检索结果-南通市图书馆

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

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5期79卷 1995-2014页

作者： Dmitry Gura Bo Dong Duaa Mehiar Nidal Al Said Department of Cadastre and Geoengineering Kuban State Technological UniversityKrasnodar350072Russian Federation Department of Geodesy Kuban State Agrarian UniversityKrasnodar350072Russian Federation School of Innovation and Entrepreneurship Liaoning UniversityLiaoning110031China Department of IT Middle East UniversityAmman11831Jordan College of Mass Communication Ajman UniversityP.O Box 346AjmanUnited Arab Emirates

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their *** proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the *** customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its *** used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were *** seconds were allotted for each *** were 318 videos used in all,199 of which were fake and 119 of which were *** proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and ***,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and *** novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

关键词： Deep fake detection video analysis convolutional neural network machine learning video dataset collection facial landmark prediction accuracy models

Recent progress in two-dimensional metallenes and their potential application as electrocatalyst

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 Energy Chemistry 2024年第7期94卷 577-598页

作者： Umer Shahzad Mohsin Saeed Muhammad Fazle Rabbee Hadi M.Marwani Jehan Y.Al-Humaidi Muhammad Altaf Raed H.Althomali Kwang-Hyun Baek Md.Rabiul Awual Mohammed M.Rahman Department of Chemistry Faculty of ScienceKing Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Biotechnology Yeungnam UniversityGyeongsanSouth Korea Center of Excellence for Advanced Materials Research(CEAMR) King Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Chemistry College of SciencePrincess Nourah Bint Abdulrahman UniversityP.O.BOX 84428Riyadh 11671Saudi Arabia Department of Chemistry Center of Excellence for Innovation in Chemistry(PERCH-CIC)Center of Excellence in Materials Science and TechnologyFaculty of ScienceChiang Mai UniversityChiang Mai 50200Thailand Department of Chemistry College of Art and SciencePrince Sattam Bin Abdulaziz UniversityWadi Al-Dawasir 11991Saudi Arabia Western Australian School of Mines:Minerals Energy and Chemical EngineeringCurtin UniversityGPO Box U 1987PerthWA 6845Australia

In this article,we looked at metallenes,a novel class of two-dimensional(2D)metals that are attracting interest in the energy and catalysis *** is one area where their exceptional physicochemical and electrical characteristics might be *** are unique because they include several metal atoms that are not in a coordinated *** makes them more active and improves their atomic uti-lization,which in turn increases their catalytic *** article delves into the potential of two-dimensional metals as electrocatalysts for carbon dioxide reduction,fuel oxidation,oxygen evolution,and oxygen reduction reactions in the context of sustainable energy *** to the exception-ally high surface-to-volume ratio,large surface area as well as their optimized atomic use efficiency,2D materials defined by atomic layers are crucial for surface-related sustainable energy *** to its exceptional properties,such as high conductivity and the ability to enhance the exposure of active metal sites,2D metallenes have recently attracted a lot of interest for use in catalysis,electronics,and energy-related *** their highly mobility,adjustable surface states,and electrical struc-tures that can be fine-tuned,2D metallenes are promising nanostructure materials for use in energy con-version with the sustainable applications.

关键词： Metallenes Electrocatalysts Electrochemical processes Atomically thin structure

Exploring Sequential Feature Selection in Deep Bi-LSTM Models for Speech Emotion Recognition

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2689-2719页

作者： Fatma Harby Mansor Alohali Adel Thaljaoui Amira Samy Talaat Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesCairo12622Egypt Department of Computer Science and Information College of Science at Zulfi Majmaah UniversityP.O.Box 66Al-Majmaah11952Saudi Arabia Preparatory Institute for Engineering Studies of Gafsa ZarrougGafsa2112Tunisia Computers and Systems Department Electronics Research InstituteCairo12622Egypt

Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional *** examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior *** identifying emotions in the SER process relies on extracting relevant information from audio *** studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals *** these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some *** this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human *** utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over *** next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster *** the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram *** attitude of feature selection is to retain only dominant features by excluding the irrelevant *** this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features ***,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short

关键词： Artificial intelligence application multi features sequential selection speech emotion recognition deep Bi-LSTM

