Connected Vehicle Data Time Series Dependence for Machine Learning Model Selection and Specification

Speech is a powerful means of expressing thoughts, emotions, and perspectives. However, accurately determining the emotions conveyed through speech remains a challenging task. Existing manual methods for analyzing speech to recognize emotions are prone to errors, limiting our understanding and response to individuals’ emotional states. To address diverse accents, an automated system capable of real-time emotion prediction from human speech is needed. This paper introduces a speech emotion recognition (SER) system that leverages supervised learning techniques to tackle cross-accent diversity. Distinctively, the system extracts a comprehensive set of nine speech features—Zero Crossing Rate, Mel Spectrum, Pitch, Root Mean Square values, Mel Frequency Cepstral Coefficients, chroma-stft, and three spectral features (Centroid, Contrast, and Roll-off) for refined speech signal processing and recognition. Seven machine learning models are employed, encompassing Random Forest, Logistic Regression, Decision Tree, Support Vector Machines, Gaussian Naive Bayes, K-Nearest Neighbors, ensemble learning, and four individual, hybrid deep learning models including Long short-term memory (LSTM) and 1-Dimensional Convolutional Neural Network (1D-CNN) with stratified cross-validation. Audio samples from diverse English regions are combined to train the models. The performance evaluation results of conventional machine learning and deep learning models indicate that the Random Forest-based feature selection model achieves the highest accuracy of up to 76% among the conventional machine learning models. Simultaneously, the 1D-CNN model with stratified cross-validation reaches up to 99% accuracy. The proposed framework enhances the cross-accent emotion recognition accuracy up to 86.3%, 89.87%, 90.27%, and 84.96% by margins of 14.71%, 10.15%, 9.6%, and 16.52% respectively.

Speaker identification is the process of automatically determining who is speaking from the known speakers by the model. It is crucial in voice-based authentication, forensic investigations, security and surveillance. In recent studies, the combination of convolutional neural network (CNN) and recurrent neural network (RNN) variants performed better than separate models of both. However, only limited studies are conducted in speaker identification using a combination of CNN and RNN variants. In this study, we proposed speaker identification using hybrid two-dimensional CNN (2DCNN) and bidirectional gated recurrent unit (BiGRU) to improve performance. The proposed model integrates the advantage of 2DCNN and BiGRU layers to improve the performance of the model. 2DCNN layers have the advantage of extracting short-term spatial features from input data and it has a limited number of parameters for computation. BiGRU layers have an advantage in extracting long-term temporal dependency between the features in both directions (i.e. backward and forward) and it is efficient in achieving convergence during training. Spectrograms of the speech were used as input in our proposed model because of the rich acoustic features of the speaker. To compare the performance of the proposed model, additional experiments are conducted using the models 2DCNN, CNN-LSTM, CNN-BiLSTM and CNN-GRU. The experiments were conducted on the VoxCeleb1 audio dataset, which consists of 153,516 utterances collected from the 1251 speakers. The accuracy, precision, recall and f1 score of the proposed model are 98.28%, 99.08%, 98.92% and 98.97% respectively. The proposed model was compared with the existing works to show the effectiveness of the proposed model. The experiment results and the comparison with the existing works show that the proposed model has higher performance than both existing works and other models experimented in this study.

<div class="section abstract"><div class="htmlview paragraph">The Exhaust Emission Control is a vital part of automotive development aimed at ensuring effective control of pollutants such as NOx, CO, and HC. The traditional method of calibrating emission control strategies is a highly time-consuming process, which requires extensive vehicle testing under a variety of operating conditions. The frequent updates in emission legislation requires a high-efficiency process to achieve a faster time-to-market. The use of Machine Learning (ML) in the domain of emission calibration is the need of the hour to proactively improve the process efficiency and achieve a faster time-to-market. This paper attempts to explores emerging trend of Machine Learning (ML) based data analysis that have improved the overall process efficiency of emission control calibration. The data generated by automated programs could be used directly in data analysis with minimal or no need for data cleaning. The Machine Learning (ML) models could be trained by historical data from relevant engine platforms to predict the output. The integration of Machine Learning (ML) models with automated measurement processes further enhances the process by enabling model-based calibration development. The use of automated programs and machine learning (ML) models could ensure high accuracy of the emission calibration data. This methodology could significantly reduce the need for volumes of measurements required for data analysis and calibration. This could further help in optimized usage of testing facilities, ultimately saving time and resources. A 70% overall savings in time and resources could be expected with the use of automation and machine learning models. This methodology also supports faster calibration development cycles that would be required for adhering to frequent legislative changes and achieving faster time-to-market.</div></div>

Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

Recent advancement in smart phones and computing technologies has played a vital role in people’s life. Develop a model to detect the human basic dynamic activities such as Amble, Climb stairs, coming down the stairs into the floor and human basic static activities like Sitting, Standing or Laying using the person’s smart phone and computers are the major work of this paper. Conventional Machine learning models like Logistic Regression, SVC, Decision tree, etc. results are compared with a recurrent deep neural network model named as Long Short Term Memory (LSTM). LSTM is proposed to detect the human behavior based on Human Activity Recognition (HAR) dataset. The data is monitored and recorded with the aid of sensors like accelerometer and Gyroscope in the user smart phone. HAR dataset is collected from 30 persons, performing different activities with a smart phone to their waists. The testing of the model is evaluated with respect to accuracy and efficiency. The designed activity recognition system can be manipulated in other activities like predicting abnormal human actions, disease by human actions, etc. The overall accuracy has improved to 95.40%.

Performance investigation of osmotically assisted reverse osmosis using explainable machine learning models: A comparative study

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

Conventional and Ensemble Machine Learning Models to Predict the Compressive Strength of Fly Ash Based Geopolymer Concrete

Missing values are a common problem of time series such as sensor-generated data due to issues of data collection, transmission, and storage. To deal with this problem, various data imputation methods have been proposed. Among these methods, variants of recurrent neural networks (RNNs) have attracted a lot of attention as they provide a natural representation of temporal dynamics. Though such methods have been shown to achieve higher imputation accuracy, they mostly focus on the modeling of temporal dynamics from a short-term perspective while ignoring the long-term features such as trend and seasonal information embedded in time series data. In this paper, we investigate different paradigms of time series imputation methods to capture temporal dynamics from both long-term and short-term perspectives. In particular, we propose a new learning paradigm called MuSDRI which combines the time series decomposition method Seasonal Trend decomposition using Loess (STL) with RNNs. Specifically, STL is used to decompose long sequences of time series into trend, seasonal, and remainder components such that long-term dynamics can be revealed; RNNs are used to capture local patterns from the remainder component extracted by STL such that short-term dynamics can be refined. Moreover, MuSDRI is able to handle time series with multiple seasonal patterns by learning their contributions with respect to the imputation task. We evaluate the proposed imputation methods on three real-world datasets. Experimental results show that the imputation methods considering both the long-term and short-term dynamics achieve higher imputation accuracy, and among them MuSDRI in general achieves the best performance.

<title>Abstract</title> Cardiovascular diseases (CVDs) are a leading cause of global mortality, necessitating early and accurate detection for improved patient outcomes. Electrocardiography (ECG) is a fundamental diagnostic tool for identifying cardiac abnormalities; however, traditional methods rely on manual interpretation and conventional machine learning (ML) models, which often struggle with feature extraction and long-range dependencies. Recent advancements in deep learning (DL) have led to the adoption of transformer-based architectures for ECG classification. In this study, we propose the Swin Transformer, a hierarchical vision transformer model, for automated ECG-based heart disease detection. By leveraging shifted window self-attention mechanisms, the Swin Transformer effectively captures both local and global dependencies, overcoming the limitations of convolutional and recurrent architectures. The proposed approach was evaluated on benchmark ECG datasets and compared with traditional ML models, including Random Forest, Gradient Boosting, Support Vector Machine (SVM), and Neural Networks. Experimental results demonstrate that the Swin Transformer significantly outperforms existing methods, achieving 99.8% accuracy, 99.72% precision, 99.91% recall, and an AUC of 99.99%, establishing a new benchmark in ECG classification. Additionally, eigenvalue analysis confirms the model’s ability to retain essential features while minimizing redundancy, ensuring robust generalization across diverse ECG patterns. Despite its superior performance, challenges such as computational complexity and interpretability remain, necessitating future research into Explainable AI (XAI) techniques, model optimization for real-time applications, and hybrid deep learning frameworks. Overall, our findings suggest that the Swin Transformer is a highly effective, scalable, and clinically viable solution for automated ECG-based cardiac disease detection, offering unprecedented accuracy and reliability over traditional approaches.

