检索结果-内蒙古大学图书馆

Optimizing Algorithm Hyperparameters and Backbone of Single-shot Detector for Object Detection

Sensors and Materials 2024年第1-3期36卷 337-350页

作者： Huang, Wei-Tai Chen, Yenming J. Tsai, Jinn-Tsong Ho, Wen-Hsien Department of Mechanical Engineering National Pingtung University of Science and Technology Pingtung912 Taiwan Department of Information Management National Kaohsiung University of Science and Technology Kaohsiung824 Taiwan Department of Computer Science and Artificial Intelligence National Pingtung University Pingtung900 Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung807 Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung807 Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung912 Taiwan

In this study, we explored a single-shot detector (SSD) backbone and its optimized algorithm hyperparameters for object detection, and proposed a systematic method for determining appropriate algorithm hyperparameter combinations for the SSD backbone. The VGG16 backbone for SSD has been used for object detection. The Resnet backbone won first place in the 2015 ImageNet Large Scale Visual Recognition Challenge (ILSVRC), while the VGG16 backbone ranked second place in the 2014 ILSVRC. We selected the Resnet50 backbone for SSD for vehicle image detection research because the Resnet50 backbone has a high feature extraction capability. We proposed SSD with the Resnet50 backbone and its optimized algorithm hyperparameters, called the SSD-Resnet50 model, to replace SSD with the VGG16 backbone and its optimized algorithm hyperparameters, called the SSD-VGG16 model, to enhance the vehicle image detection feature extraction capability. The Taguchi method optimized the algorithm hyperparameters of the Resnet50 and VGG16 backbones, thus improving the detection accuracies of the SSD-Resnet50 and SSD-VGG16 models, respectively. Experimental results show that the SSD-Resnet50 model using 300 × 300 × 3 input images achieved a detection accuracy of an average average precision (AP) of 97.15% in three independent experiments, outperforming the SSD-VGG16 model using 300 × 300 × 3 input images with an average AP of 86.83% on the test set of vehicle images. As a result, the SSD-Resnet50 model has a higher accuracy of vehicle detection in images from the Caltech cars 1999 and 2001 datasets. © 2024 M Y U Scientific Publishing Division. All rights reserved.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Retraction notice to "Incorporating crumb rubber in slag-based geopolymer: Experimental work and predictive modelling" [Case Stud. Constr. Mater. 21 (2024) e03893] (Case Studies in Construction Materials (2024) 21, (S2214509524010441), (10.1016/***.2024.e03893))

引用

Case Studies in Construction Materials 2025年

作者： Raut, Ashwin Narendra Alyaseen, Ahmad Khan, Afzal Husain Janga, Supriya Poddar, Arunava Sihag, Parveen Sumra, Vinisha Lee, Daeho Kumar, Raj Singhi, Tej Andhra Pradesh 522502 India Civil Engineering Department Shoolini University Himachal Pradesh Solan173229 India Civil and Architectural Engineering Department College of Engineering and Computer Sciences Jazan University PO Box 706 Jazan45142 Saudi Arabia Department of Civil Engineering Vikas Group of Institutions Nunna Vijayawada Rural Andhra Pradesh India Civil Engineering Department Chandigarh University Punjab Mohali140413 India Mullana Haryana Ambala India Department of Mechanical Engineering Gachon University 1342 Seongnamdaero Sujeong-gu Seongnam13120 Korea Republic of Jindal School of Environment & Sustainability O.P. Jindal Global University Haryana Sonipat131001 India Savaria Institute of Technology Faculty of Informatics ELTE Eötvös Loránd University Budapest1117 Hungary

This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://***/about/policies/article-withdrawal). This article has been retracted at the request of the Editors-in-Chief. Following concerns raised by a reader, an investigation of this paper was undertaken by the editors. The findings indicate that this paper [https://***/10.1016/***.2024.e03893] and another in Construction and Building Materials [https://***/10.1016/***.2024.138985] utilise the same dataset (see supplementary data provided for each paper) and the same methodology (identical Figures 5 and 12 in CSCM and Figures 5 and 18 in CBM paper). Four other figures (1, 2a, 3 and 4) and four tables (Tables 1, 3, 4 and 5) are also repeated in both papers. As part of this investigation, the lead author (Raut) provided additional supporting data for review. The investigating editor found the mix design data did not appear to match that reported in the published supplementary material and the compression results were suspect for their minimal apparent variation over 108 geopolymer mixes. Additionally, mix design data and density was incorrectly calculated. The corresponding author stated that this CSCM paper was submitted on June 27, 2024, and published first and claims to have no knowledge of the CBM submission on 28 August 2024 despite five common coauthors. Both papers were in review at the same time and ultimately published within five days of each other. © 2025 The Authors

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fruit Quality Assessment with Densely Connected Convolutional Neural Network

Fruit Quality Assessment with Densely Connected Convolutiona...

