There has been much recent work on fraud and Anti Money Laundering (AML) detection using machine learning techniques. However, most algorithms are based on supervised techniques. Studies show that supervised techniques often have the limitation of not adapting well to new irregular fraud patterns when the dataset is highly imbalanced. Instead, unsupervised learning can have a better capability to find anomalous and irregular patterns in new transaction. Despite this, unsupervised techniques also have the disadvantage of not being able to give state-of-the-art detection results. We propose a suite of unsupervised and deep learning techniques to implement an anti-money laundering and fraud detection system to resolve this limitation. The system leverages three deep learning models: autoencoder (AE), variational autoencoder (VAE), and a generative adversarial network. We preprocess the given dataset to separate the Transaction Date attribute into its base components to capture time-related fraud patterns. Also, Wasserstein Generative Adversarial Network (WGAN) is used to generate fraud transactions, which are then mixed with the base dataset to form a more balanced mixed dataset. These two datasets are used to train the AE and VAE models. We built two versions of the AE model (single-loss and multi-loss) besides a novel method of calculating the anomaly score threshold, called Recall-First Threshold (RFT), which helps enhance the model's performance. Experimental results demonstrated that the False Positive Rate (FPR) drops down to as low as 7% in the proposed multi-loss AE model. In comparison, we achieved an accuracy of 93%, with 100% of the fraud transactions recalled successfully.

Machine learning has been increasingly used in biochemistry. However, in organic chemistry and other experiment-based fields, data collected from real experiments are inadequate and the current coronavirus disease (COVID-19) pandemic has made the situation even worse. Such limited data resources may result in the low performance of modeling and affect the proper development of a control strategy. This paper proposes a feasible machine learning solution to the problem of small sample size in the bio-polymerization process. To avoid overfitting, the variational auto-encoder and generative adversarial network algorithms are used for data augmentation. The random forest and artificial neural network algorithms are implemented in the modeling process. The results prove that data augmentation techniques effectively improve the performance of the regression model. Several machine learning models were compared and the experimental results show that the random forest model with data augmentation by the generative adversarial network technique achieved the best performance in predicting the molecular weight on the training set (with an R² of 0.94) and on the test set (with an R² of 0.74), and the coefficient of determination of this model was 0.74.

In‐line inspection (ILI) robot has been considered as an inevitable requirement to perform non‐destructive testing methods efficiently and economically. The detection of flaws that could lead to leakages in buried concrete pipes has been an area of great concern to the oil and gas industry and water resource‐based industry. The major problem is the difficulty in modelling the detection of cracks as a result of its irregularity and randomness that cannot be easily detected. This work covers the study of defect detection of non‐destructive testing methods using fusion inspect sensors, light detection and ranging, and optic sensors. Studies on ILI robots are also reviewed to construct an efficient gauge. Nevertheless, the study on current support vector machine (SVM) technique is centred as the main classification engine for the combined sensory data. The prototype robot has been designed and successfully operated in a lab‐scale environment. Intuitively, the obtained data described the status of inspected pipe clearly. Sensors from the proposed list also well integrated as attaching to the robot. The experiments with SVM techniques to evaluate the feasibility of defects detection also achieved remarkable results.