检索结果-内蒙古大学图书馆

IAENG International Journal of computer science 2025年第6期52卷 1921-1929页

作者： Tan, Xu Zhao, Ji 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 Anshan114051 China

The rapid evolution of intelligent automotive systems has driven the urgent need for advanced damage assessment methodologies, revealing critical limitations in conventional visual inspection techniques. This study posits a multi-task learning architecture for vehicular surface damage quantification through synergistic integration of instance segmentation and monocular depth estimation. Three key technical innovations are incorporated: 1) A Heterogeneous Feature Single-Phase Booster (HFSPB) module utilizing RepViT layers to optimize backbone feature discriminability;2) A Channel-wise Cross Fusion Block facilitating adaptive multi-scale feature amalgamation with intrinsic noise attenuation;3) A depth estimation head implementing Depth Interval Attraction Refinement for geometrically consistent surface reconstruction. Benchmark evaluations revealed a threefold acceleration in inference speed relative to conventional approaches, coupled with robust metric performance (δ₁: 91.9%, δ₂: 99.4%, δ₃: 99.8%, REL=0.089, RMSE=0.312). This integrated framework establishes a computationally efficient paradigm for multimodal damage characterization, providing critical insights for autonomous vehicle maintenance systems. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

An Integrated Machine Learning Framework Based Liver Disease Diagnosis System

An Integrated Machine Learning Framework Based Liver Disease...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Imtiaz, Irsa Qaiser, Ayesha Rehman, Attique Ur Javaid, Sabeen Ali, Tahir Muhammad Mir, Azka University of Sialkot Department of Software Engineering Sialkot Pakistan Gulf University for Sciences and Technology Department of Computer Science Kuwait

ISBN: (纸本)9798350349719

Viral hepatitis increases the likelihood of developing liver cancer, which is a critical public health concern. It is a severe disorder that can be fatal if not recognized and treated promptly. The most common causes of liver cancer are hepatitis viruses. Early-stage diagnosis of HCC is crucial for improving patient outcomes, particularly when hepatitis virus infection is the underlying cause. This study looks into the use of ML algorithms for early detection of liver cancer in hepatitis virus-infected patients. The study will present a unified approach for the early detection of liver cancer that is highly accurate. Early detection of liver cancer is critical in reducing mortality and assisting practitioners in treating patients on time based on results. Machine learning algorithms have been intensively researched and applied to the diagnosis of liver cancer, especially in recent years. Researchers employed a variety of machine learning techniques to create models for detecting liver cancer at different stages, including early diagnosis. To enhance the model's flexibility and efficiency, We used three datasets that contained all of the information required for diagnosing liver cancer. Several machine-learning approaches were used to improve the model's accuracy. Our proposed model acquired a 98.10% accuracy rate with Bagging. Using several datasets in machine learning for liver disease detection enhances model performance by diversifying the training examples, resulting in a more robust and generalizable model with lower overfitting risk. This study aims to improve the quality of life for people who are at risk of or have been diagnosed with liver cancer. © 2024 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

An Approach for Early Detection of Schizophrenia 15

An Approach for Early Detection of Schizophrenia

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Paranagama, Sachin Uditha, Isiwara Daundasekara, Pamodya Hettiarachchi, Shehani Weerasinghe, Lokesha Kasthurirathna, Dharshana Sri Lanka Institue Of Information Technology Faculty Of Computing Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9798350370249

Schizophrenia is a chronic mental disorder with distorted thinking, hallucinations, and social difficulties. Early diagnosis is vital, but current methods are limited. This research proposes a web-based application integrating machine learning, emotion recognition, and game-based elements to track symptoms and aid in early diagnosis. Interactive exercises focus on specific symptoms like cognitive evaluation, emotional analysis, and memory assessment. By combining computer science, psychology, and machine learning, the project aims to improve early detection and ultimately enhance the quality of life for affected individuals. Key components include using Deep Convolutional Neural Network (DCNN) architecture for recognizing facial and physical expressions associated with schizophrenia with an 87% accuracy rate, and utilizing Vector Regressor (SVR) with a 93% accuracy rate, along with Vision Transformer (ViT) and Custom CNN models for cognitive assessment, achieving accuracy rates of 99% and 98%, respectively. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Convolutional Neural Networks to Detect Pedestrians Effectively in Various Urban Environments 6

Enhancing Deep Convolutional Neural Networks to Detect Pedes...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Hasan, Md. Mehedi Aman, Nakib Jahan, Md. Wadud Software Engineer i Developer EXperience Hub Rajshahi Bangladesh Pabna University of Science and Technology Department of Computer Science and Engineering Pabna Bangladesh

