Intra-cluster Distance Research Articles

Assessment of Genetic Diversity of 62 F4 Population of Rapeseed (Brassica Napus L.) Through Multivariate Analysis

Rapeseed (Brassica napus L.) is the best one in respect of oil production. It is the order of the day to take better steps for production and quality improvement of our local cultivars. Broadening of genetic diversity in spring oilseed Brassica napus L. (AACC, 2n = 38), canola is important for continued improvement of this crop. Sixty-two genotypes in F4 generation of Brassica napus L. were evaluated to assess genetic diversity based on randomized complete block design with three replications at the experimental field of Sher-e-Bangla Agricultural University, Dhaka. Different Multivariate analyses were performed to classify 62 genotypes. On the basis of cluster analysis, all the genotypes were classified in five clusters. The cluster IV comprised the maximum number (19) of genotypes followed by same in cluster II (18). The cluster I and V comprised 10 and 9 genotypes respectively. The lowest number of genotypes was present in cluster II. The highest inter-cluster distance (10.309) was observed between the cluster I and IV and the genotypes of these clusters involved in hybridization may produce a wide spectrum of segregating population. The lowest inter-cluster distance (3.513) was observed between the cluster III and IV. The inter-cluster distances were larger than the intra-cluster distances. Considering cluster distance, inter genotypic distance and other agronomic performance G3, G4, G24, G35 and G51 might be suggested for future breeding program. SAARC J. Agric., 19(1): 15-25 (2021)

Assessment of genetic diversity in linseed (Linum usitatissimum L.) genotypes

An investigation was carried out to assess the nature and magnitude of genetic diversity in 36 genotypes of linseed using Mahalanobis D2 statistics. Presences of diversity pave way for exploitation of genotypes in breeding programmes which intended to improve the yield and yield attributing traits. The cluster analysis grouped 36 linseed genotypes into 12 distinct clusters. Clusters II and V were the largest containing eight genotypes each followed by cluster I with seven and cluster VII with five genotypes. The pattern of distribution of genotypes within different clusters was random and independent of geographical origin or region of adaptation. The maximum inter cluster distance was observed between cluster VII and XI (227.97) followed by cluster III and VII (207.29). The greater the distance between the two clusters, wider the genetic diversity between genotypes. The intra cluster distance was maximum in cluster VII (48.85) followed by cluster V (41.30) indicating hybridization involving genotypes within the same clusters might result in good cross combinations. On the basis of cluster mean value, genotypes in cluster VI, VII and IV deserve consideration for their direct use as parents in hybridization programs to develop high yielding linseed varieties. Key wordsGenetic diversity, Cluster analysis, D2 statistics, Inter and Intra cluster distance

Clustering Using Cyclic Spaces of Reversible Cellular Automata

This paper introduces a cycle-based clustering technique using the cyclic spaces of reversible cellular automata (CAs). Traditionally, a cluster consists of close objects, which in the case of CAs necessarily means that the objects belong to the same cycle; that is, they are reachable from each other. Each of the cyclic spaces of a cellular automaton (CA) forms a unique cluster. This paper identifies CA properties based on “reachability” that make the clustering effective. To do that, we first figure out which CA rules contribute to maintaining the minimum intracluster distance. Our CA is then designed with such rules to ensure that a limited number of cycles exist in the configuration space. An iterative strategy is also introduced that can generate a desired number of clusters by merging objects of closely reachable clusters from a previous level in the present level using a unique auxiliary CA. Finally, the performance of our algorithm is measured using some standard benchmark validation indices and compared with existing well-known clustering techniques. It is found that our algorithm is at least on a par with the best algorithms existing today on the metric of these standard validation indices.

