检索结果-内蒙古大学图书馆

Personality Identification from Social Media Using Ensemble BERT and RoBERTa

Informatica (Slovenia) 2023年第4期47卷 537-544页

作者： Tsani, Eggi Farkhan Suhartono, Derwin 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

Social media growth was fast because many people used it to express their feelings, share information, and interact with others. With the growth of social media, many researchers are interested in using social media data to conduct research about personality identification. The identification result can be used as a parameter to screen candidate attitudes in the company's recruitment process. Some approaches were used for research about personality;one of the most popular is the Big Five Personality Model. In this research, an ensemble model between BERT and RoBERTa was introduced for personality prediction from the Twitter and Youtube datasets. The data augmentation method also introduces to handling the imbalance class for each dataset. Pre-trained model BERT and RoBERTa was used as the feature extraction method and modeling process. To predict each trait in the Big Five Personality, the voting ensemble from BERT and RoBERTa achieved an average f1 score 0,730 for Twitter dataset and 0,741 for Youtube dataset. Using the proposed model, we conclude that data augmentation can increase average performance compared to the model without data augmentation process. © 2023 Slovene Society Informatika. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of User Experience and Educational Outcomes in Math Memory Games

A Comparative Analysis of User Experience and Educational Ou...

引用

2024 International Conference on computer Engineering, Network and Intelligent Multimedia, CENIM 2024

作者： Martin, Nicholas Nathanael, Raffel Jeriyanto, Doni Hermawan, Eric Savero Fung, Janshen Panggabean, Francisco Maruli School of Computer Science Bina Nusantara University Game Application & Technology Program Computer Science Department Jakarta Indonesia Master of Computer Science Binus Graduate Program Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350368802

This research explores multiple varieties of effective and child-friendly learning approaches for mathematics and memorization among young children in today's increasingly digital age considering their specific developmental needs. This type of approach includes in-person teaching, engaging online videos, interactive textbooks, and innovative educational games. This research employs a detailed comparative analysis, considering both 'User Experience' and measurable learning outcome factors, and spans a range of age groups from preschoolers to elementary school children. Through highlighting the strengths and weaknesses of each method, this research aims to inspire the adoption of efficient, child-centric, and novel teaching techniques by educators and institutions, thereby advancing the quality of education in Indonesia. The results show that using serious game in education presents high usefulness score alongside positive user experience, suggesting its viability for educational purposes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Score Calculation with Local and Global Features for Visual Place Recognition

Score Calculation with Local and Global Features for Visual ...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Ikeda, Iori Adachi, Miho Miyamoto, Ryusuke Graduate School of Science and Technology Department of Computer Science Japan School of Science and Technology Meiji University Department of Computer Science Kawasaki Japan

ISBN: (纸本)9798350350821

Visual place recognition (VPR) seems effective for the localization process in visual navigation of a robot because a robot can recognize locations and poses using only visual information if the accuracy of VPR is sufficient. However, to apply VPR for actual scenarios where multiple locations to be distinguished are in a captured image, the classification accuracy should be improved. To solve this problem, we propose a novel method for likelihood computation in location matching composed of two kinds of components corresponding to local and global features. Experimental results using a novel dataset composed of actual images taken around the course of the Tsukuba Challenge showed that the proposed method improved accuracy by 1-6 % compared to conventional reranking methods using only local features. © 2024 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

DiffMat:Latent diffusion models for image-guided material generation

引用

Visual Informatics 2024年第1期8卷 6-14页

作者： Liang Yuan Dingkun Yan Suguru Saito Issei Fujishiro Graduate School of Science and Technology Keio UniversityKanagawaJapan School of Computing Tokyo Institute of TechnologyTokyoJapan Department of Information and Computer Science Keio UniversityKanagawaJapan

Creating realistic materials is essential in the construction of immersive virtual *** existing techniques for material capture and conditional generation rely on flash-lit photos,they often produce artifacts when the illumination mismatches the training *** this study,we introduce DiffMat,a novel diffusion model that integrates the CLIP image encoder and a multi-layer,crossattention denoising backbone to generate latent materials from images under various *** a pre-trained StyleGAN-based material generator,our method converts these latent materials into high-resolution SVBRDF textures,a process that enables a seamless fit into the standard physically based rendering pipeline,reducing the requirements for vast computational resources and expansive *** surpasses existing generative methods in terms of material quality and variety,and shows adaptability to a broader spectrum of lighting conditions in reference images.

