scholarly journals Functional Diagnostic System for Multichannel Mine Lifting Machine Working in Factor Cluster Analysis Mode

2020 ◽  
Vol 7 (1) ◽  
pp. E20-E27
Author(s):  
V. I. Zimovets ◽  
S. V. Shamatrin ◽  
D. E. Olada ◽  
N. I. Kalashnykova
Keyword(s):  
Machine Learning ◽  
Cluster Analysis ◽  
Initial Conditions ◽  
Essential Feature ◽  
Operating Mode ◽  
Diagnostic Features ◽  
Information Synthesis ◽  
Additional Training ◽  
Learning Factor ◽  
Intelligent Technology

The primary direction of the increase of reliability of the automated control systems of complex electromechanical machines is the application of intelligent information technologies of the analysis of diagnostic information directly in the operating mode. Therefore, the creation of the basics of information synthesis of a functional diagnosis system (FDS) based on machine learning and pattern recognition is a topical task. In this case, the synthesized FDS must be adaptive to arbitrary initial conditions of the technological process and practically invariant to the multidimensionality of the space of diagnostic features, an alphabet of recognition classes, which characterize the possible technical states of the units and devices of the machine. Besides, an essential feature of FDS is the ability to retrain by increasing the power of the alphabet recognition classes. In the article, information synthesis of FDS is performed within the framework of information-extreme intellectual data analysis technology, which is based on maximizing the information capacity of the system in the process of machine learning. The idea of factor cluster analysis was realized by forming an additional training matrix of unclassified vectors of features of a new recognition class obtained during the operation of the FDS directly in the operating mode. The proposed algorithm allows performing factor cluster analysis in the case of structured feature vectors of several recognition classes. In this case, additional training matrices of the corresponding recognition classes are formed by the agglomerative method of cluster analysis using the k-means procedure. The proposed method of factor cluster analysis is implemented on the example of information synthesis of the FDS of a multi-core mine lifting machine. Keywords: information-extreme intelligent technology, a system of functional diagnostics, multichannel mine lifting machine, machine learning, factor cluster analysis.

scholarly journals ІНФОРМАЦІЙНО-ЕКСТРЕМАЛЬНИЙ КЛАСТЕР-АНАЛІЗ ВХІДНИХ ДАНИХ ПРИ ФУНКЦІОНАЛЬНОМУ ДІАГНОСТУВАННІ

2019 ◽  
pp. 105-115
Author(s):  
Вікторія Ігорівна Зимовець ◽  
Олександр Сергійович Приходченко ◽  
Микита Ігорович Мироненко
Keyword(s):  
Machine Learning ◽  
Cluster Analysis ◽  
Diagnostic System ◽  
Analysis Model ◽  
Functional Diagnostics ◽  
Diagnostic Features ◽  
Information Synthesis ◽  
Diagnostic Signs ◽  
Diagnostics System ◽  
Functional Diagnostic

The study aims to increase the functional efficiency of machine learning of the functional diagnosis system of a multi-rope shaft hoist through cluster analysis of diagnostic features. To achieve the goal, it was necessary to solve the following tasks: formalize the formulation of the task of information synthesis, capable of learning a functional diagnosis system, which operates in the cluster-analysis mode of diagnostic signs; to propose a categorical model and, on its basis, to develop an algorithm for information-extreme cluster analysis of diagnostic signs in the process of information-extreme machine learning of a functional diagnostic system; carry out fuzzification of input fuzzy data by optimizing the geometric parameters of hyperspherical containers of recognition classes that characterize the possible technical conditions of the diagnostic object; to develop an algorithm and implement it on the example of information synthesis of the functional diagnostics system of a multi-rope mine hoisting machine. The object of the study is the processes of information synthesis of a functional diagnostic system capable of learning, integrated into the automated control system of a multi-rope mine hoisting machine. The subject of the study is categorical models, an information-extremal machine learning algorithm of a functional diagnostic system that operates in the cluster analysis model of diagnostic signs and constructs decision rules. The research methods are based on the ideas and methods of information-extreme intellectual data analysis technology, a theoretical-informational approach to assessing the functional effectiveness of machine learning and on the geometric approach of pattern recognition theory. As a result, the following results were obtained: a categorical model was proposed, and on its basis, an algorithm for information-extremal machine learning of the functional diagnostics system for a multi-rope mine hoist was developed and implemented, which allows you to automatically generate an input classified fuzzy training matrix, which significantly reduces time and material costs when creating incoming mathematical description. The obtained result was achieved by cluster analysis of structured vectors of diagnostic signs obtained from archival data for three recognition classes using the k-means procedure. As a criterion for optimizing machine learning parameters, we considered a modified Kullback measure in the form of a functional on the exact characteristics of diagnostic solutions and distance criteria for the proximity of recognition classes. Based on the optimal geometric parameters of the containers of recognition classes obtained during machine learning, decisive rules were constructed that allowed us to classify the vectors of diagnostic features of recognition classes with a rather high total probability of making the correct diagnostic decisions. Conclusions. The scientific novelty of the results obtained consists in the development of a new method for the information synthesis of the functional diagnostics system of a multi-rope mine hoisting machine, which operates in the cluster analysis model, which made it possible to automatically form an input classified fuzzy training matrix with its subsequent dephasification in the process of information-extreme machine learning system.