引用

International Conference on Electrical and computer engineering (ICECE)

作者： Md. Samin Morshed Sabbir Ahmed Tasnim Ahmed Muhammad Usama Islam A.B.M. Ashikur Rahman Department of Computer Science and Engineering Islamic University of Technology Gazipur Bangladesh School of Computing and Informatics University of Louisiana at Lafayette Lafayette LA USA Department of ICS King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

Accurate recognition of food items along with quality assessment is of paramount importance in the agricultural industry. Such automated systems can speed up the wheel of the food processing sector and save tons of manual labor. In this connection, the recent advancement of Deep learning-based architectures has introduced a wide variety of solutions offering remarkable performance in several classification tasks. In this work, we have exploited the concept of Densely Connected Convolutional Neural Networks (DenseNets) for fruit quality assessment. The feature propagation towards the deeper layers has enabled the network to tackle the vanishing gradient problems and ensured the reuse of features to learn meaningful insights. Evaluating on a dataset of 19,526 images containing six fruits having three quality grades for each, the proposed pipeline achieved a remarkable accuracy of 99.67%. The robustness of the model was further tested for fruit classification and quality assessment tasks where the model produced a similar performance, which makes it suitable for real-life applications.

关键词： Industries Pipelines Wheels Manuals Object detection Robustness Raw materials

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Assessment of OCR Tools for Gene Name Recognition in Biological Pathway Figures

Comprehensive Assessment of OCR Tools for Gene Name Recognit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Stuart Aldrich Micheal Olaolu Arowolo Fei He Mihail Popescu Dong Xu Department of Electrical Engineering and Computer Science University of Missouri Columbia Missouri USA College of Information Science and Technology Northeast Normal University Changchun China Department of Health Management and Informatics University of Missouri Columbia Missouri USA

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Optical Character Recognition (OCR) is becoming more and more effective in text detection in images. However, OCR’s performance in special applications may vary. In particular, OCR in visual representations of complex processes known as pathway figures in the biomedical literature is challenging. The information depicted in a pathway graphic usually represents the article’s most important conclusions. Still, the huge number of pathway figures cannot be automatically processed for large-scale search, data mining, and downstream analysis. Assisted by recent developments in OCR, we have developed a method to extract gene names from pathway images. For usage in the method, we thoroughly evaluated and compared major available OCR tools using 563 genes from 45 pathway images, 1000 images of alphanumeric characters and gene names from HUGO, and KEGG data with 20 random pathway genes curated routes. Our study showed that Google Cloud Vision and MMOCR are best suitable for gene name recognition in pathway figures.

关键词： Visualization Image recognition Sensitivity Limiting Text recognition Biological system modeling Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

A new approach to b-coloring of regular graphs

arXiv

引用

arXiv 2023年

作者： Dettlaff, Magda Furmańczyk, Hanna Peterin, Iztok Roux, Riana Ziemann, Radoslaw University of Gdańsk Institute of Informatics Faculty of Mathematics Physics and Informatics Wit Stwosz 57 Gdańsk80-309 Poland University of Maribor Faculty of Electrical Engineering and Computer Science Koroška 46 Maribor2000 Slovenia Institute of Mathematics Physics and Mechanics Jadranska 19 Ljubljana1000 Slovenia Department of Mathematical Sciences Stellenbosch University Stellenbosch South Africa

Let G be a graph and c: V (G) → {1, . . ., k} a proper k-coloring of G, i.e. c(u) 6= c(v) for every edge uv from G. A proper k-coloring is a b-coloring if there exists a vertex in every color class that contains all the colors in its closed neighborhood. The maximum number of colors k admitting b-coloring of G is the b-chromatic number χb(G). We present two separate approaches to the conjecture posed by Blidia et. al [Discrete Appl. Math., 157(8):1787–1793, 2009] that χb(G) = d + 1 for every d-regular graph of girth at least five except the Petersen *** Codes 05C15 Copyright © 2023, The Authors. All rights reserved.

