检索结果-内蒙古大学图书馆

arXiv 2025年

作者： He, Yuting Wang, Boyu Ge, Rongjun Chen, Yang Yang, Guanyu Li, Shuo Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Nanjing China School of Instrument Science and Engineering Southeast University Nanjing China Department of Computer Science Western University LondonONN6A 3K7 Canada Department of Biomedical Engineering Department of Computer and Data Science Case Western Reserve University ClevelandOH44106 United States

Dense contrastive representation learning (DCRL) has greatly improved the learning efficiency for image dense prediction tasks, showing its great potential to reduce the large costs of medical image collection and dense annotation. However, the properties of medical images make unreliable correspondence discovery, bringing an open problem of large-scale false positive and negative (FP&N) pairs in DCRL. In this paper, we propose GEoMetric vIsual deNse sImilarity (GEMINI) learning which embeds the homeomorphism prior to DCRL and enables a reliable correspondence discovery for effective dense contrast. We proposes a deformable homeomorphism learning (DHL) which models the homeomorphism of medical images and learns to estimate a deformable mapping to predict the pixels’ correspondence under the condition of topological preservation. It effectively reduces the searching space of pairing and drives an implicit and soft learning of negative pairs via gradient. We also proposes a geometric semantic similarity (GSS) which extracts semantic information in features to measure the alignment degree for the correspondence learning. It will promote the learning efficiency and performance of deformation, constructing positive pairs reliably. We implement two practical variants on two typical representation learning tasks in our experiments. Our promising results on seven datasets which outperform the existing methods show our great superiority. We will release our code at a companion website. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Green IoT Edge Computing Towards Sustainable and Distributed data Processing

Green IoT Edge Computing Towards Sustainable and Distributed...

引用

IEEE UP Section Conference on Electrical computer and Electronics (UPCON)

作者： K.R. Ananth Hari Shankar Punna Krishnamoorthy Selvaraj Rajagopal K Vaishali Mahajan Sakthivel S. Department of Computer Science (Artificial Intelligence and Data Science) Nandha Arts and Science College Erode Tamilnadu Department Of CSE CVR College Of Engineering (An Autonomous Institution) Telangana Department of ERP Keller Marketing Symbiosis Centre for Management & Human Resource Development (SCMHRD) Pune Maharashtra Marketing Symbiosis Centre for Management & Human Resource Development (SCMHRD) Pune Maharashtra Department of Computer Applications K.S.Rangasamy College of Arts and Science Tiruchengode Tamilnadu

data creation in the network's periphery has increased exponentially as IoT devices have become more commonplace. To address the challenges this large data deluge poses, sustainable and efficient data processing technologies are required. The term “Green IoT Edge Computing” refers to a new strategy that uses distributed data processing and renewable energy to improve the efficiency and longevity of Internet of Things (IoT) applications. In the Internet of Things (IoT), edge computing is used to process data locally, at the network's periphery, rather than forwarding it to a centralized data center. This method improves real-time decision-making, minimizes network latency, and helps preserve bandwidth. However, in locations with limited access to power or other resources, the high power consumption of edge computing devices continues to be a major issue. Green IoT edge computing addresses this challenge by combining renewable energy sources like solar panels and wind turbines with traditional edge computing facilities. This guarantees low- impact and long-term power for edge devices, cutting down on their environmental impact and operational expenses. This strategy harmonizes IoT operations with environmental sustainability targets by utilizing renewable energy sources. The ability to handle data in a distributed manner is also crucial to green IoT edge computing. Rather than a centralized server, a distributed group of edge devices processes data. This improves energy efficiency as well as fault tolerance and dependability. Edge devices working together to properly spread processing activities can reduce the demand for powerful, energy-hungry servers. Green IoT Edge Computing's primary invention is the “Renewable Edge Optimizer.” This clever piece of code automatically adjusts data processing tasks in accordance with the availability of renewable power. When clean energy is plentiful, the optimizer may shift more data processing to distributed nodes, relieving press

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Operations through Machine Learning: Opportunities and Challenges

Optimizing Supply Chain Operations through Machine Learning:...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： D. Santhakumar Gopalakrishnan Soundararajan Suman Chintala E. Bharath Krishna Murthy Inumula Kuldeep Chouhan Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam – Chennai Tamil Nadu Muscat College Ruwi Sultanate of Oman Business Intelligence Architect USA Department of Artificial Intelligence & Data Science C K College of Engineering & Technology Anna University Cuddalore Tamil Nadu Symbiosis Institute of International Business (SIIB) Symbiosis International (Deemed University) Pune Maharashtra India Department of Computer Science and Applications Sharda School of Engineering and Technology Sharda University Greater Noida India

