Domain Correction-Based Adaptive Extreme Learning Machine

In this work, a new adaptive extreme learning machine (ELM) neural network-based fuzzy controller is designed and simulated for implementing speed regulation in a permanent magnet synchronous motor. ELM is a neural model wherein the number of hidden neurons to be placed in the hidden layer is tuned during the process of neural network training itself. A new adaptive ELM model is developed for placing the number of hidden neurons in the hidden layer, and this new adaptive ELM is tuned with artificial bee colony (ABC) algorithm for optimizing its weight parameters and also the number of hidden neurons. Fuzzy proportional–integral (PI) controller is developed in this work in order to eliminate the steady-state error. The new adaptive ELM neural model optimized with ABC algorithm is applied to tune the input parameters of the fuzzy PI controller and also on optimizing the rules and fuzzy membership functions. The optimized adaptive ELM neural network-based fuzzy PI controller is utilized to investigate the speed regulation of permanent magnet synchronous motor (PMSM) in this work. The developed new PI controller with the PMSM is tested for its performance characteristics and to prove its validity is compared with the traditional controller and other heuristic controllers proposed in earlier literature works.

For Pichia pastoris fermentation process with multi-operating conditions, it is difficult to predict the cell concentration under the new operating conditions by the soft sensor model established under the specific operating conditions. Inspired by the idea of transfer learning, a method based on an improved balanced distribution adaptive regularization extreme learning machine (IBDA-RELM) was proposed to solve the problem. The domain adaptation (DA) method in transfer learning is developed to reduce distribution distance by transforming data. However, the joint distribution adaptation (JDA) and the balanced distribution adaptation (BDA) in DA cannot be directly applied to regression problems. The fuzzy sets (FSs) method was proposed to solve this issue. Finally, a soft sensor model of Pichia pastoris cell concentration was realized by inputting the converted data to the RELM model. Simulation verification was carried out with three operating conditions at the scene of fermentation. The transfer effects of three DA methods, including transfer component analysis (TCA), improved joint distribution adaptation (IJDA) as well as IBDA, were compared. The predicted results show that IBDA-RELM had a better performance in the soft sensor of Pichia pastoris cell concentration under multi-operating conditions.

Predicting water consumption is of key importance for water supply management, which is also relevant in processes for reviewing prices.In this study, a hybrid method based on extreme learning machine model with the adaptive metrics of inputs is proposed for improving forecasting accuracy.The adaptive metrics of inputs can solve the problems of amplitude changing and trend determination, and reduce the effect of the overfitting of networks.It was found that the proposed model is practical for water demand forecasting and outperforms the autoregression (AR), artificial neural network (ANN), support vector machine(SVM) and extreme learning machine (ELM) models.

TU34. ASSOCIATION BETWEEN DEPRESSION DIAGNOSIS, POLYGENIC RISK FOR DEPRESSION AND ANTIHYPERTENSIVE MEDICATION NON-PERSISTENCE

Accurately forecasting the daily production of coalbed methane (CBM) is important forformulating associated drainage parameters and evaluating the economic benefit of CBM mining. Daily production of CBM depends on many factors, making it difficult to predict using conventional mathematical models. Because traditional methods do not reflect the long-term time series characteristics of CBM production, this study first used a long short-term memory neural network (LSTM) and transfer learning (TL) method for time series forecasting of CBM daily production. Based on the LSTM model, we introduced the idea of transfer learning and proposed a Transfer-LSTM (T-LSTM) CBM production forecasting model. This approach first uses a large amount of data similar to the target to pretrain the weights of the LSTM network, then uses transfer learning to fine-tune LSTM network parameters a second time, so as to obtain the final T-LSTM model. Experiments were carried out using daily CBM production data for the Panhe Demonstration Zone at southern Qinshui basin in China. Based on the results, the idea of transfer learning can solve the problem of insufficient samples during LSTM training. Prediction results for wells that entered the stable period earlier were more accurate, whereas results for types with unstable production in the early stage require further exploration. Because CBM wells daily production data have symmetrical similarities, which can provide a reference for the prediction of other wells, so our proposed T-LSTM network can achieve good results for the production forecast and can provide guidance for forecasting production of CBM wells.

