检索结果-内蒙古大学图书馆

Domain generalization with semi-supervised learning for people-centric activity recognition

science China(Information sciences) 2025年第1期68卷 171-188页

作者： Jing LIU Wei ZHU Di LI Xing HU Liang SONG Academy for Engineering & Technology Fudan University Shanghai East-bund Research Institute on Networking Systems of AI School of Optoelectronic Information and Computer Engineering University of Shanghai for Science & Technology

People-centric activity recognition is one of the most critical technologies in a wide range of real-world applications,including intelligent transportation systems, healthcare services, and brain-computer interfaces. Large-scale data collection and annotation make the application of machine learning algorithms prohibitively expensive when adapting to new tasks. One way of circumventing this limitation is to train the model in a semi-supervised learning manner that utilizes a percentage of unlabeled data to reduce the labeling burden in prediction tasks. Despite their appeal, these models often assume that labeled and unlabeled data come from similar distributions, which leads to the domain shift problem caused by the presence of distribution gaps. To address these limitations, we propose herein a novel method for people-centric activity recognition,called domain generalization with semi-supervised learning(DGSSL), that effectively enhances the representation learning and domain alignment capabilities of a model. We first design a new autoregressive discriminator for adversarial training between unlabeled and labeled source domains, extracting domain-specific features to reduce the distribution gaps. Second, we introduce two reconstruction tasks to capture the task-specific features to avoid losing information related to representation learning while maintaining task-specific consistency. Finally, benefiting from the collaborative optimization of these two tasks, the model can accurately predict both the domain and category labels of the source domains for the classification task. We conduct extensive experiments on three real-world sensing datasets. The experimental results show that DGSSL surpasses the three state-of-the-art methods with better performance and generalization.

关键词： activity recognition deep learning domain generalization semi-supervised learning adversarial training

来源：评论

学校读者我要写书评

暂无评论

M-Bi-GRU-CNN: a hybrid deep learning model with optimized feature selection for enhanced crop yield prediction

引用

Multimedia Tools and Applications 2025年 1-25页

作者： J, Madhuri M, Indiramma N, Nagarathna Department of Computer Science and Engineering Bangalore Institute of Technology Karnataka Bengaluru560004 India Department of Computer Science and Engineering BMS College of Engineering Karnataka Bengaluru560019 India

Weather variability significantly impacts crop yield, posing challenges for large-scale agricultural operations. This study introduces a deep learning-based approach to enhance crop yield prediction accuracy. A Multi-Head Attention-based Bi-Directional Gated Recurrent Unit (M-Bi-GRU) integrated with a Convolutional Neural Network (CNN) is proposed. The publicly available Crop Recommendation dataset is pre-processed using data cleaning and Min–Max normalization to eliminate inconsistencies. Then, the Adaptive Reptile Search Optimization (ARSO) algorithm is used to identify the most relevant features for the prediction task. The M-Bi-GRU-CNN model uses these selected features to predict crop yields. The implementation is carried out in Python, and the performance is measured using a variety of metrics. Experimental results demonstrate that the proposed model outperforms existing methods, achieving a Mean Absolute Error (MAE) of 0.45, Mean Absolute Percentage Error (MAPE) of 0.07, and Root Mean Square Error (RMSE) of 0.28. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Boosting cervical cancer detection with a multi-stage architecture and complementary information fusion

引用

Soft Computing 2025年第2期29卷 1191-1206页

作者： Sahoo, Pranab Saha, Sriparna Sharma, Saksham Kumar Mondal, Samrat Computer Science and Engineering Indian Institute of Technology Patna India Computer Science University of Maryland Baltimore CountyMD United States

