Average Linkage Research Articles

Impact of Dataset Scaling on Hierarchical Clustering: A Comparative Analysis of Distance-Based and Ratio-Based Methods

In this study, the distance-based agglomerative hierarchical clustering techniques were compared to a ratio-based approach. Two real datasets, which were also used in a prior study by Roux (2018), were considered. Firstly, it was observed that the type of scaling applied to the datasets was found to affect the results of hierarchical clustering. Thus, various scaling methods were employed prior to implementing hierarchical clustering. Furthermore, two rank-based goodness-of-fit measures were used to evaluate the hierarchical clustering methods. In contrast to Roux (2018) findings, it was observed that the distance-based methods, such as Median linkage, Average linkage, and centroid linkage, performed better than the ratio-based method. The ratio-based methods also showed issues with branch crossing in the hierarchical clustering dendrogram. Consequently, this study illustrates that, with appropriate dataset scaling, the distance-based methods outperform ratio-based methods in terms of goodness-of-fit measures.

Sparrow search mechanism-based effective feature mining algorithm for the broken wire signal detection of prestressed concrete cylinder pipe

To enhance the capability of distributed optical fiber (DOF) monitoring system on real-time broken wire signal detection of prestressed concrete cylinder pipe (PCCP), this research proposes a novel effective parameter mining algorithm by utilizing wrapper theory and sparrow search algorithm (SSA). First, the improvement approach of SSA is investigated by applying the adaptive adjustment strategy, the Gaussian mutation perturbation, and the Tent chaotic perturbation. The subset search method is constructed based on the improved SSA (ISSA). Second, the similarity degrees of vibration signals are characterized by the Euclidean distance and the average linkage distance. On this basis, the subset evaluation criterion is established according to the classification accuracy of hierarchical clustering (HC). Finally, the prototype experiment is conducted in which the phase-sensitive optical time-domain reflectometry (Φ-OTDR) monitoring system is employed to collect vibration signals. Then, the effectiveness and the performance of the developed methodology are validated. The following results are drawn. (1) Benchmark function tests indicate that the convergence performance, the optimization ability, and the operation stability of ISSA are superior to those of SSA and the improved particle swarm optimization (IPSO). (2) The original set that has 122 feature parameters is established, and ISSA-HC, IPSO-HC, and SSA-HC extract 24, 31, and 55 effective parameters, respectively. (3) The recognition accuracies of the 3 parameter subsets are 95.83%, 84.17%, and 80.83%, respectively. The parameter subset mined by ISSA-HC has the best pattern recognition ability. This research provides technical support for the broken wire monitoring of in-service PCCP engineering. Meanwhile, it offers a foundation for further developing suitable pattern recognition algorithms to identify PCCP broken wire signals.

Pengelompokan Provinsi di Indonesia Menggunakan Time Series Clustering pada Sektor Ekspor Nonmigas

Indonesia's export activities are dominated by non-oil and gas exports consisting of four sectors, namely the processing industry, agriculture, mining, and others. The government must pay attention to non-oil and gas exports for each province because exports can play an essential role in a country's economic growth. This study was conducted to cluster provinces in Indonesia using time series clustering in the non-oil and gas export sector based on data patterns concerning Dynamic Time Warping (DTW) distance. The sectors used in this study are the manufacturing industry sector and the agricultural sector in 34 Indonesian provinces in the period 2017 - 2021. Time series clustering analysis uses the average linkage method with DTW distance and the selection of the optimum number of clusters using the silhouette coefficient method. The results of the analysis in the processing industry sector resulted in 3 optimum clusters, namely cluster 1 consisting of 1 province that has high processing industry exports, cluster 2 consisting of 8 provinces that have medium processing industry exports, and cluster 3 consisting of 25 provinces that have low processing industry exports. As for the agricultural sector, it produces 2 optimum clusters, namely cluster 1 consisting of 5 provinces that have high agricultural industry exports, and cluster 2 consisting of 29 provinces that have low agricultural industry exports. The clustering results in the processing industry sector and the agricultural sectors have a silhouette coefficient value of 0.778 and 0.798, so it is said to have a strong cluster structure.

