检索结果-内蒙古大学图书馆

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Sari, Azani Cempaka Heryadi, Yaya Kartowisastro, Iman Herwidiana Budiharto, Widodo Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

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. © 2024 IEEE.

关键词： Convolutional E-commerce Graph Network Product Review Summarization Text

来源：评论

学校读者我要写书评

暂无评论

Autonomous face mask detection using single shot multibox detector, and ResNet-50 with identity retrieval through face matching using deep siamese neural network

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第8期14卷 11195-11205页

作者： Vignesh Baalaji, S. Sandhya, S. Sajidha, S.A. Nisha, V.M. Vimalapriya, M.D. Tyagi, Amit Kumar School of Compter Science and Engineering Vellore Institute of Technology Chennai India Post Graduate Department of Computer Science and Technology Women’s Christian College Chennai India Department of Fashion Technology National Institute of Fashion Technology New Delhi India

The COVID-19 pandemic poses a global health challenge. The World Health Organization states that face masks are proven to be effective, especially in public areas. Real-time monitoring of face masks is challenging and exhaustive for humans. To reduce human effort and to provide an enforcement mechanism, an autonomous system has been proposed to detect non-masked people and retrieve their identity using computer vision. The proposed method introduces a novel and efficient method that involves fine-tuning the pre-trained ResNet-50 model with a new head layer for classification between masked and non-masked people. The classifier is trained using adaptive momentum optimization algorithm with decaying learning rate and binary cross-entropy loss. Data augmentation and dropout regularization are employed to achieve best convergence. During real-time application of our classifier on videos, a Caffe face detector model based on Single Shot MultiBox Detector is used to extract the face regions of interest from each frame, on which the trained classifier is applied for detecting the non-masked people. The faces of these people are then captured, which is passed on to a deep siamese neural network, based on VGG-Face model for face matching. The captured faces are compared with the reference images from the database, by extracting the features and calculating cosine distance. If the faces match, the details of that person are retrieved from the database and displayed on the web application. The proposed method has secured best results where the trained classifier has achieved 99.74% accuracy, and the identity retrieval model achieved 98.24% accuracy. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

GAN.s Approach On Generating Synthetical Skin Image Dataset for Imbalance Dataset 8

GAN.s Approach On Generating Synthetical Skin Image Dataset ...

引用

8th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2024

作者： Setiawan, Tri Agus Heryadi, Yaya Lukas Wulandari, Lili Ayu Sonata, Ilvico Binus Graduate Program -Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia

ISBN: (纸本)9798350368970

The use of balanced medical datasets is essential to improve the precision and accuracy of machine learning models in the healthcare field. However, dataset imbalance often becomes an obstacle, especially in the diagnosis of skin diseases. This research aims to develop a Generative Adversarial Networks (GAN) method that is more effective in generating synthetic skin datasets to overcome problems in integrating medical datasets. The methods used include developing and training a GAN model to produce realistic synthetic skin images, with a focus on improving the quality and diversity of the synthetic data produced. Important results from this research show that the developed GAN model is able to produce synthetic skin images that are not only realistic but also able to balance the original dataset. The implications of these findings include improving the accuracy and performance of machine learning models in the diagnosis of skin diseases, as well as the potential use of these methods in other medical fields that face similar problems with imbalanced datasets. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Single Image Perspective Grid System on Floor Surface for 2D to 3D Transformation 8

Single Image Perspective Grid System on Floor Surface for 2D...

引用

8th IEEE International Conference on Computing, Engineering and Design, ICCED 2022

作者： Rusjdi, Darma Abdurachman, Edi Heryadi, Yaya Kusuma, Gede Putra Bina Nusantara University Computer Science Jakarta Indonesia Bina Nusantara University BINUS Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665453899

Our study discusses the application of the perspective grid concept as the basis for the process of transforming the 2D coordinates of the image into 3D coordinates in real space for estimating the location of objects in a single image scene. In several other studies in the field of robotics, AR use methods and media in the form of a chessboard box as a reference for camera calibration and location estimation. However, it does not show accurate results for the size of objects in the room. We saw the potential areas of Alberti's perspective grid, which is often used as a reference in making sketches for the arts and various engineering fields so that they are visually precise with reality. Our study uses 6 reference points in a room arrangement with a floor grid pattern as a reference for the formation of a perspective grid. Based on the triangle comparison approach to determine the x-ordinate, the average error is 0.2193. And through 3 interpolation approaches to get the most accurate results with the Lagrange and Newton methods on the 6th order with the average difference between the actual and predicted points of 1.5 cm from the y-direction distance of the camera from 2 meters to 6.80 meters. © 2022 IEEE.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

The Classification Model of Learners Based on Diagnostic Assessment Results in E-learning With Machine Learning 1

The Classification Model of Learners Based on Diagnostic Ass...