关键词： SVBRDF Diffusion model Generative model Appearance modeling

来源：评论

学校读者我要写书评

暂无评论

SiamS3C: spatial-channel cross-correlation for visual tracking with centerness-guided regression

引用

Multimedia Systems 2024年第5期30卷 1-14页

作者： Zhang, Jianming Chen, Wentao He, Yufan Kuang, Li-Dan Sangaiah, Arun Kumar School of Computer and Communication Engineering Changsha University of Science and Technology Changsha410076 China International Graduate School of AI National Yunlin University of Science and Technology Douliu64002 Taiwan

Visual object tracking can be divided into the object classification and bounding-box regression tasks, but only one sharing correlation map leads to inaccuracy. Siamese trackers compute correlation map by cross-correlation operation with high computational cost, and this operation performed either on channels or in spatial domain results in weak perception of the global information. In addition, some Siamese trackers with a centerness branch ignore the associations between the centerness branch and the bounding-box regression branch. To alleviate these problems, we propose a visual object tracker based on Spatial-Channel Cross-Correlation and Centerness-Guided Regression. Firstly, we propose a spatial-channel cross-correlation module (SC3M) that combines the search region feature and the template feature both on channels and in spatial domain, which suppresses the interference of distractors. As a lightweight module, SC3M can compute dual independent correlation maps inputted to different subnetworks. Secondly, we propose a centerness-guided regression subnetwork consisting of the centerness branch and the bounding-box regression branch. The centerness guides the whole regression subnetwork to enhance the association of two branches and further suppress the low-quality predicted bounding boxes. Thirdly, we have conducted extensive experiments on five challenging benchmarks, including GOT-10k, VOT2018, TrackingNet, OTB100 and UAV123. The results show the excellent performance of our tracker and our tracker achieves real-time requirement at 48.52 fps. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

A METHOD FOR IMPROVING THE ACCURACY OF SFM 3D MEASUREMENTS BY RANDOM PATTERN PROJECTION

引用

AIJ Journal of technology and Design 2023年第71期29卷 533-537页

作者： Sugano, Miki Kakizaki, Ken'ichi Tominaga, Yasumasa Araki, Shunsuke Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Japan

SfM can reconstruct the 3D shape of an object with high accuracy if there are many feature points on the surface to be measured. However, in the field of architecture, there is a problem that building surfaces are beautifully preserved and the shape cannot be reconstructed because of the small number of feature points. In this study, we proposed a method to improve the measurement accuracy of SfM by projecting a random pattern on a wall surface and distributing a large number of feature points. Experiments confirmed that the measurement accuracy was as good as that of a laser scanner. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： 3D measurement Measurement accuracy Pattern projection Point cloud Random pattern SfM

来源：评论

学校读者我要写书评

暂无评论

StackFi: An Ensemble Learning-Based Model for WiFi Sensing Classification Tasks 4

StackFi: An Ensemble Learning-Based Model for WiFi Sensing C...

引用

4th International Conference on Consumer Electronics and computer Engineering, ICCECE 2024

作者： Liu, Jiaxing The Graduate School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9798350384062

The widespread adoption of WiFi devices and ubiquitous WiFi networks has fostered the development of the WiFi sensing domain. With the continuous progress in deep learning, a rising prevalence is observed in the application of deep learning techniques to the field of WiFi sensing. However, researchers often face the dilemma of choosing either convolutional neural networks, disregarding the temporal nature of Channel State Information data, or recurrent neural networks, overlooking the similarity between its subcarriers and the multiple channels in image data. We propose an ensemble learning-based model, StackFi, which combines two prevailing approaches in deep learning for processing Channel State Information (CSI) data. One approach analogizes CSI data to images, utilizing deep convolutional neural networks for feature extraction. The other treats CSI data as temporal data, employing recurrent neural networks for feature extraction. Our model extracts features from CSI data in WiFi signals, and these extracted features are then fed into a classifier. We gathered some commonly employed deep learning models in the field of WiFi sensing and contrasted them with StackFi using the public datasets UT-HAR and NTU-Fi HAR. Our model exhibited outstanding performance, achieving accuracy rates of 99.13% and 99.27% on these two public datasets, surpassing the performance of other models in the field. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Microprocessor Instruction Design Tool for RISC-V Architecture 22

Microprocessor Instruction Design Tool for RISC-V Architectu...