Cervical cancer is one of the most fatal and prevalent illnesses affecting women globally. Early detection of cervical cancer is crucial for effective treatment. Pap smear tests are commonly used, but population-based screening is time-consuming, expensive, and requires expert physicians. computer-Aided Diagnosis (CAD) has shown promise in addressing this challenge. However, accurately predicting the disease using a single model can be difficult due to the complex data patterns involved. This research proposes a multi-stage architecture to improve cervical cancer screening. Initially, three pre-trained models are employed for image classification, after which the proposed advanced fusion technique is applied to combine the predictions. Additionally, we introduce a filtering approach in the third stage to refine the predictions. Unlike traditional fusion methods, the proposed architecture considers the confidence score of the base classifiers in making the final predictions on test samples. To enhance the performance of the models, we incorporate advanced augmentation techniques, including CutMix, CutOut, and MixUp. We assessed the performance of the proposed framework using a 5-fold cross-validation technique on two benchmark datasets. We evaluated the performance of the proposed framework through 5-fold cross-validation on two benchmark datasets. Remarkably, our framework achieved a classification accuracy of 97.62% and an F1-score of 97.64% on the SIPaKMeD dataset, demonstrating its effectiveness in accurately categorizing various cell types in the dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Cervical cancer computer-aided detection Deep learning Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Halo reduction multi-exposure image fusion technique

引用

Multimedia Tools and Applications 2025年第13期84卷 12347-12370页

作者： Sharif, Rizwan Amin, Benish Sukhia, Komal Nain Department of Electrical Engineering Institute of Space Technology Islamabad Pakistan Department of Computer Science Institute of Space Technology Islamabad Pakistan

Multi-exposure image fusion (MEF) involves combining images captured at different exposure levels to create a single, well-exposed fused image. MEF has a wide range of applications, including low light, low contrast, night photography, medical imaging, and remote sensing. However, MEF methods often face issues like artifacts, halos around edges, color inconsistencies, noise amplification, and difficulty in preserving fine details. Moreover, assessing the quality of fused images objectively is complex due to the subjective nature of human perception. Solving the challenges is essential to developing efficient MEF techniques that produce high-quality results across various scenarios. The proposed technique introduces an approach to handling halo artifacts and implementing MEF. The Dense Scale-Invariant Feature Transform (DSIFT) is used to capture vital information about image brightness, texture, and edges from source images. Three weight maps are computed from the local mean, signal strength, and the global gradient for initial weight estimation. The local mean represents the brightness of specific image areas, signal strength preserves essential details like textures and edges while reducing image noise, and global gradient helps identify regions with significant pixel value shifts across multiple exposure images. The weight maps are then combined using a weighted average and a Gaussian smoothing filter is applied to reduce inherent noise and discontinuities in the original weights. Subsequently, pyramid decomposition is performed to generate a fused image. The efficiency of the proposed method is extensively tested on challenging multi-exposure image sequences. The results of the proposed approach demonstrate its superiority in both subjective evaluation and objective metrics like the MEF-Structural Similarity Index (MEF-SSIM), Natural Image Quality Evaluator (NIQE) and Gradient based performance measure (QAB/f). © The Author(s), under exclusive licence to Springer

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Realizing the potential of Internet of Things (IoT) in Industrial applications

引用

Discover Internet of Things 2025年第1期5卷 1-16页

作者： Rathi, Bharat Thapaswi, S. Kambhampati, Meghana Jain, Vineet Akshay, P. Pandey, Trilok Nath Pradhan, Sunil Kumar School of Electronics Engineering Vellore Institute of Technology Chennai600127 India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

The Internet of Things (IoT), which enables seamless connectivity and effective data exchange between physical items and digital systems, has completely changed the way we interact with our surroundings. This study evaluates IoT applications in healthcare, transportation, agriculture, and smart cities, highlighting advancements, opportunities, and challenges. Using a systematic literature review and case study analysis, it identifies essential IoT components, including sensors, communication protocols, data analytics, and security methods. Key findings demonstrate IoT's potential to enhance healthcare through real-time monitoring and cost reduction, optimize transportation systems for resource efficiency, improve agricultural productivity via precision farming, and enable sustainable urban development in smart cities. However, challenges like data privacy, interoperability, and scalability remain critical barriers to widespread adoption. This study underscores the need for interdisciplinary collaboration among researchers, policymakers, and industry stakeholders to address these challenges and unlock IoT's full potential. It provides actionable insights and future directions for realizing a connected, efficient, and sustainable IoT-driven future. © The Author(s) 2025.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

