检索结果-内蒙古大学图书馆

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Sunaina Sunaina basu Dev Shivahare Vikas Kumar S K Gupta Prabhishek Singh Manoj Diwakar Amity University Greater Noida Uttar Pradesh India Galgotias University Greater Noida Uttar Pradesh India Deptt. Of Computer Science and Engineering B.I.E.T Jhansi Uttar Pradesh India Bennett University Greater Noida Uttar Pradesh India Graphic era Deemed to be University Dehradun Uttarakhand India

Optimization is the process of searching optimal solution of complex prob.ems more efficiently. There is a class of prob.ems which is called NP (nondeterministic polynomial) prob.em which means that solution of NP prob.em based on metaheuristic approach may be verified in polynomial time which might take exponential number of steps to find the solution. To solve such prob.ems, we may use special type of algorithm which is called Meta Heuristic (MA’s) algorithm. MA’s are ab.e to provide near optimal solution by introducing randomization technique with deterministic approach. In this paper, we have discussed some meta heuristic algorithms and their applications in research areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Label-efficient Ob.ect Detection via Region Proposal Network Pre-Training

arXiv

引用

arXiv 2022年

作者： Dong, Nanqing ericsson, Linus Yang, Yongxin Leonardis, Ales McDonagh, Steven Shanghai Artificial Intelligence Laboratory Shanghai200232 China School of Engineering University of Edinburgh EdinburghEH9 3FG United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom

Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient ob.ect detection. However, existing studies focus on pre-training only a feature extractor network to learn transferab.e representations for downstream detection tasks. This leads to the necessity of training multiple detection-specific modules from scratch in the fine-tuning phase. We argue that the region proposal network (RPN), a common detection-specific module, can additionally be pre-trained towards reducing the localization error of multi-stage detectors. In this work, we propose a simple pretext task that provides an effective pre-training for the RPN, towards efficiently improving downstream ob.ect detection performance. We evaluate the efficacy of our approach on benchmark ob.ect detection tasks and additional downstream tasks, including instance segmentation and few-shot detection. In comparison with multi-stage detectors without RPN pre-training, our approach is ab.e to consistently improve downstream task performance, with largest gains found in label-scarce settings. Copyright © 2022, The Authors. All rights reserved.

关键词： Ob.ect detection

来源：评论

学校读者我要写书评

暂无评论

Language-based document image retrieval for Trilingual System

引用

International Journal of Information Technology (Singapore) 2020年第4期12卷 1217-1226页

作者： Dixit, Umesh D. Shirdhonkar, M.S. Department of Electronics and Communication Engineering B.L.D.E.A’s V. P. Dr. P.G. Halakatti College of Engineering and Technology Vijayapur 586103 India Department of Computer Science and Engineering B.L.D.E.A’s V. P. Dr. P. G. Halakatti College of Engineering and Technology Vijayapur 586103 India

Language-based document image retrieval (LbDIR) is an essential need for a multi-lingual environment. It provides an ease of accessing, searching and browsing of the documents pertaining to a particular language. This paper proposes a method for LbDIR using multi-resolution Histogram of Oriented Gradient (HOG) features. These features are obtained by computing HOG on the sub-bands of Discrete Wavelet Transform. The Canberra distance is used for matching and retrieval of the documents. The proposed scheme is investigated on the three datasets (Dataset1, Dataset2 and Dataset3) consisting of 1437 document images of Kannada, Marathi, Telugu, Hindi and english languages. The ob.ective of this work is to provide an efficient LbDIR for the government and non-government organizations of Karnataka, Maharashtra and Telangana states with the context of the tri-lingual model adopted. An average precision (AP) of 96.2%, 95.4%, 94.6%, 99.4% and 99.6% for Kannada, Marathi, Telugu, Hindi and english language documents is achieved while retrieving top 50 documents with the proposed method. The proposed feature extraction scheme provided promising results compared to existing techniques. © 2019, bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Canberra distance Document image retrieval DWT HOG Similarity metric

