检索结果-内蒙古大学图书馆

IAENG International Journal of computer Science 2025年第1期52卷 1-10页

作者： Wang, Tingting Fan, Qi Tan, Liang Zhang, Beier School of Computer and Software Engineering Anhui Institute of Information Technology China School of Computer Science and Technology Huaibei Normal University China School of Computer and Software Engineering Anhui Institute of Information Technology China School of Computer Science and Technology Huaibei Normal University China

Predicting the metastatic direction of primary breast cancer (BC), thus assisting physicians in precise treatment, strict follow-up, and effectively improving the prognosis. The clinical data of 293,946 patients with primary BC diagnosed between 2010 and 2015 were collected from the Surveillance, Epidemiology, and End Results database. Multiple interpolations and Multi-label Synthetic Minority Over-sampling Technique methods were used for data analysis, and machine learning model was established for multi-label classification. Finally, Surgical information, lymph node status, distant metastasis, tumor size, chemotherapy, histological type, and radiotherapy had significant influence as inputs. Compared with the k-nearest neighbor model, average accuracies of the decision tree and random forest (RF) models increased from 88.84% to 93.59% and 94.14%, respectively. Their average precision, recall rate, F1 score, area under the receiver operating characteristic curve and weighted-F1 increased from 87.24% to 95.85% and 94.74%, 87.73% to 90.40% and 91.76%, 87.07% to 92.16% and 93.45%, 97.11% to 99.53% and 99.95%, 82.13% to 89.44% and 90.48%, respectively. In conclusion, the RF model, which showed the best performance, can be used in multi-label prediction of BC metastasis directions, and can assist physicians in diagnosing and treating patients with primary BC. © (2025), (International Association of Engineers). All rights reserved.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Improved A* Algorithm for Intelligent Navigation Path Planning

引用

Informatica (Slovenia) 2024年第10期48卷 181-194页

作者： Dong, Lisha School of Computer and Software Engineering Sias University Zhengzhou Zhengzhou450000 China

For path planning in intelligent navigation, traditional navigation maps currently fail to meet the requirements of autonomous navigation and optimal path search in terms of three-dimensional environmental features and accuracy. Therefore, the study combined multiple sensors of LIDAR and depth camera to construct a three-dimensional simulation environment map model, and the optimized A* algorithm used to improve path planning. The cost proportion factor and improved heuristic function were used to optimize the A* algorithm. Through experimental comparison before and after optimization, the shortest path and time of the A* algorithm in the 8×8 grid map before optimization were 12.89 and 0.56s, respectively. It had a shortest path and time of 28.76 and 0.28s in a grid map of 16×16, respectively. The improved A* algorithm had an optimal path and time of 12.26 and 0.34s on an 8×8 grid map, and a shortest path and time of 26.34 and 0.28s on a 16×16 grid map. These experiments confirm that the improved A* algorithm improves the search range and efficiency of path planning. This demonstrates its superiority for intelligent navigation path planning and provides technical references for environmental map construction and optimal path planning. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

software Test Data Management Based on Knowledge Graph

引用

Informatica (Slovenia) 2024年第16期48卷 27-36页

作者： Gao, Li Qiu, Junlin Chen, Guanhua Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai’an223003 China

As software development models and methods mature, large-scale software systems emerge. However, a critical challenge remains: the lack of a comprehensive software test data management model that integrates basic data management with advanced knowledge reasoning. To address this issue, we developed a software test data management model based on knowledge graphs, enabling intelligent management and reasoning of software test data. The model incorporates an entity extraction model based on a feed-forward neural network, a knowledge graph integration method based on graph databases, and a knowledge reasoning submodule based on deep learning. To validate the effectiveness of our model, we evaluated the performance of each component individually. Our deep learning-based entity extraction model achieved an accuracy of 0.92, a recall of 0.88, and an F1 score of 0.90, significantly outperforming traditional methods such as regular expressions and dictionary-based approaches. Utilizing Cypher for graph database querying, our system provides accurate answers with a response time of 0.12 seconds, outperforming SQL and SPARQL-based querying methods. Furthermore, our approach excels in knowledge-based reasoning with an accuracy of 0.89 and site coverage of 0.81, surpassing both ontology-based and graph-based reasoning methods. These results highlight the enhanced construction, querying, and reasoning capabilities of our knowledge graph-based approach for managing software testing data. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

ROBOT PATH PLANNING WITH A HYBRID ARITHMETIC OPTIMIZATION ALGORITHM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2024年第3期86卷 197-210页

