检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Zhong Hui An Di Liaoning Province Big Data Management and Analysisline Laboratory of Urban Construction School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

In order to realize intelligent processing of drawings in building construction, improve the accuracy of drawings and provide more security for construction personnel, this paper proposes a layout algorithm of all steel attached wall climbing frame walkway boards, which can read and process the building contour data. Based on the building contour data, the layout drawing of building peripheral climbing frame walkway boards can be generated by one click in Revit and the walkway board data can be obtained Read and process the recognized building contour in the database, analyze the coordinate change and summarize the law by using the processed data, and obtain the walkway board contour map, walkway board partition map and walkway board data. The implementation of this algorithm greatly improves the work efficiency of technicians and lays the foundation for the layout of other parts. It has great application value in the field of computer- aided building construction design.

关键词： Visualization databases Buildings Layout Partitioning algorithms C# languages Steel

来源：评论

学校读者我要写书评

暂无评论

Learning from Multi-Perception Features for Real-Word Image Super-resolution

arXiv

引用

arXiv 2023年

作者： Niu, Axi Zhang, Kang Pham, Trung X. Wang, Pei Sun, Jinqiu Kweon, In So Zhang, Yanning The School of Computer Science Northwestern Polytechnical University Xi’an710072 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710072 China The School of Electrical Engineering Korea Advanced Institute of Science and Technology Korea Republic of The School of Astronautics Northwestern Polytechnical University Xi’an710072 China

Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model’s learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures. © 2023, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Donut Modes in Space Wavelength Division Multiplexing: Multimode Optical Fiber Transmission based on Electrical Feedback Equalizer 5

Donut Modes in Space Wavelength Division Multiplexing: Multi...

引用

5th International Conference on Electronic Design, ICED 2020

作者： Ghazi, Alaan Aljunid, S.A. Idrus, Syed Zulkarnain Syed Endut, R. Ali, N. Amphawan, Angela Fareed, Alaa Al-Dawoodi, Aras Noori, Awab School of Human Development and Techno-communication University Malaysia Perlis Malaysia School of Computer and Communication Engineering University Malaysia Perlis Malaysia Computer Technical Engineering Al-Qalam University College Iraq Centre of Excellence Universiti Malaysia Perlis Malaysia Universiti Malaysia Perlis Perlis Malaysia Lightwave Laboratory School of Engineering and Technology Sunway University Petaling Jaya Selangor47500 Malaysia School of Computing University Utara Malaysia Malaysia Computer Science Department College of Computer Science and Information Technology Kirkuk University Iraq Data Science Research Lab School of Computing Universiti Utara Malaysia Malaysia

This study demonstrates the implementation of multi-input-multi-output (MIMO) transmission donut modes in space wavelength division multiplexing (SWDM) over multi-mode optical fiber (MMOF) and simulating the effect of mode coupling of the transmitted signal. However, during the data transmitted over MMF by using SWDM an issue is encountered, which is the inter symbol interference (ISI) due to mode coupling. ISI has been recognized as a major obstacle to high-speed data transmission. The signal processing in SDM of donut modes over MMOF with electrical feedback equalizer is used to improve the performance for increasing the bandwidth. A data rate 80 Gbit/s up for a distance of 1600 meters is achieved. SWDM topology was designed emitted from a spatial vertical cavity surface-emitting laser (VCSEL) through MMOF in conjunction with the configurations of electrical feedback equalizer. The parameters and values used in Opt-Sim simulation topology were listed. The performance measurement of this study based on bit-error rates (BER) and eye diagram before and after electrical feedback equalization were analysed. © 2021 Published under licence by IOP Publishing Ltd.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Routing Protocol Design to Perform Cost Efficient data Communication over Wireless Sensor Networks

An Enhanced Routing Protocol Design to Perform Cost Efficien...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Dattatraya Arun Jadhav Sajja Suneel M. Amina Begum Meghana Harsh Ghogare Madhan Sekhar Murri Parashuram Shankar Vadar Electronic and telecommunication department Keystone school of Engineering pune Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Department of ECE Oxford College of Engineering Venmani Tamilnadu India byteXL-Department of Computer Science and Engineering Parul University Vadodara Department of Management Studies Vignan’s Institute of Information Technology(A) AP India Yashwantrao Chavan School of Rural Development Shivaji University Kolhapur Maharashtra India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

