Search

This paper presents a hybrid Machine Learning (ML)-based feature selection algorithm to create an Intrusion Detection Systems (IDS) model in distributed computing environments such as in Internet of Things (IoT) requests. IoT applications need frequent network connections to reach either the cloud or fog resources. Since reliability and trust are very prominent attributes in distributed systems, utilizing the ML-based algorithm is vital to efficiently detect malicious/attack behaviors at the earliest time with high accuracy. To address the issue, a hybrid ML-based algorithm is presented that includes four phases. In the first phase, the pre-processing including cleansing and normalization on the relevant dataset is performed. Then, the two next phases, namely heuristic-based and meta-heuristic-based approaches, are passed for the training step. In the second phase, three effective filter-based heuristic feature rankers are utilized to sort features according to their importance. Afterward, the fuzzy TOPSIS approach is also applied to prepare a consensus among them returning top-K features. In the third phase, to optimize the consensus feature subsets, a novel Discrete Gray Wolf Optimization Algorithm (DGWA) as a meta-heuristic approach is designed. It leads to a balance in exploitation and exploration searching areas. The effectiveness of the proposed hybrid model is tested in the fourth phase on the famous NSL-KDD and UNWS-NB15 datasets against some state of the art. The simulation results of running different scenarios prove that the proposed hybrid ML-based model gives an average 10.60%, 15.85%, 3.30%, 4.39%, and 2.03% improvement in testing datasets in terms of accuracy, precision, recall, F-cost, and specificity against other comparative state of the art in the same conditions. [ABSTRACT FROM AUTHOR]

Purpose: Amid rapid technological progress, the construction industry is embracing Construction 4.0, redefining work practices through emerging technologies. However, the implications of Construction 4.0 technologies to enhancing well-being are still poorly understood. Particularly, the challenge lies in selecting technologies that critically contribute to well-being enhancement. Therefore, this study aims to evaluate the implications of Construction 4.0 technologies to enhancing well-being. Design/methodology/approach: A list of Construction 4.0 technologies was identified from a national strategic plan on Construction 4.0, using Malaysia as a case study. Fourteen construction industry experts were selected to evaluate the implications of Construction 4.0 technologies on well-being using fuzzy Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). The expert judgment was measured using linguistic variables that were transformed into fuzzy values. Then, the collected data was analyzed using the following analyses: fuzzy TOPSIS, Pareto, normalization, sensitivity, ranking performance and correlation. Findings: Six Construction 4.0 technologies are critical to enhancing well-being: cloud & real-time collaboration, big data & predictive analytics, Internet of Things, building information modeling, autonomous construction and augmented reality & virtualization. In addition, artificial intelligence and advanced building materials are recommended to be implemented simultaneously as a very strong correlation exists between them. Originality/value: The novelty of this study lies in a comprehensive understanding of the implications of Construction 4.0 technologies to enhancing well-being. The findings can assist researchers, industry practitioners and policymakers in making well-informed decisions to select Construction 4.0 technologies when targeting the enhancement of the overall well-being of the local construction industry. [ABSTRACT FROM AUTHOR]

Expanding mining operations in goaf zones heightens gas production potential, posing challenges in maintaining adequate ventilation within development panels, consequently impacting coal production. Various strategies have been explored to enhance mine ventilation and gas drainage effectiveness. However, deficiencies persist in the proposed ventilation system for the Okaba underground coal mine, prompting this study's necessity. Addressing these concerns, the study evaluates the feasibility of employing booster fans to mitigate the identified drawbacks. Prioritizing booster fans for airflow distribution in underground mines is a complex decision-making process, requiring an advanced expert system approach. To address this, the study proposes an intuitionistic-based fuzzy TOPSIS (IFT) method for booster fan prioritization in the Okaba mine. Results indicate that booster fan 4 (BF4) ranks highest, followed by booster fan 3 (BF3), consistent with fuzzy TOPSIS findings. Sensitivity analysis supports the predicted importance order, affirming the efficacy of the hybrid expert decision method in selecting a booster fan capable of enhancing the overall efficiency of gas drainage and ventilation systems in underground mines. This study introduces a Hybrid Expert Decision Approach that integrates IFT and traditional fuzzy TOPSIS methodologies. This hybrid approach is particularly novel because it combines the strengths of both methods to prioritize booster fans in underground coal mines. [ABSTRACT FROM AUTHOR]