Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient...Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient representation of land-surface processes.In addition to PB models,deep learning(DL)models have been widely used in SM predictions recently.However,few pure DL models have notably high success rates due to lacking physical information.Thus,we developed hybrid models to effectively integrate the outputs of PB models into DL models to improve SM predictions.To this end,we first developed a hybrid model based on the attention mechanism to take advantage of PB models at each forecast time scale(attention model).We further built an ensemble model that combined the advantages of different hybrid schemes(ensemble model).We utilized SM forecasts from the Global Forecast System to enhance the convolutional long short-term memory(ConvLSTM)model for 1–16 days of SM predictions.The performances of the proposed hybrid models were investigated and compared with two existing hybrid models.The results showed that the attention model could leverage benefits of PB models and achieved the best predictability of drought events among the different hybrid models.Moreover,the ensemble model performed best among all hybrid models at all forecast time scales and different soil conditions.It is highlighted that the ensemble model outperformed the pure DL model over 79.5%of in situ stations for 16-day predictions.These findings suggest that our proposed hybrid models can adequately exploit the benefits of PB model outputs to aid DL models in making SM predictions.展开更多
Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being...Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being one of the most crucial due to their rapid cyberattack detection capabilities on networks and hosts.The capabilities of DL in feature learning and analyzing extensive data volumes lead to the recognition of network traffic patterns.This study presents novel lightweight DL models,known as Cybernet models,for the detection and recognition of various cyber Distributed Denial of Service(DDoS)attacks.These models were constructed to have a reasonable number of learnable parameters,i.e.,less than 225,000,hence the name“lightweight.”This not only helps reduce the number of computations required but also results in faster training and inference times.Additionally,these models were designed to extract features in parallel from 1D Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),which makes them unique compared to earlier existing architectures and results in better performance measures.To validate their robustness and effectiveness,they were tested on the CIC-DDoS2019 dataset,which is an imbalanced and large dataset that contains different types of DDoS attacks.Experimental results revealed that bothmodels yielded promising results,with 99.99% for the detectionmodel and 99.76% for the recognition model in terms of accuracy,precision,recall,and F1 score.Furthermore,they outperformed the existing state-of-the-art models proposed for the same task.Thus,the proposed models can be used in cyber security research domains to successfully identify different types of attacks with a high detection and recognition rate.展开更多
With continuous hydrocarbon exploration extending to deeper basins,the deepest industrial oil accumulation was discovered below 8,200 m,revealing a new exploration field.Hence,the extent to which oil exploration can b...With continuous hydrocarbon exploration extending to deeper basins,the deepest industrial oil accumulation was discovered below 8,200 m,revealing a new exploration field.Hence,the extent to which oil exploration can be extended,and the prediction of the depth limit of oil accumulation(DLOA),are issues that have attracted significant attention in petroleum geology.Since it is difficult to characterize the evolution of the physical properties of the marine carbonate reservoir with burial depth,and the deepest drilling still cannot reach the DLOA.Hence,the DLOA cannot be predicted by directly establishing the relationship between the ratio of drilling to the dry layer and the depth.In this study,by establishing the relationships between the porosity and the depth and dry layer ratio of the carbonate reservoir,the relationships between the depth and dry layer ratio were obtained collectively.The depth corresponding to a dry layer ratio of 100%is the DLOA.Based on this,a quantitative prediction model for the DLOA was finally built.The results indicate that the porosity of the carbonate reservoir,Lower Ordovician in Tazhong area of Tarim Basin,tends to decrease with burial depth,and manifests as an overall low porosity reservoir in deep layer.The critical porosity of the DLOA was 1.8%,which is the critical geological condition corresponding to a 100%dry layer ratio encountered in the reservoir.The depth of the DLOA was 9,000 m.This study provides a new method for DLOA prediction that is beneficial for a deeper understanding of oil accumulation,and is of great importance for scientific guidance on deep oil drilling.展开更多
The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based ...The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.展开更多
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera im...The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.展开更多
Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of tra...Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.展开更多
We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract informa...We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.展开更多
