检索结果-内蒙古大学图书馆

International Conference on Computer and Communications (ICCC)

作者： Bo Yu Shun Li Wei Wang Dongying Liu Yuanze Meng Shenyang Institute of Computing Technology Chinese Academy of Science University of Chinese Academy of Sciences Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Science School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Wargame environments present unique challenges for reinforcement learning algorithms due to their large-scale state-action spaces, environmental asymmetry, and high random-ness. To address these challenges, this paper proposes DS-PPO, an improved reinforcement learning algorithm. DS-PPO incorpo-rates dual state input and action masking mechanisms to enhance the agent's perception of the environment and prevent invalid actions. Additionally, a redesigned loss function promotes policy ex-ploration and reduces instability. Experimental results demon-strate that DS-PPO outperforms other algorithms, achieving a win rate of 56.15%.

关键词： Military communication Military computing Design methodology Robot control Reinforcement learning Games Aerospace electronics Space exploration Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Brain Abnormalities in MRI Images Using Integrated Deep Convolutional Neural Networks With K-Means Algorithm 3

Automated Detection of Brain Abnormalities in MRI Images Usi...

引用

3rd IEEE Global Conference for Advancement in technology, GCAT 2022

作者： Jaisingh, W. Kavitha, R.K. Saravanan, S. Gour, Radhika School of Computing Science and Engineering Vit Bhopal University Madhya Pradesh Bhopal466114 India Kumaraguru College of Technology Department of Computer Applications Tamilnadu Coimbatore India

ISBN: (数字)9781665468558

ISBN: (纸本)9781665468534

Computerization in the medical field has turned out to be a necessity in recent medical development. Radiotherapists and doctors require such computerized systems for the precise identification and treatment of chronic diseases. The field of Machine learning has observed remarkable attention in recent times. Deep neural networks are considered to be one of the popular machine learning models applied in many areas like image analysis, natural language processing, etc. It is also commonly used in both academia and industry. These improvements offer a huge potential in the fields of medical imaging, medical data analysis and diagnostics, and health care. This paper proposes a method for automatically categorizing normal and pathological brain MR images using deep transfer learning. K-Means model along with the Convolutional neural network (CNN) is engaged as a model for deep learning. The proposed method was assessed by focusing on the imaging data offered by the Kaggle dataset. The proficiency of the method was evaluated, and the results were presented. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multiple Cryptography for Data Encryption

Hybrid Multiple Cryptography for Data Encryption

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： M. Anuradha Sathyapriya Loganathan G. Suseela Mercy Paul Selvan M. Nalini Chitra Devi D Dept of CSE S.A.Engineering College Computing Technologies Faculty of Engineering and Technology SRM Institute of Science and Technology Dept of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology CSE Department Sathyabama Institute of Science & Technology Dept of CSE S.A. Engineering College

Since the information technology revolution, cryptography has been essential for protecting sensitive information and communication. A plethora of algorithms have been developed to safeguard data and protect data integrity, with the goal of improving data security and protection. Modern cryptography is based on a variety of encryption techniques, namely Hybrid cryptography and multiple cryptography. Hybrid cryptography combines asymmetric key and symmetric key encryption to combine the strengths of both. Multiple cryptography is the process of encrypting a previously encrypted message one or more times, each time using the same or a different symmetric or asymmetric algorithm. The study proposes an approach that seeks to incorporate both hybrid and multiple cryptography as a way to combine all of their benefits while also minimizing the drawbacks that each technique has on its own to provide an additional layer of security. Although these techniques have all contributed to data protection, not all of them have been successful in providing a high level of security as they have shown a propensity for being targeted and exploited over time. This research project implements a cryptosystem based on Hybrid Multiple Cryptography (HMC) which is a novel scheme for data encryption that offers a greater level of security for sending data in an Android messaging application, in order to showcase the system's security capabilities in real time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Assisted Covid-19 Detection Model

Federated Learning Assisted Covid-19 Detection Model

引用

作者： Banerjee, Sourav Barik, Sudip Das, Debashis Ghosh, Uttam Debnath, Narayan C. Computer Science and Engineering Kalyani Government Engineering College Nadia Kalyani India Computer Science and Engineering University of Kalyani Nadia Kalyani India Department of CS and DS Meharry Medical College NashvilleTN United States School of Computing and Information Technology Eastern International University Binh Duong Viet Nam

