检索结果-内蒙古大学图书馆

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Yuto Inokuchi Pedro Henrique González Masayoshi Aritsugi Israel Mendonça Graduate School of Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

In this paper, we aim to reduce the number of nodes from Graph Neural Networks (GNNs), thereby simplifying models and reducing computational costs. GNNs are highly effective for various tasks, such as prediction, classification, and clustering, due to their ability to learn node and edge attributes and relationships, and they have been utilized for intelligent transportation systems recently by converting sensor networks into graph structures. Deep spatio-temporal neural networks, including Spatio-Temporal Graph Convolutional Networks (STGCNs), capture spatial and temporal dependencies, making them suitable for traffic speed forecasting, traffic demand prediction, and travel time estimation. Despite their success, GNNs face challenges in industrial applications due to significant memory usage and time consumption. In this paper, we propose a new approach to node reduction that outperforms existing methods in computational efficiency. Our experiments on two real-world traffic datasets demonstrate that using the heuristic and edge information to reduce nodes can cut computation time of optimization up to 95% and, by eliminating noise, can even enhance prediction accuracy.

关键词： Graph convolutional networks Noise Memory management Estimation Computational efficiency Forecasting Optimization Intelligent transportation systems Faces Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

The Internet of Things: Real-Time Monitoring System for Production Machine 5

The Internet of Things: Real-Time Monitoring System for Prod...

引用

5th IEEE International Conference on information technology, information Systems and Electrical Engineering, ICITISEE 2021

作者： Tarigan, Masmur Heryadi, Yaya Lukas Wibowo, Antoni Suparta, Wayan Bina Nusantara University Graduate Program Computer Science Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Department Jakarta Indonesia Jakarta Indonesia Bina Nusantara University Computer Science Department Jakarta Indonesia Faculty Of Computer Science Esa Unggul University Jakarta Indonesia

ISBN: (纸本)9781665401968

The importance of optimization in the manufacturing industry to achieve efficiency and effectiveness, especially in production machines. This research focuses on developing a real-time monitoring system based on the internet to monitor power consumption and production machines' speed accurately. The data taken by the real-time monitoring system is integrated into the ERP System, which is stored as time series data of power consumption and engine speed. The importance of making production cost estimates, especially on the power consumption of a production machine for the future, and functioning as a tool for real-time monitoring, the data obtained is processed by regression to get an estimate of the total power consumption for several expected outputs. The data is processed using a linear regression algorithm to predict power consumption at the desired speed on the intended production machine. To get a better tool than the one that existed before, the method in its development uses PIECES analysis. In its implementation, this real-time monitoring system runs according to the objectives, and the data obtained is as expected. This model was developed on production machines in the flexible packaging industry that uses rotogravure machines. It is possible that it can be used on production machines in other industries that use electrical power correlated with the speed measured based on the rotation of a motor. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Smart Healthcare: A GAN-based Approach for Imbalanced Alzheimer's Disease Classification 19

Deep Learning in Smart Healthcare: A GAN-based Approach for ...

引用

19th International Conference on Future Networks and Communications, FNC 2024 / 21st International Conference on Mobile Systems and Pervasive Computing, MobiSPC 2024 / 14th International Conference on Sustainable Energy information technology, SEIT 2024

作者： Tufail, Hina Ahad, Abdul Puspitasari, Ira Shayea, Ibraheem Coelho, Paulo Jorge Pires, Ivan Miguel Department of Computer Science University of Management and Technology Sialkot Pakistan Information System Study Program Faculty of Science and Technology Universitas Airlangga Indonesia School of Software Northwestern Polytechnical University Shaanxi Xian China Turkey Polytechnic University of Leiria Leiria Portugal Coimbra Portugal Instituto de Telecomunicações Escola Superior de Tecnologia e Gestão de Águeda Universidade de Aveiro Águeda Portugal

Alzheimer's disease (AD) is a type of dementia that leads to memory loss and impairment, which affects patients' lives badly. It is not curable yet, but its progression can be slowed down if detected at earlier stages. In this research study, we propose a transfer learning-based convolutional neural network (CNN) model to classify magnetic resonance imaging (MRI) into one of four stages of Alzheimer's disease. One of the major limitations of the deep learning-based classification model is the non-availability of healthcare datasets related to AD. The widely used Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset has a major class imbalance issue. We propose a generative adversarial network (GAN) based data augmentation technique to overcome the data imbalance. This promotes the investigation of applying GANs to generate synthetic samples for minority classes in Alzheimer's disease datasets to enhance classification performance. The results show the progression in the overall classification process of AD. © 2024 The Authors. Published by Elsevier B.V.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Strawberry Disease Detection With Wall-Mounted Monitoring Cameras