Against the backdrop of continuous development in the field of education,universities are encouraged to innovate their talent cultivation systems and objectives.The deep integration of industry and education has emerg...Against the backdrop of continuous development in the field of education,universities are encouraged to innovate their talent cultivation systems and objectives.The deep integration of industry and education has emerged as an effective strategy,aligning with the basic requirements of the new engineering education initiative and exerting a positive impact on socioeconomic development.However,an analysis of the current state of industry-education integration in universities reveals several issues that require optimization,affecting the ultimate effectiveness of integration.To optimize this phenomenon and achieve high-quality development,universities need to further explore the construction of a deep integration model of industry and education,adhering to corresponding principles to form a comprehensive system.On this basis,pathways for deep industry-education integration can be summarized.展开更多
The dilation angle is the most commonly used parameter to study nonlinear post-peak dilatancy(PPD)behavior and simulate surrounding rock deformation;however,simplified or constant dilatancy models are often used in nu...The dilation angle is the most commonly used parameter to study nonlinear post-peak dilatancy(PPD)behavior and simulate surrounding rock deformation;however,simplified or constant dilatancy models are often used in numerical calculations owing to their simple mathematical forms.This study developed a PPD model for rocks(rock masses)based on the Alejanoe-Alonso(A-A)dilatancy model.The developed model comprehensively reflects the influences of confining pressure(σ_(3))and plastic shear strain(γ^(p)),with the advantages of a simple mathematical form,while requiring fewer parameters and demonstrating a clear physical significance.The overall fitting accuracy of the PPD model for 11 different rocks was found to be higher than that of the A-A model,particularly for Witwatersrand quartzite and jointed granite.The applicability and reliability of the PPD model to jointed granites and different scaled Moura coals were also investigated,and the model was found to be more suitable for the soft and large-scale rocks,e.g.deep rock mass.The PPD model was also successfully applied in studying the mechanical response of a circular tunnel excavated in strain-softening rock mass,and the developed semi-analytical solution was compared and verified with existing analytical solutions.The sensitivities of the rock dilatancy to γ^(p) and σ_(3) showed significant spatial variabilities along the radial direction of the surrounding rock,and the dilation angle did not exhibit a monotonical increasing or decreasing law from the elasticeplastic boundary to the tunnel wall,thereby presenting the σ3-or γ^(p)-dominated differential effects of rock dilatancy.Tunnel deformation parabolically or exponentially increased with increasing in situ stress(buried depth).The developed PPD model is promising to conduct refined numerical and analytical analyses for deep tunneling,which produces extensive plastic deformation and exhibits significant nonlinear post-peak behavior.展开更多
Renewable energy has become a solution to the world’s energy concerns in recent years.Photovoltaic(PV)technology is the fastest technique to convert solar radiation into electricity.Solar-powered buses,metros,and car...Renewable energy has become a solution to the world’s energy concerns in recent years.Photovoltaic(PV)technology is the fastest technique to convert solar radiation into electricity.Solar-powered buses,metros,and cars use PV technology.Such technologies are always evolving.Included in the parameters that need to be analysed and examined include PV capabilities,vehicle power requirements,utility patterns,acceleration and deceleration rates,and storage module type and capacity,among others.PVPG is intermit-tent and weather-dependent.Accurate forecasting and modelling of PV sys-tem output power are key to managing storage,delivery,and smart grids.With unparalleled data granularity,a data-driven system could better anticipate solar generation.Deep learning(DL)models have gained popularity due to their capacity to handle complex datasets and increase computing power.This article introduces the Galactic Swarm Optimization with Deep Belief Network(GSODBN-PPGF)model.The GSODBN-PPGF model predicts PV power production.The GSODBN-PPGF model normalises data using data scaling.DBN is used to forecast PV power output.The GSO algorithm boosts the DBN model’s predicted output.GSODBN-PPGF projected 0.002 after 40 h but observed 0.063.The GSODBN-PPGF model validation is compared to existing approaches.Simulations showed that the GSODBN-PPGF model outperformed recent techniques.It shows that the proposed model is better at forecasting than other models and can be used to predict the PV power output for the next day.展开更多
Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit prop...Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byfloods.The massive amount of data generated by social media platforms such as Twitter opens the door toflood analysis.Because of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue strategy.However,due to the shorter duration of Tweets,it is difficult to construct a perfect prediction model for determiningflood.Machine learning(ML)and deep learning(DL)approaches can be used to statistically developflood prediction models.At the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forflood prediction.In this regard,this work provides an optimal deep learning-basedflood forecasting model with big data analytics(ODLFF-BDA)based on Twitter data.The suggested ODLFF-BDA technique intends to anticipate the existence offloods using tweets in a big data setting.The ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable format.In addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from tweets.Furthermore,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theflood.Finally,an Equilibrium Optimizer(EO)is used tofine-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction performance.The memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm techniques.The ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and thefindings showed that it outperformed other recent approaches significantly.展开更多