Federated learning (FL) ensures data privacy and security, which has been emerging as a promising approach for developing an accurate and efficient model for COVID-19 detection. This paper highlights the FL-assisted systematic review of the current state-of-the-art COVID-19 detection methods. This work conducts a comprehensive study of the relevant literature and identifies relevant articles. The included articles described various FL-based COVID-19 detection models that utilized different types of data and machine learning algorithms. Furthermore, these models have several advantages over traditional centralized models, including privacy protection, data security, and scalability. The findings of this systematic review suggest that FL-based COVID-19 detection models have great potential for accurate and efficient COVID-19 detection while protecting data privacy and security. FL requires further research to validate the findings on different metrics and enhance the performance of the models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

WeakPolyp-SAM: Segment Anything Model-driven weakly-supervised polyp segmentation

引用

Knowledge-Based Systems 2025年 322卷

作者： Zhao, Yiming Zhou, Tao Gu, Yunqi Zhou, Yi Zhang, Yizhe Wu, Ye Fu, Huazhu School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Engineering Southeast University Nanjing211189 China Institute of High Performance Computing A*STAR Singapore

Accurate polyp segmentation is essential for early detection of polyps, which is of significant clinical importance for the prevention of colorectal cancer. Although various fully-supervised deep learning techniques have been developed for polyp segmentation, pixel-wise annotation by physicians during diagnosis is both time-consuming and expensive. Meanwhile, visual foundation models such as the Segment Anything Model (SAM) have demonstrated remarkable performance in general segmentation tasks. However, directly applying SAM to medical segmentation may not yield satisfactory results due to the lack of medical knowledge. In this paper, we propose a novel SAM-driven weakly-supervised polyp segmentation framework (termed WeakPolyp-SAM), which enables a collaborative learning process between our segmentation network and SAM to boost the model performance. Specifically, we propose a Cross-aware Feature Aggregation Network (CFANet) to effectively aggregate cross-level features and leverage global cues for weakly-supervised polyp segmentation. Within CFANet, we propose a Cross-level Fusion Module (CFM) that integrates the adjacent features to enhance the representation capabilities of different resolution features. Additionally, a Local-and-global Context Decoder (LCD) is presented to capture richer features across multiple levels. Moreover, we present a box-augmentation strategy that combines the segmentation maps generated by CFANet with scribble annotations to create more precise prompts. These prompts are then fed into SAM, generating segmentation SAM-driven masks, which provide additional supervision to effectively train CFANet. Furthermore, we present an image-level filtering mechanism to filter out unreliable masks. Experimental results demonstrate that our WeakPolyp-SAM outperforms state-of-the-art weakly-supervised segmentation methods. The scribble-annotated datasets and code will be released at https://***/taozh2017/WeakPolyp-SAM. © 2025 Elsevier B.V.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection Based on Information Entropy Feature Extraction in Software Defined Networks

DDoS Attack Detection Based on Information Entropy Feature E...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Wenjiang Ji Yixin Yang Yaling Zhang Yichuan Wang Mengjie Tian Yuan Qiu School of computer science and engineering Xi'an University of technology Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technology

Distributed Denial of Service(DDoS) attacks target the forwarding-control separation feature of Software-Defined Networking(SDN) to launch attacks, causing network disruptions. Therefore security against DDoS attack detection for SDN controllers is the focus of current research. This paper proposes an Extreme Gradient Boosting (XGBoost) DDoS attack detection algorithm based on a combination of information gain and recursive feature elimination algorithms. We evaluated the performance of the method using the CICDDoS2019 dataset. This method works well in multi-classification model for attack detection with an accuracy of 93.41%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite–Map Translation

arXiv

引用

arXiv 2025年

作者： Dong, Zhe Sun, Yuzhe Liu, Tianzhu Zuo, Wangmeng Gu, Yanfeng School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China Faculty of Computing Harbin Institute of Technology Harbin China Peng Cheng Lab Shenzhen China

Satellite imagery and maps, as two fundamental data modalities in remote sensing, offer direct observations of the Earth’s surface and human-interpretable geographic abstractions, respectively. The task of bidirectional translation between satellite images and maps (BSMT) holds significant potential for applications in urban planning and disaster response. However, this task presents two major challenges: first, the absence of precise pixel-wise alignment between the two modalities substantially complicates the translation process;second, it requires achieving both high-level abstraction of geographic features and high-quality visual synthesis, which further elevates the technical complexity. To address these limitations, we introduce EarthMapper, a novel autoregressive framework for controllable bidirectional satellite-map translation. EarthMapper employs geographic coordinate embeddings to anchor generation, ensuring region-specific adaptability, and leverages multi-scale feature alignment within a geo-conditioned joint scale autoregression (GJSA) process to unify bidirectional translation in a single training cycle. A semantic infusion (SI) mechanism is introduced to enhance feature-level consistency, while a key point adaptive guidance (KPAG) mechanism is proposed to dynamically balance diversity and precision during inference. We further contribute CNSatMap, a large-scale dataset comprising 302,132 precisely aligned satellite-map pairs across 38 Chinese cities, enabling robust benchmarking. Extensive experiments on CNSatMap and the New York dataset demonstrate EarthMapper’s superior performance, achieving significant improvements in visual realism, semantic consistency, and structural fidelity over state-of-the-art methods. Additionally, EarthMapper excels in zero-shot tasks like in-painting, out-painting and coordinate-conditional generation, underscoring its versatility. The source code for EarthMapper and the CNSatMap dataset will be publicly available at ht

