检索结果-内蒙古大学图书馆

Classification of chicken egg quality using faster region convolutional neural network

AIP Conference Proceedings 2024年第1期2987卷

作者： Amira Nurul Amanda Ivan Jaya Fanindia Purnamasari Research Laboratory in Data Science Intelligent System and Software Engineering Faculty of Computer and Information Technology Universitas Sumatera Utara Medan Indonesia

Chicken eggs are one of animal product which have high nutrition with cheaper price compared to another animal product. As one of the most consumed food, the quality of chicken eggs need to be more considered. According to SNI 3926:2008 and Egg Grading Manual Booklet, the quality of chicken egg can be seen from inside and also external characteristic of egg (egg shell). The internal characteristic are the yolk, egg whites, blood stains. The external characteristic are color, texture, cleanliness, thickness of the shell. This study builds a system which can detect the quality of chicken eggs by seeing the texture and the color of the shell. The quality of that chicken eggs grouped into three levels which is Grade A, Grade B, and Grade C. The amount of data that used in this study are 60 data that divided into 480 data for training and 120 data for testing. Data were doing pre-processing before classified with Faster Region Convolutional Neural Network method with ResNet-50 as pre-trained model. Based on the result of training system, this system can classify the quality of chicken eggs with an accuracy rate of 94%. The performance of the system in classifying egg quality is very sufficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model

arXiv

引用

arXiv 2022年

作者： Wang, Di Zhang, Qiming Xu, Yufei Zhang, Jing Du, Bo Tao, Dacheng Zhang, Liangpei The School of Computer Science Wuhan University Wuhan430072 China The National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Wuhan430072 China The School of Computer Science Faculty of Engineering The University of Sydney Australia The JD Explore Academy China The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models in remote sensing (RS) have not yet been sufficiently explored. In this paper, we resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models tailored to RS tasks and investigate how such large models perform. To handle the large sizes and objects of arbitrary orientations in RS images, we propose a new rotated varied-size window attention to replace the original full attention in transformers, which can significantly reduce the computational cost and memory footprint while learning better object representation by extracting rich context from the generated diverse windows. Experiments on detection tasks show the superiority of our model over all state-of-the-art models, achieving 81.24% mAP on the DOTA-V1.0 dataset. The results of our models on downstream classification and segmentation tasks also show competitive performance compared to existing advanced methods. Further experiments show the advantages of our models in terms of computational complexity and data efficiency in transferring. The code and models will be released at https://***/ViTAE-Transformer/Remote-Sensing-RVSA Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced local attention dual networks for pathological image restoration in healthcare

引用

Measurement: Sensors 2024年 33卷

作者： Hassan, Abdelwahab Said Thakare, Anuradha Bhende, Manisha Prasad, K.D.V. Singh, Pavitar Parkash Byeon, Haewon Department of Mathematics Faculty of Science Suez Canal University Egypt Department of Computer Engineering Pimpri Chinchwad College of Engineering Pune411044 India Dr. D. Y. Patil Vidyapeeth Pune Dr. D. Y. Patil School of Science & Technology Tathawade Pune India Hyderabad Pune India Department of Management Lovely Professional University India Department of AI and Software Inje University Gimhae50834 Korea Republic of Inje University Medical Big Data Research Center Gimhae50834 Korea Republic of

High-resolution pathological images play a pivotal role in accurate disease diagnosis and are important in precision medicine. However, obtaining real-time high-resolution images faces challenges due to hardware limitations and scanning time constraints. Conventional image super-resolution restoration algorithms struggle to provide satisfactory results for pathological images, resulting in blurred and unrealistic restorations. In response to this challenge, this research proposes a pioneering approach by integrating Internet of Things (IoT) technology with Local Attention Dual Network (IOT-LAT) for super-resolution restoration of pathological images. The enhanced IOT-LATincorporates IoT-based data acquisition and processing, IoT-Enhanced non-local attention mechanisms, Gaussian constraint, and parameter-sharing strategies in up-sampling and down-sampling branches. This integration enables real-time super-resolution restoration of pathological images with improved accuracy. The reconstructed images exhibit a structural similarity of 0.914 and a peak signal-to-noise ratio of 30.84 dB. These results validate the effectiveness of the suggested approach in precisely reconstructing high-frequency details and improving modelling efficiency via a lightweight non-local attention mechanism enhanced by the Internet of Things. This work discusses IoT and non-local attention dual networks to improve pathological image super-resolution restoration. This allows for faster and more accurate disease diagnosis and treatment in precision medicine. © 2024 The Authors

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

引用

Communications in Theoretical Physics 2021年第6期73卷 158-166页

作者： Ammarah Raees Umer Farooq Muzamil Hussain Waseem Asghar Khan Fozia Bashir Farooq Faculty of Computer Science and Software Engineering Huaiyin Institute of TechnologyHuai'anChina Department of Mathematics COMSATS University IslamabadPark Road Chak Shahzad Islamabad 44000Pakistan Department of Mathematics College of Sciences AIZulfiMajmaah UniversityA1 Majma'ah11952 Saudi Arabia Department of Mathematics Imam Muhammad ibn Saud Islamic UniversityRiyadh 11432Saudi Arabia Department of Mathematics University of the Poonch RawalakotRawalakot 12350Pakistan