Modeling patient disease progression using their historical Electronic Health Records (EHRs) is critical to assist clinical decision making and provide prompt medications. Long-Short Term Memory (LSTM) has been widely applied to handle large-scale sequential data such as EHRs. However, when applied to EHRs, the standard LSTM encounters one major limitation: lack of the generalizability given the intricate heterogeneity among different patient groups. To overcome this limitation, we propose a domain adaptation (DA) framework named Time-aware Adversarial Networks, which combines two temporal LSTM-based recurrent components, a label predictor and a domain classifier, to extract an invariant feature representation across different patient groups (domains) through an adversarial learning process. The label predictor learns the temporal developing patterns of the disease while the domain classifier identifies the temporal changes of feature distributions across patient groups. We evaluate the proposed DA framework on modeling the progression of an extremely challenging disease, septic shock, by using real-world EHRs among different patient groups across age, race, and gender. Our results demonstrate that our proposed DA framework can significantly improve the performance for the disease progression modeling while standard machine learning models are severely impacted by the data heterogeneity in EHRs.

Transformer fault diagnosis technology based on AdaBoost enhanced transferred convolutional neural network

Cutting tool wear degrades the product quality in manufacturing processes. Hence, real-time online estimation of tool wear is important for suggesting a tool replacement before the wear limit is reached, in order to protect the workpiece and the CNC machine from damage and breakdown. In this study, using both statistical features and wavelet features extracted from sensor signals, an adaptive evolutionary extreme learning machine (ELM) learning paradigm is developed for tool wear estimation in high-speed milling process. In the proposed method, a discrete differential evolution (DE) algorithm is used to select input features for the ELM, and a continuous DE algorithm is used for parameter optimisation of the mixed kernel function for the ELM. The experimental results indicate that the proposed adaptive evolutionary ELM-based tool wear estimation model can effectively estimate the tool wear in high-speed milling process. Empirical comparisons show that the proposed model performs better than existing approaches in estimating the tool wear.

Catastrophic forgetting is a major problem that affects neural networks during progressive learning. In it, the previously learned representation vanishes as the network learns new information. The extreme learning machine is one of the variants of the neural network. It is used in many domains due to fast training and good generalization ability. However, like other neural networks, it suffers from catastrophic forgetting and negative forward and backward transfer during the progression of neurons in incremental learning. The study hypothesizes that it is due to overlapping in hidden neurons and output weights. The global representation by an activation function further supports this hypothesis. To address this, the study proposes a neuron clustering approach to mitigate it in an adaptive class incremental extreme learning machine. The neuron clustering method activates k nearest neurons during learning and testing. It helps to partition the network to select overlapping subnetwork. Experimental results on four food datasets show that the proposed approach reduces negative forward and backward transfer when neurons are added incrementally during progressive learning.

We propose a beauty product image retrieval method based on multi-feature fusion and feature aggregation. The key idea is representing the image with the feature vector obtained by multi-feature fusion and feature aggregation. VGG16 and ResNet50 are chosen to extract image features, and Crow is adopted to perform deep feature aggregation. Benefited from the idea of transfer learning, we fine turn VGG16 on the Perfect-500K data set to improve the performance of image retrieval. The proposed method won the third price in Perfect Corp. Challenge 2018 with the best result 0.270676 mAP. We released our code on GitHub: https://github.com/wangqi12332155/ACMMM-beauty-AI-challenge.

When a high-speed train is running, it is easy for foreign objects like rail-side plastic bags to enter bottom bogies, cables and equipment gaps, which affects the safety of driving. At present, the detection accuracy of such foreign objects is low. To solve this problem, the present study used the latest deep learning based object detection networks, such as SSD and Faster R-CNN, which combined with different feature extractors to build a detection network. Through data augmentation of a sample, the number of sizes was expanded. By the idea of transfer learning, the COCO dataset was used as the source data to transfer features to the new detection network and then retrained to build a train bottom plastic bag detection network based on deep learning. It was shown that through data augmentation, the precision of each combination significantly improved. Moreover, the results using combination of SSD and MobileNet obtained the fastest detection speed with an average time of 41 ms and a precision rate of 81.3%. The accuracy using combination of SSD + Inception V2 combination reached to 89.7%, with an average time of 53 ms.