ISBN: (纸本)9798350385779

In computer vision, accurately identifying pedestrians is a crucial difficulty, especially in applications where safety is of the highest priority, such autonomous driving and urban planning. Deep learning has made progress, but challenges such changing conditions, barriers, and processing power requirements still exist. In this paper, we present an improved deep convolutional neural network (DCNN) designed with pedestrian identification in mind. Improving accuracy in various settings while maximizing processing efficiency is our goal. We carefully prepare the data and create a novel DCNN architecture that can handle a variety of pedestrian appearances and urban surroundings by utilizing well-known datasets such as Penn-Fudan and PnPLO. Our model performs exceptionally well in terms of accuracy, speed, and durability, according to a thorough evaluation that compares it to recognized benchmarks. In addition to making important advances, our study has shown novel approaches to enhancing performance in challenging environments, such as the analysis of transfer learning and the deployment of real-time systems. This work paves the way for future developments in intelligent, self-governing systems and is a maj or leap forward in pedestrian detection technology. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neighborhood Subgraph-based Illicit Transaction Detection in Cryptocurrency Networks 12

Neighborhood Subgraph-based Illicit Transaction Detection in...

引用

12th IEEE International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2024

作者： Jin, Shenghao Yang, Qiwen Chen, Shengyu Zhang, Hui Beihang University State Key Laboratory of Complex & Critical Software Environment School of Computer Science & Engineering Beijing China

ISBN: (纸本)9798331510633

With the widespread adoption of cryptocurrencies, associated illicit activities such as money laundering, fraud, extortion, and Ponzi schemes have garnered significant attention. Traditional studies have extensively employed graph neural network technologies to identify illicit transactions, typically treating the entire transaction network as input to classify its nodes. Although these methods perform well on small-scale networks, they face performance limitations when processing large-scale blockchain transaction data. To address this issue, we propose a neighborhood subgraph-based method for detecting illicit transactions, integrating GCN and LSTM. In this approach, the GCN captures and integrates information from adjacent nodes for each transaction, facilitating a deep understanding of network structures. The LSTM is tasked with capturing the sequence and variations in fund flows, effectively tracking the direction and temporal characteristics of the money flow. Experimental results indicate that when using 3-hop neighborhood subgraphs, our model's performance surpasses other GCN-based methods. Compared to previous models that require considering the entire transaction network, our approach only needs to utilize information from an average of 80 nodes, significantly improving efficiency. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review on Pattern-based GUI Testing of Android and Web Apps: State-of-the-Art, Taxonomy, Challenges and Future Directions 25

A Systematic Review on Pattern-based GUI Testing of Android ...

引用

25th International Multi Topic Conference, INMIC 2023

作者： Kousar, Ambreen Khan, Saif Ur Rehman Hussain, Shahid Abdul Basit Ur Rahim, M. Wang, Wen-Li Ibrahim, Naseem Comsats University Islamabad Dept of Computer Science Islamabad Pakistan Shifa Tameer-e-Millat University Dept. of Software Engineering Islamabad Pakistan Penn State University Behrend School of Computer Science and Software Engineering Pennsylvania16563 United States California State University Dept. of Computer Engineering and Computer Science Long Beach United States Penn State Erie Dept. of Computer Science and Software Engineering United States

ISBN: (纸本)9798350317701

Graphical User Interface (GUI) designing and testing of different applications is significant from a user point of view. GUI testing ensures that the user interface of apps is visually appealing, user-friendly, and enhances user satisfaction. Pattern-Based GUI Testing (PBGT) is a new model-based testing approach that aims to enhance reusability while reducing the workload associated with modeling user interfaces and testing applications. The objective of conducting a Systematic Literature Review (SLR) on pattern-based GUI testing is to consolidate existing knowledge and provide insights for improving the effectiveness of PBGT methods. The objectives of conducting an SLR are the identification of current state-of-the-art approaches and tools in the targeted research context. To accomplish the mentioned objectives, A hybrid methodology combining Kitchenham's SLR and PRISMA guidelines was used to conduct this SLR. We performed a keyword-based search on well-known databases IEEE, ACM, science Direct, Wiley, and Springer Link to determine the potential studies published in the last 10 years. Following a comprehensive systematic analysis, we identified a total of twenty-four studies employing varied approaches for pattern-based GUI testing. Additionally, we identified 11 tools that have been used and proposed in PBGT for Android and web apps and made a taxonomy of tools. We also identified challenges and research directions. The implications of this study are significant. The current study is helpful for researchers intending to work in pattern-based GUI testing. The comprehensive knowledge about the current state-of-the-art Tools, techniques, and approaches will help practitioners to effectively apply them in industry and enable researchers to extend their work in this context in future research. © 2023 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

GATBind: Accurate protein-RNA binding sites prediction via graph attention networks with pre-trained language model

GATBind: Accurate protein-RNA binding sites prediction via g...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Shen, Siyuan Wu, Shangqian Chen, Jie Huang, Zhijian Deng, Lei Central South University School of Computer Science and Engineering Changsha China Xinjiang University School of Software Urumqi China