In the second member of the Upper Triassic Xujiahe Formation(T_(3)x_(2))in the Xinchang area,western Sichuan Basin,only a low percent of reserves has been recovered,and the geological model of gas reservoir sweet spot...In the second member of the Upper Triassic Xujiahe Formation(T_(3)x_(2))in the Xinchang area,western Sichuan Basin,only a low percent of reserves has been recovered,and the geological model of gas reservoir sweet spot remains unclear.Based on a large number of core,field outcrop,test and logging-seismic data,the T_(3)x_(2) gas reservoir in the Xinchang area is examined.The concept of fault-fold-fracture body(FFFB)is proposed,and its types are recognized.The main factors controlling fracture development are identified,and the geological models of FFFB are established.FFFB refers to faults,folds and associated fractures reservoirs.According to the characteristics and genesis,FFFBs can be divided into three types:fault-fracture body,fold-fracture body,and fault-fold body.In the hanging wall of the fault,the closer to the fault,the more developed the effective fractures;the greater the fold amplitude and the closer to the fold hinge plane,the more developed the effective fractures.Two types of geological models of FFFB are established:fault-fold fracture,and matrix storage and permeability.The former can be divided into two subtypes:network fracture,and single structural fracture,and the later can be divided into three subtypes:bedding fracture,low permeability pore,and extremely low permeability pore.The process for evaluating favorable FFFB zones was formed to define favorable development targets and support the well deployment for purpose of high production.The study results provide a reference for the exploration and development of deep tight sandstone oil and gas reservoirs in China.展开更多
BACKGROUND Multiple linear stapler firings during double stapling technique(DST)after laparoscopic low anterior resection(LAR)are associated with an increased risk of anastomotic leakage(AL).However,it is difficult to...BACKGROUND Multiple linear stapler firings during double stapling technique(DST)after laparoscopic low anterior resection(LAR)are associated with an increased risk of anastomotic leakage(AL).However,it is difficult to predict preoperatively the need for multiple linear stapler cartridges during DST anastomosis.AIM To develop a deep learning model to predict multiple firings during DST anastomosis based on pelvic magnetic resonance imaging(MRI).METHODS We collected 9476 MR images from 328 mid-low rectal cancer patients undergoing LAR with DST anastomosis,which were randomly divided into a training set(n=260)and testing set(n=68).Binary logistic regression was adopted to create a clinical model using six factors.The sequence of fast spin-echo T2-weighted MRI of the entire pelvis was segmented and analyzed.Pure-image and clinical-image integrated deep learning models were constructed using the mask region-based convolutional neural network segmentation tool and three-dimensional convolutional networks.Sensitivity,specificity,accuracy,positive predictive value(PPV),and area under the receiver operating characteristic curve(AUC)was calculated for each model.RESULTS The prevalence of≥3 linear stapler cartridges was 17.7%(58/328).The prevalence of AL was statistically significantly higher in patients with≥3 cartridges compared to those with≤2 cartridges(25.0%vs 11.8%,P=0.018).Preoperative carcinoembryonic antigen level>5 ng/mL(OR=2.11,95%CI 1.08-4.12,P=0.028)and tumor size≥5 cm(OR=3.57,95%CI 1.61-7.89,P=0.002)were recognized as independent risk factors for use of≥3 linear stapler cartridges.Diagnostic performance was better with the integrated model(accuracy=94.1%,PPV=87.5%,and AUC=0.88)compared with the clinical model(accuracy=86.7%,PPV=38.9%,and AUC=0.72)and the image model(accuracy=91.2%,PPV=83.3%,and AUC=0.81).CONCLUSION MRI-based deep learning model can predict the use of≥3 linear stapler cartridges during DST anastomosis in laparoscopic LAR surgery.This model might help determine the best anastomosis strategy by avoiding DST when there is a high probability of the need for≥3 linear stapler cartridges.展开更多
The Coronavirus Disease 2019(COVID-19)is wreaking havoc around the world,bring out that the enormous pressure on national health and medical staff systems.One of the most effective and critical steps in the fight agai...The Coronavirus Disease 2019(COVID-19)is wreaking havoc around the world,bring out that the enormous pressure on national health and medical staff systems.One of the most effective and critical steps in the fight against COVID-19,is to examine the patient’s lungs based on the Chest X-ray and CT generated by radiation imaging.In this paper,five keras-related deep learning models:ResNet50,InceptionResNetV2,Xception,transfer learning and pre-trained VGGNet16 is applied to formulate an classification-detection approaches of COVID-19.Two benchmark methods SVM(Support Vector Machine),CNN(Conventional Neural Networks)are provided to compare with the classification-detection approaches based on the performance indicators,i.e.,precision,recall,F1 scores,confusion matrix,classification accuracy and three types of AUC(Area Under Curve).The highest classification accuracy derived by classification-detection based on 5857 Chest X-rays and 767 Chest CTs are respectively 84%and 75%,which shows that the keras-related deep learning approaches facilitate accurate and effective COVID-19-assisted detection.展开更多