来源：评论

学校读者我要写书评

暂无评论

Modification approach of Northern Wall to improve the performance of solar greenhouse dryers: A review

Green Energy and Resources

引用

Green energy and Resources 2024年第4期2卷

作者： Ndukwu, M.C. Akuwueke, Leonard Akpan, Godwin Umunna, M.F. Usoh, Godwin ekop, Inemesit etim, Promise Okosa, I. Orji, Francis Ikechukwu-edeh, e.C. ekop, Ifiok Simo-Tagne, Merlin bennamoun, Lyes Wu, Hongwei Abam, Fidelis Department of Agricultural and Bio-Resources Engineering Michael Okpara University of Agriculture Umudike P.M.B.7267 Umuahia Nigeria Department of Agricultural Engineering Akwa Ibom State University Akwa Ibom state Nigeria Department of Agricultural Engineering Faculty of Engineering Delta State University of Science and Technology Ozoro Nigeria Department of Building University of Uyo Akwa Ibom State Nigeria Department of Forestry and Agriculture CFA-CFPPA of Mirecourt 22 rue du Docteur Grosjean Mirecourt 88500 France Department of Mechanical Engineering University of New Brunswick 15 Dineen Drive Fredericton E3B 5A3 NB Canada School of Physics Engineering and Computer Science University of Hertfordshire Hatfield United Kingdom Department of Mechanical Engineering University of Calabar Cross River State Nigeria

Globally, interest is shifting toward green energy due to its environmental appeal. Therefore, to promote energy and environmental conservation in drying, several solar dryers have b.en developed which offers limitless, clean, and free energy to dry agricultural product. Among these solar dryers, solar greenhouse dryers offer a very simple low-temperature, energy-efficient structure capab.e of drying large beds of crops by harnessing thermal radiation energy from the sun. To improve the thermal performance in the passive mode especially, several modification approaches have b.en adopted. This article, therefore, reviewed various possib.e modification methods that have b.en adopted to improve the thermal performance of the greenhouse, with a focus on the modification of the northern wall. The various strategies involved in the modification of the north wall structure include creating an opaque north wall with black painted materials, installing a reflective north wall using a mirror, integrating heat storage materials like pebb.es or brick, integrating phase change materials into the north wall, digging the soil depth to form a north wall and creating a variab.e southern roof with a modified north wall. Modifying the northern wall showed higher drying chamber temperature compared to completely transparent convectional greenhouse dryers in all the studies. These modifications can increase the temperature of the modified greenhouse by 13.38∼21.10% for a natural convection solar greenhouse dryer compared to the conventional type. With this approach, the radiation losses from the northern wall can be minimized and the energy management system of the greenhouse can be optimized for higher performance, making it more sustainab.e and eliminating the use of fossil fuel in agricultural product drying. © 2024 The Author(s)

关键词： Crop drying Greenhouse dryer Northern wall Solar energy

来源：评论

学校读者我要写书评

暂无评论

SHbO-based U-Net for image segmentation and FSHbO-enab.ed DbN for classification using hyperspectral image

引用

The Journal of Photographic science 2024年第4期72卷

作者： Tatireddy Subba Reddy V. V. Krishna Reddy R. Vijaya Kumar Reddy Chandra Sekhar Kolli V. Sitharamulu Majjaru Chandrababu a Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur India b Department of Information Technology Lakireddy Bali Reddy College of Engineering Mylavaram India c Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur India d Department of Computer Science Gandhi Institute of Technology and Management Visakhapatnam India e Department of Computer Science and Engineering GITAM School of Technology GITAM (Deemed-to-be-University) Hyderabad India f School of Information Technology VIT University Vellore India

