The importance of robust flight delay prediction has recently increased in the air transportation industry. This industry seeks alternative methods and technologies for more robust flight delay prediction because of its significance for all stakeholders. The most affected are airlines that suffer from monetary and passenger loyalty losses. Several studies have attempted to analysed and solve flight delay prediction problems using machine learning methods. This research proposes a novel alternative method, namely social ski driver conditional autoregressive-based (SSDCA-based) deep learning. Our proposed method combines the Social Ski Driver algorithm with Conditional Autoregressive Value at Risk by Regression Quantiles. We consider the most relevant instances from the training dataset, which are the delayed flights. We applied data transformation to stabilise the data variance using Yeo-Johnson. We then perform the training and testing of our data using deep recurrent neural network (DRNN) and SSDCA-based algorithms. The SSDCA-based optimisation algorithm helped us choose the right network architecture with better accuracy and less error than the existing literature. The results of our proposed SSDCA-based method and existing benchmark methods were compared. The efficiency and computational time of our proposed method are compared against the existing benchmark methods. The SSDCA-based DRNN provides a more accurate flight delay prediction with 0.9361 and 0.9252 accuracy rates on both dataset-1 and dataset-2, respectively. To show the reliability of our method, we compared it with other meta-heuristic approaches. The result is that the SSDCA-based DRNN outperformed all existing benchmark methods tested in our experiment.
26 March 2019 in Journal of Statistics and Management Systems
The need for appropriate applications of the various similarity measures for clustering has arisen over the years as data massively keep on increasing. The issue of deciding which similarity measure is the best and on what kind of dataset have been a very cumbersome task in the field of data mining, data science, other related fields, and organizations that highly depends on the knowledge outcome from a huge set of data to make some vital / crucial decisions. This is because various datasets portray some common features associated with them; the need for clearer understanding of the various similarity measures for clustering different datasets is needed. This paper presents a critical review of various similarity measures applied in text and data clustering. A theoretical comparison has been made to check the suitability of the measures on different kind of data sets.
1 January 2018 in International Journal of Knowledge Engineering and Data Mining
The rapid progress of information technology and web makes it easier to store huge amount of collected textual information, e.g., blogs, news articles, e-mail messages, reviews and forum postings. The growing size of textual dataset with high-dimensions and natural language pose a big challenge making it hard for such information to be categorised efficiently. Document clustering is an automatic unsupervised machine learning technique that aimed at grouping related set of items into clusters or subsets. The target is creating clusters with high internal coherence, but different from each other substantially. This paper presents a new document clustering technique using N-grams and efficient similarity measure known as 'improved sqrt-cosine similarity measure'. Comprehensive experiments are conducted to evaluate our proposed clustering technique and compared with an existing method. The results of the experiments show that our proposed clustering technique outperforms the existing techniques.
Predicting pilots’ mental states is a critical challenge in aviation safety and performance, with electroencephalogram data offering a promising avenue for detection. However, the interpretability of machine learning and deep learning models, which are often used for such tasks, remains a significant issue. This study aims to address these challenges by developing an interpretable model to detect four mental states—channelised attention, diverted attention, startle/surprise, and normal state—in pilots using EEG data. The methodology involves training a convolutional neural network on power spectral density features of EEG data from 17 pilots. The model’s interpretability is enhanced via the use of SHapley Additive exPlanations values, which identify the top 10 most influential features for each mental state. The results demonstrate high performance in all metrics, with an average accuracy of 96%, a precision of 96%, a recall of 94%, and an F1 score of 95%. An examination of the effects of mental states on EEG frequency bands further elucidates the neural mechanisms underlying these states. The innovative nature of this study lies in its combination of high-performance model development, improved interpretability, and in-depth analysis of the neural correlates of mental states. This approach not only addresses the critical need for effective and interpretable mental state detection in aviation but also contributes to our understanding of the neural underpinnings of these states. This study thus represents a significant advancement in the field of EEG-based mental state detection.
1 January 2023 in Journal of Aviation/Aerospace Education & Research
This paper proposes a classification approach for flight delays using Bidirectional Long Short-Term Memory (BiLSTM) and Long Short-Term Memory (LSTM) models. Flight delays are a major issue in the airline industry, causing inconvenience to passengers and financial losses to airlines. The BiLSTM and LSTM models, powerful deep learning techniques, have shown promising results in a classification task. In this study, we collected a dataset from the United States (US) Bureau of Transportation Statistics (BTS) of flight on-time performance information and used it to train and test the BiLSTM and LSTM models. We set three criteria for selecting highly important features to train and test the models. The performance evaluation of the models and Confusion matrix shows that BiLSTM outperforms the LSTM model. In evaluating the models using the Mathews Correlation Coefficient (MCC), the BiLSTM model offers a better correlation of 0.99 between the original and predicted classes. Our experiment shows that for predicting flight delays, the BiLSTM model takes advantage of the forward and backward hidden sequences and the deep neural network for performance exploration and exploitation to achieve high accuracy, recall, and F1-Score. Our findings suggest that the BiLSTM model can effectively predict flight delays and provide valuable information for airlines, passengers, and airport managers.
1 January 2024 in Journal of Aviation/Aerospace Education & Research
Accurate and timely flight delay prediction cannot be overemphasized because of the ever-increasing demand for air travel and its importance in deploying intelligent transportation systems. Nonetheless, there has not been a universal solution to the problem, as more intelligent flight decision systems are required for the aviation industry's future growth. Existing flight delay classification and prediction approaches are mainly shallow traffic models and do not satisfy many applications in the real world. Our motivation to rethink the deep architecture model for predicting flight delays emanates from the problem. In this research, we proposed a technique that modified stacked autoencoder architecture parameters for training the network and understanding the link between space, time and information gained from the flight on-time data. We developed three different types of autoencoders based on the architecture of the modified stacked autoencoder. The models learn the generic flight delay features, and it's trained greedily in a layer-wise fashion. To the best of our knowledge, this is the first time these performances of vanilla autoencoder, logistic regression autoencoder and Multilayer perceptron for classification were evaluated based on the developed modified stacked autoencoder architecture. Moreover, our experiment demonstrates that the models achieved varying levels of accuracy in the flight delay classifications task. The deep vanilla autoencoder shows superior accuracy, recall and precision performance compared to logistic regression autoencoder and Multilayer perceptron autoencoders at different parameter settings.