Interval model calibration with response-consistent supervised learning network

In order to improve the accuracy rate of surface EMG (sEMG) pattern recognition, a modified Kohonen self-organizing competitive network is presented in this paper. Kohonen network has a simple algorithm and short time for clustering. There we adjust the structure of this network, and turn it into a supervised learning network by adding an output layer, then optimize the initial weight. The integrate EMG and power spectral density ratio of sEMG as the input of modified Kohonen network to identify the five kinds of movement patterns: extension of thumb, extension of wrist, flexion of wrist, side flexion of wrist and extension of palm. Experiments show that, compared with the traditional Kohonen network, the modified neural network classifier has the higher classification ability.

SummaryElectronic commutator in Brushless DC motor (BLDC) drives decides the sequence of driving current through the stator windings based on the rotor position sensed by the three Hall position sensors. If any fault occurs in the Hall sensors, it will result in a faulty driving sequence of rotors and the motor will stall. This paper investigates an artificial intelligence‐based Fault Diagnosis and Compensation (FDC) system for correcting up to two position sensor failures in trapezoidal back EMF BLDC motor drives. The proposed fault‐tolerant system is a simple, fast, and efficient method to diagnose and reconstruct the commutation signals using the existing processor‐based commutator arrangements. An Artificial Intelligence algorithm is developed to estimate the correct switching sequence in the absence of up to two Hall sensor signals while the motor is running. This supervised learning network is advantageous as it is added as an additional control algorithm with the existing control algorithm for BLDC motor. The simulation and hardware results showcase the effective performance of the proposed algorithm for different Hall sensor fault conditions.

As well said “health is wealth”, good health is the key to human happiness. But nowadays due to bad eating habits, stressful life and unawareness among people, the number of cases of death due to heart diseases is increasing day by day. With the help of machine learning techniques, this hazard can be minimized up to some extent by helping healthcare professionals in the quick and efficient prediction of diseases. The motive of this study is to detect the risk of heart disease through a supervised learning network. The paper uses the back propagation approach of neural network. The data set here consists of 180 samples with four attributes adapted from UCI Machine Repository. We have set 70% data for training, 15% data for validation and 15% data for testing. The system gives a better accuracy as compared to the previous researches and with a good figure. It shows an accuracy of 91% for training part which is a good value for any data.

Given that vibration fault signals collected from industrial circumstances are usually insufficient and have no labels, supervised learning networks cannot be directly applied to recognize fault types in this case. Hence, automatic feature extraction of unlabeled data is urgently needed. In this study, an automatic fault feature extractor (AFFE) based on the contrastive learning algorithm—Bootstrap Your Own Latent (BYOL) network, which can extract fault features automatically without needing labeled information—is proposed. A data augmentation method for vibration signals is studied because it is critical to the contrastive learning algorithm. This study determines a data augmentation combination that can help AFFE achieve excellent performance in extracting features from unlabeled bearing fault data. To verify the validity of the proposed method, we utilize some labeled data (5% of samples with labels in a dataset) to fit linear classifiers, which are combined with the proposed AFFE to extract a feature. The aim is to predict the accuracy score of feature classification for the remaining data. The case study demonstrates that the fault features extracted using AFFE can achieve a high accuracy score of 94.81%. Therefore, the proposed AFFE-BYOL is a promising diagnostic fault feature extraction scheme to process unlabeled vibrational data.

The capability of artificial neural networks to use and combine simple learning rules to master different complex tasks is very motivating and has sufficed on lots of challenging pattern recognition problems. Thus, in this paper, we selected a pattern recognition task that can be tough even for humans. The aim is to investigate the capability of neural networks to learn and recognize patterns describing some segmented chest organs in binary segmented images. The geometric descriptions in addition to the entropy of those images have been leveraged on in this work for classification purposes. Two learning algorithms are used for training both feedforward and competitive neural networks which have been considered for the pattern recognition task. Overall, we show that a competitive neural network that falls into unsupervised learning category outperformed the feedforward network which is considered a supervised learning network. This outperformance is in terms of time, error rate, cost, and accuracy.KeywordsArtificial neural networksPattern recognitionSegmented chest organsCompetitive neural networksUnsupervised learningSupervised learning

