“深”度学习深圳人大经验,促进“内地”人大业务和履职能力的大提升

随着经济社会的不断发展民主法制建设进程的不断推进 , 对人大常委会履职能力和工作业务水平也提出了更高的要求。要适应新的形势和任务需要 , 就要在学习、工作、作风、创新上有新的突破 , 不断提高人大工作的整体水平,更好为人民服务。

Deep Learning Hybrid Model for Lithium-Ion Battery Aging Estimation and Prediction

The degradation process of lithium-ion batteries is intricately linked to their entire lifecycle as power sources and energy storage devices,encompassing aspects such as performance delivery and cycling utilization.Consequently,the accurate and expedient estimation or prediction of the aging state of lithium-ion batteries has garnered extensive attention.Nonetheless,prevailing research predominantly concentrates on either aging estimation or prediction,neglecting the dynamic fusion of both facets.This paper proposes a hybrid model for capacity aging estimation and prediction based on deep learning,wherein salient features highly pertinent to aging are extracted from charge and discharge relaxation processes.By amalgamating historical capacity decay data,the model dynamically furnishes estimations of the present capacity and forecasts of future capacity for lithium-ion batteries.Our approach is validated against a novel dataset involving charge and discharge cycles at varying rates.Specifically,under a charging condition of 0.25 C,a mean absolute percentage error(MAPE)of 0.29%is achieved.This outcome underscores the model's adeptness in harnessing relaxation processes commonly encountered in the real world and synergizing with historical capacity records within battery management systems(BMS),thereby affording estimations and prognostications of capacity decline with heightened precision.

Improvement of High-Speed Detection Algorithm for Nonwoven Material Defects Based on Machine Vision

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished products.Recently,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial fields.This paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus model.Using the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection framework.Within this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection accuracy.The half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection speed.Performance comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

Re-identifying beef cattle using improved AlignedReID++

Accurate and continuous identification of individual cattle is crucial to precision farming in recent years.It is also the prerequisite to monitor the individual feed intake and feeding time of beef cattle at medium to long distances over different cameras.However,beef cattle can tend to frequently move and change their feeding position during feeding.Furthermore,the great variations in their head direction and complex environments(light,occlusion,and background)can also lead to some difficulties in the recognition,particularly for the bio-similarities among individual cattle.Among them,AlignedReID++model is characterized by both global and local information for image matching.In particular,the dynamically matching local information(DMLI)algorithm has been introduced into the local branch to automatically align the horizontal local information.In this research,the AlignedReID++model was utilized and improved to achieve the better performance in cattle re-identification(ReID).Initially,triplet attention(TA)modules were integrated into the BottleNecks of ResNet50 Backbone.The feature extraction was then enhanced through cross-dimensional interactions with the minimal computational overhead.Since the TA modules in AlignedReID++baseline model increased the model size and floating point operations(FLOPs)by 0.005 M and 0.05 G,the rank-1 accuracy and mean average precision(mAP)were improved by 1.0 percentage points and 2.94 percentage points,respectively.Specifically,the rank-1 accuracies were outperformed by 0.86 percentage points and 0.12 percentage points,respectively,compared with the convolution block attention module(CBAM)and efficient channel attention(ECA)modules,although 0.94 percentage points were lower than that of squeeze-and-excitation(SE)modules.The mAP metric values were exceeded by 0.22,0.86 and 0.12 percentage points,respectively,compared with the SE,CBAM,and ECA modules.Additionally,the Cross-Entropy Loss function was replaced with the CosFace Loss function in the global branch of baseline model.CosFace Loss and Hard Triplet Loss were jointly employed to train the baseline model for the better identification on the similar individuals.AlignedReID++with CosFace Loss was outperformed the baseline model by 0.24 and 0.92 percentage points in the rank-1 accuracy and mAP,respectively,whereas,AlignedReID++with ArcFace Loss was exceeded by 0.36 and 0.56 percentage points,respectively.The improved model with the TA modules and CosFace Loss was achieved in a rank-1 accuracy of 94.42%,rank-5 accuracy of 98.78%,rank-10 accuracy of 99.34%,mAP of 63.90%,FLOPs of 5.45 G,frames per second(FPS)of 5.64,and model size of 23.78 M.The rank-1 accuracies were exceeded by 1.84,4.72,0.76 and 5.36 percentage points,respectively,compared with the baseline model,part-based convolutional baseline(PCB),multiple granularity network(MGN),and relation-aware global attention(RGA),while the mAP metrics were surpassed 6.42,5.86,4.30 and 7.38 percentage points,respectively.Meanwhile,the rank-1 accuracy was 0.98 percentage points lower than TransReID,but the mAP metric was exceeded by 3.90 percentage points.Moreover,the FLOPs of improved model were only 0.05 G larger than that of baseline model,while smaller than those of PCB,MGN,RGA,and TransReID by 0.68,6.51,25.4,and 16.55 G,respectively.The model size of improved model was 23.78 M,which was smaller than those of the baseline model,PCB,MGN,RGA,and TransReID by 0.03,2.33,45.06,14.53 and 62.85 M,respectively.The inference speed of improved model on a CPU was lower than those of PCB,MGN,and baseline model,but higher than TransReID and RGA.The t-SNE feature embedding visualization demonstrated that the global and local features were achieve in the better intra-class compactness and inter-class variability.Therefore,the improved model can be expected to effectively re-identify the beef cattle in natural environments of breeding farm,in order to monitor the individual feed intake and feeding time.