KARAKTERISASI BENIH DAN KEKERABATAN KULTIVAR PADI LOKAL PASANG SURUT DI KABUPATEN INDRAGIRI HILIR

Similarity analysis was carried out on the characteristics of local type tidal rice grain in Indragiri Hilit Regency in January-October 2015 in Indragiri Hilir Regency. This research aims to inventory, characterize and determine the relationship between each type of local tidal rice grain in Indragiri Hilir Regency. This research uses a qualitative-quantitative description method. The beginning of this research was to explore the types of rice grains in each village and sub-district of Indfagiri Hilir Regency, then they were characterized and analyzed using the agglomerative method by calculating the distance between relatives using hierarchical cluster average linkage (between gropus). The research results show that Indragiri Hilir Regency has 27 local tidal rice cultivars. These cultivars consist of 'Karya Kuning', 'Karanduku', 'Ramos', 'Pulut Putih', 'Pandan Wangi', 'Ordinary', 'Lembu Sawah Merah', 'Karya Merah', 'Pulut Hitam', ' Pariaman', 'Lembu Sawah', 'Karya Tinggi', 'Panama', 'Batang Tuaka', 'Ir Super', 'Batang Piaman', 'Maron', 'Merah Putih', 'Serang', 'Putri Malu', 'Super', 'Opium', 'White', 'Kuatik', 'Frog', 'Lentik Bamban', 'Sere'. Morphological characters that differentiate rice cultivars are grain characteristics (length, width, thickness, weight of 100 seeds, grain surface shape, grain surface color, sterile lemma length, grain tip color, grain tip tail feather color and grain tip tail feather length), character rice (length, width, thickness, ratio of length to width, and color of rice epidermis). Phenetic analysis using the Minitab Release version 17 program divided 27 local tidal rice cultivars into 9 clusters at a similarity level of 56.78%. Which consists of group 1, consisting of Karya Kuning, Karya Merah, Maron, Pulut Putih, Putih, Putri Malu, Merah Putih, Super; Group II consists of Karanduku, Opium and Lembu Sawah Merah; cluster III consists of Ramos, Batang Tuaka, Karya Tinggi, Serang and Pariaman, cluster IV consists of paddy cattle; Group V consists of Kuatik, Serai, Lentik Bamban, Kodok, Group VI consists of Ordinary and Batang Piaman and groups VII, VIII and IX respectively consist of Pandan Wangi, Super and Pulut Hitam.

Weighted Combination of Łukasiewicz implication and Fuzzy Jaccard similarity in Hybrid Ensemble Framework (WCLFJHEF) for Gene Selection

A framework is developed for gene expression analysis by introducing fuzzy Jaccard similarity (FJS) and combining Łukasiewicz implication with it through weights in hybrid ensemble framework (WCLFJHEF) for gene selection in cancer. The method is called weighted combination of Łukasiewicz implication and fuzzy Jaccard similarity in hybrid ensemble framework (WCLFJHEF). While the fuzziness in Jaccard similarity is incorporated by using the existing Gödel fuzzy logic, the weights are obtained by maximizing the average F-score of selected genes in classifying the cancer patients. The patients are first divided into different clusters, based on the number of patient groups, using average linkage agglomerative clustering and a new score, called WCLFJ (weighted combination of Łukasiewicz implication and fuzzy Jaccard similarity). The genes are then selected from each cluster separately using filter based Relief-F and wrapper based SVMRFE (Support Vector Machine with Recursive Feature Elimination). A gene (feature) pool is created by considering the union of selected features for all the clusters. A set of informative genes is selected from the pool using sequential backward floating search (SBFS) algorithm. Patients are then classified using Naïve Bayes’(NB) and Support Vector Machine (SVM) separately, using the selected genes and the related F-scores are calculated. The weights in WCLFJ are then updated iteratively to maximize the average F-score obtained from the results of the classifier. The effectiveness of WCLFJHEF is demonstrated on six gene expression datasets. The average values of accuracy, F-score, recall, precision and MCC over all the datasets, are 95%, 94%, 94%, 94%, and 90%, respectively. The explainability of the selected genes is shown using SHapley Additive exPlanations (SHAP) values and this information is further used to rank them. The relevance of the selected gene set are biologically validated using the KEGG Pathway, Gene Ontology (GO), and existing literatures. It is seen that the genes that are selected by WCLFJHEF are candidates for genomic alterations in the various cancer types. The source code of WCLFJHEF is available at http://www.isical.ac.in/~shubhra/WCLFJHEF.html.

Morphological Diversity and Genetic Parameter of Okra (Abelmoschus esculentus L. Moench) Genotypes.

