检索结果-内蒙古大学图书馆

Image Classification of multimedia Platforms With Texture algorithms and Neural Networks

IEEE access 2025年 13卷 46478-46494页

作者： Sauzameda-Gonzalez, Mauricio Alvarez-Borrego, Josue Guerra-Rosas, Esperanza Ctr Invest Cient & Educ Super Ensenada CICESE Ensenada 22860 Baja California Mexico Univ Autonoma Baja California Fac Ingn Arquitectura & Diseno Ensenada 22860 Baja California Mexico

In this paper, a methodology for real-time image classification on multimedia platforms has been developed. For this purpose, six feedforward neural network models were trained with images from two databases, which were preprocessed by three texture extraction methods: local binary pattern-uniform (LBP-U), gray level co-occurrence matrix (GLCM), and wavelet image scattering (WIS). The databases used consist of 157,448 images of the sections with the thumbnails of the platform content (mosaics) representing 14 classes and 38,214 images with the descriptions of the available content (descriptors) representing 11 classes, where all images have a resolution of 1280 x 720 pixels. The six models (three for mosaics and three for descriptors) were validated with images from the databases, which were not part of the training process, to obtain their performance metrics. The training and validation process was performed 30 times, and the average results were compared. The most outstanding models for each database were the neural networks trained with the wavelet image scattering method, with metrics of 99.97 +/- 0.01 % accuracy, 99.99 +/- 0.01 % specificity, 99.84 +/- 0.06 % sensitivity, 99.59 +/- 0.13 % precision and 99.71 +/- 0. 08 % of F1 score with a response time of 0.7349 seconds for the model trained with mosaics and with metrics of 99.90 +/- 0.03 % of accuracy, 99.94 +/- 0.02 % of specificity, 99.58 +/- 0.15 % of sensitivity, 98.63 +/- 0.55 % of precision and 99.09 +/- 0.30 % of F1 score with a response time of 0.6227 seconds for the model trained with descriptor images. The results are very significant due to the high efficiency obtained and confirm the effectiveness of the models with the WIS method for the classification of multimedia platform images with the characteristics of the databases used. It is suggested that the remaining methods be adjusted to improve their performance.

关键词： Gray-scale Mathematical models Symmetric matrices Scattering Real-time systems Image classification Statistical analysis Object recognition multimedia databases Histograms Classification method neural networks texture analysis methods local binary pattern grayscale co-occurrence matrix performance metrics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Various Encryption Techniques for Digital Images in multimedia Networks 2

A Comprehensive Study on Various Encryption Techniques for D...

引用

2nd IEEE International Conference on Integrated Circuits and Communication systems, ICICACS 2024

作者： Santhosha, Benaka Sudheesh, K.V. Kiran, K. Parameshachari, B.D. Dayanand Sagar University Harohalli Bengaluru Visvesveraya Technological University Department of CSE Belagavi India Vidyavardhaka College of Enginerring Mysuru Visvesveraya Technological University Department of ECE Belagavi India Nitte Meenakshi Institute of Technology Department of ECE Bengaluru India

ISBN: (纸本)9798350317558

Image encryption is a fundamental component of modern data security that guarantees the integrity, privacy, and confidentiality of sensitive visual content. This paper provides a thorough examination of image encryption, comparing and contrasting different encryption techniques and their benefits and limitations as well as real-world uses. In order to strengthen image data security against unwanted access and manipulation, we first offer some basic understanding of image encryption. The suitability of symmetric, asymmetric, and hybrid encryption techniques in various contexts is examined. We also explore the assessment criteria used to evaluate encryption algorithms, highlighting the significance of using suitable measures to precisely gauge security and effectiveness. We also discuss common issues with image encryption, like complicated key management and computational complexity. The review also explores future directions that picture encryption might take, including multi-media encryption techniques, resistance to cryptanalysis, and quantum image encryption. We also highlight how important image encryption is in a variety of fields, such as finance, healthcare, journalism, intellectual property protection, and military operations. We will conduct a thorough analysis of current cryptography schemes and multimedia encryption algorithms to provide a comprehensive overview of the current security landscape tailored to digital multimedia technology. The findings from this survey will enhance our understanding of the efficacy and dependability of secure multimedia encryption schemes, ultimately aiding in the development of more efficient and robust encryption methods for the future. This article aims to summarize and assess numerous algorithms using different methodologies based on multiple characteristics such as MSE, PSNR, NC, BER, and so on. © 2024 IEEE.

关键词： Cryptography Image multimedia Networks Security Attacks Steganography Watermarking

来源：评论

学校读者我要写书评

暂无评论

Assessment of the effects of 5G MEC cache on DASH adaptation algorithms

Assessment of the effects of 5G MEC cache on DASH adaptation...

