The use of machine learning to assess failure risks of shallow continuous tunnels subjected to active dip-slip faults

Integration of growing self-organizing map and bee colony optimization algorithm for part clustering

fMRI data analysis is challenging because data are generally a modest signal embedded in a high dimensional space. We present here a method for classification and discrimination among fMRI data that is based on the Self Organizing Map (SOM) algorithm. This allows no prior selection of spatial or temporal features. We applied the method to single-subject and inter-subject classification. fMRI data are issued from a block design experiment where subjects were passively viewing emotional pictures of positive, neutral and negative valences. These data are classified with an unsupervised non-linear method, the SOM. We demonstrate here that the SOM algorithm is a good candidate for multi-voxel pattern analysis methods as it leads to good performance and it allows to extract information about cognitive processes. Our method presents three phases: data dimensionality reduction: where non relevant data for classification (ie non grey matter) are deleted from a volume, SOM algorithm training: where statistic regularities relevant for classification are extracted, SOM algorithm test: where classification and recognition performance are calculated.

This paper presents a novel prediction model for Regional Economic Development (RED) levels using the Self-Organizing Map (SOM) algorithm. It posits that the SOM algorithm can effectively forecast RED levels by processing multidimensional datasets that include economic, social, and environmental indicators. The approach involves constructing an Evaluation Index System (EIS) comprising 14 indicators across three domains: financial performance, social conditions, and ecological sustainability. The performance of the SOM model is compared to the traditional Support Vector Regression (SVR) model. The analytical tools utilized in this study include the SOM neural network and the SVR model, both applied to predict the Gross Domestic Product (GDP) and the Consumer Price Index (CPI) in Region C. The SOM model achieves a relative error of 0.01% in predicting GDP and 0.12% in predicting CPI, outperforming the SVR model. Additionally, the model is applied to forecast the economic development levels of two Chinese provinces from 2026 to 2035, revealing significant regional disparities. The findings suggest that the SOM algorithm is a promising tool for predicting RED, providing valuable insights for policy-making processes.

Abstract. Analyzing concentration–discharge (C–Q) hysteresis loops is essential for understanding both dissolved and particulate constituent sources and transport mechanisms in watershed hydrology. However, traditional hysteresis analysis methods, including loop classification schemes and hysteresis indices, fail to capture the full variability and gradual transitions between loop patterns. To address these limitations, we introduce an alternative approach for characterizing hysteresis patterns in watersheds using the Self-Organizing Map (SOM) algorithm, which better represents loop variability without relying on rigid categories. This technical note outlines the application – and the advantages – of SOM-based hysteresis loop characterization and presents a general workflow for its implementation to characterize C–Q hysteresis for any watershed constituent. We demonstrate the efficacy of the SOM algorithm through a proof-of-concept with sediment transport hysteresis loops. The SOM algorithm was able to classify hysteresis loops with a high degree of accuracy, correctly mapping the amplitude, direction, and concavity of hysteresis loops in the training dataset. We also used the SOM algorithm to develop a General Turbidity-Discharge (T–Q) SOM – which may be used as a standard for characterizing primary loop types in sediment hysteresis analysis. We demonstrate the use of the General T–Q SOM in describing loop frequency distributions and exploring associations with hydrologic variables to infer hydrologic controls of loop types. We found that the General T–Q SOM captures key differences in loop shape (and thus sediment transport processes) overlooked by hysteresis indices while preserving the gradual transitions between loop types that are often lost in classification schemes. Additionally, SOM-based correlation analysis effectively detected associations between loop types and hydrologic variables, enhancing understanding of their hydrologic significance. This method offers a powerful tool for advancing the identification of constituent sources and transport mechanisms at the watershed scale. To support broader adoption of the methodology described in this paper, we have developed a Python package, equipped with detailed documentation, to facilitate SOM implementation and application in future C–Q analysis.