Artificial Intelligence(AI)and Computer Vision(CV)advancements have led to many useful methodologies in recent years,particularly to help visually-challenged people.Object detection includes a variety of challenges,fo...Artificial Intelligence(AI)and Computer Vision(CV)advancements have led to many useful methodologies in recent years,particularly to help visually-challenged people.Object detection includes a variety of challenges,for example,handlingmultiple class images,images that get augmented when captured by a camera and so on.The test images include all these variants as well.These detection models alert them about their surroundings when they want to walk independently.This study compares four CNN-based pre-trainedmodels:ResidualNetwork(ResNet-50),Inception v3,DenseConvolutional Network(DenseNet-121),and SqueezeNet,predominantly used in image recognition applications.Based on the analysis performed on these test images,the study infers that Inception V3 outperformed other pre-trained models in terms of accuracy and speed.To further improve the performance of the Inception v3 model,the thermal exchange optimization(TEO)algorithm is applied to tune the hyperparameters(number of epochs,batch size,and learning rate)showing the novelty of the work.Better accuracy was achieved owing to the inclusion of an auxiliary classifier as a regularizer,hyperparameter optimizer,and factorization approach.Additionally,Inception V3 can handle images of different sizes.This makes Inception V3 the optimum model for assisting visually challenged people in real-world communication when integrated with Internet of Things(IoT)-based devices.展开更多
The Coronavirus Disease(COVID-19)pandemic has exposed the vulnerabilities of medical services across the globe,especially in underdeveloped nations.In the aftermath of the COVID-19 outbreak,a strong demand exists for ...The Coronavirus Disease(COVID-19)pandemic has exposed the vulnerabilities of medical services across the globe,especially in underdeveloped nations.In the aftermath of the COVID-19 outbreak,a strong demand exists for developing novel computer-assisted diagnostic tools to execute rapid and cost-effective screenings in locations where many screenings cannot be executed using conventional methods.Medical imaging has become a crucial component in the disease diagnosis process,whereas X-rays and Computed Tomography(CT)scan imaging are employed in a deep network to diagnose the diseases.In general,four steps are followed in image-based diagnostics and disease classification processes by making use of the neural networks,such as network training,feature extraction,model performance testing and optimal feature selection.The current research article devises a Chaotic Flower Pollination Algorithm with a Deep Learning-Driven Fusion(CFPADLDF)approach for detecting and classifying COVID-19.The presented CFPA-DLDF model is developed by integrating two DL models to recognize COVID-19 in medical images.Initially,the proposed CFPA-DLDF technique employs the Gabor Filtering(GF)approach to pre-process the input images.In addition,a weighted voting-based ensemble model is employed for feature extraction,in which both VGG-19 and the MixNet models are included.Finally,the CFPA with Recurrent Neural Network(RNN)model is utilized for classification,showing the work’s novelty.A comparative analysis was conducted to demonstrate the enhanced performance of the proposed CFPADLDF model,and the results established the supremacy of the proposed CFPA-DLDF model over recent approaches.展开更多
基金supported by the Natural Science Foundation of China(Grant Nos.42088101 and 42205149)Zhongwang WEI was supported by the Natural Science Foundation of China(Grant No.42075158)+1 种基金Wei SHANGGUAN was supported by the Natural Science Foundation of China(Grant No.41975122)Yonggen ZHANG was supported by the National Natural Science Foundation of Tianjin(Grant No.20JCQNJC01660).
文摘Accurate soil moisture(SM)prediction is critical for understanding hydrological processes.Physics-based(PB)models exhibit large uncertainties in SM predictions arising from uncertain parameterizations and insufficient representation of land-surface processes.In addition to PB models,deep learning(DL)models have been widely used in SM predictions recently.However,few pure DL models have notably high success rates due to lacking physical information.Thus,we developed hybrid models to effectively integrate the outputs of PB models into DL models to improve SM predictions.To this end,we first developed a hybrid model based on the attention mechanism to take advantage of PB models at each forecast time scale(attention model).We further built an ensemble model that combined the advantages of different hybrid schemes(ensemble model).We utilized SM forecasts from the Global Forecast System to enhance the convolutional long short-term memory(ConvLSTM)model for 1–16 days of SM predictions.The performances of the proposed hybrid models were investigated and compared with two existing hybrid models.The results showed that the attention model could leverage benefits of PB models and achieved the best predictability of drought events among the different hybrid models.Moreover,the ensemble model performed best among all hybrid models at all forecast time scales and different soil conditions.It is highlighted that the ensemble model outperformed the pure DL model over 79.5%of in situ stations for 16-day predictions.These findings suggest that our proposed hybrid models can adequately exploit the benefits of PB model outputs to aid DL models in making SM predictions.
