The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation fo...The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.展开更多
The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotatio...The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotation is difficult and expensive.The incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and2)the distribution of target domain samples becomes misaligned with the false-labeled samples.To overcome these negative effects,this article proposes a solution called the label recovery and trajectory designable network(LRTDN).LRTDN consists of three parts.First,a residual network with dual classifiers is to learn features from cross-domain samples.Second,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source domain.With the training of relabeled samples,the complexity of diagnosis model is reduced via semi-supervised learning.Third,the adaptation trajectories are designed for sample distributions across domains.This ensures that the target domain samples are only adapted with the pure-labeled samples.The LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related machines.The results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.展开更多
Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of ...Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis,thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis.Methods In total,623 eligible patients were recruited from two medical institutions.Seven deep learning models,namely Alex,GoogLeNet,Resnet18,Resnet101,Vgg16,Vgg19,and MobileNetv3(small),were utilized to extract deep image histological features.The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient(r≥0.9)and Least Absolute Shrinkage and Selection Operator.Eleven machine learning methods,namely Support Vector Machine,K-nearest neighbor,Random Forest,Extra Trees,XGBoost,LightGBM,Naive Bayes,AdaBoost,Gradient Boosting Decision Tree,Linear Regression,and Multilayer Perceptron,were employed to construct classification prediction models for the filtered final features.The diagnostic performances of the models were assessed using various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value.Calibration and decision-curve analyses were also performed.Results The present study demonstrated that using deep radiomic features extracted from Vgg16,in conjunction with a prediction model constructed via a linear regression algorithm,effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer.The performance of the model was evaluated based on various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value,which yielded values of 0.808,0.834,0.851,0.745,0.829,and 0.776,respectively.The validation set of the model was assessed using clinical decision curves,calibration curves,and confusion matrices,which collectively demonstrated the model's stability and accuracy.Conclusion In this study,information on the deep radiomics of Vgg16 was obtained from computed tomography images,and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.展开更多
In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power grid.Furthe...In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power grid.Furthermore, by integrating Machine Learning (ML), NILM can efficiently use electrical energy and offer less ofa burden for the energy monitoring process. However, conducted research works have limitations for real-timeimplementation due to the practical issues. This paper aims to identify the contribution of ML approaches todeveloping a reliable Energy Management (EM) solution with NILM. Firstly, phases of the NILM are discussed,along with the research works that have been conducted in the domain. Secondly, the contribution of machinelearning approaches in three aspects is discussed: Supervised learning, unsupervised learning, and hybridmodeling.It highlights the limitations in the applicability of ML approaches in the field. Then, the challenges in the realtimeimplementation are concerned with six use cases: Difficulty in recognizing multiple loads at a given time,cost of running the NILM system, lack of universal framework for appliance detection, anomaly detection andnew appliance identification, and complexity of the electricity loads and real-time demand side management.Furthermore, options for selecting an approach for an efficientNILMframework are suggested. Finally, suggestionsare provided for future research directions.展开更多
Classification and monitoring of microalgae species in aquatic ecosystems are important for understanding population dynamics.However,manual classification of algae is a time-consuming method and requires a lot of eff...Classification and monitoring of microalgae species in aquatic ecosystems are important for understanding population dynamics.However,manual classification of algae is a time-consuming method and requires a lot of effort with expertise due to the large number of families and genera in its classification.The recognition of microalgae species has become an increasingly important research area in image recognition in recent years.In this study,machine learning and deep learning methods were proposed to classify images of 12 different microalgae species in order to successfully classify algae cells.8 Different novel models(MobileNetV3Small-Lr,MobileNetV3Small-Rf,MobileNetV3Small-Xg,MobileNetV3Large-Lr,MobileNetV3Large-Rf,MobileNetV3Large-Xg,Mobile-NetV3Small-Improved and MobileNetV3Large-Improved)have been proposed to classify these microalgae species.Among these proposed model structures,the best classification accuracy rate was 92.22%and the loss rate was 0.72,obtained from the MobileNetV3Large-Improved model structure.In addition,as a result of the experimental results obtained,metrics such as the confusion matrix,which can meet the experts in the correct diagnosis of microalgae species,were also evaluated.This research may in the future open a new avenue for the development of a cost-effective,highly sensitive computer-based system for the use of image analysis and deep learning techniques for the identification and classification of different microalgae.展开更多
The dynamic performance of the coupling shaft system in a carpet tufting machine is the most critical factor affecting the carpet tufting machine's efficiency,and the product quality of the tufted carpet. To deter...The dynamic performance of the coupling shaft system in a carpet tufting machine is the most critical factor affecting the carpet tufting machine's efficiency,and the product quality of the tufted carpet. To determine how to avoid resonance produced by the coupling shaft system's vibration during the weaving process,the dynamic performance of a coupling shaft system in a carpet tufting machine was analyzed. Focusing on a DHGN801D-400 carpet tufting machine,a dynamic model of coupling shaft system was established by utilizing transfer matrix methodology. On the basis of this model,the natural frequencies and mode shapes of the coupling shaft system were obtained through simulations. The correctness of the theoretical model and the dynamic performance of the coupling shaft system were validated by experiments. The first order natural frequency of the coupling shaft system was close to 600 r / min. A conclusion can thus be drawn that operating the carpet tufting machine near this speed should be avoided as much as possible.展开更多
Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appea...Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appear at the initial level. To preventblindness, early detection and regular treatment are needed. Automated detectionbased on machine intelligence may assist the ophthalmologist in examining thepatients’ condition more accurately and efficiently. The purpose of this study is toproduce an automated screening system for recognition and grading of diabetic retinopathyusing machine learning through deep transfer and representational learning.The artificial intelligence technique used is transfer learning on the deep neural network,Inception-v4. Two configuration variants of transfer learning are applied onInception-v4: Fine-tune mode and fixed feature extractor mode. Both configurationmodes have achieved decent accuracy values, but the fine-tuning method outperformsthe fixed feature extractor configuration mode. Fine-tune configuration modehas gained 96.6% accuracy in early detection of DR and 97.7% accuracy in gradingthe disease and has outperformed the state of the art methods in the relevant literature.展开更多
Soil extracellular electron transfer(EET)is a pivotal biological process within the realm of soil.Unfortunately,EET suffers from a lack of predictive models.Herein,an intricately crafted machine learning model has bee...Soil extracellular electron transfer(EET)is a pivotal biological process within the realm of soil.Unfortunately,EET suffers from a lack of predictive models.Herein,an intricately crafted machine learning model has been developed for the purpose of predicting soil EET by using the physicochemical properties of soil as independent input variables and the EET capabilities in terms of current density(j_(max))and Coulombic charge(C_(out))as dependent output variables.An autoencoder ensemble stacking(AES)model was developed to address the aforementioned issue by integrating support vector machine,multilayer perceptron,extreme gradient boosting,and light gradient boosting machine algorithms as the stacking algorithms.With 10-fold crossvalidation,the AES model exhibited notable improvements in predicting j_(max)and C_(out),with average test R^(2)values of 0.83 and 0.84,respectively,surpassing those of single machine learning(ML)models and the basic ensemble model.By utilizing partial correlation plots(PDPs),Shapley Additive explanations(SHAP)values,and SHAP decision plots,we quantitatively explained the impact and contribution of the input molecules on the AES model’s predictions of j_(max)and C_(out).In the context of the SHAP method for the AES model,total carbon(TC)was identified as the most correlated descriptor for j_(max),while total organic carbon(TOC)stood out as the most relevant descriptor for C_(out).In the prediction tasks of j_(max)and C_(out)within the AES model,employing a multitask ML approach allowed the model to benefit from the shared information of input variables,thereby enhancing its overall generalizability.This study provides a feasible tool for the prediction of soil EET from soil physiochemical properties and an advanced understanding of the relationship between soil physiochemical properties and EET capability.展开更多
The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,whi...The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,which makes it challenging and a big issue to improve approaches for efficient identification of COVID-19 disease.In this study,an automatic prediction of COVID-19 identification is proposed to automatically discriminate between healthy and COVID-19 infected subjects in X-ray images using two successful moderns are traditional machine learning methods(e.g.,artificial neural network(ANN),support vector machine(SVM),linear kernel and radial basis function(RBF),k-nearest neighbor(k-NN),Decision Tree(DT),andCN2 rule inducer techniques)and deep learningmodels(e.g.,MobileNets V2,ResNet50,GoogleNet,DarkNet andXception).A largeX-ray dataset has been created and developed,namely the COVID-19 vs.Normal(400 healthy cases,and 400 COVID cases).To the best of our knowledge,it is currently the largest publicly accessible COVID-19 dataset with the largest number of X-ray images of confirmed COVID-19 infection cases.Based on the results obtained from the experiments,it can be concluded that all the models performed well,deep learning models had achieved the optimum accuracy of 98.8%in ResNet50 model.In comparison,in traditional machine learning techniques, the SVM demonstrated the best result for an accuracy of 95% and RBFaccuracy 94% for the prediction of coronavirus disease 2019.展开更多
Tunnel boring machine(TBM) vibration induced by cutting complex ground contains essential information that can help engineers evaluate the interaction between a cutterhead and the ground itself.In this study,deep recu...Tunnel boring machine(TBM) vibration induced by cutting complex ground contains essential information that can help engineers evaluate the interaction between a cutterhead and the ground itself.In this study,deep recurrent neural networks(RNNs) and convolutional neural networks(CNNs) were used for vibration-based working face ground identification.First,field monitoring was conducted to obtain the TBM vibration data when tunneling in changing geological conditions,including mixed-face,homogeneous,and transmission ground.Next,RNNs and CNNs were utilized to develop vibration-based prediction models,which were then validated using the testing dataset.The accuracy of the long short-term memory(LSTM) and bidirectional LSTM(Bi-LSTM) models was approximately 70% with raw data;however,with instantaneous frequency transmission,the accuracy increased to approximately 80%.Two types of deep CNNs,GoogLeNet and ResNet,were trained and tested with time-frequency scalar diagrams from continuous wavelet transformation.The CNN models,with an accuracy greater than 96%,performed significantly better than the RNN models.The ResNet-18,with an accuracy of 98.28%,performed the best.When the sample length was set as the cutterhead rotation period,the deep CNN and RNN models achieved the highest accuracy while the proposed deep CNN model simultaneously achieved high prediction accuracy and feedback efficiency.The proposed model could promptly identify the ground conditions at the working face without stopping the normal tunneling process,and the TBM working parameters could be adjusted and optimized in a timely manner based on the predicted results.展开更多
