This research focuses on using BIM modeling optimization to control construction-period risks in the pre-construction stage of industrial factory buildings.It analyzes common risk factors and limitations of traditiona...This research focuses on using BIM modeling optimization to control construction-period risks in the pre-construction stage of industrial factory buildings.It analyzes common risk factors and limitations of traditional approaches.BIM-based methods like collision detection,4D simulation,multi-dimensional data integration,etc.,can effectively mitigate risks.Stakeholder collaboration,digital twin testing,and lean BIM integration is also crucial.Case studies show BIM can reduce risks by 32-41%,with a three phase roadmap provided.展开更多
Theauthor proposes a dual layer source grid load storage collaborative planning model based on Benders decomposition to optimize the low-carbon and economic performance of the distribution network.The model plans the ...Theauthor proposes a dual layer source grid load storage collaborative planning model based on Benders decomposition to optimize the low-carbon and economic performance of the distribution network.The model plans the configuration of photovoltaic(3.8 MW),wind power(2.5 MW),energy storage(2.2 MWh),and SVC(1.2 Mvar)through interaction between upper and lower layers,and modifies lines 2–3,8–9,etc.to improve transmission capacity and voltage stability.The author uses normal distribution and Monte Carlo method to model load uncertainty,and combines Weibull distribution to describe wind speed characteristics.Compared to the traditional three-layer model(TLM),Benders decomposition-based two-layer model(BLBD)has a 58.1%reduction in convergence time(5.36 vs.12.78 h),a 51.1%reduction in iteration times(23 vs.47 times),a 8.07%reduction in total cost(12.436 vs.13.528 million yuan),and a 9.62%reduction in carbon emissions(12,456 vs.13,782 t).After optimization,the peak valley difference decreased from4.1 to 2.9MW,the renewable energy consumption rate reached 93.4%,and the energy storage efficiency was 87.6%.Themodel has been validated in the IEEE 33 node system,demonstrating its superiority in terms of economy,low-carbon,and reliability.展开更多
High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of ...High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.展开更多
Electric vehicle is a kind of new energy vehicle which uses batteries as energy supply unit.A huge gap in charging infrastructures will be created by the expansion of electric vehicles.The effectiveness and rationalit...Electric vehicle is a kind of new energy vehicle which uses batteries as energy supply unit.A huge gap in charging infrastructures will be created by the expansion of electric vehicles.The effectiveness and rationality of charging facilities will directly affect the convenience and economy of the users,as well as the safe operation of the power grid.Three types of charging facilities:charging pile,charging station and battery swap station are introduced in this paper.According to the different methods of charging infrastructure planning,the research status of the method of determining charging demand points is expounded.And the spatial distribution of charging demand points extracted by the current site selection method has a certain deviation.Then the models and algorithms of charging infrastructure optimized layout are reviewed.Currently,many researches focus on three categories optimization objectives:benefit of power company side,investment cost of charging facility and user side cost,and the genetic algorithm and particle swarm optimization are the main solving algorithms.Finally,the relative methods and development trend of the charging infrastructures optimized layout are summarized,and some suggestions on the optimized layout of electric vehicle charging infrastructures are given forward.展开更多
Objective:Emerging studies have demonstrated the promising clinical value of circulating tumor cells(CTCs)for diagnosis,disease assessment,treatment monitoring and prognosis in epithelial ovarian cancer.However,the cl...Objective:Emerging studies have demonstrated the promising clinical value of circulating tumor cells(CTCs)for diagnosis,disease assessment,treatment monitoring and prognosis in epithelial ovarian cancer.However,the clinical application of CTC remains restricted due to diverse detection techniques with variable sensitivity and specificity and a lack of common standards.Methods:We enrolled 160 patients with epithelial ovarian cancer as the experimental group,and 90 patients including 50 patients with benign ovarian tumor and 40 healthy females as the control group.We enriched CTCs with immunomagnetic beads targeting two epithelial cell surface antigens(EpCAM and MUC1),and used multiple reverse transcription-polymerase chain reaction(RT-PCR)detecting three markers(EpCAM,MUC1 and WT1)for quantification.And then we used a binary logistic regression analysis and focused on EpCAM,MUC1 and WT1 to establish an optimized CTC detection model.Results:The sensitivity and specificity of the optimized model is 79.4%and 92.2%,respectively.The specificity of the CTC detection model is significantly higher than CA125(92.2%vs.82.2%,P=0.044),and the detection rate of CTCs was higher than the positive rate of CA125(74.5%vs.58.2%,P=0.069)in early-stage patients(stage I and II).The detection rate of CTCs was significantly higher in patients with ascitic volume≥500 mL,suboptimal cytoreductive surgery and elevated serum CA125 level after 2 courses of chemotherapy(P<0.05).The detection rate of CTC;and CTC;was significantly higher in chemo-resistant patients(26.3%vs.11.9%;26.4%vs.13.4%,P<0.05).The median progression-free survival time for CTC;patients trended to be longer than CTC;patients,and overall survival was shorter in CTC;patients(P=0.043).Conclusions:Our study presents an optimized detection model for CTCs,which consists of the expression levels of three markers(EpCAM,MUC1 and WT1).In comparison with CA125,our model has high specificity and demonstrates better diagnostic values,especially for early-stage ovarian cancer.Detection of CTC;and CTC;had predictive value for chemotherapy resistance,and the detection of CTC;suggested poor prognosis.展开更多
