A Novel on Transmission Line Tower Big Data Analysis Model Using Altered K-means and ADQL

Abstract

This study sought to propose a big data analysis and prediction model for transmission line tower outliers to assess when something is wrong with transmission line tower big data based on deep reinforcement learning. The model enables choosing automatic cluster K values based on non-labeled sensor big data. It also allows measuring the distance of action between data inside a cluster with the Q-value representing network output in the altered transmission line tower big data clustering algorithm containing transmission line tower outliers and old Deep Q Network. Specifically, this study performed principal component analysis to categorize transmission line tower data and proposed an automatic initial central point approach through standard normal distribution. It also proposed the A-Deep Q-Learning algorithm altered from the deep Q-Learning algorithm to explore policies based on the experiences of clustered data learning. It can be used to perform transmission line tower outlier data learning based on the distance of data within a cluster. The performance evaluation results show that the proposed model recorded an approximately 2.29%~4.19% higher prediction rate and around 0.8% ~ 4.3% higher accuracy rate compared to the old transmission line tower big data analysis model.

Steady-State Fault Detection with Full-Flight Data

“…In general, k-means clustering does not provide intrinsic outlier detection necessary for fault detection. Utilizing k-means clustering for fault detection requires additional algorithms, e.g., artificial neural networks [21], or cluster evaluation [22]. These additional algorithms increase the complexity of the k-means clustering.…”

“…For each of the 100 sampled flights, transient datasets for the nominal and faulty engine performance were generated. For simulating the component faults, the capacities Q Map and efficiencies η Map derived from the component maps were adjusted by scaling factors defined by Equations ( 20) and (21).…”

Holding out the promise of Lasswell's dream: Big data analytics in public policy research and teaching

“…This is depicted, for instance, in the case of transportation by Gerum et al (2019) in their predictive analysis of defects in railways using a discounted Markov decision process, Ying et al (2020) in their use of deep reinforcement learning for metro train scheduling, and Rasouli and Timmermans (2014) in their prediction of modal choice in the Netherlands using a model ensemble with decision trees. Illustrative applications in other policy areas include the use of reinforcement learning for evaluation of dialogue strategies (Rieser & Lemon, 2011), implementation of A-Deep Q-Learning clustering algorithm for transmission line tower fault prediction (Jung & Huh, 2019), and integration of machine learning with quasi-random assignment to analyze its potential to enhance judicial decision-making (Kleinberg et al, 2018). Some publications in this theme also go beyond the direct application of machine learning.…”

Efficient chaotic-Baker-map-based cancelable face recognition

“…In contrast, the DWT is implemented using multi-level filter banks. A single level decomposition of a 1-D signal x(k) can be mathematically conveyed as follows (Guan et al 2005;Ma et al 2017;Jiang et al 2016;Jung and Huh 2019;Huh 2018):…”