<b>Background and Objective:</b> Considering that the potential for okra as an anti-diabetic is very high, while okra productivity in Indonesia is still low, a plant breeding program through variety development is needed. One of the initial activities that needs to be carried out is the characterization of various genotypes, both quantitative and qualitative characters. This research aimed to obtain information on the diversity of morpho-agronomic characters in okra genotypes. <b>Materials and Methods:</b> The experiment was conducted as a randomized block design, one factor is genotype with three replications. The materials used in this research were 20 okra genotypes. The experimental units used in this research were 60 units. Each experimental unit consists of 10 sample plants. Analysis of quantitative character variations used PKBT-STAT 3.1. Cluster analysis was carried out with PBSTAT-CL 2.1.2 with the Gower dissimilarity and average linkage clustering methods. Furthermore, analysis was carried out using SAS OnDemand for Academics to see the distinguishing characteristics between clusters. <b>Results:</b> There were differences in okra genotypes based on qualitative and quantitative characteristics. The most diverse quantitative character is the yield component, which is the fruit character. Variance in genetic and heritability showed broad and high criteria, respectively. Based on cluster analysis results, okra genotypes were grouped into 3 clusters with a cophenetic distance value of 0.40. Cluster 1 consists of 9 genotypes. Cluster 2 consists of 10 genotypes. Cluster 3 consists of 1 genotype the Red Hill Country genotype. The grouping in cluster analysis was carried out based on leaf width, number of fruits, fruit weight, fruit diameter and carpel thickness character. <b>Conclusion:</b> This diversity of okra germplasm can facilitate plant breeding activities in the future by selecting genotypes to serve as parents according to the objectives carried out.

Evaluation of Distance Measurement Using Complete Linkage Method

Cluster analysis is the process of grouping a number of objects based on information obtained from data that explains the relationship between objects with the principle of maximizing similarities between members of one cluster and minimizing similarities between clusters. Cluster analysis is useful for identifying objects (recognition), supporting decision-making systems, and data mining. Cluster analysis consists of hierarchical (Average Linkage, Single Linkage, Complete Linkage, Ward's, and Centroid) and non-hierarchical (K-Means) methods. Each method generally has advantages and disadvantages. Apart from that, there are several distance measures that are commonly used in the grouping process, such as Euclidean, Canberra Metric, Czekanowski Coefficient, and others. In general, researchers will choose one or several cluster analysis methods as a comparison and a certain distance measure to be applied to the data in order to group objects based on certain criteria. In this research, a study and evaluation of Euclidean distance measures, Canberra Metric, and Czekanowski Coefficient were carried out using the Complete Linkage method based on simulated data. The conclusion obtained from evaluating measures of object similarity, namely Euclidean distance, Canberra Metric, and Czekanowski Coefficient by applying the Complete Linkage method, concluded that Euclidean distance is better used as a measure of object similarity in grouping cases compared to Canberra Metric and Czekanowski Coefficient.

CLUSTER ANALYSIS FOR DISTRICT/CITY GROUPING BASED ON VARIABLES AFFECTING POVERTY IN ACEH PROVINCE USING AVERAGE LINKAGE METHOD

Poverty is an inability of a person/household to meet basic needs in everyday life. Aceh is one of the provinces in Indonesia which is still faced with the problem of poverty. In March 2021 the poor population in Aceh numbered 834.24 thousand people and in September 2021 the poor population in Aceh increased by 16 thousand people, a total of 850.26 thousand people. Therefore the authors are interested in classifying and looking at the characteristics of 23 districts/cities in Aceh Province based on 5 variables that affect poverty. This study uses data from SUSENAS processed from BPS Kota Langsa in 2021. The variables used are households with the type of floor of a residential building made of soil/bamboo (X1), households with a floor area of ​​a residential building < 10 m2 per capita (X2), households with residential walls made of bamboo/rumbia/wood (X3), households with a source of drinking water from unprotected wells/springs/rivers/rainwater (X5), and households whose head of household did not attend school/didn't finish primary school/only primary school (X8). This study uses the average linkage method, namely the distance between two clusters is measured by the average distance between objects in each cluster. Of the 23 regencies/cities, 3 clusters were formed, namely cluster 1 with the lowest poverty rate consisting of 17 regencies/cities. Cluster 2 with the highest poverty rate consists of 2 districts/cities. Cluster 3 with a moderate poverty level consists of 4 districts/cities. The characteristics of the clusters that are formed are in clusters 1, 2 and 3 the dominant poverty level is influenced by the variable X3, which means that there are still many households that have houses with inadequate wall types. In clusters 1 and 3 the poverty rate is not dominantly influenced by variable X1, which means that many households have houses with proper floor types. In cluster 2 the poverty rate is not dominantly influenced by variable X5, which means that many households consume drinking water from cleaner and more protected sources.

