Accurate estimation of the remaining useful life(RUL)of lithium-ion batteries is critical for their large-scale deployment as energy storage devices in electric vehicles and stationary storage.A fundamental understand...Accurate estimation of the remaining useful life(RUL)of lithium-ion batteries is critical for their large-scale deployment as energy storage devices in electric vehicles and stationary storage.A fundamental understanding of the factors affecting RUL is crucial for accelerating battery technology development.However,it is very challenging to predict RUL accurately because of complex degradation mechanisms occurring within the batteries,as well as dynamic operating conditions in practical applications.Moreover,due to insignificant capacity degradation in early stages,early prediction of battery life with early cycle data can be more difficult.In this paper,we propose a hybrid deep learning model for early prediction of battery RUL.The proposed method can effectively combine handcrafted features with domain knowledge and latent features learned by deep networks to boost the performance of RUL early prediction.We also design a non-linear correlation-based method to select effective domain knowledge-based features.Moreover,a novel snapshot ensemble learning strategy is proposed to further enhance model generalization ability without increasing any additional training cost.Our experimental results show that the proposed method not only outperforms other approaches in the primary test set having a similar distribution as the training set,but also generalizes well to the secondary test set having a clearly different distribution with the training set.The PyTorch implementation of our proposed approach is available at https://github.com/batteryrul/battery_rul_early_prediction.展开更多
Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-mak...Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-makings such as the allocation of resource in module verification and validation. Nevertheless, due to the complicated situations of software development process in the early stage, the applicability and accuracy of these models are still under research. In this paper, a software quality prediction model based on a fuzzy neural network is presented, which takes into account both the internal factors and external factors of software. With hybrid-learning algorithm, the proposed model can deal with multiple forms of data as well as incomplete information, which helps identify design errors early and avoid expensive rework.展开更多
BACKGROUND Acute pancreatitis in pregnancy(APIP)is a rare and serious condition,and severe APIP(SAPIP)can lead to pancreatic necrosis,abscess,multiple organ dysfunction,and other adverse maternal and infant outcomes.T...BACKGROUND Acute pancreatitis in pregnancy(APIP)is a rare and serious condition,and severe APIP(SAPIP)can lead to pancreatic necrosis,abscess,multiple organ dysfunction,and other adverse maternal and infant outcomes.Therefore,early identification or prediction of SAPIP is important.AIM To assess factors for early identification or prediction of SAPIP.METHODS The clinical data of patients with APIP were retrospectively analyzed.Patients were classified with mild acute pancreatitis or severe acute pancreatitis,and the clinical characteristics and laboratory biochemical indexes were compared between the two groups.Logical regression and receiver operating characteristic curve analyses were performed to assess the efficacy of the factors for identification or prediction of SAPIP.RESULTS A total of 45 APIP patients were enrolled.Compared with the mild acute pancreatitis group,the severe acute pancreatitis group had significantly increased(P<0.01)heart rate(HR),hemoglobin,neutrophil ratio(NEUT%),and neutrophil–lymphocyte ratio(NLR),while lymphocytes were significantly decreased(P<0.01).Logical regression analysis showed that HR,NEUT%,NLR,and lymphocyte count differed significantly(P<0.01)between the groups.These may be factors for early identification or prediction of SAPIP.The area under the curve of HR,NEUT%,NLR,and lymphocyte count in the receiver operating characteristic curve analysis was 0.748,0.732,0.821,and 0.774,respectively.The combined analysis showed that the area under the curve,sensitivity,and specificity were 0.869,90.5%,and 70.8%,respectively.CONCLUSION HR,NEUT%,NLR,and lymphocyte count can be used for early identification or prediction of SAPIP,and the combination of the four factors is expected to improve identification or prediction of SAPIP.展开更多
AIM:To determine if serum inter-cellular adhesion molecule 1(ICAM-1)is an early marker of the diagnosis and prediction of severe acute pancreatitis(SAP) within 24 h of onset of pain,and to compare the sensitivity,spec...AIM:To determine if serum inter-cellular adhesion molecule 1(ICAM-1)is an early marker of the diagnosis and prediction of severe acute pancreatitis(SAP) within 24 h of onset of pain,and to compare the sensitivity,specificity and prognostic value of this test with those of acute physiology and chronic health evaluation(APACHE)Ⅱscore and interleukin-6(IL-6). METHODS:Patients with acute pancreatitis(AP)were divided into two groups according to the Ranson's criteria:mild acute pancreatitis(MAP)group and SAP group.Serum ICAM-1,APACHEⅡand IL-6 levels were detected in all the patients.The sensitivity,specificity and prognostic value of the ICAM-1,APACHEⅡscore and IL-6 were evaluated. RESULTS:The ICAM-1 level in 36 patients with SAP within 24 h of onset of pain was increased and was significantly higher than that in the 50 patients with MAP and the 15 healthy volunteers(P<0.01).The ICAM-1 level(25 ng/mL)was chosen as the optimum cutoff to distinguish SAP from MAP,and the sensitivity,specificity,positive predictive value,negative predictive value(NPV),positive likelihood ratio and negative likelihood ratio were 61.11%,71.42%,0.6111,0.7142, 2.1382 and 0.5445,respectively.The area under the curve demonstrated that the prognostic accuracy of ICAM-1(0.712)was similar to the APACHE-Ⅱscoring system(0.770)and superior to IL-6(0.508)in distinguishing SAP from MAP. CONCLUSION:ICAM-1 test is a simple,rapid and reliable method in clinical practice.It is an early marker of diagnosis and prediction of SAP within the first 24 h after onset of pain or on admission.As it has a relatively low NPV and does not allow it to be a stand-alone test for the diagnosis of AP,other conventional diagnostic tests are required.展开更多
Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coro...Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coronary artery bypass (OPCAB) surgery in China. Methods Data of patients who underwent OPCAB between 2004 and 2005 in展开更多