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 Software Competence Center Hagenberg Softwarepark 32aHagenberg4232Austria Department of Computer Science School of Engineering and Digital SciencesNazarbayev UniversityAstana010000Kazakhstan Department of Information 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 crafted language,characterized by a script that amalgamates elements from diverse languages, including Arabic, Parsi, Pashtu,Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguisticfeatures, presents an additional hurdle due to the lack of accessible datasets, rendering sentiment analysis aformidable undertaking. The limited availability of resources has fueled 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 fivelabels: 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 from 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), for bothtraining and evaluating sentiment analysis performance. Additionally, the study explores hyperparameter tuning tooptimize the models’ efficacy. Evaluation metrics such as precision, recall, and the F1-score are employed to assessthe effectiv

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

Climate-influenced vector-borne diseases in Africa: a call to empower the next generation of African researchers for sustainable 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

贫困所致传染病(英文) 2024年第2期13卷 1-10页

作者： Obame-Nkoghe Judica?l Agossou Adjoavi Esse Mboowa Gerald Kamgang Basile Caminade Cyril Duke Dawn C. Githeko Andrew Karanja Ogega Obed M. Elloué Nestor Engone Sarr Fatou Bintou Nkoghe Dieudonné Kengne Pierre Ndam Nicaise T. Paupy Christophe Bockarie Moses Otomo Patricks Voua Molecular and Cellular Biology Laboratory (LabMC) Biology Department University of Science and Technology of Masuku BP Franceville Gabon Ecology and Health Research Unit Interdisciplinary Center for Medical Research of Franceville BP Franceville Gabon Department of Zoology and Entomology Faculty of Natural and Agricultural Sciences University of the Free State Private Bag x13 Phuthaditjhaba Republic of South Africa Laboratory of Pharmacology and Improved Traditional Medicines Department of Animal Physiology Faculty of Science and Technology University of Abomey-Calavi BP Cotonou Benin The African Center of Excellence in Bioinformatics and Data-Intensive Sciences Infectious Diseases Institute College of Health Sciences Makerere University P. O Box Kampala Uganda Africa Centers for Disease Control and Prevention African Union Commission Roosevelt Street P.O. Box WKAddis Ababa Ethiopia Centre for Research in Infectious Diseases P.O. Box Yaoundé Cameroon Earth System Physics Department The Abdus Salam International Centre for Theoretical Physics Trieste Italy Africa Research Excellence Fund Charterhouse Street London EC1MHR UK Community Health Support Program P.O. Box Kisumu Kenya The African Academy of Sciences Nairobi Kenya Center for Phylosophical Studies and Research (CERP) Omar Bongo University (UOB) BP Libreville Gabon UMRED Health Training and Research Unit University of Iba Der Thiam of Thiès BP Thiès Senegal National Parasitic Diseases Control Program Ministry of Health Libreville Gabon MIVEGEC Univ. Montpellier CNRS IRD Montpellier France MERIT IRD Paris Cité University Paris France Department of Parasitology Noguchi Memorial Institute for Medical Research University of Ghana LG Accra Ghana School of Community Health Sciences Njala University Bo Sierra Leone

We look at the link between climate change and vector-borne diseases in low- and middle-income countries in Africa. The large endemicity and escalating threat of diseases such as malaria and arboviral diseases, intensified by climate change, disproportionately affects vulnerable communities globally. We highlight the urgency of prioritizing research and development, advocating for robust scientific inquiry to promote adaptation strategies, and the vital role that the next generation of African research leaders will play in addressing these challenges. Despite significant challenges such as funding shortages within countries, various pan-African-oriented funding bodies such as the African Academy of Sciences, the Africa Research Excellence Fund, the Wellcome Trust, the U.S. National Institutes of Health, and the Bill and Melinda Gates Foundation as well as initiatives such as the African Research Initiative for Scientific Excellence and the Pan-African Mosquito Control Association, have empowered (or are empowering) these researchers by supporting capacity building activities, including continental and global networking, skill development, mentoring, and African-led research. This article underscores the urgency of increased national investment in research, proposing the establishment of research government agencies to drive evidence-based interventions. Collaboration between governments and scientific communities, sustained by pan-African funding bodies, is crucial. Through these efforts, African nations are likely to enhance the resilience and adaptive capacity of their systems and communities by navigating these challenges effectively, fostering scientific excellence and implementing transformative solutions against climate-sensitive vector-borne diseases.

