The emergence of smart technologies and the wide adoption of the Internet of Things (IoT) have revolutionized various sectors, yet they have also introduced significant security challenges due to the extensive attack surface they present. In recent years, many efforts have been made to minimize the attack surface. However, most IoT devices are resource-constrained with limited processing power, memory storage, and energy sources. Such devices lack the sufficient means for running existing resource-hungry security solutions, which in turn makes it challenging to secure IoT networks from sophisticated attacks. Feature Selection (FS) approaches in Machine Learning enabled Intrusion Detection Systems (IDS) have gained considerable attention in recent years for having the potential to detect sophisticated cyber-attacks while adhering to the resource limitations issues in IoT networks. Apropos of that, several researchers proposed FS-enabled IDS for IoT networks with a focus on lightweight security solutions. This work presents a comprehensive study discussing FS-enabled lightweight IDS tailored for resource-constrained IoT devices, with a special focus on the emerging Ensemble Feature Selection (EFS) techniques, portraying a new direction for the research community to inspect. The research aims to pave the way for the effective design of futuristic FS/EFS-enabled lightweight IDS for IoT networks, addressing the critical need for robust security measures in the face of resource limitations.

Understanding the visual quality of a feature map plays a significant role in many active vision applications. Previous works mostly rely on object-level features, such as compactness, to estimate the quality score of a feature map. However, the compactness is leveraged on feature maps produced by salient object detection techniques where the maps tend to be compact. As a result, the compactness feature fails when the feature maps are blurry (e.g., fixation maps). In this paper, we regard the process of estimating the quality score of feature maps, specifically fixation maps, as a regression problem. After extracting several local, global, geometric and positional characteristic features from a feature map, a model is learned using a random forest regressor to estimate the quality score of any unseen feature map. Our model is specifically tailored to estimate the quality of three types of maps: bottom-up, target and contextual feature maps. These maps are produced for a large benchmark fixation dataset of more than 900 challenging outdoor images. We demonstrate that our approach provides an accurate estimate of the quality of the abovementioned feature maps compared to the groundtruth data. In addition, we show that our proposed approach is useful in feature map integration for predicting human fixation. Instead of naively integrating all three feature maps when predicting human fixation, our proposed approach dynamically selects the best feature map with the highest estimated quality score on an individual image basis, thereby improving the fixation prediction accuracy.

Top-down visual attention models are essential for task-driven object detection; however, many existing approaches do not effectively integrate multiple sources of high-level guidance such as scene context and target-specific information. This paper proposes a computational framework that combines contextual information and target object features to dynamically modulate low-level visual features for improved attentional selection. The proposed model consists of three key components: (i) a contextual weighting module that learns feature weights optimised using Particle Swarm Optimisation and predicted through a hetero-associative neural network; (ii) a target-aware attention module that estimates feature importance based on target-specific characteristics derived from low-level feature distributions; and (iii) a recognition module that performs region classification using a Naïve Bayes classifier. Experiments conducted on seven challenging datasets with diverse objects and cluttered backgrounds demonstrate that integrating contextual and target-specific information improves detection performance compared to using either source independently. The primary objective of this work is to investigate the complementary and synergistic effects of combining contextual information and target object knowledge within a bottom-up saliency framework. The goal is not to propose or claim a state-of-the-art top-down visual attention model, but rather to demonstrate that integrating multiple sources of guidance can enhance saliency-based target detection under varied visual conditions.