This paper sums up four security factors after analyzing co-residency threats caused by the special multitenant environment in the cloud.To secure the factors,a multiway dynamic trust chain transfer model was proposed...This paper sums up four security factors after analyzing co-residency threats caused by the special multitenant environment in the cloud.To secure the factors,a multiway dynamic trust chain transfer model was proposed on the basis of a measurement interactive virtual machine and current behavior to protect the integrity of the system.A trust chain construction module is designed in a virtual machine monitor.Through dynamic monitoring,it achieves the purpose of transferring integrity between virtual machine.A cloud system with a trust authentication function is implemented on the basis of the model,and its practicability is shown.展开更多
The dynamic performances of an ultra-precision fly cutting machine tool(UFCMT)has a dramatic impact on the quality of ultra-precision machining.In this study,the dynamic model of an UFCMT was established based on the ...The dynamic performances of an ultra-precision fly cutting machine tool(UFCMT)has a dramatic impact on the quality of ultra-precision machining.In this study,the dynamic model of an UFCMT was established based on the transfer matrix method for multibody systems.In particular,the large-span scale flow field mesh model was created;and the variation in linear and angular stiffness of journal and thrust bearings with respect to film thickness was investigated by adopting the dynamic mesh technique.The dynamic model was proven to be valid by comparing the dynamic characteristics of the machine tool obtained by numerical simulation with the experimental results.In addition,the power spectrum density estimation method was adopted to simulate the statistical ambient vibration excitation by processing the ambient vibration signal measured over a long period of time.Applying it to the dynamic model,the dynamic response of the tool tip under ambient vibration was investigated.The results elucidated that the tool tip response was significantly affected by ambient vibration,and the isolation foundation had a good effect on vibration isolation.展开更多
Forward radiative transfer(RT)models are essential for atmospheric applications such as remote sensing and weather and climate models,where computational efficiency becomes equally as important as accuracy for high-re...Forward radiative transfer(RT)models are essential for atmospheric applications such as remote sensing and weather and climate models,where computational efficiency becomes equally as important as accuracy for high-resolution hyperspectral measurements that need rigorous RT simulations for thousands of channels.This study introduces a fast and accurate RT model for the hyperspectral infrared(HIR)sounder based on principal component analysis(PCA)or machine learning(i.e.,neural network,NN).The Geosynchronous Interferometric Infrared Sounder(GIIRS),the first HIR sounder onboard the geostationary Fengyun-4 satellites,is considered to be a candidate example for model development and validation.Our method uses either PCA or NN(PCA/NN)twice for the atmospheric transmittance and radiance,respectively,to reduce the number of independent but similar simulations to accelerate RT simulations;thereby,it is referred to as a multi-domain compression model.The first PCA/NN gives monochromatic gas transmittance in both spectral and atmospheric pressure domains for each gas independently.The second PCA/NN is performed in the traditional spectral radiance domain.Meanwhile,a new method is introduced to choose representative variables for the PCA/NN scheme developments.The model is three orders of magnitude faster than the standard line-by-line-based simulations with averaged brightness temperature difference(BTD)less than 0.1 K,and the compressions based on PCA or NN methods result in comparable efficiency and accuracy.Our fast model not only avoids an excessively complicated transmittance scheme by using PCA/NN but is also highly flexible for hyperspectral instruments with similar spectral ranges simply by updating the corresponding spectral response functions.展开更多
The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster ...The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.展开更多
The article considers negative effects of mechanical oscillations of a fuselage on the flying machine autopilot. The dynamic model of control system of flight is made which provides stability and compensates the mecha...The article considers negative effects of mechanical oscillations of a fuselage on the flying machine autopilot. The dynamic model of control system of flight is made which provides stability and compensates the mechanical oscillations arising in flight of flying machine with the autopilot.展开更多
With the progress of deep learning research, convolutional neural networks have become the most important method in feature extraction. How to effectively classify and recognize the extracted features will directly af...With the progress of deep learning research, convolutional neural networks have become the most important method in feature extraction. How to effectively classify and recognize the extracted features will directly affect the performance of the entire network. Traditional processing methods include classification models such as fully connected network models and support vector machines. In order to solve the problem that the traditional convolutional neural network is prone to over-fitting for the classification of small samples, a CNN-TWSVM hybrid model was proposed by fusing the twin support vector machine (TWSVM) with higher computational efficiency as the CNN classifier, and it was applied to the traffic sign recognition task. In order to improve the generalization ability of the model, the wavelet kernel function is introduced to deal with the nonlinear classification task. The method uses the network initialized from the ImageNet dataset to fine-tune the specific domain and intercept the inner layer of the network to extract the high abstract features of the traffic sign image. Finally, the TWSVM based on wavelet kernel function is used to identify the traffic signs, so as to effectively solve the over-fitting problem of traffic signs classification. On GTSRB and BELGIUMTS datasets, the validity and generalization ability of the improved model is verified by comparing with different kernel functions and different SVM classifiers.展开更多
