A Multi-Objective Method Based on Tag Eigenvalues Is Used to Predict the Supply Chain for Online Retailers DOI Open Access
Leilei Jiang, Pan Hu, Ke Dong

et al.

International Journal of Information Systems and Supply Chain Management, Journal Year: 2024, Volume and Issue: 17(1), P. 1 - 15

Published: June 5, 2024

E-commerce has grown quickly in recent years thanks to advancements Internet and information technologies. For the majority of consumers, online shopping emerged as a primary mode shopping. However, it become more challenging for businesses satisfy consumer demand due their increasingly individualized wants. To address need customized products with numerous kinds small quantities, must rebuild supply chain systems increase efficiency adaptability. The SI-LSF technique, which employs boosting learning target-relative feature space lower prediction error enhance algorithm's capacity handle input-output interactions, is validated this study using genuine industrial dataset. successfully identifies relationship between sales well target-specific features by applying multi-objective regression integration algorithm based on label-specific real-world scenario.

Language: Английский

HoleMal: A lightweight IoT malware detection framework based on efficient host-level traffic processing DOI
Ziqian Chen, Wei Xia, Zhen Li

et al.

Computers & Security, Journal Year: 2025, Volume and Issue: unknown, P. 104360 - 104360

Published: Feb. 1, 2025

Language: Английский

Citations

0
A new a flow-based approach for enhancing botnet detection using convolutional neural network and long short-term memory DOI Creative Commons
Mehdi Asadi, Arash Heidari, Nima Jafari Navimipour

et al.

Knowledge and Information Systems, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

Language: Английский

Citations

0
Construction of a BIM smart building collaborative design model combining the Internet of Things DOI Creative Commons

Man Feng,

Hanmei Wu

Nonlinear Engineering, Journal Year: 2025, Volume and Issue: 14(1)

Published: Jan. 1, 2025

Abstract The research aims to solve the problem of data synchronization and redundancy in building information model co-design with blockchain technology. A hyper-ledger fabric federated blockchain, combined a revolving door compression algorithm, is used for construction an intelligent model. Experiments showed that method outperformed other technologies terms throughput response time, block-out time reduced by 19.31% transaction increased 12.38%. proposes innovative cycle division mechanism utilizes algorithm maintenance model, thereby enhancing security design efficiency collaboration. This positive significance design. However, limitation study only blockchain-based designed, further development example validation are needed future.

Language: Английский

Citations

0
Feature selection for IoT botnet detection using equilibrium and Battle Royale Optimization DOI
Qanita Bani Baker,

Alaa Samarneh

Computers & Security, Journal Year: 2024, Volume and Issue: 147, P. 104060 - 104060

Published: Aug. 23, 2024

Language: Английский

Citations

3
Enhancing IoT security: A comparative study of feature reduction techniques for intrusion detection system DOI Creative Commons
Jing Li, Hewan Chen,

Mohd Othman Shahizan

et al.

Intelligent Systems with Applications, Journal Year: 2024, Volume and Issue: 23, P. 200407 - 200407

Published: June 15, 2024

Internet of Things (IoT) devices are extensively utilized but susceptible to cyberattacks, posing significant security challenges. To mitigate these threats, machine learning techniques have been implemented for network intrusion detection in IoT environments. These commonly employ various feature reduction methods, prior inputting data into models, order enhance the efficiency processes meet real-time requirements. This study provides a comprehensive comparison selection (FS) and extraction (FE) systems (NIDS) environments, utilizing TON-IoT BoT-IoT datasets both binary multi-class classification tasks. We evaluated FS including Pearson correlation Chi-square, FE such as Principal Component Analysis (PCA) Autoencoders (AE), across five classic models: Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), k-Nearest Neighbors (kNN), Multi-Layer Perceptron (MLP). Our analysis revealed that generally achieve higher accuracy robustness compared with RF paired AE delivering superior performance despite computational demands. DTs most effective smaller sets, while MLPs excel larger sets. Chi-square is identified efficient method, balancing efficiency, whereas PCA outperforms runtime efficiency. The also highlights methods more complex less sensitive set size, show improvements informative features. Despite costs they demonstrate greater capability detect diverse attack types, making them particularly suitable findings crucial academic research industry applications, providing insights optimizing NIDS networks.