Determining the Optimum Number of Clusters in Hierarchical Clustering Using Pseudo-F

Poverty refers to the condition where a person cannot meet the basic necessities based on the minimum living standards. Statistics Indonesia proxied an increase in the poverty rate in North Sumatra Province in 2021 from 8.75% to 9.01%. However, this increase is exclusive to North Sumatra Province, which has Indonesia's 3rd largest number of districts/cities. This study discussed mapping the North Sumatra Province region based on 10 poverty factor variables. The 10 variables are life expectancy, health complaints, poverty line, Gross Regional Domestic Product (GRDP), population growth rate, Expected Years of Schooling (EYS), Human Development Index (HDI), labor force participation rate, open unemployment rate, and district/city minimum wage. The Hierarchical Clustering analysis was employed to compare single, complete, and average linkage methods. The best method was determined based on the pseudo-F statistic value. 4 clusters had complete linkage methods, each of which possessed varied characteristics. Cluster 1 contains cities with the lowest poverty rate, including Medan City and Pematang Siantar City. Cluster 2 consists of cities with low poverty rates, while Cluster 3 consists of cities with high poverty rates. Cities that are included in Cluster 4 have very high poverty rates, including South Nias District and Pakpak Bharat District. The clusters present significant poverty rate gaps among North Sumatra Province regions.

KMD clustering: robust general-purpose clustering of biological data

The noisy and high-dimensional nature of biological data has spawned advanced clustering algorithms that are tailored for specific biological datatypes. However, the performance of such methods varies greatly between datasets and they require post hoc tuning of cryptic hyperparameters. We present k minimal distance (KMD) clustering, a general-purpose method based on a generalization of single and average linkage hierarchical clustering. We introduce a generalized silhouette-like function to eliminate the cryptic hyperparameter k, and use sampling to enable application to million-object datasets. Rigorous comparisons to general and specialized clustering methods on simulated, mass cytometry and scRNA-seq datasets show consistent high performance of KMD clustering across all datasets.

Prediction of FKRTL Services Diagnosed with Type 2 Diabetes Mellitus Using the Hierarchical Agglomerative Clustering Time Series Method

Diabetes Mellitus (DM) is a disease characterized by hyperglycemia or increased blood sugar levels and metabolic disorders. DM is a disease with a high prevalence rate in Indonesia. DM is included in the 10 most frequent Advanced Referral Health Facility (FKRTL) visits diagnoses. This research aims to find out provincial groupings based on data from FKRTL visits of participants diagnosed with T2DM using the Hierarchical Agglomerative Clustering method (single linkage, complete linkage, average linkage) and to find out predictions of participants diagnosed with T2DM at FKRTL visits using the Autoregressive Integrated Moving Average (ARIMA) method. The method used is Hierarchical Agglomerative Clustering Time Series. This research shows that the best algorithm is average linkage with a number of clusters of two. Forecasting provides a pattern that tends to decline.

Segmentasi Wilayah Indonesia Yang Berpotensi Budidaya Cabai Dengan Hierarki Clustering

Chili is one of the most widely consumed and highly price-volatile horticultural vegetables in Indonesia. In terms of consumption, it is a staple ingredient in the daily diet of most Indonesians. When chili prices surge, it not only affects the purchasing power of the population but also disrupts economic stability. Daily chili price data from the Department of Trade for the period of January 2010 to December 2015 demonstrates significant price fluctuations, primarily influenced by seasonal variations driven by weather conditions. Policy recommendations include promoting off-season chili cultivation, regulating production, and fostering farmer-industry partnerships. In pursuit of these objectives, mapping chili production regions in Indonesia using big data and data mining techniques, particularly hierarchical clustering, emerges as a valuable approach. This methodology allows the creation of models identifying optimal areas for chili cultivation, taking into account soil conditions conducive to optimal growth.The hierarchical clustering process employs average linkage and cosine distance to group regions based on climatic and environmental characteristics. The analysis reveals that Cluster C4, encompassing various provinces across Indonesia, exhibits the most favorable conditions for chili cultivation. This conclusion offers valuable guidance to farmers and researchers in determining the optimal locations for chili cultivation. Furthermore, the approach holds potential for application to other agricultural commodities, contributing to increased domestic production and price stability in the market.