The study by Cao et al aimed to identify early second-trimester biomarkers that could predict gestational diabetes mellitus(GDM)development using advanced proteomic techniques,such as Isobaric tags for relative and ab...The study by Cao et al aimed to identify early second-trimester biomarkers that could predict gestational diabetes mellitus(GDM)development using advanced proteomic techniques,such as Isobaric tags for relative and absolute quantitation isobaric tags for relative and absolute quantitation and liquid chromatography-mass spectrometry liquid chromatography-mass spectrometry.Their analysis revealed 47 differentially expressed proteins in the GDM group,with retinol-binding protein 4 and angiopoietin-like 8 showing significantly elevated serum levels compared to controls.Although these findings are promising,the study is limited by its small sample size(n=4 per group)and lacks essential details on the reproducibility and reliability of the protein quantification methods used.Furthermore,the absence of experimental validation weakens the interpretation of the protein-protein interaction network identified through bioinformatics analysis.The study's focus on second-trimester biomarkers raises concerns about whether this is a sufficiently early period to implement preventive interventions for GDM.Predicting GDM risk during the first trimester or pre-conceptional period may offer more clinical relevance.Despite its limitations,the study presents valuable insights into potential GDM biomarkers,but larger,well-validated studies are needed to establish their predictive utility and generalizability.展开更多
Forecasting crop yields based on remote sensing data is one of the most important tasks in agriculture.Soybean is the main crop in the Russian Far East.It is desirable to forecast soybean yield as early as possible wh...Forecasting crop yields based on remote sensing data is one of the most important tasks in agriculture.Soybean is the main crop in the Russian Far East.It is desirable to forecast soybean yield as early as possible while maintaining high accuracy.This study aimed to investigate seasonal time series of the normalized difference vegetation index(NDVI) to achieve early forecasting of soybean yield.This research used data from the Moderate Resolution Image Spectroradiometer(MODIS),an arable-land mask obtained from the VEGA-Science web service,and soybean yield data for 2008-2017 for the Jewish Autonomous Region(JAR) districts.Four approximating functions were fitted to model the NDVI time series:Gaussian,double logistic(DL),and quadratic and cubic polynomials.In the period from calendar weeks 22-42(end of May to mid-October),averaged over two districts,the model using the DL function showed the highest accuracy(mean absolute percentage error-4.0%,root mean square error(RMSE)-0.029,P <0.01).The yield forecast accuracy of prediction in the period of weeks 25-30 in JAR municipalities using the parameters of the Gaussian function was higher(P <0.05) than that using the other functions.The mean forecast error for the Gaussian function was 14.9% in week 25(RMSE was0.21 t ha) and 5.1%-12.9% in weeks 26-30(RMSE varied from 0.06 to 0.15 t ha) according to the2013-2017 data.In weeks 31-32,the error was 5.0%-5.4%(RMSE was 0.07 t ha) using the Gaussian parameters and 7.4%-7.7%(RMSE was 0.09-0.11 t ha) for the DL function.When the method was applied to municipal districts of other soy-producing regions of the Russian Far East.RMSE was0.14-0.32 t hain weeks 25-26 and did not exceed 0.20 t hain subsequent weeks.展开更多
Objective:To study the application of a machine learning algorithm for predicting gestational diabetes mellitus(GDM)in early pregnancy.Methods:This study identified indicators related to GDM through a literature revie...Objective:To study the application of a machine learning algorithm for predicting gestational diabetes mellitus(GDM)in early pregnancy.Methods:This study identified indicators related to GDM through a literature review and expert discussion.Pregnant women who had attended medical institutions for an antenatal examination from November 2017 to August 2018 were selected for analysis,and the collected indicators were retrospectively analyzed.Based on Python,the indicators were classified and modeled using a random forest regression algorithm,and the performance of the prediction model was analyzed.Results:We obtained 4806 analyzable data from 1625 pregnant women.Among these,3265 samples with all 67 indicators were used to establish data set F1;4806 samples with 38 identical indicators were used to establish data set F2.Each of F1 and F2 was used for training the random forest algorithm.The overall predictive accuracy of the F1 model was 93.10%,area under the receiver operating characteristic curve(AUC)was 0.66,and the predictive accuracy of GDM-positive cases was 37.10%.The corresponding values for the F2 model were 88.70%,0.87,and 79.44%.The results thus showed that the F2 prediction model performed better than the F1 model.To explore the impact of sacrificial indicators on GDM prediction,the F3 data set was established using 3265 samples(F1)with 38 indicators(F2).After training,the overall predictive accuracy of the F3 model was 91.60%,AUC was 0.58,and the predictive accuracy of positive cases was 15.85%.Conclusions:In this study,a model for predicting GDM with several input variables(e.g.,physical examination,past history,personal history,family history,and laboratory indicators)was established using a random forest regression algorithm.The trained prediction model exhibited a good performance and is valuable as a reference for predicting GDM in women at an early stage of pregnancy.In addition,there are cer tain requirements for the propor tions of negative and positive cases in sample data sets when the random forest algorithm is applied to the early prediction of GDM.展开更多
Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,an...Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,and economic consequences.展开更多
