检索结果-内蒙古大学图书馆

A novel hybrid ConvNeXt-based approach for enhanced skin lesion classification

Expert Systems with Applications 2025年 283卷

作者： Aruk, Ibrahim Pacal, Ishak Toprak, Ahmet Nusret Department of Computer Engineering Faculty of Engineering Erciyes University Kayseri38000 Turkey Department of Software Engineering Faculty of Engineering Architecture and Design Kahramanmaras Istiklal University Kahramanmaras46050 Turkey Department of Computer Engineering Faculty of Engineering Igdir University Igdir76000 Turkey Department of Electronics and Information Technologies Faculty of Architecture and Engineering Nakhchivan State University NakhchivanAZ 7012 Azerbaijan

Skin cancer is a serious health problem that, if not diagnosed correctly at an early stage, leads to disease progression, increased risk of metastasis, and decreased quality of life. Therefore, it is critical to develop accurate and effective rapid diagnosis methods to assist physicians and enable autonomous diagnosis. While deep learning-based methods generally rely on convolutional neural networks (CNNs) or vision transformers (ViTs), hybrid approaches remain limited. In this work, we propose a novel proposed model that combines the strengths of both CNN and ViT architectures. The model utilizes the CNN approach to extract local patterns and detailed textural features, while using ViT structures to capture long-range relationships between skin cancer regions. Initially, ConvNeXt blocks extract highly detailed local features such as texture, edges, and color transitions. Transformer blocks then model the contextual relationships and global structure of these features, effectively addressing data imbalance and improving the overall classification performance. For a fair evaluation, the model is tested on two widely recognized skin cancer datasets, HAM10000 and ISIC 2019, and compared with 10 CNN and 10 ViT-based models trained under the same conditions. The proposed model achieves 94.30% accuracy and 91.11% F1-score on HAM10000, and 92.50% accuracy and 90.38% F1-score on ISIC 2019, outperforming more than 20 deep learning models and literature. These results indicate that the integration of local and global features plays a critical role in accurately classifying skin lesions and can significantly assist dermatologists in clinical practice. © 2025 Elsevier Ltd

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Container Performance in Space Systems 25th

Container Performance in Space Systems

引用

25th International Conference on Internet Computing and IoT, ICOMP 2024, and 22nd International Conference on Embedded Systems, Cyber-physical Systems, and Applications, ESCS 2024, held as part of the World Congress in Computer Science, Computer engineering and Applied Computing, CSCE 2024

作者： Alamgir, Shariar M. Bohra, Dhruv L. Nguyen, Elisabeth A. Embedded and Specialized Computing Department The Aerospace Corporation El SegundoCA United States Software Architecture and Engineering Department The Aerospace Corporation El SegundoCA United States

ISBN: (纸本)9783031859229

Critical embedded software, such as spacecraft flight software, requires high reliability, efficiency, and real-time performance while being capable enough to meet application needs. The increasing prevalence of Linux, and in particular Linux containers, presents opportunities for space systems but also poses potential risks since Linux was not designed to be a real-time operating system. In this study, we conducted a variety of experiments to look at both the overhead imposed by containers and the latency experienced in Linux using various combinations of patched OS and containers running on a Raspberry Pi 4. We found that containers have little impact on CPU utilization but do incur penalties in RAM, disk storage, and startup time. We also found the unpatched Linux kernel performs well for real time;and that, while the real-time kernel patch reduces both overall and maximum latency, it can negatively impact performance, particularly on single-core systems running non-real-time tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Intrusion Detection System Approach Using PCA and SMOTE with Advanced Ensemble Models

A Hybrid Intrusion Detection System Approach Using PCA and S...

