Classification of Rail Switch Data Using Machine Learning Techniques

According to Common NOise aSSessment methOdS in EUrope (CNOSSOS-EU) in Annex II of Directive 2002/49/EC, noise from road, rail and airplane traffic, as well as noise from industries, shall be assessed using this common method. For railway noise in Sweden, noise assessment has previously been done using the Nordic Assesment Method for Train Noise, revised 1996 (NMT96). NMT96 includes a simple correction for rail joints of +3dB and for rail switches of +6dB. CNOSSOS-EU instead introduces a speed dependent correction based on a third octave band wavelength spectrum adding up to 20dB rolling noise energy in lower frequencies and down to -40 dB in higher frequencies. Measurements recently performed for two different rail switch types along the Swedish rail system indicate that the frequency distribution corresponds well to the CNOSSOS-EU correction for one type of rail switch but not for the other, and for the overall level difference the opposite is true. In order to investigate to what extent this deviation is affecting noise exposure an inventory of more than 11000 rail switches along the swedish railroad network has been performed to identify what types are situated in densely populated areas such as railway stations.

Accurate real-time bus arrival information is essential for an efficient public transport network, as it significantly impacts passenger experience, system reliability, reduced waiting times, dwell times, and operational efficiency. In Sri Lanka's public transport system, current bus arrival time computations primarily rely on static data, neglecting real-time information and critical factors influencing travel times. This highlights the need to identify the unique variables affecting bus arrival times within the Sri Lankan context and to develop robust prediction models that account for these influences. While traditional methods such as Historical Average Models, Regression, Time Series Analysis, and Kalman Filtering have been used in previous research for short-term travel time predictions, Machine Learning (ML) approaches have proven to deliver superior accuracy. ML models are regarded as the most effective for heterogeneous, lane-less traffic conditions with varying traffic volumes, such as those found in Sri Lanka. ML techniques excel in processing large, high-quality datasets and provide accurate predictions by accounting for all relevant variables influencing travel times. Although research has been conducted on developing various basic ML models for travel time prediction, there is a noticeable gap in studies comparing these models to determine the most suitable one for the Sri Lankan context. A Long- Short Term Memory (LSTM) neural network is a deep learning model that is capable of handling long-term dependencies. In the context of bus travel time prediction, LSTMs can leverage historical traffic and travel data to capture temporal patterns and fluctuations that influence travel times. By evaluating LSTMs against basic machine learning models, this study seeks to explore the advantages of applying deep learning techniques to transportation forecasting, ultimately contributing to more accurate and efficient predictive systems in transit planning. The ML models selected in this study include two basic traditional models K- Nearest Neighbours (KNN) and Support Vector Regression (SVR) and four advanced models that utilize ensemble techniques and advanced optimization as Random Forest Regression (RFR), Ada Boost, XG Boost and Gradient Boosting Machine (GBM). The performance of these models was compared with the LSTM model to identify the gap in their accuracies.

This paper presents an approach that aims to detect track geometry defects using machine learning techniques. It specifically involves the implementation of a bidirectional long short-term memory (LSTM) neural network to analyze displacement data derived from sensor acceleration signals. The methodology is validated using the standards set by the Rail Industry Safety and Standards Board (RISSB). By utilizing a dynamics vehicle model simulation, the approach extracts displacement data, which enables the training of the LSTM model. The neural network consists of three layers: a bidirectional LSTM layer, a fully connected layer, and an output layer that indicates the defect label for a given input. Through experimentation with various parameter configurations, the current implementation achieves a detection accuracy of approximately 92.7% within a 10-s time window. The proposed approach demonstrates the potential of machine learning in intelligently identifying track geometry defects, highlighting its practicality in the rail industry. By automating the defect detection process, this technique provides valuable insights for maintenance crews, facilitating timely repairs and enhancing safety and operational efficiency.

