A Fault Prediction Algorithm Based on Rough Sets and Back Propagation Neural Network for Vehicular Networks

Geng, Rui; Wang, Xiaojie; Ye, Ning; Li, Jun

doi:10.1109/access.2018.2881890

Cited by 20 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Jaringan saraf tiruan Backpropagation adalah struktur jaringan saraf tiga lapis atau multilayer yaitu lapisan masukan, lapisan tersembunyi, dan lapisan keluaran. Lapisan tersembunyi bisa mempunyai lebih dari satu lapisan [11]. Korespondensi internodal secara efektif mencirikan properti pemetaan nonlinier dari Backpropagation, memungkinkan jaringan untuk mengungkapkan mekanisme dan prinsip masalah nonlinier yang kompleks [12].…”

Section: Pendahuluanunclassified

Prediksi Pencapaian Target Peserta Keluarga Berencana Pasca Persalinan Menggunakan Algoritma Backpropagation

2021

View full text Add to dashboard Cite

Population growth in Indonesia continues to increase, so the government makes a program to control the rate of growth of the population, namely the Family Planning Program (KB). The implementation of family planning also has another objective, namely to reduce the risk of maternal death after childbirth. To measure the level of increasing target achievement of postpartum family planning participants. So that it can be a reference for the DPPKBP3A in carrying out the postpartum family planning program. Data from the Population Control, Family Planning, Women Empowerment and Child Protection (DPPKBP3A) District Lima Puluh Kota data processed in this study is data on the achievement of postpartum family planning participants from 2018 to 2020. Data processing uses the Backpropagation algorithm through several stages, namely the stage initialization, activation stage, weight training (weight change) and iteration stage. One of the results obtained from the calculation is the comparison of the target with the output gradient error in Suliki District in 2018, namely the target of 0.11311 and the result of the error gradient output is -0.1171. The prediction results obtained from this process become a reference for the Population Control, Family Planning and Women Empowerment and Child Protection Agency (DPPKBP3A) of District Lima Puluh Kota to implement the implementation of postpartum family planning programs to the community the following year.

show abstract

Section: Pendahuluanunclassified

Prediksi Pencapaian Target Peserta Keluarga Berencana Pasca Persalinan Menggunakan Algoritma Backpropagation

2021

View full text Add to dashboard Cite

show abstract

“…In spite of the significant development of ANN models, it was found that complex nonlinear optimization problems cannot be efficiently solved by the available neural network models. In particular, some problems persist, such as the difficulty of determining the initial connection weight thresholds and the slow convergence of BPNNs [44]. The gradient descent method used in BPNNs is highly sensitive to the initial connection weight and the set threshold [45]; therefore, the selection of different initial values may lead to different training results and there exists sparse theoretical guidance for determining the appropriate weight and threshold.…”

Section: Related Studiesmentioning

confidence: 99%

Cognitive Competence Improvement for Autonomous Vehicles: A Lane Change Identification Model for Distant Preceding Vehicles

Wang

Sun

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The motion status recognition of the preceding vehicle in a long-distance region is a requirement for autonomous vehicles to make appropriate decisions and increase their comprehension of the environment. At present, the lane change behavior of the leading vehicle at a short distance is detected using stereo cameras and LiDAR. However, the short detection distance (about 100 m) does not meet the requirements of high-speed driving of autonomous vehicles on expressways; this is a fundamental problem limiting the development of autonomous vehicles exhibiting human-like behavior. In this paper, a comprehensive model consisting of a back-propagation (BP) neural network model optimized by a particle swarm optimization (PSO) algorithm, and a continuous identification model is developed based on the results of naturalistic on-road experiments using millimeter-wave radar data. By considering different time-to-lane crossings (TLCs), the PSO-BP neural network model is trained using real vehicle lane change data and implemented when the TLC of the leading vehicle is longer than 1.0 s. In contrast, when the TLC is less than 1 s, the continuous recognition model of the TLC is used. By comparison with the BP neural network model, the recognition accuracy rate of the proposed model is increased from 80% to 87% after the PSO optimization for a time window of 1.0 s; these results meet the recognition requirements of the autonomous driving systems for distant targets. The findings of this paper improve the cognitive competence and safety of autonomous driving systems.INDEX TERMS Autonomous driving perception, cognitive competence, lane change behavior, BP neural network.

show abstract

“…Communication network becomes a familiar concept nowadays for providing many functional capabilities to real‐world systems such as signal processing, 1 system monitoring, 2 state filtering, 3 fault diagnosing, 4 target tracking, 5 remote navigating, 6 and distribute controlling 7 . By the assistance of communication facilities, the networked control systems (NCSs) are gradually emerged and they have received extensive attention due to some superior advantages such as low cost, simple implementation, convenient maintenance, high reliability, and so forth 8,9 …”

Section: Introductionmentioning

confidence: 99%

Dual event‐triggered control for linear systems with consecutive packet losses

Cui

2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article investigates an event‐triggered control for linear continuous‐time systems by tolerating consecutive packet losses. Two event‐triggers are, respectively, employed in the sensor‐to‐controller and controller‐to‐actuator channels in order to reduce the data transmission pressures. A simple discrete‐time state feedback control law is proposed and the control command is only updated when the actuator successfully receives the command information. By the proposed method, the event‐triggers are proved to be maintained or violated consecutively. The appropriate data sampling period and the maximal allowable packet loss numbers can be quantitatively determined. In addition, it is also proved that the event‐trigger in controller‐to‐actuator may not be violated immediately with the event‐trigger in sensor‐to‐actuator. The uniform ultimate bound of the closed‐loop system can be achieved. Finally, numerical examples are provided to demonstrate the effectiveness of the proposed method.

show abstract

A Fault Prediction Algorithm Based on Rough Sets and Back Propagation Neural Network for Vehicular Networks

Cited by 20 publications

References 22 publications

Prediksi Pencapaian Target Peserta Keluarga Berencana Pasca Persalinan Menggunakan Algoritma Backpropagation

Prediksi Pencapaian Target Peserta Keluarga Berencana Pasca Persalinan Menggunakan Algoritma Backpropagation

Cognitive Competence Improvement for Autonomous Vehicles: A Lane Change Identification Model for Distant Preceding Vehicles

Dual event‐triggered control for linear systems with consecutive packet losses

Contact Info

Product

Resources

About