检索结果-内蒙古大学图书馆

Research on Biomedical engineering 2025年第2期41卷 1-19页

作者： A, Padmashree Sankar, P. Alkhayyat, Ahmad Muniyandy, Elangovan Department of Computer Science and Business Systems Bannari Amman Institute of Technology Tamil Nadu Sathyamangalam India Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Applied Science Research Center Applied Science Private University Amman Jordan

Purpose: The primary objective of this research is to develop a comprehensive framework for the analysis of brain tumor images, addressing the complexities of detection, segmentation, and classification. Given the intricate nature of brain anatomy and tumor variability, the study aims to enhance the accuracy and efficiency of brain tumor diagnosis using advanced imaging and processing techniques. Methods: The framework utilizes Brain Tumor Segmentation (BraTS) 2019 and 2020 datasets, applying an AMW-PM filter to enhance image quality. Tumor segmentation employs a slimmable transformer with hybrid axial attention for precision. Classification uses similarity navigated graph neural networks (SNGNNs), optimized with the crayfish algorithm (CFO) to minimize loss and enhance performance. Results: The framework’s effectiveness was validated using key performance metrics, showing significant improvements in tumor detection and classification. The combination of advanced segmentation techniques and the SNGNN classifier, optimized by the CFO, led to a fivefold increase in diagnostic accuracy. These improvements demonstrated a substantial enhancement in the model's ability to correctly identify tumor types and provide reliable outputs for clinical use. Conclusion: The proposed framework delivers a robust solution for brain tumor analysis, integrating cutting-edge techniques for image processing, segmentation, and classification. The results not only highlight improvements in diagnostic accuracy but also contribute to better clinical decision-making in managing brain tumors. This framework sets the foundation for future advancements in brain tumor diagnostics. © The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Apple Quality Identification: A Multi-Layer Visual Feature Fusion Approach with Convolutional Neural Networks 2

Enhancing Apple Quality Identification: A Multi-Layer Visual...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Trivedi, Naresh Kumar Maheshwari, Himani Tiwari, Raj Gaurang Gautam, Vinay Agarwal, Ambuj Kumar Kaswan, Suresh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University School of Computing Uttrakhand Dehradun India Sharda University Sharda School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India Chandigarh University Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350371314

This research uses real-world images with complicated disturbance information (the backdrop was identical to the apples' surfaces) to identify and categorize apple quality. This research introduces a new model for the quick and accurate evaluation of apple quality based on convolutional neural networks (CNNs). The proposed model captures detailed, unique, and valuable image features for detection and classification. In contrast to the deep features, complex interpretation needs and large training sample requirements, the handcrafted features used in this work are mainly produced intuitively. A new feature fusion approach called multi-layer visual feature fusion (MLVSF) is created for better classification of apple images. The MLVSF model, which incorporates deep and handcrafted components obtained from bag-of-visual words, local binary pattern variations, and CNN, can improve the discriminatory power of features used for apple quality identification. With its ability to improve CNN and achieve more accurate classification - resulting in a classification accuracy of 98.93% - MLVSF beats other modern approaches when evaluated on apple image datasets. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1427-1439页

作者： Ruibing Jin Min Wu Keyu Wu Kaizhou Gao Zhenghua Chen Xiaoli Li Institute for Infocomm Research Agency for ScienceTechnology and Research(A*STAR)Singapore 138632Singapore School of Computer Science Liaocheng UniversityLiaocheng 252000 Macao Institute of System Engineering Macao University of Science and TechnologyTaipaMacao 999078China

Accurate remaining useful life(RUL)prediction is important in industrial *** prevents machines from working under failure conditions,and ensures that the industrial system works reliably and ***,many deep learning based methods have been proposed to predict *** these methods,recurrent neural network(RNN)based approaches show a strong capability of capturing sequential *** allows RNN based methods to perform better than convolutional neural network(CNN)based approaches on the RUL prediction *** this paper,we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN,which reduces their ***,the capacity of capturing sequential information is highly affected by the receptive field of CNN,which is neglected by existing CNN based *** solve these problems,we propose a series of new CNNs,which show competitive results to RNN based *** with RNN,CNN processes the input signals in parallel so that the temporal sequence is not easily *** alleviate this issue,a position encoding scheme is developed to enhance the sequential information encoded by a ***,our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based *** experiments are conducted on the C-MAPSS dataset,where our PE-Net shows state-of-the-art performance.