Assessing the genetic diversity of twenty one Colombo limon L. genotypes through multivariate and covariance matrix analysis

Assessing the genetic diversity of twenty one Colombo limon L. genotypes through multivariate and covariance matrix analysis

A state-of-art optimization method for analyzing the tweets of earthquake-prone region

With the increase in accumulated data and usage of the Internet, social media such as Twitter has become a fundamental tool to access all kinds of information. Therefore, it can be expressed that processing, preparing data, and eliminating unnecessary information on Twitter gains its importance rapidly. In particular, it is very important to analyze the information and make it available in emergencies such as disasters. In the proposed study, an earthquake with the magnitude of Mw = 6.8 on the Richter scale that occurred on January 24, 2020, in Elazig province, Turkey, is analyzed in detail. Tweets under twelve hashtags are clustered separately by utilizing the Social Spider Optimization (SSO) algorithm with some modifications. The sum-of intra-cluster distances (SICD) is utilized to measure the performance of the proposed clustering algorithm. In addition, SICD, which works in a way of assigning a new solution to its nearest node, is used as an integer programming model to be solved with the GUROBI package program on the test data-sets. Optimal results are gathered and compared with the proposed SSO results. In the study, center tweets with optimal results are found by utilizing modified SSO. Moreover, results of the proposed SSO algorithm are compared with the K-means clustering technique which is the most popular clustering technique. The proposed SSO algorithm gives better results. Hereby, the general situation of society after an earthquake is deduced to provide moral and material supports.

An Energy-Efficient Modified Metaheuristic Inspired Algorithm for Disaster Management System Using WSNs

In recent trends, Internet of Things (IoT) enabled Wireless Sensor Network (WSN) is widely used for various applications like emergency medical services, fire detection, flood control, etc. for disaster management in the smart city. Commonly, sensor devices are equipped with limited battery but they consumed a lot of battery in the communication for such scenarios. Therefore, practical comprehension of such networks is the challenging task as data collection consuming tremendous energy due to the shortcomings of the existing methods i.e., cluster overlapping, elect lower energy nodes as cluster-head (CH), formed highly dense clusters and hotspot problem in the network, and large communication distance. To overcome the above-discussed issues, an integrated modified Genetic Algorithm (GA) for CH election in WSNs is proposed to maximizing the network lifetime referred to as ModifyGA. The energy-efficiency of ModifyGA is increased by incorporating dynamic sensing range and criteria’s used for developing fitness function. The ModifyGA satisfies various constraints for optimizing intra-cluster distance, systematic utilization of node’s energy in the cluster, reducing hop-count and promoting selection of highly capable nodes for CHs. The simulation analysis of ModifyGA is carried-out to operate with a single static sink, multiple static and movable sinks to have an impartial comparative analysis.

Morpho-anatomical variability, principal component analysis and Euclidean clustering of tossa jute (Corchorus olitorius L.)

Jute, the second most important natural fibre crop after cotton in the world. Bangladesh occupied the first position for jute fibre production and exportation after India among south-east Asian countries. Tossa jute is cultivated more (80–85%) here among the commercial cultivation of jute and allied fibre crops. It produces quality fibre but yield is low due to stress susceptibility compared to capsularis jute. The self-pollination nature and sexual incompatibility between two jute species (C. capsularis and C. olitorius) cause narrower genetic base and restrict genetic exchange. So, intra specific hybridization using diversified jute germplasms or genetic change will be the best option to the jute breeders for genetic improvement of existing cultivars. Hence, 20 tossa jute genotypes were investigated through field based morphological study (RCBD) and laboratory oriented anatomical study (CRD) for yield and yield attributing morpho-anatomical variability at BJRI during March, 2019 to July, 2020. Among 20 tossa jute genotypes, Acc. 1318, O-043-7-9(G), Acc. 4311, Acc. 1306, O-0411-10-4, O-049-1-3, O-0512-6-2, Acc. 4160 showed good results for yield and yield related morphological traits at 120 days after sowing and stem anatomical traits at 100 days after sowing. Higher significant genotypic correlation coefficient values were recorded than phenotypic associations among all the morphological traits. Plant height, fresh weight, fibre yield content gave high heritability (>80%) in broad sense along with possibility of more genetic advance in percentage. The average inter-cluster distances were higher than the average intra-cluster distances, which shows the presence of wide genetic diversity among the genotypes of different clusters than those of the same cluster. The first three principal components, whose Eigen values are greater than one, accounted for 99.96% of the total variation among the studied characters. The information obtained from this investigation is useful in planning further breeding programme for tossa jute improvement.