引用

1st International Conference on Software Engineering and Information Technology, ICoSEIT 2022

作者： Yel, Mesra Betty Zarlis, Muhammad Suwilo, Saib Efendi, Syahril Sihombing, Poltak Universitas Sumatera Utara Graduate Program of Computer Science Department of Computer Science Medan Indonesia Universitas Binus Department of Computer Science Jakarta Indonesia Universitas Sumatera Utara Department of Mathematics Medan Indonesia

ISBN: (纸本)9781665473033

The development of technology and artificial intelligence, especially in the era of Industrial Revolution 4.0 almost covers all fields, one of which is e-learning. In its development, it is very important to determine the factors to produce the quality of e-learning. Machine learning can help to find various solutions in the real world, especially to solve problems for which a specific algorithm has not been found. The implementation of e-learning is often ineffective and not on target which has an impact on learning achievement that is not achieved, this is due to several things namely the learning model is applied in general, the learning materials and weights are applied equally to all users. Seeing these problems, it is necessary to have a model to classify students according to their abilities, talents, and interests before starting learning to achieve their goals to be achieved. This paper aims to create a machine learning approach model to determine the level of ability and needs of students before starting learning which can reduce disparities between students and follow up learning materials. With the machine learning based on learning model, e-learning can provide teaching materials according to the abilities, and interests of students, sustainably and improve the quality of students. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Initial Implementation and Utilization of Instruction Dynamic Simulation in MEIMAT 21

Initial Implementation and Utilization of Instruction Dynami...

引用

21st International Symposium on Communications and Information Technologies, ISCIT 2022

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

ISBN: (数字)9781665498517

ISBN: (纸本)9781665498517

We have been developing MEIMAT, meiji micro-processor (MPU) architecture design tools. Our MEIMAT has a feature to implement arbitrary instructions. However, the MEIMAT does not have a function to simulate those instructions. Therefore, we have newly developed a function of simulation to dynamically execute the designed instructions. The result of this dynamic simulation can be measured by the developed module viewers. It is also demonstrated that a higher performance MPU can be designed by our improved MEIMAT. © 2022 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Model Development for Determining a Friendly Match Sparring-Partner in Football Game 3

An Intelligent Model Development for Determining a Friendly ...

引用

3rd International Conference on Information Management and Technology, ICIMTech 2018

作者： Utama, Ditdit Nugeraha Rizky, Muhammad Bona Akbar, Muhammad Faizal Febrian, Ilman Al-Ghani, Rasyid Computer Science Department Bina Nusantara University BINUS Graduate Program-Master of Computer Science Jakarta11480 Indonesia Computer Science Universitas Mercu Buana Jakarta Indonesia

ISBN: (纸本)9781538658215

The statistical data coming from football match play an interesting phenomenon. They are possibly utilized by a football team to select a strategy to play. One strategy is to choice a proper sparring-partner in exercise. For fulfilling the purpose, the study with objective is to construct an intelligent model for choosing the most proper sparring-partner for friendly-match was academically performed. Here, two methods fuzzy logic and Euclidean distance are applied as fundamental method of model. The method fuzzy logic is operated by experts to justify nine selected parameters' urgency, and the method Euclidean distance is benefitted to calculate the fitness value of two soccer teams' combination. The object oriented method is employed to design the model. Finally, in the study result, the created model shows the list of the fittest sparring-partners of each team recorded. © 2018 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Visualization and Simulation of Any MPU Architecture Design with Meta-Instruction 23

Visualization and Simulation of Any MPU Architecture Design ...

引用

23rd International Symposium on Communications and Information Technologies, ISCIT 2024

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

ISBN: (纸本)9798350353952

Our conventional architecture design tool converted instructions of microprocessor (MPU) into meta-instructions with both semantic and functional expressions, and it displayed a circuit diagram of the meta-instruction. The tool was able to perform dynamic simulation only on an educational processor called COMET. However, the meta-instruction must be able to express the arbitrary instruction of at least different significant existing MPUs in order to design arbitrary MPUs. Furthermore, it should be possible to visualize all instructions and then execute them. Therefore, we have improved the meta-instruction so that the architecture design tool applies to major MPUs: MIPS, ARM, and RISC-V in addition to COMET. The improved architecture design tool visualizes and simulates the circuit diagram of the improved meta-instruction. The result shows the possibility of the meta-instruction-based architecture design tool being able to design any MPU. © 2024 IEEE.

关键词： Microprocessor chips

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

Visualization Tool of Microprocessor Instruction for Designing New Architecture with Meta-Instructions 21

Visualization Tool of Microprocessor Instruction for Designi...

引用

21st International Symposium on Communications and Information Technologies, ISCIT 2022

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

ISBN: (数字)9781665498517

ISBN: (纸本)9781665498517

When making a new microprocessor (MPU), the instruction set architecture is considered. It is also necessary to design how to work the instructions in hardware circuits of the MPU. As a solution to these, we previously proposed a method of expressing the instruction in two ways of semantic expression and functional expression. We also developed a tool that can visualize the instruction. In this paper, we have improved this method by extending a usual MPU to a meta-instruction for any MPU. We have also developed a conversion method for the meta-instruction using a relationship between the semantic and the functional expressions. Then we verified how well our meta-instruction can represent the usual instructions. It is confirmed that most of them can be represented by the meta-instruction. Since our developed tool user can design the meta-instructions from either semantic or functional expression and both expressions can be automatically converted to each other, they can design the instruction of a new MPU and can understand hardware circuits for the MPU instruction by the functional expression. © 2022 IEEE.

关键词： Semantics

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：