检索结果-内蒙古大学图书馆

9th International Conference on Mining Intelligence and Knowledge Exploration, MIKE 2023

作者： Kadry, Seifedine Al-Betar, Mohammed Azmi Yassine, Sahar Mohan, Ramya Arunmozhi, Rama Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India

ISBN: (纸本)9783031440830

Radiological imaging of the chest (X-ray) is a cost-effective, widely accepted method of examining the lungs and abnormalities. During this research, a clinically significant Convolutional-Neural-Network (CNN) framework will be proposed for the examination of lung abnormalities. The proposed scheme aims to achieve better detection accuracy from the selected chest X-ray data. The following stages are included in these techniques: (i) CNN segmentation of the lung section, (ii) Deep-feature extraction utilizing selected CNN schemes, (iii) Handcrafted-feature extraction, (iv) Optimizing features using Firefly Algorithms, and (v) Binary classification and cross-validation of fivefold cross-validation. By implementing the pre-trained VGG-UNet, this framework is capable of extracting lungs sections from X-ray images. Using this lung segment, handcrafted features such as Local Binary Patterns (LBP) and Pyramid Histograms of Oriented Gradients (PHOG) are obtained. DFs and HFs are obtained using the FA, and then a serial concatenation is performed in order to obtain a hybrid feature vector. This feature vector is used to classify X-ray images into healthy and diseased groups. For examination in this study, X-ray images of disease classes, such as tuberculosis, COVID19, pneumonia, lung masses, and effusions, are considered. Based on the experimental results of this study, >98% of disease detection accuracy was confirmed using the proposed scheme combined with the SoftMax classifier. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DLT-Based Personal Data Access Control with Key-Redistribution 5

DLT-Based Personal Data Access Control with Key-Redistributi...

引用

5th International Conference on Blockchain Computing and Applications, BCCA 2023

作者： Barbàra, Fadi Zichichi, Mirko Ferretti, Stefano Schifanella, Claudio University of Turin Department of Computer Science Italy Universidad Politécnica de Madrid Ontology Engineering Group Spain University of Urbino Carlo Bo Department of Pure and Applied Sciences Italy

ISBN: (纸本)9798350339239

Data management services present a challenge in terms of trust, as service managers can access the data on their servers easily. Decentralized data services and smart contracts can solve problems related to the presence of centralized trusted authorities, but in turn they can introduce other issues related to compliance with data protection and regulations (e.g., GDPR). Historically, encryption has been used to address some of these concerns, but it restricts data sharing. To facilitate encrypted decentralized file storage while enabling data sharing, we propose a Key-Redistribution Proxy Re-Encryption (KeRePRE) system. KeRePRE is a decentralized and encrypted data-service, where authorization servers are part of a threshold proxy re-encryption scheme. A key-redistribution mechanism (that extends the Um-bral scheme) allows for the addition and removal of managers in a decentralized and trustless manner. Additionally, we offer a proof of concept implementation, where data access control is based on an access control list, implemented as a smart contract in a DLT, and can be read-only accessed by the authorization servers. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Age and Gender Classification Using Backpropagation and Bagging Algorithms

引用

computers, Materials & Continua 2023年第2期74卷 3045-3062页

作者： Ammar Almomani Mohammed Alweshah Waleed Alomoush Mohammad Alauthman Aseel Jabai Anwar Abbass Ghufran Hamad Meral Abdalla Brij B.Gupta Research and Innovation Department Skyline University CollegeP.O.Box 1797SharjahUAE IT-department-Al-Huson University College Al-Balqa Applied UniversityP.O.Box 50IrbidJordan Prince Abdullah Ben Ghazi Faculty of Information and Communication Technology Al-Balqa Applied UniversityAl-SaltJordan School of Information Technology Skyline University CollegeSharjah P.O.Box 1797United Arab Emirates Department of Information Security Faculty of Information TechnologyUniversity of PetraAmmanJordan Department of Computer Science and Information Engineering Asia UniversityTaizhongTaiwan Department of Computer Science King Abdulaziz UniversityJeddahSaudi Arabia

Voice classification is important in creating more intelligent systems that help with student exams,identifying criminals,and security *** main aim of the research is to develop a system able to predicate and classify gender,age,and ***,a newsystem calledClassifyingVoice Gender,Age,and Accent(CVGAA)is *** and bagging algorithms are designed to improve voice recognition systems that incorporate sensory voice features such as rhythm-based features used to train the device to distinguish between the two gender *** has high precision compared to other algorithms used in this problem,as the adaptive backpropagation algorithm had an accuracy of 98%and the Bagging algorithm had an accuracy of 98.10%in the gender identification *** has the best accuracy among all algorithms,with 55.39%accuracy in the voice common dataset and age classification and accent accuracy in a speech accent of 78.94%.

