检索结果-南通市图书馆

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

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

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Common coupled fixed point theorem for two pairs compatible and sub-sequentially continuous mapping

引用

Journal of Ocean Engineering and Science 2024年第4期9卷 401-407页

作者： H.M.Abu-Donia Mona S.Bakry H.A.Atia Omnia M.A.Khater Raghda A.M.Attia Department of Mathematics Faculty of ScienceZagazig UniversityZagazigEgypt Department of Mathematics Faculty of ScienceTanta UniversityTantaEgypt Department of Basic Science Zagazig Higher Institute of Engineering and TechnologyZagazigEgypt Department of Basic Science Higher Technological Institute 10th of Ramadan CityEl Sharqia 44634Egypt

This study establishes a common coupled fixed point for two pairs of compatible and sequentially continuous mappings in the intuitionistic fuzzy metric space that satisfy theφ-contractive *** basic definitions and theorems have been used from some recent scientific papers about the binary operator,t-norm,t-conorm,intuitionistic fuzzy metric space,and compatible mapping for reaching to the paper’s purpose.

关键词： Intuitionistic fuzzy metric space φ-contractive mapping Compatible mappings Couple fixed point

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Carbon enhanced nucleophilicity of Na_(3)V_(2)(PO_(4))_(3):A general approach for dendrite-free zinc metal anodes

引用

Journal of Energy Chemistry 2024年第4期91卷 203-212页

作者： Sijun Wang Lingzi Hu Xiaohui Li Dan Qiu Shunhang Qiu Qiancheng Zhou Wenwen Deng Xiaoying Lu Ze Yang Ming Qiu Ying Yu institute of Nanoscience and Nanotechnology School of Physical Science and TechnologyCentral China Normal UniversityWuhan 430079HubeiChina School of Material Science and Engineering Suzhou University of Science and TechnologySuzhou 215000JiangsuChina Faculty of Science and Technology Technological and Higher Education Institute of Hong KongHong KongChina

Zincophilic property and high electrical conductivity are both very important parameters to design novel Zn anode for aqueous Zn-ion batteries(AZIBs).However,single material is difficult to exhibit zincophilic property and high electrical conductivity at the same ***,originating from theoretical calculation,a zincophilic particle regulation strategy is proposed to address these limitations and carbon coated Na_(3)V_(2)(PO_(4))_(3)is taken as an example to be a protective layer on zinc metal(NVPC@Zn).Na_(3)V_(2)(PO_(4))_(3)(NVP)is a common cathode material for Zn-ion batteries,which is *** materials not only offer an electron pathway to help Zn deposition onto NVPC surface,but also enhance the zinc nucleophilicity of Na_(3)V_(2)(PO_(4))_(3).Hence,this hybrid coating layer can tune zinc deposition and resist side reactions such as hydrogen generation and Zn metal ***,a symmetrical battery with NVPC@Zn electrode displays highly reversible plating/stripping behavior with a long cycle lifespan over 1800 h at2 mA cm^(-2),much better than carbon and Na_(3)V_(2)(PO_(4))_(3)solely modified Zn *** the Na_(3)V_(2)(PO_(4))_(3)is replaced with zincophobic Al2O3or zincophilic V2O3,the stability of the modified zinc anodes is also *** strategy expands the option of zincophilic materials and provides a general and effective way to stabilize the Zn electrode.

关键词： Zinc-ion batteries Zinc anode Carbon enhanced nucleophilicity Zincophilic particle regulation

来源：

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

Interaction of edge dislocations with voids in tungsten

引用

Tungsten 2024年第3期6卷 633-646页

作者： Arseny Kazakov Rita I.Babicheva Aleksandr Zinovev Dmitry Terentyev Kun Zhou Elena A.Korznikova Sergey V.Dmitriev Research Laboratory for Metals and Alloys under Extreme Impacts Ufa University of Science and Technology institute for Metals Superplasticity Problems of RAS School of Mechanical and Aerospace Engineering Nanyang Technological University institute for Nuclear Energy Technology Belgian Nuclear Research Center technological Machines and Equipment Department Ufa State Petroleum Technological University institute of Mechanical Science Problems of RAS institute of Molecule and Crystal Physics UFRC of Russian Academy of Sciences

