检索结果-内蒙古大学图书馆

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Rissa Rahmania Yaya Heryadi Lukas Lukas Wayan Suparta Ilvico Sonata Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Group (CEG) Faculty of Engineering Universitas Katolik Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

The existence of fine-grained image classification supporting smart retail provides effectiveness in recognizing products with high similarity. However, the generic classification method performs poorly in identifying products from a subordinate category. This paper aims to identify augmentation techniques to leverage the Vision Transformer (ViT) model to classify the fine-grained grocery product, which involves embedding patches and transformer encoders to extract the main features. First, we develop a fine-grained image dataset with ColorJitter, CutOut, and combining both augmentations. Secondly, we perform experiments and analysis of ViT size, embedded patch size and image size in the patch embedding process. Lastly, the ViT model are evaluated according to the image sizes 224, 384, and 512 in accuracy, loss, and confusion matrix. The highest accuracy was obtained at 0.9922. The ColorJitter and CutOut improved the confusion matrix in ViT-B/16 and ViT-L/16 with an image size of 384 and 512. The results show that both augmentations in the ViT model are able to distinguish fine-grained grocery products.

关键词： Surveys computer vision Accuracy Image recognition Transformers Feature extraction Data augmentation Artificial intelligence Image classification

来源：评论

学校读者我要写书评

暂无评论

Predicting Human Activity with LSTM Face Detection on Server Surveillance System

Predicting Human Activity with LSTM Face Detection on Server...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Alexander Nurenie Yaya Heryadi Lukas Wayan Suparta Yulyani Arifin Computer Science Department BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Indonesia

Surveillance server technology was growth with new technology, effective, extra new features, human friendly, and human deals with big amount data, can't view and collect the data in the short time, and took time to analyze, playback video/picture to determine machine, human, vehicle or environment issues or performance, Surveillance Server Systems now which has the ability to face recognition, face detection, human detection, motion detection, license plate recognition, The authors perform this study that still new this research has never been done before to determine the efficacy of the LSTM in predicting human behavior (Long Short Term Memory) Face Detection on Server surveillance system, by taking log view data with a total of 91501 Face detection data downloaded from 10/18/2022~11/9/2022, the data will be processed using Python programming and training so that it can be used to predict the future regarding human activities that vary utilizing time series prediction LSTM include the number of daily activities, the highest and lowest numbers of days, and the maximum and minimum numbers of days. from the results of this study it was found to help to find out the days with the lowest number of humans and the days with the highest number of human activities, so that the owner can predict with sequence of the data the service would be provided when human activity is high in certain area or certain day, it can also can find out the maximum or minimum amount human counting day by day, and compare able some different date and location, the author will continue to do more in-depth research the others data related with prediction with deep learning server surveillance machine system interaction with human, vehicle behavior in the future studies.

关键词： Training Surveillance Time series analysis programming Behavioral sciences Servers Face detection

来源：评论

学校读者我要写书评

暂无评论

3D geometric shape assembly via efficient point cloud matching 24

3D geometric shape assembly via efficient point cloud matchi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Nahyuk Lee Juhong Min Junha Lee Seungwook Kim Kanghee Lee Jaesik Park Minsu Cho Department of Computer Science and Engineering POSTECH Pohang Korea Graduate School of Artificial Intelligence POSTECH Pohang Korea Department of Computer Science and Engineering Seoul National University Seoul Korea Department of Computer Science and Engineering Seoul National University Seoul Korea and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Department of Computer Science and Engineering POSTECH Pohang Korea and Graduate School of Artificial Intelligence POSTECH Pohang Korea

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Twenty years of e-learning in health science: A bibliometric 7

Twenty years of e-learning in health science: A bibliometric

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Maulana, Fairuz Iqbal Febriantono, M. Aldiki Raharja, Dwi Risza Budi Khaeruddin Herasmara, Ridho Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Diploma III Electronic Technology Vocational Study Program University of Muhammadiyah Malang Indonesia Electrical Engineering Faculty of Science and Technology Raden Rahmat Islamic University Malang Indonesia