This research introduces a groundbreaking approach to address the challenges of cost-efficient data communication in Wireless Sensor Networks (WSNs) through the development of a novel routing protocol named Cost-Efficient Enhanced Routing Protocol (CEERP). WSNs, characterized by resource-constrained sensor nodes and dynamic environmental conditions, necessitate innovative routing strategies to optimize energy consumption and enhance overall network performance. CEERP leverages a sophisticated methodology that integrates Energy Consumption Modeling, Adaptive Routing Decisions, alongside Optimization and Fine-Tuning. The Energy Consumption Modeling method systematically analyzes various factors influencing energy dynamics in sensor nodes, facilitating the creation of accurate mathematical models. These models inform CEERP’s routing algorithm, enabling intelligent decisions based on predicted energy consumption patterns. The protocol adapts dynamically to real-time variations in network conditions, ensuring responsiveness to changing environmental factors. Implementation and Simulation validate CEERP’s performance in diverse scenarios, while Optimization and Fine-Tuning finetune parameters for optimal efficiency. Security and reliability measures are integrated to safeguard data integrity. The research concludes with a comprehensive evaluation of CEERP’s effectiveness, positioning it as a promising solution for achieving cost-efficient and reliable data communication in WSNs. The proposed methodology and CEERP contribute to the advancement of routing protocols for WSNs, offering a holistic and adaptive approach to address the unique challenges posed by resource-constrained environments.

关键词： Wireless sensor networks Energy consumption Adaptation models Routing Routing protocols Mathematical models data communication

来源：评论

学校读者我要写书评

暂无评论

Fine-scale genetic structure of Tujia and central Han Chinese revealing massive genetic admixture under language borrowing

引用

植物分类学报 2021年第1期59卷 1-20页

作者： Guang-Lin He Ying-Xiang Li Meng-Ge Wang Xing Zou Hui-Yuan Yeh Xiao-Min Yang Zheng Wang Ren-Kuan Tang Su-Min Zhu Jian-Xin Guo Ting Luo Jing Zhao Jin Sun Zi-Yang Xia Hao-Liang Fan Rong Hu Lan-Hai Wei Gang Chen Yi-Ping Hou Chuan-Chao Wang Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Institute of Forensic Medicine West China School of Basic Science and Forensic Medicine Sichuan UniversityChengdu 610041China Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Institute of Forensic Medicine West China School of Basic Science and Forensic Medicine Sichuan UniversityChengdu 610041China Institute of Forensic Medicine West China School of Basic Science and Forensic Medicine Sichuan UniversityChengdu 610041China School of Humanities Nanyang Technological UniversityNanyang 639798Singapore Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Institute of Forensic Medicine West China School of Basic Science and Forensic Medicine Sichuan UniversityChengdu 610041China Department of Forensic Medicine College of Basic Medicine Chongqing Medical UniversityChongqing 400000China Department of Forensic Medicine College of Basic Medicine Chongqing Medical UniversityChongqing 400000China Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Department of Anthropology and Ethnology Institute of AnthropologyNational Institute for Data Science in Health and Medicineand School of Life SciencesXiamen UniversityXiamen 361005FujianChina Department of Anthropology and Ethnology In

Archaeological,genetic,and linguistic evidence has supported the idea that northern China is the original center of modern Sino-Tibetan-speaking ***,the demographic history of subsequent southward migration and genetic admixture of Han Chinese with surrounding indigenous populations remain uncharacterized,and the language shifts and assimilations accompanied by movement of people,or just an adaptation of cultural ideas among populations in central China is still unclear,especially for Tibeto-Burman-speaking Tujia and central Han Chinese *** resolve this,we genotyped over 60K genome-wide markers in 505 unrelated individuals from 63 indigenous *** results showed both studied Han and Tujia were at the intermediate position in the modern East Asian North-South genetic cline and there was a correlation between the genetic composition and the *** observed the strong genetic assimilation between Tujia people and central Han Chinese,which suggested massive population movements and genetic admixture under language *** and central Han Chinese could be modeled as a two-way admixture deriving primary ancestry from a northern ancestral population closely related to the ancient DevilsCave and present-day Tibetans and a southern ancestral population closely related to the present-day Tai-Kadai and Austronesian-speaking *** ancestral northern population we suspect to be related to the Neolithic millet farming groups in the Yellow River Basin or central *** showed that the newly genotyped populations in Hubei Province had a higher proportion of DevilsCave or modern Tungusic/Mongolic-related northern ancestries,while the Hunan populations harbored a higher proportion of Austronesian/Tai-Kadai-related southern ancestries.

