检索结果-内蒙古大学图书馆

2023 International conference on Circuit Power and Computing Technologies, ICCPCT 2023

作者： Suresh Kumar, J.S. Maria Celestin Vigila, S. Noorul Islam Centre for Higher Education Kumaracoil Department of Computer Science and Engineering Tamilnadu Kanyakumari India Noorul Islam Centre for Higher Education Kumaracoil Department of Information Technology Tamilnadu Kanyakumari India

ISBN: (纸本)9798350333244

Significant interest in content-Based Image Retrieval (CBIR) has been identified over the last two decades, which utilizes image and video perception to find adequate images. The availability of graphical and multimedia data, as well as the expansion of the Internet, demands field matching. Because of the lack of visual content as a ranking clue, methodologies for visual retrieval that use text search methods may suffer from lack of consistency between full texts and visual content. Many programmers and tools have been developed to help users develop, implement, and conduct research on visual or audio content, as well as to browse large multimedia repositories. A benchmark for transmission model has been established DICOM, and patient data can be ended up saving along with the images, although there are still a few issues with standardization. Several papers have proposed content-based access to medical images to aid clinical decision-making and simplify medical evidence, and instances for integrating based on their content access methods into images and communication systems have been developed. This work provides a thorough evaluation of current advancements in the fields of CBIR. This investigation utilizes key characteristics of numerous retrieval methods for images and frameworks, ranging from basic identification of features from images to current deep-learning approaches. © 2023 IEEE.

关键词： Hospital data processing

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

Leveraging Metaheuristic Optimization to Enhance Insider Threat Detection Through Email content Natural Language Processing

Leveraging Metaheuristic Optimization to Enhance Insider Thr...

引用

International conference on Intelligent and Fuzzy systems (INFUS)

作者： Bacanin, Nebojsa Jovanovic, Luka Janicijevic, Stefana Antonijevic, Milos Sarac, Marko Zivkovic, Miodrag Singidunum Univ Belgrade Serbia Wireless Media Grp Belgrade Serbia

ISBN: (纸本)9783031671944;9783031671951

Ensuring operational integrity in the ever-evolving internet landscape requires robust cybersecurity measures to combat emerging security compromise vectors. Despite traditional techniques, insider threats pose a significant challenge, exploiting the human element and contributing to substantial cyberattack losses. On-premises attacks, facilitated by physical access, defy conventional detection methods, necessitating alternative approaches. This study explores the integration of natural language processing (NLP) with the AdaBoost classifier for identifying malicious intent in email content, utilizing publicly available datasets to detect insider threats. Optimizing model hyperparameters through various algorithms, including a modified elk herd optimization algorithm, enhances performance. The best-performing model is analyzed in-depth, uncovering key terms crucial for malicious intent detection and their roles in the classification process.

关键词： Insider threat detection AdaBoost Cybersecurity Elk herd optimization Metaheuristics optimization

来源：评论

学校读者我要写书评

暂无评论

NORMalize: A Tutorial on the Normative Design and Evaluation of Information access systems

NORMalize: A Tutorial on the Normative Design and Evaluation...

引用

9th ACM SIGIR conference on Human Information Interaction and Retrieval, CHIIR 2024

作者： Kruse, Johannes Michiels, Lien Starke, Alain Tintarev, Nava Vrijenhoek, Sanne Ekstra Bladet Copenhagen Denmark Technical University of Denmark Kongens Lyngby Denmark University of Antwerp Antwerpen Belgium University of Amsterdam Amsterdam Netherlands MediaFutures University of Bergen Vestland Bergen Norway Maastricht University Maastricht Netherlands University of Amsterdam Amsterdam Netherlands

ISBN: (纸本)9798400704345

Information access systems, such as Google News or YouTube, increasingly employ algorithms to rank diverse content such as music, recipes, and news articles. Acknowledging the influential role of these algorithms as gatekeepers to online content, the research community is increasingly exploring 'beyond-accuracy' metrics. However, deciding what norms and values are relevant and should be prioritized when designing and evaluating information access systems is a challenging task. This tutorial aims to cultivate normative thinking and decision-making in the design and evaluation of information access systems. The tutorial comprises two key components. The first part involves a lecture on the foundational principles of normative thinking, emphasizing the importance of reflecting on the desired state of a system rather than its current state. The second part is an interactive session where participants engage in group discussions, applying normative thinking to a specific use case. Participants analyze the system's usage, stakeholders, and relevant norms and values and address potential conflicts between stakeholders and/or values. Through a point-allocation exercise, participants represent stakeholders and advocate for specific values, fostering a deeper understanding of normative decision-making in the context of information access systems. © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

LC-Beating: An Online System for Beat and Downbeat Tracking using Latency-Controlled Mechanism

LC-Beating: An Online System for Beat and Downbeat Tracking ...