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.

Phenomapping Heart Failure with Preserved Ejection Fraction Using Machine Learning Cluster Analysis

2021 ◽  
Vol 17 (3) ◽  
pp. 499-518
Author(s):  
Elena Galli ◽  
Corentin Bourg ◽  
Wojciech Kosmala ◽  
Emmanuel Oger ◽  
Erwan Donal
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Cluster Analysis ◽  
Ejection Fraction ◽  
Preserved Ejection Fraction

scholarly journals Phenotyping Women Based on Dietary Macronutrients, Physical Activity, and Body Weight Using Machine Learning Tools

Nutrients ◽  
2019 ◽  
Vol 11 (7) ◽  
pp. 1681 ◽  
Author(s):  
Ramyaa Ramyaa ◽  
Omid Hosseini ◽  
Giri P. Krishnan ◽  
Sridevi Krishnan
Keyword(s):  
Physical Activity ◽  
Machine Learning ◽  
Cluster Analysis ◽  
Body Weight ◽  
Energy Balance ◽  
Numerical Data ◽  
Support Vector ◽  
Learning Tools ◽  
K Nearest Neighbor ◽  
Numerical Predictions

Nutritional phenotyping can help achieve personalized nutrition, and machine learning tools may offer novel means to achieve phenotyping. The primary aim of this study was to use energy balance components, namely input (dietary energy intake and macronutrient composition) and output (physical activity) to predict energy stores (body weight) as a way to evaluate their ability to identify potential phenotypes based on these parameters. From the Women’s Health Initiative Observational Study (WHI OS), carbohydrates, proteins, fats, fibers, sugars, and physical activity variables, namely energy expended from mild, moderate, and vigorous intensity activity, were used to predict current body weight (both as body weight in kilograms and as a body mass index (BMI) category). Several machine learning tools were used for this prediction. Finally, cluster analysis was used to identify putative phenotypes. For the numerical predictions, the support vector machine (SVM), neural network, and k-nearest neighbor (kNN) algorithms performed modestly, with mean approximate errors (MAEs) of 6.70 kg, 6.98 kg, and 6.90 kg, respectively. For categorical prediction, SVM performed the best (54.5% accuracy), followed closely by the bagged tree ensemble and kNN algorithms. K-means cluster analysis improved prediction using numerical data, identified 10 clusters suggestive of phenotypes, with a minimum MAE of ~1.1 kg. A classifier was used to phenotype subjects into the identified clusters, with MAEs <5 kg for 15% of the test set (n = ~2000). This study highlights the challenges, limitations, and successes in using machine learning tools on self-reported data to identify determinants of energy balance.

Psammophyte vegetation of the Bargusin depression (Republic of Buryatia)

2021 ◽  
pp. 137-155
Author(s):  
N. A. Dulepova ◽  
A. Yu. Korolyuk
Keyword(s):  
Cluster Analysis ◽  
Internal Field ◽  
Diagnostic Features ◽  
Aeolian Processes ◽  
North West ◽  
Diagnostic Species ◽  
South West ◽  
The Republic ◽  
The Village ◽  
Psammophytic Vegetation