关键词： demographic history gene flow genetic admixture language borrowing Tibeto-Burman Tujia

来源：评论

学校读者我要写书评

暂无评论

Correction:Noise-Filtering Enhanced Deep Cognitive Diagnosis Model for Latent Skill Discovering

引用

Intelligent Automation & Soft Computing 2024年第5期39卷 985-986页

作者： Jing Geng Huali Yang Shengze Hu National Engineering Research Center of Educational Big Data Central China Normal UniversityWuhan430079China Faculty of Artificial Intelligence in Education Central China Normal UniversityWuhan430079China School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan430079China

In the article“Noise-Filtering Enhanced Deep Cognitive Diagnosis Model for Latent Skill Discovering”by Jing Geng,Huali Yang and Shengze Hu(Intelligent Automation&Soft Computing,2023,Vol.37,No.2,***:10.32604/iasc.2023.038481),the References[1-2],[4-12],and[23-29]were not appropriately aligned with the context of the main text.

关键词： Deep Automation app

来源：评论

学校读者我要写书评

暂无评论

Integration of Vision and Language in Multi-Mode Video Converters (Partially) Aligns with the Brain

Integration of Vision and Language in Multi-Mode Video Conve...

引用

International Conference on Computational and Characterization Techniques in engineering & sciences (CCTES)

作者： Babhuti Kashyap P. Aswini Vijilius Helena Raj Khobragade Pithamber Rajeev Sobti Z. Salman Department of Psychology School of Liberal Arts(SLS) CMR University Bengaluru India Department of Computer Science and Engineering( Data Science) Institute of Aeronautical Engineering Hyderabad India Department of Applied Sciences New Horizon College of Engineering Bangalore India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India Lovely Professional University Phagwara India Hilla University College Babylon Iraq

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

One of the most important requirements for providing AI systems with a foundation, in reality, is the integration of data from many modalities is yet unclear how successfully these models include modalities, even though there has been some progress in the development of video transformers that can learn by watching the video, reading text, and listening to audio over time. Here, the researcher provides an encouraging method for testing a multimodal video transformer model that has already been trained, using findings from neuroscience that show how the brain processes information in a multimodal fashion. By utilising brain recordings of individuals who were viewing a well-known television show, researchers investigate the influence that multi-modal connections and interactions have on the alignment of multi-modal and uni-modal brain regions in multi-modal video transformers that have previously been well-trained. Evidence suggests that visual processing improves masked prediction ability in linguistic processing; this lends credence to the idea that models including representations from many modalities might have a positive impact on each one. Despite this, researchers have not discovered any evidence that the combined multi-modal transformer representations collect any more brain-relevant information beyond what is already recorded by each modality. Show, last, that a task requiring vision-language inferences may be used for fine-tuning to enhance the brain alignments of the already trained joint representation. These results suggest that multi-modal transformers can integrate vision and language in ways that are somewhat relevant to the brain, which is encouraging. However, also found that additional techniques may be needed to improve the brain alignment of these models.

关键词： Visualization TV Neuroscience Predictive models Linguistics Transformers Brain modeling data models Recording Testing

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Few-Shot Learning with Second-Order Neural Ordinary Differential Equations 39

Cross-Modal Few-Shot Learning with Second-Order Neural Ordin...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yi Cheng, Chun-Wun He, Junyi He, Zhihai Schönlieb, Carola-Bibiane Chen, Yuyan Aviles-Rivero, Angelica I. Harbin Institute of Technology China Department of Electrical and Electronic Engineering Southern University of Science and Technology China Department of Applied Mathematics and Theoretical Physics University of Cambridge United Kingdom Pengcheng Laboratory China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Yau Mathematical Sciences Center Tsinghua University China