作者： Song, Qiang Dept. of Computer Science and Software Engineering Zhaoqing University Zhaoqing China

To address the premature convergence and search stagnation of arithmetic optimization algorithm (AOA), the paper proposes a hybrid arithmetic optimization algorithm (HAOA) and applies it to the practical robot path planning (RPP) problem. In initialization phase, the chaotic mechanism is used to create high-quality individuals. In evolution phase, the stochastic disturbance method is applied to enhance the exchange of information between different individuals. The solution space information around the candidate solution was integrated by Levy flight to enhance gene diversity and enhance search performance. In order to better solver the RPP problem, the Spline interpolation method is adapted to the HAOA algorithm for path optimization, so as to smooth the path curve and ensure the planning accuracy. Finally, numeric experiments of benchmark functions and RPP instances verify HAOA’s excellent performance in accuracy and robustness. This research shows arithmetic optimization algorithm can quickly find the global optimal solution, and has fast convergence speed and accuracy. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Algorithm of Hot-Rolled Strip Based on Improved YOLOv7

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第4期51卷 345-354页

作者： Shen, Lijia Cui, Wenhua Tao, Ye Shi, Tianwei Liao, Jinzhen School of Electronic and Information Engineering University of Science and Technology Liaoning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

To enhance the capability of classifying and localizing defects on the surface of hot-rolled strips, this paper proposed an algorithm based on YOLOv7 to improve defect detection. The BI-SPPFCSPC structure was incorporated into the feature pyramid in this algorithm, enabling enhanced extraction of features from small objects and improved accuracy in network model positioning. Additionally, a small object detection layer was introduced to enhance shallow feature capture. Then the CARAFE sampling operator was used for up-sampling to reduce the feature loss problem of small objects. Finally, the WIoU served as the loss function for network model training to expedite convergence. The NEU-DET dataset was utilized for ablation and comparison tests. The findings indicated that the enhanced YOLOv7 model's mAP value had increased to 80.7%. The detection impact was much enhanced in comparison to other traditional models, and the frequency of false and missing detections was also decreased. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Surface defects

来源：评论

学校读者我要写书评

暂无评论

Enhancing the adversarial robustness in medical image classification: exploring adversarial machine learning with vision transformers-based models

引用

Neural Computing and Applications 2025年第12期37卷 7971-7989页

作者： Kanca Gulsoy, Elif Ayas, Selen Baykal Kablan, Elif Ekinci, Murat Software Engineering Karadeniz Technical University Trabzon Turkey Computer Engineering Karadeniz Technical University Trabzon Turkey

Despite their remarkable achievements in computer-aided medical image-related tasks, including detection, segmentation, and classification, deep learning techniques remain vulnerable to imperceptible adversarial attacks, which could lead to potential misdiagnosis in clinical applications. Therefore, adversarial attacks and their defense in deep medical diagnosis systems have been witnessed remarkable progress in recent years. Although the importance of transformers in various medical applications has grown immensely, a critical concern for the reliability and security of their susceptibility to adversarial attacks has not yet been sufficiently investigated. Furthermore, many studies in the field of ViT-based adversarial machine learning mainly focus on pure ViT architecture. To this end, this paper provides a comprehensive evaluation, comparison, and analysis of state-of-the-art ViT-based models such as ViT, DeiT, Swin transformer, and PVTv2 for their robustness against FGSM and PGD adversarial machine learning attacks and investigates the impact of the k-step PGD adversarial training defense mechanism in the domain of various medical imaging tasks. The findings indicate that ViT-based models are vulnerable to adversarial attacks even at a small perturbation degree. Furthermore, the significant drop in accuracy from around 90.0% underlines the vulnerability of these models to adversarial attacks and highlights the urgent need for robust defenses. We also conclude that the ViT-based models show significant robustness against adversarial attacks using adversarial training, i.e., the defense strategy can achieve improved classification accuracy, close to the clean image accuracy. By analyzing quantitative results, we believe that this study aims to fill the gap in research on the robustness of ViT-based models to adversarial machine learning attacks in medical image analysis, highlighting future research directions. © The Author(s), under exclusive licence to Springer-

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Interpersonal Relationship Detection Using Multi-Head Graph Attention Networks with Multi-Feature Fusion