AbSTRACTHyper spectral imaging (HSI) is an advanced and fascinating remote sensing method in various domains. every sample in HS remote sensing images possesses high-size features and has a massive amount of spatial and spectral data that enhances the complexity of feature selection and mining. Also, it improves the interpretational complications and thus surpasses the prediction accuracy of the system. To counterpart such issues, this article introduces an innovative system for HSI categorization wielding introduced Fractional Snake Honey badger Optimization (FSHbO). Here, image segmentation is done through U-Net, which is trained by Snake Honey badger Optimization (SHbO). The Deep belief Network (DbN) is employed for HSI classification that outputs the pixel-wise classified result and this DbN is efficiently tuned using the proposed FSHbO. It is recorded that the proposed FSHbO-DbN has outperformed diverse classical models in terms of accuracy of 0.907, sensitivity of 0.914, and specificity of 0.904.

关键词： Hyper spectral imaging (HSI) remote sensing image (RSI) snake optimizer (SO) honey badger algorithm (HbA) Snake Honey badger Optimization (SHbO) Fractional Calculus (FC) Deep belief Network (DbN)

来源：评论

学校读者我要写书评

暂无评论

Attitude Synchronization for Multi-Agent Systems on SO(3) Using Vector Measurements

arXiv

引用

arXiv 2025年

作者： boughellaba, Mouaad berkane, Soulaimane Tayebi, Ab.elhamid Department of Electrical Engineering Lakehead University Thunder BayONP7B 5E1 Canada Department of Computer Science and Engineering University of Quebec in Outaouais GatineauQC Canada

In this paper, we address the prob.em of leaderless attitude synchronization for a group of rigid body systems evolving on SO(3), relying on local measurements of some inertial (unit-length) vectors. The interaction graph among agents is assumed to be undirected, acyclic, and connected. We first present a distributed attitude synchronization scheme designed at the kinematic level of SO(3), followed by an extended scheme designed at the dynamic level. both schemes are supported by a rigorous stability analysis, which establishes their almost global asymptotic stability properties. Finally, numerical simulations demonstrate the effectiveness of both distributed attitude synchronization schemes. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on recent development in infrared small target detection algorithms

引用

Procedia computer science 2020年 167卷 2496-2505页

作者： Sur Singh Rawat Sashi Kant Verma Yatindra Kumar Department of Computer Science and Engineering JSS Acade my of technical education Noida India Department of Computer Science and Engineering G.B.P.I.E.T Pauri Garhwal Uttarakhand India Department of Electrical Engineering Engineering G.B.P.I.E.T Pauri Garhwal Uttarakhand India

Over the last decade, many algorithms have b.en presented on an infrared target detection prob.em. This paper reviews the recent approaches in infrared small target detection algorithms. Firstly, the detailed review of Detection-before-Track methods which are seen in recent years are discussed and prob.em associated with these methods are raised. Secondly, to verify the robustness of these methods, large set of experiments are conducted and comparative analysis of different baseline methods is done. In addition to this advantages and disadvantages of baseline methods is discussed. experimental results from the dataset suggest that the patch based methods are more robust than the other filter-based methods. How to address the issues of small target detection method in complex environment and the effect of varying parameters like patch size, step size and controlling parameters is our future endeavor.

关键词： Track before detection (TbT) detect before track(DbT) infrared search track signal to clutter ratio infrared patch image model

来源：评论

学校读者我要写书评

暂无评论

Physically Agnostic Quasinormal Mode expansion in Time Dispersive Structures:from Mechanical Vibrations to Nanophotonic Resonances

arXiv

引用

arXiv 2024年

作者： Nicolet, André Demésy, Guillaume Zolla, Frédéric Campos, Carmen Roman, Jose e. Geuzaine, Christophe Aix Marseille Univ CNRS Centrale Med Institut Fresnel Marseille France Universitat de València D. Didáctica de la Matemática Avda. Tarongers 4 ValènciaE-46022 Spain Universitat Politècnica de València D. Sistemes Informàtics i Computació Camí de Vera s/n ValènciaE-46022 Spain University of Liège Dept. of Electrical Engineering and Computer Science Allée de la Découverte 10 LiègeB-4000 Belgium