Currently,breast cancer has been amajor cause of deaths in women worldwide and the World Health Organization(WHO)has confirmed this.The severity of this disease can be minimized to the large extend,if it is diagnosed ...Currently,breast cancer has been amajor cause of deaths in women worldwide and the World Health Organization(WHO)has confirmed this.The severity of this disease can be minimized to the large extend,if it is diagnosed properly at an early stage of the disease.Therefore,the proper treatment of a patient having cancer can be processed in better way,if it can be diagnosed properly as early as possible using the better algorithms.Moreover,it has been currently observed that the deep neural networks have delivered remarkable performance for detecting cancer in histopathological images of breast tissues.To address the above said issues,this paper presents a hybrid model using the transfer learning to study the histopathological images,which help in detection and rectification of the disease at a low cost.Extensive dataset experiments were carried out to validate the suggested hybrid model in this paper.The experimental results show that the proposed model outperformed the baseline methods,with F-scores of 0.81 for DenseNet+Logistic Regression hybrid model,(F-score:0.73)for Visual Geometry Group(VGG)+Logistic Regression hybrid model,(F-score:0.74)for VGG+Random Forest,(F-score:0.79)for DenseNet+Random Forest,and(F-score:0.79)for VGG+Densenet+Logistic Regression hybrid model on the dataset of histopathological images.展开更多
Cars are regarded as an indispensable means of transportation in Taiwan.Several studies have indicated that the automotive industry has witnessed remarkable advances and that the market of used cars has rapidly expand...Cars are regarded as an indispensable means of transportation in Taiwan.Several studies have indicated that the automotive industry has witnessed remarkable advances and that the market of used cars has rapidly expanded.In this study,a price prediction system for used BMW cars was developed.Nine parameters of used cars,including their model,registration year,and transmission style,were analyzed.The data obtained were then divided into three subsets.The first subset was used to compare the results of each algorithm.The predicted values produced by the two algorithms with the most satisfactory results were used as the input of a fully connected neural network.The second subset was used with an optimization algorithm to modify the number of hidden layers in a fully connected neural network and modify the low,medium,and high parameters of the membership function(MF)to achieve model optimization.Finally,the third subset was used for the validation set during the prediction process.These three subsets were divided using k-fold cross-validation to avoid overfitting and selection bias.In conclusion,in this study,a model combining two optimal algorithms(i.e.,random forest and k-nearest neighbors)with several optimization algorithms(i.e.,gray wolf optimizer,multilayer perceptron,and MF)was successfully established.The prediction results obtained indicated a mean square error of 0.0978,a root-mean-square error of 0.3128,a mean absolute error of 0.1903,and a coefficient of determination of 0.9249.展开更多
Coronavirus(COVID-19 or SARS-CoV-2)is a novel viral infection that started in December 2019 and has erupted rapidly in more than 150 countries.The rapid spread of COVID-19 has caused a global health emergency and resu...Coronavirus(COVID-19 or SARS-CoV-2)is a novel viral infection that started in December 2019 and has erupted rapidly in more than 150 countries.The rapid spread of COVID-19 has caused a global health emergency and resulted in governments imposing lock-downs to stop its transmission.There is a signifi-cant increase in the number of patients infected,resulting in a lack of test resources and kits in most countries.To overcome this panicked state of affairs,researchers are looking forward to some effective solutions to overcome this situa-tion:one of the most common and effective methods is to examine the X-radiation(X-rays)and computed tomography(CT)images for detection of Covid-19.How-ever,this method burdens the radiologist to examine each report.Therefore,to reduce the burden on the radiologist,an effective,robust and reliable detection system has been developed,which may assist the radiologist and medical specia-list in effective detecting of COVID.We proposed a deep learning approach that uses readily available chest radio-graphs(chest X-rays)to diagnose COVID-19 cases.The proposed approach applied transfer learning to the Deep Convolutional Neural Network(DCNN)model,Inception-v4,for the automatic detection of COVID-19 infection from chest X-rays images.The dataset used in this study contains 1504 chest X-ray images,504 images of COVID-19 infection,and 1000 normal images obtained from publicly available medical repositories.The results showed that the proposed approach detected COVID-19 infection with an overall accuracy of 99.63%.展开更多
文摘The visions of Industry 4.0 and 5.0 have reinforced the industrial environment.They have also made artificial intelligence incorporated as a major facilitator.Diagnosing machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe operations.Transfer learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two datasets.In response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning algorithm.It is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative transfer.The algorithm also adaptively adjusts the portion of training data to balance the learning rate and training time.The proposed algorithm is evaluated and analyzed using ten benchmark datasets.Compared with other algorithms from existing works,SA-ITL improves the accuracy of all datasets.Ablation studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.
基金the National Key R&D Program of China(2022YFB3402100)the National Science Fund for Distinguished Young Scholars of China(52025056)+4 种基金the National Natural Science Foundation of China(52305129)the China Postdoctoral Science Foundation(2023M732789)the China Postdoctoral Innovative Talents Support Program(BX20230290)the Open Foundation of Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment(2022JXKF JJ01)the Fundamental Research Funds for Central Universities。
文摘The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source domain.However,in engineering scenarios,achieving such high-quality label annotation is difficult and expensive.The incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and2)the distribution of target domain samples becomes misaligned with the false-labeled samples.To overcome these negative effects,this article proposes a solution called the label recovery and trajectory designable network(LRTDN).LRTDN consists of three parts.First,a residual network with dual classifiers is to learn features from cross-domain samples.Second,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source domain.With the training of relabeled samples,the complexity of diagnosis model is reduced via semi-supervised learning.Third,the adaptation trajectories are designed for sample distributions across domains.This ensures that the target domain samples are only adapted with the pure-labeled samples.The LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related machines.The results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.