Temperature changes have widespread impacts on the environment, economy, and municipal planning. Generating accurate climate prediction at finer spatial resolution through downscaling could help better assess the future effects of climate change on a local scale. Ensembles of multiple climate models have been proven to improve the accuracy of temperature prediction. Meanwhile, machine learning techniques have shown high performance in solving various predictive modeling problems, which make them a promising tool for temperature downscaling. This study investigated the performance of machine learning (long short-term memory (LSTM) networks and support vector machine (SVM)) and statistical (arithmetic ensemble mean (EM) and multiple linear regression (MLR)) methods in developing multi-model ensembles for downscaling long-term daily temperature. A case study of twelve meteorological stations across Ontario, Canada, was conducted to evaluate the performance of the proposed ensembles. The results showed that both machine learning and statistical techniques performed well at downscaling daily temperature with multi-model ensembles and had similar performance with relatively high accuracy. The R2 of 12 stations ranged between 0.756 and 0.820 and RMSE ranged between 4.318 and 7.063 °C. Both machine learning and statistical ensembles for downscaling had difficulty in predicting extreme values for temperature below − 10 °C and above 20 °C. The results provided technical support for using statistical and machine learning methods to generate high-resolution daily temperature prediction.

The research study is to predict human activity recognition and analyze their strength in machine learning (ML) processes to achieve precision and also to determine performance of human activities. The framework to classify the Novel Long Short Term Memory (LSTM) and Decision Tree (DT) to perform all measures. This research study used the Novel Long Short Term Memory and Decision Tree to perform the required actions to accurately identify body movements in adjacent film sequence. Recent study findings and a threshold of 0.05%, as well as 95% confidence interval and standard parameter estimates, were castoff in a study 47 samples divided into two groups calculated using the G-power of 80%. Since the novel Long Short Term Memory (LSTM) algorithm and local invariant methods have achieved an accuracy of 93.83% in predicting the activity analysis, this research needs to obtain improved accuracy to perform activity prediction by using the Decision Tree algorithm. When applied to human activity analysis, the Novel Long Short Term Memory technique was shown to have an accuracy of 90.12 percent, with a 95% confidence interval including the value 0.045 (p 0.05). Researchers found that when comparing two algorithms for analyzing human behaviour, Long Short Term Memory (LSTM) performed much better than Decision Tree (DT).

Purpose This study aims to enhance cryptocurrency price and trend prediction by applying advanced machine learning (ML) techniques. Given the market’s high volatility and complexity, the research identifies effective models for different conditions, providing insights for investors and risk management. Design/methodology/approach This study proposes a six-stage framework for cryptocurrency price prediction, integrating advanced ML techniques. Data from ten cryptocurrencies are processed, extracting 37 key features, including return, the Fear and Greed Index and various technical indicators. The model employs Deep Q-Networks (DQN), Long Short-Term Memory (LSTM) and multiple regression methods such as linear regression, support vector regression, ridge, LASSO, decision tree, Random Forest, multi-layer perceptron, stochastic gradient descent, elastic net and Bayesian regression. Model performance is evaluated using trading strategies and metrics like accuracy, sensitivity, recall, MSE, MAE and F1-score. Findings The results indicate that complex models like DQN and LSTM excel in volatile markets due to their ability to capture intricate price patterns, whereas simpler models such as linear regression and ridge regression perform better in stable conditions. The multi-layered parallel design enhances computational efficiency, enabling independent asset evaluation. These findings highlight the potential of artificial intelligence in improving prediction accuracy and supporting informed investment decisions. Originality/value This research introduces a novel six-stage ML framework incorporating diverse predictive models and key features for cryptocurrency forecasting. The multi-layered parallel approach enhances computational efficiency, setting this study apart from existing research. The comparative analysis of models offers valuable guidance for investors, traders and financial analysts navigating volatile cryptocurrency markets.

Oil-immersed power transformer being a vital component in power system, any type of faults in the transformer can cause severe outage. Therefore, continuous monitoring of its in-service behaviour should be done to improve the performance of the power system by avoiding catastrophic failures. Predicting the dissolved gas level in transformer oil is essential for detecting a developing fault in the transformer. Artificial neural network (ANN) is a powerful tool for application of establishing the power transformers’ fault prediction. In this paper, the long short-term memory (LSTM) model was established to predict the future values of DGA data based on the historical gas concentration rates. Then, the accuracy and factors influencing the LSTM model are analysed with classical regression models and machine learning techniques. This selected machine learning approach using LSTM yields a satisfactory result. It can make a reliable prediction and detection of transformer health conditions with respect to generated combustible gas rate.KeywordsDissolved gas analysis (DGA)Long short-term memory (LSTM)Artificial neural network (ANN)Fault diagnosisNeural networkPower transformer testing