Modern aeolian landscapes occupy large territories in Transbaikalia. The Barguzin depression bottom is an area with sandy lands (Ivanov, 1960). This depression is one of the largest around the Lake Baikal (Florensov et al., 1965). Its internal field are accumulative surfaces, formed by Pleistocene sands, so-called “kujtuns” (Forest, Suvinsky, Lower, and Upper), are located as stripes of variable width, replacing each other from the north-west to the south-east (Fig. 2 A-D). Aeolian processes are most dynamic on weakly sod and bare sands: in the lower part of the Argada river, in the basins of Ina, Ulan-Burga, Zhargalanty rivers, and in the marginal parts of the steppe “kuytuns” (Fig. 3, 4). The results of aeolian processes are dunes and ridge-basin relief. This publication continues the series of papers (Dulepova, Korolyuk, 2013, 2015; Dulepova, 2016) on psammophytic vegetation of Baikal Siberia (Irkutsk region, the Republic of Buryatia, and the Trans-Baikal region). The paper is based on the analysis of 116 geobotanical relevés obtained in the course of the field studies in 2009–2014 in the Barguzinsky and Kurumkansky districts of the Republic of Buryatia. Four relevés are taken from the literature (Shchipek et al., 2002). Three diagnostic species of the class Brometea korotkiji Hilbig et Koroljuk 2000 (Bromopsis korotkiji, Corispermum sibiricum, Carex sabulosa) occur on the studied sandy lands. Among species of the order Oxytropidetalia lanatae Brzeg et Wika 2001 (Brzeg, Wika, 2001) such species as Artemisia ledebouriana, Chamaerhodos grandiflora, Oxytropis lanata have high constancy and often dominate in communities. When comparing new syntaxa with the previously described alliances (Oxytropidion lanatae Hilbig et Koroljuk 2000, Aconogonion chlorochryseum Dulepova et Korolyuk 2013 and Festucion dahuricae Dulepova et Korolyuk 2015) it was found that they are closer to the alliance Festucion dahuricae. However, Artemisia xanthochroa, Caragana buriatica, Festuca dahurica, Thymus baicalensis, and Ulmus pumila, commom in the Selenga river middle mountains, are absent in the study area (Korolyuk, 2017). The psammophytic fraction of the flora of the study area is not very peculiar. Only two endemic species (Oxytropis bargusinensis and Aconogonon bargusinense) are recorded on the sands of the Barguzin depression. 5 associations, 3 subassociations and 3 communities of the class Brometea korotkiji and 1 association of the class Cleistogenetea squarrosae Mirk. et al. ex Korotkov et al. 1991 (Table 1) are established as new. Association Bromopsietum korotkiji ass. nov. hoc loco (Table 2, rel. 6–17). Nomenclature type (holotypus hoc loco): Table 2, relevé 6 (field number — nd10-200), Republic of Buryatia, Kurumkansky district, 2 km southwest of the village of Kharamodun, the convex peak of dune), 54.18734° N, 110.48333° E., altitude 473 m a.s.l., 31/07/2010, author — N. A. Dulepova (Fig. 5). Diagnostic species: Bromopsis korotkiji (dom.). Association Aconogonetum bargusinensis ass. nov. hoc loco (Table 2, rel. 18–25). Nomenclature type (holotypus hoc loco): Table 2, relevé 18 (field number — 10-591), Republic of Buryatia, Barguzinsky district, 7 km south of the village Urzhil, an elevated sandy terrace of the Ulan-Burga river, 53.87645° N, 110.32410° E, altitude 628 m a.s.l., 28/07/2010, ­author — A. Yu. Korolyuk. (Fig. 6, 7). Diagnostic species: Aconogonon bargusinense (dom.) Association Oxytropido lanatae–Caricetum sabulosae ass. nov. hoc loco (Table 2, rel. 26–37). Nomenclature type (holotypus hoc loco): Table 2, relevé 26 (field number — nd10-339), Republic of Buryatia, Kurumkansky district, 8.3 km southwest of the village of Kharamodun, an elevated sandy terrace of the Argada river, 54.12156° N, 110.45382 E, altitude 514 m a.s.l., 17/08/2010, author — N. A. Dulepova. Diagnostic species: Carex sabulosa (dom.) Association Oxytropido lanatae–Bromopsietum korotkiji ass. nov. hoc loco (Table 3, rel. 1–30). Nomenclature type (holotype hoc loco): Table 3, relevé 1 (field number — nd09-040), Republic of Buryatia, Kurumkansky district, side of the river valley Argada in 4–5 km south-west from village Argada, the lower part of the high sandy terrace, 54.20118° N, 110.64804° E, altitude 537 m a.s.l., 05/07/2009, author — N. A. Dulepova. Diagnosed by species of class and order. Subassociation B.k.–O.l. typicum subass. nov. hoc loco (Table 3, rel. 1–8. Nomenclature type (holotypus hoc loco): Table 3, relevé 1. Diagnostic features are those of association. Subassociation B.k.–O.l. chamaerhodetosum grandiflorae subass. nov. hoc loco (Table 3, rel. 9–19). Nomenclature type (holotypus hoc loco): Table 3, relevé 9 (field number — 09-176), Republic of Buryatia, Kurumkansky district, side of the valley of the Argada river 4–5 km southwest of the village Argada, upper convex part of high sandy terrace, 54.20235° N, 110.64528° E, altitude 570 m a.s.l., 05/07/2009, author — A.Yu. Korolyuk. Diagnostic species: Chamaerhodos grandiflora (dom.). Subassociation B.k.–O.l. artemisietosum ledebourianae subass. nov. hoc loco (Table 3, rel. 20–30). Nomenclature type (holotypus hoc loco): Table 3, relevé 20 (field number — nd10-325), Republic of Buryatia, Kurumkansky district, 8.3 km south-west of the village of Kharamodun, the upper third of the high sandy terrace of the Argada river, 54.12157° N, 110.48679° E, altitude 557 m a.s.l., 17/08/2010, ­author — N. A. Dulepova. Diagnostic species: Artemisia ledebouriana (dom.), Orobanche coerulescens, Stellaria dichotoma, Vincetoxicum sibiricum. Association Artemisio frigido–Oxytropidetum bargusinensis ass. nov. hoc loco (Table 3, rel. 41–46). Nomenclature type (holotypus hoc loco): Table 3, relevé 41 (field number — 10-566), Republic of Buryatia, Barguzinsky district, 4 km north-west of Bodon village, Suvinsky kujtun, flat elongated blowing trough, 53.71945° N, 110.04983° E, altitude 566 m a.s.l., 27/07/2010, author — A. Yu. Korolyuk. Diagnostic species: Bupleurum bicaule, Iris humilis, Youngia tenuifolia, Oxytropis bargusinensis. According to cluster analysis (Fig. 9) of data from Baikal Siberia, Mongolia, Tuva, and Inner Mongolia (China) the diversity of psammophytic vegetation is mainly determined by the sand land geography, which is reflected at the alliance, order, and class levels. The dynamics of overgrowth of sands is well traced at the association, subassociation, and community levels. Cluster analysis confirmed the attribution of most of the described syntaxa from the Barguzin and Selenga basins in the alliance Festucion dahuricae.

