检索结果-内蒙古大学图书馆

Estimating Ensemble Location and Width in Binaural Recordings of Music with convolutional neural networks

ARCHIVES OF ACOUSTICS 2025年第1期50卷 81-93页

作者： Antoniuk, Pawel Zielinski, Slawomir K. Bialystok Tech Univ Fac Comp Sci Bialystok Poland

Binaural audio technology has been in existence for many years. However, its popularity has significantly increased over the past decade as a consequence of advancements in virtual reality and streaming techniques. Along with its growing popularity, the quantity of publicly accessible binaural audio recordings has also expanded. Consequently, there is now a need for automated and objective retrieval of spatial content information, with ensemble location and width being the most prominent. This study presents a novel method for estimating these ensemble parameters in binaural recordings of music. For this purpose, a dataset of 23 040 binaural recordings was synthesized from 192 publicly-available music recordings using 30 head-related transfer functions. The synthesized excerpts were then used to train a multi-task spectrogram-based convolutional neural network model, aiming to estimate the ensemble location and width for unseen recordings. The results indicate that a model for estimating ensemble parameters can be successfully constructed with low prediction errors: 4.76 circle (+/- 0.10 circle) for ensemble location and 8.57 circle (+/- 0.19 circle) for ensemble width. The method developed in this study outperforms previous spatiogram-based techniques recently published in the literature and shows promise for future development as part of a novel tool for binaural audio recordings analysis.

关键词： ensemble width ensemble location binaural spatial audio localization convolutional neural net- work head-related transfer function angle of arrival

来源：评论

学校读者我要写书评

暂无评论

Image Classification with Regularized Likelihood Estimation and Large Interval Discriminant Dimensionality Reduction

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2025年第2期41卷 385-400页

作者： Shen, Ying Zhu, Wei-hua Fu, Si-yong Wu, Guang-sheng Xinyu Univ Zhongxing Commun & Informat Coll Xinyu 338004 Peoples R China Xinyu Univ Sch Math & Comp Sci Xinyu 338004 Peoples R China

With the expansion of image application scale and the development of artificial intelligence industry, the demand for high precision and high robustness of image feature expression is gradually increasing. convolutional neural networks (CNNS) have attracted much attention in the field of computer vision in recent years because of their excellent image feature learning ability. In order to further improve the accuracy and robustness of image classification, a second-order statistical convolutional neural network with multilayer fusion and cross-convolutional layer pooling are proposed in this study to obtain feature information of different dimensions in different convolutional layers. Due to the increase of computing and storage costs, an image classification method based on robust covariance of deep convolution features is proposed, and two regularized maximum likelihood estimators are introduced. Finally, the proposed method is tested by fine-grained experiments, image retrieval experiments and image classification experiments. The results show that MFBP (4,5) structure achieves 92.4%, 74.2% and 72.9% accuracy in finegrained image classification. Compared with MFBP (3,4,5), despite a slight decrease in accuracy, FPS performance is improved by more than 40%, demonstrating the advantages of this method in real-time applications. In addition, RMIE-VND and RMIE-IM methods improved by 4.1%, 8.4%, 7.8% and 7.1%, 12%, 9.8%, respectively, compared with LW methods on different data sets. The experimental results of image classification show that MFBP+RLME (VND+IM) has better performance and applicability than the current mainstream classification methods. This research is of great value for improving the efficiency and accuracy of image processing in big data environment, and provides a new research direction and practical tool for future real-time image application and computer vision system development.

关键词： image classification image dimensionality reduction convolutional neural net- work bilinear pooling regularized likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for Enhanced Information Security: A Comprehensive Approach to Threat Detection and Mitigation

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第12期15卷 964-972页

作者： Wang, Kaijing Chuzhou City Vocat Coll Sch Management & Informat Chuzhou 239000 Anhi Peoples R China

-Forcing developments in cyberspace means protecting information resources requires enhanced and more dynamic protection models. Traditional approaches don't adequately address the numerous, sophisticated, varied, and frequently intersecting emergent security challenges, such as malware, phishing, and DDoS attacks. This paper introduces a novel hybrid deep learning framework leveraging convolutional neural networks (CNN) and recurrent neural networks (RNN) for enhanced threat detection and mitigation within a Zero Trust Architecture (ZTA). The model identifies anomalies indicative of potential security threats by analysing large network traffic datasets. To decrease false positive instances, autoencoders are integrated, significantly improving the system's ability to differentiate between normal and anomalous behaviour. Extensive experiments were conducted using a benchmark cybersecurity dataset, achieving an accuracy rate of 98.75% and a false positive rate of only 1.43%. Compared to traditional approaches, this dynamic deep learning framework is highly adaptable, requiring little oversight to respond effectively to new and evolving threats. From the study results, it can be concluded that deep learning provides a robust and scalable solution for addressing emerging cyber threats and creating a more secure and reliable information security environment. Future work will focus on extending the framework to improve its accuracy and robustness, further advancing cybersecurity capabilities. This research significantly contributes to information security, establishing a promising direction for applying machine learning to enhance cybersecurity.