引用

IEEE Internet of Things Journal 2024年第1期11卷 1439-1451页

作者： Lin, Yi-Bing Liu, Chun-You Chen, Wen-Liang Chang, Chia-Hui Ng, Fung-Ling Yang, Krista Hsung, Jerry Department of Computer Science National Yang Ming Chiao Tung University Hsinchu30010 Taiwan China Medical University College of Humanities and Sciences Taichung404 Taiwan National Cheng Kung University MiinWu School of Computing Tainan701 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei115 Taiwan National Yang Ming Chiao Tung University College of Biological Science and Technology Hsinchu30010 Taiwan National Yang Ming Chiao Tung University Industrial Development Graduate Program College of Biological Science and Technology Hsinchu30010 Taiwan Proto Solution System Company Ltd. Hsinchu302052 Taiwan

This article proposes StrawberryTalk, an Internet of Things (IoT) platform for image-based strawberry disease detection. StrawberryTalk reuses the wall-mounted monitoring cameras without extra hardware cost. The contributions of StrawberryTalk are the utilization of IoT for automatic photo shoot and the wind detection mechanism to eliminate the obscure photos due to the wind effects. Also, the data preprocessing and the infection detection models are manipulated as IoT devices to simplify the implementation of the multicascade artificial intelligence (AI) models. We derive the relationship between the camera zoom factor and the distance between the camera and the strawberries for optimal disease detection. Accuracy of detection may be affected by obscure photos. In terms of eliminating obscure photos due to wind effect, we analytically derive the relationship between the wind alert delay and the number of obscure photos that must be retaken. For the greenhouses in the Bao Mountain, we only need to retake one photo. Based on the experiments, the mean average precision (mAP) of StrawberryTalk (to detect exact spots in a leaf) can be up to 92.37%, which is better than the previous approaches. To detect if a pot has infected leaves, the accuracy of StrawberryTalk can be up to 97.92% at the zoom factor 30×. In commercial operation, it is important to detect all infected strawberry pots. StrawberryTalk is able to detect all infected pots (i.e., recall is 100%) with a camera of zoom factor of 12× . The accuracy is 96.88%. © 2014 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Mini-InternVL:a flexible-transfer pocket multi-modal model with 5%parameters and 90%performance

引用

Visual Intelligence 2024年第1期2卷 392-408页

作者： Zhangwei Gao Zhe Chen Erfei Cui Yiming Ren Weiyun Wang Jinguo Zhu Hao Tian Shenglong Ye Junjun He Xizhou Zhu Lewei Lu Tong Lu Yu Qiao Jifeng Dai Wenhai Wang Shanghai AI Laboratory Shanghai200232China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai200240China School of Computer Science Nanjing UniversityNanjing210023China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen518055China School of Computer Science Fudan UniversityShanghai200433China SenseTime Research Shanghai200233China Department of Electronic Engineering Tsinghua UniversityBeijing100084China Beijing National Research Center for Information Science and Technology Department of AutomationTsinghua UniversityBeijing100084China Department of Information Engineering The Chinese University of Hong KongHong Kong999077China

Multi-modal large language models(MLLMs)have demonstrated impressive performance in vision-language tasks across a wide range of ***,the large model scale and associated high computational cost pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices,thereby hindering their widespread *** this work,we introduce Mini-InternVL,a series of MLLMs with parameters ranging from 1 billion to 4 billion,which achieves 90% of the performance with only 5% of the *** significant improvement in efficiency and effectiveness makes our models more accessible and applicable in various real-world *** further promote the adoption of our models,we are developing a unified adaptation framework for Mini-InternVL,which enables our models to transfer and outperform specialized models in downstream tasks,including autonomous driving,medical image processing,and remote *** believe that our models can provide valuable insights and resources to advance the development of efficient and effective MLLMs.

关键词： Lightweight multi-modal large language model Vision-language model Knowledge distillation Visual instruction tuning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis: Indonesia Netflix User's Comment Using Multiple Lexicon-Based Dictionaries

Sentiment Analysis: Indonesia Netflix User's Comment Using M...