关键词： Convolutional neural network(CNN) deep learning position encoding remaining useful life prediction

来源：评论

学校读者我要写书评

暂无评论

Cross-modal image text retrieval based on Cross-optimization and Joint strategy

Cross-modal image text retrieval based on Cross-optimization...

引用

2024 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2024

作者： Zheng, Wei Han, Na Hu, Yan Kang, Peipei Zhang, Yue Yang, Aqing Zhang, Lei School of Computer Science Guangdong Polytechnic Normal University China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data China School of Computer Science and Technology Guangdong University of Technology China School of Information Engineering East University of Heilongjiang China

ISBN: (纸本)9781510680425

In the fields of computer vision and natural language processing, cross-modal retrieval is of great importance that cannot be ignored. In existing multi-granularity alignment methods, significant progress has been made by globally aligning images and sentences or locally aligning regions and words. However, most of these methods rely on attention mechanisms, which may be affected by noise and cannot balance the differences between modalities, resulting in suboptimal image-text alignment. In addition, training with attention mechanisms consumes a lot of computational resources, and the retrieval process is time-consuming. To address these challenges, we develop a novel multigranularity image-text alignment model, which we call DFVLM. First, we independently train the intra-modal encoder and cross-modal encoder to reduce interference between different modal encoders and better learn intra-modal and inter-modal information. Then, we propose a joint strategy to combine the intra-modal and inter-modal information to better capture the information between image and text. In addition, we introduce a hard negative pair-based method to train the performance of the intra-modal multi-granularity encoder without using attention mechanisms. Unlike existing methods, We treat image and text retrieval as a two-way process and delve into the intrinsic connections between the two matrices. We propose a cross-validation method to optimize the retrieval result based on common image-to-text alignment scenarios in daily life, i.e., during the image-to-text retrieval process, a text-to-image reverse verification is performed on the retrieved corresponding text. Through extensive qualitative experiments and analysis, our approach performs well on both Flickr30K and MSCOCO datasets and also significantly reduces the time required for testing. © 2024 SPIE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

SKSP: Selected Kernel Spatial Pattern Analysis in Euclidean and Hilbert Space for Decoding Motor Imagery 10

SKSP: Selected Kernel Spatial Pattern Analysis in Euclidean ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Zhibin, Zhang Niu, Jianwei Ren, Lu Ouyang, Zhenchao Mo, Shasha Beihang University School of Computer Science and Engineering Beijing China Zhongfa Aviation Institute Beihang University Hangzhou China Beihang University School of Cyber Science and Technology Beijing China

ISBN: (纸本)9798331520861

Brain-computer Interface (BCI) has promising prospects as the most active research direction in the fields of brain science and artificial intelligence. The Common Spatial Pattern (CSP) algorithm has attracted extensive attention and has been demonstrated to be effective for Motor Imagery (MI) tasks. However, CSP is limited to capturing complex nonlinear characteristics under its linear assumption. Many variants of CSP cannot deal with multiple relationships simultaneously. This paper proposes a Selected Kernel Spatial Pattern (SKSP) algorithm for human behavior recognition. Electroencephalogram (EEG) signals are projected onto a high-dimensional Reproducing Kernel Hilbert Space (RKHS) by the selected kernel function, where the nonlinear relationship is transformed into a linear one. This approach exploits wavelet transform and CSP patterns to compute the energy spectrum and differential entropy of data in RKHS to represent EEG patterns of brain activities. In addition, a multi-view module was proposed to strengthen pattern representations, which employs mutual information maximization to select the optimal sliding window in both frequency and time domains. The experiments are conducted on the BCI Competition IV-2a dataset. The four classes' classification accuracy reaches 92% in subject seven. The proposed method outperforms the best state-of-the-art classification method by 4% in average subject accuracy. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Exploring information hiding in images – problems and measures: a survey

