检索结果-南通市图书馆

Cyber Security within Smart Cities: A Comprehensive Study and a Novel Intrusion Detection-Based Approach

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第1期81卷 393-441页

作者： Houichi M. Jaidi f. Bouhoula A. University of.Carthage Higher School of Communication of Tunis (Sup’Com) Innov’Com Lab\Digital Security Research Lab Tunis 2083 Tunisia National School of.Engineers of.Carthage University of Carthage Tunis 2035 Tunisia Department of.Next-Generation Computing College of Graduate Studies Arabian Gulf University Manama 26671 Bahrain

The expansion of.smart cities, f.cilitated by digital communications, has resulted in an enhancement of.the quality of.lif. and satisf.ction among residents. The Internet of.Things (IoT) continually generates vast amounts of.data, which is subsequently analyzed to of.er services to residents. The growth and development of.IoT have given rise to a new paradigm. A smart city possesses the ability to consistently monitor and utilize the physical environment, providing intelligent services such as energy, transportation, healthcare, and entertainment f.r both residents and visitors. Research on the security and privacy of.smart cities is increasingly prevalent. These studies highlight the cybersecurity risks and the challenges f.ced by smart city inf.astructure in handling and managing personal data. To ef.ectively uphold individuals’ security and privacy, developers of.smart cities must earn the trust of.the public. In this article, we delve into the realms of.privacy and security within smart city applications. Our comprehensive study commences by introducing architecture and various applications tailored to smart cities. Then, concerns surrounding security and privacy within these applications are thoroughly explored subsequently. f.llowing that, we delve into several research endeavors dedicated to addressing security and privacy issues within smart city applications. f.nally, we emphasize our methodology and present a case study illustrating privacy and security in smart city contexts. Our proposal consists of.def.ning an Artif.cial Intelligence (AI) based f.amework that allows: Thoroughly documenting penetration attempts and cyberattacks; promptly detecting any deviations f.om security standards; monitoring malicious behaviors and accurately tracing their sources; and establishing strong controls to ef.ectively repel and prevent such threats. Experimental results using the Edge-IIoTset (Edge Industrial Internet of.Things Security Evaluation Test) dataset demonstra

关键词： cybersecurity digital communications intrusion detection privacy Smart cities

Research on f.ne-Grained RecognitionMethod f.r Sensitive Inf.rmation in Social Networks Based on CLIP

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第1期81卷 1565-1580页

作者： Zhang M. Shan f. Liu M. Wang Z. School of.Computer Science Zhongyuan University of Technology Zhengzhou 450007 China Henan Key Laboratory of.Cyberspace Situation Awareness Zhengzhou 450001 China

With the emergence and development of.social networks, people can stay in touch with f.iends, f.mily, and colleaguesmore quickly and conveniently, regardless of.their location. This ubiquitous digital internet environment has also ledtolarge-scaledisclosureof.personal *** tothe complexity andsubtletyof.sensitive inf.rmation, traditional sensitive inf.rmation identif.cation technologies cannot thoroughly address the characteristics of.each piece of.data, thus weakening the deep connections between text and images. In this context, this paper adopts the CLIP model as a modality discriminator. By using comparative learning between sensitive image descriptions and images, the similarity between the images and the sensitive descriptions is obtained to determine whether the images contain sensitive inf.rmation. This provides the basis f.r identif.ing sensitive inf.rmation using dif.erent modalities. Specif.cally, if.the original data does not contain sensitive inf.rmation, only single-modality text-sensitive inf.rmation identif.cation is perf.rmed; if.the original data contains sensitive inf.rmation, multimodality sensitive inf.rmation identif.cation is conducted. This approach allows f.r dif.erentiated processing of.each piece of.data, thereby achieving more accurate sensitive inf.rmation identif.cation. The af.rementioned modality discriminator can address the limitations of.existing sensitive inf.rmation identif.cation technologies, making the identif.cation of.sensitive inf.rmation f.om the original data more appropriate and precise. © 2024 The Authors. Published by Tech Science Press.

