检索结果-内蒙古大学图书馆

PolypSeg+: A Lightweight Context-Aware Network for Real-Time Polyp Segmentation

IEEE Transactions on Cybernetics 2023年第4期53卷 2610-2621页

作者： Wu, Huisi Zhao, Zebin Zhong, Jiafu Wang, Wei Wen, Zhenkun Qin, Jing Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The Hong Kong Polytechnic University Centre for Smart Health School of Nursing Hong Kong

Automatic polyp segmentation from colonoscopy videos is a prerequisite for the development of a computer-assisted colon cancer examination and diagnosis system. However, it remains a very challenging task owing to the large variation of polyps, the low contrast between polyps and background, and the blurring boundaries of polyps. More importantly, real-time performance is a necessity of this task, as it is anticipated that the segmented results can be immediately presented to the doctor during the colonoscopy intervention for his/her prompt decision and action. It is difficult to develop a model with powerful representation capability, yielding satisfactory segmentation results and, simultaneously, maintaining real-time performance. In this article, we present a novel lightweight context-aware network, namely, PolypSeg+, attempting to capture distinguishable features of polyps without increasing network complexity and sacrificing time performance. To achieve this, a set of novel lightweight techniques is developed and integrated into the proposed PolypSeg+, including an adaptive scale context (ASC) module equipped with a lightweight attention mechanism to tackle the large-scale variation of polyps, an efficient global context (EGC) module to promote the fusion of low-level and high-level features by excluding background noise and preserving boundary details, and a lightweight feature pyramid fusion (FPF) module to further refine the features extracted from the ASC and EGC. We extensively evaluate the proposed PolypSeg+ on two famous public available datasets for the polyp segmentation task: 1) Kvasir-SEG and 2) CVC-Endoscenestill. The experimental results demonstrate that our PolypSeg+ consistently outperforms other state-of-the-art networks by achieving better segmentation accuracy in much less running time. The code is available at https://***/szu-zzb/polypsegplus. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Crop Pest Image Classification Based on Multi-Scale Convolutional Neural Network 9

Crop Pest Image Classification Based on Multi-Scale Convolut...

引用

9th International Conference on Fuzzy Systems and Data Mining, FSDM 2023

作者： Ma, Chi Li, Huikai Hu, Hui Li, Jingyan Wu, Jie School of Computer Science and Engineering Huizhou University Huizhou516007 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

ISBN: (纸本)9781643684703

Crop diseases and pests are major threats to crop yield and quality, as well as global food security and agricultural livelihoods. Therefore, it is essential to identify crop pests and diseases in a timely, efficient and accurate manner. In this paper, we propose MConvNeXt, a crop pest classification model based on multi-scale feature fusion, which adds a multi-scale module to the original ConvNeXt network model to better capture feature information at different scales. We experimentally analyzed the MConvNeXt model on the IP102 dataset, and the results show that it outperforms the baseline network and other classical image classification models in pest classification. © 2023 The authors and IOS Press.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Leaching Fraction (LF) of Irrigation Water for Saline Soils Using Machine Learning

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1915-1930页

作者： Rab Nawaz Bashir Imran Sarwar Bajwa Muhammad Waseem Iqbal Muhammad Usman Ashraf Ahmed Mohammed Alghamdi Adel ABahaddad Khalid Ali Almarhabi Department of Computer Science COMSATS University IslamabadVehari CampusPakistan Department of Computer Science and IT Islamia University BahawalpurPakistan Department of Software Engineering Superior University Lahore54000Pakistan Department of Computer Science GC Women UniversitySialkot53310Pakistan Department of Software Engineering College of Computer Science and EngineeringUniversity of Jeddah21493Saudi Arabia Department of Information System Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science College of Computing in Al-QunfudahUmm Al-Qura UniversityMakkah24381Saudi Arabia

Soil salinity is a serious land degradation issue in *** is a major threat to agriculture *** irrigation water is applied to leach down the salts from the root zone of the plants in the form of a Leaching fraction(LF)of irrigation *** the leaching process to be effective,the LF of irriga-tion water needs to be adjusted according to the environmental conditions and soil salinity level in the form of Evapotranspiration(ET)*** relationship between environmental conditions and ET rate is hard to be deﬁned by a linear relationship and data-driven Machine learning(ML)based decisions are required to determine the calibrated Evapotranspiration(ETc)***-assisted ETc is pro-posed to adjust the LF according to the ETc and soil salinity level.A regression model is proposed to determine the ETc rate according to the prevailing tempera-ture,humidity,and sunshine,which would be used to determine the smart LF according to the ETc and soil salinity *** proposed model is trained and tested against the Blaney Criddle method of Reference evapotranspiration(ETo)*** validation of the model from the test dataset reveals the accu-racy of the ML model in terms of Root mean squared errors(RMSE)are 0.41,Mean absolute errors(MAE)are 0.34,and Mean squared errors(MSE)are 0.28 mm *** applications of the proposed solution in a real-time environ-ment show that the LF by the proposed solution is more effective in reducing the soil salinity as compared to the traditional process of leaching.

