Mapping the Sensory Fingerprint of Swedish Beer Market through Text and Data Mining and Multivariate Strategies

The continuous increase of online data with consumers’ and experts’ reviews and preferences is a potential tool for sensory characterization. The present work aims to overview the Swedish beer market and understand the sensory fingerprint of Swedish beers based on text data extracted from the Swedish alcohol retail monopoly (Systembolaget) website. Different multivariate strategies such as heatmaps, correspondence analysis and hierarchical cluster analysis were used to understand the sensory space of the different beer styles. Additionally, sensory space for specific hop cultivars was also investigated. Results highlighted Gothenburg as the main producing area in Sweden. The style Indian Pale Ale (IPA) is the largest available at the retail monopoly. From a sensory perspective, commonalities and differences were found between beer types and styles. Based on the aroma description, different types of ale and lager can cluster together (such as Porter and Stout and Dark lagers). Additionally, an associative relationship between specific aromas and hop cultivars from text data information was successfully achieved.

Download Full-text

Chemometric Expertise Of Clinical Monitoring Data Of Prolactinoma Patients

Open Chemistry ◽

10.1515/chem-2019-0050 ◽

2019 ◽

Vol 17 (1) ◽

pp. 408-412

Author(s):

Miroslava Nedyalkova ◽

Dimitar Dimitrov ◽

Borjana Donkova ◽

Vasil Simeonov

Keyword(s):

Data Mining ◽

Cluster Analysis ◽

Data Analysis ◽

Health Status ◽

Hierarchical Cluster ◽

Health Status Indicators ◽

Clinical Parameters ◽

Intelligent Data Analysis ◽

Major Goal ◽

Monitoring Procedure

AbstractThe present investigation indicates hidden relationships between the several clinical parameters usually monitored on prolactinoma patients using non-hierarchical cluster analysis. The major goal of the chemometric data mining is to offer a possible mode of optimization of the monitoring procedure by selecting a reduced number of health status indicators. The intelligent data analysis reveals the formation of three patterns of prolactinoma patients each one of them described by a set of clinical parameters. Thus, better strategies for considering patients with this diagnosis could be developed and clinically applied.

Download Full-text

A Clustering Analysis Method for Massive Music Data

Modern Electronic Technology ◽

10.26549/met.v5i1.6763 ◽

2021 ◽

Vol 5 (1) ◽

pp. 24

Author(s):

Yanping Xu ◽

Sen Xu

Keyword(s):

Data Mining ◽

Cluster Analysis ◽

Pattern Recognition ◽

Fourier Transform ◽

Clustering Analysis ◽

Clustering Algorithm ◽

Analysis Method ◽

Audio File ◽

Beat Period ◽

Different Types

Clustering analysis plays a very important role in the field of data mining, image segmentation and pattern recognition. The method of cluster analysis is introduced to analyze NetEYun music data. In addition, different types of music data are clustered to find the commonness among the same kind of music. A music data-oriented clustering analysis method is proposed: Firstly, the audio beat period is calculated by reading the audio file data, and the emotional features of the audio are extracted; Secondly, the audio beat period is calculated by Fourier transform. Finally, a clustering algorithm is designed to obtain the clustering results of music data.

Download Full-text

Novel anti-tuberculosis drug designs by data mining for similarity in substituent substitution and structure modification

Drugs and Therapy Studies ◽

10.4081/dts.2011.e15 ◽

2011 ◽

Vol 1 (1) ◽

pp. 15 ◽

Cited By ~ 1

Author(s):

Ronald Lee Bartzatt

Keyword(s):

