检索结果-内蒙古大学图书馆

3rd International Conference on Intelligent Cybernetics technology and Applications, ICICyTA 2023

作者： Martha, Gede Indra Raditya Gaol, Ford Lumban Supangkat, Suhono Harso Ranti, Benny Bina Nusantara University Graduate Program - Computer Science Jakarta Indonesia Bina Nusantara University Computer Science Departement Computer Science Jakarta Indonesia Institute Technology Bandung Faculty of Digital Communication and Hotel & Tourism Bandung Indonesia University of Indonesia Faculty of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350394559

Research related to digital assets & ownership is currently rising along with the escalation utilization of Blockchain through various use cases and its derevatives, for example in facilitating Digital Assets in the form of virtual property (virtual houses / buildings and virtual land) in the Metaverse. These digital assets often have utilities, features, and even limited copies of quantities so that these digital objects have more value for specific users on a platform and even general people who are interested in and value them. To be able to preserve the value of digital assets in the Metaverse such as virtual property previously mentioned especially for transactions, a set of regulations/governance, as well as sustainable development in the future in the Metaverse is really needed so that the use of Decentralized Autonomous Organization (DAO) in the metaverse is one way to maintain the sustainability of the ecosystem & market and its potential of virtual property. After conducting research for DAO development for virtual property transactions, starting with determining goals & purposes, breaking down the DAO focus object (virtual property), clustering relevant attributes, matching socio-economic impacts, and finally designing smart contracts & governance consensus, we obtained 4 main layers namely Consensus Governance, Smart Contract, Virtual Property & Socio-Economic. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of CNN-Based Models in Macroscopic Motion Direction Detection 6

The Effectiveness of CNN-Based Models in Macroscopic Motion ...

引用

6th International Conference on Robotics and computer Vision, ICRCV 2024

作者： Qiu, Zhiyu Chen, Tianqi Hua, Yuxiao Todo, Yuki Graduate School of Natural Science & Technology Kanazawa University Division of Electrical Engineering and Computer Science Kanazawa Japan Kanazawa University Faculty of Electrical Information and Communication Engineering Kanazawa Japan

ISBN: (纸本)9798331527426

Convolutional Neural Networks (CNNs) have revolutionized the field of computer vision, offering significant advancements in image and video recognition, classification, and segmentation tasks. Leveraging hierarchical pattern recognition capabilities, CNNs have demonstrated superior performance over traditional machine learning methods. One particularly critical application of CNNs is in motion direction detection, which is essential for enhancing security in surveillance systems, ensuring safe navigation in autonomous vehicles, and providing valuable insights in sports analytics. In this study, our primary goal was to investigate how different types of input data impact the accuracy of motion direction detection. We applied five distinct preprocessing methods to test the effect of input data on accuracy. Furthermore, we conducted experiments in various object and background scenarios to evaluate adaptability of simple 4-layer CNN, EfficientNetBO and ResNet50 in detecting motion direction. Finally, we tested the noise resistance of these three models. The results indicate that CNNs are capable of extracting the macroscopic motion direction of objects in images. Our study highlights the potential of CNN-based models for efficient and effective motion direction 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

LLM2Vec Sentence Embeddings Analysis in Sentiment Classification

LLM2Vec Sentence Embeddings Analysis in Sentiment Classifica...

引用

2024 IEEE International Conference on Data and Software Engineering, ICoDSE 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Isnan, Mahmud Kurnianingrum, Dian Ratnapuri, Chyntia Ika Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Entrepreneurship Department Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331506407

Sentiment analysis is crucial method in business intelligence to extract insights, which typically begin with sentiment classification. One of the latest frameworks for generating sentence embeddings for sentiment classification is LLM2Vec, which allows Transformer decoder-based models to generate sentence embeddings for text representation. Its capability is deemed language-agnostic, which, in this study, the framework is leveraged for Tokopedia tweet sentiment analysis to prove the claim. The base decoder models used in the LLM2Vec framework were Llama 3 8B, Llama 2 7B, Sheared Llama 1.3B, and Mistral 7B. Two BERT-based models, which are the Indonesian SBERT model and IndoBERT trained with the SimCSE approach, were employed as a comparison. The generated embeddings were classified using logistic regression, SVM, and MLP Classifier. Classifiers using embedding generated by LLM2Vec with Llama 3 8B and Mistral 7B achieves on-par performance with classifiers that utilize IndoBERT SimCSE embeddings, while classifiers using embeddings generated by LLM2Vec with Llama 2 7B and Sheared Llama 1.3B achieves much lower performance. Classifiers with Indonesian SBERT embeddings achieve the highest F1 score performance. Despite slightly lower performance, this study has proven the language-agnostic capability of LLM2Vec, especially with Llama 3 8B and Mistral 7B in colloquial Bahasa Indonesia sentiment analysis, since none of the base decoders were ever trained using the Bahasa Indonesia corpus. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Determining Variables Associated with Annual Oil Palm Yield: An Explainable Gradient Boosting Approach 8

Determining Variables Associated with Annual Oil Palm Yield:...