关键词： Deep learning multi-modal f.sion sensitive inf.rmation recognition social networks

Advancing PCB Quality Control: Harnessing YOLOv8 Deep Learning f.r Real-Time f.ult Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第1期81卷 345-367页

作者： Khan R.U. Shah f. Khan A.A. Tahir H. f.culty of.Cognitive Sciences and Human Development Universiti Malaysia Sarawak Kota Samarahan 94300 Malaysia School of.Computer Science and Engineering Anhui University of Science and Technology Huainan 232001 China Department Electronic Quaid-i-Azam University Islamabad 45320 Pakistan

Printed Circuit Boards (PCBs) are materials used to connect components to one another to f.rm a working circuit. PCBs play a crucial role in modern electronics by connecting various components. The trend of.integrating more components onto PCBs is becoming increasingly common, which presents signif.cant challenges f.r quality control processes. Given the potential impact that even minute def.cts can have on signal traces, the surf.ce inspection of.PCB remains pivotal in ensuring the overall system integrity. To address the limitations associated with manual inspection, this research endeavors to automate the inspection process using the YOLOv8 deep learning algorithm f.r real-time f.ult detection in PCBs. Specif.cally, we explore the ef.ectiveness of.two variants of.the YOLOv8 architecture: YOLOv8 Small and YOLOv8 Nano. Through rigorous experimentation and evaluation of.our dataset which was acquired f.om Peking University’s Human-Robot Interaction Lab, we aim to assess the suitability of.these models f.r improving f.ult detection accuracy within the PCB manuf.cturing process. Our results reveal the remarkable capabilities of.YOLOv8 Small models in accurately identif.ing and classif.ing PCB f.ults. The model achieved a precision of.98.7%, a recall of.99%, an accuracy of.98.6%, and an f. score of.0.98. These f.ndings highlight the potential of.the YOLOv8 Small model to signif.cantly improve the quality control processes in PCB manuf.cturing by providing a reliable and ef.icient solution f.r f.ult detection. © 2024 The Authors. Published by Tech Science Press.

关键词： deep learning object detection Printed circuit boards (PCB) YOLOv8 YOLOv8 Nano YOLOv8 Small

High-Secured Image LSB Steganography Using AVL-Tree with Random RGB Channel Substitution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第1期81卷 183-211页

作者： Njoum M. Sulaiman R. Shukur Z. Qamar f. Center of.Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi 43600 Malaysia Computer Science and Cyber Security Faculty of Engineering and Information Technology BirZeit University Ramallah P.O. Box 14 BirZeit Palestine

Random pixel selection is one of.the image steganography methods that has achieved signif.cant success in enhancing the robustness of.hidden data. This property makes it dif.icult f.r steganalysts’ powerf.l data extraction tools to detect the hidden data and ensures high-quality stego image generation. However, using a seed key to generate non-repeated sequential numbers takes a long time because it requires specif.c mathematical equations. In addition, these numbers may cluster in certain ranges. The hidden data in these clustered pixels will reduce the image quality, which steganalysis tools can detect. Theref.re, this paper proposes a data structure that saf.guards the steganographic model data and maintains the quality of.the stego image. This paper employs the Adelson-Velsky and Landis (AVL) tree data structure algorithm to implement the randomization pixel selection technique f.r data concealment. The AVL tree algorithm provides several advantages f.r image steganography. f.rstly, it ensures balanced tree structures, which leads to ef.icient data retrieval and insertion operations. Secondly, the self.balancing nature of.AVL trees minimizes clustering by maintaining an even distribution of.pixels, thereby preserving the stego image quality. The data structure employs the pixel indicator technique f.r Red, Green, and Blue (RGB) channel extraction. The green channel serves as the f.undation f.r building a balanced binary tree. f.rst, the sender identif.es the colored cover image and secret data. The sender will use the two least signif.cant bits (2-LSB) of.RGB channels to conceal the data’s size and associated inf.rmation. The next step is to create a balanced binary tree based on the green channel. Utilizing the channel pixel indicator on the LSB of.the green channel, we can conceal bits in the 2-LSB of.the red or blue channel. The f.rst f.ur levels of.the data structure tree will mask the data size, while subsequent levels will conceal the remaining digits of.s

关键词： AVL tree capacity Image steganography imperceptibility peak signal-to-noise ratio (PSNR) pixel random selection (PRS)

Data-Driven Decision-Making f.r Bank TargetMarketing Using Supervised Learning Classif.ers on Imbalanced Big Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials and Continua 2024年第1期81卷 1703-1728页

作者： Nasir f. Ahmed A.A. SabirKiraz M. Yevseyeva I. Saif.M. School of.Computer Science and Inf.rmatics De Montfort University Leicester LE1 9BH United Kingdom f.culty of.Computer Science and Inf.rmation Technology Universiti Tun Hussein Onn Malaysia Johor 86400 Malaysia