A novel and effective artificial neural network(ANN) optimized using differential evolution(DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters.The proposed computation...A novel and effective artificial neural network(ANN) optimized using differential evolution(DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters.The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters(i.e.the epoch size,the number of neurons in a hidden layer,the number of hidden layers,and the regularization parameter) that govern the neural network efficacy.This approach is further enhanced by a stochastic gradient optimization algorithm to allow ’expensive’ computation efforts.The ANN-DE is first trained using a prepared jet grouting dataset,then verified and compared with the prevalent machine learning tools,i.e.neural networks and support vector machine(SVM).The results show that,the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance.Specifically,the ANN-DE achieved root mean square error(RMSE)values of 0.90603 and 0.92813 for the training and testing phases,respectively.The corresponding values were 0.8905 and 0.9006 for the optimized ANN,then,0.87569 and 0.89968 for the optimized SVM,respectively.The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.展开更多
Emotions serve various functions.The traditional emotion recognition methods are based primarily on readily accessible facial expressions,gestures,and voice signals.However,it is often challenging to ensure that these...Emotions serve various functions.The traditional emotion recognition methods are based primarily on readily accessible facial expressions,gestures,and voice signals.However,it is often challenging to ensure that these non-physical signals are valid and reliable in practical applications.Electroencephalogram(EEG)signals are more successful than other signal recognition methods in recognizing these characteristics in real-time since they are difficult to camouflage.Although EEG signals are commonly used in current emotional recognition research,the accuracy is low when using traditional methods.Therefore,this study presented an optimized hybrid pattern with an attention mechanism(FFT_CLA)for EEG emotional recognition.First,the EEG signal was processed via the fast fourier transform(FFT),after which the convolutional neural network(CNN),long short-term memory(LSTM),and CNN-LSTM-attention(CLA)methods were used to extract and classify the EEG features.Finally,the experiments compared and analyzed the recognition results obtained via three DEAP dataset models,namely FFT_CNN,FFT_LSTM,and FFT_CLA.The final experimental results indicated that the recognition rates of the FFT_CNN,FFT_LSTM,and FFT_CLA models within the DEAP dataset were 87.39%,88.30%,and 92.38%,respectively.The FFT_CLA model improved the accuracy of EEG emotion recognition and used the attention mechanism to address the often-ignored importance of different channels and samples when extracting EEG features.展开更多
Employing machine learning techniques in predicting the parameters of metamaterial antennas has a significant impact on the reduction of the time needed to design an antenna with optimal parameters using simulation to...Employing machine learning techniques in predicting the parameters of metamaterial antennas has a significant impact on the reduction of the time needed to design an antenna with optimal parameters using simulation tools.In this paper,we propose a new approach for predicting the bandwidth of metamaterial antenna using a novel ensemble model.The proposed ensemble model is composed of two levels of regression models.The first level consists of three strong models namely,random forest,support vector regression,and light gradient boosting machine.Whereas the second level is based on the ElasticNet regression model,which receives the prediction results from the models in the first level for refinement and producing the final optimal result.To achieve the best performance of these regression models,the advanced squirrel search optimization algorithm(ASSOA)is utilized to search for the optimal set of hyper-parameters of each model.Experimental results show that the proposed two-level ensemble model could achieve a robust prediction of the bandwidth of metamaterial antenna when compared with the recently published ensemble models based on the same publicly available benchmark dataset.The findings indicate that the proposed approach results in root mean square error(RMSE)of(0.013),mean absolute error(MAE)of(0.004),and mean bias error(MBE)of(0.0017).These results are superior to the other competing ensemble models and can predict the antenna bandwidth more accurately.展开更多
Applications of process systems engineering(PSE)in plants and enterprises are boosting industrial reform from automation to digitization and intelligence.For ethylene thermal cracking,knowledge expression,numerical mo...Applications of process systems engineering(PSE)in plants and enterprises are boosting industrial reform from automation to digitization and intelligence.For ethylene thermal cracking,knowledge expression,numerical modeling and intelligent optimization are key steps for intelligent manufacturing.This paper provides an overview of progress and contributions to the PSE-aided production of thermal cracking;introduces the frameworks,methods and algorithms that have been proposed over the past10 years and discusses the advantages,limitations and applications in industrial practice.An entire set of molecular-level modeling approaches from feedstocks to products,including feedstock molecular reconstruction,reaction-network auto-generation and cracking unit simulation are described.Multilevel control and optimization methods are exhibited,including at the operational,cycle,plant and enterprise level.Relevant software packages are introduced.Finally,an outlook in terms of future directions is presented.展开更多
An optimized nonlinear grey Bernoulli model was proposed by using a particle swarm optimization algorithm to solve the parameter optimization problem. In addition, each item in the first-order accumulated generating s...An optimized nonlinear grey Bernoulli model was proposed by using a particle swarm optimization algorithm to solve the parameter optimization problem. In addition, each item in the first-order accumulated generating sequence was set in turn as an initial condition to determine which alternative would yield the highest forecasting accuracy. To test the forecasting performance, the optimized models with different initial conditions were then used to simulate dissolved oxygen concentrations in the Guantlng reservoir inlet and outlet （China）. The empirical results show that the optimized model can remarkably improve forecasting accuracy, and the particle swarm optimization technique is a good tool to solve parameter optimization problems. What＇s more, the optimized model with an initial condition that performs well in in-sample simulation may not do as well as in out-of-sample forecasting.展开更多
Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid...Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybrid model. Therefore, a simultaneous hybrid modeling approach is presented in this paper. It transforms the training of the empirical model part into a dynamic system parameter identification problem, and thus allows training the empirical model part with only measured data. An adaptive escaping particle swarm optimization(AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.展开更多
An effort to model the dynamic optimal advertising was made with the uncertainty of sales responses in consideration. The problem of dynamic advertising was depicted as a Markov decision process with two state variabl...An effort to model the dynamic optimal advertising was made with the uncertainty of sales responses in consideration. The problem of dynamic advertising was depicted as a Markov decision process with two state variables. When a firm launches an advertising campaign, it may predict the probability that the campaign will obtain the sales réponse. This probability was chosen as one state variable. Cumulative sales volume was chosen as another state variable which varies randomly with advertising. The only decision variable was advertising expenditure. With these variables, a multi-stage Markov decision process model was formulat ed. On the basis of some propositions the model was analyzed. Some analytical results about the optimal strategy have been derived, and their practical implications have been explained.展开更多
The supersonic oxygen supply technology, including the coherent supersonic jet and the conventional supersonic jet, is now widely adopted in electric arc furnace steelmaking process to increase the bath stirring, reac...The supersonic oxygen supply technology, including the coherent supersonic jet and the conventional supersonic jet, is now widely adopted in electric arc furnace steelmaking process to increase the bath stirring, reaction rates and energy efficiency. However, there has been limited study on the impact characteristics of the coherent supersonic jet and the conventional supersonic jet. Thus, integrating theoretical models and numerical simulations, an optimized theoretical model was developed to calculate the volume of the impact zone generated by coherent and conventional supersonic jets. The optimized theoretical model was validated by water model experiments. The results show that the jet impact zone volume with coherent supersonic jet is much larger than that with conventional supersonic jet at the same lance height. The kd value, a newly defined variable that is the product of the dimensionless quantity of velocity and free distance, reflects the velocity attenuation and the potential core length of the main supersonic jet, which is a key parameter of the optimized theoretical model. The optimized theoretical model can well predict the jet impact zone volumes of coherent and conventional supersonic jets with the error no more than 3.62 and 9.37%, respectively.展开更多
Through the study of mutual process between groundwater systems and eco-environmental water demand, the eco-environmental water demand is brought into groundwater systems model as the important water consumption item ...Through the study of mutual process between groundwater systems and eco-environmental water demand, the eco-environmental water demand is brought into groundwater systems model as the important water consumption item and unification of groundwater抯 economic, environmental and ecological functions were taken into account. Based on eco-environmental water demand at Da抋n in Jilin province, a three-dimensional simulation and optimized management model of groundwater systems was established. All water balance components of groundwater systems in 1998 and 1999 were simulated with this model and the best optimal exploitation scheme of groundwater systems in 2000 was determined, so that groundwater resource was efficiently utilized and good economic, ecologic and social benefits were obtained.展开更多
This paper demonstrates empirical research on using convolutional neural networks(CNN)of deep learning techniques to classify X-rays of COVID-19 patients versus normal patients by feature extraction.Feature extraction...This paper demonstrates empirical research on using convolutional neural networks(CNN)of deep learning techniques to classify X-rays of COVID-19 patients versus normal patients by feature extraction.Feature extraction is one of the most significant phases for classifying medical X-rays radiography that requires inclusive domain knowledge.In this study,CNN architectures such as VGG-16,VGG-19,RestNet50,RestNet18 are compared,and an optimized model for feature extraction in X-ray images from various domains invol-ving several classes is proposed.An X-ray radiography classifier with TensorFlow GPU is created executing CNN architectures and our proposed optimized model for classifying COVID-19(Negative or Positive).Then,2,134 X-rays of normal patients and COVID-19 patients generated by an existing open-source online dataset were labeled to train the optimized models.Among those,the optimized model architecture classifier technique achieves higher accuracy(0.97)than four other models,specifically VGG-16,VGG-19,RestNet18,and RestNet50(0.96,0.72,0.91,and 0.93,respectively).Therefore,this study will enable radiol-ogists to more efficiently and effectively classify a patient’s coronavirus disease.展开更多
In Internet of Things (IoT), large amount of data are processed andcommunicated through different network technologies. Wireless Body Area Networks (WBAN) plays pivotal role in the health care domain with an integrati...In Internet of Things (IoT), large amount of data are processed andcommunicated through different network technologies. Wireless Body Area Networks (WBAN) plays pivotal role in the health care domain with an integration ofIoT and Artificial Intelligence (AI). The amalgamation of above mentioned toolshas taken the new peak in terms of diagnosis and treatment process especially inthe pandemic period. But the real challenges such as low latency, energy consumption high throughput still remains in the dark side of the research. This paperproposes a novel optimized cognitive learning based BAN model based on FogIoT technology as a real-time health monitoring systems with the increased network-life time. Energy and latency aware features of BAN have been extractedand used to train the proposed fog based learning algorithm to achieve low energyconsumption and low-latency scheduling algorithm. To test the proposed network,Fog-IoT-BAN test bed has been developed with the battery driven MICOTTboards interfaced with the health care sensors using Micro Python programming.The extensive experimentation is carried out using the above test beds and variousparameters such as accuracy, precision, recall, F1score and specificity has beencalculated along with QoS (quality of service) parameters such as latency, energyand throughput. To prove the superiority of the proposed framework, the performance of the proposed learning based framework has been compared with theother state-of-art classical learning frameworks and other existing Fog-BAN networks such as WORN, DARE, L-No-DEAF networks. Results proves the proposed framework has outperformed the other classical learning models in termsof accuracy and high False Alarm Rate (FAR), energy efficiency and latency.展开更多
