scholarly journals 3D Geophysical Post-Inversion Feature Extraction for Mineral Exploration Through Fast-ICA

2021 ◽  
Author(s):  
Bahman Abbassi ◽  
Li Zhen Cheng
Keyword(s):  
Feature Extraction ◽  
Physical Properties ◽  
Mineral Exploration ◽  
Physical Property ◽  
Extraction Process ◽  
Earth Model ◽  
Geological Features ◽  
Fast Independent Component Analysis ◽  
Geological Information ◽  
Ica Algorithm

A major problem in the post-inversion geophysical interpretation is the extraction of geological information from inverted physical property models, which do not necessarily represent all underlying geological features. No matter how accurate the inversions are, each inverted physical property model is sensitive to limited aspects of subsurface geology and is insensitive to other geological features that are otherwise detectable with complementary physical property models. Therefore, specific parts of the geological model can be reconstructed from different physical property models. To show how this reconstruction works, we simulated a complex geological system that comprises an original layered earth model that has passed several geological deformations and alteration overprints. Linear combination of complex geological features comprised three physical property distributions: Electrical resistivity, induced polarization chargeability, and magnetic susceptibility models. This study proposes a multivariate feature extraction approach to extract information about the underlying geological features comprising the bulk physical properties. We evaluated our method in numerical simulations and compared three feature extraction algorithms to see the tolerance of each method to the geological artifacts and noises. We show that the fast-independent component analysis (fast-ICA) algorithm by negentropy maximization is a robust method in the geological feature extraction that can handle the added unknown geological noises. The post-inversion physical properties are also used to reconstruct the underlying geological sources. We show that the sharpness of the inverted images is an important constraint on the feature extraction process. Our method successfully separates geological features in multiple 3D physical property models. This methodology is reproducible for any number of lithologies and physical property combinations and can recover the latent geological features, including the background geological patterns from overprints of chemical alteration.

scholarly journals 3D Geophysical Post-Inversion Feature Extraction for Mineral Exploration through Fast-ICA

Minerals ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 959
Author(s):  
Bahman Abbassi ◽  
Li-Zhen Cheng
Keyword(s):  
Feature Extraction ◽  
Physical Properties ◽  
Mineral Exploration ◽  
Physical Property ◽  
Extraction Process ◽  
Earth Model ◽  
Geological Features ◽  
Fast Independent Component Analysis ◽  
Geological Information ◽  
Ica Algorithm

A major problem in the post-inversion geophysical interpretation is the extraction of geological information from inverted physical property models, which do not necessarily represent all underlying geological features. No matter how accurate the inversions are, each inverted physical property model is sensitive to limited aspects of subsurface geology and is insensitive to other geological features that are otherwise detectable with complementary physical property models. Therefore, specific parts of the geological model can be reconstructed from different physical property models. To show how this reconstruction works, we simulated a complex geological system that comprised an original layered Earth model that has passed several geological deformations and alteration overprints. Linear combination of complex geological features comprised three physical property distributions: electrical resistivity, induced polarization chargeability, and magnetic susceptibility models. This study proposes a multivariate feature extraction approach to extract information about the underlying geological features comprising the bulk physical properties. We evaluated our method in numerical simulations and compared three feature extraction algorithms to see the tolerance of each method to the geological artifacts and noises. We show that the fast-independent component analysis (Fast-ICA) algorithm by negentropy maximization is a robust method in the geological feature extraction that can handle the added unknown geological noises. The post-inversion physical properties were also used to reconstruct the underlying geological sources. We show that the sharpness of the inverted images is an important constraint on the feature extraction process. Our method successfully separates geological features in multiple 3D physical property models. This methodology is reproducible for any number of lithologies and physical property combinations and can recover the latent geological features, including the background geological patterns from overprints of chemical alteration.

The Rock Physical Property Database of British Columbia, and the distinct petrophysical signature of the Chilcotin basalts,

2014 ◽  
Vol 51 (4) ◽  
pp. 327-338 ◽  
Author(s):  
Randolph J. Enkin
Keyword(s):  
British Columbia ◽  
Magnetic Susceptibility ◽  
Physical Properties ◽  
Mineral Exploration ◽  
Physical Property ◽  
Bimodal Distribution ◽  
Magnetic Survey ◽  
Survey Analysis ◽  
Magnetic Remanence ◽  
Geophysical Surveys