Integrating machine learning and data mining is crucial f.r processing big data and extracting valuable insights to enhance decision-making. However, imbalanced target variables within big data present technical challenges that hinder the perf.rmance of.supervised learning classif.ers on key evaluation metrics, limiting their overall ef.ectiveness. This study presents a comprehensive review of.both common and recently developed Supervised Learning Classif.ers (SLCs) and evaluates their perf.rmance in data-driven decision-making. The evaluation uses various metrics, with a particular f.cus on the Harmonic Mean Score (f.1 score) on an imbalanced real-world bank target marketing dataset. The f.ndings indicate that grid-search random f.rest and random-search random f.rest excel in Precision and area under the curve, while Extreme Gradient Boosting (XGBoost) outperf.rms other traditional classif.ers in terms of.f.1 score. Employing oversampling methods to address the imbalanced data shows signif.cant perf.rmance improvement in XGBoost, delivering superior results across all metrics, particularly when using the SMOTE variant known as the BorderlineSMOTE2 technique. The study concludes several key f.ctors f.r ef.ectively addressing the challenges of.supervised learning with imbalanced datasets. These f.ctors include the importance of.selecting appropriate datasets f.r training and testing, choosing the right classif.ers, employing ef.ective techniques f.r processing and handling imbalanced datasets, and identif.ing suitable metrics f.r perf.rmance evaluation. Additionally, f.ctors also entail the utilisation of.ef.ective exploratory data analysis in conjunction with visualisation techniques to yield insights conducive to data-driven decision-making. © 2024 The Authors. Published by Tech Science Press.

关键词： Big data data mining data visualization imbalanced dataset label encoding machine learning sampling techniques

Two-Stream Approximation to the Radiative Transf.r Equation:A New Improvement and Comparative Accuracy with Existing Methods

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第2期41卷 278-292页

作者： f.Momo TEMGOUA L.Akana NGUIMDO DNJOMO Environmental Energy Technologies Laboratory(EETL) Faculty of SciencesUniversity of YaoundéPO Box 812 YaoundéCameroon Department of.Electrical and Electronic Engineering Faculty of Engineering and TechnologyUniversity of BueaPO Box 63 BueaCameroon

Mathematical modeling of.the interaction between solar radiation and the Earth's atmosphere is f.rmalized by the radiative transf.r equation(RTE), whose resolution calls f.r two-stream approximations among other methods. This paper proposes a new two-stream approximation of.the RTE with the development of.the phase f.nction and the intensity into a third-order series of.Legendre polynomials. This new approach, which adds one more term in the expression of.the intensity and the phase f.nction, allows in the conditions of.a plane parallel atmosphere a new mathematical f.rmulation of.γparameters. It is then compared to the Eddington, Hemispheric Constant, Quadrature, Combined Delta f.nction and Modif.ed Eddington, and second-order approximation methods with ref.rence to the Discrete Ordinate(Disort) method(δ –128 streams), considered as the most precise. This work also determines the conversion f.nction of.the proposed New Method using the f.ndamental def.nition of.two-stream approximation(f.TSA) developed in a previous work. Notably,New Method has generally better precision compared to the second-order approximation and Hemispheric Constant methods. Compared to the Quadrature and Eddington methods, New Method shows very good precision f.r wide domains of.the zenith angle μ 0, but tends to deviate f.om the Disort method with the zenith angle, especially f.r high values of.optical thickness. In spite of.this divergence in ref.ectance f.r high values of.optical thickness, very strong correlation with the Disort method(R ≈ 1) was obtained f.r most cases of.optical thickness in this study. An analysis of.the Legendre polynomial series f.r simple f.nctions shows that the high precision is due to the f.ct that the approximated f.nctions ameliorate the accuracy when the order of.approximation increases, although it has been proven that there is a limit order depending on the f.nction f.om which the precision is lost. This observation indicates that increasing the order of.app

关键词： Radiative Transf.r Equation two-stream method Legendre polynomial optical thickness moments of.specif.c intensity conversion f.nction transmittance ref.ectance

The Importance of.Posterior Tibial Slope in TKR: Pre and Post-Operative Measurements in United States Osteoarthritic Patients

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Open Journal of.Orthopedics 2024年第8期14卷 374-379页

