检索结果-南通市图书馆

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

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

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

Frequency of and reasons behind non-listing in adult patients referred for liver transplantation: Results from a retrospective 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 Transplantation 2024年第2期14卷 99-106页

作者： Marco Biolato Luca Miele Giuseppe Marrone Claudia Tarli Antonio Liguori Rosaria Calia Giovanni Addolorato Salvatore Agnes Antonio Gasbarrini Maurizio Pompili Antonio Grieco department of Medical and surgical Sciences CEMADFondazione Policlinico Universitario Agostino Gemelli IRCCSRome 00168Italy department of Translational Medicine and Surgery Catholic University of Sacred HeartRome 00168Italy

BACKGROUND Few studies have evaluated the frequency of and the reasons behind the refusal of listing liver transplantation *** To assess the ineligibility rate for liver transplantation and its *** A single-center retrospective study was conducted on adult patients which entailed a formal multidisciplinary assessment for liver transplantation *** predictors for listing were evaluated using multivariable logistic *** In our center,314 patients underwent multidisciplinary work-up before liver transplantation enlisting over a three-year *** most frequent reasons for transplant evaluation were decompensated cirrhosis(51.6%)and hepatocellular carcinoma(35.7%).The non-listing rate was 53.8%and the transplant rate was 34.4%for the whole *** hundred and five motivations for ineligibility were *** most common contraindications were psychological(9.3%),cardiovascular(6.8%),and surgical(5.9%).Inappropriate or premature referral accounted for 76(37.1%)*** multivariable analysis,a referral from another hospital(OR:2.113;95%CI:1.259–3.548)served as an independent predictor of *** A non-listing decision occurred in half of our cohort and was based on an inappropriate or premature referral in one case out of *** referral from another hospital was taken as a strong predictor of non-listing.

关键词： Controindication Eligibility Evaluation Referral Personalized medicine

Optimizing prediction models for pancreatic fistula after pancreatectomy:Current status and future perspectives

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 Gastroenterology 2024年第10期30卷 1329-1345页

作者： Feng Yang John A Windsor De-Liang Fu department of Pancreatic Surgery Huashan HospitalShanghai Medical CollegeFudan UniversityShanghai 200040China surgical and Translational Research Centre Faculty of Medical and Health SciencesUniversity of AucklandAuckland 1142New Zealand

Postoperative pancreatic fistula(POPF)is a frequent complication after pancre-atectomy,leading to increased morbidity and *** prediction models for POPF has emerged as a critical focus in surgical *** over sixty models following pancreaticoduodenectomy,predominantly reliant on a variety of clinical,surgical,and radiological parameters,have been documented,their predictive accuracy remains suboptimal in external validation and across diverse *** models after distal pancreatectomy continue to be pro-gressively reported,their external validation is eagerly ***,POPF prediction after central pancreatectomy is in its nascent stage,warranting urgent need for further development and *** potential of machine learning and big data analytics offers promising prospects for enhancing the accuracy of prediction models by incorporating an extensive array of variables and optimizing algorithm ***,there is potential for the development of personalized prediction models based on patient-or pancreas-specific factors and postoperative serum or drain fluid biomarkers to improve accuracy in identifying individuals at risk of *** the future,prospective multicenter studies and the integration of novel imaging technologies,such as artificial intelligence-based radiomics,may further refine predictive *** these issues is anticipated to revolutionize risk stratification,clinical decision-making,and postoperative management in patients undergoing pancre-atectomy.

关键词： Pancreatic fistula Pancreaticoduodenectomy Distal pancreatectomy Central pancreatectomy Prediction model Machine learning Artificial intelligence

Hybrid Gene Selection Methods for High-Dimensional Lung Cancer Data Using Improved Arithmetic Optimization Algorithm

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6期79卷 5175-5200页

作者： Mutasem K.Alsmadi department of Management Information Systems College of Applied Studies and Community ServiceImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia

Lung cancer is among the most frequent cancers in the world,with over one million deaths per *** is required for lung cancer diagnosis and therapy to be effective,accurate,and *** expression microarrays have made it possible to find genetic biomarkers for cancer diagnosis and prediction in a high-throughput *** Learning(ML)has been widely used to diagnose and classify lung cancer where the performance of ML methods is evaluated to identify the appropriate *** and selecting the gene expression patterns can help in lung cancer diagnoses and ***,microarrays include several genes and may cause confusion or false ***,the Arithmetic Optimization Algorithm(AOA)is used to identify the optimal gene subset to reduce the number of selected *** can allow the classifiers to yield the best performance for lung cancer *** addition,we proposed a modified version of AOA which can work effectively on the high dimensional *** the modified AOA,the features are ranked by their weights and are used to initialize the AOA *** exploitation process of AOA is then enhanced by developing a local search algorithm based on two neighborhood ***,the efficiency of the proposed methods was evaluated on gene expression datasets related to Lung cancer using stratified 4-fold *** method’s efficacy in selecting the optimal gene subset is underscored by its ability to maintain feature proportions between 10%to 25%.Moreover,the approach significantly enhances lung cancer prediction *** instance,Lung_Harvard1 achieved an accuracy of 97.5%,Lung_Harvard2 and Lung_Michigan datasets both achieved 100%,Lung_Adenocarcinoma obtained an accuracy of 88.2%,and Lung_Ontario achieved an accuracy of 87.5%.In conclusion,the results indicate the potential promise of the proposed modified AOA approach in classifying microarray cancer data.

关键词： Lung cancer gene selection improved arithmetic optimization algorithm and machine learning

Anemarsaponin B mitigates acute pancreatitis damage in mice through apoptosis reduction and MAPK pathway modulation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

BIOCELL 2024年第5期48卷 745-758页

作者： YI HU ZHONGYANG REN ZHENGZHONG ZHAO YONGJIA HUANG WANTING HUANG JIE LIU LING DING Gastroenterology department Chongqing University Jiangjin HospitalJiangjin Central Hosptial of ChongqingChongqingChina surgical department Chongqing Jiangjin District Hospital of Chinese MedicineChongqingChina Pharmacy department Chongqing University Jiangjin HospitalJiangjin Central Hosptial of ChongqingChongqingChina

Background:Acute pancreatitis(AP),known for its rapid onset and significant incidence and mortality rates,presents a clinical challenge due to the limited availability of effective treatments and preventive *** B(ASB)has emerged as a potential therapeutic agent,demonstrating capabilities in reducing immune inflammation,positioning it as a promising candidate for AP ***:We investigated the effects of ASB on AP in mice,induced by caerulein and lipopolysaccharide(LPS).Peripheral blood samples were collected 24 h post-induction with caerulein to assess of key biomarkers including lipase,amylase,TNF-α,IL-1β,IL-6,SOD,and GSH-Px.A range of techniques such as immunohistochemistry staining,immunofluorescence staining,Western blotting,and quantitative Polymerase Chain Reaction(q-PCR),were employed to measure the expression of critical ***,pancreas samples from the mice were harvested for microbiome and metabolome sequencing,with the data analyzed to understand the impact of ASB on ***:Our study revealed that,compared to the sham group,the AP group exhibited significantly higher serum levels of lipase,amylase,and cytokines,while levels of SOD and GSH Px were notably *** with ASB led to a substantial decrease in the levels of lipase,amylase,and cytokines,and an increase in SOD and GSH-Px levels.q-PCR analysis of pancreatic histiocytes corroborated these serum *** and Eosin(H&E)staining indicated significant alterations in the pathological changes in the pancreas,lungs,and small intestine of the AP model due to *** assays demonstrated that ASB alleviated the apoptosis of pancreatic histiocytes in the AP *** Blot and histological analyses showed that ASB reduced the phosphorylation of TAK,p38,JNK,and ERK proteins,as well as the levels of TRAF6 protein in the AP ***,metabolomic and gut microbiota analysis identified 27 differential metabolites and 34 diffe

关键词： Anemarsaponin B Acute pancreatitis Cytokines MAPK TRAF6 Gut flora

A new approach to pedestal differentiation for soil loss estimation-a case study from a burnt area in north-central Portugal