A Framework of LSTM Neural Network Model in Multi-Time Scale Real-Time Prediction of Ship Motions in Head Waves

Ship motions induced by waves have a significant impact on the efficiency and safety of offshore operations.Real-time prediction of ship motions in the next few seconds plays a crucial role in performing sensitive activities.However,the obvious memory effect of ship motion time series brings certain difficulty to rapid and accurate prediction.Therefore,a real-time framework based on the Long-Short Term Memory(LSTM)neural network model is proposed to predict ship motions in regular and irregular head waves.A 15000 TEU container ship model is employed to illustrate the proposed framework.The numerical implementation and the real-time ship motion prediction in irregular head waves corresponding to the different time scales are carried out based on the container ship model.The related experimental data were employed to verify the numerical simulation results.The results show that the proposed method is more robust than the classical extreme short-term prediction method based on potential flow theory in the prediction of nonlinear ship motions.

Improving autoencoder-based unsupervised damage detection in uncontrolled structural health monitoring under noisy conditions

Structural health monitoring is widely utilized in outdoor environments,especially under harsh conditions,which can introduce noise into the monitoring system.Therefore,designing an effective denoising strategy to enhance the performance of guided wave damage detection in noisy environments is crucial.This paper introduces a local temporal principal component analysis(PCA)reconstruction approach for denoising guided waves prior to implementing unsupervised damage detection,achieved through novel autoencoder-based reconstruction.Experimental results demonstrate that the proposed denoising method significantly enhances damage detection performance when guided waves are contaminated by noise,with SNR values ranging from 10 to-5 dB.Following the implementation of the proposed denoising approach,the AUC score can elevate from 0.65 to 0.96 when dealing with guided waves corrputed by noise at a level of-5 dB.Additionally,the paper provides guidance on selecting the appropriate number of components used in the denoising PCA reconstruction,aiding in the optimization of the damage detection in noisy conditions.

Advancing automated pupillometry:a practical deep learning model utilizing infrared pupil images

AIM:To establish pupil diameter measurement algorithms based on infrared images that can be used in real-world clinical settings.METHODS:A total of 188 patients from outpatient clinic at He Eye Specialist Shenyang Hospital from Spetember to December 2022 were included,and 13470 infrared pupil images were collected for the study.All infrared images for pupil segmentation were labeled using the Labelme software.The computation of pupil diameter is divided into four steps:image pre-processing,pupil identification and localization,pupil segmentation,and diameter calculation.Two major models are used in the computation process:the modified YoloV3 and Deeplabv 3+models,which must be trained beforehand.RESULTS:The test dataset included 1348 infrared pupil images.On the test dataset,the modified YoloV3 model had a detection rate of 99.98% and an average precision(AP)of 0.80 for pupils.The DeeplabV3+model achieved a background intersection over union(IOU)of 99.23%,a pupil IOU of 93.81%,and a mean IOU of 96.52%.The pupil diameters in the test dataset ranged from 20 to 56 pixels,with a mean of 36.06±6.85 pixels.The absolute error in pupil diameters between predicted and actual values ranged from 0 to 7 pixels,with a mean absolute error(MAE)of 1.06±0.96 pixels.CONCLUSION:This study successfully demonstrates a robust infrared image-based pupil diameter measurement algorithm,proven to be highly accurate and reliable for clinical application.

