A comprehensive and systematic literature review on intrusion detection systems in the internet of medical things: current status, challenges, and opportunities

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(4)

Published: Jan. 30, 2025

Language: Английский

---

Improving wettability estimation in carbonate formation using machine learning algorithms: Implications for underground hydrogen storage applications

International Journal of Hydrogen Energy, Journal Year: 2025, Volume and Issue: 111, P. 781 - 797

Published: Feb. 27, 2025

Language: Английский

---

Maximizing intrusion detection efficiency for IoT networks using extreme learning machine

Discover Internet of Things, Journal Year: 2024, Volume and Issue: 4(1)

Published: July 9, 2024

Abstract Intrusion Detection Systems (IDSs) are crucial for safeguarding modern IoT communication networks against cyberattacks. IDSs must exhibit exceptional performance, low false positive rates, and significant flexibility in constructing attack patterns to efficiently identify neutralize these attacks. This research paper discusses the use of an Extreme Learning Machine (ELM) as a new technique enhance performance IDSs. The study utilizes two standard IDS-based network datasets: NSL-KDD 2009 via Distilled-Kitsune 2021. Both datasets used assess effectiveness ELM conventional supervised learning setting. investigates capacity algorithm handle high-dimensional unbalanced data, indicating potential IDS accuracy efficiency. also examines setup both NSL_KDD Kitsune using Python Google COLAB do binary multi-class classification. experimental evaluation revealed proficient proposed ELM-based among other implemented learning-based state-of-the-art models same area.

Language: Английский

---

Classification of Fritillaria using a portable near-infrared spectrometer and fuzzy generalized singular value decomposition

Industrial Crops and Products, Journal Year: 2024, Volume and Issue: 218, P. 119032 - 119032

Published: June 20, 2024

Language: Английский

---

Smart cities and the IoT: an in-depth analysis of global research trends and future directions

Discover Internet of Things, Journal Year: 2024, Volume and Issue: 4(1)

Published: Oct. 10, 2024

Extensive scientific investigation is necessary because every government wants to construct smart cities. This why examining how researchers approach this area of study critical. investigates global research trends in cities and the Internet Things (IoT) by analyzing 14,309 articles from Scopus database (2010–2024). Using text mining latent semantic analysis (LSA) via KNIME tool, identifies key areas city development. The k-means clustering algorithm predicts future directions, highlighting most active countries, influential authors, significant sources field. results underscore need for additional sectors where IoT applications are still their early stages. also offers insights into fostering international collaborations among institutions researchers. findings suggest that should focus on developing secure, scalable solutions address challenges across various industries. Overall, provides a comprehensive overview research, offering valuable guidance policymakers aiming advance integration technologies urban environments.

Language: Английский

---

Acoustic signal-based wear monitoring for belt grinding tools with pyramid-structured abrasives using BO-KELM

Computers in Industry, Journal Year: 2025, Volume and Issue: 166, P. 104235 - 104235

Published: Jan. 5, 2025

Language: Английский

---

Convolutional Neural Networks for Imbalanced Advanced Security Network Metrics and Non‐Payload‐Based Obfuscations Dataset to Detect Intrusion

Concurrency and Computation Practice and Experience, Journal Year: 2025, Volume and Issue: 37(4-5)

Published: Feb. 11, 2025

ABSTRACT Network Intrusion Detection Systems (NIDSs) are essential for identifying and preventing cyber threats in modern networks. However, improving their adaptability responsiveness to unforeseen remains a significant challenge. Among the various datasets available NIDS, ASNM dataset holds particular significance due its rich diversity of network traffic traces, including detailed labels legitimate traffic, direct attacks, obfuscated attacks. Despite potential, has been relatively underexplored existing research, presenting an opportunity further investigation application development benchmarking advanced NIDS models. In this paper, we introduce convolutional neural (CNN) architecture designed intrusion detection, which autonomously learns patterns anomalies directly from raw data. Unlike traditional methods that rely on handcrafted features or predefined signatures, proposed CNN dynamically adapts detect both known The quality balance used train NIDSs critical, as imbalanced data can skew detection results significantly impact overall system performance. To address this, innovative preprocessing technique mitigate class imbalances, ensuring more accurate classification across all categories, under‐represented attack types. was rigorously tested against decision trees, networks, k‐nearest neighbor classifiers, demonstrating superior model achieved True Positive Rate (TPR) 99.43% average recall 99.26% balanced dataset, outperforming Furthermore, method improved TPR by 62% 83% with without samples, respectively, highlighting effectiveness addressing imbalances accuracy. conclusion, combination dataset's comprehensive scenarios dynamic feature‐learning capabilities represents advancement technology.

Language: Английский

---

A review: Integration of NIRS and chemometric methods for tea quality control-principles, spectral preprocessing methods, machine learning algorithms, research progress, and future directions

Food Research International, Journal Year: 2025, Volume and Issue: 205, P. 115870 - 115870

Published: Feb. 15, 2025

Language: Английский

---

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

The Journal of Supercomputing, Journal Year: 2025, Volume and Issue: 81(5)

Published: April 10, 2025

Language: Английский

---

Case Studies Within Smart and Secure Software Development

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 173 - 198

Published: March 28, 2025

In today's digital world, software systems must adhere to the Secure Software Development Lifecycle (SSDLC) protocol guarantee security, reliability, and resilience. Despite revolutionary impact of deep learning, blockchain, Artificial Intelligence (AI) on development, substantial challenges remain be solved in terms minimizing security risks conforming regulatory standards. This (SDLC) research integrates cybersecurity throughout process primarily focuses case studies best practices relating risk assessment, secure design, testing. Data privacy, intellectual property regulations, requirements followed while developing robust that can resist cyber assaults promote innovation.

Language: Английский

---