BACKGROUND Since an initial diagnosis of Alzheimer disease(AD)in 1907,early detection,was unavailable through 116 years.Up-regulation of V-Ets erythroblastosis virus E26 oncogene homolog 2(Ets2)is capable to enhance n...BACKGROUND Since an initial diagnosis of Alzheimer disease(AD)in 1907,early detection,was unavailable through 116 years.Up-regulation of V-Ets erythroblastosis virus E26 oncogene homolog 2(Ets2)is capable to enhance neuronal susceptibility and degeneration.Protein expression(PE)of Ets2 has functional impact on AD and Down’s syndrome,with diverse intensity.PE of Ets2 has an influential pathogenic impact on AD.Clinical aspects of neurological disorders directly interact with psychological maladies.However,deterioration requires an early management including programmed based protection.AIM To include cell biology in neuro-genetics;personalized,prognostics,predictive,preventive,predisposing(5xP)platform,accompanied by stratifying brain channels behavior pre-and post-intervention by light music in the AD-patients.METHODS Include exploration of PE assay and electroencephalography of brain channels.The processes are applied according to:(1)Triangle style,by application of cellular network;and(2)PE assay of Ets2 in the peripheral blood of the patients with AD,by Manual single cell based analysis,and Flow-cytometry.(1)Applying the Genetic counselling and pedigree analysis;(2)considering the psychological status of the referral cases;(3)considering the macro-and/or micro-environmental factors;(4)performing the required Genetics’analysis;and(5)applying the required complementary test(s).RESULTS PE of Ets2 has pathogenic role in AD.PE unmasked the nature of heterogeneity/diversity/course of evolution by exploring Ets2,D1853N polymorphism in Ataxia Telangiectasia mutated gene(ATM),vascular endothelial growth factor(VEGF),epidermal growth factor(EGF)and course of evolution at the single cell level of the brain.Ets2 revealed different cellular behavior in the blood and suggested the strategy as‘Gene Product-Based Therapy’and the personalized managements for the patients.PE reflected weak expression of ATM,mosaic pattern of Ets2;remarkable expression of VEGF and EGF by highlighting an early detective platform,considering circulating neural cells(CNCs)and the required molecular investigation,for the target individual(s)predisposed to AD or other neural disease including brain neoplasia.Brain channels-cooperation with diverse/interactive-ratios lead to strategic balancing for improving the life-quality in AD.CONCLUSION We highlighted application of the single CNCs and correlated Ratio based between Brain channels by providing the 5xP personalized clinical management model for an early detection and therapy of the patients with AD and their targeted/predisposed relatives.Novel-evolutionary/hypothetic/heterogenic-results in brain-channels offer personalizd/constructive markers with unlimited cooperation in health and disease.展开更多
Objective To probe into the prelude marker of central nervous system injury in response to methyl mercury chloride （MMC） stimulation and the signal transduction molecular mechanism of injury in rat brain induced by ...Objective To probe into the prelude marker of central nervous system injury in response to methyl mercury chloride （MMC） stimulation and the signal transduction molecular mechanism of injury in rat brain induced by MMC. Methods The expression of c-fos mRNA in brain and the expression of c-FOS protein in cortex, hippocampus and ependyma were observed using reverse transcription polymerase chain reaction （RT-PCR） and immunocytochemical methods. The control group was injected with physiological saline of 0.9%, while the concentrations for the exposure groups were 0.05 and 0.5, 5 mg/kg MMC respectively, and the sampling times points were 20, 60, 240, 1440 min. Results The expression of c-FOS protein in cortex and hippocampus increased significantly, the accumulation of mercury in the brain induced by 0.05 mg/Kg MMC for 20 min had no significant difference compared with the control group. The mean value was 0.0044 mg/Kg, while the protein c-FOS expression had significant difference compared with the control group （P〈0.01）. More sensitive expression occurred in hippocampus and cortex, but not in ependyma. Conclusion The expression of c-FOS protein in cortex and hippocampus can predict the neurotoxicity of MMC in the early time, and immediately early gene （lEG） c-fos participates in the process of brain injury induced by MMC.展开更多
Background:Hepatic Golgi protein-73(GP73)expression is related to hepatocellular carcinoma(HCC)progression.The aim of this study was to investigate the dynamic expression of GP73 mRNA and protein during hepatocytes ma...Background:Hepatic Golgi protein-73(GP73)expression is related to hepatocellular carcinoma(HCC)progression.The aim of this study was to investigate the dynamic expression of GP73 mRNA and protein during hepatocytes malignant transformation.Methods:Human GP73 expressions in 88 HCC tissues and their self-control surrounding tissues were examined by immunohistochemistry,and survival time of HCC patients was evaluated by the Kaplan-Meier method.HCC model of Sprague-Dawley rats was made by diet containing 2-fluorenylacetamide.The rats were divided into the control,hepatocyte degeneration,precanceration,and HCC groups to observe GP73 protein and mRNA alterations during hepatocytes malignant transformation.Results:The GP73 expression was significantly higher in the cancerous tissues than that in the surrounding tissues,with shorter survival time,and the positive rates of GP73 protein in human HCC tissues were 53.3%at stage I,84.0%at stage II,84.6%at stage III,and 60.0%at stage IV,respectively.The positive rates of hepatic GP73 protein and mRNA in the rat models were none in the control group,66.7%and 44.4%in the hepatocytes degeneration group,88.9%and 77.8%in the hepatocytes precanceration group,and 100%in the HCC group,respectively.There was a positive correlation(r=0.91,P<0.01)between hepatic GP73 and serum GP73 during rat hepatocytes malignant transformation.Conclusions:Abnormal GP73 expression may be a sensitive and valuable biomarker in hepatocarcinogensis.展开更多
Objective Mercury (Hg), as one of the priority pollutants and also a hot topic of frontier environmental research in many countries, has been paid higher attention in the world since the middle of the last century. Gu...Objective Mercury (Hg), as one of the priority pollutants and also a hot topic of frontier environmental research in many countries, has been paid higher attention in the world since the middle of the last century. Guizhou Province (at N24°30′-29°13′, E103°1′-109°30′, 1 100 m above the sea level, with subtropical humid climate) in southwest China is an important mercury production center. It has been found that the mercury content in most media of aquatics, soil, atmosphere and in biomass of corns, plants and animals, is higher than the national standard.The present study aims to explore the influence of mercury pollution on the health of local citizens. Methods The effect of rice from two mercury polluted experimental plots of Guizhou Province on the expression of c-jun mRNA in rat brain and c-jun protein in cortex, hippocampus and ependyma was observed using reverse transcription polymerase chain reaction (RT-PCR) and immunocytochemical methods. Results The results showed that the mercury polluted rice induced expression of c-jun mRNA and its protein significantly. Selenium can reduce Hg uptake, an antagonism between selenium and mercury on the expression of c-jun mRNA and c-jun protein. Conclusion c-jun participates in the toxicity process of brain injury by mercury polluted rice, the expression of c- jun mRNA in brain, and c-jun protein in rat cortex and hippocampus can predict neurotoxicity of mercury polluted rice. People should be advised to be cautious in eating any kind of Hg-polluted foods. To reveal the relationship between c-jun induction and apoptosis, further examinations are required.展开更多
