Sofware-Defined Radio Testbed for I/Q Imbalanced Single-Carrier Communication Systems DOI Open Access
Álvaro Pendás-Recondo, Jesús A. López‐Fernández, Rafael González Ayestarán

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(15), P. 3002 - 3002

Published: July 30, 2024

An end-to-end testbed for In-phase and Quadrature (I/Q) Imbalance (IQI) communication systems based on Software-Defined Radio (SDR) is presented. The scenario under consideration a Single-Input–Single-Output (SISO) single-carrier where the transmitter heavily affected by IQI, whose effects are mitigated through digital signal processing at receiver. presented highly configurable, enabling testing of different IQI parameters. Crucial insights into practical implementation mitigation techniques, specifically use asymmetric signaling receiver, provided. Initially, detailed description mathematical framework given. This serves as foundation subsequent discussion system implementation, effectively bridging gap between research its application in architectures. Over-The-Air (OTA) Symbol Error Rate (SER) measurements constellations validate receiver design implementation. source code publicly available.

Language: Английский

Overview of AI-Models and Tools in Embedded IIoT Applications DOI Open Access
Pierpaolo Dini, Lorenzo Diana, Abdussalam Elhanashi

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(12), P. 2322 - 2322

Published: June 13, 2024

The integration of Artificial Intelligence (AI) models in Industrial Internet Things (IIoT) systems has emerged as a pivotal area research, offering unprecedented opportunities for optimizing industrial processes and enhancing operational efficiency. This article presents comprehensive review state-of-the-art AI applied IIoT contexts, with focus on their utilization fault prediction, process optimization, predictive maintenance, product quality control, cybersecurity, machine control. Additionally, we examine the software hardware tools available integrating into embedded platforms, encompassing solutions such Vitis v3.5, TensorFlow Lite Micro v2.14, STM32Cube.AI v9.0, others, along supported high-level frameworks devices. By delving both model applications facilitating deployment low-power devices, this provides holistic understanding AI-enabled practical implications settings.

Language: Английский

Citations

9
Overview on Intrusion Detection Systems for Computers Networking Security DOI Creative Commons
Lorenzo Diana, Pierpaolo Dini,

Davide Paolini

et al.

Computers, Journal Year: 2025, Volume and Issue: 14(3), P. 87 - 87

Published: March 3, 2025

The rapid growth of digital communications and extensive data exchange have made computer networks integral to organizational operations. However, this increased connectivity has also expanded the attack surface, introducing significant security risks. This paper provides a comprehensive review Intrusion Detection System (IDS) technologies for network security, examining both traditional methods recent advancements. covers IDS architectures types, key detection techniques, datasets test environments, implementations in modern environments such as cloud computing, virtualized networks, Internet Things (IoT), industrial control systems. It addresses current challenges, including scalability, performance, reduction false positives negatives. Special attention is given integration advanced like Artificial Intelligence (AI) Machine Learning (ML), potential distributed blockchain. By maintaining broad-spectrum analysis, aims offer holistic view state-of-the-art IDSs, support diverse audience, identify future research development directions critical area cybersecurity.

Language: Английский

Citations

1
Real‐time monitoring and ageing detection algorithm design with application on SiC‐based automotive power drive system DOI Creative Commons
Pierpaolo Dini,

Giovanni Basso,

Sergio Saponara

et al.

IET Power Electronics, Journal Year: 2024, Volume and Issue: 17(6), P. 690 - 710

Published: March 15, 2024

Abstract The article describes an innovative methodology for the design and experimental validation of monitoring anomaly detection algorithms, with a particular focus on aging phenomenon, linked to anomalous modification , in devices switching power electronic systems integrated into modern high‐performance electrified vehicles. case study concerns electric drive fully vehicles, which three‐phase axial flux synchronous motor wheel (Elaphe) is used high‐efficiency inverter, designed SiC technology (silicon carbide). proposes system, four consecutive phases. first phase involves creation real‐time model drive, validated through data extrapolated directly during WLTP (Worldwide Harmonized Light Vehicle Test Procedure) test. second consists virtual dataset representative via injection procedure, emulating this phenomenon scaling factor (depending value ) current motor, relating inverter branch whose device affected. third estimator based ANN (Artificial Neural Network) regression model, manipulation features extraction reduction techniques. fourth final phase, method, PIL (Processor‐In‐the‐Loop) tests, integrating algorithm (consisting AI‐based model) NXPs32k144 embedded platform (based Cortex‐M4), making interact applied.