In power plants,flue gases can cause severe corrosion damage in metallic parts such as flue ducts,heat exchangers,and boilers.Coating is an effective technique to prevent this damage.A robust fuzzy model of the surfac...In power plants,flue gases can cause severe corrosion damage in metallic parts such as flue ducts,heat exchangers,and boilers.Coating is an effective technique to prevent this damage.A robust fuzzy model of the surface roughness(Ra and Rz)of flue gas ducts coated by protective composite coating from epoxy and nanoparticles was constructed based on the experimental dataset.The proposed model consists of four nanoparticles(ZnO,ZrO2,SiO2,and NiO)with 2%,4%,6%,and 8%,respectively.Response surface methodology(RSM)was used to optimize the process parameters and identify the optimal conditions for minimum surface roughness of this coated duct.To prove the superiority of the proposed fuzzy model,the model results were compared with those obtained by ANOVA,with the coefficient of determination and the root-mean-square error(RMSE)used as metrics.For Ra,for the first output response,using ANOVA,the coefficient-of-determination values were 0.9137 and 0.4037,respectively,for training and prediction.Similarly,for Rz,the second output response,the coefficient-of-determination results were 0.9695 and 0.4037,respectively,for training and prediction.In the fuzzy modeling of Ra,for the first output response,the RMSE values were 0.0 and 0.1455,respectively,for training and testing.The values for the coefficient of determination were 1.00 and 0.9807,respectively,for training and testing.The results prove the superiority of fuzzy modeling.For modeling the second output response Rz,the RMSE values were 0.0 and 0.0421,respectively,for training and testing,and the coefficient-of-determination values were 1.00 and 0.9959,respectively,for training and testing.展开更多
To enhance system stability,solar collectors have been integrated with air-source heat pumps.This integration facilitates the concurrent utilization of solar and air as energy sources for the system,leading to an impr...To enhance system stability,solar collectors have been integrated with air-source heat pumps.This integration facilitates the concurrent utilization of solar and air as energy sources for the system,leading to an improvement in the system’s heat generation coefficient,overall efficiency,and stability.In this study,we focus on a residential building located in Lhasa as the target for heating purposes.Initially,we simulate and analyze a solar-air source heat pump combined heating system.Subsequently,while ensuring the system meets user requirements,we examine the influence of solar collector installation angles and collector area on the performance of the solar-air source heat pump dual heating system.Through this analysis,we determine the optimal installation angle and collector area to optimize system performance.展开更多
In this paper, we conduct research on the multidimensional constraint stability of bridge structure modeling based on the optimization model. The current internal and the external research results to the truss web str...In this paper, we conduct research on the multidimensional constraint stability of bridge structure modeling based on the optimization model. The current internal and the external research results to the truss web structure, the high internode the aspect ratio and the stiffness of the middle truss brace of the truss web, deffection of composite beams of the impact of stress is a very important problem in the design of the bridge. Structural health monitoring is the use of the field of the non-destructive sensing technology, including the structural response, including structural system characteristics analysis, to achieve the purpose of monitoring structural damage or degradation. Under this basis, this paper proposes the new idea on the modelling and simulates the performance.展开更多
Taking the rubber torsion bushing of a certain type of all-terrain tracked vehicle as the research object,a theoretical model of torsional stiffness was proposed according to the non-linear characteristics of rubber c...Taking the rubber torsion bushing of a certain type of all-terrain tracked vehicle as the research object,a theoretical model of torsional stiffness was proposed according to the non-linear characteristics of rubber components and structural feature of the suspension. Simulations were carried out under different working conditions to obtain root mean square of vertical weighted acceleration as the evaluation index for ride performance of the all-terrain tracked vehicle,with a dynamics model of the whole vehicle based on the theoretical model of the torsional stiffness and standard road roughness as excitation input. Response surface method was used to establish the parametric optimization model of the torsional stiffness. The evaluation index showed that ride performance of the vehicle with optimized torsional stiffness model of suspension was improved compared with previous model fromexperiment. The torsional stiffness model of rubber bushing provided a theoretical basis for the design of the rubber torsion bushing in light tracked vehicles.展开更多
文摘This research focuses on using BIM modeling optimization to control construction-period risks in the pre-construction stage of industrial factory buildings.It analyzes common risk factors and limitations of traditional approaches.BIM-based methods like collision detection,4D simulation,multi-dimensional data integration,etc.,can effectively mitigate risks.Stakeholder collaboration,digital twin testing,and lean BIM integration is also crucial.Case studies show BIM can reduce risks by 32-41%,with a three phase roadmap provided.