文摘Cyberspace is extremely dynamic,with new attacks arising daily.Protecting cybersecurity controls is vital for network security.Deep Learning(DL)models find widespread use across various fields,with cybersecurity being one of the most crucial due to their rapid cyberattack detection capabilities on networks and hosts.The capabilities of DL in feature learning and analyzing extensive data volumes lead to the recognition of network traffic patterns.This study presents novel lightweight DL models,known as Cybernet models,for the detection and recognition of various cyber Distributed Denial of Service(DDoS)attacks.These models were constructed to have a reasonable number of learnable parameters,i.e.,less than 225,000,hence the name“lightweight.”This not only helps reduce the number of computations required but also results in faster training and inference times.Additionally,these models were designed to extract features in parallel from 1D Convolutional Neural Networks(CNN)and Long Short-Term Memory(LSTM),which makes them unique compared to earlier existing architectures and results in better performance measures.To validate their robustness and effectiveness,they were tested on the CIC-DDoS2019 dataset,which is an imbalanced and large dataset that contains different types of DDoS attacks.Experimental results revealed that bothmodels yielded promising results,with 99.99% for the detectionmodel and 99.76% for the recognition model in terms of accuracy,precision,recall,and F1 score.Furthermore,they outperformed the existing state-of-the-art models proposed for the same task.Thus,the proposed models can be used in cyber security research domains to successfully identify different types of attacks with a high detection and recognition rate.
基金This work was supported by the Beijing Nova Program[Z211100002121136]Open Fund Project of State Key Laboratory of Lithospheric Evolution[SKL-K202103]+1 种基金Joint Funds of National Natural Science Foundation of China[U19B6003-02]the National Natural Science Foundation of China[42302149].We would like to thank Prof.Zhu Rixiang from the Institute of Geology and Geophysics,Chinese Academy of Sciences.
文摘With continuous hydrocarbon exploration extending to deeper basins,the deepest industrial oil accumulation was discovered below 8,200 m,revealing a new exploration field.Hence,the extent to which oil exploration can be extended,and the prediction of the depth limit of oil accumulation(DLOA),are issues that have attracted significant attention in petroleum geology.Since it is difficult to characterize the evolution of the physical properties of the marine carbonate reservoir with burial depth,and the deepest drilling still cannot reach the DLOA.Hence,the DLOA cannot be predicted by directly establishing the relationship between the ratio of drilling to the dry layer and the depth.In this study,by establishing the relationships between the porosity and the depth and dry layer ratio of the carbonate reservoir,the relationships between the depth and dry layer ratio were obtained collectively.The depth corresponding to a dry layer ratio of 100%is the DLOA.Based on this,a quantitative prediction model for the DLOA was finally built.The results indicate that the porosity of the carbonate reservoir,Lower Ordovician in Tazhong area of Tarim Basin,tends to decrease with burial depth,and manifests as an overall low porosity reservoir in deep layer.The critical porosity of the DLOA was 1.8%,which is the critical geological condition corresponding to a 100%dry layer ratio encountered in the reservoir.The depth of the DLOA was 9,000 m.This study provides a new method for DLOA prediction that is beneficial for a deeper understanding of oil accumulation,and is of great importance for scientific guidance on deep oil drilling.
基金financially supported by the National Natural Science Foundation of China (Nos.51974023 and52374321)the funding of State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,China (No.41620007)。
文摘The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
基金supported in part by the Gusu Innovation and Entrepreneurship Leading Talents in Suzhou City,grant numbers ZXL2021425 and ZXL2022476Doctor of Innovation and Entrepreneurship Program in Jiangsu Province,grant number JSSCBS20211440+6 种基金Jiangsu Province Key R&D Program,grant number BE2019682Natural Science Foundation of Jiangsu Province,grant number BK20200214National Key R&D Program of China,grant number 2017YFB0403701National Natural Science Foundation of China,grant numbers 61605210,61675226,and 62075235Youth Innovation Promotion Association of Chinese Academy of Sciences,grant number 2019320Frontier Science Research Project of the Chinese Academy of Sciences,grant number QYZDB-SSW-JSC03Strategic Priority Research Program of the Chinese Academy of Sciences,grant number XDB02060000.
