IBJA: An improved binary DJaya algorithm for feature selection

Journal of Computational Science, Год журнала: 2023, Номер 75, С. 102201 - 102201

Опубликована: Дек. 14, 2023

Язык: Английский

---

A Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes

Sensors, Год журнала: 2024, Номер 24(7), С. 2188 - 2188

Опубликована: Март 29, 2024

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to and enjoying facilities smart services. IoT marketing experiencing an impressive 16.7% growth rate a nearly USD 300.3 billion market. These eye-catching figures have made it attractive playground for cybercriminals. devices are built using resource-constrained architecture offer compact sizes competitive prices. As result, integrating sophisticated cybersecurity features beyond scope computational capabilities IoT. All these contributed surge in intrusion. This paper presents LSTM-based Intrusion Detection System (IDS) with Dynamic Access Control (DAC) algorithm not only detects but also defends against novel approach achieved 97.16% validation accuracy. Unlike most IDSs, model proposed IDS been selected optimized through mathematical analysis. Additionally, boasts ability identify wider range threats (14 be exact) compared other solutions, translating enhanced security. Furthermore, fine-tuned strike balance between accurately flagging minimizing false alarms. Its performance metrics (precision, recall, F1 score all hovering around 97%) showcase potential this innovative elevate detection rate, exceeding 98%. high accuracy instills confidence its reliability. lightning-fast response time, averaging under 1.2 s, positions among fastest intrusion systems available.

Язык: Английский

---

Advanced vehicle routing in cement distribution: a discrete Salp Swarm Algorithm approach

International Journal of Management Science and Engineering Management, Год журнала: 2024, Номер unknown, С. 1 - 13

Опубликована: Март 6, 2024

In this research, the focus is on addressing capacitated vehicle routing problem (CVRP), a prominent logistical challenge within transportation management. The discrete salp swarm algorithm (DSSA) has been introduced as an innovative adaptation of traditional (SSA), specifically redesigned to cater characteristics inherent in problems like CVRP. This integrates core principles SSA with mutation and crossover techniques, enhancing its applicability for problems. paper contributes two main areas: firstly, development DSSA, tailored address unique requirements VRP scenarios ensuring balanced approach between exploration exploitation optimization. Secondly, effectiveness DSSA demonstrated through practical applications, including 8-customer task real-world case study involving cement delivery Vietnam. these scenarios, consistently demonstrates superior performance over other meta-heuristic strategies, marking noteworthy advancement domain optimization providing potential tool complex challenges logistics distribution systems.

Язык: Английский

---

Improved Salp Swarm Optimization Algorithm based on a Robust Search Strategy and a Novel Local Search Algorithm for Feature Selection Problems

Chemometrics and Intelligent Laboratory Systems, Год журнала: 2025, Номер 258, С. 105343 - 105343

Опубликована: Фев. 7, 2025

Язык: Английский

---

EBAO: An Intrusion Detection Framework for Wireless Sensor Networks Using an Enhanced Binary Aquila Optimizer

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113156 - 113156

Опубликована: Фев. 1, 2025

Язык: Английский

---

T-Sanitation: contrastive masked auto-encoder-based few-shot learning for malicious traffic detection

The Journal of Supercomputing, Год журнала: 2025, Номер 81(5)

Опубликована: Апрель 10, 2025

Язык: Английский

---

Grey wolf optimizer with self-repulsion strategy for feature selection

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 14, 2025

Feature selection is one of the most critical steps in big data analysis. Accurately extracting correct features from massive can effectively improve accuracy processing algorithms. However, traditional grey wolf optimizer (GWO) algorithms often suffer slow convergence and a tendency to fall into local optima, limiting their effectiveness high-dimensional feature tasks. To address these limitations, we propose novel algorithm called with self-repulsion strategy (GWO-SRS). In GWO-SRS, hierarchical structure pack flattened enable rapid transmission commands alpha each member, thereby accelerating convergence. Additionally, two distinct learning strategies are employed: for based on predatory behavior wolf, facilitating self-learning both pack. These improvements mitigate weaknesses GWO, such as premature limited exploration capability. Finally, conduct comparative experimental analysis UCI test dataset using five relevant The results demonstrate that average classification error GWO-SRS reduced by approximately 15% compared related algorithms, while utilizing 20% fewer features. This work highlights need inherent limitations GWO provides robust solution complex problems.

Язык: Английский

---

Enhanced Binary Kepler Optimization Algorithm for effective feature selection of supervised learning classification

Journal Of Big Data, Год журнала: 2025, Номер 12(1)

Опубликована: Апрель 15, 2025

Язык: Английский

---

A novel improved lemurs optimization algorithm for feature selection problems

Journal of King Saud University - Computer and Information Sciences, Год журнала: 2023, Номер 35(8), С. 101704 - 101704

Опубликована: Авг. 12, 2023

The irrelevant and repeated features in high-dimensional datasets can negatively affect the final performance accuracy of classification-based models. Therefore, feature selection (FS) techniques be used to determine most optimal relevant features. In this paper, we fuse a new enhanced model from Lemurs Optimization (LO) algorithm, called Enhanced (ELO). We combine Opposition Based Learning (OBL) Local Search Algorithm (LSA) address exploration exploitation challenges, respectively. Our proposed ELO algorithm incorporates U-shaped Sigmoid transfer functions during position update step, leading improved convergence. These deployments based on are ELO-U ELO-S algorithms, all three versions our optimization algorithms (ELO, ELO-U, ELO-S) has been evaluated using 21 UCI different fields sizes. Moreover, their results also compared other competitive algorithms. evaluation process included several measurements such as fitness value, an average selected features, accuracy. Experimental demonstrate that achieves best 91.03%. Statistical analysis Friedman Wilcoxon tests confirms superiority over competitors.

Язык: Английский

---

BOC-PDO: an intrusion detection model using binary opposition cellular prairie dog optimization algorithm

Cluster Computing, Год журнала: 2024, Номер 27(10), С. 14417 - 14449

Опубликована: Июль 20, 2024

Язык: Английский

---