A novel metaheuristic optimal feature selection framework for object detection with improved detection accuracy based on pulse-coupled neural network

Hybrid Feature Selection Method for Intrusion Detection Systems Based on an Improved Intelligent Water Drop Algorithm

“…From [54] GA-RF 0.921 ± 0.000 NA 0.016 ± 0.0000 NA From [55] IGRF-RFE 0.842 ± 0.000 0.0842 NA 0.829 ± 0.000 From [10] PIO 0.913 ± 0.0003 0.897 ± 0.0002 0.052 ± 0.0004 0.904 ± 0.0002 From [56] Rule-Based 0.652 ± 0.000 0.903 ± 0.000 0.02 ± 0.000 0.681 ± 0.000 From [57] Wrapper-Based-DT 0.864 ± 0.000 0.97 ± 0.000 0.028 ± 0.000 NA The proposed model with HC PHFS-IWDHC 4 [4,10,11,6] From [54] GA-RF 9 [27,3,41,35,36,10,31,2,18] From [55] IGRF-RFE 23 [0, 1,2,3,4,5,6,7,8,9,10,12,14,15,16,18,23,24,25,26,27,31,35] From [10] PIO 14 [3,8,9,11,12,…”

“…Overall, the proposed methods provide competitive results depending on accuracy, FPR, F-score, and TPR, compared to some of the most recent methods from the literature using the least number of features, as shown in Table 5. From [10] PIO 18 [1,3,4,5,6,8,10,11,12,13,14,15,17,18,27,32,36,39,41] From [60] PSO 37 [2,3,4,5,6,7,8,9,10,11,12,13,14,15,17,18,20,21,22,23,24,25,26,27,28,29,31,32,…”

“…These methods are based on understanding the biological behaviour of animals/insects and using this understanding to solve optimization problems. Moreover, the metaheuristic approach is widely used as a feature selection algorithm, as in [15], that uses an ant colony optimization, while in [16], three algorithms based on particle swarm optimization have been proposed based on fuzzy rough fitness functions. In [17], an ensemble FS has been proposed based on the genetic algorithm.…”

“…• Data Normalization. All used datasets are normalized using the next equation [48] for scaling all data values into a range of [0, 1] in order to eliminate the classifier bias problem for achieving a better classification performance [49]: (15) 𝑋 normalized = 𝑋−𝑋 min 𝑋 max −𝑋 min .…”

Special issue on soft computing for edge-driven applications

“…The first section includes 8 research articles on novel soft computing-driven techniques. The discussion includes: analyzing key algorithms of DSP signal processing with soft computing models (Long 2022); proposing a natureinspired optimal feature selection methodology using ant colony optimization for finding the optimal features to reduce the computational complexity and increase detection accuracy (Dharini and Jain 2021); formulating a novel DNN framework for evolving predictive frameworks (Guduru et al 2021); proposing a novel oversampling approach to introduce synthetic samples via genetic algorithm (GA) for evaluating the fault prediction performance and reduced false alarm rate (Arun and Lakshmi 2021); designing and developing a task scheduling method based on a hybrid optimization algorithm to assign a task with minimal amount of waiting time (Khan and Santhosh 2021); proposing a multi-swarm optimization model for multi-cloud scheduling to obtain enhanced quality of services [QoS] in a multi-cloud environment (Mohanraj and Santhosh 2021); by using big data pattern mining algorithm and scene understanding algorithm, a framework optimization system of traditional printing and dyeing process in Xiangxi is developed for the optimization of the traditional model, wherein the edge-driven scene model is applied for the systematic study (Xiao 2021); and studying about soft multimedia assisted new energy productive landscape design based on the environmental analysis and edge-driven artificial intelligence (Ma et al 2021).…”