ANALYSIS OF TRADITIONAL CHINESE MEDICINE PRESCRIPTIONS FOR CEREBRAL STROKE-RELATED DISEASES

Cerebral stroke, a type of cerebrovascular disease, has become the second leading cause of death globally. It is closely related to many diseases, including hypertension, diabetes, senile dementia, and so forth. As traditional Chinese medicine formulas are increasingly used to treat stroke and its associated diseases, people have begun to use machine learning methods to analyze Chinese medicine prescriptions and summarize their laws. In this study, we collected the data from classic Chinese formulations. Using the Jaccard similarity coefficient method, we calculated the similarity between different prescriptions. We then employed average linkage clustering, categorizing medicine prescriptions for chronic diseases such as diabetes, hypertension, and coronary heart disease into 12 groups. Some of these included “Heart Failure and Warm Kidney Soup”, “Sinus Chamber Junction Syndrome, Quadruple One Depression, Yi Qi, Activating Blood and Feeding Heart Soup”, “Nerves One, Depression One, Tian Ma Hook and Vine Drink”, and “Bawei Antihypertensive Decoction, Anemia Decoction, Hypotension Decoction, Myocardial Live Drink”. We observed that similar prescriptions had more meaningful mutual references. Subsequently, a correlation algorithm was used to analyze the “indications” and “prescription composition”, revealing 11 effective correlation rules. Among these, palpitations were strongly correlated with Astragalus membranaceus, Angelica sinensis, and cassia twig; weakness with Salvia miltiorrhiza, A. membranaceus, and A. sinensis; headaches with Ligusticum wallichii; and vertigo with A. membranaceus. These findings provided a theoretical reference for using traditional Chinese medicine in treating cerebral stroke and associated illnesses.

Hierarchical clustering with OWA-based linkages, the Lance–Williams formula, and dendrogram inversions

Agglomerative hierarchical clustering based on Ordered Weighted Averaging (OWA) operators not only generalises the single, complete, and average linkages, but also includes intercluster distances based on a few nearest or farthest neighbours, trimmed and winsorised means of pairwise point similarities, amongst many others. We explore the relationships between the famous Lance–Williams update formula and the extended OWA-based linkages with weights generated via infinite coefficient sequences. Furthermore, we provide some conditions for the weight generators to guarantee the resulting dendrograms to be free from unaesthetic inversions.

Assessment of genetic diversity for seed vigor traits in rice (Oryza sativa L.) through principal component and cluster analysis

Seed vigor, an important characteristic of seed quality attributes, determines the rate of early, rapid, uniform germination, emergenceand growth of strong seedling in any environmental condition. In the present set of experiment, 44 rice (Oryza sativa L.) varieties wereassessed for different seed vigor component traits. For evaluation of these traits, basic statistics, correlation, principal component (PC) andcluster analysis were carried out to obtain genetic diversity for seed vigor traits and early seedling vigor among rice varieties specifically to select the best varieties and important seed vigor traits for its possible use in future rice breeding programme. The estimation of descriptive statistics of 20 quantitative seed vigor-related traits indicated existence of variability among the varieties. The 44 varieties were grouped into five clusters on the basis of average linkage and dendogram. Varieties in Cluster I are considered to possess very high vigor traits and cluster IV with least seed vigor traits. Principal component (PC) analysis showed first 5 PCs having Eigen value >1 explaining 77.01% of the total variation with different seed vigor traits. In the biplot analysis between PCs 1 and 2, the varieties remained scattered in all four quadrants, showing large genetic variation in quantitative traits. Seed vigor index-I, seed vigor index-II, seed dry weight, shoot length, reserve mobilization, germination percentage, dehydrogenase, mean germination rate, germination speed, and mean germination time contributed to high variability among the varieties. The seed vigor traits were positively correlated with germination percentage, shoot length, seedling dry weight, speed of germination, mean germination rate, reserve mobilization, superoxide dismutase, dehydrogenase and alpha-amylase. The positive correlation among these seed vigor-contributing traits suggested that these characteristics are important for direct selection of high seed vigor varieties and early emergence.