关键词： Climate change Vector-borne diseases Africa Environmental justice Research and development Pan-African funding initiatives

Theoretical analysis of the double-differential cross-sections of neutron,proton,deuteron,^(3)He,andαfor the p+^(6) Li reaction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第3期35卷 181-197页

作者： Fang-Lei Zou Xiao-Jun Sun Jing-Shang Zhang Hai-Rui Guo Yin-Lu Han Rui-Rui Xu Xi Tao Ji-Min Wang Xiao-Dong Sun Yuan Tian Tao Ye Yong-Li Xu Chun-Tian Liang College of Physics Guangxi Normal University541004 GuilinChina Guangxi Key Laboratory of Nuclear Physics and Nuclear Technology 541004 GuilinChina China Institute of Atomic Energy P.O.Box 275(41)102413 BeijingChina Institute of Applied Physics and Computational Mathematics 10094 BeijingChina College of Physics and Electronic Shanxi Datong University037009 DatongChina School of Science Tianjin Chengjian University300384 TianjinChina

Based on the unified Hauser–Feshbach and exciton model,which can describe the particle emission processes between discrete energy levels with energy,angular momentum,and parity conservations,a statistical theory of light nucleus reaction(STLN)is developed to calculate the double-differential cross-sections of the outgoing neutron and light charged particles for the proton-induced^(6) Li reaction.A significant difference is observed between the p+^(6) Li and p+^(7) Li reactions owing to the discrepancies in the energy-level structures of the *** reaction channels,including sequential and simultaneous emission processes,are analyzed in *** the double-differential cross-sections of the outgoing proton as an example,the influence of contaminations(such as^(1) H,^(7)Li,^(12)C,and^(16)O)on the target is identified in terms of the kinetic energy of the first emitted *** optical potential parameters of the proton are obtained by fitting the elastic scattering differential *** calculated total double-differential cross-sections of the outgoing proton and deuteron at E_(p)=14 MeV agree well with the experimental data for different outgoing ***,the mixed double differential cross-sections of^(3) He andαare in good agreement with the *** agreement between the measured data and calculated results indicates that the two-body and three-body breakup reactions need to be considered,and the pre-equilibrium reaction mechanism dominates the reaction *** on the STLN model,a PLUNF code for the p+^(6) Li reaction is developed to obtain an ENDF-6-formatted file of the double-differential cross-sections of the nucleon and light composite charged particles.

关键词： Statistical theory of light nucleus reaction p+^(6)Li reaction Light composite charged particle Double-differential cross-sections Two-body breakup Three-body breakup

Luminescence regulation of Sb^(3+)in 0D hybrid metal halides by hydrogen bond network for optical anti-counterfeiting

在线全文

学校读者我要写书评

暂无评论

Opto-Electronic Advances 2024年第3期7卷 15-25页

作者： Dehai Liang Saif M.H.Qaid Xin Yang Shuangyi Zhao Binbin Luo Wensi Cai Qingkai Qian Zhigang Zang Key Laboratory of Optoelectronic Technology&Systems(Ministry of Education) Chongqing UniversityChongqing 400044China Department of Physics&Astronomy College of SciencesKing Saud UniversityP.O.Box 2455Riyadh 11451Saudi Arabia Department of Chemistry and Chemical Engineering Key Laboratory for Preparation and Application of Ordered Structural Materials of Guangdong ProvinceShantou UniversityShantou 515063China Department of Oil Army Logistics Academy of PLAChongqing 401311China

The Sb^(3+) doping strategy has been proven to be an effective way to regulate the band gap and improve the photophysical properties of organic-inorganic hybrid metal halides(OIHMHs).However,the emission of Sb^(3+) ions in OIHMHs is primarily confined to the low energy region,resulting in yellow or red *** date,there are few reports about green emission of Sb^(3+)-doped ***,we present a novel approach for regulating the luminescence of Sb^(3+) ions in 0D C_(10)H_(2)_(2)N_(6)InCl_(7)·H_(2)O via hydrogen bond network,in which water molecules act as agents for hydrogen ***^(3+)-doped C_(10)H_(2)2N_(6)InCl_(7)·H_(2)O shows a broadband green emission peaking at 540 nm and a high photoluminescence quantum yield(PLQY)of 80%.It is found that the intense green emission stems from the radiative recombination of the self-trapped excitons(STEs).Upon removal of water molecules with heat,C_(10)H_(2)_(2)N_(6)In_(1-x)Sb_(x)Cl_(7) generates yellow emis-sion,attributed to the breaking of the hydrogen bond network and large structural distortions of excited *** water molecules are adsorbed by C_(10)H_(2)_(2)N_(6)In_(1-x)Sb_(x)Cl_(7),it can subsequently emit green *** water-induced reversible emission switching is successfully used for optical security and information *** findings expand the under-standing of how the local coordination structure influences the photophysical mechanism in Sb^(3+)-doped metal halides and provide a novel method to control the STEs emission.