Tungsten is widely used as a material capable of withstanding extreme operating conditions and is one of the candidates for use in fusion and Generation Ⅳ fission *** modelling implemented to solve various material science problems is an indispensable approach for improving material *** work analyzes the interaction of an edge dislocation with a void in single-crystal tungsten with the help of molecular dynamics *** different approaches for studying the dynamics of dislocations in tungsten that differ in boundary conditions are *** interactions of the dislocation and void at different temperatures are investigated,and based on the obtained stress-strain curves,the dislocation obstacle strength for voids having various diameters is *** is shown that when applied to a crystal with small voids,the model with the fixed boundary conditions returns incorrect ***,the influence of the cell size for the model with periodic boundary conditions is analyzed,and the case of a non-central interaction of a dislocation with a void is *** obtained results improve our understanding of the mechanical response of irradiated materials.

关键词： Tungsten Molecular dynamics method Dislocations Voids Boundary conditions

来源：

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

Exercise and exerkine upregulation:Brain-derived neurotrophic factor as a potential non-pharmacological therapeutic strategy for Parkinson’s disease

引用

BIOCELL 2024年第5期48卷 693-706页

作者： VIRAAJ VISHNU PRASAD JENNIFER SALLY SAMSON VENKATACHALAM DEEPA PARVATHI Department of Biomedical Sciences Sri Ramachandra Institute of Higher Education and ResearchChennai600116India

Physical activity and exercise have several beneficial roles in enhancing both physiological and psychological well-being of an *** addition to aiding the regulation of aerobic and anaerobic metabolism,exercise can stimulate the synthesis of exerkine hormones in the circulatory *** several exerkines that have been investigated for their therapeutic potential,Brain-derived neurotrophic factor(BDNF)is considered the most promising candidate,especially in the management of neurodegenerative *** to the ability of physical activity to enhance BDNF synthesis,several experimental studies conducted so far have validated this hypothesis and produced satisfactory results at the pre-clinical *** review highlights some of the recent animal model studies that have evaluated the efficiency of exercise in enhancing BDNF synthesis and promoting neuroprotective ***,this review focuses on understanding the therapeutic benefits of exercise-induced exerkine synthesis as a non-pharmacological strategy in Parkinson’s disease(PD).Regarding physical activity and exerkine induction,the neuromuscular electrical stimulation(NMES)strategy could be considered as an alternate treatment modality for patients affected with PD.

关键词： Exercise therapy Dopaminergic neurons Parkinson’s disease Brain-derived neurotrophic factor Electrical stimulation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Proactive Resilience Enhancement of Power Systems with Link Transmission Model-based Dynamic Traffic Assignment Among Electric Vehicles

引用

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1320-1330页

作者： Haoyuan Yan Tianyang Zhao Zhanglei Guan Energy Electricity Research Center Jinan UniversityGuangzhou 510632China Energy Research institute Nanyang Technological UniversitySingapore IEEE

The rapid development of electric vehicles(EVs)is strengthening the bi-directional interactions between electric power networks(EPNs)and transportation networks(TNs)while providing opportunities to enhance the resilience of power systems towards extreme *** quantify the temporal and spatial flexibility of EVs for charging and discharging,a novel dynamic traffic assignment(DTA)problem is *** DTA problem is based on a link transmission model(LTM)with extended charging links,depicting the interaction between EVs and power *** models the charging rates as continuous variables by an energy boundary *** consider the evacuation requirements of TNs and the uncertainties of traffic conditions,the DTA problem is extended to a two-stage distributionally robust *** is further incorporated into a two-stage distributionally robust unit commitment problem to balance the enhancement of EPNs and the performance of *** problem is reformulated into a mixed-integer linear programming problem and solved by off-the-shelf commercial *** studies are performed on two test *** effectiveness is verified by the numerical results,e.g.,reducing the load shedding amount without increasing the unmet traffic demand.

