检索结果-内蒙古大学图书馆

Ensuring Data Integrity in multi-Tenant Cloud Environments Through Advanced Testing 1

Ensuring Data Integrity in Multi-Tenant Cloud Environments T...

1st international conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Gali, Vinay Kumar Chauhan, Sansar Singh Gupta, Gopal Kumar Bulani, Padmini Rajendra Ravalji, Vardhansinh Yogendrasinnh Jayaraman, Kumaresan Durvas Nagarjuna University Andhra Pradesh Guntur522510 India G.L. Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida201306 India Nagpur Campus Pune440008 India Institute of Chartered Accountants of India India Northeastern University BostonMA United States Bharathidasan University Tamil Nadu Tiruchirappalli India

ISBN: (纸本)9798331518578

fortunately, multi-tenant cloud environments offer a more cost-effective provisioning model that consumes infrastructure to store and access data. As the volume of sensitive data processed and stored in the cloud continues to grow, ensuring data integrity has become a top concern for organizations. Data integrity is the information that is correct, consistent, and reliable is stored in the cloud. To address this issue, we also present a solution that allows us to maintain integrity in a multi-tenant cloud environment using advanced testing. The standard approach to testing (functional and performance testing) does not identify and will enable us to prevent data integrity problems. That's because these approaches describe the system's functionality and performance rather than the accuracy of the system's data. They proposed a solution that used techniques like anomaly detection, data profiling, and data quality checks to discover possible integrity issues in the dataset. The new techniques work within the testing process, while all data is assessed for integrity before being stored in the cloud. © 2025 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Road Defect Detection Model Based on YOLOv8

IAENG International Journal of Computer Science

引用

IAENG international Journal of computer science 2025年第4期52卷 986-994页

作者： Cong, Shengqiang Zhang, Chunna Yu, Yang Yue, Xiaoping Zhao, Jinchi Shen, Yuming School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China University of Science and Technology Liaoning Liaoning Anshan114051 China

The detection of road defects is crucial for ensuring vehicular safety and facilitating the prompt repair of roadway imperfections. Existing YOLOv8-based models face the following issues: extraction capabilities and insufficient feature representation in complex scenarios, slow bounding box regression speed. To address these challenges, we propose the YOLOv8-DSW model. Firstly, we incorporate the Dilation-wise Residual (DWR) module into the C2f module in the neck, improving the detection performance of multi-scale feature maps. Secondly, We incorporate the SENetv2 attention mechanism into the neck of the YOLOv8 model to augment feature expression capabilities. Finally, we introduce Wise-IoU (WIoU) to enhance the speed of bounding box regression. Experimental results indicate that YOLOv8-DSW enhances the mean Average Precision at 50% (mAP50) by 2.5% in comparison to the YOLOv8n, significantly improving detection accuracy and provide valuable method for the development of road defect detection. © (2025.0), (international Association of Engineers). All Rights Reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating urban scene understanding for autonomous vehicles with multi-GPU training of Semantic Segmentation 5

Accelerating urban scene understanding for autonomous vehicl...

引用

5th international conference on Smart Electronics and Communication, ICOSEC 2024

作者： Jayasimhan, Anusha Pabitha, P. Sri Sivasubramaniya Nadar College of Engineering Department of Computer Science and Engineering Chennai India Anna University Mit Campus Department of Computer Technology Chennai India

ISBN: (纸本)9798331504403

An important challenge in the field of computer vision revolves around semantic segmentation, which involves the partitioning of an image into distinct semantic regions or objects. This paper introduces a semantic segmentation model utilizing the well-regarded Cityscapes dataset for urban scene comprehension, coupled with the UNet architecture. Additionally, a PyTorch-based approach is developed to facilitate efficient training of the model on multiple GPUs within a single node. The UNet architecture comprises an encoder and a decoder pathway, responsible for feature extraction and subsequent upsampling, respectively. Customized for the Cityscapes dataset, the architecture employs a combination of convolutional and pooling layers to adeptly capture both global and local contextual details. To streamline the training process of the proposed model, a PyTorch-based strategy for single node multi-GPU distributed data training is outlined. This strategy utilizes the *** module, permitting the model to be trained on multiple GPUs within a single node. The proposed single node multi-GPU distributed data training technique not only accelerates the training process but also enhances efficiency. In comparison to a single GPU setup, it demonstrates the potential to cut down training time by as much as 50%. This advancement paves the way for more rapid and effective training of complex models, contributing to the advancement of semantic segmentation tasks in computer vision. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A computer Vision Framework for Enhanced Object Detection Using ConvNeXt-YOLO Architecture with multi-Scale Signal Processing 7

A Computer Vision Framework for Enhanced Object Detection Us...

