检索结果-内蒙古大学图书馆

Wavelet-Infused Convolution-Transformer for Efficient Segmentation in Medical Images

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3326-3337页

作者： Dutta, Pallabi Mitra, Sushmita Roy, Swalpa K. Indian Statistical Institute Machine Intelligence Unit Kolkata700108 India Alipurduar Government Engineering and Management College Department of Computer Science and Engineering Alipurduar736206 India

Recent medical image segmentation methods extract the characteristics of anatomical structures only from the spatial domain, ignoring the distinctive patterns present in the spectral representation. This study aims to develop a novel segmentation architecture that leverages both spatial and spectral characteristics for better segmentation outcomes. This research introduces the wavelet-infused convolutional Transformer (WaveCoformer), a computationally effective framework to fuse information from both spatial and spectral domains of medical images. Fine-grained textural features are captured from the wavelet components by the convolution module. A transformer block identifies the relevant activation maps within the volumes, followed by self-attention to effectively learn long-range dependencies to capture the global context of the target regions. A cross-attention mechanism effectively combines the distinctive features acquired by both modules to produce a comprehensive and robust representation of the input data. WaveCoformer outperforms related state-of-the-art networks in publicly available Synapse and Adrenal tumor segmentation datasets, with a mean Dice score of 83.86% and 79%, respectively. The model is feasible for deployment in resource-constrained environments with rapid medical image analysis due to its computationally efficient nature and improved segmentation performance. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Minimizing energy consumption in fixed node networks using a novel neutrosophic model: comparative analysis with standard and existing algorithms

引用

International Journal of Information Technology (Singapore) 2025年 1-15页

作者： Ghimire, Sangam Bhurtel, Nirjal Jha, Sudan Ahmad, Sultan Abdeljaber, Hikmat A. M. Nazeer, Jabeen Department of Computer Science and Engineering Kathmandu University 28 kilo Bagmati Dhulikhel 45210 Nepal Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-kharj 11942 Saudi Arabia School of Computer Science and Engineering Lovely Professional University Punjab Phagwara 144411 India Department of Computer Science Faculty of Information Technology Applied Science Private University Amman Jordan MEU Research Unit Middle East University Amman 11831 Lebanon

The growing development and utilization of networked systems has led to more concern regarding the energy efficiency of these systems. In this paper, we present a novel approach to minimizing energy consumption in fixed node network for which we propose a new Neutrosophic model. This model leverages the unique strengths of Neutrosophic logic to enhance the efficiency by minimizing the energy consumption. The simulation of results is performed using Matplotlib (Python) with implementation parameters such as number of nodes (n) and additive white Gaussian noise (AWGN) (η). Additionally, we show a comparative analysis between the proposed model and other prevalent approaches used in minimizing energy consumption in networked systems. The comparative results shows improvement in energy efficiency, showcasing the potential of the proposed model as an alternative for optimizing energy consumption in networked systems. This work highlights the effectiveness of the proposed model and opens new avenues for future advancements in energy-efficient networked system using Neutrosophic approach. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Comparative analysis Energy-consumption optimization Networked systems Neutrosophic model Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in NSL-KDD Dataset Using Hybrid Self-Organizing Map Model

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 639-671页

作者： Noveela Iftikhar Mujeeb Ur Rehman Mumtaz Ali Shah Mohammed J.F.Alenazi Jehad Ali Knowledge Unit of Systems and Technology University of Management and TechnologySialkot51310Pakistan Department of Computer Science University ofWahWah Cantt47010Pakistan Department of Computer Engineering College of Computer and Information Sciences(CCIS)King Saud UniversityRiyadh11451Saudi Arabia Department of AI Convergence Network Ajou UniversitySuwon16499Republic of Korea

Intrusion attempts against Internet of Things(IoT)devices have significantly increased in the last few *** devices are now easy targets for hackers because of their built-in security *** a Self-Organizing Map(SOM)hybrid anomaly detection system for dimensionality reduction with the inherited nature of clustering and Extreme Gradient Boosting(XGBoost)for multi-class classification can improve network traffic intrusion *** proposed model is evaluated on the NSL-KDD *** hybrid approach outperforms the baseline line models,Multilayer perceptron model,and SOM-KNN(k-nearest neighbors)model in precision,recall,and F1-score,highlighting the proposed approach’s scalability,potential,adaptability,and real-world ***,this paper proposes a highly efficient deployment strategy for resource-constrained network *** results reveal that Precision,Recall,and F1-scores rise 10%-30% for the benign,probing,and Denial of Service(DoS)*** particular,the DoS,probe,and benign classes improved their F1-scores by 7.91%,32.62%,and 12.45%,respectively.

关键词： Intrusion detection self-organizing map Internet of Things dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Constructing Rectilinear Steiner Minimum Tree with Conditional Generative Adversarial Network 38

Constructing Rectilinear Steiner Minimum Tree with Condition...