scholarly journals Reducing Energy Waste through Eco-Aware Everyday Things

2014 ◽  
Vol 10 (1) ◽  
pp. 79-103 ◽  
Author(s):  
Juan López-de-Armentia ◽  
Diego Casado-Mansilla ◽  
Sergio López-Pérez ◽  
Diego López-de-Ipiña
Keyword(s):  
Machine Learning ◽  
Research Laboratory ◽  
Operating Mode ◽  
Public Spaces ◽  
Learning Approaches ◽  
Usage Pattern ◽  
Electrical Devices ◽  
Wasted Energy ◽  
Reducing Energy ◽  
Coffee Machine

Society wastes much more energy than it should. This produces tons of unnecessary CO2emissions. This is partly due to the inadequate use of electrical devices given the intangible and invisible nature of energy. This misuse of devices and energy unawareness is particularly relevant in public spaces (offices, schools, hospitals and so on), where people use electrical appliances, but they do not directly pay the invoice to energy providers. Embedding intelligence within public, shared appliances, transforming them into Eco-aware things, is valuable to reduce a proportion of the unnecessarily consumed energy. To this end, we present a twofold approach for better energy efficiency in public spaces: (1) informing persuasively to concerned users about the misuse of electronic appliances; (2) Customizing the operating mode of this everyday electrical appliances as a function of their real usage pattern. To back this approach, a capsule-based coffee machine placed in a research laboratory has been augmented. This device is able to continuously collect its usage pattern to offer feedback to coffee consumers about the energy wasting and also, to intelligently adapt its operation to reduce wasted energy. To this aim, several machine learning approaches are compared and evaluated to forecast the next-day device usage.

