scholarly journals Automatic Slowness Vector Measurements of Seismic Arrivals with Uncertainty Estimates using Bootstrap Sampling, Array Methods and Unsupervised Learning

2020 ◽  
Author(s):  
James Ward ◽  
michael Thorne ◽  
Andy Nowacki ◽  
Sebastian Rost
Keyword(s):  
Unsupervised Learning ◽  
Bootstrap Sampling ◽  
Slowness Vector ◽  
Uncertainty Estimates

scholarly journals An artificial immune system with bootstrap sampling for the diagnosis of recurrent endometrial cancers

Open Medicine ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. 237-245
Author(s):  
Chih-Yen Chang ◽  
Yen-Chiao (Angel) Lu ◽  
Wen-Chien Ting ◽  
Tsu-Wang (David) Shen ◽  
Wen-Chen Peng
Keyword(s):  
Endometrial Cancer ◽  
Immune System ◽  
Unsupervised Learning ◽  
Artificial Immune System ◽  
Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Artificial Immune ◽  
Bootstrap Sampling ◽  
Recurrent Endometrial Cancer

Abstract Endometrial cancer is one of the most common gynecological malignancies in developed countries. The prevention of the recurrence of endometrial cancer has always been a clinical challenge. Endometrial cancer is asymptomatic in the early stage, and there remains a lack of time-series correlation patterns of clinical pathway transfer, recurrence, and treatment. In this study, the artificial immune system (AIS) combined with bootstrap sampling was compared with other machine learning techniques, which included both supervised and unsupervised learning categories. The back propagation neural network, support vector machine (SVM) with a radial basis function kernel, fuzzy c-means, and ant k-means were compared with the proposed method to verify the sensitivity and specificity of the datasets, and the important factors of recurrent endometrial cancer were predicted. In the unsupervised learning algorithms, the AIS algorithm had the highest accuracy (83.35%), sensitivity (77.35%), and specificity (92.31%); in supervised learning algorithms, the SVM algorithm had the highest accuracy (97.51%), sensitivity (95.02%), and specificity (99.29%). The results of our study showed that histology and chemotherapy are important factors affecting the prediction of recurrence. Finally, behavior code and radiotherapy for recurrent endometrial cancer are important factors for future adjuvant treatment.

Classification of Observations through Combination of the Dimension Reduction and the Cluster Analysis

2017 ◽  
Vol 7 (8) ◽  
pp. 30
Author(s):  
Hyeuk Kim
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Cluster Analysis ◽  
Unsupervised Learning ◽  
Principal Component ◽  
Component Analysis ◽  
Baseball Players ◽  
Partitioning Around Medoids ◽  
Different Characteristics

Unsupervised learning in machine learning divides data into several groups. The observations in the same group have similar characteristics and the observations in the different groups have the different characteristics. In the paper, we classify data by partitioning around medoids which have some advantages over the k-means clustering. We apply it to baseball players in Korea Baseball League. We also apply the principal component analysis to data and draw the graph using two components for axis. We interpret the meaning of the clustering graphically through the procedure. The combination of the partitioning around medoids and the principal component analysis can be used to any other data and the approach makes us to figure out the characteristics easily.

Exchange Spin Coupling from Gaussian Process Regression

2020 ◽  
Author(s):  
Marc Philipp Bahlke ◽  
Natnael Mogos ◽  
Jonny Proppe ◽  
Carmen Herrmann
Keyword(s):  
Machine Learning ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Molecular Magnets ◽  
Molecular Structures ◽  
Spin Coupling ◽  
Structure Property ◽  
Data Set ◽  
Uncertainty Estimates

