检索结果-内蒙古大学图书馆

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

ECAS-ML: Edge Computing Assisted Adaptation Scheme with Machine Learning for HTTP Adaptive Streaming 28th

ECAS-ML: Edge Computing Assisted Adaptation Scheme with Mach...

引用

28th International Conference on multimedia Modeling (MMM)

作者： Aguilar-Armijo, Jesus Cetinkaya, Ekrem Timmerer, Christian Hellwagner, Hermann Alpen Adria Univ Klagenfurt Inst Informat Technol Christian Doppler Lab ATHENA Klagenfurt Austria

ISBN: (纸本)9783030983550;9783030983543

As the video streaming traffic in mobile networks is increasing, improving the content delivery process becomes crucial, e.g., by utilizing edge computing support. At an edge node, we can deploy adaptive bitrate (ABR) algorithms with a better understanding of network behavior and access to radio and player metrics. In this work, we present ECAS-ML, Edge Assisted Adaptation Scheme for HTTP Adaptive Streaming with Machine Learning. ECAS-ML focuses on managing the tradeoff among bitrate, segment switches and stalls to achieve a higher quality of experience (QoE). For that purpose, we use machine learning techniques to analyze radio throughput traces and predict the best parameters of our algorithm to achieve better performance. The results show that ECAS-ML outperforms other client-based and edge-based ABR algorithms.

关键词： HTTP Adaptive Streaming Edge computing content delivery Network-assisted video streaming Quality of experience Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Digital Technology to Analyze the Combined Effect of Artificial Intelligence and Big Data Analytics for multimedia Information Processing

An Enhanced Digital Technology to Analyze the Combined Effec...

引用

2024 International Conference on Smart systems for Electrical, Electronics, Communication and Computer Engineering, ICSSEEC 2024

作者： Naser, Zamen Latef Adile, Mohaned Hussain, Angham Khalid Hasan, Forat Falih Majed, Safa Mohammed, Mohammed Abdulamer Almusawi, Muntather National University of Science and Technology Department of Medical Devices Engineering Technologies Nasiriyah Dhi Qar Iraq Al-farahidi University Medical Instruments Engineering Techniques Baghdad Iraq Al-Turath University College Computer Technologies Engineering Baghdad Iraq Al-Kitab University Department of Computer Engineering Technologies Kirkuk Iraq Al-Kunooze University College Technical Computer Engineering Department Basrah Iraq Hilla University College Babil Iraq College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq

ISBN: (纸本)9798350378177

For the past several years, taking very large collections of images in everyday life has become more common. All audiovisual artifacts are more likely to be shared and collaborated on since images might come from various devices such as smartphones, satellites, web cams, and drones. Not only that but they are often employed to represent things in a wide range of settings (public areas, train stations, hospitals, political and sports events, competitions, etc.). Hence, multimedia information processor approaches are growing in significance for the many kinds of visual identification jobs that must be adapted to handle large numbers while filling available window processing time. New approaches are being developed, audiences' tastes are shifting, and digital media technologies are becoming more powerful and accessible regularly, contributing to the medium's ever-evolving landscape. This article presents the planning stages of a MIPS (multimedia Information Processing System). This study provides a platform for image processing methods using a virtualized toolbox. Virtual servers, applications, system time, and data mining are all made possible on this platform thanks to the combination of these digital processing approaches. Additionally, the necessary frameworks and equipment adapters are automatically linked and installed, allowing members to access various apps without downloading and installing software programs. Experiments employed digital processing applications, (ii) a deep backpropagation algorithm for picture classification and multiobject placement, and (iii) a program for indexing and retrieving images. These analyses indicated the system's goal of facilitating the open distribution of important developments and annotation databases to guarantee the efficacy of artificial intelligence-based applications for processing multimedia content. © 2024 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Securing multimedia-based personal data: towards a methodology for automated anonymization risk assessment seeking GDPR compliance 2

Securing multimedia-based personal data: towards a methodolo...

引用

Artificial Intelligence for Security and Defence Applications ii 2024

作者： Aramburu, Mikel Redó, David García-Castaño, Jorge Vicomtech Foundation Mikeletegi 57 Donostia-San Sebastián20009 Spain

ISBN: (纸本)9781510681200

Anonymizing personal data in multimedia content (image, audio and text) has become crucial for secure data-sharing while adhering to the rigorous data compliance requirements of the European Union (EU) General Data Protection Regulation (GDPR). Given the substantial volume of data involved, manual verification of anonymization accuracy is not feasible due to the high potential for human error and the impracticality of scaling such efforts. Consequently, automated or semi-automated processes are indispensable. However, it is important to note that these methodologies cannot guarantee absolute anonymization, potentially leading to inadvertent disclosure of personal information and associated legal and privacy implications. Therefore, when dealing with extensive multimedia datasets, it is strongly advised to conduct a comprehensive anonymization risk assessment. In response to this challenge, we introduce a novel methodology with an innovative design to quantitatively evaluate the effectiveness and reliability of the anonymization techniques by generating metrics to calculate risk indicators to conduct a comprehensive anonymization risk assessment. This methodology is built based on de-identification techniques to protect personal data while preserving data integrity. Our approach leverages a novel algorithmic framework that helps humans inspect the anonymized dataset, ensuring higher data privacy and security. The methodology detects non-anonymized personal data within an extensive dataset automatically. This is achieved by extracting characteristics related to personal data during the anonymization process and correlating attributes from the surrounding data using sophisticated AI-driven analysis. Afterwards, a rule-based algorithm is applied to the extracted characteristics from both processes to identify and qualitatively assess the anonymization risk. We demonstrate the applicability and effectiveness of our methodology through a focused application on license pla

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Optimizing Perceptual Quality Prediction Models for multimedia Processing systems: Going Beyond the Mean Opinion Score

Optimizing Perceptual Quality Prediction Models for Multimed...