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Saha, Kritanta Banerjee, Pritha Sur-Kolay, Susmita Indian Statistical Institute Advanced Computing and Microelectronics Unit Kolkata India Sister Nivedita University Department of Computer Science and Engineering Kolkata India University of Calcutta Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331522445

Given n points in the 2D plane which are the pins of a net, a Rectilinear Steiner Minimum Tree (RSMT) which consists only of vertical and horizontal line segments is the shortest network to interconnect the pins along with a few extra (Steiner) points. An RSMT for a net has a minimum total wirelength in Manhattan distance and acts as a backbone to many state-of-the-art global routers. However, finding an RSMT is NPcomplete. In this work, we propose a method for constructing an RSMT with an image-to-image translation using a conditional generative adversarial network (cGAN) based model. Images of RSMTs with optimal wirelength for randomly generated nets form our training dataset. Experimental results show that, after training, our model generates RSMTs with = 0.348% wirelength error on average compared with the optimal solution for nets with degrees up to 50. This is the first successful attempt to solve the RSMT construction problem as an image-to-image translation problem using a cGAN based model. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

PulmoNetX: A Hybrid Vision Transformer Approach for Multi-scale Spatial Feature Reduction in Pneumonia Classification 27th

PulmoNetX: A Hybrid Vision Transformer Approach for Multi-sc...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lasker, Asifuzzaman Ghosh, Mridul Obaidullah, Sk Md Chakraborty, Chandan Roy, Kaushik Pal, Umapada Department of Computer Science and Engineering Aliah University Kolkata700160 India Department of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah711312 India Department of Computer Science and Engineering National Institute of Technical Teachers’ Training and Research Kolkata700106 India Department of Computer Science West Bengal State University Barasat700126 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9783031781650

An innovative deep learning structure, PulmoNetX, integrates the capabilities of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance pneumonia detection in chest X-ray imagery. During preprocessing, images are normalized in size, converted to grayscale, and subjected to contrast amplification to emphasize essential features. PulmoNetX employs a hybrid methodology to capture both the local and global characteristics of images, leading to significant advancements in diagnosing different pneumonia types, such as COVID-19-induced, viral, and bacterial pneumonia. Comparative studies reveal that PulmoNetX surpasses leading Vision Transformer models in terms of precision, recall, F1-score, and overall accuracy, highlighting its advanced processing abilities and its promise as an effective diagnostic tool in X-ray lung disease detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Augmented Evolutionary Strategies for Intelligent Global Optimization

引用

IEEE Access 2025年 13卷 70138-70178页

作者： Ezugwu, Absalom El-Shamir Oyelade, Olaide Nathaniel Agushaka, Jeffrey Ovre Saha, Apu Kumar Unit for Data Science and Computing North-West University Potchefstroom2520 South Africa School of Electronics Electrical Engineering and Computer Science Queen’s University BelfastBT9 5BN United Kingdom Department of Computer Science Federal University of Lafia Lafia950101 Nigeria Department of Mathematics National Institute of Technology Agartala Tripura Agartala799046 India

This paper introduces the Susceptible-Infected-Removed Optimizer (SIRO), a novel learned heuristic inspired by biological systems and deep learning techniques. SIRO models its search process after the SIR epidemiological compartmental model, predicting the susceptibility, infection, and recovery dynamics of solutions. SIRO integrates deep learning into its initialization and parameter setting to enhance its efficiency, enabling intelligent and adaptive behavior. This hybridization improves solution quality, accelerates convergence, enhances robustness, and reduces computational costs. The algorithm’s performance was evaluated using CEC 2017 benchmark functions, demonstrating superior results in hybrid functions (C1-C28) despite moderate performance on traditional CEC1-CEC14 functions. Friedman’s test ranked SIRO 4th overall, with SSA as the top-performing algorithm. Additionally, SIRO was tested on real-world optimization problems, including mechanical engineering design, hyperparameter tuning, and feature selection for medical image classification. In the classification task, SIRO-enhanced CNN achieved an accuracy of 0.86 at the 5th epoch, outperforming CNN (0.66), CNN-GA (0.76), and CNN-WOA (0.75). Furthermore, SIRO reported a precision of 0.96, recall of 1.0, and F1-score of 0.98, highlighting its effectiveness. These results validate the benefits of integrating a learning mechanism into SIRO, yielding superior precision, computational efficiency, and performance over conventional optimization approaches. © 2013 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Online Menu-Based Scheduling of Electric Vehicle Charging

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2478-2491页

作者： Mathioudaki, Angeliki Tsaousoglou, Georgios Varvarigos, Emmanouel Fotakis, Dimitris National Technical University of Athens School of Electrical and Computer Engineering Zografou15772 Greece Technical University of Denmark Department of Applied Mathematics and Computer Science Section for Dynamical Systems Kongens Lyngby2800 Denmark Archimedes Research Unit Athena Research Center Marousi15125 Greece

This paper addresses the problem of efficiently scheduling of EV charging requests in a single Charging Station (CS), also taking into consideration the inability of EV users to express their preferences in closed-form utility functions. We consider a paradigm where a menu of possible charging intervals, each associated with an urgency price, is generated online. By letting the EV users pick their most preferable menu option, the proposed algorithm commits on each EV’s charging completion time upon its arrival, achieves a near optimal total weighted charging completion time, and prevents the users from strategically misreporting their preferences, while offering a practical and implementable solution to the problem of EVs - charging station interaction. Our experimental evaluation demonstrates that our algorithmic approach performs nearly optimal in a variety of practically relevant scenarios. © 2010-2012 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

An Overview of Event Extraction Methods based on Semantic Disambiguation 24

An Overview of Event Extraction Methods based on Semantic Di...

