检索结果-内蒙古大学图书馆

DieT Transformer model with PCA-ADE integration for advanced multi-class brain tumor classification

Intelligence-Based Medicine 2025年 11卷 100192-100192页

作者： Amin, Mohammad Nahar, Khalid M.O. Gharaibeh, Hasan Nasayreh, Ahmad Alsalmanc, Neda'a Alomar, Alaa Malkawi, Majd Alqasem, Noor Smerat, Aseel Zitar, Raed Abu Nusier, Shawd Ezugwu, Absalom E. Abualigah, Laith Department of Information Technology and Computer Sciences Yarmouk University Irbid 211633 Jordan Faculty of Computer Studies Arab Open University P.O.Box 84901 Riyadh 11681 Saudi Arabia Department of Computer Science Faculty of Information Technology Jordan University of Science and Technology Irbid 22110 Jordan Department of Medicine Faculty of Medicine Jordan University of Science and Technology Irbid 22110 Jordan Department of Biomedical Systems and Informatics Engineering Hijjawi Faculty for Engineering Technology Yarmouk University Irbid 21163 Jordan Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India Artificial Intelligence and Sensing Technologies (AIST) Research Center University of Tabuk Tabuk 71491 Saudi Arabia Faculty of Engineering and Computing Liwa College Abu Dhabi United Arab Emirates Department of Health and Clinical Outcomes Research Saint Louis University St. Louis MO United States Unit for Data Science and Computing North-West University 11 Hofman Street Potchefstroom 2520 South Africa Computer Science Department Al al-Bayt University Mafraq 25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan

Early and accurate diagnosis of brain tumors is crucial to improving patient outcomes and optimizing treatment strategies. Long-term brain injury results from aberrant proliferation of either malignant or nonmalignant tissues in the brain. MRIs, or magnetic resonance imaging, are one of the most used approaches for detecting brain tumors. Professionals physically evaluate people after they have had MRI filtering, the process of enhancing MRI scans for radiologist interpretation, to establish if they have a brain tumor. Because different specialists use different frames to make judgments on the same MRI image, their analyses may yield contradictory results. Furthermore, simply detecting a tumor is insufficient. Inconsistent diagnoses can lead to delays in treatment, impacting survival rates and quality of care. It is also crucial to diagnose the patient's tumor so that treatment can begin as soon as possible. In this research, we investigate the multi-class classification of brain tumors utilizing a cutting-edge methodology that includes feature extraction from pictures using the DieT Transformer model, dimensionality reduction with PCA, and feature selection using the ADE algorithm. The proposed model, known in the publication as ADE_DieT, obtained an accuracy of 96.09 %. In addition, this article analyzes the performance of various pre-trained models, including MobileNetV3, NasNet, ResNet50, VGG16, VGG19, and DeiT. The proposed approach shortens the time required for manual diagnosis by clinicians by assisting in the rapid and accurate identification of brain tumors using MRI data. In oncology, this is important since it allows for early treatment. Integrating ADE_DieT into clinical workflows can support radiologists by reducing diagnosis time and enhancing diagnostic consistency. © 2024 The Authors

关键词： Brain tumor Medical image analysis MRI Vision Transformer

来源：评论

学校读者我要写书评

暂无评论

Collaborative Perception datasets for Autonomous Driving: A Review

arXiv

引用

arXiv 2025年

作者： Wang, Naibang Shang, Deyong Gong, Yan Hu, Xiaoxi Song, Ziying Yang, Lei Huang, Yuhan Wang, Xiaoyu Lu, Jianli Beijing100083 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China State Key Laboratory of Intelligent Green Vehicle and Mobility Tsinghua University Beijing100084 China Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence School of Computer Science and Technology Beijing Jiaotong University China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore School of Mechatronics Engineering Harbin Institute of Technology 92 West Dazhi St. Harbin China Department of Electronic & Electrical Engineering University of Bath United Kingdom

Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the advancement of Vehicle-to-Everything (V2X) communication, numerous collaborative perception datasets have emerged, varying in cooperation paradigms, sensor configurations, data sources, and application scenarios. However, the absence of systematic summarization and comparative analysis hinders effective resource utilization and standardization of model evaluation. As the first comprehensive review focused on collaborative perception datasets, this work reviews and compares existing resources from a multi-dimensional perspective. We categorize datasets based on cooperation paradigms, examine their data sources and scenarios, and analyze sensor modalities and supported tasks. A detailed comparative analysis is conducted across multiple dimensions. We also outline key challenges and future directions, including dataset scalability, diversity, domain adaptation, standardization, privacy, and the integration of large language models. To support ongoing research, we provide a continuously updated online repository of collaborative perception datasets and related literature: https://***/frankwnb/Collaborative-Perceptio n-datasets-for-Autonomous-Driving. © 2025, CC BY-SA.