Human induced pluripotent stem cells(hiPSCs)are invaluable resources for producing high-quality differentiated cells in unlimited quantities for both basic research and clinical use.They are particularly useful for st...Human induced pluripotent stem cells(hiPSCs)are invaluable resources for producing high-quality differentiated cells in unlimited quantities for both basic research and clinical use.They are particularly useful for studying human disease mechanisms in vitro by making it possible to circumvent the ethical issues of human embryonic stem cell research.However,significant limitations exist when using conventional flat culturing methods especially concerning cell expansion,differentiation efficiency,stability maintenance and multicellular 3D structure establishment,differentiation prediction.Embryoid bodies(EBs),the multicellular aggregates spontaneously generated from iPSCs in the suspension system,might help to address these issues.Due to the unique microenvironment and cell communication in EB structure that a 2D culture system cannot achieve,EBs have been widely applied in hiPSC-derived differentiation and show significant advantages especially in scaling up culturing,differentiation efficiency enhancement,ex vivo simulation,and organoid establishment.EBs can potentially also be used in early prediction of iPSC differentiation capability.To improve the stability and feasibility of EB-mediated differentiation and generate high quality EBs,critical factors including iPSC pluripotency maintenance,generation of uniform morphology using micro-pattern 3D culture systems,proper cellular density inoculation,and EB size control are discussed on the basis of both published data and our own laboratory experiences.Collectively,the production of a large quantity of homogeneous EBs with high quality is important for the stability and feasibility of many PSCs related studies.展开更多
By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the earl...By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.展开更多
This study investigates the use of computational frameworks for sepsis.We consider two dimensions for investi-gation-early diagnosis of sepsis(EDS)and mortality prediction rate for sepsis patients(MPS).We concentrate ...This study investigates the use of computational frameworks for sepsis.We consider two dimensions for investi-gation-early diagnosis of sepsis(EDS)and mortality prediction rate for sepsis patients(MPS).We concentrate on the clinical parameters on which sepsis diagnosis and prognosis are currently done,including customized treatment plans based on historical data of the patient.We identify the most notable literature that uses com-putational models to address EDS and MPS based on those clinical parameters.In addition to the review of the computational models built upon the clinical parameters,we also provide details regarding the popular publicly available data sources.We provide brief reviews for each model in terms of prior art and present an analysis of their results,as claimed by the respective authors.With respect to the use of machine learning models,we have provided avenues for model analysis in terms of model selection,model validation,model interpretation,and model comparison.We further present the challenges and limitations of the use of computational models,providing future research directions.This study intends to serve as a benchmark for first-hand impressions on the use of computational models for EDS and MPS of sepsis,along with the details regarding which model has been the most promising to date.We have provided details regarding all the ML models that have been used to date for EDS and MPS of sepsis.展开更多
Preeclampsia is a progressive,multi-system disorder of pregnancy associated with morbidity and mortality on both the mother and the fetus.Currently,research is directed at identifying early biomarkers of preeclampsia ...Preeclampsia is a progressive,multi-system disorder of pregnancy associated with morbidity and mortality on both the mother and the fetus.Currently,research is directed at identifying early biomarkers of preeclampsia in order to predict its occurrence.This is important because it helps understand the pathophysiology of the disease,and thus,promises new treatment modalities.Although a clear understanding of the pathogenesis of PE remains elusive,the currently most accepted theory suggests a two-stage process.The first stage results in inadequate remodeling of the spiral arteries and leads to the second stage,whereby the clinical features of the syndrome are featured.In this review,we summarize the modalities that have been studies so far to predict preeclampsia.The use of uterine artery Doppler and several other biomarkers such as vitamin D,soluble fms-like tyrosine kinase 1/placental growth factor(sFLT1/PIGF)ratio,soluble endoglin,and a subset of T-lymphocytes has shown promising results.We are still at early stages in this advance,and no clear recommendations have been made about their clinical use to date.Further studies are still needed to improve screening strategies and evaluate the cost-effectiveness of any intervention.展开更多
The Qinghai-Tibet Plateau is a climate-sensitive region.The characteristics of drought and flood events in this region are significantly different as compared to other areas in the country,which could potentially indu...The Qinghai-Tibet Plateau is a climate-sensitive region.The characteristics of drought and flood events in this region are significantly different as compared to other areas in the country,which could potentially induce a series of water security,ecological and environmental problems.It is urgent that innovative theories and methods for estimation of drought and flood disasters as well as their adaptive regulations are required.Based on extensive literature review,this paper identifies new situations of the evolution of drought and flood events on the Qinghai-Tibet Plateau,and analyzes the research progress in terms of monitoring and simulation,forecasting and early warning,risk prevention and emergency response.The study found that there were problems such as insufficient integration of multi-source data,low accuracy of forecasting and early warning,unclear driving mechanisms of drought and flood disaster chains,and lack of targeted risk prevention and regulation measures.On this basis,future research priorities are proposed,and the possible research and development paths are elaborated,including the evolution law of drought and flood on the Qinghai-Tibet Plateau,the coincidence characteristics of drought and flood from the perspective of a water resources system,prediction and early warning of drought and flood coupled with numerical simulation and knowledge mining,identification of risk blocking points of drought and flood disaster chain and the adaptive regulations.Hopefully,the paper will provide technical support for preventing flood and drought disasters,water resources protection,ecological restoration and climate change adaptation on the Qinghai-Tibet Plateau.展开更多