Data Mining ◽

Molecular Weight ◽

Cluster Analysis ◽

Discriminant Analysis ◽

Surface Area ◽

Hierarchical Cluster Analysis ◽

Hierarchical Cluster ◽

Log P ◽

Polar Surface Area ◽

Pharmaceutical Properties

<em>Mycobacterium tuberculosis</em> (TB) is among the most common of infectious diseases that cause death, and as many as one-third of the world’s population may be infected. This work presents 17 novel hydrazide agents formed by focused in silico data mining utilizing search parameters restricted to substituent replacement only. Substituent substitution has been highly successful in design of novel antibacterial and antiviral drugs. This diverse set of hydrazide constructs possess molecular properties indicating favorable bioavailability with excellent intestinal absorption for oral administration. All agents have zero violations of the Rule of 5, indicating favorable druglikeness. Important pharmaceutical properties including polar surface area, Log P, and formula weight were determined and compared to that of the parent structure of isoniazid by hierarchical cluster analysis and discriminant analysis. The average Log P with range is -0.258 and -2.165 to 1.373, respectively. The average polar surface area (PSA) with range is 75.19 A2 and 55.121 A2 to 94.036 A2, respectively. The diverse range of PSA and Log P, with other descriptors, portend a versatile group of hydrazide drugs having substantial potential to expand the application and effectiveness for clinical treatment of multi-organ infected TB patients. Analysis of similarity indicated that all 17 agents are significantly similar to isoniazid, however discriminant analysis and hierarchical cluster analysis are able to differentiate isoniazid based upon molecular properties. Molecular weight and number of atoms were highly correlated by Pearson r (r > 0.9000), with Log P moderately correlated (r > 0.5500) to number of atoms, molecular weight, and volume. Seventeen hydrazide compounds (success rate of approximately 38%) having diverse pharmaceutical properties resulted from substituent data mining with potential for clinical application.

Download Full-text

Aid of End-Milling Condition Decision Using Data Mining from Tool Catalog Data for Rough Processing

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.325.345 ◽

2011 ◽

Vol 325 ◽

pp. 345-350

Author(s):

Hiroyuki Kodama ◽

Toshiki Hirogaki ◽

Eiichi Aoyama ◽

Keiji Ogawa

Keyword(s):

Data Mining ◽

Cluster Analysis ◽

End Milling ◽

Hierarchical Cluster ◽

Cutting Conditions ◽

New Knowledge ◽

End Mills ◽

Milling Condition ◽

Mining Methods ◽

Using Data

The uses of data mining methods to support workers decide on reasonable cutting conditions has been investigated in this work. The aim of our research is to find new knowledge by applying data mining techniques to a tool catalog. Hierarchical and non-hierarchical clustering of catalog data as well as multiple regression analysis was used. The K-means method was used and on the shape presented in the catalog data and grouped end mills from the viewpoint of the tool's shape, which here means the ratio of dimensions has been focused. The numbers of variables were decreased using hierarchical cluster analysis. In addition, an expression for calculating the better cutting conditions was found and the calculated values were compared with the catalog values. There were three cutting conditions: conditions recommended in the catalog, conditions derived by data mining, and proven cutting conditions for die machining (rough processing).

Download Full-text

Cutting Condition Decision Methodology Based on Data-Mining of Tool Catalog Data

ASME 2010 International Manufacturing Science and Engineering Conference, Volume 2 ◽

10.1115/msec2010-34199 ◽

2010 ◽

Author(s):

Hiroyuki Kodama ◽

Toshiki Hirogaki ◽

Eiichi Aoyama ◽

Keiji Ogawa

Keyword(s):

Data Mining ◽

Cluster Analysis ◽

Regression Analysis ◽

Hierarchical Cluster ◽

Cutting Conditions ◽

Cutting Condition ◽

New Knowledge ◽

Tool Shape ◽

End Mills ◽

Mining Methods

Data-mining methods were used to support decisions about reasonable cutting conditions. The aim of our research was to extract new knowledge by applying data-mining techniques to a tool catalog. We used both hierarchical and non-hierarchical clustering of catalog data and also used applied multiple regression analysis. We focused on the shape element of catalog data and we visually grouped end mills from the viewpoint of tool shape, which here meant the ratio of dimensions, by using the k-means method. We then decreased the number of variables by using hierarchical cluster analysis. We also found an expression for calculating the best cutting conditions, and we compared the calculated values with the catalog values. We did 15 minutes of cutting work using three kinds of cutting conditions: conditions recommended in the catalog, conditions derived by data-mining, and proven cutting conditions for die machining (rough processing).

