检索结果-内蒙古大学图书馆

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Low-Resource Language Literature Using Data Processing and Deep Learning

引用

computers, Materials & Continua 2024年第4期79卷 713-733页

作者： Aizaz Ali Maqbool Khan Khalil Khan Rehan Ullah Khan Abdulrahman Aloraini Department of IT and Computer Science Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur22620Pakistan Software Competence Center Hagenberg Softwarepark 32aHagenberg4232Austria Department of Computer Science School of Engineering and Digital SciencesNazarbayev UniversityAstana010000Kazakhstan Department of Information Technology College of ComputerQassim UniversityP.O.Box 1162BuraydahSaudi Arabia

Sentiment analysis, a crucial task in discerning emotional tones within the text, plays a pivotal role in understandingpublic opinion and user sentiment across diverse *** numerous scholars conduct sentiment analysisin widely spoken languages such as English, Chinese, Arabic, Roman Arabic, and more, we come to grapplingwith resource-poor languages like Urdu literature which becomes a challenge. Urdu is a uniquely crafted language,characterized by a script that amalgamates elements from diverse languages, including Arabic, Parsi, Pashtu,Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguisticfeatures, presents an additional hurdle due to the lack of accessible datasets, rendering sentiment analysis aformidable undertaking. The limited availability of resources has fueled increased interest among researchers,prompting a deeper exploration into Urdu sentiment analysis. This research is dedicated to Urdu languagesentiment analysis, employing sophisticated deep learning models on an extensive dataset categorized into fivelabels: Positive, Negative, Neutral, Mixed, and Ambiguous. The primary objective is to discern sentiments andemotions within the Urdu language, despite the absence of well-curated datasets. To tackle this challenge, theinitial step involves the creation of a comprehensive Urdu dataset by aggregating data from various sources such asnewspapers, articles, and socialmedia comments. Subsequent to this data collection, a thorough process of cleaningand preprocessing is implemented to ensure the quality of the data. The study leverages two well-known deeplearningmodels, namely Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), for bothtraining and evaluating sentiment analysis performance. Additionally, the study explores hyperparameter tuning tooptimize the models’ efficacy. Evaluation metrics such as precision, recall, and the F1-score are employed to assessthe effectiv

关键词： Urdu sentiment analysis convolutional neural networks recurrent neural network deep learning natural language processing neural networks

来源：评论

学校读者我要写书评

暂无评论

Structured Light Center Extraction Study with Multiple Attention Mechanisms

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第4期51卷 437-446页

作者： Sun, Hang Zhou, Ziwei School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China

The integration of deep learning with conventional structured light center extraction techniques improves the accuracy of extracting structural gold centers. The method is divided into three steps. The initial step involves calibration, which aims to establish a correlation between image coordinates and world coordinates. The subsequent stage involves identifying the laser fringe area. This study employs a self-designed Multi-Att DeepLabV3+ encoder-decoder neural network architecture to extract the laser fringe region. The self-designed SE-ResSkipNet module is incorporated into the structure as the backbone. The decoder utilizes a parallel alternating dual attention mechanism. The third step involves extracting the center of the laser fringe utilizing the Steger algorithm, which is based on a Hessian matrix. Conducting experimental validation on a laser image dataset that is open-source. The experimental resluts indicate that the network architecture's mIoU, fwIoU, Acc, and Acc class evaluation metrics for complex laser fringe segmentation have shown improvements of 4.22%, 0.67%, 0.33%, and 4.96%, respectively. This algorithm demonstrates superior accuracy compared to other algorithms in laser fringe segmentation, playing a crucial role in the subsequent processes of 3D reconstruction and 3D measurement. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Optimizing Solar-Energy Harvesting Communication Systems: An energy allocation scheme for maximizing data transmission 4

Optimizing Solar-Energy Harvesting Communication Systems: An...

