Convolutional Neural Networks for Real-Time and Wireless Damage Detection

Avcı, Onur; Abdeljaber, Osama; Kıranyaz, Serkan; Inman, Daniel J.

doi:10.1007/978-3-030-12115-0_17

Cited by 35 publications

(15 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Firstly, normal analysis when some of the selected nodes are exposed to be unsecured by eliminating the security mechanism over them. The selected nodes are nodes number (11,14,20,22,25,30). The second sector focus on implementing an artificial neural network system using MATLAB simulator.…”

Section: Resultsmentioning

confidence: 99%

“…For example, the highest difference of PDR is occurred at node 2 by 91.66% and the lowest PDR at -216% at node 15. Moreover, the PDR values at unsecured nodes are 90.83%, 33.33%, 20.83 %, 8.3%, 16.66%, and 70.83% for nodes 11,14,20,22,25,30, respectively. The variations in PDR at these nodes when all nodes are secured and some are unsecured are 55.2%, 42.85%, 58.88%, 71.42%, 33.33%, and 10.52%.…”

Section: Performance Evaluation 411 Packet Delivery Ratiomentioning

confidence: 98%

“…Besides, the unsecured condition makes significant variations in energy consumption, so it is used as a second input in designing the ANN to detect the unsecured nodes in WSN. Moreover, the energy consumption values at unsecured nodes are 12.107 mw, 19.885 mw, 22.023 mw, 5.415 mw, 11.913 mw, and 9.825 mw for nodes 11,14,20,22,25,30, respectively. The variations in energy consumption at these nodes when all nodes are secured and some are unsecured are -60.16%, -44.55%, -115.17%, 31.56%, 28.07%, and 5.1%.…”

Section: Energy Consumptionmentioning

confidence: 99%

See 2 more Smart Citations

Secured node detection technique based on artificial neural network for wireless sensor network

Hasan

Alani²,

Saad³

2021

IJECE

View full text Add to dashboard Cite

The wireless sensor network is becoming the most popular network in the last recent years as it can measure the environmental conditions and send them to process purposes. Many vital challenges face the deployment of WSNs such as energy consumption and security issues. Various attacks could be subjects against WSNs and cause damage either in the stability of communication or in the destruction of the sensitive data. Thus, the demands of intrusion detection-based energy-efficient techniques rise dramatically as the network deployment becomes vast and complicated. Qualnet simulation is used to measure the performance of the networks. This paper aims to optimize the energy-based intrusion detection technique using the artificial neural network by using MATLAB Simulink. The results show how the optimized method based on the biological nervous systems improves intrusion detection in WSN. In addition to that, the unsecured nodes are affected the network performance negatively and trouble its behavior. The regress analysis for both methods detects the variations when all nodes are secured and when some are unsecured. Thus, Node detection based on packet delivery ratio and energy consumption could efficiently be implemented in an artificial neural network.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Performance Evaluation 411 Packet Delivery Ratiomentioning

confidence: 98%

Section: Energy Consumptionmentioning

confidence: 99%

See 1 more Smart Citation

Secured node detection technique based on artificial neural network for wireless sensor network

Hasan

Alani²,

Saad³

2021

IJECE

View full text Add to dashboard Cite

show abstract

“…It was noticed that the process of generating the data required to train the 1D CNNs in [50,52,71] requires a large number of measurement sessions especially for a large civil structure. Therefore, Avci et al in [53] and then Abdeljaber et al in [54] developed a novel approach based on 1D CNNs, which require significantly less effort and labeled data for training.…”

Section: Figure 11mentioning

confidence: 99%

“…Damaged joint acceleration signal Accelerometer to record acceleration signal Loosened bolts at the joint Figure 12: The test setup and wireless sensors used in [50,71].…”

Section: Loosened Boltsmentioning

confidence: 99%

1-D Convolutional Neural Networks for Signal Processing Applications

Kıranyaz

İnce

Abdeljaber

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

275

View full text Add to dashboard Cite

During the last decade, Convolutional Neural Networks (CNNs) have become the de facto standard for various Computer Vision and Machine Learning operations. CNNs are feed-forward Artificial Neural Networks (ANNs) with alternating convolutional and subsampling layers. Deep 2D CNNs with many hidden layers and millions of parameters have the ability to learn complex objects and patterns providing that they can be trained on a massive size visual database with ground-truth labels. With a proper training, this unique ability makes them the primary tool for various engineering applications for 2D signals such as images and video frames. Yet, this may not be a viable option in numerous applications over 1D signals especially when the training data is scarce or application-specific. To address this issue, 1D CNNs have recently been proposed and immediately achieved the state-of-the-art performance levels in several applications such as personalized biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and motor-fault detection. Another major advantage is that a real-time and low-cost hardware implementation is feasible due to the simple and compact configuration of 1D CNNs that perform only 1D convolutions (scalar multiplications and additions). This paper presents a comprehensive review of the general architecture and principals of 1D CNNs along with their major engineering applications, especially focused on the recent progress in this field. Their state-of-the-art performance is highlighted concluding with their unique properties. The benchmark datasets and the principal 1D CNN software used in those applications are also publically shared in a dedicated website.

show abstract