关键词： Sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

A USER-TUNABLE MACHINE LEARNING FRAMEWORK FOR STEP-WISE SYNTHESIS PLANNING

arXiv

引用

arXiv 2025年

作者： Prakash, Shivesh Jacobsen, Hans-Arno Prasad, Viki Kumar Department of Computer Science University of Toronto 40 St George St TorontoONM5S 2E4 Canada The Edward S. Rogers Sr. Department of Electrical & Computer Engineering University of Toronto 10 King’s College Rd TorontoONM5S 3G8 Canada Data Sciences Institute University of Toronto 700 University Ave 10th floor TorontoONM7A 2S4 Canada

We introduce MHNPATH, a machine learning-driven retrosynthetic tool designed for computer-aided synthesis planning. Leveraging modern Hopfield networks and novel comparative metrics, MHNPATH efficiently prioritizes reaction templates, improving the scalability and accuracy of retrosynthetic predictions. The tool incorporates a tunable scoring system that allows users to prioritize pathways based on cost, reaction temperature, and toxicity, thereby facilitating the design of greener and cost-effective reaction routes. We demonstrate its effectiveness through case studies involving complex molecules from ChemByDesign, showcasing its ability to predict novel synthetic and enzymatic pathways. Furthermore, we benchmark MHNPATH against existing frameworks, replicating experimentally validated "gold-standard" pathways from PaRoutes. Our case studies reveal that the tool can generate shorter, cheaper, moderate-temperature routes employing green solvents, as exemplified by compounds such as dronabinol, arformoterol, and lupinine. © 2025, CC BY-SA.

关键词： computer systems programming

来源：评论

学校读者我要写书评

暂无评论

Enhancing Knee Contact Force Prediction Using Transformer Networks: A Comparative Study with Lstm and Mlp

SSRN

引用

SSRN 2025年

作者： Xu, Fashu Wang, Junqing Tong, Bingkui Fang, Xuyi Zhang, Hui Deng, Tao Wei, Qu Nie, Yong Li, Kang Department of Orthopedic Surgery West China Biomedical Big Data Center West China Hospital Sichuan University Sichuan Chengdu China Department of Orthopedic Surgery Orthopedic Research Institute West China Hospital Sichuan University Sichuan Chengdu China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang China College of Computer Science Sichuan University Sichuan Chengdu China College of Electrical Engineering Sichuan University Sichuan Chengdu China School of Mechanical Engineering Sichuan University Sichuan Chengdu China

Background and objectiveKnee contact force (KCF) is pivotal in both the study and degenerative pathologies like Knee Osteoarthritis. Traditionally, they are primarily estimated using musculoskeletal modeling and machine learning predictive algorithms. However, musculoskeletal modeling is limited by intricate experimental protocols, prohibitive equipment cost, and scalability challenges. While machine learning methods, though computationally efficient, exhibit suboptimal predictive accuracy. This study innovatively developed a Transformer model for predicting KCF, benchmarked against long short-term memory (LSTM) and multilayer perceptron (MLP) *** comprehensive database was constructed with gait data from 513 participants, incorporating three degrees of freedom of hip, knee flexion/extension, and ankle dorsiflexion/plantarflexion, constituting four input combinations for the models. Contact forces derived from OpenSim served as the ground truth. Root mean square error (RMSE) and coefficient of determination (R2) were used to evaluate the performance of *** results indicated that the Transformer model demonstrated superior performance, achieving a significantly lower mean root mean square error of 0.02 body weight (BW) compared to MLP (0.54 BW) and LSTM (0.45 BW). Furthermore, the mean R2 of the Transformer network (0.99) was markedly superior to that of MLP (0.45) and LSTM (0.58).ConclusionsThe application of Transformer networks significantly improved the accuracy of KCF prediction, addressing the limitations of traditional musculoskeletal modeling and existing machine learning approaches, which was of paramount importance in both clinical practice and biomechanical research. © 2025, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Optimized Consensus for Blockchain in Internet of Things Networks via Reinforcement Learning