引用

4th International Conference on Internet of Things and Smart City, IoTSC 2024

作者： Li, Shuai Yao, Zhonghao Chen, Shengbo Schoool of Software Henan University Henan Kaifeng China School of Computer Science & Technology Beijing Institute of Technology Beijing China School of Computer and Information Engineering Henan University Henan Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Henan Kaifeng China

ISBN: (纸本)9781510681767

The solar energy harvesting communication system is the basic support layer that is associated with the Internet of Things (IoT). However, the inherent stochasticity of solar energy brings about extensive research on energy allocation in the system. In this paper, we propose an energy allocation algorithm for maximizing the data transfer (MDT) of a solar energy harvesting communication system while jointly considering the practical constraints of battery capacity and link capacity restrictions. We can solve it through the convex optimization problem, but the solution is extremely complicated. This complexity is the result of the coupling of energy allocation problems caused by restricted battery capacity and link capacity. To simplify the solution process, we propose a decoupled energy allocation (DEA) algorithm. Simulation experiments are conducted through real energy harvesting data sets, and the results show that DEA outperforms the other two heuristic schemes. © 2024 SPIE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Adversarial Machine Learning for Detecting Advanced Threats Inspired by StuxNet in Critical Infrastructure Networks 12

Adversarial Machine Learning for Detecting Advanced Threats ...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Ahmad, Hafiz Bilal Gao, HaiChang Latif, Naila Aziiz, Abdul Auraangzeb, Muhammad Khan, Muhammad Tanveer School of Computer Science and Technology Xidian University Shaanxi 710071 China School of Telecommunications and Engineering Xidian University Shaanxi 710071 China School of Computer Science and Engineering Southeast University Nanjing China School of Electrical Engineering Southeast University Nanjing China School of Software Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350330366

Inspired by the notorious StuxNet malware, this paper presents a unique and resilient architecture to address the imminent issue of identifying advanced threats within critical infrastructure networks. We use adversarial machine learning techniques to keep ahead of ever-changing threats. Our defense system's fundamental component is a Multi-Layer Perceptron (MLP) architecture that we've dubbed 'StuxNet.' This innovative method combines threat intelligence, anomaly detection, and deep learning to forecast and counter sophisticated attacks. The effectiveness of our method in bolstering the security of critical infrastructure networks is supported by empirical evaluations and real-world case studies. Importantly, the StuxNet-MLP architecture has a 98 percent detection accuracy for sophisticated threats. These results highlight the paramount significance of preventative cybersecurity measures in protecting mission-critical systems and provide useful insights for fending off sophisticated attacks. To ensure a safer and more resilient digital future, this study highlights the need to stay ahead in the continuous battle to secure key infrastructure. © 2024 IEEE.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

Detection of Deepfakes: Protecting Images and Vedios Against Deepfake 21

Detection of Deepfakes: Protecting Images and Vedios Against...

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Tian, Ying Zhou, Wang Haq, Amin Ul Sichuan Police College Intelligent Policing Key Laboratory of Sichuan Province LuZhou China School of Computer and Software Engineering Xihua University Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798331519254

In recent years, with the rapid development of deep learning and computer vision technology, the forgery technology of images and videos has become increasingly mature, posing new challenges to information security and social stability. Behind the re-evolution of deepfake lies the rampant proliferation of fake content, which is used for election tampering, identity fraud, fraud, spreading fake news, and so on. To address these challenges, researchers are constantly exploring and developing image-based deepfake detection techniques, which aim to effectively identify and prevent deepfake content in images and videos. This article will introduce the current development status of deepfake detection technology, present its principles and methods in detail, and look ahead to its future development directions. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition 38

Continuous Contrastive Learning for Long-Tailed Semi-Supervi...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhou, Zi-Hao Fang, Siyuan Zhou, Zi-Jing Wei, Tong Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Group Recommendation Method Based on Graph Neural Network

