A semi-supervised total electron content anomaly detection method using LSTM-auto-encoder

Muhammad, Ahmad; Külahçı, Fatih

doi:10.1016/j.jastp.2022.105979

Cited by 5 publications

(1 citation statement)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaining a comprehensive understanding of these complex phenomena is crucial for enhancing the overall effectiveness of the methodology [9]. Deriving analytical expressions for the scattered field caused by a slender inclusion is a challenging task that necessitates a deep comprehension of the relationship between the Bessel function of the first kind and the Hankel function of the second kind [10]. Rigorous numerical methods were employed to calculate the eigenvectors and eigenvalues of the MSR matrix to overcome this challenge [11].…”

Section: Introductionmentioning

confidence: 99%

Localization of Dielectric Anomalies with Multi-level Outlier Detection through Membership Function and Ensemble Classification Framework

Md,

ASCS,

B T P

2024

SCPE

View full text Add to dashboard Cite

This research presents an innovative method for real-time detection of dielectric anomalies, with a primary focus on evaluating apple quality and ripeness using dielectric tomography. The study involves the development of an advanced tomography system within an anechoic chamber, harnessing electromagnetic wave technology and sophisticated antenna systems for data acquisition. The proposed framework encompasses critical stages, including data collection, range bounds computation, threshold determination, class membership assignment, and ensemble classification. By seamlessly integrating statistical methods, density-based clustering, and ensemble learning, this approach significantly enhances precision and reliability in anomaly detection. The integration of available statistical methods, density-based clustering, and ensemble learning may demand substantial computational resources, limiting the scalability and real-time applicability of the proposed framework. Empirical results demonstrate the superior performance of the method, with an accuracy rate of 98.9%, precision of 0.989, F-measure of 0.989, dielectric anomaly recall rate of 0.99, and a low error rate of 0.18. Overall, this research introduces an advanced approach with the potential to revolutionize apple quality assessment and industrial processes across various sectors.

show abstract

Section: Introductionmentioning

confidence: 99%

Localization of Dielectric Anomalies with Multi-level Outlier Detection through Membership Function and Ensemble Classification Framework

Md,

ASCS,

B T P

2024

SCPE

View full text Add to dashboard Cite

show abstract

GRIMS: global and regional ionosphere monitoring system

Ozdemir,

Alcay,

Ogutcu

et al. 2024

GPS Solut

View full text Add to dashboard Cite

The ionosphere shows regular changes such as daily, 27 days, seasonal, semi-annual, annual, and 11 years. These changes can be modeled and their effects largely determined. However, in addition to regular changes, irregular changes occur in the ionosphere due to space weather conditions, natural disasters, and human-induced irregularities. GNSS is one of the instruments along with many others that can give a piece of information on the ionospheric state. Various indices/parameters are used to determine the effect of space weather conditions. The well-known ones are solar activity indices, geomagnetic storm indices, magnetic field components, proton density, and proton flux parameters. It is important to take all of these indices into consideration when investigating the source of the anomaly. Considering only some of them may lead to incorrect inferences about the source of possible anomalies. To carry out comprehensive research in this field, it is necessary to analyze a very large data set. This indicates the requirement for an automatic system. With the Global and Regional Ionosphere Monitoring System (GRIMS) designed within the scope of this study, the ionosphere can be monitored globally and regionally. The GRIMS is online at https://www.online-grims.com/. By using Global ionospheric maps and GNSS receiver data, global, regional, and station-specific anomalies can be detected regularly through methods such as HDI (Highest Density Interval) and ARIMA (Autoregressive Integrated Moving Average). GRIMS gathers space weather-related parameters from ionospheric data centers to help users interpret the situation, and it allows users to download the results and request data for specific days. The details of the experimental results and output products of the system designed during the geomagnetic active days of March 17, 18, 2015 are given in this paper. Moreover, geomagnetic active days that occurred between 2000 and 2023 are given in the GRIMS.

show abstract