文摘Theauthor proposes a dual layer source grid load storage collaborative planning model based on Benders decomposition to optimize the low-carbon and economic performance of the distribution network.The model plans the configuration of photovoltaic(3.8 MW),wind power(2.5 MW),energy storage(2.2 MWh),and SVC(1.2 Mvar)through interaction between upper and lower layers,and modifies lines 2–3,8–9,etc.to improve transmission capacity and voltage stability.The author uses normal distribution and Monte Carlo method to model load uncertainty,and combines Weibull distribution to describe wind speed characteristics.Compared to the traditional three-layer model(TLM),Benders decomposition-based two-layer model(BLBD)has a 58.1%reduction in convergence time(5.36 vs.12.78 h),a 51.1%reduction in iteration times(23 vs.47 times),a 8.07%reduction in total cost(12.436 vs.13.528 million yuan),and a 9.62%reduction in carbon emissions(12,456 vs.13,782 t).After optimization,the peak valley difference decreased from4.1 to 2.9MW,the renewable energy consumption rate reached 93.4%,and the energy storage efficiency was 87.6%.Themodel has been validated in the IEEE 33 node system,demonstrating its superiority in terms of economy,low-carbon,and reliability.
基金supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(RS-2020-NR049579).
文摘High-dimensional data causes difficulties in machine learning due to high time consumption and large memory requirements.In particular,in amulti-label environment,higher complexity is required asmuch as the number of labels.Moreover,an optimization problem that fully considers all dependencies between features and labels is difficult to solve.In this study,we propose a novel regression-basedmulti-label feature selectionmethod that integrates mutual information to better exploit the underlying data structure.By incorporating mutual information into the regression formulation,the model captures not only linear relationships but also complex non-linear dependencies.The proposed objective function simultaneously considers three types of relationships:(1)feature redundancy,(2)featurelabel relevance,and(3)inter-label dependency.These three quantities are computed usingmutual information,allowing the proposed formulation to capture nonlinear dependencies among variables.These three types of relationships are key factors in multi-label feature selection,and our method expresses them within a unified formulation,enabling efficient optimization while simultaneously accounting for all of them.To efficiently solve the proposed optimization problem under non-negativity constraints,we develop a gradient-based optimization algorithm with fast convergence.Theexperimental results on sevenmulti-label datasets show that the proposed method outperforms existingmulti-label feature selection techniques.
基金Project(21805217)supported by the National Natural Science Foundation of ChinaProject(2015BAG08B02)supported by the National Key Technologies Research and Development Program of ChinaProject(2019IVB014)supported by the Fundamental Research Funds for the Central Universities,China。
文摘Electric vehicle is a kind of new energy vehicle which uses batteries as energy supply unit.A huge gap in charging infrastructures will be created by the expansion of electric vehicles.The effectiveness and rationality of charging facilities will directly affect the convenience and economy of the users,as well as the safe operation of the power grid.Three types of charging facilities:charging pile,charging station and battery swap station are introduced in this paper.According to the different methods of charging infrastructure planning,the research status of the method of determining charging demand points is expounded.And the spatial distribution of charging demand points extracted by the current site selection method has a certain deviation.Then the models and algorithms of charging infrastructure optimized layout are reviewed.Currently,many researches focus on three categories optimization objectives:benefit of power company side,investment cost of charging facility and user side cost,and the genetic algorithm and particle swarm optimization are the main solving algorithms.Finally,the relative methods and development trend of the charging infrastructures optimized layout are summarized,and some suggestions on the optimized layout of electric vehicle charging infrastructures are given forward.
文摘Objective:Emerging studies have demonstrated the promising clinical value of circulating tumor cells(CTCs)for diagnosis,disease assessment,treatment monitoring and prognosis in epithelial ovarian cancer.However,the clinical application of CTC remains restricted due to diverse detection techniques with variable sensitivity and specificity and a lack of common standards.Methods:We enrolled 160 patients with epithelial ovarian cancer as the experimental group,and 90 patients including 50 patients with benign ovarian tumor and 40 healthy females as the control group.We enriched CTCs with immunomagnetic beads targeting two epithelial cell surface antigens(EpCAM and MUC1),and used multiple reverse transcription-polymerase chain reaction(RT-PCR)detecting three markers(EpCAM,MUC1 and WT1)for quantification.And then we used a binary logistic regression analysis and focused on EpCAM,MUC1 and WT1 to establish an optimized CTC detection model.Results:The sensitivity and specificity of the optimized model is 79.4%and 92.2%,respectively.The specificity of the CTC detection model is significantly higher than CA125(92.2%vs.82.2%,P=0.044),and the detection rate of CTCs was higher than the positive rate of CA125(74.5%vs.58.2%,P=0.069)in early-stage patients(stage I and II).The detection rate of CTCs was significantly higher in patients with ascitic volume≥500 mL,suboptimal cytoreductive surgery and elevated serum CA125 level after 2 courses of chemotherapy(P<0.05).The detection rate of CTC;and CTC;was significantly higher in chemo-resistant patients(26.3%vs.11.9%;26.4%vs.13.4%,P<0.05).The median progression-free survival time for CTC;patients trended to be longer than CTC;patients,and overall survival was shorter in CTC;patients(P=0.043).Conclusions:Our study presents an optimized detection model for CTCs,which consists of the expression levels of three markers(EpCAM,MUC1 and WT1).In comparison with CA125,our model has high specificity and demonstrates better diagnostic values,especially for early-stage ovarian cancer.Detection of CTC;and CTC;had predictive value for chemotherapy resistance,and the detection of CTC;suggested poor prognosis.