文摘The prediction of fundus fluorescein angiography(FFA)images from fundus structural images is a cutting-edge research topic in ophthalmological image processing.Prediction comprises estimating FFA from fundus camera imaging,single-phase FFA from scanning laser ophthalmoscopy(SLO),and three-phase FFA also from SLO.Although many deep learning models are available,a single model can only perform one or two of these prediction tasks.To accomplish three prediction tasks using a unified method,we propose a unified deep learning model for predicting FFA images from fundus structure images using a supervised generative adversarial network.The three prediction tasks are processed as follows:data preparation,network training under FFA supervision,and FFA image prediction from fundus structure images on a test set.By comparing the FFA images predicted by our model,pix2pix,and CycleGAN,we demonstrate the remarkable progress achieved by our proposal.The high performance of our model is validated in terms of the peak signal-to-noise ratio,structural similarity index,and mean squared error.
文摘Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.
文摘We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.
基金2023 Annual Project of the China Association for Construction Education“Research on the Development Path of Private Colleges and Industry Integration in Liaoning Province Under the Strategy of Intelligent Manufacturing Strong Province”(Project number:2023239)。
文摘Against the backdrop of continuous development in the field of education,universities are encouraged to innovate their talent cultivation systems and objectives.The deep integration of industry and education has emerged as an effective strategy,aligning with the basic requirements of the new engineering education initiative and exerting a positive impact on socioeconomic development.However,an analysis of the current state of industry-education integration in universities reveals several issues that require optimization,affecting the ultimate effectiveness of integration.To optimize this phenomenon and achieve high-quality development,universities need to further explore the construction of a deep integration model of industry and education,adhering to corresponding principles to form a comprehensive system.On this basis,pathways for deep industry-education integration can be summarized.
基金funded by a Special Fund for Basic Research on Scientific Instruments of the National Natural Science Foundation of China(Grant No.41827807)the Study on Intelligent Technology for Tunnels Construction of Sichuan-Tibet Railway(Grant No.19-21-1).
文摘The dilation angle is the most commonly used parameter to study nonlinear post-peak dilatancy(PPD)behavior and simulate surrounding rock deformation;however,simplified or constant dilatancy models are often used in numerical calculations owing to their simple mathematical forms.This study developed a PPD model for rocks(rock masses)based on the Alejanoe-Alonso(A-A)dilatancy model.The developed model comprehensively reflects the influences of confining pressure(σ_(3))and plastic shear strain(γ^(p)),with the advantages of a simple mathematical form,while requiring fewer parameters and demonstrating a clear physical significance.The overall fitting accuracy of the PPD model for 11 different rocks was found to be higher than that of the A-A model,particularly for Witwatersrand quartzite and jointed granite.The applicability and reliability of the PPD model to jointed granites and different scaled Moura coals were also investigated,and the model was found to be more suitable for the soft and large-scale rocks,e.g.deep rock mass.The PPD model was also successfully applied in studying the mechanical response of a circular tunnel excavated in strain-softening rock mass,and the developed semi-analytical solution was compared and verified with existing analytical solutions.The sensitivities of the rock dilatancy to γ^(p) and σ_(3) showed significant spatial variabilities along the radial direction of the surrounding rock,and the dilation angle did not exhibit a monotonical increasing or decreasing law from the elasticeplastic boundary to the tunnel wall,thereby presenting the σ3-or γ^(p)-dominated differential effects of rock dilatancy.Tunnel deformation parabolically or exponentially increased with increasing in situ stress(buried depth).The developed PPD model is promising to conduct refined numerical and analytical analyses for deep tunneling,which produces extensive plastic deformation and exhibits significant nonlinear post-peak behavior.
基金funded by the Deanship of Scientific Research,Princess Nourah bint Abdulrahman University,through the Program of Research Project Funding after publication,Grand No.PRFA-P-42-16.
文摘Renewable energy has become a solution to the world’s energy concerns in recent years.Photovoltaic(PV)technology is the fastest technique to convert solar radiation into electricity.Solar-powered buses,metros,and cars use PV technology.Such technologies are always evolving.Included in the parameters that need to be analysed and examined include PV capabilities,vehicle power requirements,utility patterns,acceleration and deceleration rates,and storage module type and capacity,among others.PVPG is intermit-tent and weather-dependent.Accurate forecasting and modelling of PV sys-tem output power are key to managing storage,delivery,and smart grids.With unparalleled data granularity,a data-driven system could better anticipate solar generation.Deep learning(DL)models have gained popularity due to their capacity to handle complex datasets and increase computing power.This article introduces the Galactic Swarm Optimization with Deep Belief Network(GSODBN-PPGF)model.The GSODBN-PPGF model predicts PV power production.The GSODBN-PPGF model normalises data using data scaling.DBN is used to forecast PV power output.The GSO algorithm boosts the DBN model’s predicted output.GSODBN-PPGF projected 0.002 after 40 h but observed 0.063.The GSODBN-PPGF model validation is compared to existing approaches.Simulations showed that the GSODBN-PPGF model outperformed recent techniques.It shows that the proposed model is better at forecasting than other models and can be used to predict the PV power output for the next day.