Group Recommendation Method Based on Graph Neural Network

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Lu, Mengye Zhu, Peng Miao, Chun Wang, Youjian Wang, Jiacun Nanjing University of Science and Technology School of Economics and Management Nanjing China Monmouth University Department of Computer Science and Software Engineering NJ United States

ISBN: (纸本)9798350376739

Group activities are becoming more and more common on the Internet in the big data environment. Which makes many scholars focus on how to recommend items or activities to a group. However, conventional recommendation systems grapple with issues like data sparsity and the cold start problem, which limits the relevance and accuracy of recommendation. Therefore, this paper conducts an in-depth exploration of group recommendation methods utilizing graph neural networks and introduces a novel recommendation framework aimed at enhancing the efficacy of group recommendations. Firstly, this paper discusses how to construct an effective graph structure to encode the social interaction and individual characteristics of users. Then, an improved graph neural network architecture is proposed. Finally, extensive experimental evaluation is carried out on actual datasets, and the findings demonstrate that our framework markedly enhances the accuracy of recommendations. © 2024 IEEE.

关键词： Graph neural network Group recommendation Recommendation system

来源：评论

学校读者我要写书评

暂无评论

DIG: Improved DINO for Graffiti Detection

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3557-3569页

作者： Wang, Bingshu Mao, Qianchen Liu, Aifei Chen, Long Chen, C. L. Philip Northwestern Polytechnical University School of Software Xi’an710129 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen518060 China University of Macao Department of Computer and Information Science China South China University of Technology School of Computer Science and Engineering Guangzhou510641 China

Graffiti detection is essential in historic building protection and urban neighborhood management. Graffiti detection has made significant progress in recent years based on the development of deep learning. However, small-scale graffiti, interference from the background, and the false detection of word parts in graffiti make it a challenging problem. This article proposes a Transformer-based high-precision graffiti detection method, namely DIG. Precisely, it consists of three modules: 1) Spatial query selection (SQS), scale-aware IoU loss (SIL);2) Denoising Task with binary contrastive denoising (BCDN);and 3) IoU-guided box denoising (IBD) modules. To detect small-scale graffiti, this paper proposes SIL to help the loss function to perceive small-scale graffiti and large-scale graffiti fairly. To reduce the false detection of word parts, this article presents the SQS module, which integrates spatial information into the query selection process of the Encoder to filter out falsely detected bounding boxes within the graffiti. To reduce the interference from the background, this article introduces a denoising task with BCDN and IBD modules, improving the model’s ability to distinguish graffiti from the background and accurately select appropriate bounding boxes. A large number of experimental results on the STORM dataset show that our method achieves state-of-the-art results with an AP50 of 87.9%. Moreover, DIG achieved competitive results on the FineFM dataset for mask detection. This indicates that DIG can also be conveniently transferred to detect other scenarios. © 2013 IEEE.

关键词： Historic preservation

来源：评论

学校读者我要写书评

暂无评论

A novel image encryption algorithm based on new one-dimensional chaos and DNA coding

引用

Multimedia Tools and Applications 2024年第36期83卷 84275-84297页

作者： Feng, Sijia Zhao, Maochang Liu, Zhaobin Li, Yuanyu Tianjin public emergency early warning information release center Tianjin Meteorology Information Center Tianjin300074 China School of Information Science & amp Technology Dalian Maritime University Dalian116026 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

This paper introduces a new one-dimensional chaotic system and a new image encryption algorithm. Firstly, the new chaotic system is analyzed. The bifurcation diagram and Lyapunov exponent show that the system has strong chaotic characteristics and is suitable for the field of image encryption. The chaotic sequence generated by the system is used in image encryption, scrambled according to its sequence value, and several sequences required for DNA coding operation are generated. The encrypted image is obtained by encoding, decoding, and diffusion operation according to the sequence. The initial values and parameters of system are generated by Hash algorithm based on plain image, so it has strong sensitivity and can effectively resist attacks such as selective plaintext attack. Experimental results show that the algorithm has high security and robustness, and can resist common attacks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Chaotic systems

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：