基金the Science and Technology Funding Project of Hunan Province,China(2023JJ50410)(HX)Key Laboratory of Tumor Precision Medicine,Hunan colleges and Universities Project(2019-379)(QL).
文摘Background The prognosis and survival of patients with lung cancer are likely to deteriorate with metastasis.Using deep-learning in the detection of lymph node metastasis can facilitate the noninvasive calculation of the likelihood of such metastasis,thereby providing clinicians with crucial information to enhance diagnostic precision and ultimately improve patient survival and prognosis.Methods In total,623 eligible patients were recruited from two medical institutions.Seven deep learning models,namely Alex,GoogLeNet,Resnet18,Resnet101,Vgg16,Vgg19,and MobileNetv3(small),were utilized to extract deep image histological features.The dimensionality of the extracted features was then reduced using the Spearman correlation coefficient(r≥0.9)and Least Absolute Shrinkage and Selection Operator.Eleven machine learning methods,namely Support Vector Machine,K-nearest neighbor,Random Forest,Extra Trees,XGBoost,LightGBM,Naive Bayes,AdaBoost,Gradient Boosting Decision Tree,Linear Regression,and Multilayer Perceptron,were employed to construct classification prediction models for the filtered final features.The diagnostic performances of the models were assessed using various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value.Calibration and decision-curve analyses were also performed.Results The present study demonstrated that using deep radiomic features extracted from Vgg16,in conjunction with a prediction model constructed via a linear regression algorithm,effectively distinguished the status of mediastinal lymph nodes in patients with lung cancer.The performance of the model was evaluated based on various metrics,including accuracy,area under the receiver operating characteristic curve,sensitivity,specificity,positive predictive value,and negative predictive value,which yielded values of 0.808,0.834,0.851,0.745,0.829,and 0.776,respectively.The validation set of the model was assessed using clinical decision curves,calibration curves,and confusion matrices,which collectively demonstrated the model's stability and accuracy.Conclusion In this study,information on the deep radiomics of Vgg16 was obtained from computed tomography images,and the linear regression method was able to accurately diagnose mediastinal lymph node metastases in patients with lung cancer.
文摘In recent years,Non-Intrusive LoadMonitoring (NILM) has become an emerging approach that provides affordableenergy management solutions using aggregated load obtained from a single smart meter in the power grid.Furthermore, by integrating Machine Learning (ML), NILM can efficiently use electrical energy and offer less ofa burden for the energy monitoring process. However, conducted research works have limitations for real-timeimplementation due to the practical issues. This paper aims to identify the contribution of ML approaches todeveloping a reliable Energy Management (EM) solution with NILM. Firstly, phases of the NILM are discussed,along with the research works that have been conducted in the domain. Secondly, the contribution of machinelearning approaches in three aspects is discussed: Supervised learning, unsupervised learning, and hybridmodeling.It highlights the limitations in the applicability of ML approaches in the field. Then, the challenges in the realtimeimplementation are concerned with six use cases: Difficulty in recognizing multiple loads at a given time,cost of running the NILM system, lack of universal framework for appliance detection, anomaly detection andnew appliance identification, and complexity of the electricity loads and real-time demand side management.Furthermore, options for selecting an approach for an efficientNILMframework are suggested. Finally, suggestionsare provided for future research directions.
文摘Classification and monitoring of microalgae species in aquatic ecosystems are important for understanding population dynamics.However,manual classification of algae is a time-consuming method and requires a lot of effort with expertise due to the large number of families and genera in its classification.The recognition of microalgae species has become an increasingly important research area in image recognition in recent years.In this study,machine learning and deep learning methods were proposed to classify images of 12 different microalgae species in order to successfully classify algae cells.8 Different novel models(MobileNetV3Small-Lr,MobileNetV3Small-Rf,MobileNetV3Small-Xg,MobileNetV3Large-Lr,MobileNetV3Large-Rf,MobileNetV3Large-Xg,Mobile-NetV3Small-Improved and MobileNetV3Large-Improved)have been proposed to classify these microalgae species.Among these proposed model structures,the best classification accuracy rate was 92.22%and the loss rate was 0.72,obtained from the MobileNetV3Large-Improved model structure.In addition,as a result of the experimental results obtained,metrics such as the confusion matrix,which can meet the experts in the correct diagnosis of microalgae species,were also evaluated.This research may in the future open a new avenue for the development of a cost-effective,highly sensitive computer-based system for the use of image analysis and deep learning techniques for the identification and classification of different microalgae.
基金National Natural Science Foundation of China(No.51175075)the Research and Innovation Project of Shanghai Municipal Education Commission,China(No.15ZZ034)
文摘The dynamic performance of the coupling shaft system in a carpet tufting machine is the most critical factor affecting the carpet tufting machine's efficiency,and the product quality of the tufted carpet. To determine how to avoid resonance produced by the coupling shaft system's vibration during the weaving process,the dynamic performance of a coupling shaft system in a carpet tufting machine was analyzed. Focusing on a DHGN801D-400 carpet tufting machine,a dynamic model of coupling shaft system was established by utilizing transfer matrix methodology. On the basis of this model,the natural frequencies and mode shapes of the coupling shaft system were obtained through simulations. The correctness of the theoretical model and the dynamic performance of the coupling shaft system were validated by experiments. The first order natural frequency of the coupling shaft system was close to 600 r / min. A conclusion can thus be drawn that operating the carpet tufting machine near this speed should be avoided as much as possible.
