检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pratheesh, R. Divya, V. School Of Computing Sciences Vels Institute Of Science Technology & Advanced Studies India School Of Computing Sciences Vels Institute Of Science Technology & Advanced Studies Department Of Information Technology Chennai India

ISBN: (纸本)9798350318609

Big data analytics delves into these immense datasets to reveal hidden patterns and correlations, yet its pervasive use raises substantial security and privacy concerns. This article centers on the specific issues concerning privacy and security within the realm of big data, distinguishing between these concerns and outlining their distinct requirements. The focus is on various privacy strategies, including L-diversity, k-anonymity, HyBrEx, and T-closeness, examining their practical applications in diverse business contexts. Privacy protection methods have surfaced throughout various stages of the big data life cycle, aiming to ensure privacy during data creation, retention, and handling. This paper provides an extensive review of these privacy mechanisms while addressing the challenges encountered by current approaches. As the extended comprehensive study is experimented with features extraction techniques such as Principle component analysis (PCA), Independent component analysis (ICA), Linear discriminant analysis(LDA) the evaluated performance in terms of accuracy achieved with 98%, 99% and 95% respectively. © 2024 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Multi-dataset learning with channel modulation loss for blind image quality assessment

引用

Multimedia Tools and Applications 2024年第40期83卷 88159-88178页

作者： Li, Hui Yan, Zhaoyi Fan, Xiaopeng Department of Computing Science Harbin Institute of Technology Harbin China Department of Network Intelligence Pengcheng Laboratory Shenzhen China

In Blind Image Quality Assessment (BIQA), due to the problem of laborious labeling, it is perceived as the intractability of collecting a new large-scale dataset that has plentiful images with a large diversity in distortion and scene. Therefore, to develop a general model, training with data from diverse datasets could be a viable solution and hold significant value. A straightforward solution is to mix multiple datasets to train a robust model. However, as IQA datasets vary in terms of distortion types and labeling mechanisms, models fail to adapt well across various datasets. To solve the multi-dataset adaption problem, we propose a Channel Modulation Loss that encourages each channel to adaptively enhance/diminish dataset-corresponding features. In detail, when training a CNN with data from all the datasets, certain channels acquire knowledge that can be applied across some datasets, whereas others are only effective for a specific dataset. Therefore, we propose a dataset-specific kernel as supervision, by which channel attention can be explicitly optimized to emphasize the channels corresponding to the dataset of an input image. Finally, extensive experiments on six IQA databases show the promise of the learned method in blindly assessing image quality. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fusion for facial expression recognition

引用

Neural computing and Applications 2025年第17期37卷 11399-11420页

作者： Guo, Jiatao Peng, Junjie Huang, Yansong Chen, Gan Cai, Zesu Tan, Shuhua School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China National Engineering Laboratory for Logistics Information Technology YTO Express Co. Ltd. Shanghai China

As an important computer vision task that can be used in many areas, facial expression recognition (FER) has been widely studied which much progress has been obtained especially when deep learning (DL) approaches have been introduced in FER. However, existing methods are restricted to extracting localized information or utilizing attention mechanism to focus on the region most relevant to the emotion, possibly resulting in errors in facial expression interpretation. Moreover, the inconsistency of image sizes in the wild FER datasets further increases the difficulty of the FER task. To address these issues, we propose a multi-scale feature fusion (MSFF) for FER. Specifically, our method first extracts features from facial images using multi-scale feature extraction to obtain rich multi-dimensional information. Meanwhile, extensive feature extraction at different scales is achieved by expanding the receptive field of the model, which provides the basis for more detailed analysis of facial expressions. Eventually, features at different scales are fused to enhance their synergistic effect. Subsequently, the adaptive extraction of comprehensive and valuable information from the fused features is performed, optimizing the performance of expression recognition. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on in-the-wild datasets. It is promising for FER in realistic and complex scenarios. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis of multi social media using machine and deep learning models: a review

引用

Multimedia Tools and Applications 2024年第42期83卷 90033-90051页

作者： Vasanthi, P. Madhu Viswanatham, V. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