引用

International Conference on Electrical, Computer and Communication engineering (ECCE)

作者： Khaled Mahmud Sujon Nusrat Jahan Someyo Kamal Utsho Mahadi Hasan Shuvo Md Najmus Sakib Razin Department of Software Engineering Universiti Teknologi Malaysia (UTM) Johor Bahru Johor Malaysia Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Department of Software Engineering Universiti Teknologi Malaysia Johor Bahru Johor Malaysia Department of Architecture American International University-Bangladesh Dhaka Bangladesh Department of Electrical & Electronics Engineering Universiti Teknologi Malaysia Johor Bahru Johor Malaysia

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

A persistent issue of class imbalance in intrusion detection systems (IDS) is addressed in this research, particularly in the context of cyber-physical systems and IoT devices. Current IDS approaches often struggle to detect rare attack patterns due to the dominance of normal traffic in imbalanced datasets. To address this, we present a unique strategy that combines Principal Component Analysis (PCA) for selecting features with the Synthetic Minority Oversampling Technique (SMOTE) to deal with class imbalance, applied to four powerful classifiers: Random Forest (RF), Decision Trees (DT), XGBoost (XGB), and AdaBoost. By reducing the feature space with PCA and balancing the dataset with SMOTE, our methodology significantly enhances model performance. Evaluating on the KDDCup ’99 dataset, we observe notable improvements: for instance, Random Forest achieves 96.42% accuracy, 98.52% precision, 94.68% recall 96.55% F1-score, and 93.87% MCC. Similarly, XGBoost achieves 94.78% accuracy, 96.72% precision, 92.94% recall, 94.81% F1-score, and 92.36% MCC. These results demonstrate that the integration of SMOTE and PCA effectively addresses class imbalance and enhances the detection of minority class attacks. Our findings contribute to the advancement of machine learning techniques in IDS and provide a foundation for further research into combining oversampling methods and dimensionality reduction for robust cybersecurity solutions. Future work will focus on exploring alternative oversampling methods, incorporating deep learning models, and assessing the practical deployment of the proposed methodology in real-time network environments.

关键词： Dimensionality reduction Deep learning Accuracy Computational modeling Intrusion detection Real-time systems Decision trees Random forests Principal component analysis Testing

来源：评论

学校读者我要写书评

暂无评论

Explanation Rectification Framework: An Attribution Score Generation Method Based on Standard Explanations

引用

Jisuanji Xuebao/Chinese Journal of Computers 2025年第4期48卷 949-970页

作者： Xing, Zhong-Yu Liang, Jia-Xuan Yu, Guo-Xian Wang, Jun Guo, Mao-Zu Cui, Li-Zhen School of Software Shandong University Jinan250101 China Joint SDU-NTU Centre for Artificial Intelligence Research Shandong University Jinan250101 China School of Intelligence Science and Technology Beijing University of Civil Engineering and Architecture Beijing102616 China

Model interpretability has become increasingly critical in artificial intelligence research, particularly for high-stakes applications where transparency and trustworthiness are paramount. A fundamental challenge in this field emerges from an intriguing phenomenon: models that achieve comparable predictive performance often yield inconsistent feature importance scores (attribution scores interpretations) for identical data. This interpretability dilemma, manifest in both the Rashomon effect set (diverse models with different architectures achieving similar performance) and its subset, the Underspecification set (identical architectures varying due to training randomness), significantly diminishes the credibility of models' explanations. To address this challenge, this paper firstly explores theoretically the relationship between explanation inconsistency and model indeterminacy factors, and then proves that due to the local accuracy property of SHAP (SHapley Additive exPlanation), there exists an upper bound on the uncertainty of SHAP methods for models with similar predictions. On this basis, we thoroughly investigate experimentally the specific impacts of variables (i. e., model training stochastic factors) on various feature attribution methods. It finds that explanation uncertainty arising from model indeterminacy is widespread, whereas SHAP methods exhibit lower uncertainty due to the impact of its upper bound. Based on these findings, we propose an explanation rectification framework called ASGM (Attribution Score Generation Method) to generate stable attribution score explanations using standard explanations obtained from diverse models, aiming to reduce the inconsistency of attribution score explanations and enhance the stability and credibility of model interpretations. ASGM identifies disparities between explanations from several sampled models and standard explanations generated from massive models on specified data. Through bias rectification deep networ