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

In order to create enduring partnerships that are essential to attaining long-term economic success, supply chain management, or SCM, is essential. Strict standards and decision-making procedures are necessary for efficient SCM, and they have a big influence on the final results. In order to efficiently manage inventory levels and logistical procedures, this study offers a complex ML system that combines demand forecasts and optimisation methods. For predicting demand, the approach uses a Generative Adversarial Networks (GAN) model, taking advantage of its capacity to process time-series data and identify intricate trends. The algorithm achieves an impressive 96.4% forecasting of demand accuracy by examining extensive historical sales data and a variety of supply chain variables. In order to optimise inventory rules, the investigation also uses optimisation techniques, particularly Genetic Algorithms (GA) in conjunction with Simulated Annealing (SA). The model demonstrated significant improvements when implemented to an actual commercial logistics system. Notably, it reduced storage expenses by 19% and increased order fulfillment rates by 24%, proving its capacity for combining service standards with financial efficiency. The findings highlight the significant impact of ML on improving supply chain efficiency and show how it can result in significant cost savings and improve service quality.

关键词： Supply chain management Costs Accuracy Supply chains Demand forecasting Machine learning Predictive models Generative adversarial networks Standards Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Empowering Breast Cancer Detection with AI: A Modified Support Vector Machine Approach for Improved Classification Accuracy

Empowering Breast Cancer Detection with AI: A Modified Suppo...

引用

Expert Clouds and applications (ICOECA), International Conference on

作者： Suresh Palarimath Pyingkodi Maran Thenmozhi K K.V. Shiny T Sujatha Wilfred Blessing N.R Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman Department of Computer Applications Kongu Engineering College Erode India Department of Compute Science Kristu Jayanti College (Autonomous) Bengaluru India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Artificial Intelligence and Data Science Sri Krishna College of Engineering and Technology Coimbatore India Information Technology Department College of Computing and Information Sciences Univesity of Technology and Applied Sciences Ibri Sultanate of Oman

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

Breast cancer poses a significant threat to women's health, being a leading cause of cancer-related mortality among female population. In recent years, machine learning has emerged as a promising approach in medical field, particularly in detection and classification tasks. However, existing algorithms often exhibit suboptimal accuracy, necessitating improved methodologies. This research presents a novel approach using a Modified Support Vector Machine (MSVM) for breast cancer classification into benign and malignant categories. Leveraging the Wisconsin Breast Cancer dataset (WBCD), preprocessing techniques are applied to enhance data quality. Principle Component Analysis (PCA) reduces dimensionality, while linear Discriminant Analysis (LDA) extracts discriminative features crucial for classification. The proposed MSVM classifier achieves exceptional performance, with a classification accuracy of 99.42%, outperforming other existing methods such as Deep Convolutional Neural Networks and Fuzzy Rule-based Systems. These results highlight the efficacy of the MSVM approach in accurately distinguishing between benign and malignant breast cancer cases, showcasing its potential as a reliable tool for medical image analysis and cancer diagnosis.

关键词： Support vector machines Accuracy Sociology Machine learning Feature extraction Breast cancer Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Elevating Digital Experiences by Enhancing Service Delivery through Revolutionary Cloud Services and applications

Elevating Digital Experiences by Enhancing Service Delivery ...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： V Asha S Sreekanth Ginni Nijhawan K. Varada Rajkumar Monica Garg Ali Abduhussien Hameed Department of Computer Applications New Horizon College of Engineering Bangalore India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana India Lloyd Law College Plot No. 11 Knowledge Park II Greater Noida Uttar Pradesh Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