Analysis of small three-dimensional fluorescence spectroscopy dataset using migration learning an example of phenol concentration prediction in wastewater

A cognitive radio network (CRN) is a novel solution that promises to solve the spectrum scarcity problem and enhance spectrum utilization. However, unsecured CRN can easily be manipulated in order to attack legacy users on the communication channel. As a result, the network’s performance significantly degrades. Therefore, communication channel security is an important issue that needs to be addressed in a CRN. In this work, we focus on improving the security of multi-channel communication in a CRN, while various jammers try to access channels of interest to prevent SUs from using them. By using game-theoretic concepts and by defining states, actions, and players’ rewards, we propose game–based schemes that find the best channel for the secondary users (SUs) in order to avoid jammer’s attacks on communication channels. Accordingly, the problem is finding the optimal channel to maximize the long-term reward of the SU where communication channels are not used by the primary users (PUs) and are not jammed by attackers. In addition, the idea of transfer learning might be applied to the problem under consideration, and thus, a transfer Game-Actor-Critic (TGACT) scheme is proposed, which uses the transferred knowledge in a double-game period to accelerate the learning process and provide performance improvement in channel selection. Finally, the performance of the proposed schemes is simulated with different configurations. The simulation results show that the proposed schemes are quite resistant to jammer attacks, and achieve better performance compared to other channel selection schemes.

Recently, deep learning convolutional neural network has been widely used in food recognition and other fields, but there are still some problems such as poor semantic feature extraction ability and low recognition accuracy of Chinese food images. Based on the above reasons, this paper proposed a DenseNet model based on attention mechanism for image recognition of Chinese food. Using the idea of transfer learning, this paper applied the DenseNet pre-training model with excellent classification performance to the Chinese food image dataset. In order to improve the ability of extracting distinguishable features and learning fine-grained features of Chinese food images, this paper proposed an attention mechanism based on the DenseNet-169 model. This paper used the attention module to extract the key semantic feature map of the image, and then carried out the adaptive multi-fine-grained region tailoring. Finally, based on the region weight fusion scheme, the multi-fine-grained region feature map was integrated into an image feature description and sent to DenseNet-169 for recognition, so as to realize the end-to-end image recognition network. Experiments were carried out on VIREO Food-172 dataset, and the results shows that our method achieves considerable and comparable recognition performance to the state-of-art.

BackgroundDetection of any form of cognitive impairment is challenging and the subjects have to undergo numerous evaluations and clinical tests. Hence, it would be of great importance to design a reliable and accessible procedure by which patients may get diagnosed for dementia remotely. The capability of the Clock Drawing Test (CDT)as an effective cognitive assessment tool has motivated us to develop an online diagnostic tool by leveraging artificial intelligence techniques.MethodDigital pen recordings of 3,263 normal subjects and 160 with dementia in the Framingham Heart Study (FHS) were collected, where all subjects have completed two analog clock drawings, one drawn on command and the other by copying. Using the idea of transfer learning, we first modified and trained a Convolutional Neural Network (CNN) pre‐trained on the ImageNet dataset to extract high level features of the CDT images, which generated a score associated with the likelihood of dementia for each patient. The proposed method integrates the scores of the CDT images and other demographic information. Therefore, the generated scores for both command and copy CDTs along with age were used to train a logistic regression model to classify individuals as demented or normal.ResultWe have evaluated the performance of the developed models by applying 5‐fold cross validation on the FHS dataset. On the test dataset, the model (modified pre‐trained CNN) based on command CDT images yielded an AUC of 0.81±0.043. The logistic regression model using age and the generated scores of command and copy CDTs, yielded an average AUC and average F1 score of 0.92±0.008 and 0.94±0.008, respectively.ConclusionOur method need not necessarily have access to digital biomarkers or clinical tests since the CDT can be completed using pen and paper, capturing the image using a smartphone. Hence, our method offers a cost‐effective and accurate screening tool to diagnose dementia and related diseases remotely.