基金the National Research Foundation(NRF)of Korea under the auspices of the Ministry of Science and ICT,Republic of Korea(Grant No.NRF-2020R1G1A1012741)received by M.R.Bhutta.https://nrf.kird.re.kr/main.do.
文摘Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appear at the initial level. To preventblindness, early detection and regular treatment are needed. Automated detectionbased on machine intelligence may assist the ophthalmologist in examining thepatients’ condition more accurately and efficiently. The purpose of this study is toproduce an automated screening system for recognition and grading of diabetic retinopathyusing machine learning through deep transfer and representational learning.The artificial intelligence technique used is transfer learning on the deep neural network,Inception-v4. Two configuration variants of transfer learning are applied onInception-v4: Fine-tune mode and fixed feature extractor mode. Both configurationmodes have achieved decent accuracy values, but the fine-tuning method outperformsthe fixed feature extractor configuration mode. Fine-tune configuration modehas gained 96.6% accuracy in early detection of DR and 97.7% accuracy in gradingthe disease and has outperformed the state of the art methods in the relevant literature.
基金supported by Guangdong Basic and Applied Basic Research Foundation(Grant No.2023B1515040022)the National Natural Science Foundation of China(Grant Nos.42177270 and 42207340).
文摘Soil extracellular electron transfer(EET)is a pivotal biological process within the realm of soil.Unfortunately,EET suffers from a lack of predictive models.Herein,an intricately crafted machine learning model has been developed for the purpose of predicting soil EET by using the physicochemical properties of soil as independent input variables and the EET capabilities in terms of current density(j_(max))and Coulombic charge(C_(out))as dependent output variables.An autoencoder ensemble stacking(AES)model was developed to address the aforementioned issue by integrating support vector machine,multilayer perceptron,extreme gradient boosting,and light gradient boosting machine algorithms as the stacking algorithms.With 10-fold crossvalidation,the AES model exhibited notable improvements in predicting j_(max)and C_(out),with average test R^(2)values of 0.83 and 0.84,respectively,surpassing those of single machine learning(ML)models and the basic ensemble model.By utilizing partial correlation plots(PDPs),Shapley Additive explanations(SHAP)values,and SHAP decision plots,we quantitatively explained the impact and contribution of the input molecules on the AES model’s predictions of j_(max)and C_(out).In the context of the SHAP method for the AES model,total carbon(TC)was identified as the most correlated descriptor for j_(max),while total organic carbon(TOC)stood out as the most relevant descriptor for C_(out).In the prediction tasks of j_(max)and C_(out)within the AES model,employing a multitask ML approach allowed the model to benefit from the shared information of input variables,thereby enhancing its overall generalizability.This study provides a feasible tool for the prediction of soil EET from soil physiochemical properties and an advanced understanding of the relationship between soil physiochemical properties and EET capability.
文摘The quick spread of the CoronavirusDisease(COVID-19)infection around the world considered a real danger for global health.The biological structure and symptoms of COVID-19 are similar to other viral chest maladies,which makes it challenging and a big issue to improve approaches for efficient identification of COVID-19 disease.In this study,an automatic prediction of COVID-19 identification is proposed to automatically discriminate between healthy and COVID-19 infected subjects in X-ray images using two successful moderns are traditional machine learning methods(e.g.,artificial neural network(ANN),support vector machine(SVM),linear kernel and radial basis function(RBF),k-nearest neighbor(k-NN),Decision Tree(DT),andCN2 rule inducer techniques)and deep learningmodels(e.g.,MobileNets V2,ResNet50,GoogleNet,DarkNet andXception).A largeX-ray dataset has been created and developed,namely the COVID-19 vs.Normal(400 healthy cases,and 400 COVID cases).To the best of our knowledge,it is currently the largest publicly accessible COVID-19 dataset with the largest number of X-ray images of confirmed COVID-19 infection cases.Based on the results obtained from the experiments,it can be concluded that all the models performed well,deep learning models had achieved the optimum accuracy of 98.8%in ResNet50 model.In comparison,in traditional machine learning techniques, the SVM demonstrated the best result for an accuracy of 95% and RBFaccuracy 94% for the prediction of coronavirus disease 2019.