引用

International Symposium on Broadband multimedia systems and Broadcasting (BMSB)

作者： Viola, Roberto Amendola, Danilo Fernandez, Zaloa Gabilondo, Alvaro Zorrilla, Mikel Casals, Mikel Angueira, Pablo Montalban, Jon Basque Res & Technol Alliance Vicomtech Fdn San Sebastian Spain Univ Navarra Tecnun San Sebastian Spain Univ Basque Country Dept Commun Engn Bilbao 48013 Spain Univ Basque Country Dept Elect Technol Bilbao 48013 Spain

ISBN: (纸本)9781665469012

video streaming services are the major sources of Internet traffic, and their usage is constantly growing. To cope with this increasing video traffic demand, 5G comes with a new Radio access Network (RAN), having increased network data rates, and the Multi-access Edge Computing (MEC) architecture, enabling the deployment of services closer to the end devices. 5G RAN and MEC open to new opportunities to enforce and boost the video content delivery, as the content can be cached locally at the MEC host and served with improved RAN connectivity. However, the presence of a cache located at MEC may affect player adaptation algorithm when employing Adaptive Bitrate (ABR) streaming technologies, such as Dynamic Adaptive Streaming over HTTP (DASH). The cache influences the network measurements performed by the DASH player, which are later used, among other factors, by its adaptation algorithm to select the video representation bitrate. This paper investigates the interactions between MEC cache and DASH adaptation algorithms in a real testbed, including 5G RAN and MEC platform. The effects on different adaptation algorithms are analyzed while caching the DASH video content at the MEC.

关键词： 5G Adaptive Streaming content Caching Multi-access Edge Computing & Quality of Service

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Detection of Inappropriate Speech content for Film Censorship

引用

IEEE access 2022年 10卷 101697-101715页

作者： Wazir, Abdulaziz Saleh Ba Karim, Hezerul Abdul Lyn, Hor Sui Fauzi, Mohammad Faizal Ahmad Mansor, Sarina Lye, Mohd Haris Multimedia Univ Fac Engn Cyberjaya 63000 Malaysia

Audible content has become an effective tool for shaping one's personality and character due to the ease of accessibility to a huge audible content that could be an independent audio files or an audio of online videos, movies, and television programs. There is a huge necessity to filter inappropriate audible content of the easily accessible videos and films that are likely to contain an inappropriate speech content. With this in view, all the broadcasting and online video/audio platform companies hire a lot of manpower to detect the foul voices prior to censorship. The process has a large cost in terms of manpower, time and financial resources. In addition to inaccurate detection of foul voices due to fatigue of manpower and weakness of human visual and hearing system in long time and monotonous tasks. As such, this paper proposes an intelligent deep learning-based system for film censorship through a fast and accurate detection and localization approach using advanced deep Convolutional Neural Networks (CNNs). The dataset of foul language containing isolated words samples and continuous speech were collected, annotated, processed, and analyzed for the development of automated detection of inappropriate speech content. The results indicated the feasibility of the suggested systems by reporting a high volume of inappropriate spoken terms detection. The proposed system outperformed state-of-the-art baseline algorithms on the novel foul language dataset evaluation metrics in terms of macro average AUC (93.85%), weighted average AUC (94.58%), and all other metrics such as F1-score. Additionally, proposed acoustic system outperformed ASR-based system for profanity detection based on the evaluation metrics including AUC, accuracy, precision, and F1-score. Additionally, proposed system was proven to be faster than human manual screening and detection of audible content for films' censorship.

关键词： Speech recognition Acoustics Computational modeling Deep learning Motion pictures Censorship Speech processing Foul language speech recognition key word spotting spoken term detection censorship deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Video Summarization on the Cloud: A Pathway to Efficient Storage and Quick access 16

Deep Learning-Driven Video Summarization on the Cloud: A Pat...

引用

16th IEEE International Symposium on Embedded Multicore/Many-core systems-on-Chip (MCSoC)

作者： Darwich, Mahmoud Khalil, Kasem Ismail, Yasser Bayoumi, Magdy Univ Mt Union Dept Math & Comp Sci Alliance OH 44601 USA Univ Mississippi Dept Elect & Comp Engn University MS 38677 USA Southern Univ A&M Coll Dept Elect Engn Baton Rouge LA 70807 USA Univ Louisiana Lafayette Dept Elect & Comp Engn Lafayette LA 70504 USA

ISBN: (纸本)9798350393613

Cloud-based video summarization is an increasingly popular technique for managing large video repositories more efficiently. In this research, we present a novel approach for cloud-based video summarization that focuses on reducing storage costs and improving accessibility by automatically extracting critical information from videos and generating brief summaries. Our approach leverages cloud computing technology and deep learning algorithms for video analysis and processing. We evaluate the effectiveness of our approach using a realworld dataset of video files and demonstrate that it can generate high-quality video summaries while significantly reducing storage requirements. Our proposed approach has potential applications in areas such as security monitoring, video surveillance, and multimedia content management. This paper contributes to the existing literature by presenting a comprehensive study of cloud-based video summarization and proposing a novel solution that addresses the limitations of existing approaches, thereby improving the efficiency and cost-effectiveness of video management.