Polar residual network model for assisting evaluation on rat myocardial infarction segment in myocardial contrast echocardiography

Objective To investigate the value of polar residual network(PResNet)model for assisting evaluation on rat myocardial infarction(MI)segment in myocardial contrast echocardiography(MCE).Methods Twenty-five male SD rats were randomly divided into MI group(n=15)and sham operation group(n=10).MI models were established in MI group through ligation of the left anterior descending coronary artery using atraumatic suture,while no intervention was given to those in sham operation group after thoracotomy.MCE images of both basal and papillary muscle levels on the short axis section of left ventricles were acquired after 1 week,which were assessed independently by 2 junior and 2 senior ultrasound physicians.The evaluating efficacy of MI segment,the mean interpretation time and the consistency were compared whether under the assistance of PResNet model or not.Results No significant difference of efficacy of evaluation on MI segment was found for senior physicians with or without assistance of PResNet model(both P>0.05).Under the assistance of PResNet model,the efficacy of junior physicians for diagnosing MI segment was significantly improved compared with that without the assistance of PResNet model(both P<0.01),and was comparable to that of senior physicians.Under the assistance of PResNet model,the mean interpretation time of each physician was significantly shorter than that without assistance(all P<0.001),and the consistency between junior physicians and among junior and senior physicians were both moderate(Kappa=0.692,0.542),which became better under the assistance(Kappa=0.763,0.749).Conclusion PResNet could improve the efficacy of junior physicians for evaluation on rat MI segment in MCE images,shorten interpretation time with different aptitudes,also improve the consistency to some extent.

Automated body composition analysis system based on chest CT for evaluating content of muscle and adipose

Objective To establish a body composition analysis system based on chest CT,and to observe its value for evaluating content of chest muscle and adipose.Methods T7—T8 layer CT images of 108 pneumonia patients were collected(segmented dataset),and chest CT data of 984 patients were screened from the COVID 19-CT dataset(10 cases were randomly selected as whole test dataset,the remaining 974 cases were selected as layer selection dataset).T7—T8 layer was classified based on convolutional neural network(CNN)derived networks,including ResNet,ResNeXt,MobileNet,ShuffleNet,DenseNet,EfficientNet and ConvNeXt,then the accuracy,precision,recall and specificity were used to evaluate the performance of layer selection dataset.The skeletal muscle(SM),subcutaneous adipose tissue(SAT),intermuscular adipose tissue(IMAT)and visceral adipose tissue(VAT)were segmented using classical fully CNN(FCN)derived network,including FCN,SegNet,UNet,Attention UNet,UNET++,nnUNet,UNeXt and CMUNeXt,then Dice similarity coefficient(DSC),intersection over union(IoU)and 95 Hausdorff distance(HD)were used to evaluate the performance of segmented dataset.The automatic body composition analysis system was constructed based on optimal layer selection network and segmentation network,the mean absolute error(MAE),root mean squared error(RMSE)and standard deviation(SD)of MAE were used to evaluate the performance of automatic system for testing the whole test dataset.Results The accuracy,precision,recall and specificity of DenseNet network for automatically classifying T7—T8 layer from chest CT images was 95.06%,84.83%,92.27%and 95.78%,respectively,which were all higher than those of the other layer selection networks.In segmentation of SM,SAT,IMAT and overall,DSC and IoU of UNet++network were all higher,while 95HD of UNet++network were all lower than those of the other segmentation networks.Using DenseNet as the layer selection network and UNet++as the segmentation network,MAE of the automatic body composition analysis system for predicting SM,SAT,IMAT,VAT and MAE was 27.09,6.95,6.65 and 3.35 cm 2,respectively.Conclusion The body composition analysis system based on chest CT could be used to assess content of chest muscle and adipose.Among them,the UNet++network had better segmentation performance in adipose tissue than SM.

