Multimodal emotion recognition from electroencephalogram (EEG) and eye movement signals has shown to be a promising approach to provide more discriminative information about human emotional states. However, most current works rely on a subject-dependent approach, limiting their applicability to new users. Recently, some studies have explored multimodal domain adaptation to address the mentioned issue by transferring information from known subjects to new ones. Unfortunately, existing methods are still exposed to negative transfer as a suboptimal distribution alignment is performed between subjects, while irrelevant information is not discarded. In this article, we present a multimodal and multisource domain adaptation (MMDA) method, which adopts the following three strategies: 1) marginal and conditional distribution alignments must be performed between each known subject and a new one; 2) relevant distribution alignments must be prioritized to avoid a negative transfer; and 3) modality fusion results should be improved by extracting more discriminative features from EEG signals and selecting relevant features across modalities. Our proposed method was evaluated with leave-one-subject-out cross validation on four public datasets: SEED, SEED-GER, SEED-IV, and SEED-V. Experimental results show that our proposal outperforms state-of-the-art results for each dataset when subject data from different sessions are combined into a single dataset. Moreover, MMDA exceeds the state of the art in 8 out of 11 different sessions when each session is evaluated.
Early detection of fault events through electromechanical systems operation is one of the most attractive and critical data challenges in modern industry. Although these electromechanical systems tend to experiment with typical faults, a common event is that unexpected and unknown faults can be presented during operation. However, current models for automatic detection can learn new faults at the cost of forgetting concepts previously learned. This article presents a multiclass incremental learning (MCIL) framework based on 1D convolutional neural network (CNN) for fault detection in induction motors. The presented framework tackles the forgetting problem by storing a representative exemplar set from past data (known faults) in memory. Then, the 1D CNN is fine‐tuned over the selected exemplar set and data from new faults. Test samples are classified using nearest centroid classifier (NCC) in the feature space from 1D CNN. The proposed framework was evaluated and validated over two public datasets for fault detection in induction motors (IMs): asynchronous motor common fault (AMCF) and Case Western Reserve University (CWRU). Experimental results reveal the proposed framework as an effective solution to incorporate and detect new induction motor faults to already known, with a high accuracy performance across different incremental phases.
17 March 2025 in IEEE Transactions on Instrumentation and Measurement
Multimodal physiological data from Electroencephalogram (EEG) and eye movement (EM) signals have been shown to be useful in effectively recognizing human emotional states. Unfortunately, individual differences reduce the applicability of existing multimodal classifiers to new users, as low performance is usually observed. Indeed, existing works mainly focus on multimodal domain adaptation from a labeled source domain and unlabeled target domain to address the mentioned problem, transferring knowledge from known subjects to new one. However, a limited set of labeled target data has not been effectively exploited to enhance the knowledge transfer between subjects. In this paper, we propose a multimodal semisupervised domain adaptation method, called Cross-modal Joint Distribution Adaptation (CMJDA), to address the limitations of existing works, following three strategies: (1) discriminative features are exploited per modality through independent neural networks, (2) correlated features and consistent predictions are produced between modalities, and (3) marginal and conditional distributions are encouraged to be similar between the labeled source data, limited labeled target data, and abundant unlabeled target data. We conducted comparison experiments on two public benchmarks for emotion recognition, SEED-IV and SEED-V, using leave-one-out cross-validation. Our proposal achieves an average accuracy of 92.50% and 96.13% across the three available sessions on SEED-IV and SEED-V, only including 3 labeled target samples per class from the first recorded trial.
Creating synthetic images of trabecular tissue provides an alternative for researchers to validate algorithms designed to study trabecular bone. Developing synthetic images requires baseline data, such as datasets of digital biological samples or templates, often unavailable due to privacy restrictions. Even when this baseline is available, the standard procedure combines the information to generate a single template as a starting point, reducing the variability in the generated synthetic images. This work proposes a methodology for building synthetic images of trabecular bone structure, creating a 3D network that simulates it. Next, the technical characteristics of the micro-CT scanner, the biomechanical properties of trabecular bones, and the physics of the imaging process to produce a synthetic image are simulated. The proposed methodology does not require biological samples, datasets, or templates to generate synthetic images. Since each synthetic image built is unique, the methodology is enabled to generate a vast number of synthetic images, useful in the performance comparison of algorithms under different imaging conditions. The created synthetic images were assessed using microarchitecture parameters of reference, and experimental results provided evidence that the obtained values match approaches requiring initial data. The scope of this methodology covers research aspects related to using synthetic images in further biomedical research or the development of educational training tools to understand the medical image.