Biodiversity and functional roles of soil organisms: An analysis of millipede populations in Southern Albania

Soil organisms are an important component of the biodiversity of terrestrial biogeocenoses. Their considerable taxonomic and ecological variability determines a significant functional role in soil formation processes, mechanisms of sustainable development and productivity of natural ecosystems. The aim of the study is to develop a practical approach to the ecological assessment of soil organisms populations using the example of Diplopoda in the southern region of Albania. The study was carried out using general scientific methods of cognition: system and cluster analysis, synthesis, specification, abstraction, formalization, deduction, generalization, and the statistical method. The article systematizes and analyses statistical data on the assessment of populations of millipede species found in the study area. It considers the influence of environmental factors on the distribution of representatives of the class Diplopoda. It calculated the frequency of species according to the collection areas, constant values for the species of the three represented orders. Based on the data variety, composition of each zone is carried out with cluster analysis using Average Linkage. The similarity between zones is studied. The dendrogram obtained indicates the proximity of zones according to their diversity composition. Based on the results of the study, a system of tools was proposed as part of the ecological assessment of soil organisms populations, and the main approaches to its implementation were developed. The practical significance of the obtained results lies in the possibility of using them to study the dynamics of soil organism populations, including in the period of global climate change, to develop a dynamic approach to the ecological assessment of soil ecosystems and to implement an appropriate adaptation and regeneration strategy

Application of self-organizing maps to coal elemental data

Understanding the modes of occurrence of elements in coal is important, not only to help properly evaluate the impacts of potentially toxic elements on the environment and human health but also to provide technical guidance for recovering critical elements from coal ash. Statistical and multivariate data analysis methods have widely been used, together with physical and chemical methods, to determine the modes of occurrence of elements in coal. However, some of the statistical methods, e.g., average linkage hierarchical clustering algorithm have some disadvantages (e.g., statistical errors and poor visualization). A self-organizing map is an unsupervised artificial neural network, and it is known for its high data mining capability and excellent data visualization. In contrast to the average linkage hierarchical clustering algorithm that is commonly used for analyzing the modes of occurrence of elements in coal, the self-organizing map algorithm can provide a topological relationship among elements instead of merely providing the groups to which the elements belong. This paper focuses on the application of self-organizing map to coal elemental data for analyzing the modes of occurrence of elements in coal. Samples used in this study are from the Adaohai, Hailiushu, and Datanhao mines, all located in the Daqingshan Coalfield, Inner Mongolia, China. The results obtained from the self-organizing map algorithm are compared with those produced by average linkage hierarchical clustering algorithm. Based on the previous investigations (mainly direct methods) and further analysis, it can be concluded that the results from the self-organizing map algorithm in this investigation are more consistent with the geochemical nature and previous investigations by direct methods than those from average linkage hierarchical clustering algorithm. Consequently, the self-organizing map algorithm is a new reliable and intuitive method for analyzing the modes of occurrence of elements in coal.

Multivariate Analysis for Post Harvest Quality and Yield Attributes in Tomato (Solanum lycopersicum L.)

Aim: To study the multivariate analysis, genetic parameters and correlation for post harvest quality and yield traits in tomato.
 Study Design: The variability in the twenty genotypes of tomato (Solanum lycopersicum L.) was evaluated for 18 yield attributes and post harvest quality traits using randomized block design and analyzed with multivariate methods.
 Place and Duration of Study: Twenty genotypes of tomato augmented from Indian Institute of Vegetable Research, Varanasi were sown during rainy season at Horticulture Research Farm of Banaras Hindu University.
 Methodology: The unweighted pair group method of the average linkage (UPGMA) cluster analysis and principal component analysis (PCA) were used to analyze the data. Canonical discriminant analysis showed the contribution of each trait to the classification of the tomato accessions into different cluster groups.
 Results: The first seven principal components (PC) explained 87.83% of total variation and has eigen values >1. The traits that mainly contributed for this variation in PC1 and PC2 are fruit yield, plant height, number of flower clusters per plant, number of fruits per plant, days to first fruit set, number of fruits per cluster. High (>20%) genotypic coefficient of variation (GCV) and phenotypic coefficient of variation (PCV) was observed for number of fruits/cluster, fruit shape index, number of fruits/plant, fruit yield and shelf life. The correlation coefficients of number of primary branches/plant, days to first fruit set, number of flower clusters/plant, number of fruits/cluster, fruit width (cm), number of fruits/plant, fruit weight (g) and lycopene (mg/100 g) were positively and significantly correlated to fruit yield/plant.
 Conclusion: Number of flower clusters/plant, fruit weight and number of fruits per plant had contributed for maximum variation. These traits also had high heritability, high genetic gain and significant correlation with fruit yield.