Improving the Performance of Multidimensional Clinical Data for OLAP using an Optimized Data Clustering approach

Medicine is a fresh way to utilize for curing, analyzing and detecting the diseases through data clustering with OLAP (Online Analytical Processing). The large amount of multidimensional clinical data is reduced the efficiency of OLAP query processing by enhancing the query accessing time. Hence, the performance of OLAP model is improved by using data clustering in which huge data is divided into several groups (clusters) with cluster heads to achieve fast query processing in least time. In this paper, a Dragon Fly Optimization based Clustering (DFOC) approach is proposed to enhance the efficiency of data clustering by generating optimal clusters from multidimensional clinical data for OLAP. The results are evaluated on MATLAB 2019a tool and shown the better performance of DFOC against other clustering methods ACO, GA and K-Means in terms of intra-cluster distance, purity index, F-measure, and standard deviation

A Grey-Wolf based Optimized Clustering approach to improve QoS in wireless sensor networks for IoT applications

Wireless sensor networks (WSNs) have gained much attention in public and research communities due to their incredible capabilities and ever-growing range of applications. The WSN is equipped with a specialized transducer that adds the sensing services to IoT. This equipment is limited to battery and resource capacity, which introduces many challenges to academia and industry. Hence WSN has to be utilized in an energy-efficient manner to maximize the network’s lifetime while providing a precise QoS guarantee. QoS is an essential issue in many IoT applications such as environmental monitoring, smart cities, weather monitoring, animal tracking, disaster management, bio-medical applications. An optimal clustering technique for WSN, which includes the formation of clusters, and cluster head (CH) selection, can significantly improve the QoS to increase the lifespan of a WSN. This paper proposes a Grey wolf optimization-based cluster head selection technique for WSN considering distinct factors like energy level of the node, node degree, sink distance, intracluster distance, and priority factor. This paper also addresses the routing through QoS aware relay node selection for effective and reliable inter-cluster routing from CHs to Base station (BS). The proposed technique is simulated and evaluated based on the Quality of Service (QoS) parameters viz. residual energy, stability period, throughput, network lifetime, and delay. The proposed techniques improve the overall network performance by 10.00%, 23.75%, and 54.54% corresponding to ESO, GECR, and LEACH. Hence, the study infers that the protocol is well suited to design WSNs in IoT applications.

Genetic divergence among Ramnad mundu chilli (Capsicum annuum L.) genotypes for yield and quality

Genetic diversity among forty-seven genotypes of Mundu chilli (Capsicum annuum L.) was assessed for fifteen yield and quality characters during kharif 2018. The analysis of variance disclosed that significant difference present for most of the parameters studied, which indicated the existence of wide diversity among all Mundu chilli genotypes. Mahalanobis D2 statistic stated that the forty-seven genotypes were grouped into six clusters. The highest contribution for genetic divergence was dry fruit yield per plant (25.7%), Ascorbic acid (11.56%), 1000 seed weight (10.85%) and the number of seeds per fruit (10.5%). Among the clusters, the largest was cluster II containing 21 genotypes followed by cluster III (13 genotypes) and cluster I (10 genotypes) whereas, clusters IV, V and VI were grouped as solitary clusters (one genotype in each cluster). The highest inter-cluster distance was noted between clusters IV and VI (1588.27) whereas, the lowest was recorded between clusters II and V (192.44). Cluster III (144.94) has recorded the highest intra-cluster distance and the lowest was observed in clusters IV, V and VI (0.00). D2 cluster analysis revealed wide genetic distance (inter-cluster) between the genotypes of cluster I (PKMCA-38), II (PKMCA-20, PKMCA-32, PKMCA-33) and V (PKMCA-08). Hence, genetic improvement by crossing among these groups can exploit heterotic hybrids.