基金supported by the National Natural Science Foundation of China(Grant No.52090082)the Natural Science Foundation of Shandong Province,China(Grant No.ZR2020ME243)the Shanghai Committee of Science and Technology(Grant No.19511100802)。
文摘Tunnel boring machine(TBM) vibration induced by cutting complex ground contains essential information that can help engineers evaluate the interaction between a cutterhead and the ground itself.In this study,deep recurrent neural networks(RNNs) and convolutional neural networks(CNNs) were used for vibration-based working face ground identification.First,field monitoring was conducted to obtain the TBM vibration data when tunneling in changing geological conditions,including mixed-face,homogeneous,and transmission ground.Next,RNNs and CNNs were utilized to develop vibration-based prediction models,which were then validated using the testing dataset.The accuracy of the long short-term memory(LSTM) and bidirectional LSTM(Bi-LSTM) models was approximately 70% with raw data;however,with instantaneous frequency transmission,the accuracy increased to approximately 80%.Two types of deep CNNs,GoogLeNet and ResNet,were trained and tested with time-frequency scalar diagrams from continuous wavelet transformation.The CNN models,with an accuracy greater than 96%,performed significantly better than the RNN models.The ResNet-18,with an accuracy of 98.28%,performed the best.When the sample length was set as the cutterhead rotation period,the deep CNN and RNN models achieved the highest accuracy while the proposed deep CNN model simultaneously achieved high prediction accuracy and feedback efficiency.The proposed model could promptly identify the ground conditions at the working face without stopping the normal tunneling process,and the TBM working parameters could be adjusted and optimized in a timely manner based on the predicted results.
基金supported by The National Natural Science Foundation for Young Scientists of China under Grant No.61303263the Jiangsu Provincial Research Foundation for Basic Research(Natural Science Foundation)under Grant No.BK20150201+4 种基金the Scientific Research Key Project of Beijing Municipal Commission of Education under Grant No.KZ201210015015Project Supported by the National Natural Science Foundation of China(Grant No.61370140)the Scientific Research Common Program of the Beijing Municipal Commission of Education(Grant No.KMKM201410015006)The National Science Foundation of China under Grant Nos.61232016 and U1405254and the PAPD fund
文摘This paper sums up four security factors after analyzing co-residency threats caused by the special multitenant environment in the cloud.To secure the factors,a multiway dynamic trust chain transfer model was proposed on the basis of a measurement interactive virtual machine and current behavior to protect the integrity of the system.A trust chain construction module is designed in a virtual machine monitor.Through dynamic monitoring,it achieves the purpose of transferring integrity between virtual machine.A cloud system with a trust authentication function is implemented on the basis of the model,and its practicability is shown.
文摘The dynamic performances of an ultra-precision fly cutting machine tool(UFCMT)has a dramatic impact on the quality of ultra-precision machining.In this study,the dynamic model of an UFCMT was established based on the transfer matrix method for multibody systems.In particular,the large-span scale flow field mesh model was created;and the variation in linear and angular stiffness of journal and thrust bearings with respect to film thickness was investigated by adopting the dynamic mesh technique.The dynamic model was proven to be valid by comparing the dynamic characteristics of the machine tool obtained by numerical simulation with the experimental results.In addition,the power spectrum density estimation method was adopted to simulate the statistical ambient vibration excitation by processing the ambient vibration signal measured over a long period of time.Applying it to the dynamic model,the dynamic response of the tool tip under ambient vibration was investigated.The results elucidated that the tool tip response was significantly affected by ambient vibration,and the isolation foundation had a good effect on vibration isolation.
基金supported by the National Natural Science Foundation of China(Grant No.42122038)。
文摘Forward radiative transfer(RT)models are essential for atmospheric applications such as remote sensing and weather and climate models,where computational efficiency becomes equally as important as accuracy for high-resolution hyperspectral measurements that need rigorous RT simulations for thousands of channels.This study introduces a fast and accurate RT model for the hyperspectral infrared(HIR)sounder based on principal component analysis(PCA)or machine learning(i.e.,neural network,NN).The Geosynchronous Interferometric Infrared Sounder(GIIRS),the first HIR sounder onboard the geostationary Fengyun-4 satellites,is considered to be a candidate example for model development and validation.Our method uses either PCA or NN(PCA/NN)twice for the atmospheric transmittance and radiance,respectively,to reduce the number of independent but similar simulations to accelerate RT simulations;thereby,it is referred to as a multi-domain compression model.The first PCA/NN gives monochromatic gas transmittance in both spectral and atmospheric pressure domains for each gas independently.The second PCA/NN is performed in the traditional spectral radiance domain.Meanwhile,a new method is introduced to choose representative variables for the PCA/NN scheme developments.The model is three orders of magnitude faster than the standard line-by-line-based simulations with averaged brightness temperature difference(BTD)less than 0.1 K,and the compressions based on PCA or NN methods result in comparable efficiency and accuracy.Our fast model not only avoids an excessively complicated transmittance scheme by using PCA/NN but is also highly flexible for hyperspectral instruments with similar spectral ranges simply by updating the corresponding spectral response functions.
基金the National Key R&D Program of China(No.2021YFC2900500).
文摘The efficient processing of large amounts of data collected by the microseismic monitoring system(MMS),especially the rapid identification of microseismic events in explosions and noise,is essential for mine disaster prevention.Currently,this work is primarily performed by skilled technicians,which results in severe workloads and inefficiency.In this paper,CNN-based transfer learning combined with computer vision technology was used to achieve automatic recognition and classification of multichannel microseismic signal waveforms.First,data collected by MMS was generated into 6-channel original waveforms based on events.After that,sample data sets of microseismic events,blasts,drillings,and noises were established through manual identification.These datasets were split into training sets and test sets according to a certain proportion,and transfer learning was performed on AlexNet,GoogLeNet,and ResNet50 pre-training network models,respectively.After training and tuning,optimal models were retained and compared with support vector machine classification.Results show that transfer learning models perform well on different test sets.Overall,GoogLeNet performed best,with a recognition accuracy of 99.8%.Finally,the possible effects of the number of training sets and the imbalance of different types of sample data on the accuracy and effectiveness of classification models were discussed.