DIVERSIDAD DEL MAÍZ EN TRES ZONAS GEOMORFOLÓGICAS DE YUCATÁN, MÉXICO

<p><strong>Background: </strong>Maize (<em>Zea mays</em> L.) is the main sustenance in the daily diet of Mexican families. As a crop, it is one of the most important in the country of Mexico, and in Yucatan state, it is grown under rainfed conditions in milpas with no mechanizable lands. In this study, an analysis of the phenotypic variability from cob collects of native maize from Yucatan state was carried out, with ethnobotanical information collected within passport data. <strong>Objectives:</strong> To introduce the genetic diversity of maize into a germplasm bank, to know the genetic diversity of native populations based on the characteristics of cob, to know its distribution, to find the potential populations in each collection area for its use in genetic improvement programs. <strong>Methodology: </strong>66 Tuxpeños, 13 Dzit bacal, 6 Nal tel, 13 Xmejen nal, and 2 Nal xoy were collected in the southern, central, and eastern regions of the state, from January to March 2020, by sampling the four cardinal points in each community visited. A vector map of collections in Yucatan was developed and quantitative data of 13 biometric cob variables were recorded in 100 populations (crop cycles: late n=68; intermediate n=26; early n=6), a general data analysis of variance (ANOVA) and by crop cycles were made, principal component analysis (PCA), hierarchically clustered with the average linkage method and discriminant analysis were made. Qualitative data from ethnobotanical surveys with mixed questions applied to milperos at the time of collection are presented. <strong>Results: </strong>The diversity of native maize in Yucatan is made up of three main groups based on the crop cycle: late, intermediate, and early. The southern and eastern regions of Yucatan preserve greater diversity, representing 44 and 40% of the total collections, respectively. There were significant differences in all ear variables; in a late growth cycle, only the grain thickness did not show differences between populations, and in the early growth cycle the grain thickness, width, and length variables were not significant. The PCA explained 80% of the total variation, seven different groups were formed, with greater differentiation in early maize Nal tel, intermediate Xmejen nal and Dzit bacal, contrary to the Tuxpeños late maize. Ten promising populations were identified for selection in each geomorphological region: eight correspond to the southern, two to the eastern, and one to the center of Yucatan state. The main factors to select for sowing corn in the region are: white and yellow maize for yield, the resistance to weevil attack for red maize, and the perception of color and palatability in purple maize. <strong>Implications: </strong>A complete phenotypic characterization in the field is required with a special interest in red-pigmented maize.<strong> Conclusions: </strong>The interest of the milperos in conserving and sowing the different native maize are based on the color of the grain, the benefits and uses that they can obtain from them, which determine the planting area in the milpas of the different races/varieties of maize. Red grain maize is being planted in a lower area in relation to other colors. The southern and eastern geomorphological regions showed a genetic flow between them.</p>

Using Clustering Methods for the Identification of Acoustic Emission Signals Generated by the Selected Form of Partial Discharge in Oil-Paper Insulation

The article presents the results concerning the use of clustering methods to identify signals of acoustic emission (AE) generated by partial discharge (PD) in oil-paper insulation. The conducted testing featured qualitative analysis of the following clustering methods: single linkage, complete linkage, average linkage, centroid linkage and Ward linkage. The purpose of the analysis was to search the tested series of AE signal measurements, deriving from three various PD forms, for elements of grouping (clusters), which are most similar to one another and maximally different than in other groups in terms of a specific feature or adopted criteria. Then, the conducted clustering was used as a basis for attempting to assess the effectiveness of identification of particular PD forms that modelled exemplary defects of the power transformer’s oil-paper insulation system. The relevant analyses and simulations were conducted using the Matlab estimation environment and the clustering procedures available in it. The conducted tests featured analyses of the results of the series of measurements of acoustic emissions generated by the basic PD forms, which were obtained in laboratory conditions using spark gap systems that modelled the defects of the power transformer’s oil-paper insulation.