The Internet has become an important origin of text information, which is then used inside a wide range of research domains. This has been regarded as a necessary foundation for institutions to obtain valuable information in addition to assessing consumers' feelings and views on a particular subject. Message clustering is the method of assigning specific tags to known categories based on one ‘s content material. It is difficult to classify the text using aspect-based sentiment. So each research on sentiment has addressed this issue, as existing research focuses on file and predominant component assessment instead of the specifics of the emotions. This survey reviewed the sentiment analysis based on both X and Facebook. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

SecuDroid : Android Malware Detection using ML classifier on Static Features 2

SecuDroid : Android Malware Detection using ML classifier on...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Vanusha, D. Singh, Shashank Jha, Abhijeet Kumar Delsi Robinsha, S. School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350365269

The Android operating system's widespread use has unfortunately made it a target for malware attacks, underlining the necessity for robust detection strategies. Existing literature has explored the potential of machine learning in combating Android malware, often employing a mix of static and dynamic analyses. However, a major portion of these malwares are zero-day vulnerabilities. In this context, our study makes a significant contribution by focusing on using static features extracted from Android application package (APK) files to differentiate between benign and malicious applications. Specifically, all training and testing in this study were performed on the Drebin-215 dataset, a comprehensive collection known for its relevance in Android security research. Improving malware detection using static features allows for detection of malwares before they are run on devices. We analyzed five ML classification algorithms, beginning with a Decision Tree, followed by SVM (Support Vector Machine) with an RBF kernel, then moving to Logistic Regression and K-Nearest Neighbor, and finally, we introduced our proposed model, the SecuDroid Neural Network - employing a methodology that employs precise hyper-parameter tuning, and evaluation through stratified 4-fold cross-validation. The evaluation on an unseen test dataset, based on accuracy, F1-score, and AUC metrics, revealed the SecuDroid Neural Network surpassed its counterparts by reaching an accuracy of 0.993, an F1-score of 0.991, and an AUC of 0.999. Our findings not only offer a comparative analysis of different machine learning models for malware detection but also introduce an efficient approach, thereby enriching the arsenal against Android malware threats, with all empirical validations grounded in the Drebin-215 dataset. © 2024 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

MixDiT: Accelerating Image Diffusion Transformer Inference With Mixed-Precision MX Quantization

IEEE Computer Architecture Letters

引用

IEEE computer Architecture Letters 2025年第1期24卷 141-144页

作者： Kim, Daeun Hwang, Jinwoo Oh, Changhun Park, Jongse Korea Advanced Institute of Science and Technology School of Computing Graduate School of AI Semiconductor Daejeon34141 Korea Republic of

Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on datacenter-scale GPUs, primarily due to its iterative nature and heavy reliance on GEMM operations inherent to its encoder-based structure. To address the challenge, prior work has explored quantization, but achieving low-precision quantization for DiT inferencing with both high accuracy and substantial speedup remains an open problem. To this end, this paper proposes MixDiT, an algorithm-hardware co-designed acceleration solution that exploits mixed Microscaling (MX) formats to quantize DiT activation values. MixDiTquantizes the DiT activation tensors by selectively applying higher precision to magnitude-based outliers, which produce mixed-precision GEMM operations. To achieve tangible speedup from the mixed-precision arithmetic, we design a MixDiTaccelerator that enables precision-flexible multiplications and efficient MX precision conversions. Our experimental results show that MixDiTdelivers a speedup of 2.10–5.32× over RTX 3090, with no loss in FID. © 2002-2011 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

PODBoost: an explainable AI model for polycystic ovarian syndrome detection using grey wolf-based feature selection approach

引用

Neural computing and Applications 2024年第30期36卷 18627-18644页

作者： Moral, Poonam Mustafi, Debjani Sahana, Sudip Kumar Department of Computer Science and Engineering Birla Institute of Technology Mesra Jharkhand Ranchi835215 India