引用

7th international conference on Automation Electronics and Electrical engineering

作者： Jiang, Bojun Lin, Zekai Li, Zhuoyuan Jia, Ce Lu, Haiyang Northeastern Univ Shenyang Peoples R China Liaoning Tech Univ Coll Min Fuxin Peoples R China Liaoning Geol Engn Vocat Coll Dandong Peoples R China

ISBN: (纸本)9798350377040;9798350377033

We propose a comprehensive computer vision framework that integrates multi-scale signal processing with an enhanced ConvNeXt-YOLO architecture for robust object detection. Our framework addresses three critical challenges in visual recognition: multi-scale feature representation, signal quality enhancement, and model generalization. The framework implements a sophisticated signal processing pipeline for image preprocessing. Initially, we develop an adaptive resolution normalization algorithm that maintains consistent feature quality across varying input dimensions. Subsequently, we design a context-aware Gaussian filtering mechanism that optimizes the signal-to-noise ratio while preserving essential feature characteristics. These preprocessing techniques significantly enhance the framework's capability to extract discriminative features and maintain computational stability. To optimize the learning process, we introduce a systematic data augmentation strategy incorporating both geometric and signal-level transformations. Our approach combines predetermined rotation sampling (90 degrees, 180 degrees, 270 degrees) with continuous-space ROI augmentation during inference. This hybrid strategy enables the framework to achieve rotation invariance and enhanced generalization capabilities, particularly beneficial for complex object detection scenarios. The core innovation lies in our architectural integration of ConvNeXt with YOLO. We redesign the feature extraction backbone using hierarchical ConvNeXt blocks, enabling efficient multi-scale feature learning. The cross-branch information fusion mechanism, coupled with our signal-aware design, substantially improves the model's representational capacity. Experimental results on standard computer vision benchmarks demonstrate superior performance, achieving state-of-the-art accuracy (improvement of X%) and recall rates (improvement of Y%) compared to conventional approaches.

关键词： computer Vision Framework multi-scale Signal Processing Deep Learning Architecture ConvNeXt-YOLO Integration Feature Fusion Advanced Object Detection Semi-supervised Learning Object Summary

来源：评论

学校读者我要写书评

暂无评论

Research on Large Scene Adaptive Feature Extraction based on Deep Learning 24

Research on Large Scene Adaptive Feature Extraction based on...

引用

2024 7th international conference on computer Information science and Artificial Intelligence, CISAI 2024

作者： Yang, Yahe Li, Iris Sang, Ningjing Liu, Lipeng Tang, Xirui Tian, Qiyuan School of Business George Washington University Washington United States Courant Institute of Mathematical Sciences New York University New York United States The Fu Foundation School of Engineering and Applied Science Columbia University New York United States College of Engineering Peking University Beijing China College of Computer Sciences Northeastern University Boston United States George Washington University Washington United States

ISBN: (纸本)9798400707254

The proliferation of intelligent monitoring devices has led to the widespread adoption of background extraction technology across a multitude of domains, including intelligent transportation, video surveillance, human-computer interaction, and medical diagnosis. In this work, the model employs a multi-layer convolutional neural network structure, which enables the extraction and fusion of scene features from different scales in a layer-by-layer manner. This approach facilitates the comprehensive capture of complex scene information. The convolutional network comprises multiple layers, with each layer responsible for extracting features at a specific scale. The shallower layers capture more detailed feature information, whereas the deeper layers focus on more global scene features. The strategy of multi-scale feature fusion allows the model to fully capture multi-level and multi-dimensional information in the context of large-scale scenes. Furthermore, the incorporation of an attention mechanism enables the model to adaptively allocate attention to salient regions, thereby enhancing its capacity to discern intricate scenes by assigning greater significance to pivotal features. The experimental results demonstrate that the proposed method is effective in practice, as evidenced by its performance on public datasets. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An NLP-Based Approach for Detecting Ambiguity of Thai Software Requirements Specification 21

An NLP-Based Approach for Detecting Ambiguity of Thai Softwa...

