检索结果-内蒙古大学图书馆

5th International Conference on Advancements in Computing, ICAC 2023

作者： Nirasha Jayasiri, K.C. Chandrasiri, Sanjeevi Rupasinghe, Shalini Karunanayake, K.O. Rivindu Uthayachandran, Abineshh Zihara, M.I. Fathima Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Sri Lanka

ISBN: (纸本)9798350358131

Tomato is one of the most popular crops worldwide. The success of a tomato crop is highly dependent on the health of the plants. Nutrient deficiency surveillance is typically conducted through visual inspections, which can be challenging for inexperienced farmers and home gardeners to work accurately. There is a growing need for a quick, reliable, and accurate nutrient deficiency identification system to address this issue. The proposed method is based on image processing and deep learning technologies that are highly effective for image classification tasks. Two models were trained using a dataset collected from tomato plants in Sri Lanka and evaluated using Mask Region-based Convolutional Neural Network (Mask R-CNN) and, You Only Look Once (YOLO) for deficiency classification, and results obtained 92% and 98% accuracy, respectively. Deficiency dispersion level expressed as a percentage using Mask R-CNN and followed by image processing techniques. Overall, this proposed system offers a convenient and accessible tool for farmers and home gardeners to monitor and maintain the health of their tomato plants, enabling them to achieve optimal yields and ensure profitable returns. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Integrated Approach to Enhance Legal information Retrieval of Sri Lankan Supreme Court Verdicts 5

An Integrated Approach to Enhance Legal Information Retrieva...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Jayasooriya, Asel Ahamed, Akeel Bandara, Yomal Gavindya, Chamod Kasthurirathna, Dharshana Abeywardhana, Lakmini Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept.of Computer Science & Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

Legal professionals and law students often grapple with the arduous task of locating prior Supreme Court rulings for argument preparation and academic study, leading to a laborious and resource-intensive process. This study introduces an innovative approach to streamline the retrieval of legal information from Sri Lankan Supreme Court verdicts. The method centers on developing a Custom Named Entity Recognition (NER) model, boasting a remarkable accuracy exceeding 90%. This model efficiently extracts crucial legal entities from Supreme Court rulings, readily available on the Ministry of Justice's Supreme Court website. The high accuracy ensures precise entity extraction, followed by systematic organization within a dedicated database. Subsequently, a knowledge graph is formed by linking recorded legal entities, reducing information retrieval time to a mere 179 milliseconds, significantly outperforming existing methods. Moreover, a BART summarization model is crafted to generate concise, accurate, and insightful summaries of Supreme Court decisions, boasting an impressive ROGUE1 score of 85%. This approach revolutionizes legal information retrieval, delivering a user-friendly platform that enhances the identification of cases and fosters a deeper understanding, ultimately elevating the quality of legal research and practice. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

RSChat:Intelligent Question Answering Model for Railway Safety Knowledge 24

RSChat:Intelligent Question Answering Model for Railway Safe...

引用

24th IEEE/ACIS International Conference on Computer and information Science, ICIS 2024

作者： Li, Jinyu Li, Chao Niu, Sen Dai, Bingrong School of Computer and Information Engineering Shanghai Polytechnic University Shanghai China Shanghai Development Center of Computer Software Technology Shanghai China

ISBN: (纸本)9798350376647

The release of ChatGPT heralds a new era in artificial intelligence, as large language models (LLMs) empower myriad industries. This paper introduces RSChat, a model based on supervised fine-tuning of multiple large language models (LLMs), exploring a novel paradigm for applying knowledge in railway safety. Initially, we perform prompt engineering using collected domain data, including key information extraction and knowledge expansion. Subsequently, leveraging the constructed fine-tuning datasets, we conduct supervised fine-tuning using multiple large language models (LLMs) as base models. Finally, experimental evaluations demonstrate that RSChat can generate more professional responses in the railway safety domain, exhibiting robust potential for application. © 2024 IEEE.

关键词： Railroad accidents

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Method for Statistical Downscaling of CLDAS Relative Humidity with Different Sources of Data:Sensitivity Analysis

引用

Journal of Meteorological Research 2023年第6期37卷 878-895页

作者： Bin BAI Chunxiang SHI Ling YANG Lingling GE Luhui YUE Guangyu LIU College of Electronic Engineering Chengdu University of Information TechnologyChengdu610225China Key Laboratory of Atmospheric Sounding of China Meteorological Administration Chengdu610225China National Meteorological Information Centre China Meteorological AdministrationBeijing100081China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China