基金supported by Agency for Science,Technology and Research(A*STAR)under the Career Development Fund(C210112037)。
文摘Accurate estimation of the remaining useful life(RUL)of lithium-ion batteries is critical for their large-scale deployment as energy storage devices in electric vehicles and stationary storage.A fundamental understanding of the factors affecting RUL is crucial for accelerating battery technology development.However,it is very challenging to predict RUL accurately because of complex degradation mechanisms occurring within the batteries,as well as dynamic operating conditions in practical applications.Moreover,due to insignificant capacity degradation in early stages,early prediction of battery life with early cycle data can be more difficult.In this paper,we propose a hybrid deep learning model for early prediction of battery RUL.The proposed method can effectively combine handcrafted features with domain knowledge and latent features learned by deep networks to boost the performance of RUL early prediction.We also design a non-linear correlation-based method to select effective domain knowledge-based features.Moreover,a novel snapshot ensemble learning strategy is proposed to further enhance model generalization ability without increasing any additional training cost.Our experimental results show that the proposed method not only outperforms other approaches in the primary test set having a similar distribution as the training set,but also generalizes well to the secondary test set having a clearly different distribution with the training set.The PyTorch implementation of our proposed approach is available at https://github.com/batteryrul/battery_rul_early_prediction.
基金Supported by the National Defense Pre-research Project
文摘Due to the rapid development of computers and their applications, early software quality prediction in software industry becomes more and more cruciaL Software quality prediction model is very helpful for decision-makings such as the allocation of resource in module verification and validation. Nevertheless, due to the complicated situations of software development process in the early stage, the applicability and accuracy of these models are still under research. In this paper, a software quality prediction model based on a fuzzy neural network is presented, which takes into account both the internal factors and external factors of software. With hybrid-learning algorithm, the proposed model can deal with multiple forms of data as well as incomplete information, which helps identify design errors early and avoid expensive rework.
文摘BACKGROUND Acute pancreatitis in pregnancy(APIP)is a rare and serious condition,and severe APIP(SAPIP)can lead to pancreatic necrosis,abscess,multiple organ dysfunction,and other adverse maternal and infant outcomes.Therefore,early identification or prediction of SAPIP is important.AIM To assess factors for early identification or prediction of SAPIP.METHODS The clinical data of patients with APIP were retrospectively analyzed.Patients were classified with mild acute pancreatitis or severe acute pancreatitis,and the clinical characteristics and laboratory biochemical indexes were compared between the two groups.Logical regression and receiver operating characteristic curve analyses were performed to assess the efficacy of the factors for identification or prediction of SAPIP.RESULTS A total of 45 APIP patients were enrolled.Compared with the mild acute pancreatitis group,the severe acute pancreatitis group had significantly increased(P<0.01)heart rate(HR),hemoglobin,neutrophil ratio(NEUT%),and neutrophil–lymphocyte ratio(NLR),while lymphocytes were significantly decreased(P<0.01).Logical regression analysis showed that HR,NEUT%,NLR,and lymphocyte count differed significantly(P<0.01)between the groups.These may be factors for early identification or prediction of SAPIP.The area under the curve of HR,NEUT%,NLR,and lymphocyte count in the receiver operating characteristic curve analysis was 0.748,0.732,0.821,and 0.774,respectively.The combined analysis showed that the area under the curve,sensitivity,and specificity were 0.869,90.5%,and 70.8%,respectively.CONCLUSION HR,NEUT%,NLR,and lymphocyte count can be used for early identification or prediction of SAPIP,and the combination of the four factors is expected to improve identification or prediction of SAPIP.
文摘AIM:To determine if serum inter-cellular adhesion molecule 1(ICAM-1)is an early marker of the diagnosis and prediction of severe acute pancreatitis(SAP) within 24 h of onset of pain,and to compare the sensitivity,specificity and prognostic value of this test with those of acute physiology and chronic health evaluation(APACHE)Ⅱscore and interleukin-6(IL-6). METHODS:Patients with acute pancreatitis(AP)were divided into two groups according to the Ranson's criteria:mild acute pancreatitis(MAP)group and SAP group.Serum ICAM-1,APACHEⅡand IL-6 levels were detected in all the patients.The sensitivity,specificity and prognostic value of the ICAM-1,APACHEⅡscore and IL-6 were evaluated. RESULTS:The ICAM-1 level in 36 patients with SAP within 24 h of onset of pain was increased and was significantly higher than that in the 50 patients with MAP and the 15 healthy volunteers(P<0.01).The ICAM-1 level(25 ng/mL)was chosen as the optimum cutoff to distinguish SAP from MAP,and the sensitivity,specificity,positive predictive value,negative predictive value(NPV),positive likelihood ratio and negative likelihood ratio were 61.11%,71.42%,0.6111,0.7142, 2.1382 and 0.5445,respectively.The area under the curve demonstrated that the prognostic accuracy of ICAM-1(0.712)was similar to the APACHE-Ⅱscoring system(0.770)and superior to IL-6(0.508)in distinguishing SAP from MAP. CONCLUSION:ICAM-1 test is a simple,rapid and reliable method in clinical practice.It is an early marker of diagnosis and prediction of SAP within the first 24 h after onset of pain or on admission.As it has a relatively low NPV and does not allow it to be a stand-alone test for the diagnosis of AP,other conventional diagnostic tests are required.