文摘Aflood is a significant damaging natural calamity that causes loss of life and property.Earlier work on the construction offlood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byfloods.The massive amount of data generated by social media platforms such as Twitter opens the door toflood analysis.Because of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue strategy.However,due to the shorter duration of Tweets,it is difficult to construct a perfect prediction model for determiningflood.Machine learning(ML)and deep learning(DL)approaches can be used to statistically developflood prediction models.At the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forflood prediction.In this regard,this work provides an optimal deep learning-basedflood forecasting model with big data analytics(ODLFF-BDA)based on Twitter data.The suggested ODLFF-BDA technique intends to anticipate the existence offloods using tweets in a big data setting.The ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable format.In addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from tweets.Furthermore,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theflood.Finally,an Equilibrium Optimizer(EO)is used tofine-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction performance.The memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm techniques.The ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and thefindings showed that it outperformed other recent approaches significantly.
基金Supported by the Sinopec Science and Technology Project(P21040-1).
文摘In the second member of the Upper Triassic Xujiahe Formation(T_(3)x_(2))in the Xinchang area,western Sichuan Basin,only a low percent of reserves has been recovered,and the geological model of gas reservoir sweet spot remains unclear.Based on a large number of core,field outcrop,test and logging-seismic data,the T_(3)x_(2) gas reservoir in the Xinchang area is examined.The concept of fault-fold-fracture body(FFFB)is proposed,and its types are recognized.The main factors controlling fracture development are identified,and the geological models of FFFB are established.FFFB refers to faults,folds and associated fractures reservoirs.According to the characteristics and genesis,FFFBs can be divided into three types:fault-fracture body,fold-fracture body,and fault-fold body.In the hanging wall of the fault,the closer to the fault,the more developed the effective fractures;the greater the fold amplitude and the closer to the fold hinge plane,the more developed the effective fractures.Two types of geological models of FFFB are established:fault-fold fracture,and matrix storage and permeability.The former can be divided into two subtypes:network fracture,and single structural fracture,and the later can be divided into three subtypes:bedding fracture,low permeability pore,and extremely low permeability pore.The process for evaluating favorable FFFB zones was formed to define favorable development targets and support the well deployment for purpose of high production.The study results provide a reference for the exploration and development of deep tight sandstone oil and gas reservoirs in China.
基金Shanghai Jiaotong University,No.YG2019QNB24This study was reviewed and approved by Ruijin Hospital Ethics Committee(Approval No.2019-82).
文摘BACKGROUND Multiple linear stapler firings during double stapling technique(DST)after laparoscopic low anterior resection(LAR)are associated with an increased risk of anastomotic leakage(AL).However,it is difficult to predict preoperatively the need for multiple linear stapler cartridges during DST anastomosis.AIM To develop a deep learning model to predict multiple firings during DST anastomosis based on pelvic magnetic resonance imaging(MRI).METHODS We collected 9476 MR images from 328 mid-low rectal cancer patients undergoing LAR with DST anastomosis,which were randomly divided into a training set(n=260)and testing set(n=68).Binary logistic regression was adopted to create a clinical model using six factors.The sequence of fast spin-echo T2-weighted MRI of the entire pelvis was segmented and analyzed.Pure-image and clinical-image integrated deep learning models were constructed using the mask region-based convolutional neural network segmentation tool and three-dimensional convolutional networks.Sensitivity,specificity,accuracy,positive predictive value(PPV),and area under the receiver operating characteristic curve(AUC)was calculated for each model.RESULTS The prevalence of≥3 linear stapler cartridges was 17.7%(58/328).The prevalence of AL was statistically significantly higher in patients with≥3 cartridges compared to those with≤2 cartridges(25.0%vs 11.8%,P=0.018).Preoperative carcinoembryonic antigen level>5 ng/mL(OR=2.11,95%CI 1.08-4.12,P=0.028)and tumor size≥5 cm(OR=3.57,95%CI 1.61-7.89,P=0.002)were recognized as independent risk factors for use of≥3 linear stapler cartridges.Diagnostic performance was better with the integrated model(accuracy=94.1%,PPV=87.5%,and AUC=0.88)compared with the clinical model(accuracy=86.7%,PPV=38.9%,and AUC=0.72)and the image model(accuracy=91.2%,PPV=83.3%,and AUC=0.81).CONCLUSION MRI-based deep learning model can predict the use of≥3 linear stapler cartridges during DST anastomosis in laparoscopic LAR surgery.This model might help determine the best anastomosis strategy by avoiding DST when there is a high probability of the need for≥3 linear stapler cartridges.