关键词： Cloud computing Video summarization Deep learning Storage costs multimedia content management

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Recommending Universal Decimal Classification Codes for Cataloguing in Slovenian Digital Libraries

引用

IEEE access 2022年 10卷 85595-85605页

作者： Borovic, Mladen Ojstersek, Milan Strnad, Damjan Univ Maribor Fac Elect Engn & Comp Sci Lab Heterogeneous Comp Syst Maribor 2000 Slovenia Univ Maribor Fac Elect Engn & Comp Sci Lab Geospatial Modelling Multimedia & Artificial Maribor 2000 Slovenia

In this article we present a hybrid approach to recommending the Universal Decimal Classification (UDC) codes for unclassified documents. By recommending UDC codes to librarians, we can provide the decision support as part of a semi-automatic cataloguing process. As current approaches to recommending UDC codes are scarce and limited to certain fields of expertise, our motivation was to create a hybrid approach which covers all fields of expertise within the UDC hierarchy. The cascade hybrid approach combines the BM25 ranking function with a multi-label classifier based on a BERT (Bidirectional Encoder Representations from Transformers) deep neural network architecture. Additionally, lists of the most commonly used UDC codes within a document's origin organization are used as a final content-based filtering method. The BM25 ranking function is used to create an initial list of recommendations. The first cascade step re-ranks the initial list of recommendations using the list of recommendations produced by the multi-label BERT-based classifier. The second cascade step re-ranks the resulting recommendation list from the first cascade step using a list of most commonly used UDC codes within the document's organization. Finally, post-processing steps are applied to obtain the final list of recommended UDC codes. We present in detail the UDC structure, the used text corpus of documents and the functioning of our hybrid recommendation approach. We perform the analysis of the generated recommendation lists for the corpus from the Slovenian Open-access Infrastructure using the metrics hit-ratio, normalized discounted cumulative gain, mean reciprocal rank and mean average precision. Our hybrid recommendation approach improves reference scores of individual methods for these metrics.

关键词： Codes Libraries Recommender systems Filtering Measurement Computer science Labeling Classification algorithms Hybrid recommender systems multi-label classification digital libraries universal decimal classification

来源：评论

学校读者我要写书评

暂无评论

Vis2Rec: A Large-Scale Visual Dataset for Visit Recommendation 23

Vis2Rec: A Large-Scale Visual Dataset for Visit Recommendati...

引用

23rd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Soumm, Michael Popescu, Adrian Delezoide, Bertrand Amanda 34 Ave Champs Elysees F-75008 Paris France Univ Paris Saclay CEA List F-91120 Palaiseau France

ISBN: (纸本)9781665493468

Most recommendation datasets for tourism are restricted to one world region and rely on explicit data such as checkins. However, in reality, tourists visit various places worldwide and document their trips primarily through photos. These images contain a wealth of raw information that can be used to capture users' preferences and recommend personalized content. Visual content was already used in past works, but no large-scale publicly-available dataset that gives access to users' personal images exists for recommender systems. As such a resource would open-up possibilities for new image-based recommendation algorithms, we introduce Vis2Rec, a new dataset based on visit data extracted from users' Flickr photographic streams, which includes over 7 million photos, 36k recognizable points of interest, and 14k user profiles. Google Landmarks v2 is used as an auxiliary dataset to identify points of interest in users' photos, using a state-of-the-art image-matching deep architecture. Image-based user profiles are then constituted by aggregating the points of interest detected for each user. In addition, ground truth visits were determined for the test subset in order to enable accurate evaluation. Finally, we benchmark Vis2Rec using various existing recommender systems, and discuss the possibilities opened up by the availability of user images, as well as the societal issues that come with them. Following good practice in dataset sharing, Vis2Rec is created using only freely distributable content, and additional anonymization is performed to ensure the privacy of users. The raw dataset and the preprocessed user profiles will be publicly available at https://***/MSoumm/Vis2Rec.

关键词： Visualization Data privacy Image databases Semantics multimedia Web sites Benchmark testing Streaming media

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Various Encryption Techniques for Digital Images in multimedia Networks

A Comprehensive Study on Various Encryption Techniques for D...

