To avoid the over-fitting phenomenon that appeared in performing Graph Neural Networks (GNNs) on test examples, the feature encoding scheme of GNNs usually introduces the dropout procedure. However, after learning latent node representations under this scheme, Gaussian noise produced by the dropout operation is inevitably transmitted into the next neighborhood aggregation step, which necessarily hampers the unbiased aggregation ability of GNN models. To address this issue, we present a novel aggregator, De-Noising Aggregation (DNAG), which utilizes Principal Component Analysis (PCA) to preserve the aggregated real signals from neighboring features and simultaneously filter out the Gaussian noise. The idea is different from using PCA on traditional applications to reduce the feature dimension. We regard PCA as an aggregator to compress the neighboring node features to have better expressive de-noising power. We propose new training architectures to simplify the intensive computation of PCA in DNAG. Numerical experiments show the apparent superiority of the proposed DNAG models in gaining more de-noising capability and achieving the state-of-the-art for a set of predictive tasks on several graph-structured datasets.

The proliferation of Internet of Things (IoT) devices has created unprecedented cybersecurity vulnerabilities, with botnets emerging as a critical threat to network infrastructure. This study focuses on traditional machine learning and deep learning approaches, proposes a novel ensemble framework to address these issues, integrating Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), Random Forest (RF), and Logistic Regression (LR) via a weighted soft-voting mechanism. Our approach introduces a Quantile Uniform transformation to reduce feature skewness, a multi-layered feature selection method to enhance discriminative power, an individual performance of deep learning–traditional machine learning and a hybrid models (ensemble models) for robust detection. Evaluated on BOT-IOT, CICIOT2023, and IOT23 datasets, the framework achieves 100% accuracy on BOT-IOT, 99.2% on CICIOT2023, and 91.5% on IOT23, outperforming state-of-the-art models by up to 6.2%. These contributions advance IoT security by enabling scalable, high-performance detection adaptable to diverse network scenarios, with practical optimizations for real-world deployment.

The Sensor-based Human Activity Recognition (SHAR) task seeks to recognize signals collected by various sensors embedded in intelligent devices to assist people in their daily lives. Motivated by the success of deep learning, many researchers are studying combining deep learning with SHAR. The key to implementing sensor-based human activity recognition with deep learning lies in facilitating model performance and maintaining efficiency when the model is performed on resource-constrained devices. To address this challenge, we present an effective sensor signal representation method, termed the Temporal-Spatial Dynamic Convolutional (TS-DyConv) network, to recognize human activity. TS-DyConv aims to dynamically learn the convolutional kernels weighted with attention generated along the temporal and spatial kernel spaces. This way, the TS-DyConv can diversify the kernel to enhance the sensor signal’s recognition capabilities without raising complexity and maintaining efficiency. Extensive experiments conducted on three benchmark SHAR datasets, e.g., OPPORTUNITY, PAMAP2, and USC-HAD, demonstrate the superiority of our method over the deep learning baselines and existing SHAR works.