关键词： Coupled transportation and power network link transmission model resilience enhancement

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Instance Segmentation of Characters Recognized in Palmyrene Aramaic Inscriptions

引用

Computer Modeling in Engineering & Sciences 2024年第9期140卷 2869-2889页

作者： Adéla Hamplová Alexey Lyavdansky TomášNovák Ondrej Svojše David Franc Arnošt Veselý Czech University of Life Sciences in Prague(CULS) Faculty of Economics and ManagementDepartment of Information EngineeringPrague16500Czech Republic National Research University higher School of Economics(HSE) Faculty of HumanitiesInstitute for Oriental and Classical StudiesMoscow101000The Russian Federation

This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions,employing two state-of-the-art deep learning algorithms,namely YOLOv8 and Roboflow *** goal is to contribute to the preservation and understanding of historical texts,showcasing the potential of modern deep learning methods in archaeological *** research culminates in several key findings and scientific *** comprehensively compare the performance of YOLOv8 and Roboflow 3.0 in the context of Palmyrene character segmentation—this comparative analysis mainly focuses on the strengths and weaknesses of each algorithm in this *** also created and annotated an extensive dataset of Palmyrene inscriptions,a crucial resource for further research in the *** dataset serves for training and evaluating the segmentation *** employ comparative evaluation metrics to quantitatively assess the segmentation results,ensuring the reliability and reproducibility of our findings and we present custom visualization tools for predicted segmentation *** study advances the state of the art in semi-automatic reading of Palmyrene inscriptions and establishes a benchmark for future *** availability of the Palmyrene dataset and the insights into algorithm performance contribute to the broader understanding of historical text analysis.

关键词： Optical character recognition instance segmentation Palmyrene ancient languages computer vision

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Combined CNN-LSTM Deep Learning Algorithms for Recognizing Human Physical Activities in Large and Distributed Manners:A Recommendation System

引用

Computers, Materials & Continua 2024年第4期79卷 351-372页

作者： Ameni Ellouze Nesrine Kadri Alaa Alaerjan Mohamed Ksantini Control and Energy Management Laboratory National Engineering SchoolPreparatory Institute for Engineering StudiesUniversity of SfaxSfax3029Tunisia higher institute of Computer Science and Communication Technologies University of SousseSousseBN19RHTunisia College of Computer and Information Sciences Jouf UniversityPO Box 2014SakakahSaudi Arabia

Recognizing human activity(HAR)from data in a smartphone sensor plays an important role in the field of health to prevent chronic *** and weekly physical activities are recorded on the smartphone and tell the user whether he is moving well or ***,smartphones and their associated sensing devices operate in distributed and unstable ***,collecting their data and extracting useful information is a significant *** this context,the aimof this paper is twofold:The first is to analyze human behavior based on the recognition of physical *** the results of physical activity detection and classification,the second part aims to develop a health recommendation system to notify smartphone users about their healthy physical behavior related to their physical *** system is based on the calculation of calories burned by each user during physical *** this way,conclusions can be drawn about a person’s physical behavior by estimating the number of calories burned after evaluating data collected daily or even weekly following a series of physical *** identify and classify human behavior our methodology is based on artificial intelligence models specifically deep learning techniques like Long Short-Term Memory(LSTM),stacked LSTM,and bidirectional *** human activity data contains both spatial and temporal information,we proposed,in this paper,to use of an architecture allowing the extraction of the two types of information *** Convolutional Neural Networks(CNN)has an architecture designed for spatial information,our idea is to combine CNN with LSTM to increase classification accuracy by taking into consideration the extraction of both spatial and temporal *** results obtained achieved an accuracy of 96%.On the other side,the data learned by these algorithms is prone to error and *** overcome this constraint and improve performance(96%),we proposed to use the

关键词： Human physical activities smartphone sensors deep learning distributed monitoring recommendation system uncertainty healthy calories

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

BCCLR:A Skeleton-Based Action Recognition with Graph Convolutional Network Combining Behavior Dependence and Context Clues