High-resolution relative humidity(RH)data are essential in studies of climate change and in numerical meteorological ***,because high-resolution meteorological grid data require a large number of stations,the sparse distribution of ground meteorological stations in China before 2008 has limited the development of long-term and high-resolution RH products in the China Meteorological Administration’s Land Assimilation System(CLDAS)*** retrieve high-quality and high-resolution RH data before 2008,we propose a statistical downscaling model(SDM)based on a generative adversarial network(GAN)to transform the original RH data from a resolution of0.05°to 0.01°.The GAN-based SDM(GSDM)is trained with the RH of the CLDAS(0.05°)dataset after 2008 as its input,and the RH of the high-resolution CLDAS(HRCLDAS,0.01°)dataset after 2008 as its target for ***2-m air temperature data from the HRCLDAS dataset are also included in the input,and the station observations of RH are incorporated in the target for *** select the optimum data combination for the model,we compared three methods:(1)incorporating without auxiliary data(GSDM),(2)incorporating air temperature as an additional input(GSDM_T),and(3)incorporating air temperature as an additional input and the RH data at stations as an additional target for training(GSDM_TO).Taking the Beijing–Tianjin–Hebei region as an example,we trained the GSDM by using data from 2018 and tested the model performance in *** experimental results showed that the GSDM_TO algorithm achieved the lowest root-mean-square error(3.85%),followed by the GSDM_T(4.01%)and GSDM(4.95%)*** proposed models showed a competitive performance and captured more local details of the RH fields than other deep learning models and traditional bilinear *** general,the GSDM_TO algorithm using a combination of different sources of data(air temperature and observed RH)achieved the best results among the various d

关键词： relative humidity statistical downscaling generative adversarial network(GAN) temperature

来源：评论

学校读者我要写书评

暂无评论

YOLOv5s-FSDA: Fire and Smoke Detection Algorithm Based on Improved YOLOv5s

YOLOv5s-FSDA: Fire and Smoke Detection Algorithm Based on Im...

引用

2024 International Symposium on Digital Home, ISDH 2024

作者： Li, Yuhua Xu, Yanru Zhang, Mengyue Sheng, Jianqiang Software Engineering College Zhengzhou University of Light Industry Zhengzhou450001 China Shenzhen Institute of Information Technology Shenzhen518172 China

ISBN: (纸本)9798331509873

Fire and smoke detection are critical to reducing fire losses. Edge devices with limited resources require a model that is more lightweight while still maintaining the detection accuracy necessary for fire and smoke detection tasks. To solve these problems, this paper proposes a fire and smoke detection algorithm based on YOLOvSs, named YOLOvSsFSDA. Firstly, we incorporate the Cross-scale Feature Fusion (CFF) structure, enhancing the recognition and representation capabilities of features across different scales. Secondly, to further reduce the model burden, we adopt Ghost Convolution (GhostConv) technology to reduce model parameter count and computational load. Thirdly, to enhance the model's overall grasp of fire and smoke areas, we integrate the Content-Aware ReAssembly of Features (CARAFE) upsampling method. In addition, we introduce the Similarity Intersection over Union (SIoU) loss function to reduce the positioning error between the prediction and actual boxes, ensuring that fire and smoke targets of different scales can be located more accurately. Experimental results show that the YOLOvSs-FSDA algorithm, while maintaining the high detection accuracy of YOLOvSs, reduces model complexity by 30% and computational costs by 18%. © 2024 IEEE.

关键词： Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

Research and Applications of Large Language Models for Converting Unstructured Data into Structured Data 3

Research and Applications of Large Language Models for Conve...

引用

3rd International Conference on Cloud Computing, Big Data Application and software engineering, CBASE 2024

作者： Liu, Xiangfeng Sun, Jianting Lei, Aidi Zhu, Junzhi Co. Ltd Chengdu610073 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798331506582

The rapid growth of data has led to a significant increase in unstructured data, such as text, audio, and images, which dominate modern information processing. However, the complexity of unstructured data presents challenges for automated analysis and processing. Converting unstructured data into structured formats is crucial for tasks like data mining, information extraction, and knowledge graph construction. Traditional methods that rely on manual rules or statistical models struggle with complex, context-dependent data. Recently, large language models (LLMs), such as GPT-4 and BERT, have demonstrated great potential in unstructured data processing due to their powerful natural language understanding and generation capabilities. This study explores the application of large language models in transforming unstructured data into structured formats. It begins by reviewing the limitations of traditional approaches and then presents a framework for unstructured data processing using LLMs, covering data preprocessing, information extraction, and structured representation. The study's experiments demonstrate the superior performance of LLMs in handling various types of unstructured data, particularly in tasks like named entity recognition, relation extraction, and contextual understanding. The results show that LLMs achieve higher accuracy and generalization while reducing reliance on manual rules. The paper discusses the strengths and limitations of this method, proposing future improvements, such as combining domain-specific knowledge for model optimization and expanding applications to multimodal data processing. The research highlights the promising role of large language models in converting unstructured data into structured formats. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Semantic Segmentation in Remote Sensing Images Using Active Learning and Deep Global Second Order Pooling Network 20

Semi-Supervised Semantic Segmentation in Remote Sensing Imag...