文摘Objective To compare the validation of the Sino System for Coronary Operative Risk Evaluation (SinoSCORE) with the European system for cardiac operative risk evaluation (EuroSCORE) in patients undergoing off-pump coronary artery bypass (OPCAB) surgery in China. Methods Data of patients who underwent OPCAB between 2004 and 2005 in
文摘The study by Cao et al aimed to identify early second-trimester biomarkers that could predict gestational diabetes mellitus(GDM)development using advanced proteomic techniques,such as Isobaric tags for relative and absolute quantitation isobaric tags for relative and absolute quantitation and liquid chromatography-mass spectrometry liquid chromatography-mass spectrometry.Their analysis revealed 47 differentially expressed proteins in the GDM group,with retinol-binding protein 4 and angiopoietin-like 8 showing significantly elevated serum levels compared to controls.Although these findings are promising,the study is limited by its small sample size(n=4 per group)and lacks essential details on the reproducibility and reliability of the protein quantification methods used.Furthermore,the absence of experimental validation weakens the interpretation of the protein-protein interaction network identified through bioinformatics analysis.The study's focus on second-trimester biomarkers raises concerns about whether this is a sufficiently early period to implement preventive interventions for GDM.Predicting GDM risk during the first trimester or pre-conceptional period may offer more clinical relevance.Despite its limitations,the study presents valuable insights into potential GDM biomarkers,but larger,well-validated studies are needed to establish their predictive utility and generalizability.
文摘Forecasting crop yields based on remote sensing data is one of the most important tasks in agriculture.Soybean is the main crop in the Russian Far East.It is desirable to forecast soybean yield as early as possible while maintaining high accuracy.This study aimed to investigate seasonal time series of the normalized difference vegetation index(NDVI) to achieve early forecasting of soybean yield.This research used data from the Moderate Resolution Image Spectroradiometer(MODIS),an arable-land mask obtained from the VEGA-Science web service,and soybean yield data for 2008-2017 for the Jewish Autonomous Region(JAR) districts.Four approximating functions were fitted to model the NDVI time series:Gaussian,double logistic(DL),and quadratic and cubic polynomials.In the period from calendar weeks 22-42(end of May to mid-October),averaged over two districts,the model using the DL function showed the highest accuracy(mean absolute percentage error-4.0%,root mean square error(RMSE)-0.029,P <0.01).The yield forecast accuracy of prediction in the period of weeks 25-30 in JAR municipalities using the parameters of the Gaussian function was higher(P <0.05) than that using the other functions.The mean forecast error for the Gaussian function was 14.9% in week 25(RMSE was0.21 t ha) and 5.1%-12.9% in weeks 26-30(RMSE varied from 0.06 to 0.15 t ha) according to the2013-2017 data.In weeks 31-32,the error was 5.0%-5.4%(RMSE was 0.07 t ha) using the Gaussian parameters and 7.4%-7.7%(RMSE was 0.09-0.11 t ha) for the DL function.When the method was applied to municipal districts of other soy-producing regions of the Russian Far East.RMSE was0.14-0.32 t hain weeks 25-26 and did not exceed 0.20 t hain subsequent weeks.
基金supported by the Qingdao Municipal Bureau of Science and Technology(No.19-6-1-55-nsh)。
文摘Objective:To study the application of a machine learning algorithm for predicting gestational diabetes mellitus(GDM)in early pregnancy.Methods:This study identified indicators related to GDM through a literature review and expert discussion.Pregnant women who had attended medical institutions for an antenatal examination from November 2017 to August 2018 were selected for analysis,and the collected indicators were retrospectively analyzed.Based on Python,the indicators were classified and modeled using a random forest regression algorithm,and the performance of the prediction model was analyzed.Results:We obtained 4806 analyzable data from 1625 pregnant women.Among these,3265 samples with all 67 indicators were used to establish data set F1;4806 samples with 38 identical indicators were used to establish data set F2.Each of F1 and F2 was used for training the random forest algorithm.The overall predictive accuracy of the F1 model was 93.10%,area under the receiver operating characteristic curve(AUC)was 0.66,and the predictive accuracy of GDM-positive cases was 37.10%.The corresponding values for the F2 model were 88.70%,0.87,and 79.44%.The results thus showed that the F2 prediction model performed better than the F1 model.To explore the impact of sacrificial indicators on GDM prediction,the F3 data set was established using 3265 samples(F1)with 38 indicators(F2).After training,the overall predictive accuracy of the F3 model was 91.60%,AUC was 0.58,and the predictive accuracy of positive cases was 15.85%.Conclusions:In this study,a model for predicting GDM with several input variables(e.g.,physical examination,past history,personal history,family history,and laboratory indicators)was established using a random forest regression algorithm.The trained prediction model exhibited a good performance and is valuable as a reference for predicting GDM in women at an early stage of pregnancy.In addition,there are cer tain requirements for the propor tions of negative and positive cases in sample data sets when the random forest algorithm is applied to the early prediction of GDM.
文摘Traumatic brain injury（TBI）represents a global pandemic and is currently a leading cause of injury related death worldwide.Unfortunately,those who survive initial injury often suffer devastating functional,social,and economic consequences.