Education about health sciences has historically been limited in the curriculum of health professionals and largely inaccessible to the public. In practice, most of the health science education is still running conventionally. Supposedly with the advancement of technology and the use of the internet everywhere, learning such as e-learning can be important, especially in the health sector. Until this research was conducted, only 514 academic documents about e-learning in health sciences were found for 20 years from 2001 to 2020, obtained in searching on the Scopus database. This study presents a comprehensive overview of studies related to E-learning in the Health sciences sector. This study uses bibliometric analysis and indexed digital methods to map scientific publications throughout the world. This research employs the Scopus database to gather information, as well as the Scopus online analysis tool and Vosviewer to show the bibliometric network. The method consists with five stages: determining search keywords, initial search results, refinement of search results, initial compilation, and data analysis. Among the most published and indexed articles by Scopus, papers published by researchers in the United States have the highest number of publications (80), followed by United Kingdom (63) and Australia with 45 academic publications. The processed data shows the pattern and trend of increasing the number of international publications in E-learning in Health sciences field, which Scopus index. © 2022 Elsevier B.V.. All rights reserved.

关键词： Publishing

来源：评论

学校读者我要写书评

暂无评论

Statistical Device Simulation and Machine Learning of Process Variation Effects of Vertically Stacked Gate-All-Around Si Nanosheet CFETs

引用

IEEE Transactions on Nanotechnology 2024年 23卷 386-392页

作者： Kola, Sekhar Reddy Li, Yiming Butola, Rajat National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Biomedical Engineering Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation Hsinchu300093 Taiwan

In this study, we report the process variation effect (PVE) including the work function fluctuation (WKF) on the DC/AC characteristic fluctuation of stacked gate-all-around silicon complementary field-effect transistors (CFETs). The PVE affects characteristic fluctuation significantly;in particular, for the variability of off-state current. Owing to the bottom channel of a fin-type, the P-FET suffers from the worst off-state current fluctuation (more than 200% variation) compared to the N-FET. The device variability induced by the WKF is marginal because of amorphous-type metal grains. As input features to an artificial neural network (ANN) model, low and high work function values, as well as parameters of PVE that have prevalent effects on CEFT transfer characteristics are further considered and modeled. The estimated values of R2-score prove that the ANN model properly grasps information from the dataset successfully;thus, it can be used to model emerging CFETs for circuit simulation. © 2002-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of autism spectrum disorder using epigenetic, brain, and sensory behavioral factors

Prediction of autism spectrum disorder using epigenetic, bra...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Yong Jeon Cheong Jihyun Bae Seonkyoung Lee Ro Ji Hyeong Hirotaka Kosaka Ilwoo Lyu Minyoung Jung Cognitive Science Research Group Korea Brain Research Institute Daegu Republic of Korea Department of Neuropsychiatry University of Fukui Fukui Japan Computer Science and Engineering Ulsan National Institute of Science and Technology Ulsan Republic of Korea

Autism spectrum disorder (ASD) is characterized by clinical and etiological heterogeneity. Although there is broad agreement on the necessity of integrating reliable biomarkers of ASD, little is known about how epigenetic and/or brain factors contribute to ASD. To probe epigenetic factors, we obtained the participants’ saliva samples to obtain DNA methylation values of the oxytocin receptor and arginine vasopressin genes. Given the atypical sensory processing associated with ASD and the role of thalamus as the sensory relay station, we acquired neuroimaging data to create a thalamocortical resting state functional connectivity map of ASD. Integrating features derived from epigenetic, brain, and sensory behavior factors, the current study aims to develop a model that predicts ASD using an eXtreme Gradient Boosting algorithm with ensemble feature selection procedure based on feature occurrence frequency and automatically optimized hyperparameters. We found the full model with all three factors (83.95%) to be superior for ASD classification, compared to models with epigenetic and behavioral factors (76.89%) or with brain and behavioral factors (81.19%).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Advances aiding Recognition and Classification of Indian Monuments and Landmarks 8

Machine Learning Advances aiding Recognition and Classificat...

