检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 556-565页

作者： Aralikatti, Rajath C Pawan, S.J. Rajan, Jeny National Institute of Technology Karnataka Department of Computer Science and Engineering Surathkal575025 India

Deep neural networks have played a vital role in developing automated methods for addressing medical image segmentation. However, their reliance on labeled data impedes the practicability. Semi-Supervised learning is gaining attention for its intrinsic ability to extract valuable information from labeled and unlabeled data with improved performance. Recently, consistency regularization methods have gained interest due to their efficient learning procedures. They are, however, confined to data or network-level perturbations, negating the benefit of having both forms in a single framework. In light of this, we ask an intriguing but unexplored question: Can we have both network-level and data-level perturbation in the semi-supervised framework? To this end, we present a holistic approach that integrates data-level perturbation in the model pre-training stage, followed by implicit network-level perturbation in the fine-tuning stage. Furthermore, we incorporate networks with manifold learning paradigms throughout the training to facilitate the formation of robust data representations by ensuring local and global semantic affinities adhering to the theory of consensus. Notably, this may be the first attempt in the semi-supervised medical image segmentation archetype to use data and network-level perturbation with a model pre-training strategy. We extensively validated the efficacy of the proposed framework on three benchmark datasets, namely the Automated Cardiac Diagnosis Challenge, ISIC-2018, and Left Atrial Segmentation Challenge datasets, subjected to severely low-sampled labeled data. Notably, in ACDC (4%), ISIC-2018 (5%), and LA (6%) labeled cases, the proposed method outperforms the second-best method by 2.95%, 1.31%, and 0.71% in the Dice Similarity Metric. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Maximizing Emotion Recognition Accuracy with Ensemble Techniques on EEG Signals

引用

Recent Advances in computer science and Communications 2024年第5期17卷 24-36页

作者： Jha, Sonu Kumar Suvvari, Somaraju Kumar, Mukesh Department of Computer Science and Engineering National Institute of Technology Patna Patna800005 India

Background: Emotion is a strong feeling such as love, anger, fear, etc. Emotion can be recognized in two ways, i.e., External expression and Biomedical data-based. Nowadays, various research is occurring on emotion classification with biomedical data. Aim: One of the most current studies in the medical sector, gaming-based applications, education sector, and many other domains is EEG-based emotion identification. The existing research on emotion recognition was published using models like KNN, RF Ensemble, SVM, CNN, and LSTM on biomedical EEG data. In general, only a few works have been published on ensemble or concatenation models for emotion recognition on EEG data and achieved better results than individual ones or a few machine learning approaches. Various papers have observed that CNN works better than other approaches for extracting features from the dataset, and LSTM works better on the sequence data. Methods: Our research is based on emotion recognition using EEG data, a mixed-model deep learning methodology, and its comparison with a machine learning mixed-model methodology. In this study, we introduced a mixed model using CNN and LSTM that classifies emotions in valence and arousal on the DEAP dataset with 14 channels across 32 people. Result and Discussion: We then compared it to SVM, KNN, and RF Ensemble, and concatenated these models with it. First preprocessed the raw data, then checked emotion classification using SVM, KNN, RF Ensemble, CNN, and LSTM individually. After that with the mixed model of CNN-LSTM, and SVM-KNN-RF Ensemble results are compared. Proposed model results have better accuracy as 80.70% in valence than individual ones with CNN, LSTM, SVM, KNN, RF Ensemble and concatenated models of SVM, KNN and RF Ensemble. Conclusion: Overall, this paper concludes a powerful technique for processing a range of EEG data is the combination of CNNs and LSTMs. Ensemble approach results show better performance in the case of valence at 80.70% and 78.24

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

SuspAct: novel suspicious activity prediction based on deep learning in the real-time environment

引用

Neural Computing and Applications 2024年第34期36卷 21307-21320页

作者： Kansal, Sachin Jain, Akshat Kumar Biswas, Moyukh Bansal, Shaurya Mahindru, Namay Kansal, Priya Computer Science Engineering Department Thapar Institute of Engineering and Technology Punjab Patiala India