Genetic diversity in foxtail millet genotypes

A total of 80 foxtail millet genotypes were evaluated for ten quantitative characters at MARS (Main Agricultural Research Station), UAS (University of Agricultural Sciences), Raichur during kharif 2018 to assess the genetic diversity using Mahalanobis D2 statistic. The eighty genotypes were grouped into twelve clusters. The highest inter-cluster distance (6623.62) was observed between cluster-VIII and cluster-XII. The highest intra-cluster distance was observed in cluster VII (529.01). A high mean grain yield was observed in cluster-XI (59.72g). Plant height (46.96%) and grain yield (46.39%) have the highest contribution to the total divergence. The crosses between genotypes of the divergent clusters VIII and XII would manifest wide variability.

Genetic divergence analysis in basmati rice genotypes (Oryza sativa L.) for agro-morphological and quality traits using multivariate approach

Genetic diversity of 30 basmati rice genotypes was analysed based on nine agro-morphological and six quality traits. The results of the principal component analysis showed that the first six principal components explained 89.16% of the total variation in the experimental material. These 30 basmati genotypes were grouped into six clusters which indicated the presence of sufficient diversity among the tested genotypes. Cluster I and cluster III was found to be the largest comprising of 10 genotypes each followed by cluster II having seven genotypes. The highest average intra-cluster distance was observed in cluster III. Highest inter-cluster distance (D2) was observed between clusters III and VI followed by clusters III and V, III and IV & clusters II and III. Cluster II showed high mean value for grain yield per plant, 1000 grain weight, and grain length. The characters viz., amylose content, grain length after cooking, spikelet per panicle, grain width, grain length and 1000 grain weight contributed maximum towards total genetic divergence, suggest their suitability of selection.

Genetic divergence in Indian mustard (Brassica juncea L. Czern. & Coss.

Genetic divergence was carried out in 15 Indian mustard varieties/strains, 4 testers and 60 F1s developed by crossing 15 lines with 4 testers. Based on D2 values between the pair of genotypes, 19 parental lines were grouped into five clusters in E1 (timely sown) & E2 (late sown) condition. In E1, cluster II was the largest having 8 genotypes followed by cluster I and IV with four genotypes. Whereas, in E2 cluster I was largest having 9 genotypes followed by cluster V which had four genotypes. In E1 the intra-cluster distance ranged from 0.00 (cluster V) to 581.64 (cluster IV). Cluster IV and V were the most diverse with inter-cluster distance of 7169.70 followed by cluster II and V (4829.11). Whereas, in E2 the intra-cluster distance ranged from 0.00 (cluster IV) to 296.03 (cluster V). Clusters IV and V were the most diverse with inter-cluster distance of 1894.16. The 60 F1s were grouped into eight clusters in E1 and E2. In E1, the maximum number of genotypes were grouped in clusters I and VI (12) and the intra-cluster distance ranged from 111.59 to 318.07. The maximum inter-cluster distance was observed between cluster IV and VIII (3554.76). Whereas, in E2 maximum number of genotypes grouped in cluster III (15) and intra-cluster distance ranged from 0.00 to 351.31. The maximum inter-cluster distance (D2) was observed between cluster V and VIII (43829.30).

Diversity and association studies in various yield and quality traits in tomato (Solanum lycopersicum L.)