引用

8th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2021

作者： Paul, Aditya Jyoti Ghose, Smaranjit Aggarwal, Kanishka Nethaji, Niketha Pal, Shivam Dutta Purkayastha, Arnab Department of Computer Science and Engineering Bharati Vidyapeeth's College of Engineering New Delhi India Cognitive Applications Research Lab India Department of Computer Science and Engineering Srm Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Srm Institute of Science and Technology Chennai India

ISBN: (纸本)9781665409629

Tourism in India plays a quintessential role in the country's economy with an estimated 9.2% GDP share for the year 2018. With a yearly growth rate of 6.2%, the industry holds a huge potential for being the primary driver of the economy as observed in the nations of the Middle East like the United Arab Emirates. The historical and cultural diversity exhibited throughout the geography of the nation is a unique spectacle for people around the world and therefore serves to attract tourists in tens of millions in number every year. Traditionally, tour guides or academic professionals who study these heritage monuments were responsible for providing information to the visitors regarding their architectural and historical significance. However, unfortunately this system has several caveats when considered on a large scale such as unavailability of sufficient trained people, lack of accurate information, failure to convey the richness of details in an attractive format etc. Recently, machine learning approaches revolving around the usage of monument pictures have been shown to be useful for rudimentary analysis of heritage sights. This paper serves as a survey of the research endeavors undertaken in this direction which would eventually provide insights for building an automated decision system that could be utilized to make the experience of tourism in India more modernized for visitors. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Analysis of Parallel Graph Applications

Analysis of Parallel Graph Applications

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Funda Atik Serif Yesil Hamza Ouarnoughi Smail Niar Ozcan Ozturk Computer Science and Engineering Department Washington University in St. Louis Doimukh MI USA NVidia Urbana IL USA Department of Computer Science Université Polytechnique Hauts-de-France Valenciennes France LAMIH/CNRS Université Polytechnique Hauts-de-France Valenciennes France Computer Science and Engineering Program Electronics Engineering Program Sabanci University Istanbul Turkey

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Despite the increasing computing power of shared memory systems with high core counts, parallel graph processing frameworks cannot exploit it effectively. The reason behind this is the inherent challenges in parallel graph algorithms, which are efficient management of dynamically created tasks and irregular data access patterns. In this paper, we categorize several popular design choices into three design dimensions: (i) execution mode, (ii) data access pattern, and (iii) work activation. We provide their high-level parallel implementations and analyze various implementations of three representative iterative graph algorithms by considering these design dimensions. To gain a better understanding of design choices, we examine their impacts on performance, communication, scalability, and work efficiency. We also investigate the communication characteristics of the design choices on two state-of-the-art shared-memory platforms by performing micro-architectural analysis. Our microarchitectural analysis reveals that a topology-driven, pull-based model gives up to $20 x$ better performance.

关键词： Analytical models Microarchitecture Scalability Heuristic algorithms Benchmark testing Throughput Iterative algorithms System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Van der Waals device integration beyond the limits of van der Waals forces using adhesive matrix transfer

