首页|Researchers from University of the Free State Report Recent Findings in Machine Learning (Effectiveness of Lof, Iforest and Ocsvm In Detecting Anomalies In Stre am Sediment Geochemical Data)
Researchers from University of the Free State Report Recent Findings in Machine Learning (Effectiveness of Lof, Iforest and Ocsvm In Detecting Anomalies In Stre am Sediment Geochemical Data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in Machine Learning. According to news originating from Bloemfontein, South Africa, by NewsRx correspondents, research stated, “This paper compares three unsupervi sed machine-learning algorithms - local outlier factor (LOF), Isolation Forest ( iForest) and oneclass support vector machine (OCSVM) - for anomaly detection in a multivariate geochemical dataset in northeastern Iran. This area contains sev eral Au, Cu and Pb-Zn mineral occurrences.” Our news journalists obtained a quote from the research from the University of t he Free State, “The methodology incorporates single-element geochemistry, multiv ariate data analysis and application of the three unsupervised machine-learning algorithms. Principal component analysis unveiled diverse elemental associations for the first seven principal components (PCs): PC1 shows a Co-Cr-Ni-V-Sn assoc iation indicating a lithological influence; PC2 shows a Au-Bi-Cu-W association s uggesting epithermal Au mineralization; PC3 shows variability in Zn-V-Co-Sb-Cu-C r; PC4 shows a Au-Cu-Ba-Sr-Ag association indicating Au and polymetallic mineral ization; PC5 reflects Zn-Ag-Ni-Pb related to hydrothermal mineralization; and PC 6 and PC7 show element associations suggesting epithermal and intrusive-related polymetallic mineralization. It was found that OCSVM performed slightly better t han LOF and iForest in detecting anomalies associated with known Cu occurrences, and it successfully delineated dispersion from all known Au occurrences. LOF ou tperformed iForest and OCSVM in identifying all four Pb-Zn occurrences, and the three methods substantially limited the areas of the anomaly class. The analysis showed that LOF produced a less cluttered anomaly map compared to the isolated patterns in the iForest map. LOF was accurate in identifying anomalies associate d with Au-Pb mineralization, while iForest detected anomalies associated with Pb -Zn-Cu occurrences and neighbouring Pb-Zn occurrence. OCSVM performed similarly in the northern and western areas but displayed unique discrepancies in the SE a nd west by detecting anomalies associated with two Cu occurences and a Pb-Cu occ urrence. This study examined the influence of contamination fraction on detectio n of geochemical anomalies, revealing a noteworthy rise in the count of mineral occurrences delineated by anomalies when the contamination fraction increases fr om 5 to 10 %.”
BloemfonteinSouth AfricaAfricaCybo rgsEmerging TechnologiesMachine LearningUniversity of the Free State
NETL
NSTL
