Explore the vast range of titles available.

For a long time, researchers have tried to find a way to analyze tropical cyclone (TC) intensity in real-time. Since there is no standardized method for estimating TC intensity and the most widely used method is a manual algorithm using satellite-based cloud images, there is a bias that varies depending on the TC center and shape. In this study, we adopted convolutional neural networks (CNNs) which are part of a state-of-art approach that analyzes image patterns to estimate TC intensity by mimicking human cloud pattern recognition. Both two dimensional-CNN (2D-CNN) and three-dimensional-CNN (3D-CNN) were used to analyze the relationship between multi-spectral geostationary satellite images and TC intensity. Our best-optimized model produced a root mean squared error (RMSE) of 8.32 kts, resulting in better performance (~35%) than the existing model using the CNN-based approach with a single channel image. Moreover, we analyzed the characteristics of multi-spectral satellite-based TC images according to intensity using a heat map, which is one of the visualization means of CNNs. It shows that the stronger the intensity of the TC, the greater the influence of the TC center in the lower atmosphere. This is consistent with the results from the existing TC initialization method with numerical simulations based on dynamical TC models. Our study suggests the possibility that a deep learning approach can be used to interpret the behavior characteristics of TCs.

Design requirements for different mechanical metamaterials, porous constructions and lattice structures, employed as tissue engineering scaffolds, lead to multi-objective optimizations, due to the complex mechanical features of the biological tissues and structures they should mimic. In some cases, the use of conventional design and simulation methods for designing such tissue engineering scaffolds cannot be applied because of geometrical complexity, manufacturing defects or large aspect ratios leading to numerical mismatches. Artificial intelligence (AI) in general, and machine learning (ML) methods in particular, are already finding applications in tissue engineering and they can prove transformative resources for supporting designers in the field of regenerative medicine. In this study, the use of 3D convolutional neural networks (3D CNNs), trained using digital tomographies obtained from the CAD models, is validated as a powerful resource for predicting the mechanical properties of innovative scaffolds. The presented AI-aided or ML-aided design strategy is believed as an innovative approach in area of tissue engineering scaffolds, and of mechanical metamaterials in general. This strategy may lead to several applications beyond the tissue engineering field, as we analyze in the discussion and future proposals sections of the research study.

The three-dimensional convolutional neural network (3D-CNN) and long short-term memory (LSTM) have consistently outperformed many approaches in video-based facial expression recognition (VFER). The image is unrolled to a one-dimensional vector by the vanilla version of the fully-connected LSTM (FC-LSTM), which leads to the loss of crucial spatial information. Convolutional LSTM (ConvLSTM) overcomes this limitation by performing LSTM operations in convolutions without unrolling, thus retaining useful spatial information. Motivated by this, in this paper, we propose a neural network architecture that consists of a blend of 3D-CNN and ConvLSTM for VFER. The proposed hybrid architecture captures spatiotemporal information from the video sequences of emotions and attains competitive accuracy on three FER datasets open to the public, namely the SAVEE, CK + , and AFEW. The experimental results demonstrate excellent performance without external emotional data with the added advantage of having a simple model with fewer parameters. Moreover, unlike the state-of-the-art deep learning models, our designed FER pipeline improves execution speed by many factors while achieving competitive recognition accuracy. Hence, the proposed FER pipeline is an appropriate candidate for recognizing facial expressions on resource-limited embedded platforms for real-time applications.

In recent years, the importance of catching humans’ emotions grows larger as the artificial intelligence (AI) field is being developed. Facial expression recognition (FER) is a part of understanding the emotion of humans through facial expressions. We proposed a robust multi-depth network that can efficiently classify the facial expression through feeding various and reinforced features. We designed the inputs for the multi-depth network as minimum overlapped frames so as to provide more spatio-temporal information to the designed multi-depth network. To utilize a structure of a multi-depth network, a multirate-based 3D convolutional neural network (CNN) based on a multirate signal processing scheme was suggested. In addition, we made the input images to be normalized adaptively based on the intensity of the given image and reinforced the output features from all depth networks by the self-attention module. Then, we concatenated the reinforced features and classified the expression by a joint fusion classifier. Through the proposed algorithm, for the CK+ database, the result of the proposed scheme showed a comparable accuracy of 96.23%. For the MMI and the GEMEP-FERA databases, it outperformed other state-of-the-art models with accuracies of 96.69% and 99.79%. For the AFEW database, which is known as one in a very wild environment, the proposed algorithm achieved an accuracy of 31.02%.

A micro-expression is defined as an uncontrollable muscular movement shown on the face of humans when one is trying to conceal or repress his true emotions. Many researchers have applied the deep learning framework to micro-expression recognition in recent years. However, few have introduced the human visual attention mechanism to micro-expression recognition. In this study, we propose a three-dimensional (3D) spatiotemporal convolutional neural network with the convolutional block attention module (CBAM) for micro-expression recognition. First image sequences were input to a medium-sized convolutional neural network (CNN) to extract visual features. Afterwards, it learned to allocate the feature weights in an adaptive manner with the help of a convolutional block attention module. The method was testified in spontaneous micro-expression databases (Chinese Academy of Sciences Micro-expression II (CASME II), Spontaneous Micro-expression Database (SMIC)). The experimental results show that the 3D CNN with convolutional block attention module outperformed other algorithms in micro-expression recognition.