This project focuses on improving the detection of network attacks by using a machine learning technique known as Long Short-Term Memory (LSTM) networks. LSTM networks are a type of neural network that excels at analyzing sequences of data, making them well-suited for identifying patterns associated with network intrusions. To enhance the LSTM model's effectiveness, we introduce new probability features that help the model better distinguish between normal and malicious activities. Our approach includes collecting network data, preprocessing it to make it suitable for training, and then using this data to train the LSTM model. We evaluate the model's performance using a range of metrics to ensure its accuracy and reliability. The results indicate that our method significantly improves the detection rate of network attacks while also reducing the number of false alarms. This means that our LSTM-based model not only catches more real threats but also makes fewer mistakes in identifying normal activities as attacks. Overall, this project showcases the potential of advanced machine learning techniques, like LSTM networks, to enhance cyber security measures and protect against network threats more effectively.

While the growing accessibility of technology improves usability, it also creates more opportunities for cybercriminals to exploit vulnerabilities, significantly accelerating the proliferation of cybersecurity attacks. Deep learning (DL) approaches present significant advancements over conventional machine learning (ML) techniques by automating feature selection and extraction while minimizing external dependencies. This study proposes a deep learning-based model to enhance cyberattack detection and ensure that data security goals are achieved. This study employs a quantitative research design, utilizing simulation and modeling as the primary analytical tools. The dataset used is the Canadian Institute for Cybersecurity Intrusion Detection System (CIC-IDS-2017) dataset. Three distinct DL algorithms are used to design the detection models, namely, Deep Neural Network (DNN), Long Short-Term Memory (LSTM), and Recurrent Neural Network (RNN). The performance comparison metrics are F1-score, accuracy, sensitivity, false positive rate (FPR), specificity, positive predictive value (PPV), false negative rate (FNR), and negative predictive value (NPV). Optimization concepts are integrated to enhance the detection efficiency in web-based systems, including loss functions, gradient-based optimization, and efficient model generalization techniques. The results of k-fold cross-validation show LSTM’s higher scores for F1-score (94.6%), recall (94.7%), accuracy (94.8%), and precision (94.6%). LSTM outperformed RNN and DNN, achieving the highest accuracy, precision, specificity, and sensitivity at 94.7%, 94.3%, 98.9%, and 94.7% respectively, validating LSTM's superior generalizability for cyberattack detection tasks.

Automating real-time sign language translation through deep learning and machine learning techniques can greatly enhance communication between the deaf community and the wider public. This research investigates how these technologies can change the way individuals with speech impairments communicate. Despite advancements, developing accurate models for recognizing both static and dynamic gestures remains challenging due to variations in gesture speed and length, which affect the effectiveness of the models. We introduce a hybrid approach that merges machine learning and deep learning methods for sign language recognition. We provide new model for the recognition of Kazakh Sign Language (QazSL), employing five algorithms: Support Vector Machine (SVM), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Networks (CNN) with VGG19, ResNet-50, and YOLOv5. The models were trained on a QazSL dataset of more than 4,400 photos. Among the assessed models, the GRU attained the highest accuracy of 100%, followed closely by SVM and YOLOv5 at 99.98%, VGG19 at 98.87% for dynamic dactyls, LSTM at 85%, and ResNet-50 at 78.61%. These findings illustrate the comparative efficacy of each method in real-time gesture recognition. The results yield significant insights for enhancing sign language recognition systems, presenting possible advancements in accessibility and communication for those with hearing impairments.

Data analytics is rapidly growing field in both academia and industry dealing with processing and interpreting large and complex data sets. It has got already many successful applications via advancing machine (ML) and deep learning (DL) techniques, starting to evolve in the upstream petroleum industry as well. The industry operates now with huge amount of sensors installed in different facilities, particularly in production and injection wells. These sensors provide millions of measurements, such as pressure, temperature, and rate every year for every well. The measurements may be highly correlated and carry crucial information for decision making. This paper concentrates on pressure-rate data sets accumulated with massive installation of permanent downhole gauges in such wells. The non-linear autoregessive (NARX) and the long short term memory (LSTM) neural networks were assembled and tested on a synthetic data set to compare results of pressure prediction, already addressed in the literature. The LSTM provided better predictions, but did not manage to capture entirely the pattern of the data. The shifting window method was then applied to improve the LSTM prediction capabilities, based on previous successful application in forecasting electricity demand. The method implies smooth transition from training to prediction improving network performance. The LSTM with the shifting window provided more accurate results for pressure prediction, and it was then successfully applied for rate prediction. Testing of different configurations of the LSTM network has shown that the pressure prediction performs well with less number of nodes in the hidden layers if compared with the rate predictions. Significant error decrease is achieved relatively fast (after 20 iterations) for both prediction tasks, making such predictions feasible for large data sets. The results provide basis for filling gaps in well monitoring data and short-term performance forecast, crucial tasks for decision making in all the industries operating with wells.