scholarly journals Overview of Smart Aquaculture System: Focusing on Applications of Machine Learning and Computer Vision

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2882
Author(s):  
Thi Thu Em Vo ◽  
Hyeyoung Ko ◽  
Jun-Ho Huh ◽  
Yonghoon Kim
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Sustainable Development ◽  
Species Classification ◽  
The Sustainable Development ◽  
Aquaculture System ◽  
Aquaculture Industry ◽  
Intelligent Technology ◽  
Applications Of Machine Learning ◽  
Aquaculture Production

Smart aquaculture is nowadays one of the sustainable development trends for the aquaculture industry in intelligence and automation. Modern intelligent technologies have brought huge benefits to many fields including aquaculture to reduce labor, enhance aquaculture production, and be friendly to the environment. Machine learning is a subdivision of artificial intelligence (AI) by using trained algorithm models to recognize and learn traits from the data it watches. To date, there are several studies about applications of machine learning for smart aquaculture including measuring size, weight, grading, disease detection, and species classification. This review provides and overview of the development of smart aquaculture and intelligent technology. We summarized and collected 100 articles about machine learning in smart aquaculture from nearly 10 years about the methodology, results as well as the recent technology that should be used for development of smart aquaculture. We hope that this review will give readers interested in this field useful information.

scholarly journals Combining Regression and Clustering for Financial Analysis

2020 ◽  
Vol 2 (1) ◽  
pp. 109-118
Author(s):  
Andreea Ioana Chiriac
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cluster Analysis ◽  
Business Processes ◽  
Financial Analysis ◽  
Two Dimensions ◽  
Machine Learning Algorithms ◽  
Financial Ratio ◽  
Research Perspective ◽  
Systems Learning

Abstract Artificial Intelligence is used in business through machine learning algorithms. Machine learning is a part of computer science focused on computer systems learning to perform a specific task without using explicit instructions, relying on patterns and inference instead. Though it might seem like we’ve come a long way in the last ten years, which is true from a research perspective, the adoption of AI among corporations is still relatively low. Over time it became possible to automate more tasks and business processes than ever before. The benefit of using artificial intelligence is that does not require to program every step of the process, predicting at each step what could happen and how to resolve it. The algorithms decide for themselves in each case how the problems should be solved, based on the data that is used. I apply Python language to create a synthetic feature vector that allows visualizations in two dimensions for EDIBTA financial ratio. I use Mean-Square Error in order to evaluate the success, having the optimal parameters. In this section, I also mentioned about the purpose, goals, and applications of cluster analysis. I indicated about the basics of cluster analysis and how to do it and also did a demonstration on how to use K-Means.

Machine Learning for Chaotic Rayleigh Transitions

2021 ◽  
Author(s):  
Ben Tribelhorn ◽  
H. E. Dillon
Keyword(s):  
Machine Learning ◽  
Cluster Analysis ◽  
Natural Convection ◽  
Prandtl Number ◽  
Learning System ◽  
Lorenz Equations ◽  
Time Step ◽  
Learning Methods ◽  
Unsupervised Machine Learning ◽  
Machine Learning Methods

Abstract This paper is a preliminary report on work done to explore the use of unsupervised machine learning methods to predict the onset of turbulent transitions in natural convection systems. The Lorenz system was chosen to test the machine learning methods due to the relative simplicity of the dynamic system. We developed a robust numerical solution to the Lorenz equations using a fourth order Runge-Kutta method with a time step of 0.001 seconds. We solved the Lorenz equations for a large range of Raleigh ratios from 1–1000 while keeping the geometry and Prandtl number constant. We calculated the spectral density, various descriptive statistics, and a cluster analysis using unsupervised machine learning. We examined the performance of the machine learning system for different Raleigh ratio ranges. We found that the automated cluster analysis aligns well with well known key transition regions of the convection system. We determined that considering smaller ranges of Raleigh ratios may improve the performance of the machine learning tools. We also identified possible additional behaviors not shown in z-axis bifurcation plots. This unsupervised learning approach can be leveraged on other systems where numerical analysis is computationally intractable or more difficult. The results are interesting and provide a foundation for expanding the study for Prandtl number and geometry variations. Future work will focus on applying the methods to more complex natural convection systems, including the development of new methods for Nusselt correlations.

Sign in / Sign up

Export Citation Format

Share Document