关键词： Coloring

来源：评论

学校读者我要写书评

暂无评论

Analysis of Dense Descriptors in 3D Face Recognition

Analysis of Dense Descriptors in 3D Face Recognition

引用

11th IEEE International Conference on System engineering and Technology, ICSET 2021

作者： Zebari, Dilovan Asaad Abrahim, Araz Rajab Ibrahim, Dheyaa Ahmed Othman, Gheyath M. Ahmed, Falah Y. H. Nawroz University Department of Computer Science Kurdistan Region Duhok42001 Iraq Duhok Polytechnic University Technical College of Informatics Department of Information Technology Iraq Information Technology Collage Imam Ja 'Afar Al-Sadiq University Communications Engineering Techniques Department Baghdad Iraq Management Science University Faculty of Information Sciences Engineering Selangor Shah Alam Malaysia

ISBN: (纸本)9781665437660

In the past years, a revolution took place in the world of technology and developed rapidly in all areas, covering various aspects of life. One of the hottest topics that researchers work in is computer vision including artificial intelligence. As it has a great importance, it represents the basics for many applications that are currently used in various sectors. The technology of biometric recognition has progressively developed specially in security for identification purposes. Such technology is face recognition, which uses facial information of humans to recognize people. In this paper 3D (three-dimensional) face recognition approach is proposed by using dense descriptors Local Binary Pattern (LBP), Local Ternary Pattern (LTP), and Gabor with Support Vector Machine (SVM). LTP technique which is a variant and extension of LBP. LBP and LTP have been used for feature information extraction individuality and merging with Gabor from the 3D images, and then the SVM technique is employed to classify and recognize the faces according to extracted features. The database that depended in this work is Three-Dimensional Face Recognition Database (Texas 3DFRD). The accuracy obtained from the proposed model was about 94.9% after many attempts the better one is selected. © 2021 IEEE.

关键词： Support vector machines Three-dimensional displays Image resolution Databases Face recognition Merging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DQPS: An Intelligent Multi-Hop Computation Offloading Scheme for Workflow Applications in Vehicular Edge Computing Networks

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Lin, Bing Chen, Qiaoxin Chen, Xing Jia, Wen-Kang Lu, Yu Xiong, Neal N. Fujian Normal University College of Physics and Energy Fujian Provincial Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou350117 China Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering Fuzhou350117 China Peking University School of Computer Science 100871 China Xiamen University Department of Informatics and Communication Engineering Xiamen361005 China Fuzhou University College of Computer and Data Science Fuzhou350118 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350118 China Fujian Normal University College of Photonic and Electronic Engineering Fuzhou350117 China Fujian Normal University Concord University College Fuzhou350117 China Sul Ross State University Department of Computer Mathematical and Physical Sciences AlpineTX79830 United States

Vehicular Edge Computing (VEC) is a feasible solution for autonomous driving as it can offload latency-sensitive and computation-intensive tasks from vehicle terminals to roadside units (RSUs) for real-time processing. Due to the high computational resource the workflow applications (i.e., autonomous driving) required, the small vehicle-to-RSUs communication range, and the scarce available resources for each vehicle, it might be difficult to accomplish complex workflow applications through the single-hop offloading paradigm in the Internet of Vehicles (IoV). In this paper, we propose a reinforcement learning (RL) based multi-hop computation offloading scheme for workflow applications to reduce their execution latency in the VEC networks, which considers the data dependency in workflow applications as well as the trust relationship and communication interference among RSUs. Firstly, a preprocessing method is employed to merge the cut-edges in a workflow to reduce the offloading scale of tasks and compress the encoding dimension of offloading solutions. Then, a Deep Q-network algorithm using Phase-optimal State update (DQPS) is proposed to update the offloading policy distribution, in which the deviation of the phase-optimal state from the current state is estimated as the reward of RL to promote the algorithm's convergence to adapt the dynamic VEC networks. Simulation results show that DQPS has the best performance compared to other benchmark schemes. Moreover, the latency of the identical applications can be reduced by 2.5%-25.3% through our offloading scheme with a multi-hop model compared to that with the single-hop paradigm in IoV. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

An All-Optical Metro Network Architecture and QoS-Aware Wavelength Allocation Study for Converged Fixed, Mobile, and Edge Computing Multi-Granular Traffic

arXiv

引用

arXiv 2025年

作者： Georgantas, David Liu, Zhaoyang Drainakis, Georgios Pan, Bitao Bogris, Adonis Baziana, Peristera Department of Informatics and Telecommunications University of Thessaly Greece State Key Lab of Information Photonics and Optical Communications Beijing University of Posts and Telecommunications China School of Electrical and Computer Engineering National Technical University of Athens Greece Department of Informatics and Computer Engineering University of West Attica Greece