引用

Integrated Circuits and Communication systems (ICICACS), IEEE International Conference on

作者： Benaka Santhosha S Sudheesh K V Kiran Kiran Parameshachari B D Department of CSE Dayanand Sagar University Harohalli Bengaluru Visvesveraya Technological University Belagavi Department of ECE Vidyavardhaka College of Enginerring Mysuru Visvesveraya Technological University Belagavi Department of ECE Nitte Meenakshi Institute of Technology Bengaluru India

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical Bit-Plane-Based 3D-JST Cryptography Algorithm With Cascaded 2D-FrFT Encryption for Efficient and Secure HEVC Communication

引用

IEEE access 2021年 9卷 35004-35026页

作者： El-Shafai, Walid Almomani, Iman M. Alkhayer, Aala Prince Sultan Univ Comp Sci Dept Secur Engn Lab Riyadh 11586 Saudi Arabia Menou Univ Fac Elect Engn Dept Elect & Elect Commun Engn Menoufia 32952 Egypt Univ Jordan King Abdullah II Sch Informat Technol Comp Sci Dept Amman 11942 Jordan

The rapid growth of multimedia communication systems has expanded the High-Efficiency Video Coding (HEVC) security applications precipitously. Therefore, there is an urgent, elevated need to protect and secure the HEVC content during streaming and communication over insecure channels to ensure the privacy of HEVC data against intruders and attackers. This paper introduces an optical HEVC cipher algorithm based on bit-plane 3D-JST (Three-Dimensional Jigsaw Transform) and multistage 2D-FrFT (Two-Dimensional Fractional Fourier Transform) encryption. The main advantage of employing 3D-JST is its unitary transform that has an inverse transform used to reorganize the HEVC frame-blocks in an indiscriminately way. The proposed algorithm embraces the cascaded 2D-FrFT encryption in the optical domain using a single arbitrary phase code;to be executed all optically with a lone lens. The suggested algorithm utilizes the two 2D-FrFT stages with distinct kernels in mutually dimensions separated by employing the arbitrary phase code. A foregoing bit-plane permutation stage is conducted on the input HEVC frames before the 3D-JST and 2D-FrFT processes to accomplish a high robustness and security level. To validate the efficacy of the proposed cryptography algorithm for secure HEVC streaming, a comprehensive evaluation framework has been introduced and followed to (a) test HEVC streams against different statistical cryptographic metrics, (b) compare the proposed algorithm with recent related works whether optical-based or digital-based algorithms and (c) study the impact of different security attacks on its performance. The evaluation results show a secure and efficient proposed cryptography algorithm that outperforms the conventional and related cryptography algorithms in terms of all examined evaluation metrics.

关键词： Encryption Streaming media Cryptography Security Two dimensional displays Optical network units Optical imaging Optical encryption HEVC communication 3D-JST 2D-FrFT cryptography multimedia applications video coding security efficiency diffusion attack histogram

来源：评论

学校读者我要写书评

暂无评论

multimedia Data Privacy Against Machines

引用

IEEE multimedia 2020年第2期27卷 5-7页

作者： Kankanhalli, Mohan Natl Univ Singapore Singapore Singapore

With the explosion of multimedia data, machine learning applications are proliferating. Privacy concerns have recently resurfaced, due to a few prominent incidents of user data leakage, which divulged sensitive information to other people. multimedia data platform providers-social networks, their affiliates or governments with access to users' content-use algorithms to profile users by extracting or inferring demographic information, personality traits, relationships, opinions, and beliefs. These results, in turn, feed algorithms for targeted advertising but also for personalized content recommendation to maximize user engagement. While this is ostensibly for users' benefit, they have serious privacy implications. We highlight this new problem of privacy protection against machines in contrast to the traditional problem of privacy protection against humans. We briefly touch upon our initial solution, a human-sensitivity-aware image perturbation model, which is able to modify the computational classification results of sensitive attributes while preserving the remaining attributes. We then point to many exciting open problems in this new area.

关键词： Advertising Data Processing Data Protection Learning Artificial Intelligence multimedia Computing Recommender systems Social Networking Online multimedia Data Privacy Machine Learning Applications Sensitive Information Demographic Information Personality Traits Feed algorithms Targeted Advertising Personalized content Recommendation User Engagement Serious Privacy Implications Privacy Protection Human Sensitivity Aware Image Perturbation Model Computational Classification Results Sensitive Attributes multimedia Data Platform Providers Social Networks Data Privacy Streaming Media Privacy Social Networking Online Machine Learning algorithms Machine Learning Government

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：