The present investigation was conducted on twenty five diverse genotypes of tomato for yield and quality traits at the experimental farm of RHR&TS, Jachh, Kangra, Dr. YS Parmar University of Horticulture and Forestry, Nauni, Solan, Himachal Pradesh during the year 2018. Experiment was conducted in Randomized Complete Block Design with three replications. Character association studies revealed a positive and significant correlation coefficient of marketable fruit yield per plant at genotypic and phenotypic level with fruit length, fruit breadth, average fruit weight, number of fruit clusters/plant, number of fruits/plant, number of locules/fruit, harvest duration, shelf life, pericarp thickness and total soluble solid whereas it was negatively and significantly correlated with incidence of buckeye rot. The results of path analysis at genotypic level revealed that average fruit weight, fruit length, number of locules/fruit, harvest duration, pericarp thickness, fruit breadth, total soluble solids and days to first fruit harvesting had positive and direct effects on marketable fruit yield per plant. The intra-cluster distance was recorded maximum in cluster IV and minimum in cluster V. The inter cluster distance was maximum to the tune of between cluster I and IV. The minimum inter cluster distance was observed for cluster I and V.

Presenting a Proper Ensemble Clustering (EC) Method Based on Hierarchical Methods and Classical Generative Algorithms

Ensemble Clustering (EC) methods became more popular in recent years. In this methods, some primary clustering algorithms are considered to be as inputs and a single cluster is generated to achieve the best results combined with each other. In this paper, we considered three hierarchical methods, which are single-link, average-link, and complete-link as the primary clustering and the results were combined with each other. This combination was done based on correlation matrix. The basic algorithms were combined as binary and triplicate and the results were evaluated as well. the IMDB film dataset were clustered based on existing features. CH, Silhouette and Dunn Index criteria were used to evaluate the results. These criteria evaluate the clustering quality by calculating intra-cluster and inter-cluster distances. CH index had the highest value when all three basic clusters are combined. our method shows that EC can achieve better results and present clusters with higher robustness and accuracy.

Variants of bat algorithm for solving partitional clustering problems

Clustering is an exploratory data analysis technique that organize the data objects into clusters with optimal distance efficacy. In this work, a bat algorithm is considered to obtain optimal set of clusters. The bat algorithm is based on the echolocation feature of micro bats. Moreover, some improvements are proposed to overcome the shortcoming associated with bat algorithm like local optima, slow convergence, initial seed points and trade-off between local and global search mechanisms etc. An enhanced cooperative co-evolution method is proposed for addressing the initial seed points selection issue. The local optima issue is handled through neighbourhood search-based mechanism. The trade-off issue among local and global searches of bat algorithm is addressed through a modified elitist strategy. On the basis of aforementioned improvements, three variants (BA-C, BA-CN and BA-CNE) of bat algorithm is developed and efficacy of these variants is tested over twelve benchmark clustering datasets suing intra-cluster distance, accuracy and rand index parameters. Simulation results showed that BA-CNE variant achieves more effective clustering results as compared to BA-C, BA-CN and BA. The simulation results of BA-CNE are also compared with several existing clustering algorithms and two statistical tests are also applied to investigate the statistical difference among BA-CNE and other clustering algorithms. The simulation and statistical results confirmed that BA-CNE is an effective and robust algorithm for handling partitional clustering problems.

Chaotic sequence and opposition learning guided approach for data clustering

Data clustering is a prevalent problem that belongs to the data mining domain. It aims to partition the given data objects into some specified number of clusters based on the sum of the intra-cluster distances. It is an NP-hard problem, and many heuristic approaches have already been proposed to target the desired objective. However, during the search process, the problem of local entrapment is prevalent due to nonlinear objective functions and a large range of search domains. In this paper, an opposition learning and chaotic sequence guided approaches are incorporated in a fast converging evolutionary algorithm called improved environmental adaptation method with real parameter (IEAM-R) for solving the data clustering problem. A chaotic sequence generated by a sinusoidal chaotic map has been utilized to target promising solutions in the search domain. On the other hand, the inclusion of the opposition learning-based approach allows the solutions to explore more appropriate locations in the search domain. The performance of the proposed approach is compared against some well-known algorithms using fitness values, statistical values, convergence curves, and box plots. These comparisons justify the efficacy of the suggested approach.