引用

Tsinghua science and Technology 2023年第6期28卷 1009-1022页

作者： Yifei Zou Zongjing Jin Yanwei Zheng Dongxiao Yu Tian Lan Institute of Intelligent Computing School of Computer Science and TechnologyShandong UniversityQingdao 266237China Department of Electrical and Computer Engineering George Washington UniversityWashingtonDC 20052USA

Most blockchain systems currently adopt resource-consuming protocols to achieve consensus between miners;for example,the Proof-of-Work(PoW)and Practical Byzantine Fault Tolerant(PBFT)schemes,which have a high consumption of computing/communication resources and usually require reliable communications with bounded ***,these protocols may be unsuitable for Internet of Things(IoT)networks because the IoT devices are usually lightweight,battery-operated,and deployed in an unreliable wireless ***,this paper studies an efficient consensus protocol for blockchain in IoT networks via reinforcement ***,the consensus protocol in this work is designed on the basis of the Proof-of-Communication(PoC)scheme directly in a single-hop wireless network with unreliable communications.A distributed MultiAgent Reinforcement Learning(MARL)algorithm is proposed to improve the efficiency and fairness of consensus for miners in the blockchain *** this algorithm,each agent uses a matrix to depict the efficiency and fairness of the recent consensus and tunes its actions and rewards carefully in an actor-critic framework to seek effective *** results from the simulation show that the fairness of consensus in the proposed algorithm is guaranteed,and the efficiency nearly reaches a centralized optimal solution.

关键词： consensus in blockchain Proof-of-Communication(PoC) MultiAgent Reinforcement Learning(MARL) Internet of Things(IoT)networks

来源：评论

学校读者我要写书评

暂无评论

Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound

arXiv

引用

arXiv 2025年

作者： Huang, Yuhao Chang, Ao Dou, Haoran Tao, Xing Zhou, Xinrui Cao, Yan Huang, Ruobing Frangi, Alejandro F. Bao, Lingyun Yang, Xin Ni, Dong National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Lab Shenzhen University Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen China School of Computing University of Leeds Leeds United Kingdom Shenzhen RayShape Medical Technology Co. Ltd Shenzhen China Division of Informatics Imaging and Data Science School of Health Sciences University of Manchester Manchester United Kingdom Department of Computer Science School of Engineering University of Manchester Manchester United Kingdom Department of Electrical Engineering Department of Cardiovascular Sciences KU Leuven Belgium Alan Turing Institute London United Kingdom NIHR Manchester Biomedical Research Centre Manchester Academic Health Science Centre Manchester United Kingdom Department of Ultrasound Affiliated Hangzhou First People’s Hospital School of Medicine Westlake University China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China

Accurate segmentation of nodules in both 2D breast ultrasound (BUS) and 3D automated breast ultrasound (ABUS) is crucial for clinical diagnosis and treatment planning. Therefore, developing an automated system for nodule segmentation can enhance user independence and expedite clinical analysis. Unlike fully-supervised learning, weakly-supervised segmentation (WSS) can streamline the laborious and intricate annotation process. However, current WSS methods face challenges in achieving precise nodule segmentation, as many of them depend on inaccurate activation maps or inefficient pseudo-mask generation algorithms. In this study, we introduce a novel multi-agent reinforcement learning-based WSS framework called Flip Learning, which relies solely on 2D/3D boxes for accurate segmentation. Specifically, multiple agents are employed to erase the target from the box to facilitate classification tag flipping, with the erased region serving as the predicted segmentation mask. The key contributions of this research are as follows: 1) Adoption of a superpixel/supervoxel-based approach to encode the standardized environment, capturing boundary priors and expediting the learning process. 2) Introduction of three meticulously designed rewards, comprising a classification score reward and two intensity distribution rewards, to steer the agents’ erasing process precisely, thereby avoiding both under- and over-segmentation. 3) Implementation of a progressive curriculum learning strategy to enable agents to interact with the environment in a progressively challenging manner, thereby enhancing learning efficiency. Extensively validated on the large in-house BUS and ABUS datasets, our Flip Learning method outperforms state-of-the-art WSS methods and foundation models, and achieves comparable performance as fully-supervised learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive distributed honeypot detection network for enhanced cybersecurity against DoS and DDoS attacks