A user-adaptive privacy-preserving authentication of IoMT using zero knowledge proofs with ECC

引用

Multimedia Tools and Applications 2025年 1-32页

作者： Misra, Garima Hazela, Bramah Chaurasia, Brijesh Kumar Department of Computer Science and Engineering Amity School of Engineering and Technology Lucknow Amity University Uttar Pradesh India Department of Computer Science & Engineering Pranveer Singh Institute of Technology Utter Pradesh Kanpur India

The Internet of Things (IoT) has developed into a crucial component for meeting the connection needs of the current smart healthcare systems. The Internet of Medical Things (IoMT) consists of medical devices that are connected to patients in order to sense their medical parameters and exchange that information with healthcare professionals so they can deliver remote healthcare services. The need to protect the patient’s private information from being misused makes IoMT security an urgent issue that merits further study. Elliptic Curve cryptography (ECC), a popular substitute for traditional public key encryption like RSA, has several advantages. ECC is a prime contender for implementation on constrained devices with confined memory and speed, as well as wireless communication protocols that use low power like IoMT environment. The economic complexity of the current security protocols makes them inappropriate, hence new security protocols must be developed for resource-constrained and diverse IoT networks. This work suggests an authenticated key agreement protocol for the IoMT that is based on elliptic curve encryption based zero-knowledge proof (ZKP) protocols. The proposed mechanism completes in order of milliseconds up to 300 ms for 160 bits. The research will include the comparison between computational delays in traditional protocols and ZKP-ECC protocol. This paper provides a protocol to obtain privacy of data in IoMT environment on the basis of zero knowledge phenomenon and anonymous communication by ZKP-ECC. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Cognitive Transformation in Personal IoT: Pioneering Intelligent Automation

引用

Cyber-Physical Systems 2025年第2期11卷 183-240页

作者： Gulzar, Bisma Ahmad Sofi, Shabir Sholla, Sahil Department of Information Technology National Institute of Technology Srinagar India Department of Computer Science Engineering Islamic University of Science & Technology Srinagar India

In recent years, IoT has transformed personal environments by integrating diverse smart devices. This paper presents an advanced IoT architecture that optimizes network infrastructure, focusing on the adoption of MQTT protocol and introducing Cognitive Smart Objects for managing personal IoT applications. These objects use Neural Networks to predict optimal actions based on user behavior patterns. A Continuous Learning mechanism enables real-time adaptation of the network to evolving user interactions. The study highlights the role of Cognitive Transformation in Personal IoT, driving intelligent automation and enhancing user experience. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Internet of Things (IoT) Personal Internet of Things (PIoT) Social Internet of Things (SIoT) IoT architecture network infrastructure

来源：评论

学校读者我要写书评

暂无评论

EPDTNet + -EM: Advanced Transfer Learning and SubNet Architecture for Medical Image Diagnosis

引用

Cognitive Computation 2025年第2期17卷 1-22页

作者： K, Dhivya K, Sangamithrai S, Indra Priyadharshini M, Vedaraj Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & d Institute of Science and Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Tamilnadu Kavaraipettai Thiruvallur601206 India

This paper presents a novel medical imaging framework, Efficient Parallel Deep Transfer SubNet+-based Explainable Model (EPDTNet + -EM), designed to improve the detection and classification of abnormalities in medical images. The model integrates Enhanced Exponential Transfer Learning (En-ETL) and the Parallel SubNet (PSNet +) architecture, addressing challenges like overfitting, high computational cost, and limited generalization across complex datasets. En-ETL accelerates learning and enhances precision, while PSNet + balances computational efficiency and performance through parallel convolutional layers and an axis attention mechanism. The proposed framework preprocesses medical images using resizing, noise removal, and contrast enhancement, ensuring high-quality inputs for analysis. For classification, the PSNet + model categorizes medical images into normal and abnormal cases. Explainable AI (XAI) is applied to highlight key features in classified images, improving interpretability and clinical decision-making. Experimental results validate the framework on various datasets, including MRI, CT, X-ray, and mammography images. The proposed model achieves a classification accuracy of 98.83%, a false positive rate of 2%, and an execution time of 5.3 ms. Comparative Analysis show superior performance over existing approaches in classification accuracy and efficiency. Ablation studies confirmed the significant contributions of the proposed model using each component in enhancing performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Spatial attention-based hybrid VGG-SVM and VGG-RF frameworks for improved cotton leaf disease detection