Download Full-text

Research on Classification of Primary Liver Cancer Syndrome Based on Data Mining Technology

Journal of Healthcare Engineering ◽

10.1155/2022/2629509 ◽

2022 ◽

Vol 2022 ◽

pp. 1-14

Author(s):

Jiwei Fang ◽

Jianfeng Li

Keyword(s):

Data Mining ◽

Cluster Analysis ◽

Liver Cancer ◽

Primary Liver Cancer ◽

Hierarchical Cluster ◽

Cancer Syndrome ◽

Mining Technology ◽

Computer Data ◽

Cancer Syndromes

This study is based on the analysis of the status quo of the research on liver cancer syndromes, starting with the clinical objective and true four-diagnosis information of TCM inpatients with primary liver cancer, using computer data mining technology to analyze and summarize the syndrome rules from the bottom to the top. Let the data itself show the essence of liver cancer syndrome. First, with the help of hierarchical cluster analysis, we can understand the general characteristics through the rough preliminary classification of the four-diagnosis information of liver cancer patients. Then, with the help of the emerging and mature hidden structure model analysis in recent years, through data modeling, the classification of common syndromes of liver cancer and the corresponding relationship with the four-diagnosis information are comprehensively analyzed. Finally, considering the inherent shortcomings of implicit structure and hierarchical clustering based on the assumption that there is a unique one-to-one correspondence between the four diagnostic information factors and the class (or hidden class) when classifying, we plan to use factor analysis and joint cluster analysis, as supplementary means to further explore the classification of liver cancer syndromes and the corresponding relationship with the four-diagnosis information.

Download Full-text

Precipitation regionalization of southwest monsoon by hierarchical cluster analysis

MAUSAM ◽

10.54302/mausam.v60i2.1069 ◽

2021 ◽

Vol 60 (2) ◽

pp. 185-196

Author(s):

A. B. MAZUMDAR

Keyword(s):

Cluster Analysis ◽

Hierarchical Cluster Analysis ◽

Monsoon Rainfall ◽

Principal Component ◽

Hierarchical Cluster ◽

Southwest Monsoon ◽

Different Types ◽

Synoptic Features ◽

Southwest Monsoon Rainfall ◽

Homogeneous Regions

An attempt has been made to identify coherent zones of southwest monsoon rainfall over the Indian region by employing hierarchical cluster analysis. Examination of dendrograms produced by different fusion strategies revealed the presence of 13 nuclei clusters of meteorological subdivisions. Formation of these nuclei clusters could be interpreted by their average principal component (PC) scores and associated synoptic features of PCs. Higher level inter-nuclei joinings have occurred in various fusion strategies to produce different types of clusters of subdivisions. A flexible strategy providing well separated groups of meteorological sub-divisions has been found to be suitable. The method has identified six homogeneous regions of rainfall over India. The meteorological subdivisions have been found to be evenly distributed in these coherent zones. The clustering obtained by this method has been reasonable and largely interpretable.

Download Full-text

Transient Stability Multi Swing Step-out Prediction with Online Data Mining

IEEJ Transactions on Power and Energy ◽

10.1541/ieejpes.136.137 ◽

2016 ◽

Vol 136 (2) ◽

pp. 137-144 ◽

Cited By ~ 2

Author(s):

Takuya Omi ◽

Hiroto Kakisaka ◽

Shinichi Iwamoto

Keyword(s):

Data Mining ◽

Transient Stability ◽

Online Data

Download Full-text

DRSA: a non-hierarchical clustering algorithm using k-NN graph and its application in vegetation classification

Vegetation of Russia ◽

10.31111/vegrus/2015.27.125 ◽

2015 ◽

pp. 125-138 ◽

Cited By ~ 2

Author(s):

I. V. Goncharenko

Keyword(s):

Cluster Analysis ◽

Clustering Algorithm ◽

Nearest Neighbor ◽

Clustering Algorithms ◽

Protein Structures ◽

Hierarchical Cluster ◽

Vegetation Classification ◽

K Nearest Neighbor ◽

Neighbor Graph ◽

Nearest Neighbor Graph

In this article we proposed a new method of non-hierarchical cluster analysis using k-nearest-neighbor graph and discussed it with respect to vegetation classification. The method of k-nearest neighbor (k-NN) classiﬁcation was originally developed in 1951 (Fix, Hodges, 1951). Later a term “k-NN graph” and a few algorithms of k-NN clustering appeared (Cover, Hart, 1967; Brito et al., 1997). In biology k-NN is used in analysis of protein structures and genome sequences. Most of k-NN clustering algorithms build «excessive» graph firstly, so called hypergraph, and then truncate it to subgraphs, just partitioning and coarsening hypergraph. We developed other strategy, the “upward” clustering in forming (assembling consequentially) one cluster after the other. Until today graph-based cluster analysis has not been considered concerning classification of vegetation datasets.

Download Full-text