Polycystic Ovary Syndrome (PCOS) is a recurring endocrine disorder that primarily affects women of reproductive age. It is difficult to diagnose due to its heterogeneous characteristics and overlapping symptoms with other illnesses. As a result, accurate and trustworthy prediction models are required to detect PCOS early. This research work aims to develop ML methods that predict the risk of PCOS among women based on demographic and clinical features. The entire framework is divided into four phases: in Phase I of the study, the SMOTE-Tomek Links (SMTL) technique balances the data set by combining oversampling and undersampling approaches. A novel meta-heuristic-based feature selection approach, the Grey Wolf Optimization (GWO) method, has been employed to select the most crucial features from the dataset, explained in Phase II. Subsequently, in Phase III, a hybridized classifier PODBoost algorithm (Polycystic Ovarian Disorder Boosting algorithm) is devised for faithful early prediction of PCOS using the concepts of different classical supervised learning algorithms. Finally, Explainable AI (XAI) such as the Local Interpretable Model-Agnostic Explanations (LIME) tool has been implemented to interpret relevant predictions made by the proposed classifier. The proposed algorithm is examined utilizing numerous metrics such as Accuracy, Error-Rate, ROC-AUC Score, Recall, Precision, and F1-Score. Among all the evaluated models, the proposed hybridized model has shown an impressive performance with an exceptional accuracy of 97.42%, indicating its superiority by delivering outstanding results. Based on the findings, the novel meta-heuristic-based feature selection method significantly impacts the outcomes of the proposed hybridized PODBoost algorithm. This algorithm may be recommended to predict PCOS or other relevant diseases having datasets which are multimodal in nature. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 202

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

引用

Journal of computer science & technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

来源：评论

学校读者我要写书评

暂无评论

Explainable AI in Large Language Models: A Review 2

Explainable AI in Large Language Models: A Review

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Sauhandikaa, S. Bhagavath Narenthranath, R. Sathya Bama Krishna, R. Sathyabama Institute of Science and Technology School of Computing Chennai India

ISBN: (纸本)9798331534950

Explainable AI in Large Language Models (LLMs) represents an exciting frontier in Artificial Intelligence. In recent times, LLMs provides various AI applications ranging from chatbots to content generation. While these applications are exciting, their decision-making process behind the intelligent systems plays a major role. These processes are also a mystery and they operate as "Black boxes", where the processes are often challenging to interpret. This paper helps to give a sense of the processes that occurs behind these decisions. It helps to understand why the AI has chosen one sentence rather than the other. It explores key breakthroughs of XAI techniques that helps in solving these complexities. Methods such as Attention Visualization, Feature Importance Analysis and Counterfactual Explanations provide insights on why certain decisions are made. These techniques provide a voice to the intricate processes and address real-world challenges, which makes it more reliable. This enables better transparency and makes it trust-worthy. XAI has the potential to address ethical concerns, enhance user trust and improve Human-AI collaboration. This research highlights how better transparency in AI is not merely a technical challenge but a foundational step towards building a future where humans and AI work together seamlessly and responsibly. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection using VGG16 CNN with Data Augmentation 2

Brain Tumor Detection using VGG16 CNN with Data Augmentation

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Sri Sathwik, P. Yugandran, B. Bandyopadhyay, Om Prakash, B. Shanmugam, Selvanayaki Kolandapalayam Srm Institute of Science and Technology Computing Technologies School of Computing Kattankulathur Chennai India Ashland University Department of Mathematics and Computer Science OH United States

ISBN: (纸本)9798350372892

Brain tumors represent a critical condition characterized by the abnormal growth of cells in specific brain regions, potentially forming life-threatening masses. Early diagnosis is crucial for prompt treatment, yet the laborious and time-consuming human analysis of magnetic resonance imaging (MRI) can cause significant delays. Recent advancements in deep learning have revolutionized healthcare and medical diagnostics, offering promising solutions to these challenges. Given the constraint of limited datasets, improving deep learning algorithms, particularly convolutional neural networks (CNNs), becomes essential. Data augmentation techniques effectively address dataset limitations, enabling the training of various CNN architectures such as VGG16, EfficientNetB0, MobileNetV2, and DenseNet121. These models are compared using evaluation metrics like accuracy and other standard classification metrics, with the VGG model demonstrating superior performance, achieving a notable 97% accuracy rate. This research underscores the potential of deep learning and CNNs in accelerating brain tumor identification from MRI images, emphasizing the advantages of different CNN architectures in medical applications. © 2024 IEEE.

关键词： Magnetic resonance imaging

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：