This research introduces an approach named “Cloud-Driven Personalized Experience Enhancement” to satisfy the escalating demand for enhanced digital connectivity. Via cutting-edge cloud services and applications, the CPExE framework provides a groundbreaking solution for digital platforms. The framework is built upon three core components: Together with the Quantum-Inspired data Analytics and Evaluation (QIDAE) and Personalized Content Recommendations (PRA), Dynamic Resource Allocation and Adaptation (DRAA) completes the framework. By leveraging quantum-inspired approaches, QIDAE analyzes vast datasets with outstanding effectiveness and exactness improving processes for data handling and personalization. This strategy allows for swift detection of patterns while making certain that data-driven understandings are both on time and precise. By changing cloud resources according to user requests the DRAA module guarantees uninterrupted access to computing power and data storage. By managing resources effectively in real-time it decreases latency and improves service speeds. By using complex algorithms to assess user habits and choices the PRA system boosts the digital experience. PRA uses both content-focused filtering and collaborative screening strategies to provide users with engaging content that matches their unique preferences. By applying sophisticated analytics and resource management methods with content personalization CPExE boosts the user experience and develops cloud technology efficiency. This framework signifies an important progress toward developing dynamic and tailored online environments.

关键词： Heating systems Histograms data analysis Heuristic algorithms Scalability Memory Dynamic scheduling Real-time systems User experience Resource management

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Contagion and Submerged Infections During the Second Wave of The SARS-CoV-2 Epidemic in the Italian Regions

Research Square

引用

Research Square 2021年

作者： Cereda, Giulia Viscardi, Cecilia Gherardini, Luca Mealli, Fabrizia Baccini, Michela Department of Statistics Computer Science Applications University of Florence Italy Florence Center for Data Science University of Florence Italy

After the SARS-CoV-2 outbreak in spring 2020, Italy faced a second epidemic wave in autumn. Using a SIRD model calibrated on COVID19-related deaths, we describe the regional epidemic dynamics from August to November 2020. We explore the time-varying reproductive number, R0(t), and quantify the number of infections, included their submerged portion, under different infection fatality rate scenarios. Results indicate that during the second epidemic wave, R0(t) changed over time heterogeneously across regions, with some important common elements including a mid-October peak and a decline during November, which suggest the possible role in inflating or deflating the contagion rate of specific events (e.g. schools reopening, regional elections) and of the restrictions imposed at the national and local level to reduce the infection spread. Despite the decline of R0(t) in most regions, the prevalence of circulating infections estimated at the end of the study period was not negligible, in particular in the North of the country. This suggests that even small increases of R0(t) in December may lead in a short time to unsustainable levels of contagion spread, depending on the regional supply of hospital and ICU beds and healthcare services throughout the territory. © 2021, CC BY.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Traffic Incident Detection using Factor Analysis and Weighted Random Forest Algorithm

An Enhanced Traffic Incident Detection using Factor Analysis...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： P. Rajesh Kanna S. Vanithamani P. Karunakaran P. Pandiaraja N. Tamilarasi P. Nithin Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode Tamil Nadu India Department of Master of Computer Applications M. Kumarasamy College of Engineering Karur Tamil Nadu India Department of Artificial Intelligence and Data Science Nandha Engineering College Erode Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Nehru Institute of Technology Coimbatore Tamil Nadu India Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Erode Tamil Nadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Efficient and precise traffic incident detection is essential to reduce casualties and property damage. To address the issue of unbalanced event data, this work offers a novel methodology known as FA-WRF (Factor Analysis and Weighted Random Forest). This approach combines dimensionality reduction through factor analysis with classification using weighted random forests, data preparation through the Synthetic Minority Over-Sampling Technique (SMOTE), and data preparation with SMOTE. The included feature of severity detection is highlighted, as are the performance metrics of the FA-WRF model using well-established metrics such as detection level rate, number of false count alarm rate, classification type rate, and area specification under the receiver operating characteristic curve (AUC). The superiority of the FA-WRF model is illustrated using real-world expressway traffic data represented by imbalanced incidents through thorough comparisons with various machine learning-based algorithms such as Support Vector Machine, k-nearest neighbours algorithms, Logistic Regression algorithms, and decision-making trees. In addition to advancing incident detection, this technique has encouraging prospects for enhancing traffic management procedures and well-informed decision-making procedures in transportation networks.