Rock physical properties provide the link between geophysical surveys and their geological interpretation. The British Columbia rock physical properties database, compiled by the Geological Survey of Canada, now comprises 3876 values of density, 930 values of electric resistivity, 12 356 values of magnetic susceptibility, and 2576 values of magnetic remanence and Koenigsberger ratio. The measurements are linked to sample locations, lithologies, and geological formation or unit. Maps, histograms, and biplots are used to demonstrate useful links between lithology and physical properties, and serve as a background for future rock physical properties studies. As expected, density and resistivity are controlled mostly by porosity and mineralogy. Magnetic susceptibility has a bimodal distribution (maxima at 4 × 10−4 and 2 × 10−2 SI) controlled by magnetite concentration. Magnetic remanence is shown to be more important than usually considered in magnetic survey analysis, with Koenigsberger ratios greater than unity in 42% of the samples. A case study of the Chilcotin Group basalts is highlighted, as they form a significant barrier to mineral exploration in central British Columbia. These rocks are magnetically distinct from other basalts in British Columbia, distinguished by magnetic susceptibilities having a range of values concentrated around 3 × 10−3 SI and falling in the valley between the two susceptibility modes. These basalts are also characterized by very high Koenigsberger ratios (96% above unity), probably caused by a preponderance of fine-grained single-domain magnetite. The database provides a wealth of petrophysical properties that can help constrain analysis of several types of geophysical surveys and, in particular, modelling of anomalies in the quest to determine the three-dimensional distribution of rock units.

Joint inversion of seismic traveltimes and gravity data on unstructured grids with application to mineral exploration

Geophysics ◽  
2012 ◽  
Vol 77 (1) ◽  
pp. K1-K15 ◽  
Author(s):  
Peter G. Lelièvre ◽  
Colin G. Farquharson ◽  
Charles A. Hurich
Keyword(s):  
Seismic Data ◽  
Unstructured Grids ◽  
Joint Inversion ◽  
Mineral Exploration ◽  
Gravity Data ◽  
Physical Property ◽  
Sulfide Deposit ◽  
Earth Model ◽  
Data Set ◽  
First Arrival

Seismic methods continue to receive interest for use in mineral exploration due to the much higher resolution potential of seismic data compared to the techniques traditionally used, namely, gravity, magnetics, resistivity, and electromagnetics. However, the complicated geology often encountered in hard-rock exploration can make data processing and interpretation difficult. Inverting seismic data jointly with a complementary data set can help overcome these difficulties and facilitate the construction of a common earth model. We considered the joint inversion of seismic first-arrival traveltimes and gravity data to recover causative slowness and density distributions. Our joint inversion algorithm differs from previous work by (1) incorporating a large suite of measures for coupling the two physical property models, (2) slowly increasing the effect of the coupling to help avoid potential convergence issues, and (3) automatically adjusting two Tikhonov tradeoff parameters to achieve a desired fit to both data sets. The coupling measures used are both compositional and structural in nature and allow the inclusion of explicitly known or implicitly assumed empirical relationships, physical property distribution information, and cross-gradient structural coupling. For any particular exploration scenario, the combination of coupling measures used should be guided by the geologic knowledge available. We performed our inversions on unstructured grids comprised of triangular cells in 2D, or tetrahedral cells in 3D, but the joint inversion methods are equally applicable to rectilinear grids. We tested our joint inversion methodology on scenarios based on the Voisey’s Bay massive sulfide deposit in Labrador, Canada. These scenarios present a challenge to the inversion of first-arrival traveltimes and we show how joint inversion with gravity data can improve recovery of the subsurface features.

Handwritten Balinesse Character Recognition using K-Nearest Neighbor

2018 ◽  
Author(s):  
I Wayan Agus Surya Darma
Keyword(s):  
Feature Extraction ◽  
Success Rate ◽  
Character Recognition ◽  
Nearest Neighbor ◽  
Recognition System ◽  
Extraction Process ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
K Nearest Neighbor Algorithm ◽  
Character Feature

Balinese character recognition is a technique to recognize feature or pattern of Balinese character. Feature of Balinese character is generated through feature extraction process. This research using handwritten Balinese character. Feature extraction is a process to obtain the feature of character. In this research, feature extraction process generated semantic and direction feature of handwritten Balinese character. Recognition is using K-Nearest Neighbor algorithm to recognize 81 handwritten Balinese character. The feature of Balinese character images tester are compared with reference features. Result of the recognition system with K=3 and reference=10 is achieved a success rate of 97,53%.

scholarly journals Categorisation of EEG suppression using enhanced feature extraction for SUDEP risk assessment