关键词： Leaching fraction saline soil evapotranspiration machine learning calibrated evapotranspiration artiﬁcial intelligence blaney criddle method

来源：评论

学校读者我要写书评

暂无评论

Learning a generalizable re-identification model from unlabelled data with domain-agnostic expert

引用

Visual Intelligence 2024年第1期2卷 337-349页

作者： Fangyi Liu Mang Ye Bo Du National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication EngineeringSchool of Computer ScienceHubei Luojia LaboratoryWuhan UniversityWuhan430072China

In response to real-world scenarios,the domain generalization(DG)problem has spurred considerable research in person re-identification(ReID).This challenge arises when the target domain,which is significantly different from the source domains,remains ***,the performance of current DG ReID relies heavily on labor-intensive source domain *** the potential of unlabeled data,we investigate unsupervised domain generalization(UDG)in *** goal is to create a model that can generalize from unlabeled source domains to semantically retrieve images in an unseen target *** address this,we propose a new approach that trains a domain-agnostic expert(DaE)for unsupervised domain-generalizable person *** involves independently training multiple experts to account for label space inconsistencies between source *** the same time,the DaE captures domain-generalizable information for *** experiments demonstrate the effectiveness of this method for learning generalizable features under the UDG *** results demonstrate the superiority of our method over state-of-the-art *** will make our code and models available for public use.

关键词： Domain generalization(DG) Unlabeled source domains Label space inconsistencies Domain-agnostic expert(DaE)

来源：评论

学校读者我要写书评

暂无评论

GSD-YOLO: a Lightweight Framework for Traffic Sign Detection

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第6期52卷 1815-1823页

作者： Jianbang, Ding Tianwei, Shi Zhehao, Zhang Ruiqi, Wang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

To address the challenges of detecting small traffic signs, low detection accuracy, complex detection network models, and large parameter counts, this paper proposes a lightweight traffic sign detection framework called GSD-YOLO. This framework integrates the GCSconv module, SENetV2 module, and DySample module. Specifically, the Slim-net architecture, formed by combining the GCSconv and VOVGSCP modules, is employed to replace the Conv and C2f modules in the original YOLOv8 neck network. This substitution not only reduces the number of parameters and computational load during training but also achieves a lightweight design. The lightweight SENetV2 module is incorporated into the backbone of the detection model, further lightening the backbone. In the neck network, the DySample module replaces the original upsampling module, enhancing the model’s upsampling capability while reducing the parameter count. Compared to the original YOLOv8 detection network, Grad-CAM visualization shows that traffic signs in the detected regions appear darker and more concentrated. On the CCTSDB dataset, the proposed framework achieves an mAP@0.5 of 95.5%, which is 2.3% higher than the original YOLOv8 (93.3%). The model size is reduced to 4.2MB, which is 32.2% smaller than the original YOLOv8. The GFLOPs are reduced by 35%, and the overall parameter count is decreased by 40%. The lightweight detection framework proposed in this paper effectively reduces model size, simplifies model complexity, decreases parameter count, and improves detection accuracy, achieving significant improvements in the field of traffic sign detection. © (2025), (International Association of Engineers). All rights reserved.

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

Neural Transformers for Bias Detection: Assessing Pakistani News 5

Neural Transformers for Bias Detection: Assessing Pakistani ...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Ali, Owais Zaland, Zubair Bazai, Sibghat Ullah Ghafoor, Muhammad Imran Hussain, Laiq Haider, Arsalan Buitems Department of Software Engineering Quetta Pakistan Buitems Department of Computer Engineering Quetta Pakistan Pakistan Television Corporation Department of Engineering Lahore Pakistan Buitems Department of Electrical Engineering Quetta Pakistan

ISBN: (纸本)9798350394764

Political bias in the media poses a significant persuasive challenge within today's literary landscape, capable of reshaping individuals' perspectives and judgments. Therefore, it becomes imperative to categorize such biases in literature. One manifestation of bias is evident through word choice, a complex task due to the absence of standardized datasets and classification models. Transformer-based models proved highly effective in bias classification, and this research contributes to this field by evaluating classifiers, particularly ConvBERT, known for their exceptional performance in previous bias identification studies. Our models are trained using distant supervision and domain-aware pretraining, two successful techniques with impressive outcomes. Additionally, the study assesses various hyperparameters for ConvBERT and the most proficient models from prior research, revealing ConvBERT's remarkable potential in bias detection and achieving a peak macro F1 score of 0.815. Furthermore, the top-performing model was employed to discern the political bias in Pakistani media, classifying the Pakistani news dataset to elucidate prevailing political inclinations and leniencies within the current media landscape. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Comparison of Leading Language Parsers - ANTLR, JavaCC, SableCC, Tree-sitter, Yacc, Bison 13

Comparison of Leading Language Parsers - ANTLR, JavaCC, Sabl...