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Mechanism for Intrusion Detection: Leveraging RFE-Based Feature Selection and PCA for Improved Accuracy

Optimized Deep Learning Mechanism for Intrusion Detection: L...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： M. Rajkumar Lakshi VS Karthik R Pavithra S Department of Smart Computing School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu India B. Tech-Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

With the growing demand for wireless networks, network traffic has surged, particularly involving large-scale data transmission. This results in an increased number of network security threats and the emergence of various cyber-attacks. To overcome these threats, the development of an efficient intrusion detection system (IDS) has become crucial. By leveraging the recent advancements in Artificial intelligence (AI), this project introduces an optimized deep learning mechanism utilizing a prevalent deep learning model, the Deep Neural Network (DNN) algorithm. This proposed method uses feature engineering techniques like feature selection and feature reduction. Given the high dimensionality of the selected datasets, these techniques are employed to prevent over-fitting. Recursive feature elimination performs feature selection followed by Principal Component Analysis for the feature reduction process, thus enhancing the model's efficiency. The system is assessed using two benchmark datasets: KDD and UNSW-NB15. The experimental results indicate that the presented DNN model on the KDD dataset has achieved 92.45% accuracy and 91.35% accuracy on the UNSW-NB15 dataset for intrusion classification.

关键词： Deep learning Accuracy Wireless networks Computational modeling Intrusion detection Artificial neural networks Feature extraction Data models Tuning Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Low-Light Image Enhancement Performance: DCE-Net vs. MirNetv2

Comparative Study of Low-Light Image Enhancement Performance...

引用

Emerging Trends in Information technology and engineering (ic-ETITE), Conference on

作者： Bharathi Mohan G. Prasanna Kumar R. Mithilesh A Sriram S Surya Santhosh V R Balaji M Sameer N MD Logeshwar B S Srinath Doss Dept. of CSE Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho university Botswana

The difficult computer vision task of low-light image augmentation tries to raise the standard of photographs taken in low light. Deep learning-based low-light picture enhancing systems have recently attained modern outcomes. In this article, we compare the effectiveness of two cutting-edge deep learning-based algorithms-DCE-Net and MirNetv2-to enhance the quality of images in low light. A deep cross-enhancement network called DCE-Net uses a cutting-edge cross-connection module to take advantage of the complementing data that exists between the network's various tiers. A multi-scale feature extraction module is used by the multi-scale illumination recovery network MirNetv2 to extract features from various scales of the picture. On the LOLdataset benchmark Datasets for enhancing low-light images, we compare the execution of DCE-Net and MirNetv2. The outcomes demonstrate that DCE-Net and MirNetv2 provides cutting-edge outcomes. On the LOLdataset, DCE-Net performs better than MirNetv2 in terms of improving contrast and brightness. The findings of this study indicate that the deep learning-based Improving visibility in low-light images method DCE-Net- a promising one. In a wide range of applications, including surveillance, night photography, and medical imaging, DCE-Net can be utilized to improve low-light photos.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fusion Attention Network for Facial Expression Recognition 23

Adaptive Fusion Attention Network for Facial Expression Reco...

引用

Proceedings of the 2023 12th International Conference on computing and Pattern Recognition

作者： Guodong Li Cheng Peng Kun Zou Bowen Zhang School of Computer Science and Engineering(School of Cybersecurity) University of Electronic Science and Technology of China China School of Computing University of Electronic Science and Technology of China Zhongshan Institute China College of Big Data and Internet Shenzhen Technology University China

ISBN: (纸本)9798400707988

In this paper, we propose a novel facial expression recognition network, called Adaptive Fusion Attention Network (AFAN). Facial expression recognition is different from traditional image classification tasks. There are potentially similar features between different categories, and the differences between them may be subtle and difficult to distinguish. To solve this problem, we propose AFAN, which not only can get multi-dimensional features, but also can generate an attention map with stronger representation ability. The comparative experiments on AffectNet-7 dataset verify the excellent performance of the proposed method on facial expression recognition tasks.

关键词： Adaptive convolutional blocks Facial expression recognition Fine-grained classification Multi-head attention 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：