Deep learning (DL) is now generally acknowledged as the benchmark and evolution in machine learning (ML) fields. Further more, it has steadily suited the most extensively in computational techniques for ML, delivering excellent outcomes in several challenging intellectual works that have equal or still outperformed human ability. DL has the advantage of learning from enormous amounts of data. Here, the DL approach has been applied to classify thunderstorms and non-thunderstorms with a meteorological dataset. Daily observational hourly data sets from 2016 to 2021 have been used to classify the incidence of thunderstorms and non-thunderstorms. Three DL approaches are used: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) to classify thunderstorm incidences. These DL techniques are compared with conventional ML techniques, showing that DL approaches outperformed ML. The CNN method provides the highest performance with 92.01% accuracy among all DL and ML approaches.

Renewable energy (RE) plays a critical role in mitigating climate change and ensuring energy security globally. As the adoption of RE technologies continues to grow, accurate forecasting of renewable energy consumption has become increasingly important for grid planning and integration. This paper provides a comprehensive review of the key factors influencing renewable energy consumption and the application of machine learning and deep learning models for forecasting RE consumption. The study examines various socioeconomic, demographic, and environmental variables that have been found to impact the demand and usage of renewable energy sources such as solar, wind, and hydropower. Factors like GDP, population, energy prices, government policies, and weather conditions are discussed in detail for their influence on RE consumption patterns. The paper also analyzes how technological advancements, consumer behavior, and energy efficiency measures can shape renewable energy demand. Furthermore, the paper evaluates the performance of various machine learning techniques, which have been done in various research from 2020 to 2024, including artificial neural networks, support vector machines, random forests, gradient boosting, and deep learning models such as long short-term memory (LSTMs) and convolutional neural networks (CNNs), in forecasting renewable energy consumption. The study analyzes the strengths, limitations, and accuracy of these models based on case studies across residential, commercial, and industrial sectors. The findings indicate that deep learning models, particularly LSTMs and CNNs, have outperformed traditional machine learning techniques in renewable energy consumption forecasting. These deep learning models are able to capture the complex nonlinear relationships and temporal dependencies inherent in RE consumption data, leading to higher accuracy and better generalization performance.

Utilizing various statistical methods to model the impact of the COVID-19 pandemic on Gross domestic product

Plant stress reduction research has advanced significantly with the use of Artificial Intelligence (AI) techniques, such as machine learning and deep learning. This is a significant step toward sustainable agriculture. Innovative insights into the physiological responses of plants mostly crops to drought stress have been revealed through the use of complex algorithms like gradient boosting, support vector machines (SVM), recurrent neural network (RNN), and long short-term memory (LSTM), combined with a thorough examination of the TYRKC and RBR-E3 domains in stress-associated signaling proteins across a range of crop species. Modern resources were used in this study, including the UniProt protein database for crop physiochemical properties associated with specific signaling domains and the SMART database for signaling protein domains. These insights were then applied to deep learning and machine learning techniques after careful data processing. The rigorous metric evaluations and ablation analysis that typified the study’s approach highlighted the algorithms’ effectiveness and dependability in recognizing and classifying stress events. Notably, the accuracy of SVM was 82%, while gradient boosting and RNN showed 96%, and 94%, respectively and LSTM obtained an astounding 97% accuracy. The study observed these successes but also highlights the ongoing obstacles to AI adoption in agriculture, emphasizing the need for creative thinking and interdisciplinary cooperation. In addition to its scholarly value, the collected data has significant implications for improving resource efficiency, directing precision agricultural methods, and supporting global food security programs. Notably, the gradient boosting and LSTM algorithm outperformed the others with an exceptional accuracy of 96% and 97%, demonstrating their potential for accurate stress categorization. This work highlights the revolutionary potential of AI to completely disrupt the agricultural industry while simultaneously advancing our understanding of plant stress responses.