[1] Despite observations of tectonic tremor in many locations around the globe, the emergent phase arrivals, low-amplitude waveforms, and variable event durations make automatic detection a nontrivial task. In this study, we employ a new method to identify tremor in large data sets using a semiautomated technique. The method first reduces the data volume with an envelope cross-correlation technique, followed by a Self-Organizing Map (SOM) algorithm to identify and classify event types. The method detects tremor in an automated fashion after calibrating for a specific data set, hence we refer to it as being “semiautomated”. We apply the semiautomated detection algorithm to a newly acquired data set of waveforms from a temporary deployment of 13 seismometers near Cholame, California, from May 2010 to July 2011. We manually identify tremor events in a 3 week long test data set and compare to the SOM output and find a detection accuracy of 79.5%. Detection accuracy improves with increasing signal-to-noise ratios and number of available stations. We find detection completeness of 96% for tremor events with signal-to-noise ratios above 3 and optimal results when data from at least 10 stations are available. We compare the SOM algorithm to the envelope correlation method of Wech and Creager and find the SOM performs significantly better, at least for the data set examined here. Using the SOM algorithm, we detect 2606 tremor events with a cumulative signal duration of nearly 55 h during the 13 month deployment. Overall, the SOM algorithm is shown to be a flexible new method that utilizes characteristics of the waveforms to identify tremor from noise or other seismic signals.

In the realm of stock market prediction and classification, the use of machine learning algorithms has gained significant attention. In this study, we explore the application of Multilayer Perceptron (MLP) and Radial Basis Function (RBF) algorithms in predicting and classifying stock prices, specifically amidst economic policy uncertainty. Stock market fluctuations are greatly influenced by economic policies implemented by governments and central banks. These policies can create uncertainty and volatility, which in turn makes accurate predictions and classifications of stock prices more challenging. By leveraging MLP and RBF algorithms, we aim to develop models that can effectively navigate these uncertainties and provide valuable insights to investors and financial analysts. The MLP algorithm, based on artificial neural networks, is able to learn complex patterns and relationships within financial data. The RBF algorithm, on the other hand, utilizes radial basis functions to capture non-linear relationships and identify hidden patterns within the data. By combining these algorithms, we aim to enhance the accuracy of stock price prediction and classification models. The results showed that both MLB and RBF predicted stock prices well for a group of countries using an index reflecting the impact of news on economic policy and expectations, where the MLB algorithm proved its ability to predict chain data. Countries were also classified according to stock price data and uncertainty in economic policy, allowing us to determine the best country to invest in according to the data. The uncertainty surrounding economic policy is what makes stock price forecasting so crucial. Investors must consider the degree of economic policy uncertainty and how it affects asset prices when deciding how to allocate their assets.

The author investigated topography and geology in western and southern margins of the Kofu Basin, in order to consider a characteristic of active faults through late Quaternary in these areas, on the basis of deformed landforms. The Kofu Basin, about 20km accross, is one of the tectonic basins in Central Japan, and consists of a flight of dissected fans in the area less than 500 m high (Fig. 1). In the western (Ichinose Upland) and the southern (Bone Hill) margins of the basin, dissected fans are well developed and classified into several steps. As a time marker tephra for the classification of terraces, Pm-I, one of widely distributed pumice layer (ca. 80, 000 y. B. P., Machida and Suzuki, 1971) which was erupted from Ontake Volcano, and Nirasaki mud flow deposits (ca. 300, 000y. B. P.) which were erupted from Yatsugatake Volcano, were used (Table 1). In the Ichinose Upland, geomorphic surfaces are classified into five levels, Higher terraces, Ia, Ib, II and III surfaces in descending order (Fig. 3). In the Sone Hill, they are classified into six levels (Ia, Ib, II, IIIa, IIIb and IV surfaces in descending order) as shown in Fig. 5. Table 1 shows correlation of terraces in both areas. Many active faults which displace these geomorphic surfaces are observed in the Kofu Basin, especially in the both areas of the Ichinose Upland and Sone Hill (Figs. 1, 3 and 5). Active faults of the Kofu Basin are dip slip faults without strike slip component. Most of them are distributed in margins of the Upland and the Hill. Detailed features of deformed surfaces and terrace deposits are illustrated in the maps and cross sections (Figs. 6-13). All the active faults are expressed as fault scarps, scarplets and flexure scarps, and most of them are estimated to be reverse faults or thrust faults. Warped terrace surfaces and reverse tilting towards mountain area are the typical types of deformed landforms in these areas. Rate of faulting of active faults in these areas are listed in Table 2. Since older terraces are usually much more deformed than the younger ones, progressive faulting in the late Quaternary is indicated. Average rate of vertical displacement is calculated to be 0.3_??_1.4m/1, 000 yrs. for the Ichinose Upland and less than 0.6m/1, 000 yrs. for the Sone Hill. It is interesting to note that major active faults are located at the outer margins of terraces far away from the piedmont lines themselves, both in the Ichinose Upland and Sone Hill, although some fault scarplets can be observed along the piedmont in the Ichinose Upland. Due to such arrangement of the active faults, the oldest terraces with reverse tilting are located immediately adjacent to the modern alluvial fans, and their apex area are often covered with the younger terraces. Above-mentioned characteristics of fault topographies may be explained by “a bending model of fault plane” (Ikeda and Yonekura, 1979) (Fig. 14). In the Sone Hill, this model can be applied (Fig. 15-C). But, in the Ichinose Upland, another models are devised because active faults in piedmont area were not inactive (Figs. 15-A, B).