引用

Multimedia Tools and Applications 2025年 1-63页

作者： Khan, Ahmed Sarfaraz, Aaliya School of Computer Science Taylor’s University Subang Jaya Malaysia School of Computing and Artificial Intelligence Faculty of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia

The widespread adoption of digital communication technologies across various domains has led to a significant shift towards digitalization. However, this evolution has also introduced vulnerabilities, including unauthorized access, data manipulation, and fabrication by malicious entities, which severely impact the confidentiality and integrity of information. The proliferation of digital images on the internet has facilitated the use of these media for embedding confidential data in a way that prevents detection or extraction by unauthorized third parties. Despite numerous efforts, existing image steganography and watermarking techniques often lack robustness. This paper proposes several novel strategies to enhance the dynamism and imperceptibility of these techniques, integrating cryptographic methods by manipulating the entropy of encrypted images using minimal pixel value differences and applying unique image transformations. Additionally, the study highlights that implementing multi-layered security mechanisms can protect confidential information from modern statistical steganalysis attacks, thereby preserving both the integrity of hidden data and image quality. A comprehensive review of information hiding, specifically focusing on image watermarking and steganography, is provided. Furthermore, this survey outlines key problem statements and offers quantitative metrics for future research in this area. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

An effective classification of Skin Disease using Deep Learning Techniques 13

An effective classification of Skin Disease using Deep Learn...

引用

13th International Conference on Cloud Computing, Data science and engineering, Confluence 2023

作者： Vajpayee, Harsh Arora, Chayanika Voleti, Ritvik Chaudhary, Ankur Raj, Gaurav Agrawal, Arun Prakash Sharda School of Engineering and Technology Sharda University Department of Computer Science and Engineering Greater Noida India Dalhousie University Master of Computer Science Halifax Canada

ISBN: (纸本)9781665462631

According to WHO, Skin Infection is very common but sometimes very serious and affects a large no population all over the world. Monkeypox, Chickenpox, and Measles are the major infectious disease that causes skin infection all over the world. It has been obverse that the cases of Monkeypox have drastically increased as an effect of Covid 19. This infection has spread easily and exponentially that cause serious health issues in many underdeveloped and developing countries. Some time it has been observed that people are not able to properly classify the type of skin infection well in time, which can be a main reason of serious health issues. So, it became important to propose an effective classification of Skin Disease. In this paper the authors have proposed an effective classification of Skin Disease using Deep Learning Techniques. This approach will help in classification of chicken pox, measles, and monkeypox through skin images. The authors have utilized Monkeypox Skin Images Dataset (MSID) dataset to apply the proposed approach. The Loss, Accuracy, Precision, Recall, AUC, and F1 Score parameters have been used to analyze the performance of proposed approaches. The best algorithms with maximum accuracy and other parameters are Xception, EfficientNetV2L, and EfficientNetV2M, and CNN, VGG16, and VGG19 are the least favored algorithms for this research. © 2023 IEEE.