文摘BACKGROUND Since an initial diagnosis of Alzheimer disease(AD)in 1907,early detection,was unavailable through 116 years.Up-regulation of V-Ets erythroblastosis virus E26 oncogene homolog 2(Ets2)is capable to enhance neuronal susceptibility and degeneration.Protein expression(PE)of Ets2 has functional impact on AD and Down’s syndrome,with diverse intensity.PE of Ets2 has an influential pathogenic impact on AD.Clinical aspects of neurological disorders directly interact with psychological maladies.However,deterioration requires an early management including programmed based protection.AIM To include cell biology in neuro-genetics;personalized,prognostics,predictive,preventive,predisposing(5xP)platform,accompanied by stratifying brain channels behavior pre-and post-intervention by light music in the AD-patients.METHODS Include exploration of PE assay and electroencephalography of brain channels.The processes are applied according to:(1)Triangle style,by application of cellular network;and(2)PE assay of Ets2 in the peripheral blood of the patients with AD,by Manual single cell based analysis,and Flow-cytometry.(1)Applying the Genetic counselling and pedigree analysis;(2)considering the psychological status of the referral cases;(3)considering the macro-and/or micro-environmental factors;(4)performing the required Genetics’analysis;and(5)applying the required complementary test(s).RESULTS PE of Ets2 has pathogenic role in AD.PE unmasked the nature of heterogeneity/diversity/course of evolution by exploring Ets2,D1853N polymorphism in Ataxia Telangiectasia mutated gene(ATM),vascular endothelial growth factor(VEGF),epidermal growth factor(EGF)and course of evolution at the single cell level of the brain.Ets2 revealed different cellular behavior in the blood and suggested the strategy as‘Gene Product-Based Therapy’and the personalized managements for the patients.PE reflected weak expression of ATM,mosaic pattern of Ets2;remarkable expression of VEGF and EGF by highlighting an early detective platform,considering circulating neural cells(CNCs)and the required molecular investigation,for the target individual(s)predisposed to AD or other neural disease including brain neoplasia.Brain channels-cooperation with diverse/interactive-ratios lead to strategic balancing for improving the life-quality in AD.CONCLUSION We highlighted application of the single CNCs and correlated Ratio based between Brain channels by providing the 5xP personalized clinical management model for an early detection and therapy of the patients with AD and their targeted/predisposed relatives.Novel-evolutionary/hypothetic/heterogenic-results in brain-channels offer personalizd/constructive markers with unlimited cooperation in health and disease.
基金This work was supported by National Natural Science Foundation of China (20177013 40303013) and the Chinese Academy ofSciences for Key and Innovation Projects (KZCX-SW-437).
文摘Objective To probe into the prelude marker of central nervous system injury in response to methyl mercury chloride （MMC） stimulation and the signal transduction molecular mechanism of injury in rat brain induced by MMC. Methods The expression of c-fos mRNA in brain and the expression of c-FOS protein in cortex, hippocampus and ependyma were observed using reverse transcription polymerase chain reaction （RT-PCR） and immunocytochemical methods. The control group was injected with physiological saline of 0.9%, while the concentrations for the exposure groups were 0.05 and 0.5, 5 mg/kg MMC respectively, and the sampling times points were 20, 60, 240, 1440 min. Results The expression of c-FOS protein in cortex and hippocampus increased significantly, the accumulation of mercury in the brain induced by 0.05 mg/Kg MMC for 20 min had no significant difference compared with the control group. The mean value was 0.0044 mg/Kg, while the protein c-FOS expression had significant difference compared with the control group （P〈0.01）. More sensitive expression occurred in hippocampus and cortex, but not in ependyma. Conclusion The expression of c-FOS protein in cortex and hippocampus can predict the neurotoxicity of MMC in the early time, and immediately early gene （lEG） c-fos participates in the process of brain injury induced by MMC.
基金This study was supported by grants from the Ministry of S&T National Key Research and Development Program of China(2018YFC0116902)the National Natural Science Foundation of China(81673241,81702419,31872738,81873915)and Project of Jiangsu Medical Science(BE2016698).
文摘Background:Hepatic Golgi protein-73(GP73)expression is related to hepatocellular carcinoma(HCC)progression.The aim of this study was to investigate the dynamic expression of GP73 mRNA and protein during hepatocytes malignant transformation.Methods:Human GP73 expressions in 88 HCC tissues and their self-control surrounding tissues were examined by immunohistochemistry,and survival time of HCC patients was evaluated by the Kaplan-Meier method.HCC model of Sprague-Dawley rats was made by diet containing 2-fluorenylacetamide.The rats were divided into the control,hepatocyte degeneration,precanceration,and HCC groups to observe GP73 protein and mRNA alterations during hepatocytes malignant transformation.Results:The GP73 expression was significantly higher in the cancerous tissues than that in the surrounding tissues,with shorter survival time,and the positive rates of GP73 protein in human HCC tissues were 53.3%at stage I,84.0%at stage II,84.6%at stage III,and 60.0%at stage IV,respectively.The positive rates of hepatic GP73 protein and mRNA in the rat models were none in the control group,66.7%and 44.4%in the hepatocytes degeneration group,88.9%and 77.8%in the hepatocytes precanceration group,and 100%in the HCC group,respectively.There was a positive correlation(r=0.91,P<0.01)between hepatic GP73 and serum GP73 during rat hepatocytes malignant transformation.Conclusions:Abnormal GP73 expression may be a sensitive and valuable biomarker in hepatocarcinogensis.
文摘Objective Mercury (Hg), as one of the priority pollutants and also a hot topic of frontier environmental research in many countries, has been paid higher attention in the world since the middle of the last century. Guizhou Province (at N24°30′-29°13′, E103°1′-109°30′, 1 100 m above the sea level, with subtropical humid climate) in southwest China is an important mercury production center. It has been found that the mercury content in most media of aquatics, soil, atmosphere and in biomass of corns, plants and animals, is higher than the national standard.The present study aims to explore the influence of mercury pollution on the health of local citizens. Methods The effect of rice from two mercury polluted experimental plots of Guizhou Province on the expression of c-jun mRNA in rat brain and c-jun protein in cortex, hippocampus and ependyma was observed using reverse transcription polymerase chain reaction (RT-PCR) and immunocytochemical methods. Results The results showed that the mercury polluted rice induced expression of c-jun mRNA and its protein significantly. Selenium can reduce Hg uptake, an antagonism between selenium and mercury on the expression of c-jun mRNA and c-jun protein. Conclusion c-jun participates in the toxicity process of brain injury by mercury polluted rice, the expression of c- jun mRNA in brain, and c-jun protein in rat cortex and hippocampus can predict neurotoxicity of mercury polluted rice. People should be advised to be cautious in eating any kind of Hg-polluted foods. To reveal the relationship between c-jun induction and apoptosis, further examinations are required.