In this paper, we introduce an all-optical metro network architecture, called MOON, to serve converged multi-granular traffic from fixed, mobile, and edge computing services. Since traffic is characterized by high dynamicity and diverse access requirements, MOON uses network slicing to provide quality of service (QoS) aware wavelength allocation to fulfill the various applications traffic demands. MOON incorporates hybrid optical switching (HOS) combining optical circuit switching (OCS) and optical time slotted switching (OTS) capabilities that appropriately maps different traffic types to them. Specifically, the OCS network slice explicitly serves aggregated traffic of long duration and high volume, while OTS network slice serves short bursty traffic. In order to provide flexibility, separate sets of wavelengths are used for OCS and OTS traffic service, both within a metro-access network (MAN) (intra-MAN) and between different MANs (inter-MAN). We extensively study the required number of wavelengths to efficiently serve OCS and OTS traffic for intra- and inter-MAN communication scenarios, taking into account their specific traffic access requirements in an effort to optimize wavelengths utilization. In our study, we assume non-blocking OCS communication for immediate access;therefore the number of required OCS wavelengths depends only on the number of nodes, while the number of required OTS wavelengths to obtain a desired QoS and latency level is independent from the number for OCS wavelengths. Simulation results show that within an OTS intra-MAN we achieve end-to-end (E2E) latency in sub-milliseconds scale, suitable for dynamic bursty traffic, while it is an decreasing function of the number of used OTS wavelengths. © 2025, CC BY.

关键词： Wimax

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Analysis for Temperature Classification using Bioelectric Potential of Plant

Machine Learning Analysis for Temperature Classification usi...

引用

International Conference on Information Technology, Information Systems and Electrical engineering (ICITISEE)

作者： Imam Tahyudin Hasri Akbar Awal Rozaq Hidetaka Nambo Department of Information System Faculty of Computer Science Amikom Purwokerto University Banyumas Indonesia Faculty of Computer Science Graduate School of Informatics Gazi University Yenimahalle Ankara Turkey Division of Electrical Engineering and Computer Science Graduate School of NST Kanazawa University Kakumamachi Kanazawa Ishikawa Japan

Plants can respond to changes in their surroundings, such as temperature, humidity, and human behavior. This ability is due to photosynthesis and respiration in plants, resulting in low electrical signals. We focus on room temperature change by plant bioelectric potential detection. The temperature topic is interesting for the actual research because it is one of important factor in health aspect. This study aims to analysis of temperature of Bioelectric potential of plant using machine learning. This implementation identifies the plants' bioelectric potential in distinguishing three-room temperature categories: A, B, and C temperature. We conducted the experimental in room control. For the transformation process is using wavelet transform. Furthermore, the analysis process, we used the Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighborhood (K-NN), Naïve Bayes, and linear regression. Then, for the evaluation is using confusion Matrix. The result showed that the best level of transformation using Wavelet is 7 th level for reducing the noise. Furthermore, the best accuracy of analysis process is using Decision tree which obtained 75%.

关键词： Wavelet transforms Support vector machines Radio frequency Temperature Linear regression Bioelectric phenomena Decision trees

来源：评论

学校读者我要写书评

暂无评论

Identifying Genes and Their Interactions from Pathway Figures and Text in Biomedical Articles

Identifying Genes and Their Interactions from Pathway Figure...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： He, Fei Thompson, Joshua Mao, Ziting Ren, Yijie Nussbaum, Yulia Kholod, Olha Shin, Dmitriy Hannink, Mark Popescu, Mihail Xu, Dong Northeast Normal University School of Information Science and Technology Changchun China University of Missouri Department of Electrical Engineering and Computer Science ColumbiaMO United States Institute for Data Science and Informatics University of Missouri ColumbiaMO United States University of Missouri Department of Pathology and Anatomical Sciences ColumbiaMO United States University of Missouri Department of Biochemistry ColumbiaMO United States University of Missouri Department of Health Management and Informatics ColumbiaMO United States

ISBN: (纸本)9781665401265

Many high-quality biological pathways are presented in figures and text in biomedical literature. They are great resources for studies of biological mechanisms and precision medicine practices. These pathways need to be carefully curated, reconciled, and transformed into a computable form. Current manual curation approaches are inadequate in keeping up with the pace of the literature growth. New bio-curation approaches are needed to streamline the identification of gene interactions from pathway figures and text. This paper proposes a pathway curation approach for identifying genes and their interactions using both figures and text of biomedical articles. Our method integrates deep learning-based object detection models with a Google optical character recognition service to extract genes and their interactions from pathway figures. Our pipeline was evaluated on the figures from PubMed publications with manual annotations. The results demonstrated that our model could effectively retrieve genes and their interactions in pathway figures. The proposed pipeline may accelerate various applications of the latest biomedical discoveries. We also developed a web server at http://*** to provide the gene interaction curation on uploaded pathway figures and corresponding articles. © 2021 IEEE.

关键词： Genes

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：