关键词： Classify voice gender accent age bagging algorithms back propagation algorithms AI classifiers

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Multi-Layer Security Framework for Protecting E-Health Records 1

Cloud-Based Multi-Layer Security Framework for Protecting E-...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Naidu, P Ramesh Gowda, V Dankan Mali, Ujwala Suryakant Mallikarjun, Shruti Srinivas, D. Kawale, Sheetalrani R Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Karnataka Bangalore India Bms Institute of Technology and Management Department of Electronics & Communication Engineering Karnataka Bangalore India Applied Science Bharati Vidyapeeth College of Engineering Navi Mumbai India Karnataka State Akkamahadevi Women University Department of Computer Science Karnataka Vijaypura India School of Business Sr University Telangana Warangal India

ISBN: (纸本)9798350330915

The increasing role that cloud computing plays in storing e-health data has highlighted the necessity for strong security measures. The purpose of this study is to shed light on the difficulties in protecting private health data that is kept on cloud servers. As the first priority, we developed a unique multi-layer security architecture that is cloud-based to protect electronic health data. We provide a complete analysis of the current security protocols, perform a vulnerability assessment, and create a more robust multi-layered security architecture as part of our methodology. The concept includes sophisticated encryption methods, strict access rules, and instruments for ongoing threat detection. In order to assess the effectiveness of the framework, we ran extensive simulations with an emphasis on data integrity, access control, and confidentiality. The findings show a considerable improvement over conventional, one-layer security techniques. The proposed framework guarantees regulatory compliance in addition to providing enhanced security against illegal access and data breaches. We have found that safeguarding electronic health records - which are critical for both patients and healthcare providers - requires a multi-layered security approach built on the cloud. The findings of this study may lead to improved cloud-based healthcare data security in the future. © 2023 IEEE.

关键词： Access Control Mechanisms Data Integrity E-Health Records Protection Health Data Privacy Multi-Layer Security Framework

来源：评论

学校读者我要写书评

暂无评论

EVIDENTIAL TURING PROCESSES 10

EVIDENTIAL TURING PROCESSES

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Kandemir, Melih Akgül, Abdullah Haussmann, Manuel Unal, Gozde Dept of Math and Computer Science University of Southern Denmark Odense Denmark Department of Computer Engineering Istanbul Technical University Istanbul Turkey Department of Computer Science Aalto University Espoo Finland

A probabilistic classifier with reliable predictive uncertainties i) fits successfully to the target domain data, ii) provides calibrated class probabilities in difficult regions of the target domain (e.g. class overlap), and iii) accurately identifies queries coming out of the target domain and rejects them. We introduce an original combination of Evidential Deep Learning, Neural Processes, and Neural Turing Machines capable of providing all three essential properties mentioned above for total uncertainty quantification. We observe our method on five classification tasks to be the only one that can excel all three aspects of total calibration with a single standalone predictor. Our unified solution delivers an implementation-friendly and compute efficient recipe for safety clearance and provides intellectual economy to an investigation of algorithmic roots of epistemic awareness in deep neural nets. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Turing machines

来源：评论

学校读者我要写书评

暂无评论

AI in Cybersecurity: Activities of the CINI-AIIS Lab at University of Naples Federico II

AI in Cybersecurity: Activities of the CINI-AIIS Lab at Univ...