Heisenberg exchange spin coupling between metal centers is essential for describing and understanding the electronic structure of many molecular catalysts, metalloenzymes, and molecular magnets for potential application in information technology. We explore the machine-learnability of exchange spin coupling, which has not been studied yet. We employ Gaussian process regression since it can potentially deal with small training sets (as likely associated with the rather complex molecular structures required for exploring spin coupling) and since it provides uncertainty estimates (“error bars”) along with predicted values. We compare a range of descriptors and kernels for 257 small dicopper complexes and find that a simple descriptor based on chemical intuition, consisting only of copper-bridge angles and copper-copper distances, clearly outperforms several more sophisticated descriptors when it comes to extrapolating towards larger experimentally relevant complexes. Exchange spin coupling is similarly easy to learn as the polarizability, while learning dipole moments is much harder. The strength of the sophisticated descriptors lies in their ability to linearize structure-property relationships, to the point that a simple linear ridge regression performs just as well as the kernel-based machine-learning model for our small dicopper data set. The superior extrapolation performance of the simple descriptor is unique to exchange spin coupling, reinforcing the crucial role of choosing a suitable descriptor, and highlighting the interesting question of the role of chemical intuition vs. systematic or automated selection of features for machine learning in chemistry and material science.

Klasifikasi pada Tempat Tinggal Menurut Provinsi dan Jenis Kepemilikan Berdasarkan Algoritma K-Means

2020 ◽  
Vol 4 (3) ◽  
pp. 247
Author(s):  
Dwi Swasono Rachmad
Keyword(s):  
Data Mining ◽  
Unsupervised Learning ◽  
Residential Buildings ◽  
Government Agency ◽  
Role Of Government ◽  
The Republic ◽  
Household Processing ◽  
Central Statistics

<p><em>H</em><em>ousing is derived from the word house</em><em> which means</em><em> a place that has a place to live which will stay or stop in a certain time. Housing is a residence that has been grouped into a place that has facilities and infrastructure. The problem in this study focuses on the type of residential ownership in the form of SHM ART, SHM Non ART, NON SHM and others. </em><em>T</em><em>hese four types</em><em> can be used</em><em> to know the percentage of ownership in all provinces in Indonesia. Due to the fact that there is still a lot of information about the type of certificate ownership, there is still not much ownership. Therefore, the use of the k-Means algorithm as a data mining concept in the form of clusters, where the data already has parameters or values that fall into the category of unsupervised learning. That data produced the best. The data was obtained from published sources of the Republic of Indonesia government agency, namely the Central Statistics Agency data with the category of household processing with self-owned residential buildings purchased from developers or non-developers by province and type of ownership in 2016 throughout Indonesia. In conducting the dataset, researchers used the RapidMiner application as a clustering process application. This research </em><em>shows that</em><em> there are more types of ownership in the SHM ART, but for other values it is still smaller than the value in other types of ownership which is the second largest value. So</em><em>,</em><em> in this case, the role of government in providing assistance in the process of ownership in order to become SHM ART</em><em> is very important</em><em>.</em></p>

Exploring power in response inhibition tasks using the bootstrap: The impact of number of participants, number of trials, effect magnitude, and study design

2019 ◽  
Author(s):  
Curtis David Von Gunten ◽  
Bruce D Bartholow
Keyword(s):  
Study Design ◽  
Effect Size ◽  
Statistical Power ◽  
Bootstrap Sampling ◽  
Reliable Measure ◽  
Internal Reliability ◽  
The Impact ◽  
Power Analyses ◽  
Effect Magnitude

A primary psychometric concern with laboratory-based inhibition tasks has been their reliability. However, a reliable measure may not be necessary or sufficient for reliably detecting effects (statistical power). The current study used a bootstrap sampling approach to systematically examine how the number of participants, the number of trials, the magnitude of an effect, and study design (between- vs. within-subject) jointly contribute to power in five commonly used inhibition tasks. The results demonstrate the shortcomings of relying solely on measurement reliability when determining the number of trials to use in an inhibition task: high internal reliability can be accompanied with low power and low reliability can be accompanied with high power. For instance, adding additional trials once sufficient reliability has been reached can result in large gains in power. The dissociation between reliability and power was particularly apparent in between-subject designs where the number of participants contributed greatly to power but little to reliability, and where the number of trials contributed greatly to reliability but only modestly (depending on the task) to power. For between-subject designs, the probability of detecting small-to-medium-sized effects with 150 participants (total) was generally less than 55%. However, effect size was positively associated with number of trials. Thus, researchers have some control over effect size and this needs to be considered when conducting power analyses using analytic methods that take such effect sizes as an argument. Results are discussed in the context of recent claims regarding the role of inhibition tasks in experimental and individual difference designs.

Sign in / Sign up

Export Citation Format

Share Document