引用

IEEE International conference on multimedia and Expo (ICME)

作者： Liu, Xinlu Qian, Jiale He, Qiqi Yu, Yi Li, Wei Fudan Univ Sch Comp Sci & Technol Shanghai Peoples R China Natl Inst Informat NII Digital Content & Media Sci Res Div Tokyo Japan Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China

ISBN: (纸本)9781665468916

Beat and downbeat tracking is to predict beat and downbeat time steps from a given music piece. Some deep learning models with a dilated structure such as Temporal Convolutional Network (TCN) and Dilated Self-Attention Network (DSAN) have achieved promising performance for this task. However, most of them have to see the whole music context during inference, which limits their deployment to online systems. In this paper, we propose LC-Beating, a novel latency-controlled (LC) mechanism for online beat and downbeat tracking, in which the model only looks ahead a few frames. By appending limited future information, the model can better capture the activity of relevant musical beats, which significantly boosts the performance of online algorithms with limited latency. Moreover, LC-Beating applies a novel real-time implementation of the LC mechanism to TCN and DSAN. The experimental results show that our proposed method outperforms the previous online models by a large margin and is close to the results of the offline models.

关键词： Beat Downbeat Real-time Latency-controlled mechanism

来源：评论

学校读者我要写书评

暂无评论

LAYAMRITAM: A Scalable and Secure multimedia Delivery Platform for Devotional Songs 5th

LAYAMRITAM: A Scalable and Secure Multimedia Delivery Platfo...

引用

5th International conference on Computing and Network Communications, CoCoNet 2023

作者： Guntha, Ramesh Amrita Vishwa Vidyapeetham Amritapuri Vallikavu India

ISBN: (纸本)9789819747108

The creation of a platform for delivering multimedia content poses distinct challenges, especially when focusing on devotional music. In contrast to text-based platforms, multimedia delivery necessitates meticulous management of latency, augmented storage space, and bandwidth needs. Although the market is saturated with mainstream multimedia streaming services like Spotify, Apple Music, and Amazon Music, there is a noticeable absence of a platform dedicated to devotional music, despite its deep cultural and spiritual importance. This paper introduces Layamritam, a platform thoughtfully crafted to meet the specific needs of devotional music enthusiasts and artists. Layamritam distinguishes itself through its dedication to providing an immersive musical experience, complemented by sing-along lyrics in 26 languages. We delve into the distributed server architecture of Layamritam, which utilizes adaptive and resilient algorithms to offer a scalable music listening experience while safeguarding user privacy and digital content security. Investigating the user experience of Layamritam, this paper emphasizes its intuitive interface, which organizes songs by deity, mood, speed, tune, and beat style, ensuring a frictionless experience for users across all age groups and digital proficiency levels. Not only does this paper reveal Layamritam, but it also scrutinizes its potential to transform the preservation and distribution of devotional music in the digital age. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Towards a Software Architecture to Provide Hybrid Recommendations for Smart Campuses 1

引用

15th International conference on Computer Supported Education (CSEDU)

作者： Maruyama, Martin Hideki Mensch Silveira, Luan Willig Dorneles, Ana Paula Militz Casanova, Gabriel Vieira Poy, Renan Bordignon da Silva Junior, Elvandi de Oliveira, Jose Palazzo M. Maran, Vinicius Univ Fed Santa Maria Lab Ubiquitous Mobile & Appl Comp LUMAC Polytech Sch Ave Roraima BR-1000 Santa Maria RS Brazil Univ Fed Rio Grande do Sul Inst Informat Porto Alegre RS Brazil

ISBN: (数字)9783031536564

ISBN: (纸本)9783031536557;9783031536564

Currently, several initiatives have been proposed in order to offer solutions for intelligent university campus environments. It can be said that smart university campuses are a subdomain of the smart cities domain, with some similar problems, but with specificities. Recommender systems identify and suggest relevant information to the user, recognizing their potential interests through specialized algorithms and presenting resources that align with these interests. In the context of intelligent university campuses, recommender systems have been used to define which systems and technologies should be implemented. From this scenario, the objective of this article is to present a software architecture, called SmartC, structured in different services, to provide the essential infrastructure for the application of several recommender systems and a variety of types of items. The services and layers of the architecture were defined especially for intelligent university campuses and divided into three distinct sections: the access environment, the recommendations management environment and the persistence layer. The recommendation algorithms integrated to this architecture are considered hybrids, since they incorporate two types of filtering: content-based filtering and collaborative filtering. When users request new recommendations, the type of filtering will be switched, ensuring that new features are suggested with each system call and avoiding throttling. The developed prototype was evaluated from real item data and showed significant accuracy in the recommendation process.

关键词： Recommendation system Filtering techniques Hybrid filtering Collaborative filtering content-based filtering Smart campus University Personalized recommendation Educational resources

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Triphase Community Detection for multimedia Data 4th

Deep Learning-Based Triphase Community Detection for Multime...