Research progresses of artificial intelligence in MRI of lumbar degenerative diseases

The incidence of lumbar degenerative diseases is increasing year by year,and MRI is often used in clinical diagnosis.In recent years,artificial intelligence(AI)has rapidly developed in medical field and can be used for image segmentation and auxiliary diagnosis of lumbar degenerative diseases.The research progresses of AI in MRI of lumbar degenerative diseases were reviewed in this article.

Wafer Defect Map Pattern Recognition Based on Improved ResNet

The defect detection of wafers is an important part of semiconductor manufacturing.The wafer defect map formed from the defects can be used to trace back the problems in the production process and make improvements in the yield of wafer manufacturing.Therefore,for the pattern recognition of wafer defects,this paper uses an improved ResNet convolutional neural network for automatic pattern recognition of seven common wafer defects.On the basis of the original ResNet,the squeeze-and-excitation(SE)attention mechanism is embedded into the network,through which the feature extraction ability of the network can be improved,key features can be found,and useless features can be suppressed.In addition,the residual structure is improved,and the depth separable convolution is added to replace the traditional convolution to reduce the computational and parametric quantities of the network.In addition,the network structure is improved and the activation function is changed.Comprehensive experiments show that the precision of the improved ResNet in this paper reaches 98.5%,while the number of parameters is greatly reduced compared with the original model,and has well results compared with the common convolutional neural network.Comprehensively,the method in this paper can be very good for pattern recognition of common wafer defect types,and has certain application value.

Deep learning-based recognition of stained tongue coating images

Objective To build a dataset encompassing a large number of stained tongue coating images and process it using deep learning to automatically recognize stained tongue coating images.Methods A total of 1001 images of stained tongue coating from healthy students at Hunan University of Chinese Medicine and 1007 images of pathological(non-stained)tongue coat-ing from hospitalized patients at The First Hospital of Hunan University of Chinese Medicine withlungcancer;diabetes;andhypertensionwerecollected.Thetongueimageswererandomi-zed into the training;validation;and testing datasets in a 7:2:1 ratio.A deep learning model was constructed using the ResNet50 for recognizing stained tongue coating in the training and validation datasets.The training period was 90 epochs.The model’s performance was evaluated by its accuracy;loss curve;recall;F1 score;confusion matrix;receiver operating characteristic(ROC)curve;and precision-recall(PR)curve in the tasks of predicting stained tongue coating images in the testing dataset.The accuracy of the deep learning model was compared with that of attending physicians of traditional Chinese medicine(TCM).Results The training results showed that after 90 epochs;the model presented an excellent classification performance.The loss curve and accuracy were stable;showing no signs of overfitting.The model achieved an accuracy;recall;and F1 score of 92%;91%;and 92%;re-spectively.The confusion matrix revealed an accuracy of 92%for the model and 69%for TCM practitioners.The areas under the ROC and PR curves were 0.97 and 0.95;respectively.Conclusion The deep learning model constructed using ResNet50 can effectively recognize stained coating images with greater accuracy than visual inspection of TCM practitioners.This model has the potential to assist doctors in identifying false tongue coating and prevent-ing misdiagnosis.

Deep learning echocardiographic intelligent model for evaluation on left ventricular regional wall motion abnormality

Objective To observe the value of deep learning echocardiographic intelligent model for evaluation on left ventricular(LV)regional wall motion abnormalities(RWMA).Methods Apical two-chamber,three-chamber and four-chamber views two-dimensional echocardiograms were obtained prospectively in 205 patients with coronary heart disease.The model for evaluating LV regional contractile function was constructed using a five-fold cross-validation method to automatically identify the presence of RWMA or not,and the performance of this model was assessed taken manual interpretation of RWMA as standards.Results Among 205 patients,RWMA was detected in totally 650 segments in 83 cases.LV myocardial segmentation model demonstrated good efficacy for delineation of LV myocardium.The average Dice similarity coefficient for LV myocardial segmentation results in the apical two-chamber,three-chamber and four-chamber views was 0.85,0.82 and 0.88,respectively.LV myocardial segmentation model accurately segmented LV myocardium in apical two-chamber,three-chamber and four-chamber views.The mean area under the curve(AUC)of RWMA identification model was 0.843±0.071,with sensitivity of(64.19±14.85)%,specificity of(89.44±7.31)%and accuracy of(85.22±4.37)%.Conclusion Deep learning echocardiographic intelligent model could be used to automatically evaluate LV regional contractile function,hence rapidly and accurately identifying RWMA.