引用

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

作者： Elwirehardja, Gregorius Natanael Suparyanto, Teddy Miftakhurrokhmat Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta55282 Indonesia Faculty of Industrial Technology Universitas Islam Indonesia Yogyakarta55584 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

With the growing demands for Precision Agriculture (PA) in Indonesia, researchers have evaluated the utilization of Machine Learning for predicting oil palm yields and determining variables affecting them. Previous studies showed that meteorological variables, including rainfalls and wind speed, are associated with oil palm yields. In this research, the Extreme Gradient Boosting (XGBoost) model and the Shapley Additive exPlanations (SHAP) were deployed for analyzing the importance of 15 agrometeorological variables in predicting oil palm yield. The best model attained 1.911 RMSE and 0.855 RRʹ. By analyzing the weights and gains of the XGBoost model along with the SHAP values, it was found that the yield in the previous year, the age and number of plants, the area of peat lands, and meteorological parameters such as rainfall rates and the number of rainy days in the previous three years were considered important. The previous year's yield in particular possesses the greatest weight and gain values according to the model, and the highest SHAP value among all input variables. However, the meteorological data used in this research are only limited to rainfall rates and the number of rainy days. In the future, more diverse variables can be analyzed. © 2023 The Authors. Published by Elsevier B.V.

关键词： Machine Learning Oil Palm Yield SHAP XAI XGBoost

来源：评论

学校读者我要写书评

暂无评论

Fully explicit dynamic Gaussian splatting 24

Fully explicit dynamic Gaussian splatting

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Junoh Lee Changyeon Won Hyunjun Jung Inhwan Bae Hae-Gon Jeon School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology AI Graduate School Gwangju Institute of Science and Technology Gwangju Institute of Science and Technology School of Electrical Engineering and Computer Science and AI Graduate School Gwangju Institute of Science and Technology

ISBN: (纸本)9798331314385

3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not involve novel view synthesis for dynamic motions. Ironically, this is because the main barrier is the reliance on them, which requires increasing training and rendering times to account for dynamic motions. In this paper, we design Explicit 4D Gaussian Splatting (Ex4DGS). Our key idea is to firstly separate static and dynamic Gaussians during training, and to explicitly sample positions and rotations of the dynamic Gaussians at sparse timestamps. The sampled positions and rotations are then interpolated to represent both spatially and temporally continuous motions of objects in dynamic scenes as well as reducing computational cost. Additionally, we introduce a progressive training scheme and a point-backtracking technique that improves Ex4DGS's convergence. We initially train Ex4DGS using short timestamps and progressively extend timestamps, which makes it work well with a few point clouds. The point-backtracking is used to quantify the cumulative error of each Gaussian over time, enabling the detection and removal of erroneous Gaussians in dynamic scenes. Comprehensive experiments on various scenes demonstrate the state-of-the-art rendering quality from our method, achieving fast rendering of 62 fps on a single 2080Ti GPU.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gender-Based Bimodal Analysis of Speech and Text in Non-Contextual Emotion Recognition

Gender-Based Bimodal Analysis of Speech and Text in Non-Cont...

引用

2024 Beyond technology Summit on Informatics International Conference, BTS-I2C 2024

作者： Angkasa, Abby Rasya Zahra, Amalia Fung, Wai-Keung Binus Graduate Program Computer Science Department Jakarta11480 Indonesia Cardiff Metropolitan University Cardiff School of Technologies Engineering Department Cardiff United Kingdom

ISBN: (纸本)9798331508579

Emotion recognition can help human-computer interactions by enabling systems to respond empathetically and adapt to users' emotional conditions. This capability improves user experience, supporting the development of a more intuitive and emotionally responsive communication system. This study analyzes a bimodal approach based on gender (male and female) to recognize emotions without contextual information in dialogue analysis. Utilizing the Multimodal EmoryNLP dataset extracted from the TV series Friends with acted speech, we focused on four primary emotions: Angry, Neutral, Joy, and Scared. The model used in this study for text classification is RoBERTa, and wav2vec 2.0 is used for audio feature extraction with the Bi-LSTM model for classification. The experiment results using weighted F1-score reveal that data augmentation enhanced the performance of analyzing the original dataset from 0.46% to 0.52% and the male dataset from 0.43% to 0.51 %. In comparison, the female dataset remained consistent at 0.46%. The weighted F1-score and Unweighted Averaged Recall (UAR) from the male dataset are higher, 51 % and 48%, respectively, than those from the female dataset, 46% and 47%, respectively. Gender-based analysis indicated that male and female datasets exhibited distinct performance patterns, highlighting variations in emotional expression and recognition between genders. These findings underscore the effectiveness of multimodal strategies in emotion recognition and suggest that gender-specific factors play a significant role in enhancing classification performance. While these results highlight performance trends, further validation through repeated trials and statistical analyses could provide stronger generalizations and insights into gender-based differences. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Effect of Graphite Addition on Microstructure, Mechanical Properties and Thermal Properties of Injection Molded AZ91D Alloy+1

引用

Materials Transactions 2024年第4期65卷 374-380页

作者： Hideshima, Yasutoshi Maeda, Fumiya Fukuta, Tadao Ozaki, Koichi Course of Advanced Systems Engineering Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan Process Technology Development Department Technology Development Division Seiko Epson Corp. Suwa399-0211 Japan Department of Systems Engineering Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja719-1197 Japan

