Accurate and reliable prediction of exhaust emissions is crucial for combustion optimization control and environmental protection. This study proposes a novel ensemble deep learning model for exhaust emissions (NOx an...
详细信息
Accurate and reliable prediction of exhaust emissions is crucial for combustion optimization control and environmental protection. This study proposes a novel ensemble deep learning model for exhaust emissions (NOx and CO2) prediction. In this ensemble learning model, the stacked denoising autoencoder is established to extract the deep features of flame images. Four forecasting engines include artificial neural network, extreme learning machine, support vector machine and least squares support vector machine are employed for preliminary prediction of NOx and CO2 emissions based on the extracted image deep features. After that, these preliminary predictions are combined by Gaussian process regression in a nonlinear manner to achieve a final prediction of the emissions. The effectiveness of the proposed ensemble deep learning model is evaluated through 4.2 MW heavy oil-fired boiler flame images. Experimental results suggest that the predictions are achieved from the four forecasting engines are inconsistent, however, an accurate prediction accuracy has been achieved through the proposed model. The proposed ensemble deep learning model not only provides accurate point prediction but also generates satisfactory confidence interval.
To quickly respond to variations in the state of network load demand, a solution using data-driven techniques to predict optimal power flow (OPF) has emerged in recent years. However, most of the existing methods are ...
详细信息
To quickly respond to variations in the state of network load demand, a solution using data-driven techniques to predict optimal power flow (OPF) has emerged in recent years. However, most of the existing methods are highly dependent on large data volumes. This limits their application on the newly established or expanded systems. In this regard, this work proposes a sample-efficient OPF learning method to maximize the utilization of limited samples. By decomposing the OPF task before knowledge distillation, deep learning complexity is reduced. Thereafter, knowledge distillation is used to integrate decoupled tasks and improve accuracy in low-data setups. Unsupervised pre-training is introduced to alleviate the demand for labeled data. Additionally, the focal loss function and teacher annealing strategy are adopted to achieve higher accuracy without extra samples. Numerical tests on different systems corroborate the advanced accuracy and training speed over other training methods, especially on fewer-sample occasions.
It has been proved that long noncoding RNA (lncRNA) plays critical roles in many human diseases. Therefore, inferring associations between lncRNAs and diseases can contribute to disease diagnosis, prognosis and treatm...
详细信息
It has been proved that long noncoding RNA (lncRNA) plays critical roles in many human diseases. Therefore, inferring associations between lncRNAs and diseases can contribute to disease diagnosis, prognosis and treatment. To overcome the limitation of traditional experimental methods such as expensive and time-consuming, several computational methods have been proposed to predict lncRNA-disease associations by fusing different biological data. However, the prediction performance of lncRNA-disease associations identification needs to be improved. In this study, we propose a computational model (named LDICDL) to identify lncRNA-disease associations based on collaborative deep learning. It uses an automatic encoder to denoise multiple lncRNA feature information and multiple disease feature information, respectively. Then, the matrix decomposition algorithm is employed to predict the potential lncRNA-disease associations. In addition, to overcome the limitation of matrix decomposition, the hybrid model is developed to predict associations between new lncRNA (or disease) and diseases (or lncRNA). The ten-fold cross validation and de novo test are applied to evaluate the performance of method. The experimental results show LDICDL outperforms than other state-of-the-art methods in prediction performance.
The Citation Recommendation aims to address the problem of academic information overload by filtering and suggesting relevant references for researchers. Traditional content-based citation recommendation methods may n...
详细信息
ISBN:
(纸本)9783031402883;9783031402890
The Citation Recommendation aims to address the problem of academic information overload by filtering and suggesting relevant references for researchers. Traditional content-based citation recommendation methods may not be comprehensive enough to extract paper attributes that are essential for evaluating paper content similarity. To better use the abundant attributes and interaction information, the knowledge graph is introduced to recommendation system recently. We construct a multi-task learning-based model for citation recommendation that incorporates a knowledge graph, consisting of two primary tasks: citation recommendation and knowledge graph link prediction. To identify the interactions between papers, we propose a pseudointeraction matrix in the citation recommendation task. The knowledge graph link prediction task aids in identifying paper attribute information and enhancing representation. By automatically merging and sharing low-level features, exploring feature similarity, and enhancing the performance of both tasks, the multi-task learning framework can improve the final recommendation result significantly. Multiple experiments on the academic paper datasets AMiner and DBLP verify the effectiveness of our proposed model.