引用

Computers, Materials & Continua 2024年第3期78卷 4489-4507页

作者： Yunhe Wang Yuxin Xia Shuai Liu College of Information Science and Engineering Institute of Interdisciplinary StudiesHunan Normal UniversityChangsha410081China School of Educational Sciences Institute of Interdisciplinary StudiesHunan Normal UniversityChangsha410081China

In recent years,skeleton-based action recognition has made great achievements in Computer Vision.A graph convolutional network(GCN)is effective for action recognition,modelling the human skeleton as a spatio-temporal *** GCNs define the graph topology by physical relations of the human ***,this predefined graph ignores the spatial relationship between non-adjacent joint pairs in special actions and the behavior dependence between joint pairs,resulting in a low recognition rate for specific actions with implicit correlation between joint *** addition,existing methods ignore the trend correlation between adjacent frames within an action and context clues,leading to erroneous action recognition with similar ***,this study proposes a learnable GCN based on behavior dependence,which considers implicit joint correlation by constructing a dynamic learnable graph with extraction of specific behavior dependence of joint *** using the weight relationship between the joint pairs,an adaptive model is *** also designs a self-attention module to obtain their inter-frame topological relationship for exploring the context of *** the shared topology and the multi-head self-attention map,the module obtains the context-based clue topology to update the dynamic graph convolution,achieving accurate recognition of different actions with similar *** experiments on public datasets demonstrate that the proposed method achieves better results and realizes higher quality representation of actions under various evaluation protocols compared to state-of-the-art methods.

关键词： Action recognition deep learning GCN behavior dependence context clue self-attention

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Investigation of the transformation of organic matter of carbonate deposits of the Semiluksky-Mendymsky horizon under hydrothermal conditions

引用

Petroleum 2024年第2期10卷 216-223页

作者： S.M.Petrov A.I.Lakhova E.G.Moiseeva A.G.Safiulina institute of Petroleum Chemistry and NanotechnologiesKazan National Research Technological UniversityKazan420015Russia institute of Geology and Oil and Gas Technologies Kazan Federal UniversityKazan420008Russia

The paper presents the results of studies on the transformation of the organic matter of siliceous-clayey carbonate rocks of the Semiluksko-Mendymsky horizon of the Romashkino oil field in a hydrothermal fluid for an hour(with a water-to-rock ratio of 33)at 340℃and 380℃and pressu res of 17 and 20 *** a result of hydrothermal treatment,at 340℃and 17 MPa,based on nitrogen porosimetry and electron microscopy data,transformations of rock-forming minerals in the rock are *** lead to an increase in the volume and average diameter of mesopores in it and the formation of micropores,as well,which improve its filtration *** the same time,the amount of kerogen in the composition of the organic matter decreases and the yield of the petroleum hydrocarbon extract increases,in which,according to the SARA analysis,the content of asphaltenes increases and the content of resins,aromatic and saturated hydrocarbons *** the composition of aroatic hydrocarbons,the proportion of a lkyltri methyl benzenes and dibenzothiophenes increases,phenanthrene homologues appear,and in the composition of saturated hydrocarbons,the amount of iso-structure alkanes decreases relative to the content of linear *** the temperature and pressure of the hydrothermal fluid to 380℃and 20 MPa increases the degree of kerogen conversion from 12.4%to 23.6%.At the same time,changes occurring in the component composition of petroleum hydrocarbon extracts remains similar to the experiments carried out at 340℃and 17 MPa;the content of naphthalenes decreases,the content of dibenzothiophenes increases and C_(11)-C_(17),C_(19)-C_(22)alkyltrimethylbenzenes *** to IR spectroscopy,with increasing temperature and pressure of the hydrothermal fluid the intensity of the absorption bands of the aromatic ring,aliphatic fragments,and oxygen-containing groups increases in resins;the structural-group composition of asphaltenes changes little:aromaticity and the content of conde

关键词： Carbonate deposits Organic matter Hydrothermal fluid Mobile hydrocarbons

来源：

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

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：