2020 ◽  
Vol 20 (S12) ◽  
Author(s):  
Juan C. Mier ◽  
Yejin Kim ◽  
Xiaoqian Jiang ◽  
Guo-Qiang Zhang ◽  
Samden Lhatoo
Keyword(s):  
Sensitivity Analysis ◽  
Feature Extraction ◽  
Random Forest ◽  
Window Size ◽  
Extraction Process ◽  
Unexpected Death ◽  
Power Spectral ◽  
Eeg Data ◽  
Boosted Decision Trees ◽  
Future Work

Abstract Background Sudden Unexpected Death in Epilepsy (SUDEP) has increased in awareness considerably over the last two decades and is acknowledged as a serious problem in epilepsy. However, the scientific community remains unclear on the reason or possible bio markers that can discern potentially fatal seizures from other non-fatal seizures. The duration of postictal generalized EEG suppression (PGES) is a promising candidate to aid in identifying SUDEP risk. The length of time a patient experiences PGES after a seizure may be used to infer the risk a patient may have of SUDEP later in life. However, the problem becomes identifying the duration, or marking the end, of PGES (Tomson et al. in Lancet Neurol 7(11):1021–1031, 2008; Nashef in Epilepsia 38:6–8, 1997). Methods This work addresses the problem of marking the end to PGES in EEG data, extracted from patients during a clinically supervised seizure. This work proposes a sensitivity analysis on EEG window size/delay, feature extraction and classifiers along with associated hyperparameters. The resulting sensitivity analysis includes the Gradient Boosted Decision Trees and Random Forest classifiers trained on 10 extracted features rooted in fundamental EEG behavior using an EEG specific feature extraction process (pyEEG) and 5 different window sizes or delays (Bao et al. in Comput Intell Neurosci 2011:1687–5265, 2011). Results The machine learning architecture described above scored a maximum AUC score of 76.02% with the Random Forest classifier trained on all extracted features. The highest performing features included SVD Entropy, Petrosan Fractal Dimension and Power Spectral Intensity. Conclusion The methods described are effective in automatically marking the end to PGES. Future work should include integration of these methods into the clinical setting and using the results to be able to predict a patient’s SUDEP risk.

Clinical Performance and Physical Properties of Twelve Amalgam Alloys

1978 ◽  
Vol 57 (11-12) ◽  
pp. 983-988 ◽  
Author(s):  
J.W. Osborne ◽  
E.N. Gale ◽  
C.L. Chew ◽  
B.F. Rhodes ◽  
R.W. Phillips
Keyword(s):  
Compressive Strength ◽  
Physical Properties ◽  
Failure Rate ◽  
Clinical Performance ◽  
Physical Property ◽  
One Year

An assessment of the marginal failure rate of 1,041 restorations of twelve alloys was made at one year. In addition, physical property tests were conducted. A correlation was found between the clinical performance and creep (.79), flow (.62) and 24-hour compressive strength (.60).

Study on the leakage of plunger pair under static condition in high-pressure common rail injector considering deformation effect

2021 ◽  
pp. 095440702110656
Author(s):  
Zhenbo Gao ◽  
Yong Zhang ◽  
Dandan Wang
Keyword(s):  
High Pressure ◽  
Physical Properties ◽  
Thickness Distribution ◽  
Physical Property ◽  
Static Condition ◽  
Flow Equation ◽  
Common Rail ◽  
Plunger Pair ◽  
Common Rail Injector ◽  
High Pressure Common Rail

Plunger pair is the key component of high pressure common rail injector and its sealing performance is very important. Therefore, it is of great significance to study the leakage mechanism of plunger pair. Under static condition, the high-pressure fuel flow in the gap of the plunger pair caused the deformation of the plunger pair structure and the temperature rise of fuel. For a more comprehensive and accurate study, the effect of deformation, including elastic deformation and thermal expansion, the physical properties of fuel, including density, viscosity and specific heat capacity, as well as the influence of plunger posture in the plunger sleeve, including concentric, eccentric, and inclination condition, are considered in this paper. Firstly, the mathematical models including Reynolds equation, film thickness equation, non-isothermal flow equation, parametric equation of fuel physical property, and section velocity equation are established. The numerical analysis based on finite difference method for the solution of these models is given, which can simultaneously solve for the fuel film pressure distribution, temperature distribution, thickness distribution, distribution of fuel physical properties, and leakage rate. The models are validated by comparing the calculated leakage rates with the measurements. The effects under different posture of plunger are discussed too. Some of the conclusions provided good guidance for the design of high-pressure common rail injector.