基金Supported by National Natural Science Foundation of China,No.81770621,No.81573053Ministry of Education,Culture,Sports,Science,and Technology of Japan,KAKENHI,No.16K15604,No.18H02866Natural Science Foundation of Jiangsu Province,No.BK20180281
文摘Human induced pluripotent stem cells(hiPSCs)are invaluable resources for producing high-quality differentiated cells in unlimited quantities for both basic research and clinical use.They are particularly useful for studying human disease mechanisms in vitro by making it possible to circumvent the ethical issues of human embryonic stem cell research.However,significant limitations exist when using conventional flat culturing methods especially concerning cell expansion,differentiation efficiency,stability maintenance and multicellular 3D structure establishment,differentiation prediction.Embryoid bodies(EBs),the multicellular aggregates spontaneously generated from iPSCs in the suspension system,might help to address these issues.Due to the unique microenvironment and cell communication in EB structure that a 2D culture system cannot achieve,EBs have been widely applied in hiPSC-derived differentiation and show significant advantages especially in scaling up culturing,differentiation efficiency enhancement,ex vivo simulation,and organoid establishment.EBs can potentially also be used in early prediction of iPSC differentiation capability.To improve the stability and feasibility of EB-mediated differentiation and generate high quality EBs,critical factors including iPSC pluripotency maintenance,generation of uniform morphology using micro-pattern 3D culture systems,proper cellular density inoculation,and EB size control are discussed on the basis of both published data and our own laboratory experiences.Collectively,the production of a large quantity of homogeneous EBs with high quality is important for the stability and feasibility of many PSCs related studies.
基金fund of the Hong Kong Polytechnic University(P0038174)。
文摘By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.
文摘This study investigates the use of computational frameworks for sepsis.We consider two dimensions for investi-gation-early diagnosis of sepsis(EDS)and mortality prediction rate for sepsis patients(MPS).We concentrate on the clinical parameters on which sepsis diagnosis and prognosis are currently done,including customized treatment plans based on historical data of the patient.We identify the most notable literature that uses com-putational models to address EDS and MPS based on those clinical parameters.In addition to the review of the computational models built upon the clinical parameters,we also provide details regarding the popular publicly available data sources.We provide brief reviews for each model in terms of prior art and present an analysis of their results,as claimed by the respective authors.With respect to the use of machine learning models,we have provided avenues for model analysis in terms of model selection,model validation,model interpretation,and model comparison.We further present the challenges and limitations of the use of computational models,providing future research directions.This study intends to serve as a benchmark for first-hand impressions on the use of computational models for EDS and MPS of sepsis,along with the details regarding which model has been the most promising to date.We have provided details regarding all the ML models that have been used to date for EDS and MPS of sepsis.
文摘Preeclampsia is a progressive,multi-system disorder of pregnancy associated with morbidity and mortality on both the mother and the fetus.Currently,research is directed at identifying early biomarkers of preeclampsia in order to predict its occurrence.This is important because it helps understand the pathophysiology of the disease,and thus,promises new treatment modalities.Although a clear understanding of the pathogenesis of PE remains elusive,the currently most accepted theory suggests a two-stage process.The first stage results in inadequate remodeling of the spiral arteries and leads to the second stage,whereby the clinical features of the syndrome are featured.In this review,we summarize the modalities that have been studies so far to predict preeclampsia.The use of uterine artery Doppler and several other biomarkers such as vitamin D,soluble fms-like tyrosine kinase 1/placental growth factor(sFLT1/PIGF)ratio,soluble endoglin,and a subset of T-lymphocytes has shown promising results.We are still at early stages in this advance,and no clear recommendations have been made about their clinical use to date.Further studies are still needed to improve screening strategies and evaluate the cost-effectiveness of any intervention.
基金supported by the National Key Research and Development Program of China(Grant No.2022YFC3201705)。
文摘The Qinghai-Tibet Plateau is a climate-sensitive region.The characteristics of drought and flood events in this region are significantly different as compared to other areas in the country,which could potentially induce a series of water security,ecological and environmental problems.It is urgent that innovative theories and methods for estimation of drought and flood disasters as well as their adaptive regulations are required.Based on extensive literature review,this paper identifies new situations of the evolution of drought and flood events on the Qinghai-Tibet Plateau,and analyzes the research progress in terms of monitoring and simulation,forecasting and early warning,risk prevention and emergency response.The study found that there were problems such as insufficient integration of multi-source data,low accuracy of forecasting and early warning,unclear driving mechanisms of drought and flood disaster chains,and lack of targeted risk prevention and regulation measures.On this basis,future research priorities are proposed,and the possible research and development paths are elaborated,including the evolution law of drought and flood on the Qinghai-Tibet Plateau,the coincidence characteristics of drought and flood from the perspective of a water resources system,prediction and early warning of drought and flood coupled with numerical simulation and knowledge mining,identification of risk blocking points of drought and flood disaster chain and the adaptive regulations.Hopefully,the paper will provide technical support for preventing flood and drought disasters,water resources protection,ecological restoration and climate change adaptation on the Qinghai-Tibet Plateau.