ISBN: (纸本)157735897X

We introduce SONO, a novel method leveraging Second-Order Neural Ordinary Differential Equations (Second-Order NODEs) to enhance cross-modal few-shot learning. By employing a simple yet effective architecture consisting of a Second-Order NODEs model paired with a cross-modal classifier, SONO addresses the significant challenge of overfitting, which is common in few-shot scenarios due to limited training examples. Our second-order approach can approximate a broader class of functions, enhancing the model's expressive power and feature generalization capabilities. We initialize our cross-modal classifier with text embeddings derived from class-relevant prompts, streamlining training efficiency by avoiding the need for frequent text encoder processing. Additionally, we utilize text-based image augmentation, exploiting CLIP's robust image-text correlation to enrich training data significantly. Extensive experiments across multiple datasets demonstrate that SONO outperforms existing state-of-the-art methods in few-shot learning performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Residual Networks Based Framework for Early Alzheimer’s Disease Classification and Diagnosis 6th

An Enhanced Residual Networks Based Framework for Early Alzh...

引用

6th International Conference on Communication, Devices and Networking, ICCDN 2022

作者： Awotunde, Joseph Bamidele Sur, Nath Samarendra Imoize, Agbotiname Lucky Misra, Sanjay Gaber, Tarek Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electronics and Communication Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University East Sikkim Rangpo Majitar737136 India Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria Department of Electrical Engineering and Information Technology Institute of Digital Communication Ruhr University Bochum44801 Germany Department of Applied Data Science Institute of Energy Technology Halden Norway Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt School of Science Engineering and Environment University of Salford ManchesterM5 4WT United Kingdom

ISBN: (纸本)9789819919826

Alzheimer's disease (AD) is a long-lasting, degenerative brain illness for which there is now no successful treatment. However, there are medications that can delay its growth and stop its tracks. Therefore, stopping and regulating the progression of AD depends greatly on its early diagnosis. computer-aided diagnosis (CAD) in health care has become more and more dependent on deep learning technologies. This has help in early diagnosis and detection of various disease in health care. New techniques for the early diagnosis of neurocognitive abnormalities are now possible thanks to advancements in medical imaging and computational capacity in an effort to stop or slow down cognitive aging. Therefore, this study proposes a residual network (ResNet) type 50 for early diagnosis of AD. Convolutional neural networks (CNNs) are first used in the study for features extraction and then make the ultimate diagnosis using the ResNet-50. To create a better architecture, the problem of AD diagnosis will be addressed by utilizing and incorporating ResNet-50, which improves the current categorization problem's accuracy to its maximum. With a 98.8% accuracy rate, the proposed model using ResNet-50 produces encouraging findings for AD prediction. The study reveals that the model can effectively circumvent CNNs for the diagnostic issue with AD. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach for ovarian cysts detection and classification (OCD-FCNN) using fuzzy convolutional neural network

引用

Measurement: Sensors 2023年 27卷

作者： Ravishankar, T. Nadana Makarand Jadhav, Hemlata Satheesh Kumar, N. Ambala, Srinivas Pillai N, Muthuvairavan Department of Data Science and Business Systems School of Computing SRM Institute of Science & Technology KTR Tamil Nadu Chennai India Department of E & T C Marathwada Mitra Mandal's College of Engineering Pune India Department of Electronics and Communication Engineering PBR Visvodaya Institute of Technology and Science Kavali Andhra Pradesh 524201 India Computer Engineering Department Pimpri Chinchwad College of Engineering Sector -26 Pradhikaran Nigdi Maharashtra Pune411 044 India Department of Computer Science and Business Systems R.M.D Engineering College Kavarapettai India

Most women generally have an ovarian cyst, causing the disorder. Pregnant cysts occur when many water-packed tumors appear in the womb. This is especially true for women who have a worthy cause for childbearing. Women are related to menstrual problems and cyst problems during pregnancy. Recently, ultrasound imaging and machine learning techniques have been used to detect ovarian cysts. Different domain experts provide their own decisions on finding out what kind of ovarian cyst it is from ultrasound images. However, a most accurate and uniform decision-making system is necessary for the early detection of cysts. To aid physicians, an automated detection system has been proposed in this paper to make it more effective for physicians to eliminate these problems. This system uses the extracted features from the image for cysts detection and classification. Automatic ovary cyst detection (OCD) and classification are implemented in this work using a fuzzy rule-based Convolutional Neural Network (FCNN). The proposed system (OCD-FCNN) has yielded 98.37% accurate results when tested with benchmark datasets. © 2023 The Authors

关键词： Fuzzy inference

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：