引用

作者： FOTIO TIOTSOP, LOHIC Polytechnic University of Turin

学位级别：博士

Being able to accurately predict human perceived quality of multimedia con- tent (e. g., images and videos) through computer algorithms is an important and hot research topic, since it directly leads to several advantages: storage capacity and bandwidth savings for large organizations, and possibility to offer higher qual- ity services when the communication channel capacity is limited. This PhD thesis focuses on using machine learning algorithms and advanced statistical methods to find new ways of addressing the problem. Human viewers can easily distinguish between an image with a pleasant per- ceptual quality and another one whose quality is corrupted by artifacts introduced for instance by a codec. This task that is straightforward for a human due to his daily experiences and background, is absolutely not easy for an algorithm. For this reason, in the literature, human opinion scores on the perceptual quality of a multimedia content are considered as ground truth data. Any quality prediction algorithm (QPA) is then designed to predict the so-called Mean Opinion Score (MOS) of a multimedia content, i. e., the average of the scores that a group of hu- man viewers would express if they were asked to watch that content and rate its perceptual quality on a given numerical scale. Several QPAs aiming at MOS prediction have been proposed in the literature but the state-of-the-art in media quality assessment is still suffering some crucial limitations. Some of these limitations can be summarized as follows: i) none of the existing QPAs is accurate in all application scenarios, and thus there is still large room for their improvement; ii) QPAs, as estimators of the MOS, do not provide a complete measure of quality-of-experience (QoE). In fact, QPAs simply measure the quality perception of an "average viewer" and only marginally account for the individual expectation and uncertainty that characterize different users of the same service. For instance, QPAs do not provide ans

关键词：

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

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

Adaptive cultural mediation through HBIM and VR: enhancing personalized experiencesvia thematic data structuring 8

Adaptive cultural mediation through HBIM and VR: enhancing p...

引用

8th International ISPRS Workshop LowCost 3D - Sensors, algorithms, Applications

作者： El Barhoumi, Nabil Radoine, Hassan Hajji, Rafika Harmouche, Houda College of Geomatic Sciences and Surveying Engineering Hassan II Institute of Agronomy and Veterinary Medicine Rabat6202 Morocco Mohammed VI Polytechnic University UM6P-CITINNOV SA Rabat Morocco

The mediation of architectural heritage has gained prominence in cultural and historical research, particularly through advancements in technologies like Historic Building Information Modeling (HBIM) and Extended Reality (XR). While these technologies have been extensively explored individually, their combined application for cultural mediation remains under examined. This paper presents a new concept of Adaptive Cultural Mediation (ACM), integrating HBIM and XR to create an interactive, user-specific mediation environment. ACM enables users to filter information based on interests, such as architectural elements or historical context, providing an immersive, personalized experience. Our approach is exemplified through a virtual model of the Mosque Al-Quaraouiyine in Fez, Morocco, where 3D scanning and HBIM modelling capture architectural details and historical annotations. MongoDB, a NoSQL database, supports the integration of multimedia content and user preferences, structured around thematic filters for real-time adaptability. This setup, powered by Unity in a VR environment, facilitates dynamic content retrieval, enhancing user engagement by aligning information display with selected themes. The results demonstrate the effectiveness of combining HBIM with NoSQL databases in XR environments, displaying how adaptive cultural mediation can transform heritage site exploration into an engaging, context-rich experience. Copyright: © 2024 Nabil El Barhoumi et al.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Computational Efficient Authenticated Digital content Distribution Frameworks for DRM systems: Review and Outlook

引用

IEEE systems JOURNAL 2021年第2期15卷 1586-1593页

作者： Rana, Saurabh Obaidat, Mohammad S. Mishra, Dheerendra Mukhopadhyay, Sourav Sadoun, Balqies LNM Inst Informat Technol Dept Math Jaipur 302031 Rajasthan India Univ Sharjah Coll Comp & Informat Sharjah 27272 U Arab Emirates Univ Jordan King Abdullah II Sch Informat Technol KAIST Amman 19328 Jordan Univ Sci & Technol Beijing Beijing 100083 Peoples R China Amity Univ Noida 201313 India Indian Inst Technol Dept Math Kharagpur 721302 W Bengal India Univ Sharjah Coll Engn Sharjah 27272 U Arab Emirates Al Balqa Appl Univ Coll Engn Al Salt 19110 Jordan

Advancement in digital technologies presents a user-friendly environment for the digital content distribution. However, it makes digital content prone to piracy issues. Digital rights management (DRM) systems aim to ensure the authorized content usage. As the digital content broadcasts through the public network, a secure and authorized content access mechanism is required. As digital media users are increasing, data centers draw vast amounts of power to manage consumer demands for instant access. Thus, design of efficient protocols is required for digital industry. Several authenticated content key distribution frameworks have been introduced for DRM systems to support efficient computing and mutual authentication. The main focus of recent devolvement is security and energy consumption by increasing communication and computing efficiency. Most of the existing DRM models efficiently address the consumer concerns and make the system user-friendly and computationally efficient. Thus, it is essential to analyze the security, efficiency, and related issues in the existing framework before adopting them for a DRM system. This article presents a study on the existing authenticated content key distribution frameworks of DRM systems. It proves the vulnerabilities of the existing structures against known attacks and challenges in their implementation. It also discusses the desirable attributes of DRM systems and provides possible future direction.

关键词： Copyright protection Authentication Protocols Games Media Password Digital rights management (DRM) systems efficiency multimedia systems privacy security

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

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.

关键词：

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：