文摘The article considers negative effects of mechanical oscillations of a fuselage on the flying machine autopilot. The dynamic model of control system of flight is made which provides stability and compensates the mechanical oscillations arising in flight of flying machine with the autopilot.
文摘With the progress of deep learning research, convolutional neural networks have become the most important method in feature extraction. How to effectively classify and recognize the extracted features will directly affect the performance of the entire network. Traditional processing methods include classification models such as fully connected network models and support vector machines. In order to solve the problem that the traditional convolutional neural network is prone to over-fitting for the classification of small samples, a CNN-TWSVM hybrid model was proposed by fusing the twin support vector machine (TWSVM) with higher computational efficiency as the CNN classifier, and it was applied to the traffic sign recognition task. In order to improve the generalization ability of the model, the wavelet kernel function is introduced to deal with the nonlinear classification task. The method uses the network initialized from the ImageNet dataset to fine-tune the specific domain and intercept the inner layer of the network to extract the high abstract features of the traffic sign image. Finally, the TWSVM based on wavelet kernel function is used to identify the traffic signs, so as to effectively solve the over-fitting problem of traffic signs classification. On GTSRB and BELGIUMTS datasets, the validity and generalization ability of the improved model is verified by comparing with different kernel functions and different SVM classifiers.
文摘Currently,breast cancer has been amajor cause of deaths in women worldwide and the World Health Organization(WHO)has confirmed this.The severity of this disease can be minimized to the large extend,if it is diagnosed properly at an early stage of the disease.Therefore,the proper treatment of a patient having cancer can be processed in better way,if it can be diagnosed properly as early as possible using the better algorithms.Moreover,it has been currently observed that the deep neural networks have delivered remarkable performance for detecting cancer in histopathological images of breast tissues.To address the above said issues,this paper presents a hybrid model using the transfer learning to study the histopathological images,which help in detection and rectification of the disease at a low cost.Extensive dataset experiments were carried out to validate the suggested hybrid model in this paper.The experimental results show that the proposed model outperformed the baseline methods,with F-scores of 0.81 for DenseNet+Logistic Regression hybrid model,(F-score:0.73)for Visual Geometry Group(VGG)+Logistic Regression hybrid model,(F-score:0.74)for VGG+Random Forest,(F-score:0.79)for DenseNet+Random Forest,and(F-score:0.79)for VGG+Densenet+Logistic Regression hybrid model on the dataset of histopathological images.
基金This work was supported by the Ministry of Science and Technology,Taiwan,under Grants MOST 111-2218-E-194-007.
文摘Cars are regarded as an indispensable means of transportation in Taiwan.Several studies have indicated that the automotive industry has witnessed remarkable advances and that the market of used cars has rapidly expanded.In this study,a price prediction system for used BMW cars was developed.Nine parameters of used cars,including their model,registration year,and transmission style,were analyzed.The data obtained were then divided into three subsets.The first subset was used to compare the results of each algorithm.The predicted values produced by the two algorithms with the most satisfactory results were used as the input of a fully connected neural network.The second subset was used with an optimization algorithm to modify the number of hidden layers in a fully connected neural network and modify the low,medium,and high parameters of the membership function(MF)to achieve model optimization.Finally,the third subset was used for the validation set during the prediction process.These three subsets were divided using k-fold cross-validation to avoid overfitting and selection bias.In conclusion,in this study,a model combining two optimal algorithms(i.e.,random forest and k-nearest neighbors)with several optimization algorithms(i.e.,gray wolf optimizer,multilayer perceptron,and MF)was successfully established.The prediction results obtained indicated a mean square error of 0.0978,a root-mean-square error of 0.3128,a mean absolute error of 0.1903,and a coefficient of determination of 0.9249.
文摘Coronavirus(COVID-19 or SARS-CoV-2)is a novel viral infection that started in December 2019 and has erupted rapidly in more than 150 countries.The rapid spread of COVID-19 has caused a global health emergency and resulted in governments imposing lock-downs to stop its transmission.There is a signifi-cant increase in the number of patients infected,resulting in a lack of test resources and kits in most countries.To overcome this panicked state of affairs,researchers are looking forward to some effective solutions to overcome this situa-tion:one of the most common and effective methods is to examine the X-radiation(X-rays)and computed tomography(CT)images for detection of Covid-19.How-ever,this method burdens the radiologist to examine each report.Therefore,to reduce the burden on the radiologist,an effective,robust and reliable detection system has been developed,which may assist the radiologist and medical specia-list in effective detecting of COVID.We proposed a deep learning approach that uses readily available chest radio-graphs(chest X-rays)to diagnose COVID-19 cases.The proposed approach applied transfer learning to the Deep Convolutional Neural Network(DCNN)model,Inception-v4,for the automatic detection of COVID-19 infection from chest X-rays images.The dataset used in this study contains 1504 chest X-ray images,504 images of COVID-19 infection,and 1000 normal images obtained from publicly available medical repositories.The results showed that the proposed approach detected COVID-19 infection with an overall accuracy of 99.63%.