引用

13th International Conference on software Technology and engineering, ICSTE 2023

作者： Latif, Afshan Azam, Farooque Anwar, Muhammad Waseem Zafar, Amina College of Electrical and Mechanical Engineering Department of Computer and Software Engineering Islamabad Pakistan Malardalen University Department of Innovation Design and Engineering Vasteras Sweden

ISBN: (纸本)9798350371475

software engineering applications in domains like embedded systems and health care have increased exponentially during the last few years. Developing, analyzing, and customization of languages is one of the core software engineering aspects. This usually involves lexical, syntactical, and semantic operations, technically termed parsing. For this, several parsers have been introduced in state-of-the-art. However, due to diverse features, selecting a parser for a particular operation during software engineering applications is always problematic. In this article, we identified six leading parsers (i.e., ANTLR, JavaCC, SableCC, Tree-sitter, Yacc, and Bison) from the state-of-the-art. Furthermore, we also identified significant parser features to perform meaningful comparative analysis. Results indicate that ANTLR and JavaCC provide enhanced parsing features, such as the parsing algorithm and the extended grammar notation. However, JavaCC is suitable for simple grammar definition, whereas ANTLR allows specifying complex grammar with multiple alternative paths. The findings of this article are highly beneficial for researchers and practitioners while selecting the right parser to perform specific software engineering tasks. © 2023 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation 13

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Wu, Xunfeng Liu, Songbai Ji, Junkai Ma, Lijia Leung, Victor C. M. Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798350308365

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases. © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

A Review of Technical Challenges and Power Electronic Solutions for Distribution Networks 4

A Review of Technical Challenges and Power Electronic Soluti...

引用

4th Annual IEEE Kansas Power and Energy Conference, KPEC 2023

作者： Power, Rupert Madawala, Udaya Baguley, Craig The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Auckland University of Technology Department of Engineering Computer and Mathematical Sciences Auckland New Zealand

ISBN: (纸本)9798350335408

Increasing demand for electricity, the focus on sustainability and changing the ways in which society generates and uses electricity are creating significant technical challenges for distribution network operators. Power electronics can provide new ways to manage power flow and energy storage in distribution networks, and is therefore one way in which these challenges could be addressed. This paper reviews common research trends in power electronics for distribution networks and discusses how they are being used to address the problems faced by distribution network operators. Electronically controlled microgrids, energy storage, and other custom power devices operating at Low Voltage are found to be promising solutions, some of which have already been proven in field trials. © 2023 IEEE.

关键词： Electric load flow

来源：评论

学校读者我要写书评

暂无评论

Comparison of Conventional and Modified Ant Colony Approaches for Path Planning of Robot in an Indoor Environment 2

Comparison of Conventional and Modified Ant Colony Approache...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Sharan, Sudeep Ngoc Minh, Anh Tong Nguyen, Duc Thuan Dominguez-Jimenez, Juan Jose Nauth, Peter Frankfurt University of Applied Sciences Computer Science and Engineering Frankfurt am Main Germany Ucase Software Engineering Group School of Engineering University of Cádiz Cádiz Spain

ISBN: (纸本)9798350371055

The optimal path for autonomous robots is highly needed, particularly in the industrial communities, manufacturing and social support industries. The meta-heuristic methods are strong and adaptable, and their employment in autonomous problems is taken into consideration. One of the methods used by the researchers is Ant Colony Optimization (ACO). However, this approach is less effective due to a few limitations. Thus, in order to mitigate its shortcomings and enhance the robustness of path planning, this paper aims to compare the different standard ACO algorithm with the new modified built algorithm, which is developed by taking the concept of ACO and extending it by condition-based rules, named as condition based-ant colony concept (CB-ACC), to solve path planning. The theoretical foundation of ACO with modification as another approach are used in this study to illustrate the ACO methods in the path planning, particularly in the static-complex environment. Simulation results show the comparison of the ACO approaches, including the Ant System (AS), the Ant Colony System (ACS) and the modified condition based-ant colony concept (CB-ACC), and how they are effective for static-complex environments compared to conventional ACO algorithms. Moreover, this paper presents the comparison results of the three approaches. © 2024 IEEE.

关键词： Ant Colony Optimization Ant Colony System Ant System Condition/rule-based System Modified ACO Path Planning

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：