Hybrid Machine-Learning-Based Spectrum Sensing and Allocation With Adaptive Congestion-Aware Modeling in CR-Assisted IoV Networks

Ahmed, Ramsha; Chen, Yueyun; Hassan, Bilal; Du, Liping; Hassan, Taimur; Dias, Jorge

doi:10.1109/jiot.2022.3195425

Cited by 14 publications

(7 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rapid development of technology, subway machinery is developing in the direction of large-scale, complex, high-speed, and automation, and the mechanical structure is increasingly complex [9][10][11]. The failure of a component may cause chain reaction which affects the operation of the entire device [12]. Some equipment in the way of assembly line operation will also affect the subsequent production, causing the entire production process to be interrupted [13].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Subway Mechanical Equipment Based on 5G Intelligent Sensor Network Signal Processing

2022

Journal of Sensors

View full text Add to dashboard Cite

The application of traditional feature extraction methods in subway mechanical fault diagnosis has attracted the attention of researchers. Based on the 5G intelligent sensor network signal processing theory, this paper constructs a fault diagnosis model for subway machinery and equipment and analyzes the effectiveness of the information redundancy calculation method proposed in this paper by using the on-site vibration data of subway units. The model is obtained by analyzing the entropy characteristics of the vector vibration signal in each bearing section of the subway machinery and equipment. The entropy value quantitatively reflects the vibration complexity of the rotor in the section from different angles and solves the problem of data quantitative analysis. In the simulation process, based on the 5G intelligent sensor network signal and the fuzzy mean clustering information fusion method, in the process of identifying the fault state of the subway unit, a relatively optimistic identification result was obtained. The experimental results show that, no matter whether the Gaussian kernel or the polynomial kernel is selected, the number of kernel principal components whose cumulative contribution rate is greater than 0.85 decreases with the increase of the kernel parameter, and the fault identification support rate is 85%, that is, the diagnosis results of 3 sets of sample data are nonrolling element faults, which significantly improves the performance of the bearing.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Subway Mechanical Equipment Based on 5G Intelligent Sensor Network Signal Processing

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Table VII summarizes the mentioned ML approaches in the field of tracking and localization for ISAC. Other localization works discussed in other use cases include [43], [63], [65].…”

Section: E Data-driven Methods In Isac For Tracking and Localizationmentioning

confidence: 99%

“…A similar binary classification objective was approached by [86], but with a different DL architecture (c.f., Table VIII). Then, Ahmed et al [43] proposed a joint framework for spectrum sensing and localization in Internet of Vehicle (IoV) networks. They proposed a CNN-based model with skip connection layers and an Atrous Spatial Pyramid Pooling (ASPP) [87] module.…”

Section: F Data-driven Methods In Isac For Spectrum Sensingmentioning

confidence: 99%

“…Table III presents a summary of the mentioned ML approaches in ISAC for AVs. Other ISAC-ML based works that considered AV systems include [40] for ISAC-assited AVs, [41]- [43] for vehicular networks, [44]- [46] for vehicle to everything (V2X), [47], [48] for vehicle to infrastructure (V2I), and [49], [50] for UAVs.…”

Section: A Data-driven Approached For Isac-assisted Autonomous Vehicu...mentioning

confidence: 99%

See 1 more Smart Citation

Data-driven Integrated Sensing and Communication: Recent Advances, Challenges, and Future Prospects

Salem,

Quamar,,

Magad

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This paper aims to explore integrating various ML techniques into ISAC systems, covering various applications. These applications span intelligent vehicular networks, encompassing unmanned aerial vehicles (UAVs) and autonomous cars, as well as radar applications, localization and tracking, millimeter wave (mmWave) and Terahertz (THz) communication, and beamforming. The contributions of this paper lie in its comprehensive survey of ML-based works in the ISAC domain and its identification of challenges and future research directions. By synthesizing the existing knowledge and proposing new research avenues, this survey serves as a valuable resource for researchers, practitioners, and stakeholders involved in advancing the capabilities of ISAC systems in the context of 6G networks.</p>

show abstract

“…Given the above, the motivation of this work is to present a robust framework that can jointly segment the three ocular traits (sclera, iris, and pupil), facilitating the development of a biometric system based on multiocular traits in the future. A recent spurt in the expansion of deep learning applications may be attributed to the proven effectiveness of various convolutional neural network (CNN) architectures over other traditional approaches [16], [17], [18], [19]. These advantages have proliferated deep learning-based biometric systems, and the domain has surged recently in security and authentication applications with a significant emphasis on ocular traits [20].…”

mentioning

confidence: 99%

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

Hassan

Ahmed

et al. 2023

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

The advancements in machine vision have opened up new avenues for implementing multimodal biometric identification systems for real-world applications. These systems can address the shortcomings of unimodal biometric systems, which are susceptible to spoofing, noise, nonuniversality, and intraclass variations. Besides, ocular traits among various biometric traits are preferably used in these recognition systems due to their great uniqueness, permanence, and performance. However, segmenting visual biometric features under unconstrained situations remains challenging due to a variety of variables, such as Purkinje reflexes, specular reflections, eye gaze, off-angle pictures, poor resolution, and numerous occlusions. To overcome these challenges, this research presents a novel framework called SIPFormer, comprising the encoder, decoder, and transformer blocks to simultaneously segment three ocular traits (sclera, iris, and pupil) using its discriminative multihead self-attention mechanism. Besides, we used the large publicly available iris database reflecting different unconstrained acquisition settings, with inherent noise effects such as scanner artifacts, intensity and illumination variations, motion blur, and occultations caused by eyelashes, eyelids, and eyeglasses. Furthermore, the simulation results demonstrate the efficacy of the proposed SIPFormer model, where it achieved the mean Dice similarity coefficient scores of 0.9018, 0.9176, and 0.9229 for segmenting the sclera, iris, and pupil classes, respectively.

show abstract

Hybrid Machine-Learning-Based Spectrum Sensing and Allocation With Adaptive Congestion-Aware Modeling in CR-Assisted IoV Networks

Cited by 14 publications

References 57 publications

Fault Diagnosis of Subway Mechanical Equipment Based on 5G Intelligent Sensor Network Signal Processing

Fault Diagnosis of Subway Mechanical Equipment Based on 5G Intelligent Sensor Network Signal Processing

Data-driven Integrated Sensing and Communication: Recent Advances, Challenges, and Future Prospects

SIPFormer: Segmentation of Multiocular Biometric Traits With Transformers

Contact Info

Product

Resources

About