ML-based group method of data handling: an improvement on the conventional GMDH

Physics-based and machine-learning models for accurate scour depth prediction

Scour phenomena remain a significant cause of instability in offshore structures. The present study estimates scour depths using physics-based numerical modelling and machine-learning (ML) algorithms. For the ML prediction, datasets were collected from previous studies, and the trained models checked against the statistical measures and reported outcomes. The numerical assessment of the scour depth has been also carried out for the current and coupled wave-current environment within a computational fluid dynamics framework with the aid of the open-source platform REEF3D. The outcomes are validated against the previously reported experimental studies. The results obtained from ML schemes demonstrated that the artificial neural network and adaptive neuro-fuzzy interface system models have an elevated level of effectiveness compared with the other models. Whereas the numerical analysis results show a good agreement against the reported values. For the current only conditions, the normalized scour depth (S/D) at the front and rear end of the pier is 0.65 and 0.81. For the wave-current conditions, the normalized scour depth (S/D) is 0.26. The study highlights the importance of machine learning and physics-based numerical modelling to assess scour depth within a reasonable time frame without compromising accuracy. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

Group Method of Data Handling Using Christiano-Fitzgerald Random Walk Filter for Insulator Fault Prediction

Disruptive failures threaten the reliability of electric supply in power branches, often indicated by the rise of leakage current in distribution insulators. This paper presents a novel, hybrid method for fault prediction based on the time series of the leakage current of contaminated insulators. In a controlled high-voltage laboratory simulation, 15 kV-class insulators from an electrical power distribution network were exposed to increasing contamination in a salt chamber. The leakage current was recorded over 28 h of effective exposure, culminating in a flashover in all considered insulators. This flashover event served as the prediction mark that this paper proposes to evaluate. The proposed method applies the Christiano-Fitzgerald random walk (CFRW) filter for trend decomposition and the group data-handling (GMDH) method for time series prediction. The CFRW filter, with its versatility, proved to be more effective than the seasonal decomposition using moving averages in reducing non-linearities. The CFRW-GMDH method, with a root-mean-squared error of 3.44×10-12, outperformed both the standard GMDH and long short-term memory models in fault prediction. This superior performance suggested that the CFRW-GMDH method is a promising tool for predicting faults in power grid insulators based on leakage current data. This approach can provide power utilities with a reliable tool for monitoring insulator health and predicting failures, thereby enhancing the reliability of the power supply.

A Hybrid Stacked CNN and Residual Feedback GMDH-LSTM Deep Learning Model for Stroke Prediction Applied on Mobile AI Smart Hospital Platform

Artificial intelligence (AI) techniques for intelligent mobile computing in healthcare has opened up new opportunities in healthcare systems. Combining AI techniques with the existing Internet of Medical Things (IoMT) will enhance the quality of care that patients receive at home remotely and the successful establishment of smart living environments. Building a real AI for mobile AI in an integrated smart hospital environment is a challenging problem due to the complexities of receiving IoT medical sensors data, data analysis, and deep learning algorithm complexity programming for mobile AI engine implementation AI-based cloud computing complexities, especially when we tackle real-time environments of AI technologies. In this paper, we propose a new mobile AI smart hospital platform architecture for stroke prediction and emergencies. In addition, this research is focused on developing and testing different modules of integrated AI software based on XAI architecture, this is for the mobile health app as an independent expert system or as connected with a simulated environment of an AI-cloud-based solution. The novelty is in the integrated architecture and results obtained in our previous works and this extended research on hybrid GMDH and LSTM deep learning models for the proposed artificial intelligence and IoMT engine for mobile health edge computing technology. Its main goal is to predict heart-stroke disease. Current research is still missing a mobile AI system for heart/brain stroke prediction during patient emergency cases. This research work implements AI algorithms for stroke prediction and diagnosis. The hybrid AI in connected health is based on a stacked CNN and group handling method (GMDH) predictive analytics model, enhanced with an LSTM deep learning module for biomedical signals prediction. The techniques developed depend on the dataset of electromyography (EMG) signals, which provides a significant source of information for the identification of normal and abnormal motions in a stroke scenario. The resulting artificial intelligence mHealth app is an innovation beyond the state of the art and the proposed techniques achieve high accuracy as stacked CNN reaches almost 98% for stroke diagnosis. The GMDH neural network proves to be a good technique for monitoring the EMG signal of the same patient case with an average accuracy of 98.60% to an average of 96.68% of the signal prediction. Moreover, extending the GMDH model and a hybrid LSTM with dense layers deep learning model has improved significantly the prediction results that reach an average of 99%.

A novel non-linear neuron model based on multiplicative aggregation in quaternionic domain

The learning algorithm for a three-layered neural structure with novel non-linear quaternionic-valued multiplicative (QVM) neurons is proposed in this paper. The computing capability of non-linear aggregation in the cell body of biological neurons inspired the development of a non-linear neuron model. However, unlike linear neuron models, most non-linear neuron models are built on higher order aggregation, which is more mathematically complex and difficult to train. As a result, building non-linear neuron models with a simple structure is a difficult and time-consuming endeavor in the neurocomputing field. The concept of a QVM neuron model was influenced by the non-linear neuron model, which has a simple structure and the great computational ability. The suggested neuron’s linearity is determined by the weight and bias associated with each quaternionic-valued input. Non-commutative multiplication of all linearly connected quaternionic input-weight terms accommodates the non-linearity. To train three-layered networks with QVM neurons, the standard quaternionic-gradient-based backpropagation (QBP) algorithm is utilized. The computational and generalization capabilities of the QVM neuron are assessed through training and testing in the quaternionic domain utilizing benchmark problems, such as 3D and 4D chaotic time-series predictions, 3D geometrical transformations, and 3D face recognition. The training and testing outcomes are compared to conventional and root-power mean (RPM) neurons in quaternionic domain using training–testing MSEs, network topology (parameters), variance, and AIC as statistical measures. According to these findings, networks with QVM neurons have greater computational and generalization capabilities than networks with conventional and RPM neurons in quaternionic domain.