicle damage or accidents when not properly signaled. Due to these factors, the availability of geolocation information for these obstacles can benefit several applications in Intelligent Transportation System (ITS), such as Advanced Driver Assistance Systems (ADAS) and autonomous vehicles, allowing to trace more efficient routes or alert the driver of the presence of the obstacle ahead. Speed bump detection applications described in the literature employ cameras or inertial sensors, represented by accelerometers and gyroscopes. While camera-based solutions are mature with evaluation in different contextual conditions, those based on inertial sensors do not offer multi-contextual analyses, being mostly simple applications of proof of concept, not applicable in real-world scenarios. For this reason, in this work, we propose the development of a reliable speed bump detection model based on inertial sensors, capable of operating reliably in contextual variations: different vehicles, driving styles, and environments in which vehicles can travel to. For the model development and validation, we collect nine datasets with contextual variations, using three different vehicles, with three different drivers, in three different environments, in which there are three different surface types, in addition to variations in conservation state and the presence of obstacles and anomalies. The speed bumps are present in two different pavement types, asphalt and cobblestone. We use the collected data in experiments to evaluate aspects such as the influence of the placement of the sensors for vehicle data collection and the data window size. Afterwar

关键词： Autonomous vehicles Deep learning Inertial sensors Intelligent transport systems Road conditions Speed bump

来源：评论

学校读者我要写书评

暂无评论

Video Quality Indicators for Video-Based Learning System in Higher Education 23

Video Quality Indicators for Video-Based Learning System in ...

引用

9th International Conference on Frontiers of Educational Technologies, ICFET 2023

作者： Zulkarnain, Novan Prabowo, Harjanto Gaol, Ford Lumban Isa, Sani Muhamad Computer Science Department BINUS Graduate Program Computer Science Information System Bina Nusantara University Indonesia Department School of Information System Bina Nusantara University Indonesia Management Department BINUS Business School Undergraduate Program Information System Department School of Information System Bina Nusantara University Indonesia

ISBN: (纸本)9798400707353

Higher education worldwide has adopted Video-Based Learning (VBL) over the past decade. They have tried to build a VBL system to improve services to students. However, the researcher's topic was not fully explored, especially in making the video itself. What features are mandatory and must be considered in making a video lecture to increase student engagement. A systematic review of the literature (SLR) is a way to identify these features. This study provides a critical analysis of the current research in VBL over the last five years (2017 - 2021). It presents a general trend examining 1336 journals and many literary works related to VBL design in Higher Education, selected through a stepwise process based on PRISMA Framework guidelines, using pre-defined selection criteria. We carefully selected 32 journals and found 22 features referring to the Lecture Video Design succession. © 2023 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Implementation of computer Vision of Jakarta Weather Image Categorization Using ResNet

引用

Procedia computer science 2023年 227卷 813-822页

作者： Kartika Purwandari Join W.C. Sigalingging Alam Ahmad Hidayat Tjeng Wawan Cenggoro Bens Pardamean 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

At the moment, weather data is crucial for supporting neighborhood activities. The economy and trade are both centered in Jakarta, which is also Indonesia's capital. Therefore, it is crucial to have access to weather information so that these activities don't get disrupted, which would then hinder commercial and trade activity. Social media has been a very popular tool for spreading information recently. Particularly on Instagram, where users favor taking images and sharing the information they encounter. @jktinfo is the Instagram account that posts information about the situation in Jakarta and the area, including the current weather. The @jktinfo account is utilized in this project to gather data. Utilizing a variety of techniques, the collected photographs of sunny, cloudy, and wet situations were.

关键词： computer vision weather image categorization data augmentation deep transfer learning residual network

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

Implementation of Dynamic Image for Facial Expression Recognition on Indonesian Facial Expression Dataset

Implementation of Dynamic Image for Facial Expression Recogn...

引用

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

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

Machine Learning Implementations in Childhood Stunting Research: A Systematic Literature Review 8

Machine Learning Implementations in Childhood Stunting Resea...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Rahutomo, Reza Elwirehardja, Gregorius Natanael Isnan, Mahmud Asadi, Faisal Pardamean, Bens School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Binus Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

Childhood stunting is a condition anticipated to affect the growth potential of children under the age of five. With numerous stunting researches that have been conducted, stunting datasets are now widely available to facilitate stunting research. This provides an opportunity to implement machine learning (ML) principles to produce a broader insight or a novel technique in stunting prediction. A systematic literature review is necessary to discover the landscape of machine learning implementation in the application domain as a preliminary study for creating an effective research roadmap. This paper presents a systematic literature review (SLR) of 22 curated manuscripts that focuses on identifying the ML models applied in stunting research, as well as the datasets used in such studies that were published during 2017-2022. The SLR process found that ML principles have been applied in stunting research since 2017, and the diversity of ML implementation has become more varied in 2021-2022. In terms of ML models, XGBoost and Random Forest are recognized as the two most utilized models, and stunting prediction is the most common ML implementation. The majority of stunting research utilizing ML has been conducted in Indonesia. Although national survey data has been the most commonly utilized dataset in stunting research, researchers in Indonesia have shown a preference for utilizing data from regional or independent surveys. This study will be followed by developing a classifier model for stunted children using XGBoost and Random Forest algorithms. The model will be trained on a dataset generated from StuntingDB. © 2023 IEEE.

关键词： Machine learning

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

Classifying Argument Component using Deep Learning on English Dataset

Informatica (Slovenia)

引用

Informatica (Slovenia) 2023年第5期47卷 63-68页

作者： Gunawan, William Suhartono, Derwin Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

The study focuses on the argument component in argumentation mining, specifically examining claim and premise types. Various datasets exist for argumentation components, each with different classes. The study evaluates the performance of deep learning architectures, particularly using contextual embedding as the initial layer. Six datasets with diverse argument components are used for validation. The research provides a comprehensive comparison of deep learning architectures, combining multiple layers such as BERT or word embedding with LSTM, GRU, or CNN. The results and their implications are discussed in the concluding section of the journal. The study demonstrates significant results with the BERT-BiGRU-CRF architecture after conducting several experiments. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Database Design for Pre-Eclampsia Case Administration 8

Database Design for Pre-Eclampsia Case Administration

引用

8th International Conference on Information Technology and Digital Applications, ICITDA 2023

作者： Asadi, Faisal Elwirehardja, Gregorius Natanael Trinugroho, Joko Pebrianto Rahutomo, Reza Pardamean, Bens School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia School of Information Systems Bina Nusantara University Information System Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350344691

The Ministry of Health of Indonesia has referred to pre-eclampsia as one of the most severe diseases affecting women. As an urgency, it is crucial to administrate pre-eclampsia cases for disease prevention as a long-term national healthcare strategy. Regarding health science, case data was significant in developing research and innovation. However, the main problem regarding pre-eclampsia case administration is data handling, recording, and management incompetence. Hence, this research proposed a conceptual design of a database for pre-eclampsia case administration. The proposed design covered conceptual, logical, and physical design. We elaborate the concept into three concepts of pre-eclampsia disease: pre-treatment, treatment, and post-treatment. This study proposed a solution to gain more data and study pre-eclampsia disease in Indonesia. © 2023 IEEE.

关键词： Medical informatics

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：