In today’s evolving landscape of video surveillance, our study introduces SuspAct, an innovative ensemble model designed to detect suspicious activities in real time swiftly. Leveraging advanced Long-term Recurrent Convolutional Networks (LRCN), SuspAct represents a significant advancement in intelligent surveillance technology. By combining insights from various LRCN models through the Majority Voting ensemble technique, SuspAct enhances its overall robustness, outperforming traditional surveillance methods. Through rigorous experimentation on large-scale datasets, we demonstrate SuspAct’s superiority in proactive crime prevention, showcasing its potential to revolutionize security protocols and contribute substantially to public safety. Our work addresses the challenges posed by the escalating volume of video data and lays a strong foundation for future advancements in intelligent video surveillance technology. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ResdenseNet: a lightweight dense ResNet enhanced with depthwise separable convolutions and its applications for early plant disease classification

引用

Neural Computing and Applications 2025年第8期37卷 6305-6326页

作者： Nagpal, Jyoti Goel, Lavika Department of Computer Science & Engineering The NorthCap University Gurugram122017 India Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India

In recent years, artificial intelligence has undergone robust development, leading to the emergence of numerous autonomous AI applications. However, a crucial challenge lies in optimizing computational efficiency and reducing training time while maintaining high accuracy with limited hardware resources. This paper introduces ResdenseNet, a model built upon the MobileNet, DenseNet, and ResNet architectures. ResdenseNet combines dense blocks and residual blocks from the DenseNet and ResNet architectures. In these dense blocks, the standard convolutional units are replaced by depthwise separable convolutional units, a significant part of the MobileNet architecture. The experimental outcomes are contrasted with established models and their iterations, including ResNet-50, ResNet-101, MobileNet-V1, MobileNet-V2, DenseNet-121, and DenseNet-169. The proposed model is tested on benchmark and proposed datasets, showcasing its efficiency in reducing computations and accelerating the training process. Emphasizing hyperparameter importance, ResdenseNet, optimized with a growth rate of 64, 6 layers, and ReLU activation, achieves an accuracy of (98.73%) and a F1-score of (98.20%) on the wheat and barley dataset. The results indicate that ResdenseNet significantly decreases the number of parameters to 0.72M and efficiently shortens training time to 5983.54 s. Particularly noteworthy is ResdenseNet’s superiority over other models in terms of having the fewest parameters, the shortest training time, and the highest accuracy, especially when dealing with wheat, barley, and maize datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Deep CNNs for glioma grading on conventional MRIs: Performance analysis, challenges, and future directions

引用

Mathematical Biosciences and Engineering 2024年第4期21卷 5250-5282页

作者： Saluja, Sonam Trivedi, Munesh Chandra Saha, Ashim Department of Computer Science and Engineering National Institute of Technology Agartala Tripura 799046 India

The increasing global incidence of glioma tumors has raised significant healthcare concerns due to their high mortality rates. Traditionally, tumor diagnosis relies on visual analysis of medical imaging and invasive biopsies for precise grading. As an alternative, computer-assisted methods, particularly deep convolutional neural networks (DCNNs), have gained traction. This research paper explores the recent advancements in DCNNs for glioma grading using brain magnetic resonance images (MRIs) from 2015 to 2023. The study evaluated various DCNN architectures and their performance, revealing remarkable results with models such as hybrid and ensemble based DCNNs achieving accuracy levels of up to 98.91%. However, challenges persisted in the form of limited datasets, lack of external validation, and variations in grading formulations across diverse literature sources. Addressing these challenges through expanding datasets, conducting external validation, and standardizing grading formulations can enhance the performance and reliability of DCNNs in glioma grading, thereby advancing brain tumor classification and extending its applications to other neurological disorders. © 2024 the Author(s).