引用

Intelligent Cybernetics technology & Applications (ICICyTA), International Conference on

作者： Sebastianus Adi Santoso Mola Tiwuk Widiastuti Rosa V. K. Isabela Ohe Roma Andrea Stevens Karnyoto Bens Pardamean Faculty of Science and Engineering University of Nusa Cendana Kupang Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

A subscription movie streaming service from the United States, Netflix, has been present in Indonesia since 2016 and provides a wide variety of films without showing any single advertisements that can be viewed from anywhere, as long as there is access to the internet. Despite these advantages, many users have complained through the Google Play Store's comments column. Some of the common complaints include frequent buffering and connectivity issues, dissatisfaction with the limited selection of Indonesian movies, lack of subtitles for specific languages, or pricing concerns have also been raised. In this study developed two combined scenario methods using the InSet and SentiStrength_id dictionary to obtain better performance and compare them against independent InSet and SentiStrength_id. This study collected users' comments for the Netflix app in the Google Play Store as a dataset using web scraping techniques through the Google Collaboration tool. The dataset contains 3250 rows spanning the period from January 22, 2024, through June 6, 2024. To ensure proper processing of the text, data cleaning, lowercasing, normalization, tokenization, stemming, and stopwords removal are conducted. The results show that most user opinions are negative. The InSet dictionary has an accuracy of 92%, SentiStrength_id 78%, Combined scenario 1 is 87%, and scenario 2 reaches the highest among others which is 92.52%.

关键词： Sentiment analysis Dictionaries Accuracy Films Collaboration Pricing Motion pictures Tokenization Cleaning Internet

来源：评论

学校读者我要写书评

暂无评论

Role of Fuzzy Approach towards Fault Detection for Distributed Components

引用

computers, Materials & Continua 2021年第5期67卷 1979-1996页

作者： Yaser Hafeez Sadia Ali Nz Jhanjhi Mamoona Humayun Anand Nayyar Mehedi Masud University Institute of Information Technology Pir Mehr Ali Shah Arid Agriculture UniversityRawalpindiPakistan School of Computer Science and Engineering SCETaylor’s UniversitySubang JayaMalaysia Department of Information systems College of Computer and Information SciencesJouf UniversitySaudi Arabia Graduate School Duy Tan UniversityDa Nang550000Viet Nam Faculty of Information Technology Duy Tan UniversityDa Nang550000Viet Nam Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

Component-based software development is rapidly introducing numerous new paradigms and possibilities to deliver highly customized software in a distributed *** other communication,teamwork,and coordination problems in global software development,the detection of faults is seen as the key ***,there is a need to ensure the reliability of component-based applications *** device detection faults applied to tracked components from various sources and failed to keep track of all the large number of components from different *** this study,we propose an approach for fault detection from componentbased systems requirements using the fuzzy logic approach and historical information during acceptance *** approach identified error-prone components selection for test case extraction and for prioritization of test cases to validate components in acceptance *** the evaluation,we used empirical study,and results depicted that the proposed approach significantly outperforms in component selection and acceptance *** comparison to the conventional procedures,i.e.,requirement criteria,and communication coverage criteria without irrelevancy and redundancy successfully outperform other ***,the F-measures of the proposed approach define the accurate selection of components,and faults identification increases in components using the proposed approach were higher(i.e.,more than 80 percent)than requirement criteria,and code coverage criteria procedures(i.e.,less than 80 percent),***,the rate of fault detection in the proposed approach increases,i.e.,92.80 compared to existing methods i.e.,less than 80 *** proposed approach will provide a comprehensive guideline and roadmap for practitioners and researchers.

关键词： Component-based software selection acceptance testing fault detection

来源：评论

学校读者我要写书评

暂无评论

Maintaining Image Size by Developing the Cropping Rectangle Method on CT-Scan Images

Maintaining Image Size by Developing the Cropping Rectangle ...

引用

IEEE International Conference on Communication, Networks and Satellite (ComNetSat)

作者： Guslendra Yuhandri Sarjon Defit Department of Information System Computer Science Faculty Universitas Putra Indonesia YPTK Padang Indonesia Department of Information Technology Computer Science Faculty Universitas Putra Indonesia YPTK Padang Indonesia