引用

21st international Joint conference on computer science and Software engineering (JCSSE)

作者： Intana, Adisak Laosen, Kanjana Nuanchan, Panya Pattanakit, Nattapong Dermchai, Sathani Prince Songkla Univ Coll Comp Phuket Thailand

ISBN: (纸本)9798350381771;9798350381764

Writing software requirements in the form of natural language especially Thai language is very challenging. If software engineers do not have good writing skills, this may cause the ambiguity resulting in misunderstanding and misinterpretation during the development. To prevent this occurrence, this paper presents an NLP-based approach for detecting ambiguity of Thai software requirements. This approach influences an initiative fundamental of ambiguity detection mechanism at lexical level. The words potentially causing the ambiguity in software requirements are detected and classified into the ambiguity type. The contribution of the approach is demonstrated with the development of a prototype tool, Software Requirement Ambiguity Detector (SRAD). The validation and evaluation results with real software requirements from the various system domains with the practical expert perspective confirm the benefits of the proposed approach and developed tool. In the future, our tool and model will be integrated to our redesigned approach for writing Thai software requirements specification.

关键词： natural language requirement requirement engineering software requirements specifications ambiguity ambiguous software requirements natural language processing ambiguity detection

来源：评论

学校读者我要写书评

暂无评论

KIE-STCformer: Key Information Enhanced Spatio-Temporal Correction Transformer for Time Series Forecasting 24

KIE-STCformer: Key Information Enhanced Spatio-Temporal Corr...

引用

8th international conference on computer science and Artificial Intelligence, CSAI 2024

作者： Cui, Shuolin Liu, Penglan Shi, Haoyuan Meng, Xiangfu School of Computer Science University of Glasgow Glasgow United Kingdom Hongkong Baptist University United International College Beijing Normal University Zhuhai China School of Electronic and Information Engineering Liaoning Techinaical University LiaoNing HuLudao China

ISBN: (纸本)9798400718182

Many existing time series forecasting models primarily rely on past time series points to directly forecast future multi-step sequences. However, two key problems are confronted with the existing approaches. First, within the fixed input space of size N, the initial N sequence data points may include redundant information. Second, the direct multi-step forecasting strategy often overlooks the temporal dependencies between consecutive forecasting steps. To address these issues, we propose an enhanced Transformer-based model named KIE-STCformer, designed to tackle input redundancy and weak temporal-spatial correlations in multi-step forecasting. First, we introduce a novel input data selection strategy to filter out redundant information, ensuring the input samples contain more relevant and key predictive signals. Second, an external attention mechanism that captures inter-sample correlations across different time points is integrated into the model, enabling it to leverage external relationships that significantly impact forecasting outcomes. To mitigate the weak spatial-temporal correlations typically observed in forecasted sequences, a spatial correction network with a mask matrix is designed, and a temporal correction network embedded with an agent attention mechanism is constructed. Extensive experiments are conducted on six widely-used benchmark datasets and the experimental results demonstrate that KIE-STCformer achieves superior accuracy compared to other transformer-based models. © 2024 Copyright held by the owner/author(s).

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

EJ-TransUNet: Fusion of convolutional and multiscale transUNet abdominal multiorgan segmentation networks 5

EJ-TransUNet: Fusion of convolutional and multiscale transUN...

引用

5th international conference on computer Vision and Data Mining, ICCVDM 2024

作者： Zhang, Dan School of Information Science and Engineering Shenyang Ligong University Liaoning Shenyang China

ISBN: (纸本)9781510682863

In computer-aided diagnosis, abdominal multi-organ segmentation is essential, and it has significant research implications. However, the ambiguous boundaries, complex backgrounds, and variable shapes and sizes of abdominal multi-organs make this task extremely challenging. To this goal, an abdominal multi-organ segmentation network called EJ-TransUNet—a fused convolutional and multi-scale TransUNet network—is proposed. Three components make up the network: a jump connection, a decoder, and an encoder. Regarding the input picture, firstly, a global local enhancement module (DCE) is designed in the hybrid encoder CNN-Transformer module, and the hollow convolution is introduced in the last layer of the Transformer module, which enhances the extraction of global local contextual information, so that the model strengthens the local correlation of the features while establishing the long-distance dependency;secondly, a jump connection stage is designed in the multi-scale fusion module MSC, which utilizes the CBAM attention mechanism module to capture the correlation between features at different levels and focus on features at different spatial locations to improve the accuracy of target localization;and finally in the decoder output image. Using the Synapse dataset, the model's performance is assessed, yielding an average Dice Similarity Coefficient (DSC) of 80.34%. The experimental findings demonstrate that the suggested approach performs better overall than multiple comparison networks and yields superior segmentation outcomes for organs with varying sizes and shapes. © 2024 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on multi-Beam Line Layout Model Based on Greedy Algorithm and Particle Swarm Optimization Algorithm 2