The aspiration of this research is to explore the impact of non-similar modeling for mixed convection in magnetized second-grade nanofluid *** flow is initiated by the stretching of a sheet at an exponential rate in the upward vertical *** buoyancy effects in terms of temperature and concentration differences are inserted in the x-momentum *** aspects of heat and mass transfer are studied using dimensionless thermophoresis,Schmidt and Brownian motion *** governing coupled partial differential system(PDEs)is remodeled into coupled non-similar nonlinear PDEs by introducing non-similar *** numerical analysis for the dimensionless non-similar partial differential system is performed using a local non-similarity method via ***,the quantitative effects of emerging dimensionless quantities on the nondimensional velocity,temperature and mass concentration in the boundary layer are conferred graphically,and inferences are drawn that important quantities of interest are substantially affected by these *** is concluded that non-similar modeling,in contrast to similar models,is more general and more accurate in convection studies in the presence of buoyancy effects for second-grade non-Newtonian fluids.

关键词： non-similar modeling second-grade fluid exponentially stretching surface local non-similarity bvp4c

来源：评论

学校读者我要写书评

暂无评论

Object recognition using enhanced particle swarm optimization 19

Object recognition using enhanced particle swarm optimizatio...

引用

19th International Conference on Machine Learning and Cybernetics, ICMLC 2020

作者： Willis, Michael Zhang, L.I. Liu, H.A.N. Xie, Hailun Mistry, Kamlesh Northumbria University Faculty of Engineering and Environment Department of Computer and Information Sciences NewcastleNE1 8ST United Kingdom Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9780738124261

The identification of the most discriminative features in an explainable AI decision-making process is a challenging problem. This research tackles such challenges by proposing Particle Swarm Optimization (PSO) variants embedded with novel mutation and sampling iteration operations for feature selection in object recognition. Specifically, five PSO variants integrating different mutation and sampling strategies have been proposed to select the most discriminative feature subsets for the classification of different objects. A mutation strategy is firstly proposed by randomly flipping the particle positions in some dimensions to generate new feature interactions. Moreover, instead of embarking the position updating evolution in PSO, the proposed PSO variants generate offspring solutions through a sampling mechanism during the initial search process. Two offspring generation sampling schemes are investigated, i.e. the employment of the personal and global best solutions obtained using the mutation mechanism, respectively, as the starting positions for the subsequent search process. Subsequently, several machine learning algorithms are used in conjunction with the proposed PSO variants to perform object classification. As evidenced by the empirical results, the proposed PSO variants outperform the original PSO algorithm, significantly, for feature optimization. © 2020 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Work fluctuations due to partial thermalizations in two-level systems

引用

Physical Review E 2021年第4期103卷 042141-042141页

作者： Maria Quadeer Kamil Korzekwa Marco Tomamichel Centre for Quantum Software and Information School of Computer Science University of Technology Sydney Ultimo NSW 2007 Australia Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University 30-348 Kraków Poland Department of Electrical and Computer Engineering & Centre for Quantum Technologies National University of Singapore Singapore 119077

We study work extraction processes mediated by finite-time interactions with an ambient bath—partial thermalizations—as continuous-time Markov processes for two-level systems. Such a stochastic process results in fluctuations in the amount of work that can be extracted and is characterized by the rate at which the system parameters are driven in addition to the rate of thermalization with the bath. We analyze the distribution of work for the case in which the energy gap of a two-level system is driven at a constant rate. We derive analytic expressions for average work and a lower bound for the variance of work showing that such processes cannot be fluctuation-free in general. We also observe that an upper bound for the Monte Carlo estimate of the variance of work can be obtained using Jarzynski's fluctuation-dissipation relation for systems initially in equilibrium. Finally, we analyze work extraction cycles by modifying the Carnot cycle, incorporating processes involving partial thermalizations, and we obtain efficiency at maximum power for such finite-time work extraction cycles under different sets of constraints.

关键词： Fluctuation theorems Irreversible processes Nonequilibrium statistical mechanics

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost IoT-Based System for Manufacturing Process Data Acquisition 13

A Low-Cost IoT-Based System for Manufacturing Process Data A...