ISBN: (纸本)9798350386226

Protein-RNA interactions play a pivotal role in various biological processes, making them essential for discovering novel therapeutic targets. Understanding these interactions is crucial for identifying potential drug targets and designing effective therapeutics. However, traditional experimental approaches are costly and time-consuming, highlighting the need for accurate and efficient computational methods to predict RNA-binding sites. In this study, we propose a novel method called GATBind, designed to predict RNA-binding sites on proteins. GATBind introduces a local environment-aware module that captures the local structural information surrounding target residues. Additionally, we incorporate sequence and structural features, including PSSM, HMM, DSSP, and sequence embeddings generated by the pre-trained protein language model ESMFold-2. These features are integrated and processed through a Graph Attention Network (GAT) module to predict RNA-binding sites accurately. Experimental results demonstrate that GATBind outperforms existing state-of-the-art methods, and case studies further validate its effectiveness in predicting RNA-binding sites. © 2024 IEEE.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

A Hypergraph Transformer With Adaptive EdgeConv for Skeleton-based Action Recognition 7

A Hypergraph Transformer With Adaptive EdgeConv for Skeleton...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Zhou, Fengyu Liu, Jun Zhang, Dazhi Huang, Zengxi School of Computer Science and Software Engineering Xihua University Chengdu China Sichuan Police College Criminal Science and Technolog Department Luzhou China

ISBN: (纸本)9798350350890

Skeleton-based action recognition is a crucial task in computer vision, aiming to perform pattern recognition on a skeleton sequence to identify the actions represented by the skeleton's semantics. However, current mainstream skeleton-based methods primarily rely on global edge information. Unimportant edges may influence this approach, limiting the model's performance in action recognition tasks. Additionally, because these methods treat all information equally, they may lead to resource wastage. This paper proposes a Hypergraph Transformer-based action recognition method using Adaptive EdgeConv Module(AEM) to address these issues effectively. In this method, we introduce Adaptive Edge Graph Convolution Networks(AEGCNs), which utilize the AEM to adaptive obtain edge sets and edge set weights, thereby adaptive identifying key edge sets. With this information, the model can dynamically adjust the importance of different edge sets based on various samples. This approach improves the accuracy of action recognition and reduces the loss of computational resources. Our experimental results on two challenging benchmark datasets (i.e., NTU RGB+D and NTU RGB+D 120) show that the proposed method is comparable to state-of-the-art methods. © 2024 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Overlapping Community Guided Hierarchical Self-Attention Pooling 5

Fuzzy Overlapping Community Guided Hierarchical Self-Attenti...

引用

5th International Conference on Intelligent Computing and Human-computer Interaction, ICHCI 2024

作者： Liu, Xin Xiao, Yao Zhang, Zuping School of Computer Science and Engineering Central South University Changsha China School of Software Xinjiang University Urumqi China

ISBN: (纸本)9798350368284

Graph pooling aims at extracting vital information for graph coarsening, and thus helping graph neural networks to improve their graph representation ability. However, existing methods either compress similar nodes by a clustering algorithm or discard unimportant nodes by an importance score, resulting in the coarsened graph suffering from different issues. Therefore, aiming at the goal of breaking through their limitation, this paper develops a fuzzy overlapping community guided hierarchical self-Attention pooling, namely FOCoHSAP. FOCoHSAP performs node selection within every detected community rather than the entire graph, which allows for an explicit preservation of both topology hierarchy and detailed node information. Especially, FOCoHSAP introduces fuzzy overlapping community detection algorithm to explore those fine-grained relationships between nodes and communities, allowing for a more promising learning of graph representation that can be utilized for accurate graph classification. © 2024 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

A Code Obfuscation Framework for software and Intellectual Property Protection 4

A Code Obfuscation Framework for Software and Intellectual P...

引用

4th International Multidisciplinary Information Technology and engineering Conference, IMITEC 2024

作者： Azeta, Ambrose A. Edward, Chimba S. Stanley, Colin Awal, Abdulganiyu Namibia University of Science and Technology Department of Software Engineering Namibia Covenant University Department of Computer and Information Sciences Nigeria

ISBN: (纸本)9798350387988

software piracy is a major problem faced in the software industry. Despite the several techniques proposed in previous studies, software piracy and intellectual property theft have continued to pose a threat in the software industry. The objective of this study is to design a code obfuscation framework for software and intellectual property protection. The methodology employed includes use of JavaScript and algorithms that described the key processes of the framework. The obfuscation framework presented in this study consists of five distinct transformation techniques belonging to the control-flow class of obfuscation classifications. A prototype application that executes the transformation techniques to produce obfuscated code based on specified techniques was provided. Results obtained from the evaluations shows that some transformation techniques are more effective than others in obscuring codes and that the proposed framework increases the computing overhead of the resultant obfuscated code by a relatively small margin. Results indicate that majority (76.2%) of the respondents believe that the developed obfuscator is inexpensive and that it does not adversely affect memory and execution time. The developed framework and prototype implementation would provide software vendors and developers the tool to obscure their intellectual property against attack and theft by making reverse engineering difficult and unattractive. © 2024 IEEE.

关键词： Reverse engineering

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：