Refining a [formula omitted]-nearest neighbor graph for a computationally efficient spectral clustering

Spectral clustering became a popular choice for data clustering for its ability of uncovering clusters of different shapes. However, it is not always preferable over other clustering methods due to its computational demands. One of the effective ways to bypass these computational demands is to perform spectral clustering on a subset of points (data representatives) then generalize the clustering outcome, this is known as approximate spectral clustering (ASC). ASC uses sampling or quantization to select data representatives. This makes it vulnerable to 1) performance inconsistency (since these methods have a random step either in initialization or training), 2) local statistics loss (because the pairwise similarities are extracted from data representatives instead of data points). We proposed a refined version of k-nearest neighbor graph, in which we keep data points and aggressively reduce number of edges for computational efficiency. Local statistics were exploited to keep the edges that do not violate the intra-cluster distances and nullify all other edges in the k-nearest neighbor graph. We also introduced an optional step to automatically select the number of clusters C. The proposed method was tested on synthetic and real datasets. Compared to ASC methods, the proposed method delivered a consistent performance despite significant reduction of edges.

An Energy-Aware Cluster Head Selection Protocol based on Multi-Objective Dolphin Swarm Optimization in Wireless Sensor Network

The Wireless Sensor Network (WSN) is spread widely in many applications due to its portable, cost-effective, and user-friendly approach. This needs to adopt routing schemes to forward the sensed information to the sink nodes or base station through minimum-cost links. The frequently utilized data accumulation approach is clustering which organizes the nodes into clutches to minimize the consumption of energy. Likewise, in clustering protocols, the additional load will be bear by the Cluster Head (CH) for organizing various deeds inside the cluster. As a result, appropriate CH selection and their power balance using efficient clustering protocol are significant features for the long-term operation of the Wireless Sensor Network (WSN). In this paper, An Energy-Aware Cluster Head Selection Protocol based on Multi-Objective Dolphin Swarm Optimization (EACHP-MODSO) is proposed to enrich the lifetime of Wireless Sensor Network (WSN). This proposed method considers six criteria to select effective Cluster Head like residual energy, inter cluster distance, intra-cluster distance, mobility, node density, and delay. The results of the proposed system show better enhancement of network lifetime compared to existing protocols.

Genetic Diversity in Fiber Related Traits of Tossa Jute (Corchorus Olitorius L.) Germplam

Genetic diversity of twenty-one genotypes of tossa jute was studied through Mahalanobis D2 statistic and principal component analysis for 15 quantitative traits related to yield at the research farm of Sher-e-Bangla Agricultural University, Dhaka, Bangladesh. The genotypes were grouped into four clusters. Cluster III contained the highest number of genotypes (nine), while cluster II had the lowest number of genotypes (three). The inter-cluster distances were higher than intra-cluster distances indicating wider genetic diversity among the genotypes of different clusters. The intra-cluster distances were lower in all the cases reflecting homogeneity of the genotypes within the cluster. The highest intra-cluster distance was noticed for the cluster I and the lowest for cluster IV. The genotypes from cluster I could be selected as parents for hybridization for producing transgressive segregants. The highest inter-cluster distance was found between clusters I and IV followed by clusters I and III and the lowest was between clusters III and IV. Cluster IV recorded the highest mean value for plant height, base diameter, root length, leaf area, fresh weight with and without leaves, dry fiber weight and dry stick weight. In the total divergence, the highest contribution was recorded in plant height (65.1%) followed by base diameter (16.6%). The first two principal components, whose eigen values were greater than one, accounted for 81.7% of the total variations among the genotypes for fifteen fiber related traits. Considering the magnitude of cluster distance, cluster means for different characters and contribution of characters towards divergence, the genotypes G17, G18 from cluster IV; G1, G2, G5, G10, G16 from cluster I and G4 from cluster III could be selected as promising parents for hybridization program.
 SAARC J. Agri., 18(2): 27-37 (2020)