Research on Multi-Beam Line Layout Model Based on Greedy Alg...

引用

2nd IEEE international conference on Sensors, Electronics and computer engineering, ICSECE 2024

作者： Xu, Hanbo Wang, Binghang Cui, Jingwen Yang, Liu School of Physics Jilin University Changchun China School of Computer Science and Technology Jilin University Changchun China School of Mathematics Jilin University Changchun China

ISBN: (纸本)9798350373646

In this paper, the problem of multi-beam sounding, and line layout is studied, and the optimal layout problem of multi-beam line layout is solved by greedy algorithm and particle swarm optimization algorithm. First of all, under the condition that the direction of the surveying line is variable, and the seabed topography is a rectangular sea area to be measured on a slope, a mathematical model of the coverage width of multi-beam sounding is established. By abstract the multi-beam sounding problem into a mathematical model, the relationship between the coverage width and the overlap rate between adjacent strips is sought, and the corresponding seawater depth, coverage width and the overlap rate with the previous surveying line are calculated. Secondly, the problem of optimal line layout in the rectangular slope sea area is abstracted as the shortest line planning problem, and the single objective optimization problem of optimal line layout is solved based on the greedy algorithm, and the simulated annealing algorithm is used to verify the solution results. Finally, in view of the large relief of the seabed topography, the seabed is divided into several slopes, and the particle swarm optimization algorithm is selected to solve the target planning model, which can get more accurate results in a short time. © 2024 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

WU-Net++: A novel enhanced Weighted U-Net++ model for brain tumor detection and segmentation from multi-parametric magnetic resonance scans

引用

multimedia Tools and Applications 2024年第28期83卷 71885-71908页

作者： Das, Suchismita Dubey, Rajni Jena, Biswajit Tsai, Lung-Wen Saxena, Sanjay Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar India School of Computer Engineering KIIT Deemed to Be University Bhubaneswar India Division of Cardiology Department of Internal Medicine Taipei Medical University Hospital Taipei111031 Taiwan Department of Computer Science and Engineering Institute of Technical Education and Research SOA Deemed to Be University Bhubaneswar India Department of Medicine Research Taipei Medical University Hospital Taipei111031 Taiwan Department of Information Technology Office Taipei Medical University Hospital Taipei11031 Taiwan Graduate Institute of Data Science College of Management Taipei Medical University Taipei11031 Taiwan

Brain tumor detection and segmentation from multi-parametric magnetic resonance (MR) scans are crucial for the prognosis and treatment planning of brain tumor patients in current clinical practice. With recent technological advancements, artificial intelligence-based deep learning has proven its indispensable image analysis capability in the most challenging tasks. This study proposes an automated WU-Net + + deep learning model for brain tumor segmentation using multiparametric structural MR scans obtained from the BraTS 2018 dataset. The model was validated through cross-dataset testing for intracranial hemorrhage (ICH) classification (ATLAS V2.1 dataset) and multi-organ segmentation from abdominal images of TCIA and BTCV datasets. The WU-Net++ model, a novel version of U-Net, was developed by adjusting its pooling operation as a weighted function of max and average pooling for brain tumor segmentation. The proposed model (WU-Net + +) achieved an F1 score of 0.94 ± 0.124, a dice score of 0.91 ± 0.132, and an AUC value of 0.915 for whole tumor segmentation. The model also achieved a high accuracy of 0.9949 ± 0.121 in ICH classification and dice scores of 0.912 ± 0.21, 0.844 ± 0.25, and 0.893 ± 0.17 for spleen, esophagus, and portal and splenic vein segmentation, respectively. Our study revealed that WU-Net + + has significant potential to improve the accuracy of segmentation and could be an effective method in the era of precision medicine. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

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：