基金This project is supported by National Natural Science Foundation of China(NSFC)(Nos.61902158,61806087)Graduate student innovation program for academic degrees in general university in Jiangsu Province(No.KYZZ16-0337).
文摘The Coronavirus Disease 2019(COVID-19)is wreaking havoc around the world,bring out that the enormous pressure on national health and medical staff systems.One of the most effective and critical steps in the fight against COVID-19,is to examine the patient’s lungs based on the Chest X-ray and CT generated by radiation imaging.In this paper,five keras-related deep learning models:ResNet50,InceptionResNetV2,Xception,transfer learning and pre-trained VGGNet16 is applied to formulate an classification-detection approaches of COVID-19.Two benchmark methods SVM(Support Vector Machine),CNN(Conventional Neural Networks)are provided to compare with the classification-detection approaches based on the performance indicators,i.e.,precision,recall,F1 scores,confusion matrix,classification accuracy and three types of AUC(Area Under Curve).The highest classification accuracy derived by classification-detection based on 5857 Chest X-rays and 767 Chest CTs are respectively 84%and 75%,which shows that the keras-related deep learning approaches facilitate accurate and effective COVID-19-assisted detection.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2023R191)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:(22UQU4310373DSR61)This study is supported via funding from Prince Sattam bin Abdulaziz University project number(PSAU/2023/R/1444).
文摘Artificial Intelligence(AI)and Computer Vision(CV)advancements have led to many useful methodologies in recent years,particularly to help visually-challenged people.Object detection includes a variety of challenges,for example,handlingmultiple class images,images that get augmented when captured by a camera and so on.The test images include all these variants as well.These detection models alert them about their surroundings when they want to walk independently.This study compares four CNN-based pre-trainedmodels:ResidualNetwork(ResNet-50),Inception v3,DenseConvolutional Network(DenseNet-121),and SqueezeNet,predominantly used in image recognition applications.Based on the analysis performed on these test images,the study infers that Inception V3 outperformed other pre-trained models in terms of accuracy and speed.To further improve the performance of the Inception v3 model,the thermal exchange optimization(TEO)algorithm is applied to tune the hyperparameters(number of epochs,batch size,and learning rate)showing the novelty of the work.Better accuracy was achieved owing to the inclusion of an auxiliary classifier as a regularizer,hyperparameter optimizer,and factorization approach.Additionally,Inception V3 can handle images of different sizes.This makes Inception V3 the optimum model for assisting visually challenged people in real-world communication when integrated with Internet of Things(IoT)-based devices.
文摘The Coronavirus Disease(COVID-19)pandemic has exposed the vulnerabilities of medical services across the globe,especially in underdeveloped nations.In the aftermath of the COVID-19 outbreak,a strong demand exists for developing novel computer-assisted diagnostic tools to execute rapid and cost-effective screenings in locations where many screenings cannot be executed using conventional methods.Medical imaging has become a crucial component in the disease diagnosis process,whereas X-rays and Computed Tomography(CT)scan imaging are employed in a deep network to diagnose the diseases.In general,four steps are followed in image-based diagnostics and disease classification processes by making use of the neural networks,such as network training,feature extraction,model performance testing and optimal feature selection.The current research article devises a Chaotic Flower Pollination Algorithm with a Deep Learning-Driven Fusion(CFPADLDF)approach for detecting and classifying COVID-19.The presented CFPA-DLDF model is developed by integrating two DL models to recognize COVID-19 in medical images.Initially,the proposed CFPA-DLDF technique employs the Gabor Filtering(GF)approach to pre-process the input images.In addition,a weighted voting-based ensemble model is employed for feature extraction,in which both VGG-19 and the MixNet models are included.Finally,the CFPA with Recurrent Neural Network(RNN)model is utilized for classification,showing the work’s novelty.A comparative analysis was conducted to demonstrate the enhanced performance of the proposed CFPADLDF model,and the results established the supremacy of the proposed CFPA-DLDF model over recent approaches.