Search

The use of artificial intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which has opened it up to a myriad of privacy, trust, and legal issues. Moreover, organizations have been loath to share emails, given the risk of leaking commercially sensitive information. Consequently, it has been difficult to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly federated learning (FL), is a desideratum. As it is already prevalent in the healthcare sector, questions remain regarding the effectiveness and efficacy of FL-based phishing detection within the context of multi-organization collaborations. To the best of our knowledge, the work herein was the first to investigate the use of FL in phishing email detection. This study focused on building upon a deep neural network model, particularly recurrent convolutional neural network (RNN) and bidirectional encoder representations from transformers (BERT), for phishing email detection. We analyzed the FL-entangled learning performance in various settings, including (i) a balanced and asymmetrical data distribution among organizations and (ii) scalability. Our results corroborated the comparable performance statistics of FL in phishing email detection to centralized learning for balanced datasets and low organizational counts. Moreover, we observed a variation in performance when increasing the organizational counts. For a fixed total email dataset, the global RNN-based model had a 1.8% accuracy decrease when the organizational counts were increased from 2 to 10. In contrast, BERT accuracy increased by 0.6% when increasing organizational counts from 2 to 5. However, if we increased the overall email dataset by introducing new organizations in the FL framework, the organizational level performance improved by achieving a faster convergence speed. In addition, FL suffered in its overall global model performance due to highly unstable outputs if the email dataset distribution was highly asymmetric. [ABSTRACT FROM AUTHOR]

Ionospheric forecasts are critical for space-weather anomaly detection. Forecasting ionospheric total electron content (TEC) from the global navigation satellite system (GNSS) is of great significance to near-earth space environment monitoring. In this study, we propose a novel ionospheric TEC forecasting model based on deep learning, which consists of a convolutional neural network (CNN), long-short term memory (LSTM) neural network, and attention mechanism. The attention mechanism is added to the pooling layer and the fully connected layer to assign weights to improve the model. We use observation data from 24 GNSS stations from the Crustal Movement Observation Network of China (CMONOC) to model and forecast ionospheric TEC. We drive the model with six parameters of the TEC time series, Bz, Kp, Dst, and F10.7 indices and hour of day (HD). The new model is compared with the empirical model and the traditional neural network model. Experimental results show the CNN-LSTM-Attention neural network model performs well when compared to NeQuick, LSTM, and CNN-LSTM forecast models with a root mean square error (RMSE) and R2 of 1.87 TECU and 0.90, respectively. The accuracy and correlation of the prediction results remained stable in different months and under different geomagnetic conditions. [ABSTRACT FROM AUTHOR]

Skeleton‐based action recognition is an inspired yet challenging task in computer vision. Recently, the latest graph convolutional network (GCN), which generalises well‐established convolutional neural networks to non‐Euclidean structures, is proven to be highly successful for action recognition from body skeleton data. However, the GCN architecture has not been fully studied. In this work, a Fisher vector (FV) encoding based GCN architecture (FV‐GCN) is proposed, which exceeds the limitations of existing GCN‐based methods by combining the GCN model with FV encoding. A channel‐wise spatial–temporal aggregation function to preserve spatial–temporal information in the whole action clip and integrate it into the FV‐GCN architecture is also presented. Since FV is different from the GCN structure, this hybrid architecture that incorporates the advantages of both algorithms can discover complementary information of feature representation effectively. On two challenging human action datasets, kinetics, and NTU‐RGBD, improved performance is demonstrated over the baseline method, and the FV‐GCN is better or comparable to some state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

• An orientation method with limited effective polarization area is proposed. • Using UNet to separate occluders and effective polarization regions. • Solar Meridian Fitting Using Antisymmetry of Skylight Polarization Pattern. The bionic polarized light compass has characteristics of immunity to interference from electromagnetic fields and zero error accumulation over time, and thus has good application prospects in the autonomous navigation field under conditions of Global Positioning System rejection or failure. With the aim of addressing the problem that the polarization orientation accuracy of the bionic polarized light compass can be degraded seriously by the presence of large-area occlusions such as clouds and buildings during the actual application process, this paper proposes a highly robust orientation method under the limited effective polarization area condition based on the antisymmetry of the skylight polarization pattern. The orientation algorithm first uses the UNet convolutional neural network to perform binary segmentation of the polarized image and then separates and removes the thick cloud layer/building occlusion area from the image; Then, a new solar meridian fitting method is proposed, which makes use of the characteristic of antisymmetric distribution of polarization angle along the solar meridian in atmospheric polarization mode to fit the solar meridian, and then completes the orientation. Experimental results show that the method proposed in this paper can effectively solve the problem of polarization orientation accuracy degradation caused by harsh environments, including clouds, building occlusions, and cloudy days, and can thus improve the robustness of bionic polarized light compass orientation effectively in complex environments. [ABSTRACT FROM AUTHOR]