引用

2nd International Conference on Artificial Intelligence, Systems and Network Security, AISNS 2024

作者： Li, Haili Wang, Xiaodong Zhou, Yunyan Liu, Weijie Pan, Shilong College of Computer Science and Technology National University of Defense Technology Hunan Changsha China Unit 63893 of PLA Henan Luoyang China Unit 63891 of PLA Henan Luoyang China

ISBN: (纸本)9798400711237

Event extraction is a fundamental and complex task in information extraction, aiming at automatically identifying and extracting structured event information from unstructured text. However, the same word may have different meanings in different contexts, necessitating semantic disambiguation during the classification process. The polysemy of triggers presents a significant challenge to accurate EE. Existing surveys primarily focus on different domains, fields, or technical paradigms, but none provide a systematic summary of the semantic disambiguation techniques employed. This study classifies these techniques into three categories based on the underlying technical frameworks and offers a comprehensive overview of the most advanced methods in each category. Finally, we summarize the application scenarios, strengths, and limitations of existing approaches, and discuss potential directions for future research. © 2024 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Auction-Based Optimization with Machine Learning for Cyber Threat Detection and Classification Model 3rd

Auction-Based Optimization with Machine Learning for Cyber T...

引用

3rd International Conference on Computing and Communication Networks, ICCCN 2023

作者： Alqahtani, Hamed Department of Information Systems College of Computer Science Center of Artificial Intelligence Unit of Cybersecurity King Khalid University Abha Saudi Arabia

ISBN: (纸本)9789819726707

The detection of cyber threats and cybersecurity can be benefitted greatly from the advances in artificial intelligence (AI). Cyber threat detection is the main focus of cybersecurity. It has used various tools and techniques to find unauthorized access to systems, attacks, effective security incidents or applications, and networks. Owing to data flow presence over networks and extensive devices, the possibility of intrusion detection and cyberattacks has increased. Monitorization of this immense volume of data traffic is found to be tough, though machine learning (ML) techniques effectively support this task. This study develops an auction-based optimization with machine learning for cyber threat detection and classification (ABOML-CTDC) technique. The presented ABOML-CTDC technique concentrates on the identification and classification of cyber threats in accomplishing cybersecurity. The proposed ABOML-CTDC technique makes use of the ABO-based feature subset selection (ABO-FSS) technique to elect optimal features. For cyber threat detection, the ABOML-CTDC technique utilizes a variational autoencoder (VAE) model. Finally, the moth flame optimization (MFO) algorithm is exploited for the parameter selection of the VAE method del to improve the detection rate. The experimental validation of the ABOML-CTDC approach is tested on benchmark datasets and the results pointed out the promising results on detecting threats over recent state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Predicting Aesthetic Outcomes in Breast Cancer Surgery: A Multimodal Retrieval Approach 1st

Predicting Aesthetic Outcomes in Breast Cancer Surgery: A M...

引用

1st Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Deep-Breath 2024

作者： Zolfagharnasab, Mohammad Hossein Freitas, Nuno Gonçalves, Tiago Bonci, Eduard Mavioso, Carlos Cardoso, Maria J. Oliveira, Hélder P. Cardoso, Jaime S. University of Porto Porto Portugal Institute for Systems and Computer Engineering Technology and Science Porto Portugal Breast Unit Champalimaud Foundation Lisbon Portugal

ISBN: (纸本)9783031777882

Breast cancer treatments often affect patients’ body image, making aesthetic outcome predictions vital. This study introduces a Deep Learning (DL) multimodal retrieval pipeline using a dataset of 2,193 instances combining clinical attributes and RGB images of patients’ upper torsos. We evaluate four retrieval techniques: Weighted Euclidean Distance (WED) with various configurations and shallow Artificial Neural Network (ANN) for tabular data, pre-trained and fine-tuned Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), and a multimodal approach combining both data types. The dataset, categorised into Excellent/Good and Fair/Poor outcomes, is organised into over 20K triplets for training and testing. Results show fine-tuned multimodal ViTs notably enhance performance, achieving up to 73.85% accuracy and 80.62% Adjusted Discounted Cumulative Gain (ADCG). This framework not only aids in managing patient expectations by retrieving the most relevant post-surgical images but also promises broad applications in medical image analysis and retrieval. The main contributions of this paper are the development of a multimodal retrieval system for breast cancer patients based on post-surgery aesthetic outcome and the evaluation of different models on a new dataset annotated by clinicians for image retrieval. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

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：