基金funded by“The Pearl River Talent Recruitment Program”in 2019 for Professor Shui-Long Shen(Grant No.2019CX01G338),Guangdong Provincethe Research Funding of Shantou University for New Faculty Member(Grant No.NTF19024-2019)。
文摘A novel and effective artificial neural network(ANN) optimized using differential evolution(DE) is first introduced to provide a robust and reliable forecasting of jet grouted column diameters.The proposed computational method adopts the DE algorithm to tackle the difficulties in the training and performance of neural networks and optimize the four quintessential hyper-parameters(i.e.the epoch size,the number of neurons in a hidden layer,the number of hidden layers,and the regularization parameter) that govern the neural network efficacy.This approach is further enhanced by a stochastic gradient optimization algorithm to allow ’expensive’ computation efforts.The ANN-DE is first trained using a prepared jet grouting dataset,then verified and compared with the prevalent machine learning tools,i.e.neural networks and support vector machine(SVM).The results show that,the ANN-DE outperforms the existing methods for predicting the diameter of jet grouting columns since it well balances training efficiency and model performance.Specifically,the ANN-DE achieved root mean square error(RMSE)values of 0.90603 and 0.92813 for the training and testing phases,respectively.The corresponding values were 0.8905 and 0.9006 for the optimized ANN,then,0.87569 and 0.89968 for the optimized SVM,respectively.The proposed paradigm is bound to be useful for solving various geotechnical engineering problems regardless of multi-dimension and nonlinearity.
基金This work was supported by the National Nature Science Foundation of China(No.61503423,H.P.Jiang).The URL is http://www.nsfc.gov.cn/.
文摘Emotions serve various functions.The traditional emotion recognition methods are based primarily on readily accessible facial expressions,gestures,and voice signals.However,it is often challenging to ensure that these non-physical signals are valid and reliable in practical applications.Electroencephalogram(EEG)signals are more successful than other signal recognition methods in recognizing these characteristics in real-time since they are difficult to camouflage.Although EEG signals are commonly used in current emotional recognition research,the accuracy is low when using traditional methods.Therefore,this study presented an optimized hybrid pattern with an attention mechanism(FFT_CLA)for EEG emotional recognition.First,the EEG signal was processed via the fast fourier transform(FFT),after which the convolutional neural network(CNN),long short-term memory(LSTM),and CNN-LSTM-attention(CLA)methods were used to extract and classify the EEG features.Finally,the experiments compared and analyzed the recognition results obtained via three DEAP dataset models,namely FFT_CNN,FFT_LSTM,and FFT_CLA.The final experimental results indicated that the recognition rates of the FFT_CNN,FFT_LSTM,and FFT_CLA models within the DEAP dataset were 87.39%,88.30%,and 92.38%,respectively.The FFT_CLA model improved the accuracy of EEG emotion recognition and used the attention mechanism to address the often-ignored importance of different channels and samples when extracting EEG features.
基金The authors received funding for this study from the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number(IFP2021-033).
文摘Employing machine learning techniques in predicting the parameters of metamaterial antennas has a significant impact on the reduction of the time needed to design an antenna with optimal parameters using simulation tools.In this paper,we propose a new approach for predicting the bandwidth of metamaterial antenna using a novel ensemble model.The proposed ensemble model is composed of two levels of regression models.The first level consists of three strong models namely,random forest,support vector regression,and light gradient boosting machine.Whereas the second level is based on the ElasticNet regression model,which receives the prediction results from the models in the first level for refinement and producing the final optimal result.To achieve the best performance of these regression models,the advanced squirrel search optimization algorithm(ASSOA)is utilized to search for the optimal set of hyper-parameters of each model.Experimental results show that the proposed two-level ensemble model could achieve a robust prediction of the bandwidth of metamaterial antenna when compared with the recently published ensemble models based on the same publicly available benchmark dataset.The findings indicate that the proposed approach results in root mean square error(RMSE)of(0.013),mean absolute error(MAE)of(0.004),and mean bias error(MBE)of(0.0017).These results are superior to the other competing ensemble models and can predict the antenna bandwidth more accurately.
基金The authors gratefully acknowledge the National Natural Science Foundation of China for its financial support(U1462206).
文摘Applications of process systems engineering(PSE)in plants and enterprises are boosting industrial reform from automation to digitization and intelligence.For ethylene thermal cracking,knowledge expression,numerical modeling and intelligent optimization are key steps for intelligent manufacturing.This paper provides an overview of progress and contributions to the PSE-aided production of thermal cracking;introduces the frameworks,methods and algorithms that have been proposed over the past10 years and discusses the advantages,limitations and applications in industrial practice.An entire set of molecular-level modeling approaches from feedstocks to products,including feedstock molecular reconstruction,reaction-network auto-generation and cracking unit simulation are described.Multilevel control and optimization methods are exhibited,including at the operational,cycle,plant and enterprise level.Relevant software packages are introduced.Finally,an outlook in terms of future directions is presented.
