Optical satellite images are a critical data source; however, cloud cover often compromises their quality, hindering image applications and analysis. Consequently, effectively removing clouds from optical satellite images has emerged as a prominent research direction. Recent advances in deep learning-based cloud removal methods have been significant, but image generation quality still needs improvement. Diffusion models have demonstrated remarkable success in diverse image-generation tasks, showcasing their potential in addressing this challenge. This paper presents a novel framework called DiffCR, which leverages conditional guided diffusion with deep convolutional networks for high-performance cloud removal for optical satellite imagery. Specifically, we introduce a decoupled encoder for conditional image feature extraction, providing a robust color representation to ensure the close similarity of appearance information between the conditional input and the synthesized output. Moreover, we propose a novel and efficient time and condition fusion block within the cloud removal model to accurately simulate the correspondence between the appearance in the conditional image and the target image at a low computational cost. Extensive experimental evaluations on three commonly used benchmark datasets demonstrate that DiffCR consistently achieves state-of-the-art performance on all metrics, with parameter and computational complexities amounting to only 5.1% and 5.4%, respectively, of those previous best methods. The source code, pre-trained models, and all the experimental results will be publicly available at https://github.com/XavierJiezou/DiffCR upon the paper’s acceptance of this work.

The use of multi-agent reinforcement learning (MARL) methods in coordinating traffic lights (CTL) has become increasingly popular, treating each intersection as an agent. However, existing MARL approaches either treat each agent absolutely homogeneous, i.e., same network and parameter for each agent, or treat each agent completely heterogeneous, i.e., different networks and parameters for each agent. This creates a difficult balance between accuracy and complexity, especially in large-scale CTL. To address this challenge, we propose a grouped MARL method named GPLight. We first mine the similarity between agent environment considering both real-time traffic flow and static fine-grained road topology. Then we propose two loss functions to maintain a learnable and dynamic clustering, one that uses mutual information estimation for better stability, and the other that maximizes separability between groups. Finally, GPLight enforces the agents in a group to share the same network and parameters. This approach reduces complexity by promoting cooperation within the same group of agents while reflecting differences between groups to ensure accuracy. To verify the effectiveness of our method, we conduct experiments on both synthetic and real-world datasets, with up to 1,089 intersections. Compared with state-of-the-art methods, experiment results demonstrate the superiority of our proposed method, especially in large-scale CTL.

With the increase of Internet visits and connections, it is becoming essential and arduous to protect the networks and different devices of the Internet of Things (IoT) from malicious attacks. The intrusion detection systems (IDSs) based on supervised machine learning (ML) methods require a large number of labeled samples. However, the number of abnormal behaviors is far less than that of normal behaviors, let alone that the shots of malicious behavior samples which can be intercepted as training dataset are actually limited. Consequently, it is a key research topic to conduct the anomaly detection for the small number of abnormal behavior samples. This paper proposes an anomaly detection model with a few abnormal samples to solve the problem in few-shot detection based on convolutional neural networks (CNN) and autoencoder (AE). This model mainly consists of the CNN-based supervised pretraining module and the AE-based data reconstruction module. Only a few abnormal samples are utilized to the pretrain module to build the structure of extracting deep features. The data reconstruction module simply chooses the deep features of normal samples as training data. There also exist some effective attention mechanisms in the pretraining module. Through the pretraining of small samples, the accuracy of abnormal detection is improved compared with merely training normal samples with AE. The simulation results prove that this solution can solve the above problems occurring in network behavior anomaly detection. In comparison to the original AE model and other clustering methods, the proposed model advances the detection results in a visible way.

Human activity recognition (HAR) is a popular and challenging research topic, driven by a variety of applications. More recently, with significant progress in the development of deep learning networks for classification tasks, many researchers have made use of such models to recognise human activities in a sensor-based manner, which have achieved good performance. However, sensor-based HAR still faces challenges; in particular, recognising similar activities that only have a different sequentiality and similarly classifying activities with large inter-personal variability. This means that some human activities have large intra-class scatter and small inter-class separation. To deal with this problem, we introduce a margin mechanism to enhance the discriminative power of deep learning networks. We modified four kinds of common neural networks with our margin mechanism to test the effectiveness of our proposed method. The experimental results demonstrate that the margin-based models outperform the unmodified models on the OPPORTUNITY, UniMiB-SHAR, and PAMAP2 datasets. We also extend our research to the problem of open-set human activity recognition and evaluate the proposed method’s performance in recognising new human activities.

Human activity recognition (HAR) using body-worn sensors is an active research area in human-computer interaction and human activity analysis. The traditional methods use hand-crafted features to classify multiple activities, which is both heavily dependent on human domain knowledge and results in shallow feature extraction. Rapid developments in deep learning have caused most researchers to switch to deep learning methods, which extract features from raw data automatically. Most of the existing works on human activity recognition tasks involve multimodal sensor data, and these networks mainly focus on the top representation extracted from bottom-up feedforward process without reusing other features from bottom layers. In this paper, we present a novel hybrid deep learning network for human activity recognition that also employs multimodal sensor data; however, our proposed model is a ConvLSTM pipeline that makes full use of the information in each layer extracted along the temporal domain. Thus, we propose a dense connection module (DCM) to ensure maximum information flow between the network layers. Furthermore, we employ a multilayer feature aggregation module (MFAM) to extract features along the spatial domain, and we aggregate the features obtained from every convolutional layer according to the importance of features in different spatial locations. The output of the MFAM is input into two LSTM layers to further model the temporal dependencies. Finally, a fully connected layer and a softmax function are used to compute the probability of each class. We demonstrate the effectiveness of our proposed model on two benchmark datasets: Opportunity and UniMiB-SHAR. The results illustrate that our designed network outperforms the state-of-the-art models. We also conduct experiments on efficiency, multimodal fusion and different hyperparameters to analyze our proposed network. Finally, we carry out ablation and visualization experiments to reveal the effectiveness of the two proposed modules.