CT-Scan is a computer-based imaging technology, but it presents certain weaknesses, including interpretation challenges, lengthy analysis times, and visualization limitations. The progress in digital image processing science empowers computers to identify objects through recognizing distinctive features. To facilitate further data processing, an image cropping method is essential to narrow down the area of interest, as not all parts of an object require processing. However, using a rectangular cropping method can lead to a reduction in image size, potentially compromising image quality and causing blurring when displayed on the same axes. To uphold image quality and avert blurring, maintaining the cropped image’s size becomes crucial. The developed rectangular cropping method successfully preserves the cropped image’s size by adjusting the intensity values of pixels surrounding the cutting point. Coordinate points within the cropping rectangle delineate the region where pixel intensity values are modified. In this study, input images were sourced from CT-scan images of M. Djamil Hospital, Padang, West Sumatra, in jpg format. The developed algorithm underwent testing using the Matlab program, employing the rectangle method for image cropping to ensure the image size remained constant. The study’s outcomes reveal no disparity in the number of pixels obtained when employing the developed rectangular cropping method. Based on the experiments carried out in this study using 8 input images that were successfully maintained, the size of the image from the cropped image was 8 images and 0 images were unsuccessful, so the accuracy obtained in this study was 100%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAPAST: Content Affinity Preserved Arbitrary Style Transfer

CAPAST: Content Affinity Preserved Arbitrary Style Transfer

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xinyuan Zheng Xiaojie Li Canghong Shi Jia He Zhan Ao Huang Xian Zhang Imran Mumtaz School of Computer Science Chengdu University of Information Technology China School of Computer and Software Engineering Xihua University China Faculty of Engineering and Mathematical Sciences The University of Western Australia Australia Department of Computer Science University of Agriculture Faisalabad Pakistan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Balancing the consistency of style and the integrity of content is the main challenge in arbitrary style transfer domain. Currently, local style details can be effectively captured by attention mechanism but easily produce distorted style patterns and inconsistent content structure. In this paper, we propose a Content Affinity Preserving Arbitrary Style Transfer (CAPAST) framework to ensure style features can be stably integrated into the content structure. Considering the local feature learning ability of CNN and the global feature representation advantage of transformer, a dual encoder is proposed to capture local and global features of images with the combination between transformer and CNN. In addition, a channel and spatially aligned attention (CSAA) is introduced to generate high-quality results by stably fusing style features and content features. In experiments, we demonstrated the superior performance of our method in preventing content structure distortion and maintaining consistency between style and content. Codes are available at https://***/miaopashi-zxy/CAPAST.

关键词： Representation learning Acoustic distortion Codes Attention mechanisms Fuses Transformers Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Design and Application of programmable Analog Computing Circuit for Kalman Filter Algorithm Based on Memristive Array

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and Systems for Artificial Intelligence 2024年第2期1卷 272-284页

作者： Pingdan Xiao Sichun Du Zhengmiao Wei Qinghui Hong Shiping Wen College of Computer Science and Electronic Engineering Hunan University Changsha China Australian AI Institute Faculty of Engineering and Information Technology University of Technology Sydney Sydney NSW Australia

Kalman Filter algorithm is a crucial tool for estimating the state of dynamic systems in the presence of numerous uncertainties, which plays a pivotal role in various application scenarios such as information fusion and deep learning. However, current accelerators and hardware face limitations in terms of both latency and performance overhead when executing the Kalman Filter algorithm. Aiming at the above problem, we firstly propose a programmable circuits based on memristors for full process of Kalman Filter algorithm, which can efficiently run Kalman Filter algorithm with the advantage of analog circuits in parallel and fast computing, which achieve computing speed increasing in order of magnitude. Moreover, the empowerment of programmability from memristors avoid intensive memory access. For the problem how to linearly adjust weight for the memristor, we propose a new memristor-based programmable unit, the corresponding crossbar and method in order to achieve linear weight adjustment. The evaluation shows that the proposed circuits not only has over 95 $\%$ accuracy for 32-th order parameter matrix in Kalman Filter algorithm, but also has good robustness against some non-ideal factors it can still achieve 90 $\%$ accuracy under 10 $\%$ noise interference. The evaluating results of performance also show that it reduces energy consumption by 3.1 $\times$ and 8.9 $\times$ , compared with corresponding VLSI and FPGA accelerator, respectively. Moreover, an improved image fusion algorithm and circuit based on the proposed Kalman Filter circuits is proposed, which achieve good image fusion and speedup in computing time by 82.6 $\times$ and 121.3 $\times$ , compared with corresponding ASIC and FPGA, respectively.

关键词： Memristors Circuits Kalman filters Covariance matrices Artificial intelligence Analog circuits Noise Power demand Image fusion Field programmable gate arrays

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：