引用

Nature Electronics 2024年第1期7卷 17-28页

作者： Satterthwaite, Peter F. Zhu, Weikun Jastrzebska-Perfect, Patricia Tang, Melbourne Spector, Sarah O. Gao, Hongze Kitadai, Hikari Lu, Ang-Yu Tan, Qishuo Tang, Shin-Yi Chueh, Yu-Lun Kuo, Chia-Nung Lue, Chin Shan Kong, Jing Ling, Xi Niroui, Farnaz Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA United States Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA United States Department of Chemical Engineering Massachusetts Institute of Technology CambridgeMA United States Department of Physics Massachusetts Institute of Technology CambridgeMA United States Department of Chemistry Boston University BostonMA United States Department of Materials Science and Engineering National Tsing Hua University Hsinchu Taiwan Semiconductor Research Center Hon Hai Research Institute Taipei Taiwan College of Semiconductor Research National Tsing Hua University Hsinchu Taiwan Department of Physics National Cheng Kung University Tainan Taiwan Taiwan Consortium of Emergent Crystalline Materials National Science and Technology Council Taipei Taiwan Program on Key Materials Academy of Innovative Semiconductor and Sustainable Manufacturing National Cheng Kung University Tainan Taiwan Division of Materials Science and Engineering Boston University BostonMA United States The Photonics Center Boston University BostonMA United States

Pristine van der Waals (vdW) heterostructures formed between two-dimensional (2D) and other materials can be used to create optical and electronic devices. However, the weak vdW forces alone do not allow direct physical stacking of arbitrary layers. As a result, vdW heterostructure fabrication typically requires solvents, sacrificial layers or high temperatures, which can introduce damage and contaminants. Here, we show that adhesive matrix transfer can eliminate these limitations and can provide vdW integration beyond the limits of vdW forces. In the approach, a hybrid high- and low-adhesion surface is used to decouple the forces driving the transfer from the vdW forces defining the heterostructure of interest. We show that the technique can be used to achieve direct vdW integration of diverse 2D materials (MoS2, WSe2, PtS2 and GaS) with dielectrics (SiO2 and Al2O3), which is conventionally forbidden but critical for active devices and scalable, aligned heterostructure formation. The approach also allows single-step 2D material-to-device integration, which we illustrate by fabricating arrays of monolayer MoS2 transistors. As any exposure to solvents or polymers is avoided, the interfaces and surfaces remain pristine. Thus, intrinsic 2D material properties can be probed without the influence of processing steps. The materials can be further engineered through surface treatments and used to fabricate unconventional device form factors. © 2023, The Author(s), under exclusive licence to Springer Nature Limited.

关键词： Van der Waals forces

来源：评论

学校读者我要写书评

暂无评论

A Census-Based Genetic Algorithm for Target Set Selection Problem in Social Networks

arXiv

引用

arXiv 2024年

作者： Rahman, Md Samiur Ahsan, Mohammad Shamim Chen, Tim Varadarajan, Vijayakumar Department of Computer Science & Engineering Presidency University Bangladesh Department of Computer Science & Engineering UIU Bangladesh Faculty of Information Technology Ton Duc Thang University Viet Nam Program Leader Engineering Ajeenkya D Y Patil University India

This paper considers the Target Set Selection (TSS) Problem in social networks, a fundamental problem in viral marketing. In the TSS problem, a graph and a threshold value for each vertex of the graph are given. We need to find a minimum size vertex subset to "activate" such that all graph vertices are activated at the end of the propagation process. Specifically, we propose a novel approach called "a census-based genetic algorithm" for the TSS problem. In our algorithm, we use the idea of a census to gather and store information about each individual in a population and collect census data from the individuals constructed during the algorithm's execution so that we can achieve greater diversity and avoid premature convergence at locally optimal solutions. We use two distinct census information: (a) for each individual, the algorithm stores how many times it has been identified during the execution;(b) for each network node, the algorithm counts how many times it has been included in a solution. The proposed algorithm can also self-adjust by using a parameter specifying the aggressiveness employed in each reproduction method. Additionally, the algorithm is designed to run in a parallelized environment to minimize the computational cost and check each individual's feasibility. Moreover, our algorithm finds the optimal solution in all cases while experimenting on random graphs. Furthermore, we execute the proposed algorithm on 14 large graphs of real-life social network instances from the literature, improving around 9.57 solution size (on average) and 134 vertices (in total) compared to the best solutions obtained in previous studies. Copyright © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

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：