Accurate life prediction of lithium-ion batteries is important to help assess battery quality in advance, improve long-term battery planning, and subsequently guarantee the safety and reliability of battery operations...
详细信息
Accurate life prediction of lithium-ion batteries is important to help assess battery quality in advance, improve long-term battery planning, and subsequently guarantee the safety and reliability of battery operations. In this study, a deep learning-based stacked denoising autoencoder (SDAE) method is proposed to directly predict battery life by extracting various battery features. In general, the SDAE contains autoencoders and uses a deep network architecture to learn the complex nonlinear input-output relationship in a layer-by-layer fashion. Many features enabling the life prediction of lithium-ion batteries are extracted from discharge temperature and voltage curves. As redundancies in these features may result in poor prediction accuracy, a clustering by fast search (CFS) method is adopted to filter and select essential features. The CFS selects effective features by aggregating the types of battery features into clusters. All selected features are then fed into the SDAE to predict battery life cycle. Key hyperparameters are investigated, such as the number of iterations, the learning rate, and the denoising rate of the SDAE network. Experimental results show that the proposed selected-features-based deep learning method can provide more accurate and efficient battery life predictions with less fluctuation than the method without feature selection.
Wastewater treatment plants (WWTPs) influent conditions can dramatically affect a treatment unit's state and effluent quality. WWTP sensors may record faulty measurements due to abnormal events or the malfunction ...
详细信息
Wastewater treatment plants (WWTPs) influent conditions can dramatically affect a treatment unit's state and effluent quality. WWTP sensors may record faulty measurements due to abnormal events or the malfunction of the system, leading to serious problems in the system's operation and the violation of effluent discharge standards. Therefore, automatic fault detection and faulty data reconciliation are crucial for an efficient and stable WWTP monitoring. In this study, a holistic framework for sensor validation of WWTP influent conditions is presented considering the non-linearity, measurement noise, and complexity of the WWTP's data. A stacked denoising autoencoder (SDAE) model is proposed to detect, identify, and reconcile faulty data based on data from a real WWTP in South Korea. The proposed SDAE architecture presented a detection rate (DR) between 74% and 98%. The faulty sensor was identified using an SDAE-based sensor validity index (SVI). Data reconciliation showed that the SDAE was the most suitable reconciliation method based on the root mean square error (RMSE) for total nitrogen (TN) influent conditions of 4.04 mg N/L. Finally, faulty, noisy, and reconciled measurements were evaluated in a WWTP model to determine the proposed method's resilience potential.
Narrowband and broadband indoor radar images significantly deteriorate in the presence of target-dependent and target-independent static and dynamic clutter arising from walls. A stacked and sparse denoising autoencod...
详细信息
Narrowband and broadband indoor radar images significantly deteriorate in the presence of target-dependent and target-independent static and dynamic clutter arising from walls. A stacked and sparse denoisingautoencoder (stackedSDAE) is proposed for mitigating the wall clutter in indoor radar images. The algorithm relies on the availability of clean images and the corresponding noisy images during training and requires no additional information regarding the wall characteristics. The algorithm is evaluated on simulated Doppler-time spectrograms and high-range resolution profiles generated for diverse radar frequencies and wall characteristics in around-the-corner radar (ACR) scenarios. Additional experiments are performed on range-enhanced frontal images generated from measurements gathered from a wideband radio frequency imaging sensor. The results from the experiments show that the stackedSDAE successfully reconstructs images that closely resemble those that would be obtained in free space conditions. Furthermore, the incorporation of sparsity and depth in the hidden layer representations within the autoencoder makes the algorithm more robust to low signal-to-noise ratio (SNR) and label mismatch between clean and corrupt data during training than the conventional single-layer DAE. For example, the denoised ACR signatures show a structural similarity above 0.75 to clean free space images at SNR of -10 dB and label mismatch error of 50%.
