Search

This study tackles the significant challenge of generating low-cost intrusion detection datasets for Internet of Things (IoT) camera devices, particularly for financially limited organizations. Traditional datasets often depend on costly cameras, posing accessibility issues. Addressing this, a new dataset was developed, tailored for low-cost IoT devices, focusing on essential features. The research employed an Entry/Exit IoT Network at CKT-UTAS, Navrongo, a Ghanaian University, showcasing a feasible model for similar organizations. The study gathered location and other vital features from low-cost cameras and a standard dataset. Using the XGBoost machine learning algorithm, the effectiveness of this approach for cybersecurity enhancement was demonstrated. The implementation included a model-agnostic eXplainable AI (XAI) technique, employing Shapley Additive Explanations (SHAP) values to interpret the XGBoost model's predictions. This highlighted the significance of cost-effective features like Flow Duration, Total Forward Packets, and Total Length Forward Packet, in addition to location data. These features were crucial for intrusion detection using the new IoT dataset. Training a deep-learning model with only these features maintained comparable accuracy to using the full dataset, validating the practicality and efficiency of the approach in real-world scenarios.

Graph Neural Networks (GNNs) have gained popularity in image matching methods, proving useful for various computer vision tasks like Structure from Motion (SfM) and 3D reconstruction. A well-known example is SuperGlue. Lightweight variants, such as LightGlue, have been developed with a focus on stacking fewer GNN layers compared to SuperGlue. This paper proposes the h-GNN, a lightweight image matching model, with improvements in the two processing modules, the GNN and matching modules. After image features are detected and described as keypoint nodes of a base graph, the GNN module, which primarily aims at increasing the h-GNN’s depth, creates successive hierarchies of compressed-size graphs from the base graph through a clustering technique termed SC+PCA. SC+PCA combines Principal Component Analysis (PCA) with Spectral Clustering (SC) to enrich nodes with local and global information during graph clustering. A dual non-contrastive clustering loss is used to optimize graph clustering. Additionally, four message-passing mechanisms have been proposed to only update node representations within a graph cluster at the same hierarchical level or to update node representations across graph clusters at different hierarchical levels. The matching module performs iterative pairwise matching on the enriched node representations to obtain a scoring matrix. This matrix comprises scores indicating potential correct matches between the image keypoint nodes. The score matrix is refined with a ‘dustbin’ to further suppress unmatched features. There is a reprojection loss used to optimize keypoint match positions. The Sinkhorn algorithm generates a final partial assignment from the refined score matrix. Experimental results demonstrate the performance of the proposed h-GNN against competing state-of-the-art (SOTA) GNN-based methods on several image matching tasks under homography, estimation, indoor and outdoor camera pose estimation, and 3D reconstruction on multiple datasets. Experiments also demonstrate improved computational memory and runtime, approximately 38.1% and 26.14% lower than SuperGlue, and an average of about 6.8% and 7.1% lower than LightGlue. Future research will explore the effects of integrating more recent simplicial message-passing mechanisms, which concurrently update both node and edge representations, into our proposed model.

The unparalleled availability of Satellite Image Time Series (SITS) for crop phenology classification unravels agricultural parcel observation and monitoring with applications of both economic and ecological importance. Moreover, the need for distinct classification of agricultural parcels into individual crop types falls on state-of-the-art deep learning models for this extrinsic task. However, most existing approaches implemented are complex and ineffective attention incorporated models, which in turn lack the resilience to recognize useful bands in achieving greater accuracy. We propose a Multi-Fast Channel Attention module for deep CNNs based on a Spatial Encoder (SE-MFCA) that requires a few parameters while enhancing the performance-complexity trade-off dilemma. Hence, we leverage on spatial encoder module to extract the images as disorderly sets of pixels to enhance the coarse spatial resolution features. We empirically show that appropriate parameter sharing in the cross channel interaction can preserve performance while significantly reducing model complexity. The proposed multi-channel attention module can efficiently be implemented via an encoder-decoder network to prevent the loss of detailed spatial information. Again, we parallelly distributed the input channel into multiple heads in our network to recover the specialized input features, which will concatenate with the residual to form a rich single feature representation. The extensive experiment has shown that our model SE-MFCA is efficient and effective compared with the previous state-of-the-art time series classification algorithm on a publicly available dataset of Sentinel-2 images for agricultural parcels. Performance-wise SE-MFCA achieves the highest overall accuracy of 94.50% and the highest mean intersection over union score of 51.92%, besides the least trainable params of 131 K and fewer floating point operations of 0.16 M.