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Dual Watermarking for Image Copyright Protection and Authentication

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6134-6145页

作者： Padhi, Sudev Kumar Tiwari, Archana Ali, Sk. Subidh Indian Institute of Technology Bhilai Department of Computer Science and Engineering Durg491002 India

Advancements in digital technologies make it easy to modify the content of digital images. Hence, ensuring digital images' integrity and authenticity is necessary to protect them against various attacks that manipulate them. We present a deep learning (DL) based dual invisible watermarking technique for performing source authentication, content authentication, and protecting digital content copyright of images sent over the internet. Beyond securing images, the proposed technique demonstrates robustness to content-preserving image manipulation attacks. It is also impossible to imitate or overwrite watermarks because the cryptographic hash of the image and the dominant features of the image in the form of perceptual hash are used as watermarks. We highlighted the need for source authentication to safeguard image integrity and authenticity, along with identifying similar content for copyright protection. After exhaustive testing, our technique obtained a high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM), which implies there is a minute change in the original image after embedding our watermarks. Our trained model achieves high watermark extraction accuracy and satisfies two different objectives of verification and authentication on the same watermarked image. © 2020 IEEE.

关键词： Watermarking Copyright Protection Authentication Robustness Decoding Deep Learning Artificial Intelligence Accuracy PSNR Feature Extraction Copyright Protection Cryptographic Hash Deep Learning Image Authentication Perceptual Hash Watermarking

来源：评论

学校读者我要写书评

暂无评论

Designing New Blood-Brain Barrier Penetrating Molecules Using Novel Hybridized Gravitational Search Algorithm and Explainable AI

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2127-2138页

作者： Singh, Vishakha Sharma, Ritesh Singh, Sanjay Kumar Indian Institute of Technology BHU Department of Computer Science and Engineering Varanasi221005 India

Artificial intelligence (AI) has emerged as a powerful tool in computational biology, where it is being used to analyze large datasets to detect difficult biological patterns. This has enabled the design of new drug molecules. In this article, a novel method called hybridized gravitational search algorithm (HyGSA) has been proposed to design novel blood-brain barrier penetrating peptides (B3P2s) with desirable characteristics that enable them to cross the blood-brain barrier (BBB) and deliver neurological drugs directly to the brain. The HyGSA has two important modules in the form of an explainable machine learning classifier (with an accuracy, f1-score, and area under the ROC curve (AUROC) of 84%, 84%, and 91%, respectively) and an explainable deep learning-based B3P2 classifier (with an accuracy, f1-score, and AUROC of 89%, 91%, and 95%, respectively). The former was used to determine the crucial hand-engineered features, and the latter was designed to determine the critical amino acids that play an important role in the BBB penetrability of a peptide. Moreover, the population of particles was sampled at the beginning of each iteration to ensure a good mix of particles with low, average, and high fitness. This was achieved using a novel method that takes inspiration from the subset-sum problem and uses the mean and variance of the distribution of particles. For the pilot study, some B3P2s were discovered and optimized from a set of cell-penetrating peptides. Lastly, a free online tool has been deployed at https://*** to help the scientific community discover and optimize B3P2s in protein sequences. © 2023 IEEE.

关键词： Peptides

来源：评论

学校读者我要写书评

暂无评论

Heart sound classification method using gammatonegram and SVM

引用

Multimedia Tools and Applications 2024年 1-37页

作者： Taneja, Kriti Arora, Vinay Verma, Karun Computer Science and Engineering Department Thapar Institute of Engineering and Technology Punjab Patiala India

Today cardiovascular diseases have been posing a serious threat to human lives all over the world. Various automated decision-making systems have been proposed by the researchers to help cardiologists to diagnose heart health with more perfection, thus, reducing the frequency of fatalities. This research aims at classifying the Phonocardiogram (PCG) signals captured from the functioning of the cardiac system as normal or abnormal. The methodology proposed here has been validated using the benchmark dataset PhysioNet Computing in Cardiology (CinC) 2016. As of this writing, the studies carried out using contemporary techniques have so far been unable to generate pictorial representation from cardiac audio recordings that match the way the ear processes sound. The present research suggests a unique methodology for the detection of important events in an audio signal using a biologically-inspired depiction of the audio stream through a picture known as Gammatonegram which correlates to the processing of audio in the cochlea membrane of the inner human auditory system. In this study, texture-related features which include Linear Ternary Pattern (LTP), Local Directional Pattern (LDP), Geometric Local Textural Pattern (GLTP), and Local Phase Quantization (LPQ) have been extracted from a visual representation of PCG signal such as Spectrogram, Scalogram, Mel-spectrogram, and Gammatonegram. As compared to the case when researchers were employing other images, it has been noticed that the fusion of the features retrieved from the Gammatonegram has led to an increased overall classification performance metrics. The experiment yielded an overall accuracy of 94.00 % with precision and F1 scores of 91.77 and 93.61 respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