关键词： Measurement Support vector machines Logistic regression Machine learning algorithms Decision making Transportation Receivers data models Classification algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Machine learning-driven conservative-to-primitive conversion in hybrid piecewise polytropic and tabulated equations of state

arXiv

引用

arXiv 2024年

作者： Kacmaz, Semih Haas, Roland Huerta, E.A. Department of Physics University of Illinois Urbana-Champaign UrbanaIL61801 United States National Center for Supercomputing Applications University of Illinois Urbana-Champaign UrbanaIL61801 United States Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science The University of Chicago ChicagoIL60637 United States

We present a novel machine learning (ML) method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch and optimized for GPU inference using NVIDIA TensorRT, achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves L1 and L∞ errors of 4.54×10−7 and 3.44×10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (Dual AMD 64 core 2.45 GHz Milan processors;and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally-parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. This work underscores the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Effective Short Packet Communication for Resource Allocation In Wireless Powered Iot Networks

Effective Short Packet Communication for Resource Allocation...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： K Selvi D Kanchana R Sankar B Anni Princy S Saravanan A Balamurugan Department of Information Techology R M K Engineering College Tamil Nadu India Department of Computer Applications SRM Institute of Science and Technology Tamil Nadu India Department of Electrical and Electronics Engineering Chennai Institute of Technology Tamil Nadu India Department of Computer and Communication Engineering Panimalar Engineering College Tamil Nadu India Department of Aritificial Intelligence and Data Science Jeppiaar Institute of Technology Tamil Nadu India

The Internet-of-things (IoT) is a technology that might be used to link huge amounts of equipment and gadgets in the future. This research uses a hybrid access point (HAP) to explore short packet communication (SPC), in which the IoT devices broadcast their short data packets to the HAP using the energy they gather. As compared to regular wireless networks, SPC has a lower transmission rate and a higher packet error rate. With unlimited block length codes, the allocation of resources in the literature is no longer the best it could possibly be. Based on a user’s unique effective amount of information r, their transmission time and packet error rate are tuned to maximize or decrease total effective throughput or total transmission time. Nonconvex issues need the development of efficient ways for unacceptable solutions. These algorithms outperform current benchmarks and are on par with an exhaustive search for the optimum solution in terms of performance.

关键词： Performance evaluation Error analysis Wireless networks System performance Power distribution Optimization methods Throughput

来源：评论

学校读者我要写书评

暂无评论

Modelling radiological features fusion and explainable AI in pneumonia detection: A graph- based deep learning and transformer approach

引用

Results in Engineering 2025年 26卷

作者： Kaushik, Pratham Jain, Eshika Kukreja, Vinay Hariharan, Shanmugasundaram Krishnamoorthy, Murugaperumal Ahuja, Vandana Bhattacherjee, Abhishek Kaushal, Rajesh Kumar Chen, Shih-Yu Centre for Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Artificial Intelligence and Data Science Vardhaman College of Engineering India Department of Electrical and Electronics Engineering Vardhaman College of Engineering India Department of Computer Science & Engineering Swami Vivekanand Institute of Engineering and Technology Punjab Ramnagar India Department of Computer Science Engineering Lovely Professional University Punjab India Department of Computer Applications Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin64002 Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and Technology Yunlin64002 Taiwan

Objectives: This study aims to develop a deep learning-based methodology for pneumonia detection using lung CT scans. The research focuses on integrating U-Net for lung segmentation, graph-based feature representations, and transformer-based models to improve interpretability and diagnostic accuracy. Methodology: We utilized 500 annotated lung CT scans, split into 70 % training (350 images), 15 % validation (75 images), and 15 % testing (75 images). U-Net was employed for lung segmentation, with segmentation performance evaluated using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The classification model incorporated feature fusion, combining handcrafted radiological features with transformer-based feature extraction. The model's noise sensitivity and interpretability were assessed using Grad-CAM and attention maps. Results: The segmentation model achieved a DSC of 0.943 on the training set, 0.928 on the validation set, and 0.910 on the test set. The IoU values were 0.890, 0.872, and 0.850, respectively. The model's inference time was 25 milliseconds per image. The classification model achieved an overall accuracy of 94 %, with pneumonia cases showing precision, recall, and F1-scores of 0.95, 0.94, and 0.94, respectively. For normal cases, precision, recall, and F1-scores were 0.92, 0.94, and 0.93. The model's performance improved over 20 epochs, with training accuracy reaching 0.94 and validation accuracy reaching 0.88. The feature fusion method achieved an attention score of 0.88, with node intensity scores of 0.85. Noise sensitivity analysis revealed a performance drop beyond a noise level of 0.3. Conclusions: This study demonstrates the potential of AI-driven solutions for pneumonia detection, achieving high accuracy, robustness, and interpretability. While the model performs well, further optimization is needed to address noise sensitivity and enhance model generalization for real-world applications. © 2025

关键词： Image annotation

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：