Accurate fault prediction of rolling bearing can predict the operation condition in advance, which is an important means to ensure the safety and reliability of rotating machinery. Aimed at the data processing of roll...
详细信息
Accurate fault prediction of rolling bearing can predict the operation condition in advance, which is an important means to ensure the safety and reliability of rotating machinery. Aimed at the data processing of rolling bearing vibration signal with multi-fault and long time series, an intelligent fault prediction model based on gate recurrent unit and hybrid autoencoder is proposed in this paper. Firstly, vibration signals of multi-faults are brought into multi-layer gate recurrent unit model for multi-step and multi-variable time series prediction. Secondly, variational autoencoder is used for data augmentation of fault samples. Thirdly, the augmented fault samples are brought into stacked denoising autoencoder for noise reduction and fault prediction. Finally, fault prediction results of rolling bearing can be achieved on the basis of gate recurrent unit and hybrid autoencoder of variational autoencoder and stacked denoising autoencoder. The bearing datasets of Case Western Reserve University are used to verify the effectiveness of the proposed method. Comparative experiment results show that the proposed fault prediction model has more accurate time series prediction result and higher fault prediction accuracy than other deep learning models. With 98.68% accuracy of fault prediction, the proposed fault prediction model can be taken as an effective tool for intelligent predictive maintenance of rolling bearing.
When recognizing multi-class motor imagery electoencephalogram (EEG) signals directly using stacked denoising autoencoders (SDA), it is difficult to fully train the weights due to the small sample size, which results ...
详细信息
When recognizing multi-class motor imagery electoencephalogram (EEG) signals directly using stacked denoising autoencoders (SDA), it is difficult to fully train the weights due to the small sample size, which results in poor classification effect. To overcome this problem, the multi-scale recurrence plot and SDA method are combined to extract features of multi-class motor imagery EEG signals for recognition. Firstly, multi-class motor imagery EEG signals are decomposed into a series of intrinsic mode functions (IMFs) with different scale by synchrosqueezed wavelet transform, and the recurrence plot of each IMF is constructed to form one-level feature data as input samples of SDA. Then, high-level abstract features which can better express category attributes are extracted from multi-scale recurrence plot by SDA. Finally, EEG signals are classified by using Softmax classifier. Four types of motor imagery EEG data of Datasets 2a in BCI Competition IV are used to verify the proposed method. The average classification accuracy is 0.89, which shows that the proposed method has good effectiveness and robustness.
Grape shelf-life estimation is a substantial challenge for the grape industry. The objective of this study is to investigate the potential of grape shelf-life estimation using HSI technique and a deep learning algorit...
详细信息
Grape shelf-life estimation is a substantial challenge for the grape industry. The objective of this study is to investigate the potential of grape shelf-life estimation using HSI technique and a deep learning algorithm. The visible and near-infrared (400.68-1001.61 nm) hyperspectral reflectance images data of grape samples was acquired and preprocessed with different spectral preprocessing methods. Additionally, a stacked denoising autoencoder (SDAE)-based deep learning algorithm was developed to extract deep features from pixel-level hyperspectral data of grapes, and then these features were used as inputs to establish support vector machine (SVM) models for estimating grape shelf-life. Furthermore, SVM, one-dimensional convolutional neural network (1D CNN) and long short-term memory (LSTM) models were used as traditional machine learning and end to end models for comparison. The results demonstrated that the SDAE-SVM model achieved reasonable recognition accuracy of 100 % and 98.125 % for the shelf-life of grapes in the training and test sets, respectively. The overall results suggested that SDAE-based deep learning method can be used as a powerful tool to deal with large-scale hyperspectral data as well as this research confirms the feasibility of non-destructive estimation for grapes shelflife by the combination of HSI technique and deep learning method, which would provide a valuable guidance for shelf-life estimation of other postharvest fruit.
暂无评论