Effects of strength and weight of pre-ground improvement on seismic behavior of shallow overburden tunnel

In this paper, we propose car license plate recognition using morphological information and a self-organizing map (SOM) algorithm. Morphological information on horizontal and vertical edges was used to extract the license plate from a car image. A 4-directional contour tracking algorithm was applied to extract the specific area, including characters, from an extracted plate. Recognition of extracted character strings was studied using the SOM algorithm. We used 50 car images to evaluate performance. Extraction for character strings by the proposed method showed better results than that from conventional color information on RGB and HSI. License plate recognition using the SOM algorithm was very efficient.

The hammering sound inspection for pieces plays the Digital Twin part in the Hybrid Twin approach. The map generated by Self-Organizing Map (SOM) algorithm makes it possible to cluster the pieces into defected and non-defected groups by checking the corresponding hammering sounds. However, the applicability of map generated by SOM has not yet been discussed. This paper suggests a procedure how to improve a map generated by SOM algorithm. It shows that if the hammering sound of a piece is mapped on the boundary between the areas corresponding to defected and non-defected products, the map cannot be applied to inspect this piece and another map must be generated by repeating the training including the hammering sounds of such pieces by SOM algorithm. By executing the procedure some number of times, it is likely that the improved map will be used for hammering sound inspection.

This paper presents a new image coding scheme based upon image pattern recognition (IPR) and discrete wavelet transforms (DWT). First, the original image is predicted by image pattern recognition, then the predicted error image is encoded by DWT, and the pattern library learning is based upon self-organizing maps (SOM) algorithm. To improve the performance of SOM algorithm, a frequency sensitive self-organizing feature maps (FSOM) algorithm is proposed. Experiment results show that the IPR-FSOM-DWT coding scheme can get better coding performance than standard JPEG2000.

PurposeMost of the redundant dual-arm robots are singular free, dexterous and collision free compared to other robotic arms. This paper aims to analyse the workspace of redundant arms to study the manipulability. Furthermore, multi-layer perceptron (MLP) algorithm is used to determine the various joint parameters of both the upper body redundant arms. Trajectory planning of robotic arms is carried out with the help of inverse solutions obtained from the MLP algorithm.Design/methodology/approachIn this paper, the kinematic equations are derived from screw theory approach and inverse kinematic solutions are determined using MLP algorithm. Levenberg–Marquardt (LM) and Bayesian regulation (BR) techniques are used as the backpropagation algorithms. The results from two backpropagation techniques are compared for determining the prediction accuracy. The inverse solutions obtained from the MLP algorithm are then used to optimize the cubic spline trajectories planned for avoiding collision between arms with the help of convex optimization technique. The dexterity of the redundant arms is analysed with the help of Cartesian workspace of arms.FindingsDexterity of redundant arms is analysed by studying the voids and singular spaces present inside the workspace of arms. MLP algorithms determine unique solutions with less computational effort using BR backpropagation. The inverse solutions obtained from MLP algorithm effectively optimize the cubic spline trajectory for the redundant dual arms using convex optimization technique.Originality/valueMost of the MLP algorithms used for determining the inverse solutions are used with LM backpropagation technique. In this paper, BR technique is used as the backpropagation technique. BR technique converges fast with less computational time than LM method. The inverse solutions of arm joints for traversing optimized cubic spline trajectory using convex optimization technique are computed from the MLP algorithm.