Construction and optimization of traditional Chinese medicine constitution prediction models based on deep learning

Objective To cater to the demands for personalized health services from a deep learning per-spective by investigating the characteristics of traditional Chinese medicine(TCM)constitu-tion data and constructing models to explore new prediction methods.Methods Data from students at Chengdu University of Traditional Chinese Medicine were collected and organized according to the 24 solar terms from January 21,2020,to April 6,2022.The data were used to identify nine TCM constitutions,including balanced constitution,Qi deficiency constitution,Yang deficiency constitution,Yin deficiency constitution,phlegm dampness constitution,damp heat constitution,stagnant blood constitution,Qi stagnation constitution,and specific-inherited predisposition constitution.Deep learning algorithms were employed to construct multi-layer perceptron(MLP),long short-term memory(LSTM),and deep belief network(DBN)models for the prediction of TCM constitutions based on the nine constitution types.To optimize these TCM constitution prediction models,this study in-troduced the attention mechanism(AM),grey wolf optimizer(GWO),and particle swarm op-timization(PSO).The models’performance was evaluated before and after optimization us-ing the F1-score,accuracy,precision,and recall.Results The research analyzed a total of 31655 pieces of data.(i)Before optimization,the MLP model achieved more than 90%prediction accuracy for all constitution types except the balanced and Qi deficiency constitutions.The LSTM model's prediction accuracies exceeded 60%,indicating that their potential in TCM constitutional prediction may not have been fully realized due to the absence of pronounced temporal features in the data.Regarding the DBN model,the binary classification analysis showed that,apart from slightly underperforming in predicting the Qi deficiency constitution and damp heat constitution,with accuracies of 65%and 60%,respectively.The DBN model demonstrated considerable discriminative power for other constitution types,achieving prediction accuracy rates and area under the receiver op-erating characteristic(ROC)curve(AUC)values exceeding 70%and 0.78,respectively.This indicates that while the model possesses a certain level of constitutional differentiation abili-ty,it encounters limitations in processing specific constitutional features,leaving room for further improvement in its performance.For multi-class classification problem,the DBN model’s prediction accuracy rate fell short of 50%.(ii)After optimization,the LSTM model,enhanced with the AM,typically achieved a prediction accuracy rate above 75%,with lower performance for the Qi deficiency constitution,stagnant blood constitution,and Qi stagna-tion constitution.The GWO-optimized DBN model for multi-class classification showed an increased prediction accuracy rate of 56%,while the PSO-optimized model had a decreased accuracy rate to 37%.The GWO-PSO-DBN model,optimized with both algorithms,demon-strated an improved prediction accuracy rate of 54%.Conclusion This study constructed MLP,LSTM,and DBN models for predicting TCM consti-tution and improved them based on different optimisation algorithms.The results showed that the MLP model performs well,the LSTM and DBN models were effective in prediction but with certain limitations.This study also provided a new technology reference for the es-tablishment and optimisation strategies of TCM constitution prediction models,and a novel idea for the treatment of non-disease.

Constitution identification model in traditional Chinese medicine based on multiple features

Objective To construct a precise model for identifying traditional Chinese medicine(TCM)constitutions;thereby offering optimized guidance for clinical diagnosis and treatment plan-ning;and ultimately enhancing medical efficiency and treatment outcomes.Methods First;TCM full-body inspection data acquisition equipment was employed to col-lect full-body standing images of healthy people;from which the constitutions were labelled and defined in accordance with the Constitution in Chinese Medicine Questionnaire(CCMQ);and a dataset encompassing labelled constitutions was constructed.Second;heat-suppres-sion valve(HSV)color space and improved local binary patterns(LBP)algorithm were lever-aged for the extraction of features such as facial complexion and body shape.In addition;a dual-branch deep network was employed to collect deep features from the full-body standing images.Last;the random forest(RF)algorithm was utilized to learn the extracted multifea-tures;which were subsequently employed to establish a TCM constitution identification mod-el.Accuracy;precision;and F1 score were the three measures selected to assess the perfor-mance of the model.Results It was found that the accuracy;precision;and F1 score of the proposed model based on multifeatures for identifying TCM constitutions were 0.842;0.868;and 0.790;respectively.In comparison with the identification models that encompass a single feature;either a single facial complexion feature;a body shape feature;or deep features;the accuracy of the model that incorporating all the aforementioned features was elevated by 0.105;0.105;and 0.079;the precision increased by 0.164;0.164;and 0.211;and the F1 score rose by 0.071;0.071;and 0.084;respectively.Conclusion The research findings affirmed the viability of the proposed model;which incor-porated multifeatures;including the facial complexion feature;the body shape feature;and the deep feature.In addition;by employing the proposed model;the objectification and intel-ligence of identifying constitutions in TCM practices could be optimized.