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 Forestry Research 2024年第3期35卷 45-54页

作者： Frank G.A.Verheijen Martinho A.S.Martins Sergio A.Prats Jan J.Keizer Centre for Environmental and Marine studies(CESAM) Department Environment and PlanningUniversity of Aveiro3810-193 AveiroPortugal Mediterranean Institute for Agriculture Environment and Development(MED-CHANGE)Institute for Advanced Studies and ResearchUniversity of EvoraPolo da MitraAp.947006-554 EvoraPortugal GeoBiociencias Geotecnologias E Geoengenharias(GEOBIOTEC)Department Environment and PlanningUniversity of Aveiro3810-193 AveiroPortugal

Soil pedestals have long been used as qualitative indicators of soil splash *** rangelands,plant-capped pedestals,generally grass tussocks,have also been used to quantitatively estimate soil loss since the first half of the twentieth *** agricultural lands,forests,and bad-lands,stone-capped pedestals have been used as qualitative and semi-quantitative indicators of active,'extreme'*** work has been reported on using capstone pedestal data for quantifying soil *** postulate that three distinct capstone pedestal types may be present in any given location and that a detailed analysis of a pedestal height histogram may be used to recognize their *** analysis can subsequently inform if soil loss can be reliably estimated and if so,which of the existing methods using pedestal height data will provide more accurate *** three proposed capstone pedestal types are:(1)neo-pedestals formed underneath surface stones exposed by(partial)removal of the soil surface cover;(2)endo-pedestals formed underneath stones that were buried in the soil but have been exposed by erosion;and(3)phoenix-pedestals formed underneath stones from collapsed *** the pedestal height histogram of any given location,a skew to smaller heights may indicate the existence of endo-and/or phoenix-pedestals,which may be revealed as a bi-(or tri)modal distribution when using a smaller bin *** concept was applied to a case study where soil loss had been monitored for control plots and mulched plots during a 5-year period following wildfire in a eucalypt *** measured pedestal heights and used methods to quantitatively assess soil loss from soil pedestal data in the available *** pedestal data at the end of the 5-year period under or overestimated soil loss in the control treatment,with results ranging from 60 to 115%of measured soil loss,depending on the *** is postulated that phoenix-and endo-pedestals may be a driving fact

关键词： Soil pedestals Mulch Wildfire Soil erosion Char

Multiscale spatiotemporal meteorological drought prediction:A deep learning approach

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

Advances in Climate Change Research 2024年第2期15卷 211-221页

作者： Jia-Li ZHANG Xiao-Meng HUANG Yu-Ze SUN department of Earth System Science Ministry of Education Key Laboratory for Earth System ModellingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China

Reliable monitoring and thorough spatiotemporal prediction of meteorological drought are crucial for early warning and decision-making regarding drought-related *** utilisation of multiscale methods is effective for a comprehensive evaluation of drought occurrence and progression,given the complex nature of meteorological ***,the nonlinear spatiotemporal features of meteorological droughts,influenced by various climatological,physical and environmental factors,pose significant challenges to integrated prediction that considers multiple indicators and time *** address these constraints,we introduce an innovative deep learning framework based on the shifted window transformer,designed for executing spatiotemporal prediction of meteorological drought across multiple *** formulate four prediction indicators using the standardized precipitation index and the standard precipitation evaporation index as core methods for drought definition using the ERA5 reanalysis *** indicators span time scales of approximately 30 d and one ***-term indicators capture more anomalous variations,whereas long-term indicators attain comparatively higher accuracy in predicting future *** focus on the East Asian region,notable for its diverse climate conditions and intricate terrains,to validate the model's efficacy in addressing the complexities of nonlinear spatiotemporal *** model's performance is evaluated from diverse spatiotemporal viewpoints,and practical application values are analysed by representative drought *** results substantiate the effectiveness of our proposed model in providing accurate multiscale predictions and capturing the spatiotemporal evolution characteristics of *** of the four drought indicators accurately delineates specific facets of the meteorological drought ***,three representative drought events,namely flash drought,sustained drought and severe drought,