引用

Results in engineering 2025年 26卷

作者： V. Selva Kumar K.R. Mohan Raj S. Gopalakrishnan G. Vennila D. Dhinakaran P. Kavitha Department of Computer Science and Engineering P.S.R. Engineering College Sivakasi India Department of Information Technology Velammal Engineering College Chennai India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh India Department of Artificial Intelligence and Machine Learning School of Computing Mohan Babu University Tirupati India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering R.M.K. Engineering college Chennai India

The increasing prevalence and sophistication of Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks present significant challenges in ensuring the security and stability of modern networked systems. These attacks, characterized by their ability to disrupt services and compromise resources, require innovative and robust detection mechanisms to safeguard highly interactive environments such as honeypot systems. Traditional detection techniques often fall short in addressing the complexities posed by dynamic traffic patterns, diverse attack types, and real-time processing demands. This study introduces the Adaptive Distributed Honeypot Detection Network (ADHDN), a novel framework that leverages deep learning and probabilistic modeling to address the limitations of existing solutions. ADHDN employs a combination of Deep Generative Adversarial Networks (DGANs) and Discrete Hidden Markov Models (DHMMs) to achieve superior detection precision across various DoS attack types, including application-level, protocol-level, and data volume attacks. Implemented in a highly interactive honeypot environment with distributed server and virtual machine configurations, ADHDN demonstrates remarkable adaptability and resilience. Performance evaluation using the IoTID20 dataset reveals that ADHDN consistently outperforms contemporary models, such as RBMD, BNDH, and AHDL. ADHDN achieves a true positive rate of 99.7% for protocol-level attacks, 99.4% for application-level attacks, and 97.5% for data volume attacks under low attack volumes, maintaining robust performance even as attack intensity scales. These results underscore ADHDN’s potential to redefine DoS detection in dynamic and high-interaction environments, offering a scalable and efficient solution to contemporary cybersecurity challenges.

关键词： Denial of service Distributed denial of service Intrusion detection systems Generative adversarial networks Real-time attack detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

RPF-Net: A multimodal model for the postoperative UISS risk stratification of non-metastatic ccRCC based on CT and whole-slide images

引用

computer Methods and Programs in Biomedicine 2025年 268卷 108836-108836页

作者： Mao, Jiahui Li, Wuchao Sun, Xinhuan Fu, Bangkang He, Junjie Yan, Chongzhe Zhu, Jianguo Zhang, Zhuxue Mao, Jiahui Hong, Zhangxin Tang, Qi Liu, Zhen Li, Pinhao Zhang, Yan Wang, Rongpin Medical College Guizhou University Guiyang550025 China Department of Radiology International Exemplary Cooperation Base of Precision Imaging for Diagnosis and Treatment Guizhou Provincial People's Hospital Guiyang550002 China CETC Big Data Research Institute Co. Ltd. Guizhou550022 China National Engineering Research Center of Big Data Application to Improvement of Governance Capacity Guizhou550022 China Department of Pathology Guizhou Provincial People's Hospital Guiyang550002 China Department of Urinary Guizhou Provincial People's Hospital Guiyang550002 China Department of Pathology Affiliated Hospital of Guizhou Medical University Guiyang550002 China Department of Imaging Affiliated Hospital of Guizhou Medical University Guiyang550002 China Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences Suzhou215163 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai 200082 China

Background and objectives: Postoperative non-metastatic clear cell renal cell carcinoma (nccRCC) patients face the risk of tumor recurrence and metastasis. However, prognosis assessment for nccRCC remains time-consuming and subjective. In the current diagnostic landscape, computed tomography (CT) images provide macro-scale anatomical information, and whole-slide images (WSIs) offer micro-scale details that are inaccessible to CT imaging. To address this gap, the study proposes a multimodal approach that leverages both CT and WSI data to develop an automated model for postoperative risk stratification in nccRCC. Methods: This study proposes a multimodal model named the Radiology-Pathology Fusion Network (RPF-Net), which employs self-attention, graph-attention, and dynamic attention fusion mechanisms to integrate CT images and WSIs for classifying nccRCC patients into low-risk and intermediate-high-risk groups per the University of California, Los Angeles, Integrated Staging System (UISS) criteria. The proposed model is divided into three steps. First, the ResNet-50 and 3D ResNet-50 are used as feature extractors to respectively extract representative feature maps from WSIs and CT images. Second, a dual-branch module is designed to extract global and local features of the WSIs. Finally, a multilayer dynamic attention fusion (MDAF) module is developed to facilitate cross-modal feature interaction and predict the risk stratification results. Results: The area under the curve (AUC), accuracy, precision, and F1 Score of the RPF-Net on the internal validation set are 0.949±0.013, 0.894±0.019, 0.895±0.020, and 0.894±0.019, respectively. Furthermore, the RPF-Net shows robust generalization, achieving an AUC of 0.901 on the external validation set and 0.924 on the public dataset. Conclusions: The RPF-Net models the diagnostic process of multimodal data and shows strong generalization and excellent performance. This model may be a potential tool to facilitate clinical risk str

