检索结果-南通市图书馆

Mental health status among COVID-19 patients survivors of.critical illness in Saudi Arabia:A 6-month f.llow-up questionnaire study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of.Clinical Cases 2024年第15期12卷 2560-2567页

作者： Abdullah M Alhammad Namareq f.Aldardeer Abdulaziz alqahtani Mohammad H Aljawadi Bushra Alnef.ie Raghad Alonazi Mansour Almuqbil abdulrahman Alsaadon Rakan M alqahtani Rashid Alballaa Bader Alshehri Mohammed I Alarif. f.had D Alosaimi Department of.Clinical Pharmacy College of PharmacyKing Saud UniversityRiyadh 12372Saudi Arabia Department of.Pharmacy Services King Faisal Specialist Hospital and Research CentreJeddah 21499Saudi Arabia Corporate Department of.Pharmacy Services King Saud University Medical CityRiyadh 12372Saudi Arabia College of.Pharmacy King Saud UniversityRiyadh 12372Saudi Arabia Department of.Critical Care Medicine College of MedicineKing Saud UniversityRiyadh 12372Saudi Arabia Department of.Psychiatry College of MedicineKing Saud UniversityRiyadh 12372Saudi Arabia

BACKGROUND Psychological assessment af.er intensive care unit(ICU)discharge is increasingly used to assess patients'cognitive and psychological ***,f.w studies have examined those who recovered f.om coronavirus disease 2019(COVID-19).There is a paucity of.data f.om the Middle East assessing the post-ICU discharge mental health status of.patients who had *** To evaluate anxiety and depression among patients who had severe *** This is a prospective single-center f.llow-up questionnaire-based study of.adults who were admitted to the ICU or under ICU consultation f.r>24 h f.r *** patients were contacted via *** patient’s anxiety and depression six months af.er ICU discharge were assessed using the Hospital Anxiety and Depression Scale(HADS).The primary outcome was the mean HADS *** secondary outcomes were risk f.ctors of.anxiety and/or *** Patients who were admitted to the ICU because of.COVID-19 were screened(n=518).Of.these,48 completed the *** mean age was 56.3±17.2 *** patients(62.5%)were *** main comorbidities were endocrine(n=24,50%)and cardiovascular(n=21,43.8%)*** mean overall HADS score f.r anxiety and depression at 6 months post-ICU discharge was 11.4(SD±8.5).A HADS score of.7 f.r anxiety and depression was detected in 15 patients(30%)and 18 patients(36%),*** f.om the multivariable ordered logistic regression demonstrated that vasopressor use was associated with the development of.anxiety and depression[odds ratio(OR)39.06,95% conf.dence interval:1.309-1165.8;Pf.er ICU discharge,30% of.patients who had COVID-19 demonstrated a HADS score that conf.rmed anxiety and *** compare the psychological status of.patients f.llowing an ICU admission(with vs without COVID-19),f.rther studies are warranted.

关键词： COVID-19 Critically ill Anxiety Depression HADS Saudi Arabia

Sentiment Analysis of.Low-Resource Language Literature Using Data Processing and Deep Learning

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 & Continua 2024年第4期79卷 713-733页

作者： Aizaz Ali Maqbool Khan Khalil Khan Rehan Ullah Khan abdulrahman Aloraini Department of.IT and Computer Science Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur22620Pakistan Sof.ware Competence Center Hagenberg Softwarepark 32aHagenberg4232Austria Department of.Computer Science School of Engineering and Digital SciencesNazarbayev UniversityAstana010000Kazakhstan Department of.Inf.rmation Technology College of ComputerQassim UniversityP.O.Box 1162BuraydahSaudi Arabia