引用

4th International conference on Communication, Computing and Electronics systems, ICCCES 2022

作者： Sowmyadevi, D. Srividhya, S. Department of Computer Science PSG College of Arts and Science Coimbatore India Department of Computer Science KPR College of Arts Science and Research Coimbatore India

ISBN: (纸本)9789811977527

Network analysis plays a significant role in business which is achieved through community detection. The relationship between the nodes is mined by community detection, which facilitates the analysis of complicated networks. In the current era, social media is the commonest mode of communication that leads to complex online social networks, from which useful information can be retrieved. Not only textual data is shared in social media, in addition multimedia data plays a significant role in content sharing in social network. This research work proposes a community detection method based on deep learning algorithm to detect communities for both textual content and multimedia content. The proposed method triphase–deep learning community detection (TriDL-CD) method illustrates the relationship of data in a graphical way in the first step. Second step converts the graph into user relationship table using similarity weightage analysis from which the communities are formed using convolution neural network. The proposed method proved to be efficient in detecting high quality communities for multimedia content compared with Louvain community detection algorithm, Leiden community detection, and surprise community detection algorithms. Experimental results show the efficacy of deep learning in the concept of community detection. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Improving Copy-Synthesis Anti-Spoofing Training Method with Rhythm and Speaker Perturbation 25

Improving Copy-Synthesis Anti-Spoofing Training Method with ...

引用

25th Interspeech conference

作者： Lu, Jingze Zhang, Yuxiang Li, Zhuo Shang, Zengqiang Wang, Wenchao Zhang, Pengyuan Chinese Acad Sci Inst Acoust Key Lab Speech Acoust & Content Understanding Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

The rapid development of speech synthesis algorithms poses a challenge in constructing corresponding training datasets for speech anti-spoofing systems in real-world scenarios. The copy-synthesis method offers a simple yet effective solution to this problem. However, the limitation of this method is that it only utilizes the artifacts generated by vocoders, neglecting those from acoustic models. This paper aims to locate the artifacts introduced by the acoustic models of Text-to-Speech (TTS) and Voice Conversion (VC) algorithms, and optimize the copy-synthesis pipeline. The proposed rhythm and speaker perturbation modules successfully boost anti-spoofing models to leverage the artifacts introduced by acoustic models, thereby enhancing their generalization ability when facing various TTS and VC algorithms.

关键词： Anti-Spoofing Detection Copy-Synthesis Generalization Ability Logical access

来源：评论

学校读者我要写书评

暂无评论

Secure content Protection Schemes for Industrial IoT with SRAM PUF-Based One-Time Use Cryptographic Keys

Secure Content Protection Schemes for Industrial IoT with SR...

引用

Computing conference

作者： Jain, Saloni Korenda, Ashwija Reddy Cambou, Bertrand Lucero, Chris No Arizona Univ Intel Corp Flagstaff AZ 86011 USA

ISBN: (纸本)9783031622793;9783031622779;9783031622762

This paper outlines our primary objectives, which revolved around devising a robust and lightweight solution for safeguarding industrial Internet of Things (IoT) device's content. Our study delves into the critical issue of potential vulnerabilities in cryptographic keys within insecure communication networks, vulnerable to side-channel attacks and data leaks. Additionally, it introduces practical flexibility in real-world applications by enabling the generation of keys with the required length while upholding a high level of security. To counteract the risk of losing cryptographic keys in insecure environments, our proposed solution integrates Physical Unclonable Functions (PUFs) and available Error Correction Code (ECC). This integration produces a flexible-length, one-time-use key tailored to specific software requirements. Our protocol employs commercially available Static Random access Memory (SRAM) devices, one-way hashing functions, incorporates various error-correcting schemes, and utilizes standardized cryptographic algorithms like AES128 and AES256 to enhance security. Rigorous characterization of SRAMs, achieved through multiple readings under diverse conditions and temperatures, optimizes randomness while minimizing bit error rates. Validation of the protocol encompasses demonstrating low bit error rates at low latency, understanding the random cell selection for key generation, and analyzing and comparing three different ECCs like Reed Solomon (RS), Bose-Chaudhuri-Hocquenghem (BCH), and Response-Based Cryptography (RBC). Furthermore, ECCs are refined to reduce latencies while maintaining negligible failure rates in cryptographic key recovery and ensuring that helper data remains secure. This comprehensive approach aims to significantly enhance the security and efficiency of data transfers in IoT devices, particularly in the face of potential threats in insecure communication networks.

关键词： Internet of things (IoT) Physical Unclonable Function (PUF) Static Random access Memory (SRAM) One-time key generation Error Correction Code (ECC) Cryptography Security One-way hashing function Low bit error rates Randomness Communication networks Cryptographic algorithms

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：