Seismic inversion in geophysics is a method that uses certain prior information, such as known geological laws and well logging and drilling data, to infer the physical parameters of underground media, such as wave impedance, velocity, and density, from seismic observation data, and thereby obtain the spatial structure and physical properties of underground strata. Seismic inversion is a highly complex problem with multiple solutions, and with the advancement of collection equipment, the volume of geophysical observation data is increasing at an astonishing rate. This presents new challenges for the accuracy and speed of seismic data inversion methods. There is an urgent need to develop intelligent and efficient inversion technologies for seismic inversion.Deep learning networks have powerful nonlinear fitting capabilities and can be used to solve complex nonlinear problems, such as seismic inversion. However, the predictive ability of deep learning networks largely depends on the quantity of training data. In the early stages of oil and gas exploration and development, the amount of well logging label data available for training is very limited, which poses a challenge for the application of deep learning in seismic inversion. Semi-supervised learning seismic inversion methods consider both data mismatch issues and well logging data mismatch issues, and can better adapt to inversion problems in real-world scenarios. Unlike supervised learning approaches, semi-supervised learning does not require a large amount of labeled data, thus it can better handle situations of data scarcity or mismatch.This paper utilizes a semi-supervised learning workflow to perform inversion on post-stack seismic data and has conducted experimental validation on the Marmousi 2 model. The experimental results show that, compared to supervised learning networks, the semi-supervised learning network still exhibits good predictive performance with a limited amount of data, demonstrating better stability in the presence of noise and geological variations, and effectively learns the mapping relationship between seismic data and artificial intelligence. Furthermore, as the amount of training data increases, the performance of the network also improves, confirming the importance of data quantity for training deep learning networks. The application results of the network on actual data indicate that the network has broad application prospects and feasibility. However, since the network is based on a channel-by-channel inversion method, there is still a lack of representation in terms of lateral continuity, which requires further exploration and improvement in subsequent research.

The universal learning network (ULN) which is a superset of supervised learning networks has been already proposed. Parameters in ULN are trained in order to optimize a criterion function as conventional neural networks, and after training they are used as constant parameters. In this paper, a method to alter the parameters depending on the network flows is presented to enhance representation abilities of networks. In the proposed method, there exists two kinds of networks, the first one is a basic network which includes varying parameters and the other one is a network which calculates the optimal varying parameters depending on the network flows of the basic network. It is also proposed in this paper that any type of networks such as fuzzy inference networks, radial basis function networks and neural networks can be used for the basic and parameter calculation networks. From simulations where parameters in a neural network are altered by fuzzy inference networks, it is shown that the networks with the same number of varying parameters have higher representation abilities than the conventional networks.

Bayesian networks (BNs) are being studied in recent years for system diagnosis, reliability analysis, and design of complex engineered systems. In several practical applications, BNs need to be learned from available data before being used for design or other purposes. Current BN learning algorithms are mainly developed for networks with only discrete variables. Engineering design problems often consist of both discrete and continuous variables. This paper develops a framework to handle continuous variables in BN learning by integrating learning algorithms of discrete BNs with Gaussian mixture models (GMMs). We first make the topology learning more robust by optimizing the number of Gaussian components in the univariate GMMs currently available in the literature. Based on the BN topology learning, a new multivariate Gaussian mixture (MGM) strategy is developed to improve the accuracy of conditional probability learning in the BN. A method is proposed to address this difficulty of MGM modeling with data of mixed discrete and continuous variables by mapping the data for discrete variables into data for a standard normal variable. The proposed framework is capable of learning BNs without discretizing the continuous variables or making assumptions about their conditional probability densities (CPDs). The applications of the learned BN to uncertainty quantification and model calibration are also investigated. The results of a mathematical example and an engineering application example demonstrate the effectiveness of the proposed framework.

Microsimulation models are frequently used in traffic analysis.Various optimization methods are used in calibration, and the one method that has shown success is neural networks.This paper shows the responses of neural networks during calibration of a microsimulation traffic model.We analyzed two calibration methods by applying neural networks and comparing their neural network learning (according to their achieved correlation and the mean error of prediction) and their generalization ability (comparison of generalization results was analyzed in two steps).The best correlation between the microsimulation results and neural network prediction was 88.3%, achieved for the traveling time prediction, on which the first calibration method is based.