关键词： Non-metastatic clear cell renal cell carcinoma Computed tomography Whole-slide image UISS Multimodal model

来源：评论

学校读者我要写书评

暂无评论

Foundation Models for Atomistic Simulation of Chemistry and Materials

arXiv

引用

arXiv 2025年

作者： Yuan, Eric C.-Y. Liu, Yunsheng Chen, Junmin Zhong, Peichen Raja, Sanjeev Kreiman, Tobias Vargas, Santiago Xu, Wenbin Head-Gordon, Martin Yang, Chao Blau, Samuel M. Cheng, Bingqing Krishnapriyan, Aditi Head-Gordon, Teresa Kenneth S. Pitzer Theory Center Department of Chemistry United States Department of Chemical and Biomolecular Engineering United States Electrical Engineering and Computer Science United States Bakar Institute of Digital Materials for the Planet University of California BerkeleyCA94720 United States Chemical Sciences Division United States Applied Mathematics and Computational Research Division United States Energy Technologies Area United States National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

Given the power of large language and large vision models, it is of profound and fundamental interest to ask if a foundational model based on data and parameter scaling laws and pre-training strategies is possible for learned simulations of chemistry and materials. The scaling of large and diverse datasets and highly expressive architectures for chemical and materials sciences should result in a foundation model that is more efficient and broadly transferable, robust to out-of-distribution challenges, and easily fine-tuned to a variety of downstream observables, when compared to specific training from scratch on targeted applications in atomistic simulation. In this Perspective we aim to cover the rapidly advancing field of machine learned interatomic potentials (MLIP), and to illustrate a path to create chemistry and materials MLIP foundation models at larger scale. © 2025, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Matching Based Escape Routing Algorithm With Variable Design Rules and Multiple Constraints

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Chen, Chuandong Lin, Disi Liu, Qinghai He, Huan Lin, Zhifeng Liu, Genggeng Chen, Jianli Chang, Yao-Wen Fuzhou University Department of Microelectronics Fuzhou350108 China Fuzhou University Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China Center for Applied Mathematics of Fujian Province Center for Discrete Mathematics Fuzhou350108 China Hangzhou Huawei Enterprises Telecommunication Technologies Co. Ltd Hangzhou310000 China Fuzhou University Center for Discrete Mathematics and Theoretical Computer Science Fuzhou350108 China Fuzhou University College of Computer and Data Science Fuzhou350108 China Fudan University School of Microelectronics Shanghai200433 China National Taiwan University Department of Electrical Engineering Graduate Institute of Electronics Engineering Taipei106 Taiwan

Escape routing is a critical problem in PCB routing, and its quality dramatically affects the cost of the PCB design. Unlike the traditional escape routing that works mainly for the BGA with unique line width and space, this paper presents a high-performance escape routing algorithm to handle problems with variable design rules and multiple constraints. We first propose a novel obstacle-avoiding method to project pins to the boundary and construct a channel projection graph combined with a channel merging technique to handle complex irregular packages. We then construct a bi-projection graph and propose a matching-based hierarchical sequencing algorithm to consider manual constraints. We perform global routing for each pin/differential pair by congestion-avoiding path initializing and rip-up and reroute path optimizing. Finally, a length-aware detail routing algorithm is developed to optimize the line length while ensuring the differential pair constraints. The experimental results on industrial PCB instances show that our algorithm can achieve 100% routability without violating the design rules and constraints, while two state-of-the-art PCB routers, FreeRouting and Allegro, cannot complete escape routing. © 1982-2012 IEEE.

关键词： Printed circuit design

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：