关键词： model indeterminacy rashomon effect set SHAP methods underspecification set XAI

来源：评论

学校读者我要写书评

暂无评论

Magnetic Laponite/P(AM–AA) composite hydrogels with high gel strength and thermal stability for efficient removal of heavy metals

引用

Polymer Bulletin 2025年 1-21页

作者： Huang, Zhenggen Wan, Tao Chen, Yongmei Li, Dongmei Xu, Hao Liu, Bingjun Zhao, Yang College of Materials and Chemistry and Chemical Engineering Chengdu University of Technology Sichuan Chengdu 610059 China National Quality Supervision and Inspection Test Center of Architecture Ceramic Sichuan Leshan 614000 China Wuhan Vocational College of Software and Engineering (Wuhan Open University) Hubei Wuhan 430205 China

Heavy metal wastewater contamination has become one of the greatest global environmental problems. In this study, magnetic Laponite/poly(AA-AM) composite hydrogels (mLap/P(AM–AA)) with multi-level three-dimensional networks were synthesized by radical copolymerization based on poly(acrylamide-co-acrylic acid), Laponite and PEI magnetic nanoparticles. mLap/(AA–AM) with porous and uneven structure has the target structure and composition confirmed by FTIR, FESEM, EDX and XRD results. FTIR and XRD results show that mLap/P(AM–AA) has been successfully prepared without destroying high crystallinity of magnetic Fe₃O₄, and Laponite is dispersed in the polymer matrix with amorphous structure. mLap/P(AM–AA) have high adsorption capacities of Cu(II) (238 mg/g), Cd(II) (259 mg/g) and Pb(II) (466 mg/g) in the condition of initial heavy metal ions of 1000 mg/L and absorbent dose of 0.1 g. The endothermic, entropy increasing and spontaneous nature of heavy metal ion adsorption is revealed from thermodynamic study. Heavy metal ions adsorption isotherms and kinetics are in agreement with the Langmuir model and pseudo-second-order kinetic model, respectively. Laponite within mLap/P(AM–AA) can increase thermal stability, storage modulus and loss modulus as well as adsorption capacities of heavy metals of mLap/P(AM–AA). In addition, mLap/P(AM–AA) has good magnetic response and magnetic solid–liquid separation, which can solve the shortcomings of traditional hydrogels such as insufficient gel strength and heat resistance as well as complicated recovery process, endowing its huge potential application in removing heavy metal ions from the contaminated wastewater. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Adsorption Heavy metal Hydrogel Laponite Magnetic

来源：评论

学校读者我要写书评

暂无评论

Constraint effects on the hydroelasticity of very large floating structures

引用

Ocean engineering 2025年 331卷

作者： Zhang, Guiyong Li, Qiankun Jiang, Changqing el Moctar, Ould Sun, Zhe State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Naval Architecture Engineering Dalian University of Technology Dalian116024 China Institute of Sustainable and Autonomous Maritime Systems University of Duisburg-Essen Duisburg47057 Germany

Offshore structures are continuously subjected to wave-induced loads, resulting in both rigid-body motion and elastic deformation. In very large floating structures (VLFSs), hydroelastic deformation is primarily characterized by vertical displacement, encompassing both oscillatory motion and flexible deflection. Hydroelastic analysis typically involves imposing constraints to restrict body motion in waves, which can significantly influence deformation behavior. To assess the impact of these constraints, this study examines how different boundary conditions affect the hydroelastic response of VLFSs. Specifically, five test cases with distinct constraint conditions are designed to systematically evaluate their effects across multiple wavelengths. A coupled numerical methodology integrating computational fluid dynamics (CFD) and computational structural dynamics (CSD) is developed to analyze hydroelastic deformation under these conditions. Strain distributions at key locations along the floating structure are examined under varying wave conditions. Results indicate that spring constraints provide a stable deformation pattern, aligning well with physical expectations in both long and short waves. This study highlights the critical role of constraint selection in VLFS modeling and suggests that future research should explore multi-directional wave effects and diverse restraint configurations to enhance VLFS design and performance. © 2025 The Author(s)