Language: Английский

Citations

2
3DLBS-BCHO: a three-dimensional deep learning approach based on branch splitter and binary chimp optimization for intrusion detection in IoT DOI

Roya Zareh Farkhady,

Kambiz Majidzadeh, Mohammad Masdari

et al.

Cluster Computing, Journal Year: 2024, Volume and Issue: 28(2)

Published: Nov. 26, 2024

Language: Английский

Citations

2
Botnet detection in the internet-of-things networks using convolutional neural network with pelican optimization algorithm DOI Creative Commons

Swapna Thota,

D. Menaka

Automatika, Journal Year: 2023, Volume and Issue: 65(1), P. 250 - 260

Published: Dec. 27, 2023

Hackers nowadays employ botnets to undertake cyberattacks towards the Internet of Things (IoT) by illegally exploiting scattered network's resources computing devices. Several Machine Learning (ML) and Deep (DL) methods for detecting botnet (BN) assaults in IoT networks have recently been proposed. However, training set, severely imbalanced network traffic data degrades classification performances state-of-the-art ML as well DL algorithm, particularly classes with very few samples. The Convolutional Neural Network -Pelican Optimization System (CNN-POA) is a relied attack detection algorithm developed this research. Meanwhile, typical evaluation markers are used compare overall performance proposed CNN-POA additional frequently employed algorithms. simulation results suggest that method effective dependable intrusion attacks. Experiments revealed suggested approach outperformed number current metaheuristic algorithms, an accuracy 99.5%.

Language: Английский

Citations

5
An Improved hybrid Salp Swarm Optimization and African Vulture Optimization Algorithm for Global Optimization Problems and Its Applications in Stock Market Prediction DOI Creative Commons
Ali Alizadeh, Farhad Soleimanian Gharehchopogh, Mohammad Masdari

et al.

Research Square (Research Square), Journal Year: 2023, Volume and Issue: unknown

Published: April 7, 2023

Abstract Optimization is necessary for solving and improving the solution of various complex problems. Every meta-heuristic algorithm can have a weak point, multiple mechanisms methods be used to overcome these weaknesses. We use hybrid algorithms arrive at an efficient algorithm. This paper presents new intelligent approach by hybridizing using different simultaneously without significantly increasing time complexity. For this purpose, two algorithms, Salp Swarm Optimization(SSO) African Vulture Algorithm (AVOA) been hybridized. And improve optimization process Modified Choice Function Learning Automata mechanisms. In addition, other mechanisms, named Opposition-Based (OBL) β-hill climbing (BHC) technique, presented integrated with AVOA-SSA Fifty-two standard benchmarks were test evaluate Finally, improved version Extreme Machine(ELM) classifier has real stock market data prediction. The obtained results indicate excellent acceptable performance in `solving problems able achieve high-quality solutions.

Language: Английский

Citations

4
AI/ML driven intrusion detection framework for IoT enabled cold storage monitoring system DOI
Mahendra Prasad, Pankaj Pal, Sachin Tripathi

et al.

Security and Privacy, Journal Year: 2024, Volume and Issue: 7(5)

Published: April 18, 2024

Abstract An IoT‐based monitoring system remotely controls and manages intelligent environments. Due to wireless communication, deployed sensor nodes are more vulnerable attacks. intrusion detection is an efficient mechanism detect malicious traffic prevent abnormal activities. This article suggests framework for the cold storage system. The temperature main parameter that affects environment harms stored products. A node injects false data manipulates forwards manipulated data. It also floods neighbor nodes. In this work, generated collected detection. Two machine learning techniques have been applied: supervised (Bayesian rough set) unsupervised (micro‐clustering). proposed method shows better performance than existing methods.

Language: Английский

Citations

1
An ensemble system for machine learning IoT intrusion detection based on enhanced artificial hummingbird algorithm DOI
Leyi Shi, Qihang Yang, Lin Gao

et al.

The Journal of Supercomputing, Journal Year: 2024, Volume and Issue: 81(1)

Published: Nov. 1, 2024

Language: Английский

Citations

1