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

A Target Recognition Method for High-Resolution Range Profiles in Imbalanced Datasets 2

A Target Recognition Method for High-Resolution Range Profil...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Su, Yitao Yin, Junjun Yang, Jian University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China Tsinghua University Department of Electronic Engineering Beijing China

ISBN: (纸本)9798331515669

Traditional high-resolution range profile (HRRP) recognition methods face challenges in automatically extracting targets' temporal and spatial information and demonstrate low recognition accuracy on multi-class imbalanced datasets. We propose an HRRP target recognition approach based on a lightweight Transformer and fully convolutional network (FCN) model to address these challenges. The Transformer's encoder and the FCN are utilized to extract deep temporal correlation features and deep spatial structural features of HRRP, respectively. An adaptive weight matrix is introduced at the decision level to enhance the expression capabilities of temporal features and spatial features. To address the class imbalance issue, we design an adaptive focal loss function combined with a label smoothing strategy, which enhances the model's sensitivity to minority classes and improves its generalization ability. Extensive experiments conducted on the MSTAR dataset validate the effectiveness of the proposed method. The model demonstrates superior recognition performance on both balanced and imbalanced datasets, and the proposed loss function outperforms other methods. © 2024 IEEE.

关键词： Automatic target recognition

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Cryptographic Approach for Secure Cloud-Based File Storage

A Hybrid Cryptographic Approach for Secure Cloud-Based File ...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Negi, Kanishka Shrestha, Ronika Borges, Tanya Lillian Sahana, Subrata Das, Sanjoy Sharda University Computer Science and Engineering School of Engineering and Technology Greater Noida India Indira Gandhi National Tribal University Department of Computer Science India

ISBN: (纸本)9798350331790

The tremendous increase of sensitive data on the cloud has rendered it more vulnerable. Thus, undoubtedly, the risk stems from an expanding number of individuals with harmful motives. Because the cloud is handled by a third party, guaranteeing cloud security services is critical. The security of the data may be strengthened by combining different symmetric key techniques to store the information on the server so that even if someone gains access, they are unable to access the original data. It must be decrypted, thus. A hybrid model that combines Advanced Encryption Standard (AES) algorithm and Elliptical Curve Cryptography (ECC) is put forth. ECC is employed to complete the user verification process and maintain the security of private data. Data is encrypted on the client side and then decrypted after being downloaded from the cloud, the AES technique is used to securely store and retrieve users' data in the cloud. Data is protected by encryption on the client's side and then decoded after it has been downloaded from the cloud. Enabling a suitable access mechanism to stop unlicensed access to information in the system and safe storage to allow access to information over a cloud-based network would be advantageous for the complete prototype of the suggested solution. The proposed method is efficient for encrypting small to moderate amounts of data as 1.02 milliseconds is a relatively fast encryption time. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Link Prediction in Educational Graph Data to Predict Elective Course using Graph Convolutional Network Model

Link Prediction in Educational Graph Data to Predict Electiv...

引用

2023 International Conference on computer science, Information technology and engineering, ICCoSITE 2023

作者： Indah Susanti, Meilia Nur Heryadi, Yaya Rosmansyah, Yusep Budiharto, Widodo Computer Science Bina Nusantara University Computer Science Departement Jakarta Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Bina Nusantara University School of Computer Science Computer Science Departement Jakarta Indonesia

ISBN: (纸本)9798350320954

Personalized learning has achieved the attention of many researchers in the Education field. Personalized learning is a teaching model in which students (learners) have a central role in the learning process. By using this approach, educational methods, and techniques are customized and adapted to be better suited for each learner, with their unique learning style, background, needs, and previous experiences. Based on what the learners have already learned, subjects have already known, and skills have already developed each student in a personalized learning process will get a "learning plan". This approach is different from a conventional approach or known as the "one size fits all"approach. The challenge of personalized learning is how to connect a learner's previous knowledge, skills and with learning materials that will link that understanding with new knowledge. This paper presents a novelty technique to implement personalized learning by automating a predicted linkage between a student in higher education and elective courses based on previous learning achievement. In this study, Graph Convolutional Networks (GCNs) are used to address link prediction tasks between student and elective courses. The empirical results showed that the GCN model can be used to predict elective courses for a student with 62.5 % average accuracy. © 2023 IEEE.

关键词： Forecasting

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：