引用

20th International Computer Conference on Wavelet Active Media technology and information Processing, ICCWAMTIP 2023

作者： Sarpong, Kwabena Qin, Zhinguang Addo, Daniel Patamia, Rutherford Agbesi Ekong, Favour Khamis, Asha Mzee School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China

ISBN: (纸本)9798350318982

Training convolutional neural networks (CNNs) for semi-semantic segmentation in remote sensing images is difficult due to the substantial amount of labelled data required. The scarcity of dense pixel-level annotations hampers the model's ability to extract meaningful information from the images. We propose a novel semi-supervised semantic segmentation network called 3S-Net, designed explicitly for high-resolution remote sensing imagery to overcome this challenge. This network leverages a limited number of labelled examples and many unlabeled examples to generate pseudo-labels, expanding the labelled training set. The Deep Global Second-Order Pooling Network (DG2oPN) is employed to learn discriminative and representative features from the entire image information throughout the network. Our approach involves two main steps: First, an active learning-based sampling strategy is utilized to select a representative set of labelled data. Secondly, we introduce the 3S-Net, which learns from limited annotated data and effectively leverages unlabeled images by utilizing the second-order statistics of the entire image. Experimental results on two public remote sensing datasets demonstrate that our semi-supervised semantic model efficiently and effectively addresses the issue of limited labelled samples, outperforming other state-of-the-art methods. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Accessibility Evaluation Of Five Moroccan E-government Portals 33

Accessibility Evaluation Of Five Moroccan E-government Porta...

引用

Joint of the 33rd International Workshop on software Measurement and the 18th International Conference on software Process and Product Measurement, IWSM-MENSURA 2024

作者： Ouaziz, Mohammed Rida Cheikhi, Laila Idri, Ali Abran, Alain Software Project Management Team ENSIAS Mohammed V University in Rabat Morocco Department of Software Engineering Information Technology École de Technologie Supérieure Montréal Canada

In the present era, e-government portals are viewed as an effective means of providing online services to citizens. It is imperative for everyone to guarantee equitable access to these services, irrespective of their abilities or limitations. Hence, accessibility is vital for those with disabilities and advantageous for everyone. Web Content Accessibility Guidelines (WCAG) provide a comprehensive set of guidelines, in terms of success criteria, that are widely utilized in various tools to assess the accessibility of websites or portals. By following these guidelines, developers can ensure that their websites are accessible to everyone. This paper reports on a study of the accessibility evaluation of five Moroccan e-government portals using the AChecker tool with respect to WCAG. The aim was to prepare recommendations to improve the overall user experience across Moroccan e-government portals. The evaluation results analysis showed that the portals have some common as well as different failed success criteria with different numbers of errors per WCAG principle and conformance level. In particular, all the portals exhibited varying degrees of adherence to the four principles, and most of the portals struggled to meet levels A and AA, and none of them achieve perfect conformance across all levels. To address this issue, a set of recommendations is provided for each portal to enhance accessibility. The lessons learned from this study can contribute to more inclusive e-government portals and provide insights for governments and designers to prioritize accessibility enhancements. © 2024 Copyright for this paper by its authors.

关键词： Portals

来源：评论

学校读者我要写书评

暂无评论

CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer for Downstream Vision Tasks Under Unknown Degradations

CPA-Enhancer: Chain-of-Thought Prompted Adaptive Enhancer fo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Yuwei Wu, Yan Liu, Yanming Peng, Xinyue College of Electronic and Information Engineering Tongji University Shanghai China School of Software Technology Zhejiang University Hangzhou China College of Electronic and Information Engineering Southeast University Nanjing China

ISBN: (纸本)9798350368741

Extracting valuable visual cues for downstream vision tasks poses a particular challenge under unknown degradations. A straightforward solution is to preprocess images using image restoration methods, but their high computational complexity renders them unsuitable for real-time tasks. Recent efforts have aimed to enhance image representations optimized by downstream task losses. However, these approaches are confined to known single degradation scenarios, constraining their practical applicability in unpredictable environments. Therefore, we propose a Chain-of-thought Prompted Adaptive Enhancer, CPA-Enhancer, for enhancing important features crucial for downstream vision tasks under unknown degradations. Specifically, CPA-Enhancer progressively adapts its enhancement strategies under the step-by-step guidance of CoT prompts that encode degradation-related information. Overall, CPA-Enhancer is a plug-and-play lightweight enhancement model that can be integrated into any vision pipeline and trained with task-related losses, without any prior knowledge of the degradation type. Extensive experiments demonstrate that CPA-Enhancer significantly improves performance across various vision tasks under unknown degradations. The codes is available at https://***/zyw-stu/CPA-Enhancer. © 2025 IEEE.

关键词： adaptive enhancer chain-of-thought prompting unknown degradations

来源：评论

学校读者我要写书评

暂无评论

LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

引用

Computers, Materials & Continua 2023年第4期75卷 1-17页

作者： Xiaorui Zhang Rui Jiang Wei Sun Aiguo Song Xindong Wei Ruohan Meng Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Instrument Science and Engineering Southeast UniversityNanjing211189China School of Teacher Education Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

Robust watermarking requires finding invariant features under multiple attacks to ensure correct *** learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread *** existing methods use 3×3 small kernel convolution to extract image features and embed the ***,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the *** address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss *** uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel ***,the modification of the embedded watermarking on the cover image is extended to more *** the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight ***,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image *** experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise.

关键词： Robust watermarking large kernel convolution adaptive loss weights high-frequency wavelet loss deep learning

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：