Fault diagnosis based on extremely randomized trees in wireless sensor networks

Saeed, Umer; Jan, Sana Ullah; Lee, Young-Doo; Koo, Insoo

doi:10.1016/j.ress.2020.107284

Cited by 147 publications

(67 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The full details of the selected hyperparameters for each algorithm are listed in tabular form ( Supplementary Material—Table S2 ). The modeling results were measured by accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic curve (ROC), and area under the receiver operating characteristic curve (AUC) [ 36 ]. We compared the performance of the seven AUCs between algorithms [ 28 , 32 , 37 , 38 , 39 , 40 ].…”

Section: Methodsmentioning

confidence: 99%

A Real-Time Artificial Intelligence-Assisted System to Predict Weaning from Ventilator Immediately after Lung Resection Surgery

Chang

Hung

Wang

et al. 2021

IJERPH

View full text Add to dashboard Cite

Assessment of risk before lung resection surgery can provide anesthesiologists with information about whether a patient can be weaned from the ventilator immediately after surgery. However, it is difficult for anesthesiologists to perform a complete integrated risk assessment in a time-limited pre-anesthetic clinic. We retrospectively collected the electronic medical records of 709 patients who underwent lung resection between 1 January 2017 and 31 July 2019. We used the obtained data to construct an artificial intelligence (AI) prediction model with seven supervised machine learning algorithms to predict whether patients could be weaned immediately after lung resection surgery. The AI model with Naïve Bayes Classifier algorithm had the best testing result and was therefore used to develop an application to evaluate risk based on patients’ previous medical data, to assist anesthesiologists, and to predict patient outcomes in pre-anesthetic clinics. The individualization and digitalization characteristics of this AI application could improve the effectiveness of risk explanations and physician–patient communication to achieve better patient comprehension.

show abstract

Section: Methodsmentioning

confidence: 99%

A Real-Time Artificial Intelligence-Assisted System to Predict Weaning from Ventilator Immediately after Lung Resection Surgery

Chang

Hung

Wang

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…The authors of [ 23 ] considered a Long Short-term Memory NN for fault detection and isolation against three defective classes. In earlier work [ 24 ], we proposed an ensemble learning-based lightweight approach to detect and diagnose most faults occurring in a WSN. However, a more sophisticated system that is not only lightweight but also significantly accurate is desirable.…”

Section: Related Workmentioning

confidence: 99%

“…High variance can cause the overfitting problem, while a high bias can provoke underfitting. Moreover, the ET ability in randomness makes it computationally faster, and robust towards noisy features [ 24 , 31 ].…”

Section: The Proposed Cafd Schemementioning

confidence: 99%

CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning

Saeed

Lee

Jan

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Sensors’ existence as a key component of Cyber-Physical Systems makes it susceptible to failures due to complex environments, low-quality production, and aging. When defective, sensors either stop communicating or convey incorrect information. These unsteady situations threaten the safety, economy, and reliability of a system. The objective of this study is to construct a lightweight machine learning-based fault detection and diagnostic system within the limited energy resources, memory, and computation of a Wireless Sensor Network (WSN). In this paper, a Context-Aware Fault Diagnostic (CAFD) scheme is proposed based on an ensemble learning algorithm called Extra-Trees. To evaluate the performance of the proposed scheme, a realistic WSN scenario composed of humidity and temperature sensor observations is replicated with extreme low-intensity faults. Six commonly occurring types of sensor fault are considered: drift, hard-over/bias, spike, erratic/precision degradation, stuck, and data-loss. The proposed CAFD scheme reveals the ability to accurately detect and diagnose low-intensity sensor faults in a timely manner. Moreover, the efficiency of the Extra-Trees algorithm in terms of diagnostic accuracy, F1-score, ROC-AUC, and training time is demonstrated by comparison with cutting-edge machine learning algorithms: a Support Vector Machine and a Neural Network.

show abstract

“…With the rapid development of the manufacturing industry, machine fault diagnosis plays an increasingly important role in ensuring the safe operation of equipment [1][2][3]. Unexpected equipment failures will cause severe damage to the equipment and cause more economic losses due to the interruption of plant operation.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Niche Immune Genetic Algorithm for Fault Detection Coverage in Industry Wireless Sensor Network

et al. 2021

View full text Add to dashboard Cite

The industry wireless sensor network (IWSN) technology, which is used to monitor industrial equipment, has attracted more and more attention in recent years. Sensor nodes in IWSN can spontaneously complete distributed networking and carry out monitoring tasks under random deployment conditions. Therefore, a self-organized IWSN is particularly suitable for the fault detection and diagnosis of industrial equipment in complex environments. However, due to the detection, ability of a single sensor node is limited, and the monitoring distribution problem is a typical multidimensional discrete NP-hard combinatorial stochastic optimization problem, which is challenging to solve for the traditional mathematical methods. With the purpose of improving the target monitoring capability and prolonging lifetime of IWSN, a novel hybrid niche immune genetic algorithm (HNIGA) for optimizing the target coverage model of fault detection is proposed. It uses the genetic operation to evolve antibody groups and applies niche technology to maintain the diversity of antibody groups. As a result, HNIGA can effectively reduce the failure rate of detection targets. To verify the performance of HNIGA, a series of simulations under different simulation conditions are carried out. Specifically, HNIGA is compared with genetic algorithm (GA) and simulated annealing (SA). Simulation results show that HNIGA has a faster convergence speed and more robust global search capability than the other two algorithms.

show abstract

Fault diagnosis based on extremely randomized trees in wireless sensor networks

Cited by 147 publications

References 40 publications

A Real-Time Artificial Intelligence-Assisted System to Predict Weaning from Ventilator Immediately after Lung Resection Surgery

A Real-Time Artificial Intelligence-Assisted System to Predict Weaning from Ventilator Immediately after Lung Resection Surgery

CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning

Hybrid Niche Immune Genetic Algorithm for Fault Detection Coverage in Industry Wireless Sensor Network

Contact Info

Product

Resources

About