Deep learning models for automatic classification ofechocardiographic views

Objective To observe the value of deep learning (DL) models for automatic classification of echocardiographic views. Methods Totally 100 patients after heart transplantation were retrospectively enrolled and divided into training set, validation set and test set at a ratio of 7 ∶ 2 ∶ 1. ResNet18, ResNet34, Swin Transformer and Swin Transformer V2 models were established based on 2D apical two chamber view, 2D apical three chamber view, 2D apical four chamber view, 2D subcostal view, parasternal long-axis view of left ventricle, short-axis view of great arteries, short-axis view of apex of left ventricle, short-axis view of papillary muscle of left ventricle, short-axis view of mitral valve of left ventricle, also 3D and CDFI views of echocardiography. The accuracy, precision, recall, F1 score and confusion matrix were used to evaluate the performance of each model for automatically classifying echocardiographic views. The interactive interface was designed based on Qt Designer software and deployed on the desktop. Results The performance of models for automatically classifying echocardiographic views in test set were all good, with relatively poor performance for 2D short-axis view of left ventricle and superior performance for 3D and CDFI views. Swin Transformer V2 was the optimal model for automatically classifying echocardiographic views, with high accuracy, precision, recall and F1 score was 92.56%, 89.01%, 89.97% and 89.31%, respectively, which also had the highest diagonal value in confusion matrix and showed the best classification effect on various views in t-SNE figure. Conclusion DL model had good performance for automatically classifying echocardiographic views, especially Swin Transformer V2 model had the best performance. Using interactive classification interface could improve the interpretability of prediction results to some extent.

Deep learning model based on PET/CT and combination with Cox proportional hazard model for predicting progression of lung invasive adenocarcinoma after surgery

Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUV max and SUV mean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P<0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUV max>4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.

An Intelligent Learning Algorithm for Improving BIM Object Classification and Recognition

Building information modeling(BIM)object classification takes a lot of time and energy.Misclassification or omission of any object may lead to the emergence of abnormal results,which have a great impact on the project workflow and results.Roundly understanding BIM object classification,by improving Swin Transformer classifier algorithm parameters,using the model primitives extracted from IFC format BIM model file,deep learning of 7 types of BIM object categories is taken.Through the performance and evaluation indicators obtained in training,the results improve the classification accuracy.

Research on the LA-UMamba Model for Asymmetric Modules with Added Auxiliary Information

Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling capability of the model through the self-attention mechanism,better segmentation performance can be achieve.Moreover,the high computational cost of Transformer has motivated researchers to explore more efficient models,such as the Mamba model based on state-space modeling(SSM),and for the field of medical segmentation,reducing the number of model parameters is also necessary.In this study,a novel asymmetric model called LA-UMamba was proposed,which integrates visual Mamba module to efficiently capture complex visual features and remote dependencies.The classical design of U-Net was adopted in the upsampling phase to help reduce the number of references and recover more details.To mitigate the information loss problem,an auxiliary U-Net downsampling layer was designed to focus on sizing without extracting features,thus enhancing the protection of input information while maintaining the efficiency of the model.The experiments were conducted on the ACDC MRI cardiac segmentation dataset,and the results showed that the proposed LA-UMamba achieves proved performance compared to the baseline model in several evaluation metrics,such as IoU,Accuracy,Precision,HD and ASD,which improved that the model is successful in optimizing the detail processing and reducing the complexity of the model,providing a new perspective for further optimization of medical image segmentation techniques.

A Study on Short Text Matching Method Based on KS-BERT Algorithm

To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.