1,720,987 research outputs found
Fault detection and diagnosis for rotating machinery: A model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms
No full textFault Detection and Diagnosis (FDD) of rotating machinery plays a key role in reducing the maintenance costs of the manufacturing systems. How to improve the FDD accuracy is an open and challenging issue. To make full use of signals and reveal all the fault features, this paper proposes a new feature engineering model which combines Fast Fourier Transform (FFT), Continuous Wavelet Transform (CWT) and statistical features of raw signals. Then a novel Convolutional Long Short-Term Memory (CLSTM) is developed to understand and classify these multi-channel array inputs. In order to evaluate the effectiveness of the proposed model, three different datasets are used. The paper performs a sensitivity analysis on the input channels to evaluate the efficiency of the proposed multi-domain feature set in different DL architectures, where CLSTM shows its superiority in understanding the feature set. Secondly, a comprehensive review of the state-of-the-art models is conducted, and twelve algorithms are chosen for the comparison to evaluate the performance of the proposed FDD model. The paper also performs an input length sensitivity analysis, showing that the proposed model can achieve 100 % of accuracy with shorter inputs compared to other models, meaning that it causes less delay in an online condition monitoring system. The results demonstrate the superiority of the proposed model over the state-of-the-art models in terms of accuracy on different datasets
Anthropogenic influence on global warming for effective cost-benefit analysis: a machine learning perspective
No full text
ConvLSTM-based Sound Source Localization in a manufacturing workplace
No full textIn this paper, Sound Source Localization (SSL) is explored as an approach to localize both human operators and machines emitting sound signals in a manufacturing workplace. In particular, a comprehensive analysis of the source localization ability of a state-of-the-art deep learning architecture in environments of increasing complexity is presented. Scenarios including single, dual, and multiple sound sources, in the form of both human and Computerized Numerical Control (CNC) machines, are investigated, as well as configurations with a mix of stationary and moving sources. Our work contributes to the extant literature by enriching previous research findings primarily devoted to single stationary sources. Furthermore, by focusing on the simultaneous and centralized detection of sources of different nature and type, it diverges from traditional SSL studies in manufacturing, which emphasize the localization of humans by robots in human–robot interaction, and presents a localization approach which enables a broader control over the workspace. For the localization task, a Convolutional LSTM architecture able to capture both spatial and temporal sound characteristics is also proposed, with each source assigned a dedicated model. Extensive experiments were carried out for each scenario in a simulated environment, where different levels of noise were also applied. The results showed the remarkable accuracy and robustness of the deep learning models when it comes to localizing single and dual stationary sources, as well as single moving sources. For multiple stationary and moving sources a general decline in the detection performance was observed, alongside a heightened sensitivity to noise
Discovering bayesian market views for intelligent asset allocation
No full textAlong with the advance of opinion mining techniques, public mood has been found to be a key element for stock market prediction. However, how market participants’ behavior is affected by public mood has been rarely discussed. Consequently, there has been little progress in leveraging public mood for the asset allocation problem, which is preferred in a trusted and interpretable way. In order to address the issue of incorporating public mood analyzed from social media, we propose to formalize public mood into market views, because market views can be integrated into the modern portfolio theory. In our framework, the optimal market views will maximize returns in each period with a Bayesian asset allocation model. We train two neural models to generate the market views, and benchmark the model performance on other popular asset allocation strategies. Our experimental results suggest that the formalization of market views significantly increases the profitability ( to annually) of the simulated portfolio at a given risk level
Automatic Visual Inspection of Rare Defects: A Framework based on GP-WGAN and Enhanced Faster R-CNN
Full text linkA current trend in industries such as semiconductors and foundry is to shift their visual inspection processes to Automatic Visual Inspection (AVI) systems, to reduce their costs, mistakes, and dependency on human experts. This paper proposes a two-staged fault diagnosis framework for AVI systems. In the first stage, a generation model is designed to synthesize new samples based on real samples. The proposed augmentation algorithm extracts objects from the real samples and blends them randomly, to generate new samples and enhance the performance of the image processor. In the second stage, an improved deep learning architecture based on Faster R-CNN, Feature Pyramid Network (FPN), and a Residual Network is proposed to perform object detection on the enhanced dataset. The performance of the algorithm is validated and evaluated on two multi-class datasets. The experimental results performed over a range of imbalance severities demonstrate the superiority of the proposed framework compared to other solutions
Multimodal sentiment and emotion recognition in hyperbolic space
No full textPrior approaches for multimodal sentiment and emotion recognition (SER) exploit input data representations and neural networks based on the classical Euclidean geometry. Recently, however, the hyperbolic metric proved to be a powerful tool for data mapping, being able to capture the hierarchical structure of the relations among elements in the data. In this paper we propose the use of hyperbolic learning for SER, and show that the inclusion in the neural network of hyperbolic structures mapping the input into the hyperbolic space can improve the quality of the predictions. The benefits brought by the hyperbolic features are evaluated by developing extensions of existing methods following two approaches. From one side, we modified state-of-the-art models by including hyperbolic output layers. From the other, we generated hybrid neural network architectures by combining hyperbolic and Euclidean layers according to different schemes. The proposed hyperbolic models were tested on several classification tasks applied to benchmark multimodal SER datasets. Experiments gave strong evidence that in both simple and complex networks the introduction of a hyperbolic structure results in an improvement of the model accuracy. Specifically, the combined use of hyperbolic and Euclidean layers showed superior performance in almost all the classification tasks
- …