引用

IEEE Access 2025年 13卷 90945-90961页

作者： Akay, Simge Cakir, Duygu Arica, Nafiz Bahcesehir University Department of Computer Engineering Istanbul Turkey Bahcesehir University Department of Software Engineering Istanbul Turkey Piri Reis University Department of Computer Engineering Istanbul Turkey

The ability to automatically detect and understand interpersonal relationships from visual data represents a fundamental challenge in computer vision and social signal processing. While significant advances have been made in face recognition and object detection, understanding the complex dynamics of human relationships requires a detailed approach that can integrate multiple visual and contextual cues. This paper presents a novel Multi-Head Graph Attention Network (MHF-GAT) with Multi-Feature Fusion for interpersonal relationship detection (IRD) from images. The proposed architecture decomposes heterogeneous visual and semantic features into three specialized modules: local features capturing direct interpersonal cues (e.g., age differences, expression similarity), contextual features modeling environmental information (e.g., scene, objects), and semantic features derived from image captions. By representing features as graph nodes and employing multi-head attention mechanisms within each module, MHF-GAT effectively captures complex feature interactions while reducing redundancy and overfitting risks. The model’s performance is evaluated on two benchmark datasets: the Interpersonal Relation Dataset (IPR) and People in Social Context (PISC). Experimental results demonstrate state-of-the-art performance, achieving 87.18% accuracy on IPR and 77.1% mean Average Precision (mAP) on PISC. Ablation studies and attention visualization reveal that the modular architecture significantly improves feature discrimination and relationship classification compared to single-graph approaches. © 2013 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced facial action unit detection with adaptable patch sizes on representative landmarks

引用

Neural Computing and Applications 2025年第5期37卷 3777-3791页

作者： Cakir, Duygu Yilmaz, Gorkem Arica, Nafiz Department of Software Engineering Bahcesehir University Istanbul Turkey Department of Computer Engineering Bahcesehir University Istanbul Turkey Department of Computer Engineering Piri Reis University Istanbul Turkey

The human face displays expressions through the contraction of various facial muscles. The Facial Action Coding System (FACS) is a widely accepted taxonomy that describes all visible changes in the face in terms of action units (AUs). In this study, AUs are examined by finding the most active landmarks of the face and then examining the most representative patch sizes of each landmark for the AU detection task. Sparse learning is employed to learn the most active landmarks for each AU, and then the active landmark patches are fed to ViT and Perceiver mechanisms independently. Experiments indicate that using active landmark patches with their most representative size improves the results when compared to using all the landmarks, especially when it is used on more challenging datasets as a support for the attention mechanism of the classifier. The results demonstrate that the proposed method improves the performance of the employed models and are further supported by experiments conducted across different datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deepfake Audio Detection for Urdu Language Using Deep Neural Networks

引用

IEEE Access 2025年 13卷 97765-97778页

作者： Ahmad, Omair Khan, Muhammad Sohail Jan, Salman Khan, Inayat University of Engineering and Technology Department of Computer Software Engineering Mardan Pakistan Arab Open University Faculty of Computer Studies A’Ali732 Bahrain University of Engineering and Technology Department of Computer Science Mardan Pakistan

Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Skin Lesion Segmentation Based on Pseudo-Labels

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第2期52卷 325-332页

作者： Mu, Bo Wei, JingXin Zhang, Yujun School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

In recent years, deep learning has significantly advanced skin lesion segmentation. However, annotating medical image data is specialized and costly, while obtaining unlabeled medical data is easier. To address this challenge, we propose a semi-supervised learning strategy to improve segmentation accuracy by combining a small amount of annotated data with a larger volume of unlabeled data. Our approach employs a teacher-student model framework. In this framework, the teacher model generates pseudo-labels for the unlabeled data, and the student model is trained using both these pseudo-labels and the limited true labels. To improve the student model’s learning capacity, we introduce auxiliary segmentation heads that provide joint guidance during training. We use the crossentropy (CE) loss function to quantify the discrepancies between the segmentation outputs of the main head and auxiliary heads. Since pseudo-labels generated by the teacher model may contain noise, we developed a mechanism to identify and exclude uncertain regions in each unlabeled image. This reduces pseudolabel noise and mitigates its negative impact on the student model. Our method demonstrates significant improvements in skin lesion segmentation on the publicly available ISIC2018 dataset, achieving Dice coefficients of 87.84% and 88.73% with only 5% and 10% of the total annotated data, respectively, outperforming existing methods. © (2025), (International Association of Engineers). All rights reserved.

关键词： Self-supervised 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：