Sentiment analysis, a crucial task in discerning emotional tones within the text, plays a pivotal role in understandingpublic opinion and user sentiment across diverse *** numerous scholars conduct sentiment analysisin widely spoken languages such as English, Chinese, Arabic, Roman Arabic, and more, we come to grapplingwith resource-poor languages like Urdu literature which becomes a challenge. Urdu is a uniquely craf.ed language,characterized by a script that amalgamates elements f.om diverse languages, including Arabic, Parsi, Pashtu,Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguisticf.atures, presents an additional hurdle due to the lack of.accessible datasets, rendering sentiment analysis af.rmidable undertaking. The limited availability of.resources has f.eled increased interest among researchers,prompting a deeper exploration into Urdu sentiment analysis. This research is dedicated to Urdu languagesentiment analysis, employing sophisticated deep learning models on an extensive dataset categorized into f.velabels: Positive, Negative, Neutral, Mixed, and Ambiguous. The primary objective is to discern sentiments andemotions within the Urdu language, despite the absence of.well-curated datasets. To tackle this challenge, theinitial step involves the creation of.a comprehensive Urdu dataset by aggregating data f.om various sources such asnewspapers, articles, and socialmedia comments. Subsequent to this data collection, a thorough process of.cleaningand preprocessing is implemented to ensure the quality of.the data. The study leverages two well-known deeplearningmodels, namely Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), f.r bothtraining and evaluating sentiment analysis perf.rmance. Additionally, the study explores hyperparameter tuning tooptimize the models’ ef.icacy. Evaluation metrics such as precision, recall, and the f.-score are employed to assessthe ef.ectiv

关键词： Urdu sentiment analysis convolutional neural networks recurrent neural network deep learning natural language processing neural networks

Mitigating Urban Heat Island Ef.ects: A Review of.Innovative Pavement Technologies and Integrated Solutions

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Structural Durability & Health Monitoring 2024年第5期18卷 525-551页

作者： S.f.Ismael A.H.Alias N.A.Haron B.B.Zaidan abdulrahman M.Abdulghani Department of.Civil Engineering Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia Central Region Heavy Civil DivisionGranite ConstructionWoodlandsTexas77381USA SP Jain School of.Global Management LidcombeSydneyNSW2141Australia Department of.Communication Technology and Network Faculty of Computer Science and Information TechnologyUniversiti Putra MalaysiaSerdang43400Malaysia

In this review paper,we present a thorough investigation into the role of.pavement technologies in advancing urban *** analysis traverses the historical evolution of.these technologies,meticulously evaluating their socio-economic and environmental impacts,with a particular emphasis on their role in mitigating the urban heat island *** evaluation of.pavement types and variables inﬂuencing pavement perf.rmance to be used in the multi-criteria decision-making(MCDM)f.amework to choose the optimal pavement application are at the heart of.our *** serves to assess a spectrum of.pavement options,revealing insights into the most ef.ective and sustainable *** highlighting both the existing challenges and potential innovative solutions within theﬁeld,this paper aims to of.er a directional compass f.r f.ture urban planning and inf.astructural *** review not only synthesizes the current state of.knowledge but also aims to chart a course f.r f.ture exploration,emphasizing the critical need f.r innovative and environmentally sensitive pavement tech-nologies in the creation of.resilient and sustainable urban environments.

关键词： Pavement sustainability urban heat island environmental impact of.pavements innovative pavement solutions economic and social implications sustainable development in urban areas

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

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 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

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu f.yez alqahtani Amr Gaf.r Pradip Kumar Sharma Shenzhen Institutes of.Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangf.r Technologies Inc. Shenzhen518055China School of.Data Science and Artif.cial Intelligence Wenzhou University of TechnologyWenzhou325035China College of.Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Sof.ware Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of.hardware devices and the upgrading of.smartphones,a large number of.users save privacy-related inf.rmation in mobile devices,mainly smartphones,which puts f.rward higher demands on the protection of.mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of.high precision and non-perception,but there are still shortcomings such as low data collection ef.iciency,untrustworthy participating nodes,and lack of.*** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and f.derated learning to improve the data collection ef.iciency of.mobile user authentication,reduce the probability of.the model being bypassed by attackers,and reduce the overhead of.data centralized processing and the risk of.privacy leakage;(2)Use certif.cateless encryption to realize the authentication of.the device to ensure the credibility of.the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of.mobile devices to improve the accuracy of.model *** experimental results on the real environment dataset of.1513 people show that themethod proposed in this paper can ef.ectively resist poisoning attacks while ensuring the accuracy and ef.iciency of.mobile user authentication.

关键词： Mobile authentication blockchain f.derated learning smart contract certif.cateless encryption VMD LSTM

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