With the emergence of big data, the efficiency of data querying and data storage has become a critical bottleneck in the remote sensing community. In this letter, we explore hash learning for the indexing of large-scale remote sensing images (RSIs) with a supervised pairwise neural network with the aim of improving RSI retrieval performance with a few binary bits. First, a fully connected hashing neural network (FCHNN) is proposed in order to map RSI features into binary (feature-to-binary) codes. Compared with pixel-to-binary frameworks, such as DPSH (deep pairwise-supervised hashing), FCHNN only contains three fully connected layers and incorporates another new constraint, so it can be significantly accelerated to obtain desirable performance. Second, five types of image features, including mid-level and deep features, were investigated in the learning of the FCHNN to achieve state-of-the-art performances. The mid-level features were based on Fisher encoding with affine-invariant local descriptors, and the deep features were extracted by pretrained or fine-tuned CNNs (e.g., CaffeNet and VGG-VD16). Experiments on five recently released large-scale RSI datasets (i.e., AID, NWPU45, PatternNet, RSI-CB128, and RSI-CB256) demonstrated the effectiveness of the proposed method in comparison with existing handcrafted or deep-based hashing methods. [ABSTRACT FROM AUTHOR]

Damping technology has been widely used because of its good vibration control effect. However, due to the strong nonlinearity of the added dampers, accurately predicting the seismic response of damped structures remains a challenge. This study investigates the application of interpretable machine learning (ML)-based and deep learning-based approaches to the prediction of the maximum inter-storey displacement of a damped structure. A comprehensive database consisting of 13,855 structural responses to ground motions was collected. Seven traditional interpretable ML algorithms including random forest and extreme gradient boosting (XGBoost), a convolutional neural network based on large receptive field, and seismic wave transformer (SWT) model based on a transformer network were developed. The predictions show that the error of the SWT based on unsupervised feature extraction is reduced by 50.90% compared with that of the optimal XGBoost in ensemble learning. Although the SWT has the highest global accuracy, XGBoost is found to have a smaller error when the structure is in a linear state with peak ground acceleration as partition index, so an aggregation model (AM)-based structural response prediction method was also proposed. The accuracy of the AM improved by 27.95% compared with that of the SWT. In contrast with other ML models, the proposed AM is more advantageous in terms of computational efficiency and accuracy. • Numerical model of a damped steel frame was developed using OpenSees based on shaking table test results. • A prediction dataset was built based on the numerical results of a damped structure. • Seven interpretable machine learning-based techniques were utilised to predict the maximum structural inter-storey drift. • The deep learning algorithm based on unsupervised feature extraction can obtain more satisfactory results when the structure enters strong nonlinearity. • The developed aggregation model exhibits higher prediction accuracy. [ABSTRACT FROM AUTHOR]

• A new CNN structure is designed to extract two complementary features of image. • A new feature is used to remedy the missing image details in semantic feature. • A full-feature extraction module is designed to extract the new feature. • A fusion module is used to aggregate image features selectively and effectively. Convolutional neural networks (CNN) has been widely used in biomedical image segmentation (BIS) tasks for its remarkable feature representation capability, and most of existing CNN-based segmentation networks leverage a down-sampling operation to achieve larger acceptance domain. However, down-sampling operations could inevitably loss the detailed information of images which is very important for the BIS task. In this paper, we propose a full-resolution biomedical image segmentation network(FRNet) that could maintain the integrated detailed information of image while keeping sufficient semantic information and large receptive field. Specifically, the basic semantic feature and non-destructive feature are employed to represent the semantic and detailed information of images, respectively. A backbone network and a new full-feature extraction branch are conducted to extract those two kinds of complementary features. Furthermore, a novel feature fusion module is designed to integrate those complementary features to achieve non-destructive description of images. Finally, in order to further improve the description ability of the integrated feature, a Densely connected Atrous Spatial Pyramid Pooling(DenseASPP) module is arranged at the end of our proposed FRNet to extract the multiscale information of images. Thorough experimental results on several available databases demonstrate the effectiveness and advancement of FRNet. [ABSTRACT FROM AUTHOR]

• The TIUNet is the first medical image registration CNN with triple-input structure. • Three kinds of loss functions are conducted to supporting the novel structure. • The deformation consistency of two registration results is novelly considered. • The training data could be naturally augmented with the triple-input structure. Deep-learning frameworks have been widely used in deformable image registration(DIR), which is a fundamental step in medical image analysis. In traditional deep-learning-based DIR methods, pairwise registration is conducted for each image, cooperated with a dual-input structure. They only considered that the registered images need to be as similar as possible to the target image, while ignored that all registered images to the same target image should have similar appearance too. Therefore, in this paper we add the deformation constraints between different registered images to the registration network in order to enhance the appearance consistency of the registered images and improve the registration accuracy. Specifically, a Triple-Input-Unsupervised neural Network (TIUNet) is proposed to register two source images to a common target image at the same time. Then, a novel deformation-strengthened loss is designed to simulate the deformation constraint between the two warped source images. Finally, the deformation constraints between the source images and the target image are jointly optimized to obtain the deformation field model. The experimental results on the available tissue segmentation database demonstrate that our proposed TIUNet method shows a superior performance of deformation field model over several other advanced deformable image registration algorithms. Moreover, benefited from the triple-input structure, our proposed TIUNet method could expand the available training sets naturally and is suitable for the registration task with fewer training data. [ABSTRACT FROM AUTHOR]