引用

2024 Ital-IA Intelligenza Artificiale - Thematic Workshops, Ital-IA 2024

作者： Ferraro, Antonino Galli, Antonio La Gatta, Valerio Marassi, Lidia Marrone, Stefano Moscato, Vincenzo Postiglione, Marco Sansone, Carlo Sperli, Giancarlo University of Naples Federico II Via Claudio 21 Naples80125 Italy Northwestern University Department of Computer Science McCormick School of Engineering and Applied Science 2233 Tech Dr EvanstonIL60208 United States

Artificial intelligence (AI) is revolutionizing various industries, including cybersecurity, by emulating human intelligence to address complex threats. In the cybersecurity domain, AI offers significant potential, bolstering defense mechanisms, optimizing threat detection, and advancing incident response capabilities. AI-powered systems can analyze vast datasets to identify anomalies, predict cyberattacks, and enhance overall security posture. Machine Learning (ML), a subset of AI, enables systems to learn from data and make informed decisions, such as predicting optimal security measures based on threat intelligence and operational context. Deep Learning (DL), another ML subset, harnesses Artificial Neural Networks (ANNs) to process intricate data patterns and provide accurate threat assessments. DL, especially through Convolutional Neural Networks (CNNs), is transforming cybersecurity by extracting meaningful features from network traffic and log data for anomaly detection and threat hunting. Moreover, DL integrated with Natural Language Processing (NLP) streamlines tasks like threat intelligence analysis and incident response coordination. The versatility of AI underscores its pivotal role in cybersecurity, driving resilience enhancements and fostering proactive defense strategies. In this paper, we highlight AI projects in the cybersecurity sector from the University of Naples Federico II node of the CINI-AIIS Lab, showcasing their innovative contributions to cyber defense. © 2024 Copyright for this paper by its authors.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Waterbodies from Satellite Images Using DeepLabV3+ 1

引用

9th International Conference on Mining Intelligence and Knowledge Exploration, MIKE 2023

ISBN: (数字)9783031440847

ISBN: (纸本)9783031440830

In recent times, it has become increasingly popular to examine a wide range of environmental and earth data using remote sensing schemes supported by satellite images (SI). Due to the complex nature of spatial, spectral, and temporal characteristics of SI, it is quite difficult for automatic analysis to be performed as it requires specially designed algorithms. As part of the research proposal, an enhanced deep-learning scheme will be implemented in order to extract the waterbodies from the chosen SIs. The phases involved in this scheme includes;(i) the collection and resizing of images, (ii) Shannon's Entropy preprocessing, (iii) DeepLabV3+ extraction of waterbodies, (iv) the comparison of extracted sections with ground truth (GT) and the calculation of performance metrics, and (v) validation of the effectiveness of the implemented scheme. In the proposed work, the proposed multi-thresholding approach is combined with DeepLabV3+ in order to get the waterbodies to be extracted from the chosen test images. DeepLabV3 is demonstrated to have excellent segmentation performance when it is compared to UNet and SegNet. The experimental results of this scheme indicate that DeepLabV3+ results in higher Jaccard value (>89%), Dice value (>93%), and segmentation accuracy value (>97%) when compared to other pretrained segmentation schemes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Powering IoT Systems with 5G Wireless Communication: A Comprehensive Review 8

Powering IoT Systems with 5G Wireless Communication: A Compr...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Palarimath, Suresh Pyingkodi, M. Thenmozhi, K. Maqsood, Mohammed Salam, Mohammed Abdul Palarimath, Roopa Devi University of Techonology and Applied Sciences Information Technology Department Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Compute Science Bengaluru India Governors State University Information Technology Department University Park United States Mansarovar Global University Faculty of Computer Science Bhopal India