引用

13th International UNIMAS engineering Conference, EnCon 2020

作者： Tang, Lui Sieng Jayaraman, Prakash Palanisamy, Suresh Chua, Hong Siang Swinburne University of Technology Sarawak Campus Faculty of Engineering Computer and Science Kuching Malaysia Swinburne University of Technology Hawthorn Campus Department of Computer Science and Software Engineering Hawthorn Australia Swinburne University of Technology Hawthorn Campus Department of Mechanical Engineering and Product Design Hawthorn Australia

ISBN: (纸本)9781728192932

In Malaysia, more than 90% of local industries/factories are considered Small and Medium size (SMI), most of the machine and equipment in shop floor are outdated, due to high cost of replacement. Hence, data collection inside the shop floor is time consuming and probably lack of accuracy since need to be done manually, causes low efficiency in production and delaying in delivery. As a result, it increases the cost in labor and logistics, and further resulting in low competitiveness in market. Therefore, a low cost IoT unit is presented in this research paper, aims to improve productivity and accuracy of manufacturing processes in shop floor. It is required to collect data from production line automatically. From the results, accuracy of data collected by this IoT unit is able to reach about 95% or more during production, and data are transmitted to database wirelessly in real-Time. Furthermore, it performs data analysis upon collected, minimize the time gap between processes, optimize the manufacturing processes. © 2020 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Membership-Mappings for Data Representation Learning: Measure Theoretic Conceptualization

arXiv

引用

arXiv 2021年

作者： Kumar, Mohit Moser, Bernhard Fischer, Lukas Freudenthaler, Bernhard Software Competence Center Hagenberg GmbH HagenbergA-4232 Austria Institute of Automation Faculty of Computer Science and Electrical Engineering University of Rostock Germany

A fuzzy theoretic analytical approach was recently introduced that leads to efficient and robust models while addressing automatically the typical issues associated to parametric deep models. However, a formal conceptualization of the fuzzy theoretic analytical deep models is still not available. This paper introduces using measure theoretic basis the notion of membership-mapping for representing data points through attribute values (motivated by fuzzy theory). A property of the membership-mapping, that can be exploited for data representation learning, is of providing an interpolation on the given data points in the data space. An analytical approach to the variational learning of a membership-mappings based data representation model is considered. © 2021, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Bctm:A Topic Modeling Method Based on External Information

SSRN

引用

SSRN 2022年

作者： Liu, Gang Wan, TaiYing Gao, JingQi Buntine, Wary College of Computer Science and Technology Harbin Engineering University Harbin150001 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210000 China Faculty of Information Technology Monash University Melbourne3800 Australia

Topic models are often used as intermediate algorithms for text mining and semantic analysis in natural language processing, and have a wide range of functions. However, most of the existing improvements to the topic model use word embedding to improve the accuracy of text modeling, but ignore the external information in the text. Aiming at the above problems, this paper proposes a topic model BCTM (Bi-Concept Topic Model) using the word feature information and concept information. Based on the BTM topic model, BCTM introduces word feature information through word vector technology and concept information based on ConceptNet to optimize topic modeling. The construction method of Bi-Concept pair is proposed. Based on ConceptNet semantic network, and the content of text is enriched with concept information. A more accurate topic distribution is obtained through the improved topic model, at the same time, due to the rich feature information, the model is also superior to the baseline model in short text modeling. The experiments prove that the bilingual topic model proposed in this paper has a good performance in modeling accuracy. © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Emerging case oriented agents for sustaining educational institutions going green towards environmental responsibility

引用

Journal of Systems and Information Technology 2019年第2期21卷 186-214页

作者： Anthony Jnr, Bokolo Abdul Majid, Mazlina Romli, Awanis Department of Computer Science Norwegian University of Science and Technology NTNU Trondheim Norway Universiti Malaysia Pahang Faculty of Computer Systems and Software Engineering Kuantan Malaysia

Purpose: The purpose of this paper is to design a system deployment model that integrates case-based agent technique to develop an eco-responsibility decision support tool for greening educational institutions toward environmental responsibility. Design/methodology/approach: Data were collected through questionnaires distributed among a statistical population that comprised practitioners across educational institutions in Malaysia that implement green practices. The questionnaire measured the feasibility of the developed tool based on factors derived from the literature. Accordingly, descriptive, exploratory and factor analysis approach using statistical package for social sciences (SPSS) was used to test the feasibility of the developed tool. Findings: Results from descriptive analysis confirm the tool is feasible based on mean values that range from 4.1619 to 3.6508 on a five-point scale, indicating that the tool is effective in sustaining educational institutions going green. Besides, results from exploratory analysis verify the reliability of the tool based on the acceptable Cronbach’s alpha reliability coefficient score higher than 0.7 and Kaiser–Meyer–Olkin value being above 0.5. Finally, results from factor analysis reveal that the developed tool is usable, efficient, helpful, flexible and credible and supports educational institutions in going green at 88.44 per cent of the total variance, suggesting that the respondents are satisfied with the tool. Research limitations/implications: The sample population in this study comprises only practitioners from educational institutions in Malaysia. Theoretically, this research provides feasibility factors and associated items that can be used in evaluating developed information systems. Practical implications: Practically, this study develops an eco-responsibility decision support tool to facilitate green strategies and provides information on how practitioners in educational institutions can improve green growth. So

关键词： Sustainable development

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：