Linear or non-linear multivariate calibration models? That is the question

Current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature because of the size of the combinatorial problem, which leads to suboptimal solutions. We propose a reinforcement learning strategy using a Monte Carlo Tree Search (MCTS) that can find a better beam orientation set in less time than CG. We utilize a reinforcement learning structure involving a supervised learning network to guide the MCTS and to explore the decision space of beam orientation selection problems. We previously trained a deep neural network (DNN) that takes in the patient anatomy, organ weights, and current beams, then approximates beam fitness values to indicate the next best beam to add. Here, we use this DNN to probabilistically guide the traversal of the branches of the Monte Carlo decision tree to add a new beam to the plan. To assess the feasibility of the algorithm, we used a test set of 13 prostate cancer patients, distinct from the 57 patients originally used to train and validate the DNN, to solve five-beam plans. To show the strength of the guided MCTS (GTS) compared to other search methods, we also provided the performances of Guided Search, Uniform Tree Search and Random Search algorithms. On average, GTS outperformed all the other methods. It found a better solution than CG in 237 s on average, compared to 360 s for CG, and outperformed all other methods in finding a solution with a lower objective function value in less than 1000 s. Using our GTS method, we could maintain planning target volume (PTV) coverage within 1% error similar to CG, while reducing the organ-at-risk mean dose for body, rectum, left and right femoral heads; the mean dose to bladder was 1% higher with GTS than with CG.

mmGesture: Semi-supervised gesture recognition system using mmWave radar

We propose a novel physics‐guided deep learning framework for geophysical inversion that integrates Langevin Monte Carlo (LMC) sampling to quantify uncertainties in model parameters. A statistical sampling strategy is employed to enhance computational efficiency by reducing the number of required samples while preserving diversity and informativeness. The training data for the supervised learning networks are iteratively expanded with outputs from a stochastic sampler and their corresponding observed responses, ensuring representative coverage of the model space. The Jensen–Shannon divergence is adopted as the loss function for training the network model, in which the Gaussian assumption is applied to enable analytical computation. The developed workflow is evaluated on reservoir porosity inversion, where it successfully reconstructs porosity patterns in the subsurface, yielding results that closely match the reference model. Compared to traditional LMC algorithm applied to the entire data cube, the proposed approach attains substantial computational efficiency by leveraging an active learning strategy that identifies and utilizes a limited yet representative subset of the observations. The results demonstrate the effectiveness of the proposed method, highlighting its potential for application to a wide range of geophysical inverse problems.

Bearing is a key component of rotating machinery, thus the accurate and efficient fault diagnosis of bearing is critical to the safety and reliability of rotating machinery systems. In recent years, the intelligent fault diagnosis technology of bearing represented by deep learning has made rapid development. However, the stability and generalization performance of the fault diagnosis model of bearing under complex environmental noise and variable working conditions is not good. Fortunately, self-supervised learning represented by contrastive learning can provide a good solution. The current research on contrastive learning mainly focuses on self-supervised contrastive learning, but the lack of supervised learning of fault label information leads to the reduction of diagnostic accuracy and robustness under variable working conditions. To solve this problem, this paper proposes a supervised contrastive learning combined with multi-scale attention mechanism for fault diagnosis of bearing under variable operating conditions. Firstly, the preprocessing of bearing time-domain vibration data is completed, including data set division, data augmentation, and construction of “positive” or “negative” pairs for comparative learning. Then, a supervised learning network integrating multi-scale attention mechanism is constructed to complete bearing fault feature extraction. Finally, the model transfer fault diagnosis is completed under complex noise and variable working conditions. The performance of the proposed method is evaluated through a large number of noise and variable-condition experiments. The results show that the proposed method has high fault classification accuracy and robustness under the influence of complex noise and variable working conditions.

In multiphase coronary CT angiography (CTA), a series of CT images are taken at different levels of radiation dose during the examination. Although this reduces the total radiation dose, the image quality during the low-dose phases is significantly degraded. Recently, deep neural network approaches based on supervised learning technique have demonstrated impressive performance improvement over conventional model-based iterative methods for low-dose CT. However, matched low- and routine-dose CT image pairs are difficult to obtain in multiphase CT. To address this problem, we aim at developing a new deep learning framework. We propose an unsupervised learning technique that can remove the noise of the CT images in the low-dose phases by learning from the CT images in the routine dose phases. Although a supervised learning approach is not applicable due to the differences in the underlying heart structure in two phases, the images are closely related in two phases, so we propose a cycle-consistent adversarial denoising network to learn the mapping between the low- and high-dose cardiac phases. Experimental results showed that the proposed method effectively reduces the noise in the low-dose CT image while preserving detailed texture and edge information. Moreover, thanks to the cyclic consistency and identity loss, the proposed network does not create any artificial features that are not present in the input images. Visual grading and quality evaluation also confirm that the proposed method provides significant improvement in diagnostic quality. The proposed network can learn the image distributions from the routine-dose cardiac phases, which is a big advantage over the existing supervised learning networks that need exactly matched low- and routine-dose CT images. Considering the effectiveness and practicability of the proposed method, we believe that the proposed can be applied for many other CT acquisition protocols.