基金supported by the National Natural Science Foundation of China (Nos. 51178018 and 71031001)
文摘An optimized nonlinear grey Bernoulli model was proposed by using a particle swarm optimization algorithm to solve the parameter optimization problem. In addition, each item in the first-order accumulated generating sequence was set in turn as an initial condition to determine which alternative would yield the highest forecasting accuracy. To test the forecasting performance, the optimized models with different initial conditions were then used to simulate dissolved oxygen concentrations in the Guantlng reservoir inlet and outlet （China）. The empirical results show that the optimized model can remarkably improve forecasting accuracy, and the particle swarm optimization technique is a good tool to solve parameter optimization problems. What＇s more, the optimized model with an initial condition that performs well in in-sample simulation may not do as well as in out-of-sample forecasting.
基金Supported by the Specialized Research Fund for the Doctoral Program of Higher Education(No.20120042120014)
文摘Hybrid modeling approaches have recently been investigated as an attractive alternative to model fermentation processes. Normally, these approaches require estimation data to train the empirical model part of a hybrid model. This may result in decreasing the generalization ability of the derived hybrid model. Therefore, a simultaneous hybrid modeling approach is presented in this paper. It transforms the training of the empirical model part into a dynamic system parameter identification problem, and thus allows training the empirical model part with only measured data. An adaptive escaping particle swarm optimization(AEPSO) algorithm with escaping and adaptive inertia weight adjustment strategies is constructed to solve the resulting parameter identification problem, and thereby accomplish the training of the empirical model part. The uniform design method is used to determine the empirical model structure. The proposed simultaneous hybrid modeling approach has been used in a lab-scale nosiheptide batch fermentation process. The results show that it is effective and leads to a more consistent model with better generalization ability when compared to existing ones. The performance of AEPSO is also demonstrated.
基金This work was supported by the National Natural Science Foundation(No.70271021).
文摘An effort to model the dynamic optimal advertising was made with the uncertainty of sales responses in consideration. The problem of dynamic advertising was depicted as a Markov decision process with two state variables. When a firm launches an advertising campaign, it may predict the probability that the campaign will obtain the sales réponse. This probability was chosen as one state variable. Cumulative sales volume was chosen as another state variable which varies randomly with advertising. The only decision variable was advertising expenditure. With these variables, a multi-stage Markov decision process model was formulat ed. On the basis of some propositions the model was analyzed. Some analytical results about the optimal strategy have been derived, and their practical implications have been explained.
文摘The supersonic oxygen supply technology, including the coherent supersonic jet and the conventional supersonic jet, is now widely adopted in electric arc furnace steelmaking process to increase the bath stirring, reaction rates and energy efficiency. However, there has been limited study on the impact characteristics of the coherent supersonic jet and the conventional supersonic jet. Thus, integrating theoretical models and numerical simulations, an optimized theoretical model was developed to calculate the volume of the impact zone generated by coherent and conventional supersonic jets. The optimized theoretical model was validated by water model experiments. The results show that the jet impact zone volume with coherent supersonic jet is much larger than that with conventional supersonic jet at the same lance height. The kd value, a newly defined variable that is the product of the dimensionless quantity of velocity and free distance, reflects the velocity attenuation and the potential core length of the main supersonic jet, which is a key parameter of the optimized theoretical model. The optimized theoretical model can well predict the jet impact zone volumes of coherent and conventional supersonic jets with the error no more than 3.62 and 9.37%, respectively.
基金The Key Project of the National Ninth-Five-Year Plan No. 96-004-02-09The 48Project of Ministry of Water Resources No. 985106The Project of Chinese Academy of Sciences
文摘Through the study of mutual process between groundwater systems and eco-environmental water demand, the eco-environmental water demand is brought into groundwater systems model as the important water consumption item and unification of groundwater抯 economic, environmental and ecological functions were taken into account. Based on eco-environmental water demand at Da抋n in Jilin province, a three-dimensional simulation and optimized management model of groundwater systems was established. All water balance components of groundwater systems in 1998 and 1999 were simulated with this model and the best optimal exploitation scheme of groundwater systems in 2000 was determined, so that groundwater resource was efficiently utilized and good economic, ecologic and social benefits were obtained.
文摘This paper demonstrates empirical research on using convolutional neural networks(CNN)of deep learning techniques to classify X-rays of COVID-19 patients versus normal patients by feature extraction.Feature extraction is one of the most significant phases for classifying medical X-rays radiography that requires inclusive domain knowledge.In this study,CNN architectures such as VGG-16,VGG-19,RestNet50,RestNet18 are compared,and an optimized model for feature extraction in X-ray images from various domains invol-ving several classes is proposed.An X-ray radiography classifier with TensorFlow GPU is created executing CNN architectures and our proposed optimized model for classifying COVID-19(Negative or Positive).Then,2,134 X-rays of normal patients and COVID-19 patients generated by an existing open-source online dataset were labeled to train the optimized models.Among those,the optimized model architecture classifier technique achieves higher accuracy(0.97)than four other models,specifically VGG-16,VGG-19,RestNet18,and RestNet50(0.96,0.72,0.91,and 0.93,respectively).Therefore,this study will enable radiol-ogists to more efficiently and effectively classify a patient’s coronavirus disease.