Language: Английский

Citations

8
Real-Time Personal Protective Equipment Non-Compliance Recognition on AI Edge Cameras DOI Open Access
Pubudu Sanjeewani,

Glenn Neuber,

John FitzGerald

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(15), P. 2990 - 2990

Published: July 29, 2024

Despite advancements in technology, safety equipment, and training within the construction industry over recent decades, prevalence of fatal nonfatal injuries accidents remains a significant concern among workers. Hard hats vests are crucial gear known to mitigate severe head trauma other injuries. However, adherence protocols, including use such gear, is often inadequate, posing potential risks Moreover, current manual monitoring systems laborious time-consuming. To address these challenges enhance workplace safety, there pressing need automate processes economically, with reduced processing times. This research proposes deep learning-based pipeline for real-time identification non-compliance wearing hard vests, enabling officers preempt hazards at sites. We evaluate various neural networks edge deployment find that Single Shot Multibox Detector (SSD) MobileNet V2 model excels computational efficiency, making it particularly suitable this application-oriented task. The experiments comparative analyses demonstrate pipeline’s effectiveness accurately identifying instances across different scenarios, underscoring its improving outcomes.

Language: Английский

Citations

4
Transforming agriculture with Machine Learning, Deep Learning, and IoT: perspectives from Ethiopia—challenges and opportunities DOI Creative Commons
Natei Ermias Benti, Mesfin Diro Chaka, Addisu Gezahegn Semie

et al.

Discover Agriculture, Journal Year: 2024, Volume and Issue: 2(1)

Published: Oct. 1, 2024

Language: Английский

Citations

4
ADFCNN-BiLSTM: A Deep Neural Network Based on Attention and Deformable Convolution for Network Intrusion Detection DOI Creative Commons
Bin Li, Jie Li,

Mingyu Jia

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1382 - 1382

Published: Feb. 24, 2025

Network intrusion detection systems can identify behavior in a network by analyzing traffic data. It is challenging to detect very small proportion of data from massive and the attack class tasks. Many existing studies often fail fully extract spatial features make reasonable use temporal features. In this paper, we propose ADFCNN-BiLSTM, novel deep neural for detection. ADFCNN-BiLSTM uses deformable convolution an attention mechanism adaptively data, it pays important both channel perspectives. BiLSTM mine employs multi-head allow focus on time-series information related suspicious traffic. addition, addresses issue imbalance during training process at level algorithm level. We evaluated proposed three standard datasets, i.e., NSL-KDD, UNSW-NB15, CICDDoS2019. The experimental results show that outperforms state-of-the-art model terms accuracy, rate, false-positive rate.

Language: Английский

Citations

0
Navigating Challenges and Harnessing Opportunities: Deep Learning Applications in Internet of Medical Things DOI Creative Commons

John Mulo,

Hengshuo Liang, Mian Qian

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(3), P. 107 - 107

Published: March 1, 2025

Integrating deep learning (DL) with the Internet of Medical Things (IoMT) is a paradigm shift in modern healthcare, offering enormous opportunities for patient care, diagnostics, and treatment. Implementing DL IoMT has potential to deliver better diagnosis, treatment, management. However, practical implementation challenges, including data quality, privacy, interoperability, limited computational resources. This survey article provides conceptual framework synthesizes identifies state-of-the-art solutions that tackle challenges current applications DL, analyzes existing limitations future developments. Through an analysis case studies real-world implementations, this work insights into best practices lessons learned, importance robust preprocessing, integration legacy systems, human-centric design. Finally, we outline research directions, emphasizing development transparent, scalable, privacy-preserving models realize full healthcare. aims serve as foundational reference researchers practitioners seeking navigate harness rapidly evolving field.

Language: Английский

Citations

0
Advanced Deep Learning in Medical Imaging: Brain Tumor Detection and Localization with YOLOv9 DOI
Abdussalam Elhanashi, Sergio Saponara, Pierpaolo Dini

et al.

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 113 - 120

Published: Jan. 1, 2025

Language: Английский

Citations

0
Embedded Anomaly Detection System for In-Vehicle Networking Cybersecurity DOI

Sara Visconti,

Elisabetta Soldaini,

Pierpaolo Dini

et al.

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 3 - 10

Published: Jan. 1, 2025

Language: Английский

Citations

0
A systematic review of end-to-end framework for contactless fingerprint recognition: Techniques, challenges, and future directions DOI

Pooja Kaplesh,

Aastha Gupta, Divya Bansal

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 150, P. 110493 - 110493

Published: March 23, 2025

Language: Английский

Citations

0