Urban particulate matter forecasting is regarded as an essential issue for early warning and control management of air pollution, especially fine particulate matter (PM_2.5). However, existing methods for PM_2.5 concentration prediction neglect the effects of featured states at different times in the past on future PM_2.5 concentration, and most fail to effectively simulate the temporal and spatial dependencies of PM_2.5 concentration at the same time. With this consideration, we propose a deep learning-based method, AC-LSTM, which comprises a one-dimensional convolutional neural network (CNN), long short-term memory (LSTM) network, and attention-based network, for urban PM_2.5 concentration prediction. Instead of only using air pollutant concentrations, we also add meteorological data and the PM_2.5 concentrations of adjacent air quality monitoring stations as the input to our AC-LSTM. Hence, the spatiotemporal correlation and interdependence of multivariate air quality-related time-series data are learned by the CNN–LSTM network in AC-LSTM. The attention mechanism is applied to capture the importance degrees of the effects of featured states at different times in the past on future PM_2.5 concentration. The attention-based layer can automatically weigh the past feature states to improve prediction accuracy. In addition, we predict the PM_2.5 concentrations over the next 24 h by using air quality data in Taiyuan city, China, and compare it with six baseline methods. To compare the overall performance of each method, the mean absolute error (MAE), root-mean-square error (RMSE), and coefficient of determination (R²) are applied to the experiments in this paper. The experimental results indicate that our method is capable of dealing with PM_2.5 concentration prediction with the highest performance.

The advanced metering infrastructure in modern networked smart homes brings various advantages, such as multiple pricing and energy scheduling. However, smart homes are vulnerable to many cyberattacks, and the most striking one is energy theft. Researchers have developed many countermeasures, fostered by advanced machine learning (ML) techniques. Nevertheless, recent advances are not robust enough in practice, partially due to the vulnerabilities of employed ML algorithms. Given a group of smart homes, in this article, we present a covert electricity theft strategy through mimicking normal consumption patterns and compromising neighboring meters concurrently. Such attack is almost impossible to be detected by existing solutions as the manipulated data have little deviation against honest usage records. To address this threat, we initially identify and define two levels of consumption deviations: home-level and interpersonal-level, respectively. Then, we design a feature extraction scheme that can capture the correlation between attacks and honest customers. Finally, we develop a new deep learning-based detection model. Extensive experiments based on real-world datasets show that the presented attack could evade existing mainstream detectors but still gain high profits. In addition, the proposed countermeasure outperforms state-of-the-art detection methods.

Melanoma recognition is challenging due to data imbalance and high intra-class variations and large inter-class similarity. Aiming at the issues, we propose a melanoma recognition method using deep convolutional neural network with covariance discriminant loss in dermoscopy images. Deep convolutional neural network is trained under the joint supervision of cross entropy loss and covariance discriminant loss, rectifying the model outputs and the extracted features simultaneously. Specifically, we design an embedding loss, namely covariance discriminant loss, which takes the first and second distance into account simultaneously for providing more constraints. By constraining the distance between hard samples and minority class center, the deep features of melanoma and non-melanoma can be separated effectively. To mine the hard samples, we also design the corresponding algorithm. Further, we analyze the relationship between the proposed loss and other losses. On the International Symposium on Biomedical Imaging (ISBI) 2018 Skin Lesion Analysis dataset, the two schemes in the proposed method can yield a sensitivity of 0.942 and 0.917, respectively. The comprehensive results have demonstrated the efficacy of the designed embedding loss and the proposed methodology.

Catastrophic forgetting is a key challenge for class-incremental learning with deep neural networks, where the performance decreases considerably while dealing with long sequences of new classes. To tackle this issue, in this paper, we propose a new exemplar-supported representation for incremental learning (ESRIL) approach that consists of three components. First, we use memory aware synapses (MAS) pre-trained on the ImageNet to retain the ability of robust representation learning and classification for old classes from the perspective of the model. Second, exemplar-based subspace clustering (ESC) is utilized to construct the exemplar set, which can keep the performance from various views of the data. Third, the nearest class multiple centroids (NCMC) is used as the classifier to save the training cost of the fully connected layer of MAS when the criterion is met. Intensive experiments and analyses are presented to show the influence of various backbone structures and the effectiveness of different components in our model. Experiments on several general-purpose and fine-grained image recognition datasets have fully demonstrated the efficacy of the proposed methodology.

Automatic crack detection is challenging, owing to the complex and thin topologies, diversity, and background noises of cracks. Inspired by the wavelet theory, we present an instance normalization wavelet (INW) layer and embed the layer into the deep model for segmentation. The proposed layer employs prior knowledge in the wavelets to capture the crack features and filter the high-frequency noises simultaneously, accelerating the convergence of model training. Furthermore, instance normalization in our layer is utilized to mitigate the feature differences, boosting the generalization capability. In addition, a fusion layer is added to merge the information across the different layers. The comparison experiments and ablation studies demonstrate that the INW layer steadily enhances recognition and convergence performance on the DeepCrack dataset and CRACK500 dataset.