关键词： Meteorological drought Spatiotemporal prediction Multiscale Swim transformer Deep learning

MXenes: Versatile 2D materials with tailored surface chemistry and diverse applications

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3期90卷 253-293,I0008页

作者： Sunil Kumar Nitu Kumari Yongho Seo department of Nanotechnology and Advanced Materials Engineering and HMC Sejong UniversitySeoul 05006South Korea School of studies in Chemistry Jiwaji UniversityGwalior 474011India

MXenes,the most recent addition to the 2D material family,have attracted significant attention owing to their distinctive characteristics,including high surface area,conductivity,surface characteristics,mechanical strength,*** review begins by presenting MXenes,providing insights into their structural characteristics,synthesis methods,and surface functional *** review covers a thorough analysis of MXene surface properties,including surface chemistry and termination group *** properties of MXenes are influenced by their synthesis,which can be fluorine-based or ***-based synthesis techniques involve etching with fluorine-based reagents,mainly including HF or LiF/HCl,while fluorine-free methods include electrochemical etching,chemical vapor deposition(CVD),alkaline etching,Lewis acid-based etching,*** techniques result in the emergence of functional groups such as-F,-O,-OH,-Cl,*** the MXenes surface,depending on the synthesis method *** of MXenes,such as electrical conductivity,electronic properties,catalytic activity,magnetic properties,mechanical strength,and chemical and thermal stability,are examined,and the role of functional groups in determining these properties is *** review delves into the diverse applications of MXenes,encompassing supercapacitors,battery materials,hydrogen storage,fuel cells,electromagnetic interference(EMI) shielding,pollutant removal,water purification,flexible electronics,sensors,additive manufacturing,catalysis,biomedical and healthcare fields,***,this article outlines the challenges and opportunities in the current and future development of MXenes research,addressing various aspects such as synthesis scalability,etching challenges,and multifunctionality,and exploring novel *** review concludes with future prospects and conclusions envisioning the impact of MXenes on future technologies and innovation.

关键词： MXenes 2D materials Surface chemistry MXenes structure Synthesis Applications

Lymphatic vessel:origin,heterogeneity,biological functions,and therapeutic targets

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

Signal Transduction and Targeted Therapy 2024年第2期9卷 442-478页

作者： Zhaoliang Hu Xushi Zhao Zhonghua Wu Bicheng Qu Minxian Yuan Yanan Xing Yongxi Song Zhenning Wang department of surgical Oncology and General Surgery The First Hospital of China Medical UniversityKey Laboratory of Precision Diagnosis and Treatment of Gastrointestinal Tumors(China Medical University)Ministry of Education155 North Nanjing StreetHeping DistrictShenyang 110001China

Lymphatic vessels,comprising the secondary circulatory system in human body,play a multifaceted role in maintaining homeostasis among various tissues and *** are tasked with a serious of responsibilities,including the regulation of lymph absorption and transport,the orchestration of immune surveillance and *** vessel development undergoes a series of sophisticated regulatory signaling pathways governing heterogeneous-origin cell populations stepwise to assemble into the highly specialized lymphatic vessel ***,as defined by new lymphatic vessels sprouting from preexisting lymphatic vessels/embryonic veins,is the main developmental mechanism underlying the formation and expansion of lymphatic vessel networks in an ***,abnormal lymphangiogenesis could be observed in many pathological conditions and has a close relationship with the development and progression of various *** studies have revealed a set of lymphangiogenic factors and cascades that may serve as the potential targets for regulating abnormal lymphangiogenesis,to further modulate the progression of ***,an increasing number of clinical trials have demonstrated the promising interventions and showed the feasibility of currently available treatments for future clinical *** lymphangiogenic promoters or inhibitors not only directly regulates abnormal lymphangiogenesis,but improves the efficacy of diverse *** conclusion,we present a comprehensive overview of lymphatic vessel development and physiological functions,and describe the critical involvement of abnormal lymphangiogenesis in multiple ***,we summarize the targeting therapeutic values of abnormal lymphangiogenesis,providing novel perspectives for treatment strategy of multiple human diseases.

关键词： therapeutic origin specialized