MemDefense: Defending against Membership Inference Attacks in IoT-based Federated Learning via Pruning Perturbations

引用

IEEE Transactions on Big Data 2024年 1-13页

作者： Shen, Meng Meng, Jin Xu, Ke Yu, Shui Zhu, Liehuang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science Tsinghua University Beijing China School of Computer Science University of Technology Sydney Sydney NSW Australia

Depending on large-scale devices, the Internet of Things (IoT) provides massive data support for resource sharing and intelligent decision, but privacy risks also increase. As a popular distributed learning framework, Federated Learning (FL) is widely used because it does not need to share raw data while only parameters to collaboratively train models. However, Federated Learning is not spared by some emerging attacks, e.g., membership inference attack. Therefore, for IoT devices with limited resources, it is challenging to design a defense scheme against the membership inference attack ensuring high model utility, strong membership privacy and acceptable time efficiency. In this paper, we propose MemDefense, a lightweight defense mechanism to prevent membership inference attack from local models and global models in IoT-based FL, while maintaining high model utility. MemDefense adds crafted pruning perturbations to local models at each round of FL by deploying two key components, i.e., parameter filter and noise generator. Specifically, the parameter filter selects the apposite model parameters which have little impact on the model test accuracy and contribute more to member inference attacks. Then, the noise generator is used to find the pruning noise that can reduce the attack accuracy while keeping high model accuracy, protecting each participant's membership privacy. We comprehensively evaluate MemDefense with different deep learning models and multiple benchmark datasets. The experimental results show that lowcost MemDefense drastically reduces the attack accuracy within limited drop of classification accuracy, meeting the requirements for model utility, membership privacy and time efficiency. IEEE

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Conditional Random Field-Based Blockchain Access with Hybrid Encryption for Data Privacy Preservation

引用

SN computer science 2024年第8期5卷 1-23页

作者： Viswanadham, Yedida Venkata Rama Subramanaya Panaiyappan, K. Annapurani Department of Networking and Communications SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India

Data Privacy Preservation (DPP) is a control measures to protect users sensitive information from third party. The DPP guarantees that the information of the user’s data is not being misused. User authorization is highly performed by blockchain technology that provide authentication for authorized user to utilize the encrypted data. Effective encryption techniques are emerged by employing ̣ deep-learning network and also it is difficult for illegal consumers to access sensitive information. Traditional networks for DPP mainly focus on privacy and show less consideration for data security that is susceptible to data breaches. It is also necessary to protect the data from illegal access. In order to alleviate these issues, a deep learning methods along with blockchain technology. So, this paper aims to develop a DPP framework in blockchain using deep learning. Hence, the Adaptive Deep Conditional Random Field (ADCRF) is a deep learning network utilized for accessing the blockchain in a secure manner. The parameters in the ADCRF network are optimized by Improved Running City Game Optimizer (RCGO). For securely accessing the blockchain, the data is stored after the encryption process. The data privacy is ensured by the Hybrid Elgammal-Attribute-based Encryption (HEA) method. Hybrid encryption methods enhance the security during the data preservation process. The numerical findings of the developed model are differentiated from the existing baseline works to ensure the performance of the proposed approach. The experimental findings of the developed model attain 96.35, 96.27, 96.40, 93.48 and 94.85 regarding accuracy, recall, specificity, precision, and F1-score respectively. This analysis could strengthen the developed framework to secure data with the help of user authentication model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adaptive deep conditional random field Blockchain access Data privacy preservation Hybrid Elgammal-attribute-based encryption Improved running city game optimizer

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：