引用

Neural Computing and Applications 2025年第14期37卷 8309-8329页

作者： Pandiyaraju, V. Anusha, B. Senthil Kumar, A.M. Jaspin, K. Venkatraman, Shravan Kannan, A. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Marian Engineering College Trivandram Kerala Trivandrum India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Tamil Nadu Chennai India Department of Information Science and Technology College of Engineering Guindy Anna University Tamil Nadu Chennai India

The agriculture industry's production and food quality have been impacted by plant leaf diseases in recent years. Hence, it is vital to have a system that can automatically identify and diagnose diseases at an initial stage for enhancing the quality of agricultural output and also for stopping the overall plant extinction. Most state-of-the-art methods do not provide appropriate accuracy of identification when the similarity among different diseases is higher and the input leaf images have complex background. In this work, a transfer learning-based automated crop disease recognition system is proposed to handle this problem. The cotton leaf disease detection framework being proposed here includes two key stages: (1) the feature extraction stage, where the convolutional neural network (CNN) model from the visual geometry group (VGG-16) is employed to obtain the deep features from cotton leaf images with complex background. (2) Cotton leaf disease detection stage: Here, the extracted optimal features are input to the machine learning classifiers, namely random forest (RF) and nonlinear support vector machine (SVM), for the initial classification of the diseases. For providing an optimal cotton crop disease detection performance, Kaggle’s four-class cotton disease dataset with complex background is chosen in this work. For the final decision making and analysis, two hybrid models named spatial attention-based hybrid VGG-RF and hybrid VGG-SVM have been proposed in this work for enhancing the decision accuracy. These hybrid models offered an average accuracy of approximately 98.29% and 99.31%, respectively, which is higher than the accuracy provided by the related work. This proved that the proposed hybrid model, namely spatial attention-based VGG-SVM and VGG-RF models, with spatial attention outperformed the state-of-the-art classifiers. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improved security with novel M-Log chaos steganography algorithm for huffman compressed english text

引用

Multimedia Tools and Applications 2025年第2期84卷 665-688页

作者： Raghuvanshi, Devvrat Joshi, Kamaldeep Nandal, Rainu Sehrawat, Harkesh Singh, Surender Singh, Srishti Department of Computer Science and Engineering University Institute of Engineering and Technology Maharshi Dayanand University Rohtak Haryana India

This paper addresses the underexplored landscape of chaotic functions in steganography, existing literature when examined under PRISMA-ScR framework it was realized that most of the studies predominantly focuses on utilizing chaotic functions for either concealing or diffusing messages within cover images. This study explored a different direction of using chaotic function as guards for concealed data by proposing the M-Log chaos algorithm which employs logarithmic chaotic function to drive a unique bomb generator equation, strategically placing bomb bits in the image. These bombs act as sentinels, safeguarding the concealed message. Successful retrieval involves diffusing the bombs before extracting data from the rest of the image. Failure to defuse these bombs prior to access results in irreversible damage to concealed information, thwarting unauthorized access. Our proposed method demonstrates notable advancements across quantitative performance metrics, including a 40% increase in payload capacity, a mean PSNR of 45.8981, and a mean SSIM of 0.9931. Future avenues include exploring multi-dimensional chaotic functions and employing nature-based searching algorithms such as genetic algorithms or particle swarm optimization for optimal chaos bomb placement. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Steganography

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：