Physical properties of biaxially oriented PA6 film for simultaneous stretching and sequential processing

2011 ◽  
Vol 31 (1) ◽  
Author(s):  
Masao Takashige ◽  
Toshitaka Kanai
Keyword(s):  
Impact Strength ◽  
Physical Properties ◽  
Physical Property ◽  
High Impact ◽  
Thermal Shrinkage ◽  
Double Bubble ◽  
Biaxial Stretching ◽  
High Impact Strength ◽  
The Difference ◽  
Stretching Process

Abstract There are two different stretching processes that produce the biaxially oriented film, namely the tenter process and double bubble tubular film process. Furthermore, there are two tenter processes, i.e., the sequential biaxial stretching process and simultaneous biaxial stretching process. There is no report describing the difference among film physical properties of the three different processes. The biaxially oriented polyamide film using the double bubble tubular process has good balanced physical property and high impact strength, thus it is used for proper applications utilizing their advantage properties. In this report, the influence of each biaxial stretching process on film physical properties of polyamide, which has hydrogen bond, was studied in detail. As a result, the tentering process film has anisotropic tensile properties between machine direction (MD) and transverse direction (TD). This result was influenced by a later stretching process, namely TD stretching. On the contrary, the double bubble tubular film has good balanced properties, especially thermal shrinkage and impact strength. Tentering simultaneous stretching film has much larger shrinkage in MD than in TD. The sequential stretching film has larger shrinkage in TD than in MD. The double bubble tubular film has high impact strength, because it corresponds to the balanced molecular orientation.

scholarly journals Design and Analysis System of KNN and ID3 Algorithm for Music Classification based on Mood Feature Extraction

2017 ◽  
Vol 7 (1) ◽  
pp. 486
Author(s):  
Made Sudarma ◽  
I Gede Harsemadi
Keyword(s):  
Feature Extraction ◽  
Processing Time ◽  
Nearest Neighbor ◽  
Extraction Process ◽  
Performance Comparison ◽  
K Nearest Neighbor ◽  
K Value ◽  
Id3 Algorithm ◽  
Analysis System ◽  
Music Information

Each of music which has been created, has its own mood which is emitted, therefore, there has been many researches in Music Information Retrieval (MIR) field that has been done for recognition of mood to music.  This research produced software to classify music to the mood by using K-Nearest Neighbor and ID3 algorithm.  In this research accuracy performance comparison and measurement of average classification time is carried out which is obtained based on the value produced from music feature extraction process.  For music feature extraction process it uses 9 types of spectral analysis, consists of 400 practicing data and 400 testing data.  The system produced outcome as classification label of mood type those are contentment, exuberance, depression and anxious.  Classification by using algorithm of KNN is good enough that is 86.55% at k value = 3 and average processing time is 0.01021.  Whereas by using ID3 it results accuracy of 59.33% and average of processing time is 0.05091 second.

Kernel Optimized-Support Vector Machine and MapReduce Framework for Sentiment Classification of Train Reviews

2019 ◽  
Vol 27 (06) ◽  
pp. 1025-1050
Author(s):  
Rashmi K. Thakur ◽  
Manojkumar V. Deshpande
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Public Transportation ◽  
Extraction Process ◽  
Sentiment Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Mapreduce Framework ◽  
Mapreduce Model

Sentiment analysis is one of the popular techniques gaining attention in recent times. Nowadays, people gain information on reviews of users regarding public transportation, movies, hotel reservation, etc., by utilizing the resources available, as they meet their needs. Hence, sentiment classification is an essential process employed to determine the positive and negative responses. This paper presents an approach for sentiment classification of train reviews using MapReduce model with the proposed Kernel Optimized-Support Vector Machine (KO-SVM) classifier. The MapReduce framework handles big data using a mapper, which performs feature extraction and reducer that classifies the review based on KO-SVM classification. The feature extraction process utilizes features that are classification-specific and SentiWordNet-based. KO-SVM adopts SVM for the classification, where the exponential kernel is replaced by an optimized kernel, finding the weights using a novel optimizer, Self-adaptive Lion Algorithm (SLA). In a comparative analysis, the performance of KO-SVM classifier is compared with SentiWordNet, NB, NN, and LSVM, using the evaluation metrics, specificity, sensitivity, and accuracy, with train review and movie review database. The proposed KO-SVM classifier could attain maximum sensitivity of 93.46% and 91.249% specificity of 74.485% and 70.018%; and accuracy of 84.341% and 79.611% respectively, for train review and movie review databases.

Sign in / Sign up

Export Citation Format

Share Document