关键词： Offshore structures

来源：评论

学校读者我要写书评

暂无评论

Towards Expanding Precise Timing for Collaborative Its with Deterministic Communications in 6G

Towards Expanding Precise Timing for Collaborative Its with ...

引用

IEEE Conference on Wireless Communications and Networking

作者： Hongxing Li Haotian Li Qianhan Gao Guochu Shou Yaqiong Liu Zhigang Guo Yihong Hu State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The demand for precise timing continues to grow with the rapid development of smart cities, where intelligent transportation emerges as a critical application heavily dependent on accurate time distribution. Deterministic communication is anticipated to be a defining feature of nextgeneration mobile networks (6G), enabling end-to-end timecritical applications, and unlocking new possibilities for achieving end-to-end precise time synchronization as well. To cope with the challenge of delivering precise time synchronization across broader areas at a lower cost, this paper proposes a method to achieve end-to-end precise time synchronization by leveraging the deterministic characteristics of communication networks. Specially, the proposed approach adopts the software-Defined Networking (SDN) paradigm to implement deterministic networking for the seamless integration of Time-Sensitive Networking (TSN) and cellular networks. Furthermore, to mitigate the impact of wireless channel uncertainties on synchronization accuracy, we propose a network delay measurement mechanism based on the principle of time redundancy, designed to reduce end-to-end network delay variation. Experimental results validate the effectiveness of the proposed method, demonstrating its capability to constrain the end-to-end relative time error of wired and wireless converged networks to the microsecond scale, without necessitating modifications to the existing network infrastructure.

关键词： 6G mobile communication Wireless communication Cellular networks Uncertainty Accuracy Measurement uncertainty Transportation Delays Synchronization software defined networking

来源：评论

学校读者我要写书评

暂无评论

Starfish optimization algorithm (SFOA): a bio-inspired metaheuristic algorithm for global optimization compared with 100 optimizers

引用

Neural Computing and Applications 2025年第5期37卷 3641-3683页

作者： Zhong, Changting Li, Gang Meng, Zeng Li, Haijiang Yildiz, Ali Riza Mirjalili, Seyedali School of Civil Engineering and Architecture Hainan University Haikou570228 China Department of Engineering Mechanics State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment Dalian University of Technology Dalian116024 China Ningbo Institute of Dalian University of Technology No. 26 Yucai Road Jiangbei District Ningbo315016 China School of Civil Engineering Hefei University of Technology Hefei230009 China Jianghuai Advance Technology Center Hefei230000 China BIM for Smart Engineering Centre Cardiff School of Engineering Cardiff University Queen’s Buildings Whales CardiffCF24 3AA United Kingdom Department of Mechanical Engineering College of Engineering Bursa Uludağ University Görükle Bursa16059 Turkey Centre for Artificial Intelligence Research and Optimisation Torrens University Australia Brisbane Australia University Research and Innovation Center Obuda University Budapest1034 Hungary