关键词： indium-based halides Sb^(3+)doping hydrogen bonding network optical anti-counterfeiting

Understanding the catalytic performance and deactivation behaviour of second-promoter doped Pt/WO_(χ)/γ-Al_(2)O_(3) catalysts in the glycerol hydrogenolysis for selective and cleaner production of 1,3-propanediol

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第7期94卷 486-507页

作者： Rafik Rajjak Shaikh Sittichai Damruang Rais Ahmad Khan Supareak Praserthdam Piyasan Praserthdam Center of Excellence on Catalysis and Catalytic Reaction Engineering(CECC) Department of Chemical EngineeringFaculty of EngineeringChulalongkorn UniversityBangkok 10330Thailand Department of Chemistry College of ScienceKing Saud UniversityP.O.Box 2455Riyadh 11451Saudi Arabia High-Performance Computing Unit(CECC-HCU) Centre of Excellence on Catalysis and Catalytic Reaction Engineering(CECC)Department of Chemical EngineeringFaculty of EngineeringChulalongkorn UniversityBangkok 10330Thailand

The selective aqueous-phase glycerol hydrogenolysis is a promising reaction to produce commercially useful 1,3-propanediol(1,3-PDO).The Pt-WOx bifunctional catalyst can catalyse the glycerol hydrogenol-ysis but the catalyst deactivation via sintering,metal leaching,and coking can predominantly occur in the aqueous phase *** this work,the effect of reaction temperature,pressure and second promoter(Cu,Fe,Rh,Mn,Re,Ru,Ir,Sn,B,and P)on catalytic performance and deactivation behaviour of Pt/WOx/-Al2O3 was *** doped with Rh,Mn,Re,Ru,Ir,B,and P,the second promoter boosts catalytic activity by promoting great dispersion of Pt on support and increasing Pt surface *** increased Bronsted acid sites lead to selective synthesis of 1,3-PDO than 1,2-propanediol(1,2-PDO).The characterization studies of fresh and spent catalysts reveal that the main cause of catalyst deactivation is the Pt sintering,as interpreted based on XRD,CO chemisorption,and TEM *** Pt sintering is affected depending on the second promoter that can either or reduce the interaction between Pt,WO_(χ)/γ and Al_(2)O_(3).As an electron acceptor of Pt in Pt/WO_(χ)/γ-Al_(2)O_(3),Re and Mn as second promoters resulted in increased Pt^(2+) on the catalytic surface,which strengthens the contact between Pt andγ-Al_(2)O_(3) and WO_(χ),resulting in a decrease in Pt *** metal leaching and coking are not affected by the presence of second *** catalyst modified with a second promoter possesses improved catalytic activity and 1,3-PDO production,however the stability continues to remain a *** present work unrav-elled the determining parameters of catalytic activity and deactivation,thus providing a promising pro-tocol toward effective catalysts for glycerol hydrogenolysis.

关键词： Glycerol hydrogenolysis 1,3-propanediol Metal-support interaction Second promoter Liquid phase Catalyst deactivation

Relating estimates of wood properties of birch to stem form, age and species

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2024年第3期35卷 1-11页

作者： Grace Jones Maria Ulan Mateusz Liziniewicz Johan Lindeberg Stergios Adamopoulos Teagasc Forestry Development Department Ashtown Research CentreDublin 15 D15DY05Ireland Research Institutes of Sweden(RISE) GoteborgSweden The Forest Research Institute of Sweden(Skogforsk) Ekebo 225026890SvalovSweden Department of Forestry and Wood Technology Linnaeus University35195VaxjoSweden Department of Forest Biomaterials and Technology Swedish University of Agricultural SciencesBox 700875007 UppsalaSweden

Birch has long suffered from a lack of active forest management,leading many researchers to use mate-rial without a detailed management *** collected from three birch(Betula pendula Roth,*** Ehrh.)sites in southern Sweden were analyzed using regression analysis to detect any trends or differences in wood proper-ties that could be explained by stand history,tree age and stem *** sites were genetics trials established in the same *** of acoustic velocity(AV)from non-destructive testing(NDT)and predicted AV had a higher correlation if data was pooled across sites and other stem form factors were considered.A subsample of stems had radial profiles of X-ray wood density and ring width by year created,and wood density was related to ring number from the pith and ring *** seemed likely that wood density was negatively related to ring width for both birch *** models had slight improvements if site and species were included,but only the youngest site with trees at age 15 had both birch *** paper indicated that NDT values need to be considered separately,and any predictive models will likely be improved if they are specific to the site and birch species measured.

关键词： Acoustic velocity Non-destructive testing Predictive models Regression analysis Wood density