Even though the number of motorcycle crash accidents in Japan has trended downward over the past decade, there persists a necessity to propose effective safety measures targeting factors associated with fatal crash accidents. Previous studies have demonstrated the utility of various machine-learning models in classifying and investigating crash accidents involving motorcycles. However, the comprehensive examination of fatal cases in single-vehicle motorcycle crashes remains limited due to imbalanced crash data between fatal and non-fatal cases. Despite the ability of several conventional machine learning (ML) models to predict motorcycle crash severity, the imbalanced single-vehicle crash data poses a challenge in accurately classifying fatal crashes using ML models. To address this challenge, the deep q-learning network-based imbalanced classification (DQNIC), a modification of Lin’s DQNimb, was employed to classify single-vehicle motorcycle crashes (fatal and non-fatal). Moreover, SHAP value analysis was utilized to interpret the DQNIC model and explore the factors associated with fatal crashes. The 4-year crashes in Japan nationwide are used for empirical study. The significant findings indicate 1) that the DQNIC model demonstrates effective classification of fatal crashes and 2) that factors such as the crash type, road width, terrain, road alignment, and collision point exert significant influence on fatal crashes. Traffic safety professionals can use the findings of this study to implement effective measures to reduce the fatality rate of single-vehicle motorcycle crashes.

The reduction of NOx emissions is a paramount endeavor in contemporary engineering and energy production, as these emissions are closely linked to adverse environmental and health impacts. The prediction of NOx emission from gas turbines through several integrated data-driven machine learning methods has been evaluated in study. The study compares the performance of ensemble and conventional machine learning models, demonstrating superior accuracy achieved by the ensemble models. Specifically, the Random Forest model achieved an accuracy rate of 91.68%, XGBoost yielded an accuracy of 91.54%, and CATBoost exhibited the highest accuracy at 92.76%. These findings highlight the capability of data-driven machine learning techniques in enhancing NOx emission predictions in gas turbines. The improved prediction by ensembles can be utilized in the development and implementation of more effective control and mitigation strategies in practical applications. Through the application of these advanced machine learning approaches, the gas turbine industry can play a pivotal role in minimizing its environmental impact while optimizing operational efficiency. This study also provides valuable insights into the effectiveness of ensemble machine learning models, advancing our understanding of their capabilities in addressing the critical issue of NOx emissions from gas turbines.

A novel deep learning prediction model for concrete dam displacements using interpretable mixed attention mechanism

Prediction of rockhead using a hybrid N-XGBoost machine learning framework

Recent work has shown that machine learning (ML) models can skillfully forecast the dynamics of unknown chaotic systems. Short-term predictions of the state evolution and long-term predictions of the statistical patterns of the dynamics (“climate”) can be produced by employing a feedback loop, whereby the model is trained to predict forward only one time step, then the model output is used as input for multiple time steps. In the absence of mitigating techniques, however, this feedback can result in artificially rapid error growth (“instability”). One established mitigating technique is to add noise to the ML model training input. Based on this technique, we formulate a new penalty term in the loss function for ML models with memory of past inputs that deterministically approximates the effect of many small, independent noise realizations added to the model input during training. We refer to this penalty and the resulting regularization as Linearized Multi-Noise Training (LMNT). We systematically examine the effect of LMNT, input noise, and other established regularization techniques in a case study using reservoir computing, a machine learning method using recurrent neural networks, to predict the spatiotemporal chaotic Kuramoto–Sivashinsky equation. We find that reservoir computers trained with noise or with LMNT produce climate predictions that appear to be indefinitely stable and have a climate very similar to the true system, while the short-term forecasts are substantially more accurate than those trained with other regularization techniques. Finally, we show the deterministic aspect of our LMNT regularization facilitates fast reservoir computer regularization hyperparameter tuning.