文摘In Internet of Things (IoT), large amount of data are processed andcommunicated through different network technologies. Wireless Body Area Networks (WBAN) plays pivotal role in the health care domain with an integration ofIoT and Artificial Intelligence (AI). The amalgamation of above mentioned toolshas taken the new peak in terms of diagnosis and treatment process especially inthe pandemic period. But the real challenges such as low latency, energy consumption high throughput still remains in the dark side of the research. This paperproposes a novel optimized cognitive learning based BAN model based on FogIoT technology as a real-time health monitoring systems with the increased network-life time. Energy and latency aware features of BAN have been extractedand used to train the proposed fog based learning algorithm to achieve low energyconsumption and low-latency scheduling algorithm. To test the proposed network,Fog-IoT-BAN test bed has been developed with the battery driven MICOTTboards interfaced with the health care sensors using Micro Python programming.The extensive experimentation is carried out using the above test beds and variousparameters such as accuracy, precision, recall, F1score and specificity has beencalculated along with QoS (quality of service) parameters such as latency, energyand throughput. To prove the superiority of the proposed framework, the performance of the proposed learning based framework has been compared with theother state-of-art classical learning frameworks and other existing Fog-BAN networks such as WORN, DARE, L-No-DEAF networks. Results proves the proposed framework has outperformed the other classical learning models in termsof accuracy and high False Alarm Rate (FAR), energy efficiency and latency.
文摘In power plants,flue gases can cause severe corrosion damage in metallic parts such as flue ducts,heat exchangers,and boilers.Coating is an effective technique to prevent this damage.A robust fuzzy model of the surface roughness(Ra and Rz)of flue gas ducts coated by protective composite coating from epoxy and nanoparticles was constructed based on the experimental dataset.The proposed model consists of four nanoparticles(ZnO,ZrO2,SiO2,and NiO)with 2%,4%,6%,and 8%,respectively.Response surface methodology(RSM)was used to optimize the process parameters and identify the optimal conditions for minimum surface roughness of this coated duct.To prove the superiority of the proposed fuzzy model,the model results were compared with those obtained by ANOVA,with the coefficient of determination and the root-mean-square error(RMSE)used as metrics.For Ra,for the first output response,using ANOVA,the coefficient-of-determination values were 0.9137 and 0.4037,respectively,for training and prediction.Similarly,for Rz,the second output response,the coefficient-of-determination results were 0.9695 and 0.4037,respectively,for training and prediction.In the fuzzy modeling of Ra,for the first output response,the RMSE values were 0.0 and 0.1455,respectively,for training and testing.The values for the coefficient of determination were 1.00 and 0.9807,respectively,for training and testing.The results prove the superiority of fuzzy modeling.For modeling the second output response Rz,the RMSE values were 0.0 and 0.0421,respectively,for training and testing,and the coefficient-of-determination values were 1.00 and 0.9959,respectively,for training and testing.
文摘To enhance system stability,solar collectors have been integrated with air-source heat pumps.This integration facilitates the concurrent utilization of solar and air as energy sources for the system,leading to an improvement in the system’s heat generation coefficient,overall efficiency,and stability.In this study,we focus on a residential building located in Lhasa as the target for heating purposes.Initially,we simulate and analyze a solar-air source heat pump combined heating system.Subsequently,while ensuring the system meets user requirements,we examine the influence of solar collector installation angles and collector area on the performance of the solar-air source heat pump dual heating system.Through this analysis,we determine the optimal installation angle and collector area to optimize system performance.
文摘In this paper, we conduct research on the multidimensional constraint stability of bridge structure modeling based on the optimization model. The current internal and the external research results to the truss web structure, the high internode the aspect ratio and the stiffness of the middle truss brace of the truss web, deffection of composite beams of the impact of stress is a very important problem in the design of the bridge. Structural health monitoring is the use of the field of the non-destructive sensing technology, including the structural response, including structural system characteristics analysis, to achieve the purpose of monitoring structural damage or degradation. Under this basis, this paper proposes the new idea on the modelling and simulates the performance.
文摘Taking the rubber torsion bushing of a certain type of all-terrain tracked vehicle as the research object,a theoretical model of torsional stiffness was proposed according to the non-linear characteristics of rubber components and structural feature of the suspension. Simulations were carried out under different working conditions to obtain root mean square of vertical weighted acceleration as the evaluation index for ride performance of the all-terrain tracked vehicle,with a dynamics model of the whole vehicle based on the theoretical model of the torsional stiffness and standard road roughness as excitation input. Response surface method was used to establish the parametric optimization model of the torsional stiffness. The evaluation index showed that ride performance of the vehicle with optimized torsional stiffness model of suspension was improved compared with previous model fromexperiment. The torsional stiffness model of rubber bushing provided a theoretical basis for the design of the rubber torsion bushing in light tracked vehicles.