A mathematical improvement of the self-organizing map algorithm

The forecasting of lake water level is one of the complex problems in the hydrology field owing to the incorporating with various hydrological and morphological characteristics. In this research, newly hybrid data intelligence (DI) model based on the integration of the Multilayer Perceptron (MLP) and Whale Optimization Algorithm (WOA) is developed for lake water level forecasting. The potential of the proposed hybrid MLP_WOA model is validated against several well-established DI models over the literature including the Cascade-Correlation Neural Network Model (CCNNM), Self-Organizing Map (SOM), Decision Tree Regression (DTR), Random Forest Regression (RFR), and classical MLP. The applied predictive models are examined to forecast the Van Lake water level fluctuation with monthly scale over seven-decade time period (1943–2016). The input variables are abstracted using statistical correlation analysis procedure. The modeling is diagnosed using multiple statistical metrics (i.e., root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffe coefficient (NSE), Willmott’s Index (WI), Legate and McCabe’s Index (LMI), determination coefficient (R2)). In addition, graphical distribution data such as the Taylor diagram, violin plot, and point density are investigated. Results indicated that the MLP_WOA model performed superior prediction results over the comparable models based on forecasting performance. Five-month lead times performed the best results for the prediction procedure. In quantitative terms, the RMSE and MAE are reduced by 29.8% and 33.9%, 48.3% and 52%, 57.6% and 59.7%, 53.9% and 58.3%, and 25.3% and 23.9% using the MLP_WOA model over CCNNM, SOM, DTR, RFR, and MLP models, respectively. In comparison with the literature studies, using longer span of historical data elevated the forecasting accuracy. In summary, MLP_WOA model provided an applicable and simple methodology for Van Lake water level forecasting owing to its simple learning procedure.

The importance of Predictive Maintenance is critical for engineering industries, such as manufacturing, aerospace and energy. Unexpected failures cause unpredictable downtime, which can be disruptive and high costs due to reduced productivity. This forces industries to ensure the reliability of their equip-ment. In order to increase the reliability of equipment, maintenance actions, such as repairs, replacements, equipment updates, and corrective actions are employed. These actions affect the flexibility, quality of operation and manu-facturing time. It is therefore essential to plan maintenance before failure occurs.Traditional maintenance techniques rely on checks conducted routinely based on running hours of the machine. The drawback of this approach is that maintenance is sometimes performed before it is required. Therefore, conducting maintenance based on the actual condition of the equipment is the optimal solu-tion. This requires collecting real-time data on the condition of the equipment, using sensors (to detect events and send information to computer processor).Predictive Maintenance uses these types of techniques or analytics to inform about the current, and future state of the equipment. In the last decade, with the introduction of the Internet of Things (IoT), Machine Learning (ML), cloud computing and Big Data Analytics, manufacturing industry has moved forward towards implementing Predictive Maintenance, resulting in increased uptime and quality control, optimisation of maintenance routes, improved worker safety and greater productivity.The present thesis describes a novel computational strategy of Predictive Maintenance (fault diagnosis and fault prognosis) with ML and Deep Learning applications for an FG304 series external gear pump, also known as a domino pump. In the absence of a comprehensive set of experimental data, synthetic data generation techniques are implemented for Predictive Maintenance by perturbing the frequency content of time series generated using High-Fidelity computational techniques. In addition, various types of feature extraction methods considered to extract most discriminatory informations from the data. For fault diagnosis, three types of ML classification algorithms are employed, namely Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB) algorithms. For prognosis, ML regression algorithms, such as MLP and SVM, are utilised. Although significant work has been reported by previous authors, it remains difficult to optimise the choice of hyper-parameters (important parameters whose value is used to control the learning process) for each specific ML algorithm. For instance, the type of SVM kernel function or the selection of the MLP activation function and the optimum number of hidden layers (and neurons).It is widely understood that the reliability of ML algorithms is strongly depen-dent upon the existence of a sufficiently large quantity of high-quality training data. In the present thesis, due to the unavailability of experimental data, a novel high-fidelity in-silico dataset is generated via a Computational Fluid Dynamic (CFD) model, which has been used for the training of the underlying ML metamodel. In addition, a large number of scenarios are recreated, ranging from healthy to faulty ones (e.g. clogging, radial gap variations, axial gap variations, viscosity variations, speed variations). Furthermore, the high-fidelity dataset is re-enacted by using degradation functions to predict the remaining useful life (fault prognosis) of an external gear pump.The thesis explores and compares the performance of MLP, SVM and NB algo-rithms for fault diagnosis and MLP and SVM for fault prognosis. In order to enable fast training and reliable testing of the MLP algorithm, some predefined network architectures, like 2n neurons per hidden layer, are used to speed up the identification of the precise number of neurons (shown to be useful when the sample data set is sufficiently large). Finally, a series of benchmark tests are presented, enabling to conclude that for fault diagnosis, the use of wavelet features and a MLP algorithm can provide the best accuracy, and the MLP al-gorithm provides the best prediction results for fault prognosis. In addition, benchmark examples are simulated to demonstrate the mesh convergence for the CFD model whereas, quantification analysis and noise influence on training data are performed for ML algorithms.