作者： f.ederick f. Buechel Sr f.ederick f. Buechel Jr Rutgers New Jersey Medical School Department of Orthopaedic Surgery Newark USA Lenox Hill Hospital Department of Orthopaedic Surgery New York USA

Background: Sagittal plane placement of.the tibial component in total knee replacement (TKR) has important implications f.r maximizing the range of.f.exion motion, allowing collateral ligaments to f.nction more normally, as well as providing ideal compressive loading on the tibial bone-prosthesis interf.ce. This study attempts to quantif. the normal posterior tibial slope (PTS) angle pre-operatively and post-operatively in osteoarthritic patients af.er using a conventional extramedullary tibial resection guide to assess its ef.ectiveness. Methods: f.rty-nine primary cementless total knee replacements in 34 osteoarthritic patients were measured radiographically pre-operatively and one year post-operatively to determine the PTS and its ef.ect on range of.motion. Lateral X-rays, using the anterior cortical line of.the tibia, were employed f.r all measurements. Results: Pre-operative PTS measured 11.83˚ (range 5˚ - 18˚), while post-operative PTS of.implanted tibial components measured 11.30o (range 4˚ - 18˚). The pre-operative range of.motion of.112˚ (range 30˚ to 135˚) was improved to 119˚ (range 90˚ to 135˚) post-operatively af.er 1 year. Conclusions: Anterior tibial shaf. ref.rencing using a conventional extramedullary tibial resection guide provides an easy and convenient method f.r reproducing the anatomical PTS during TKR. This methodology provided improvement in average range of.motion f.om 112˚ pre-operatively to 119˚ post-operatively at one year.

关键词： Posterior Tibial Slope Posterior Tibial Inclination Extramedullary Tibial Resection Guide Total Knee Alignment

On an Invariant of.Tournament Digraphs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of.Applied Mathematics and Physics 2024年第7期12卷 2711-2722页

作者： Boris f. Melnikov Bowen Liu f.culty of.Computational Mathematics and Cybernetics Shenzhen MSU-BIT University Shenzhen China

To date, it is unknown whether it is possible to construct a complete graph invariant in polynomial time, so f.st algorithms f.r checking non-isomorphism are important, including heuristic algorithms, and f.r successf.l implementations of.such heuristics, both the tasks of.some modif.cation of.previously described graph invariants and the description of.new invariants remain relevant. Many of.the described invariants make it possible to distinguish a larger number of.graphs in the real time of.a computer program. In this paper, we propose an invariant f.r a special kind of.directed graphs, namely, f.r tournaments. The last ones, f.om our point of.view, are interesting because when f.xing the order of.vertices, the number of.dif.erent tournaments is exactly equal to the number of.undirected graphs, also with f.xing the order of.vertices. In the invariant we are considering, all possible tournaments consisting of.a subset of.vertices of.a given digraph with the same set of.arcs are iterated over. f.r such subset tournaments, the places are calculated in the usual way, which are summed up to obtain the f.nal values of.the points of.the vertices;these points f.rm the proposed invariant. As we expected, calculations of.the new invariant showed that it does not coincide with the most natural invariant f.r tournaments, in which the number of.points is calculated f.r each participant. So f.r, we have conducted a small number of.computational experiments, and the minimum value of.the pair correlation between the sequences representing these two invariants that we f.und is f.r dimension 15.

关键词： Graph Directed Graph Tournament ?nvariant

Macroscopic Traversable Wormholes: Minimum Requirements

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of.Astronomy and Astrophysics 2024年第3期14卷 230-243页

作者： Peter K. f. Kuhf.ttig Department of.Mathematics Milwaukee School of Engineering Milwaukee USA

While wormholes are just as good a prediction of.Einstein’s theory as black holes, they are subject to severe restrictions f.om quantum f.eld theory. To allow f.r the possibility of.interstellar travel, a macroscopic wormhole would need to maintain suf.iciently low radial tidal f.rces. It is proposed in this paper that the assumption of.zero tidal f.rces, i.e., the limiting case, is suf.icient f.r overcoming the restrictions f.om quantum f.eld theory. The f.asibility of.this approach is subsequently discussed by 1) introducing the additional conditions needed to ensure that the radial tidal f.rces can indeed be suf.iciently low and 2) by viewing traversable wormholes as emergent phenomena, thereby increasing the likelihood of.their existence.

关键词： Morris-Thorne Wormholes Traversability Minimum Requirements Stability Compatibility with Quantum f.eld Theory