关键词： Artificial intelligence deep learning information security threat detection cybersecurity convolutional neural net- work recurrent neural network mitigation

来源：评论

学校读者我要写书评

暂无评论

Efficient Underwater Object Detection Using Deep neural networks 5

Efficient Underwater Object Detection Using Deep Neural Netw...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Rasool, Shaik Atheeq Annamalai, R. Natarajan, B. Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amrita School of Computing Chennai India

ISBN: (纸本)9798350383522

The increasing amount of underwater visual data and deep sea research have led to the rise of marine animal identification as a major field for data processing and analysis. The need to protect the ecosystem emphasizes how important this endeavor is, yet it's still difficult because of things like the complexities of underwater backdrops, poor picture and video quality, and the variety of movements that marine life exhibits. This research used deep learning techniques to identify certain marine species and mark their presence with bounding boxes in uploaded images and videos in order to overcome these difficulties. The main goal is to provide workable methods for detecting marine life, so providing crucial backing for further studies in this area. By using the core deep learning frameworks, YOLOv8 and Faster-RCNN, the research was able to improve the efficiency and accuracy of marine life identification by making significant progress in detection time and mean average precision (mAP). This research work not only solves the current problems with finding marine animals but also establishes the groundwork for future research into comprehending and protecting the fragile undersea ecology. © 2024 IEEE.

关键词： convolutional neural net- work Faster R-CNN Object Detection

来源：评论

学校读者我要写书评

暂无评论

Exploiting Deepfakes by Analyzing Temporal Feature Inconsistency

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第12期14卷 908-916页

作者： Gu, Junlin Xu, Yihan Sun, Juan Liu, Weiwei Jiangsu Vocat Coll Elect & Informat Huaian Peoples R China

In recent years, the rapid advancement of image generation technology has facilitated the creation of counterfeit images and videos, posing significant challenges for content authenticity verification. Malefactors can easily extract videos from social networks and generate their own deceptive renditions using state-of-the-art techniques. The latest Deepfake face forgery videos have reached an unprecedented level of sophistication, making it exceptionally difficult to discern signs of manipulation. While several methods have been proposed for detecting fraudulent media, they often target specific aspects, and as new attack methods emerge, these approaches tend to become obsolete. This paper presents a novel detection approach that combines convolutional neural networks (CNN) and Long ShortTerm Memory networks (LSTM). Initially, CNN is employed to extract image features from each frame of the input facial video, capturing subtle alterations and irregularities in manipulated content. Subsequently, the extracted feature sequence is used to train the LSTM network, mimicking the temporal consistency of human visual perception and enhancing the effectiveness of counterfeit video detection. To validate this methodology, a comprehensive evaluation is conducted using the FaceForensic++ dataset, affirming its proficiency in identifying Deepfake counterfeit videos.

关键词： Face forgery detection convolutional neural net- work Long Short-Term Memory network time consistency

来源：评论

学校读者我要写书评

暂无评论

Architecture optimization techniques for convolutional neural networks: further experiments and insights

引用

INTERNATIONAL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS 2024年第1期70卷 87-94页

作者： Sobolewski, Artur Szyc, Kamil Wroclaw Univ Sci & Technol Wroclaw Poland

In this paper, we have researched implementing convolutional neural network (CNN) models for devices with limited resources, such as smartphones and embedded computers. To optimize the number of parameters of these models, we studied various popular methods that would allow them to operate more efficiently. Specifically, our research focused on the Resnet-101 and VGG-19 architectures, which we modified using techniques specific to model optimization. We aimed to determine which approach would work best for particular requirements for a maximum accepted accuracy drop. Our contribution lies in the comprehensive ablation study, which presents the impact of different approaches on the final results, specifically in terms of reducing model parameters, FLOPS, and the potential decline in accuracy. We explored the feasibility of implementing architecture compression methods that can influence the model's structure. Additionally, we delved into post -training methods, such as pruning and quantization, at various model sparsity levels. This study builds upon our prior research [1] to provide a more comprehensive understanding of the subject matter at hand. 1

关键词： Model Compression convolutional neural net- work Computer Vision

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：