Resonances, also known as quasi normal modes (QNM) in the non-Hermitian case, play an ubiquitous role in all domains of physics ruled by wave phenomena, notably in continuum mechanics, acoustics, electrodynamics, and quantum theory. In this paper, we present a QNM expansion for dispersive systems, recently applied to photonics but based on sixty year old techniques in mechanics. The resulting numerical algorithm appears to be physically agnostic, that is independent of the considered physical prob.em and can therefore be implemented as a mere toolbox in a nonlinear eigenvalue computation *** Codes 65N25, 35b34, 78-10, 78A25, 78M10, 70J10, 74S05 © 2024, CC bY.

关键词： Continuum mechanics

来源：评论

学校读者我要写书评

暂无评论

Design of inception ResNet V2 for detecting malarial infection using the cell image captured from microscopic slide

引用

The Journal of Photographic science 2024年第5期72卷

作者： P. Mayil Vel Kumar Anita Venaik P. Shanmugaraja P. John Augustine M. Madiajagan a Department of Computer Science and Engineering Karpagam Institute of Technology Coimbatore India b Department of General Management Amity Business School Amity University Noida India c Department of Information Technology Sona College of Technology Salem India d Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore India e School of Computer Science and Engineering Vellore Institute of Technology Katpadi Vellore India

AbSTRACTOver the past decades, malarial infection is considered a dreadful disease which ruins the lives of millions of people all over the globe. Several research works were developed based on machine learning algorithms to categorize the malarial infected person. However effective prediction with precise results is not attained in conventional approaches. For accurate prediction of malarial transmission deep learning technology is designed in this proposed model. This proposed design utilized inception ResNet V2 for the prediction of malarial-infected individuals. before disease prediction, certain pre-processing techniques such as noise removal, contrast enhancement and segmentation are used to minimize the error rate during the classification process. The function of the proposed model is evaluated using metrics such as accuracy, recall, precision, etc. The simulation analysis shows that the proposed method obtains 0.98% accuracy, 0.02% error, precision is 0.92%, specificity is 0.94% so on. Thus the designed model predicted the malarial disease effectively.

关键词： Deep learning malarial transmission prediction model CNN cell image inception ResNetV2 VGG19 U-net

来源：评论

学校读者我要写书评

暂无评论

Detection of Nuclei Cell in Histopathological Images of Uterine Cancer: Adenocarcinoma of endometrium 4

Detection of Nuclei Cell in Histopathological Images of Uter...

引用

4th International Conference on Trends in electronics and Informatics, ICOeI 2020

作者： Patil, Shoba. R Patil, Veena. I Basaveshwar Engineering College Affiliated to Visvesvaraya Technological University Department of Information Science and Engineering Bagalkot India B.L.D.E.A's V. P. Dr. P. G. Halakatti College of Engineering and Technology Affiliated to Visvesvaraya Technological University Department of Computer Science and Engineering Vijayapur India

ISBN: (纸本)9781728155180

Pathologist visual inspection of Histopathological uterine tissue sample is still considered as confirmatory test for uterine cancer finding. Manual assessment depends upon the knowledge and experience of pathologist. Hence sub.ect of concern is ob.ective analysis. An effective way of diagnosis, grading and classification of endometrium adenocarcinoma is structural analysis of the tissue sample. The effectiveness of computer assisted diagnosis, grading and classification depends on glandular structure and detection of individual nuclei cell. Hematoxylin channel from He stained image is extracted using color deconvolution algorithm. Morphological operation and thresholding are carried out in this work for structural analysis of glandular region and for detection of nuclei cell. To rise the effectiveness of the system elimination of cell nuclei from stroma is done before feature extraction is also described. © 2020 Ieee.

关键词： Cells

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：