引用

22nd International Symposium on Communications and Information Technologies, ISCIT 2023

作者： Jiahui, Luo Morimoto, Tomoyuki Ogita, Tadahiro Kawamata, Ryota Wang, Ziming Tsutsumi, Toshiyuki Meiji University Computer Science Program Graduate School of Science and Technology Kanagawa Japan Meiji University School of Science and Technology Department of Computer Science Kanagawa Japan

ISBN: (纸本)9781665457316

We have been developing MEIMAT (MEiji Microprocessor Architecture Design Tools). The MEIMAT is essentially designed to be able to represent any instruction of various processors by the MEIMAT meta-instruction in two ways of semantic and functional expressions. In this paper, we have verified the RISC-V support to the MEIMAT, and have improved so that MEIMAT further supports RISC-V. First, we have verified whether the RISC-V instructions can be expressed by the MEIMAT semantic expression. It is also verified that the functional expression is automatically generated from the semantic instruction, and the corresponding correct circuit diagrams are generated in the MEIMAT instruction visualization tool. Then, we have newly developed a stage configuration mechanism to implement the RISC-V instructions. Because the RISC-V architecture is implemented by 4 or 5 processing stages in most actual processors. To develop further an easy-to-understand design tool, we have also introduced illustration windows for RISC-V specified hardware modules such as a register file, especially a status register in the instruction visualization tool. Finally, through these verifications and improvements, we have successfully confirmed that the 43 instructions in the RISCV (RV32I) instructions set of the RISC-V architecture can be converted into MEIMAT meta-instructions, and then they can be represented as circuit diagrams with the RISC-V stage configuration in the MEIMAT instruction visualization tool. © 2023 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Detection of Narcotics Money Laundering in Suspicious Financial Transactions Using Convolutional Extreme Gradient Boosting (ConvXGB) 4

Detection of Narcotics Money Laundering in Suspicious Financ...

引用

4th International Conference on Intelligent Cybernetics technology and Applications, ICICyTA 2024

作者： Winarno, Leonardus Verrell Sayoga Kinantra Wibowo, Antoni School of Computer Science Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331506490

With the development of narcotics problems that continue to increase, the Indonesian Government responds through the Badan Narkotika Nasional (BNN) with data showing the condition of narcotics tends to grow every year and is followed by the number of assets of money laundering (ML) crimes against narcotics cases. One of the banks in Indonesia as a reporting party for suspicious financial transactions (SFT) has obstacles in detecting narcotics ML due to complex and rarely found patterns. Some previous studies conducted experiments using Convolutional Neural Network (CNN), Extreme Gradient Boosting (XGBoost), and even a combination of both into Convolutional Extreme Gradient Boosting (ConvXGB), and improved model performance in several datasets. This paper designs a model using the ConvXGB algorithm by adopting the CNN architecture, LeNet-5, by applying several convolution layers and pooling layers as a baseline model for feature learning, and the XGBoost as feature classification. Three phases of research are the preprocessing phase by collecting data, transforming data, balancing data with a hybrid sampling technique, splitting data, and scaling data, followed by the implementation phase by creating a ConvXGB model, training and testing the model, then finally the evaluation phase by analyzing results and hyperparameter tuning. The dataset used is SFT from the bank during 2023. This ConvXGB has three convolution layers, a pooling layer, and a flattened layer. The performance test results are the accuracy value and F1-Score value of 99.11% each after hyperparameter tuning. By performing a hybrid model, the model performance results are better. © 2024 IEEE.

关键词： Laundering

来源：评论

学校读者我要写书评

暂无评论

Reconfiguration of vertex-disjoint shortest paths on graphs

引用

Journal of Graph Algorithms and Applications 2024年第3期28卷 87-101页

作者： Saito, Rin Eto, Hiroshi Ito, Takehiro Uehara, Ryuhei Graduate School of Information Sciences Tohoku University Sendai Japan School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan School of Information Science Japan Advanced Institute of Science and Technology Nomi Japan

We introduce and study reconfiguration problems for (internally) vertex-disjoint shortest paths: Given two tuples of internally vertex-disjoint shortest paths for fixed terminal pairs in an unweighted graph, we are asked to determine whether one tuple can be transformed into the other by exchanging a single vertex of one shortest path in the tuple at a time, so that all intermediate results remain tuples of internally vertex-disjoint shortest paths. We also study the shortest variant of the problem, that is, we wish to minimize the number of vertex-exchange steps required for such a transformation, if exists. These problems generalize the well-studied Shortest Path Reconfiguration problem. In this paper, we analyze the complexity of these problems from the viewpoint of graph classes, and give some interesting contrast. © 2024, Brown University. All rights reserved.

关键词： Graph theory

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

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

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：