Motor imagery (MI) is a crucial research field within the brain–computer interface (BCI) domain. It enables patients with muscle or neural damage to control external devices and achieve movement functions by simply imagining bodily motions. Despite the significant clinical and application value of MI-BCI technology, accurately decoding high-dimensional and low signal-to-noise ratio (SNR) electroencephalography (EEG) signals remains challenging. Moreover, traditional deep learning approaches exhibit limitations in processing EEG signals, particularly in capturing the intrinsic correlations between electrode channels and long-distance temporal dependencies. To address these challenges, this research introduces a novel end-to-end decoding network that integrates convolutional neural networks (CNNs) and a Swin Transformer, aiming at enhancing the classification accuracy of the MI paradigm in EEG signals. This approach transforms EEG signals into a three-dimensional data structure, utilizing one-dimensional convolutions along the temporal dimension and two-dimensional convolutions across the EEG electrode distribution for initial spatio-temporal feature extraction, followed by deep feature exploration using a 3D Swin Transformer module. Experimental results show that on the BCI Competition IV-2a dataset, the proposed method achieves 83.99% classification accuracy, which is significantly better than the existing deep learning methods. This finding underscores the efficacy of combining a CNN and Swin Transformer in a 3D data space for processing high-dimensional, low-SNR EEG signals, offering a new perspective for the future development of MI-BCI. Future research could further explore the applicability of this method across various BCI tasks and its potential clinical implementations.

Accurately identifying false starts in speedway racing is a very challenging task due to the subtle nature of prestart movements. Manual detection methods, often dependent on the judgment of race officials, are prone to errors and subjectivity, leading to inconsistencies in decision-making. This paper introduces an automated approach that leverages computer vision methods to enhance detection precision. Here, we have expanded its use to detect false starts in speedway racing. The proposed approach introduces image processing techniques with 3D Convolutional Neural Networks (CNNs) and Long-Short- Term Memory (LSTM) networks to analyze rider movements during the starting procedure. Unlike manual detection, which often misses fine movements at the start line, our method uses 3D CNNs to monitor racer movements and applies LSTM networks to assess time-based motion patterns that signal false starts. The presented results show that the 3D CNN achieved an accuracy of 86.36% with a higher precision when compared to traditional methods. This automated process not only enhances fairness in competitive racing, but also illustrates the broader capability of emerging technologies to refine decision-making in sports.

Convolutional neural networks (CNN) can extract the features necessary for the recognition and classification of several diseases. Yet, the intricate symptoms encompassing changes in brain anatomy pose challenges for CNN training. While an ideal scenario would leverage a patient’s entire magnetic resonance imaging (MRI) data with minimal preprocessing and human involvement, it does not always yield optimal results. To improve the performance of CNNs, researchers utilize much larger and more complex networks, which does not guarantee improvement. In this paper, we propose an innovative way to increase performance, manifested through utilizing multiple distinct 3D orientations of the data, coupled with a multi-classifier framework. The method consists of predictions from networks trained on unique angular orientations of the same data set that combine to offer a unified prediction. The results obtained from the proposed method underscore that these minimalistic, computationally frugal alterations can propel average accuracy rates from 89.84% to a commendable 94.37%, signifying a near 5% performance surge.

Motor imagery (MI) is a classical method of brain–computer interaction (BCI), in which electroencephalogram (EEG) signal features evoked by imaginary body movements are recognized, and relevant information is extracted. Recently, various deep-learning methods are being focused on in finding an easy-to-use EEG representation method that can preserve both temporal information and spatial information. To further utilize the spatial and temporal features of EEG signals, an improved 3D representation of the EEG and a densely connected multi-branch 3D convolutional neural network (dense M3D CNN) for MI classification are introduced in this paper. Specifically, as compared to the original 3D representation, a new padding method is proposed to pad the points without electrodes with the mean of all the EEG signals. Based on this new 3D presentation, a densely connected multi-branch 3D CNN with a novel dense connectivity is proposed for extracting the EEG signal features. Experiments were carried out on the WAY-EEG-GAL and BCI competition IV 2a datasets to verify the performance of this proposed method. The experimental results show that the proposed framework achieves a state-of-the-art performance that significantly outperforms the multi-branch 3D CNN framework, with a 6.208% improvement in the average accuracy for the BCI competition IV 2a datasets and 6.281% improvement in the average accuracy for the WAY-EEG-GAL datasets, with a smaller standard deviation. The results also prove the effectiveness and robustness of the method, along with validating its use in MI-classification tasks.

Water availability critically affects basil (Ocimum basilicum L.) growth and physiological performance, making the early and precise monitoring of water-deficit responses essential for precision irrigation. However, conventional visual or biochemical methods are destructive and unsuitable for real-time assessment. This study presents a multimodal optical biosensing and 3D convolutional neural network (3D-CNN) fusion framework for phenotyping physiological responses of basil under water-deficit stress. RGB, depth, and chlorophyll fluorescence (CF) imaging were integrated to capture complementary morphological and photosynthetic information. Through the fusion of 130 optical parameter layers, the 3D-CNN model learned spatial and temporal–spectral features associated with resistance and recovery dynamics, achieving 96.9% classification accuracy—outperforming both 2D-CNN and traditional machine-learning classifiers. Feature-space visualization using t-SNE confirmed that the learned latent representations reflected biologically meaningful stress–recovery trajectories rather than superficial visual differences. This multimodal fusion framework provides a scalable and interpretable approach for the real-time, non-destructive monitoring of crop water stress, establishing a foundation for adaptive irrigation control and intelligent environmental management in precision agriculture.