Magnesium chips were coated with a high concentration of graphite using a binder and were used as the raw material for injection molding. The microstructure of the magnesium injection-molded product with added graphite exhibited a dispersion of needle-like graphite particles. No significant voids were observed at the interfaces between the graphite and the matrix. The addition of more than 0.5 mass% graphite decreased the proof stress and tensile strength of the injection-molded products. The Young’s modulus of the graphite-added products tended to decrease with an increase in the graphite content, which is consistent with the lower limit of the rule of mixtures. The thermal conductivity of the 6.9 mass% graphite-added product increased compared with that of the AZ91D magnesium alloy and the coefficient of linear thermal expansion decreased. Both values are within a range that satisfied the rules of mixtures. © 2024 The Japan Institute of Metals and Materials.

关键词： Thermal expansion

来源：评论

学校读者我要写书评

暂无评论

Research on deep learning algorithms for point cloud upsampling 3

Research on deep learning algorithms for point cloud upsampl...

引用

3rd International Conference on Digital Signal and computer Communications, DSCC 2023

作者： Li, Jin Gong, Yan Li, Jiao Yue, Rui Li, Ji Department of Computer and Information Security Guilin University of Electronic Technology China Department of Computer and Artificial Intelligence Changzhou University China Science Island Branch of Graduate School University of Science and Technology of China China School of Nanotechnology and Nanobionics University of Science and Technology of China China

ISBN: (数字)9781510666566

ISBN: (纸本)9781510666559

The integration of 3D vision technology has profoundly impacted various aspects of our lives, with point clouds emerging as the predominant geometric representation in the field due to their simplicity, ease of processing, and low acquisition costs. However, limitations in 3D scanning hardware often result in sparse, noisy, and unevenly distributed point clouds, which impede the effectiveness of subsequent 3D vision tasks. To obtain high-quality and precise point clouds, researchers have introduced upsampling algorithms that enhance point cloud representativeness through *** recent years, deep learning has supplanted traditional algorithms that rely on a priori data, owing to its robust learning representation capabilities and data-driven nature. Consequently, deep learning algorithms for point cloud upsampling have become a highly valuable research direction within the 3D vision domain. This paper delves into recent advancements in deep learning algorithms for point cloud upsampling by first defining the problem and analyzing the technical challenges from six perspectives. It then provides an overview of the relevant benchmarks in point cloud upsampling and traces their developmental *** paper further examines the technical issues in the three critical steps (point cloud local feature extraction, feature space expansion, and coordinate reconstruction) of the overall deep learning algorithm for point cloud upsampling. It categorizes the prevalent technical solutions, discussing their merits and drawbacks, and offers optimization strategies. Lastly, the paper presents a forward-looking perspective on potential research directions in this field from four angles. © 2023 SPIE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Helmet Wearing Detecting Algorithms Based on YOLO 5

A Systematic Review of Helmet Wearing Detecting Algorithms B...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Wang, Tianshun Ren, Fei Fu, Lifang Doma, Bonifacio T. School of Information Technology Mapua University Makati Philippines School of Graduate Studies Mapua University Makati Philippines Zhengzhou Shengda University Department of Computer Science and Technology Zhengzhou China

ISBN: (纸本)9798350385557

In industrial production and social transportation, there are often various potential risks that threaten the life safety of participants. In all workers' lives in the most serious, generally likely to happen are falling objects, collapses, and traffic accidents, etc. These serious lessons let all workers live on the helmet wearing and supervision more and more attention, effective supervision will reduce accidents. Therefore, we collected literature and provided an overview of deep learning algorithms related to helmet detection. After comparing features of popular object detection algorithms, YOLO algorithm was chosen as the research object in this field. First, the development history of the YOLO algorithm (YOLOvl∼YOLOv8) is described, and then the literature on YOLO-based helmet wearing detection is reviewed. Second, we analyze selected literature to identify current knowledge, key gaps, and improvements in YOLO for specific helmet wearing detection tasks. Finally, future improvement ideas and research trends are analyzed and prospected. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Learning Support System based on Ontology of Multiple programming Languages 31

An Adaptive Learning Support System based on Ontology of Mul...

引用

31st International Conference on computers in Education, ICCE 2023

作者： Na Nongkhai, Lalita Wang, Jingyun Mendori, Takahiko Graduate School of Engineering Kochi University of Technology Japan Department of Computer Science Durham University United Kingdom

ISBN: (纸本)9786269689019

This research proposes to develop an adaptive ontology-based learning support system for computer programming learning. Firstly, the system adopts a previously developed ontology called CONTINUOUS, which represents programming concepts and their relation in a graph and makes use of its content to serve as hints within programming questions. Secondly, we design an adaptive strategy for recommending suitable exercises to learners, which uses CONTINUOUS as metadata of exercises and the Elo rating system to estimate learners' skills. This work aims to design a system to provide personalized exercise path for the learner and evaluate its effectiveness. © 2023 Asia-Pacific Society for computers in Education.

关键词： Ontology

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：