ISBN: (纸本)9798350396638

In today's modern world, IoT plays an important and multifaceted function in all industries. 5th Generation Wireless Systems - 5G is the primary technical platform on which the Internet of Things plays a major role in smart technologies. Incorporating 5G technology into the architecture of an IoT system is now simple. Using plug-and-play technology, remote access to configuration and control is possible. Smart technology always results in faster data transfer rates, more bandwidth, greater capacity, lower latency, and a quicker output response. Based on this notion, IoT brings about a dramatic shift in heterogeneous networks. So, there is a need to implement 5G-IoT technologies. In the age of the Internet of Things, the fifth-generation (5G) cellular networks give the smart and complex technical environment. 5G Cellular Networks offer great growth potential for IoT technologies. This article gives a thorough study of the role of 5G Cellular Networks in the expansion of IoT technologies across all industries. Since the inclusion of renewable energy emerges as a new trend in the digital world, 5G is very beneficial in the age of the Internet of Things. To achieve the link between 'Things and People,' 'Things and Things,' and 'People and People' in power Systems, it is necessary to combine IoT with 5G in power systems to a high degree of success in various power-based industry-based systems. This article demonstrates a smart scenario and provides a thorough analysis of "how 5G drives the IoT System intelligently in every way and how IoT affects as the "most promising technology"with this smart 5G Wireless Communication System."In addition, the IoT era 5G application possibilities were demonstrated. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Model Adaptation for Enhanced Liveness Face Detection: Experimental Findings on SiWMv2 Dataset 8

Model Adaptation for Enhanced Liveness Face Detection: Exper...

引用

8th IEEE International Conference on Computing, Communication, Control and Automation, ICCUBEA 2024

作者： Khairnar, Smita Gite, Shilpa Thepade, Sudeep D. Mahajan, Kashish University Symbiosis Institute of Technology Computer Science and Information Technology Department Pune412115 India Pimpri Chinchwad College of Engineering Pune411044 India Pune Symbiosis Centre for Applied Ai Symbiosis Institute of Technology Aiml Department Pune412115 India PCET's Pimpri Chinchwad University Pimpri Chinchwad College of Engineering Pune411044 India Pimpri Chinchwad College of Engineering and Research Computer Science Department Pune412101 India

ISBN: (纸本)9798350391770

The field of liveness face detection, an essential component of security and biometrics, has seen notable advancements through developments in computer vision and deep learning. It's crucial for accurately distinguishing between genuine and spoofed data samples. This study aims to elevate the performance of automated liveness face detection by focusing on model adaptation, utilizing the SiWMv2 dataset. This dataset is particularly valuable as it encompasses 14 kinds of spoofing attacks, that include print, replay attacks, obfuscation makeup, paper glasses, and various others, which significantly enhances the robustness of the detection systems against a wide array of spoofing techniques. By fine-tuning and adapting seven pre-trained architectures - VGG16, DenseNet201, InceptionV3, VGG19, ResNet50, MobileNetV2, and Xception - paper aims to push all boundaries of current automated liveness face detection capabilities. Through systematic experimentation and analysis, this study aims to contribute to the improvement and effectiveness of liveness face detection systems across various applications, ensuring they are more resilient and capable of handling diverse spoofing scenarios. © 2024 IEEE.

关键词： Data obfuscation

来源：评论

学校读者我要写书评

暂无评论

Forgive and forget: Self-stabilizing swarms in spite of Byzantine robots

Forgive and forget: Self-stabilizing swarms in spite of Byza...

引用

作者： Ashkenazi, Yotam Dolev, Shlomi Kamei, Sayaka Ooshita, Fukuhito Wada, Koichi Department of Computer Science Ben-Gurion University of the Negev Beersheba Israel Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan Graduate School of Science and Technology Nara Institute of Science and Technology Nara Japan Department of Applied Informatics Faculty of Science and Engineering Hosei University Tokyo Japan

In this article, we consider the case in which a swarm of robots collaborates in a mission, where a few of the robots behave maliciously. These malicious Byzantine robots may be temporally or constantly controlled by an adversary. The scope is synchronized full information robot operations, where a robot that does not follow the program/policy of the swarm is immediately identified and can be remembered as Byzantine. As robots may be suspected of being Byzantine due to benign temporal malfunctions, it is imperative to forgive and forget, otherwise, a robot cannot assume collaborative actions with any other robot in the swarm. Still, remembering for a while may facilitate a policy of surrounding, isolating and freezing the movement of the misbehaving robots, by several robots, allowing the rest to perform the swarm task with no intervention. We demonstrate the need to periodically forgive and forget to realize swarm several tasks including patrolling/cleaning in the presence of possible Byzantine robots. The policy for achieving the task consists of blocking the movement of the Byzantine robot(s) by some of the robots, while the rest patrol/clean the plane. © 2020 John Wiley & Sons, Ltd.

关键词： Robots

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：