This work presents the starfish optimization algorithm (SFOA), a novel bio-inspired metaheuristic for solving optimization problems, which simulates behaviors of starfish, including exploration, preying, and regeneration. SFOA consists of two main phases of exploration and exploitation. The exploration phase mimics the explorative behavior of starfish by the hybrid search pattern of combining with the five-dimensional and unidimensional search patterns to increase the computational efficiency and ensure the search capacity. The exploitation phase simulates the preying and regeneration behaviors of starfish, with a two-directional search strategy and special movement, to ensure convergence in exploitation. This work validates SFOA’s performance on 65 benchmark functions from classical functions, CEC 2017 and CEC 2022 test suites, and compares with 100 different metaheuristic algorithms, including state-of-the-art optimizers, such as marine predators algorithm, water flow optimizer (WFO), LSHADE, LSHADE-cnEpSin, and LSHADE-SPACMA. Statistical results from one-on-one comparisons demonstrate that the proposed SFOA outperforms 95 compared algorithms in accuracy and 97 algorithms in efficiency, which is only worse than WFO both in accuracy and efficiency. The scalability analysis also demonstrates that SFOA has the capacity to solve high-dimensional benchmark functions. Furthermore, ten real-world engineering optimization problems illustrate the effectiveness of SFOA to achieve global solutions and exhibit stable results. In conclusion, SFOA is promising for solving various optimization problems. The source code of SFOA is publicly available at: https://***/matlabcentral/fileexchange/173735-starfish-optimization-algorithm-sfoa. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Semantic Segmentation Tasks in Autonomous Driving: A Likelihood Active Inference Approach

Resource Allocation for Semantic Segmentation Tasks in Auton...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xinxin Zhu F. Richard Yu Ying He Biao He College of Computer Science and Software Engineering Shenzhen University China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Research Institute for Smart Cities School of Architecture and Urban Planning Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The latest Segment Anything Model enables realtime scene annotation and understanding for autonomous driving systems, enhancing driving safety. However, effectively allocating resources for real-time performance and accuracy remains challenging in edge-cloud architectures. Traditional reinforcement learning struggles with poor generalization and the explorationexploitation dilemma, making it difficult to define clear reward functions. To address this, we propose a likelihood active inference approach to optimize resource allocation and improve system resource utilization. We use "intelligence" as a high-level indicator to quantify the efficiency of cognition in active inference, evaluating the difference between predicted and actual states during policy exploration. Experimental results show our algorithm outperforms mainstream deep reinforcement learning algorithms, improving sample efficiency and suitability for dynamically changing task workloads.

关键词： Accuracy Heuristic algorithms Signal processing algorithms Signal processing Prediction algorithms Inference algorithms Real-time systems Resource management Speech processing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Frequency-dependent elastic wave filtration and separation by hexagonal topological phononic crystals

引用

Composite Structures 2025年 368卷

作者： Wang, Guifeng Guan, Yanhong Chen, Zhenyu Zhou, Zhenhuan Xu, Xinshen Lim, C.W. Chen, Weiqiu Department of Architecture and Civil Engineering City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment School of Mechanics and Aerospace Engineering Dalian University of Technology Dalian China School of Civil Engineering Southeast University Nanjing China Department of Engineering Mechanics Zhejiang University Hangzhou310027 China

Ascribe to the research significance and great application potential of elastic wave manipulation, the topological phononic crystals with peculiar functions in robust waveguiding have attracted enormous research attention. High-dimensional, higher-order, multifunctional, intelligent, and multi-frequency topological structures are expected to be a prominent research focus in the coming decades, while grand challenges still exist in designing such devices. In this regard, this paper presents a hexagonal lattice structure with six internally connected cylinders. Utilizing the accidental Dirac cones, the separate control of closing/opening and topological phases of three bandgaps at different frequencies is achieved. The subsequent parametric analyses reveal the whole picture of valley Chern numbers variation in the parametric space, which helps summarize the design principles of frequency-dependent topologically protected interface modes. Several superstructures consisting of two types of unitcells are then constructed to achieve the waveguiding in a straight path and frequency-dependent wave filtration. Consequently, introducing more types of unitcells can form interfaces that support waveguiding at different frequencies, leading to the realization of frequency-dependent wave separation and demultiplex. The presented work in this paper not only offers a novel design for multi-frequency wave separation and filtration but also inspires further explorations in multi-functional integrated elastic wave processors. © 2025 The Author(s)

关键词： Elastic waves

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：