Dissimilarity Measure Research Articles

Resolving Network Clusters Disparity Based on Dissimilarity Measurements with Nonmetric Analysis of Variance

Resolving Network Clusters Disparity Based on Dissimilarity Measurements with Nonmetric Analysis of Variance

A domestic plant differs from its wild relative along multiple axes of within-plant trait variability and diversity.

For 10,000 years humans have altered plant traits through domestication and ongoing crop improvement, shaping plant form and function in agroecosystems. To date, studies have focused on how these processes shape whole‐plant or average traits; however, plants also have characteristic levels of trait variability among their repeated parts, which can be heritable and mediate critical ecological interactions. Here, we examine an underappreciated scale of trait variation—among leaves, within plants—that may have changed through the process of domestication and improvement. Variability at this scale may itself be a target of selection, or be shaped as a by‐product of the domestication process. We explore how levels of among‐leaf trait variability differ between cultivars and wild relatives of alfalfa (Medicago sativa), a key forage crop with a 7,000‐year domestication history. We grew individual plants from 30 wild populations and 30 cultivars, and quantified variability in a broad suite of physical, nutritive, and chemical leaf traits, including measures of chemical dissimilarity (beta diversity) among leaves within each plant. We find that trait variability has changed over the course of domestication, with effects often larger than changes in trait means. Domestic alfalfa had elevated among‐leaf variability in SLA, trichomes, and C:N; increased diversity in defensive compounds; and reduced variability in phytochemical composition. We also elucidate fundamental relationships between trait means and variability, and between overall production of secondary metabolites and patterns of chemical diversity. We conclude that within‐plant variability is an overlooked dimension of trait diversity in a globally critical agricultural crop. Trait variability is actually higher in cultivated plants compared to wild progenitors for multiple nutritive, physical, and chemical traits, highlighting a scale of variation that may mitigate loss of trait diversity at other scales in alfalfa agroecosystems, and in other crops with similar histories of domestication and improvement.

A new Technique in Protein Structure Quantitative Identification

Graph distance is also named approximate graph isomorphism, error-tolerant graph matching, it is a measure of similarity (or dissimilarity) between two graphs. The graph distance function is an elusive question remaining a pressing problem in a wide range of fields. In general, graphs are usually enriched with node and edge attributes, namely, heterogeneous graphs, our focus is encapsulating node and edge identities in a graph. In addition, an adequate representation of the graph-adjacency matrix can capture the connectivity of the graph structure, while an adjacency matrix bears high-order combinatorial nature. Solving these challenges in the effective analysis of these graphs is of utmost importance. In this paper, structural and semantic features are both preserved by graphs, so the analysis of row sum and eigenspectra for vertex and edge adjacency matrix has captured the affinity interactions within graphs locally and globally. Therefore, we estimate the geometrical and semantic dissimilarities/distances between graphs extensively and systemically. Several illustrative chemical compound cases implement in practical scenarios, thus, the theory could be easily understood. Our method defines a quantitative distance (or dissimilarity) measure for comparing graphs, it has a good measure of expressiveness and a suited polynomial computation complexity, which paves the way for graph analysis.

Robust Infrared Maritime Target Detection via Anti-Jitter Spatial–Temporal Trajectory Consistency

When detecting diverse infrared (IR) small maritime targets on complicated scenes, the existing methods get into trouble and unsatisfactory performance. The main reasons are as follows: 1) affected by target characteristics and ambient temperature and so on, both bright and dark targets may exist on IR maritime images in practical application and 2) spatial information and temporal correlation of targets are not fully excavated. To these problems, we propose a robust anti-jitter spatial–temporal trajectory consistency (ASTTC) method, the main idea of which is to improve detection accuracy using single-frame detection followed by multi-frame decision. First, we innovatively design adaptive local gradient variation (ALGV) descriptor, which combines local dissimilarity measure with gradient magnitude distribution to enhance the local contrast for both bright and dark targets so that the suspected targets can be robustly extracted. For multi-frame decision, interframe displacement correction is necessary to eliminate the interference of IR imager motion and vibration for target codeword. We use pyramid optical flow to track feature point extracted by Shi-Tomasi to capture interframe registration coefficients. Then, the target position is corrected in the spatial–temporal domain. Finally, a robust spatial–temporal trajectory descriptor (STTD), which achieves target encoding and target trajectory consistency measurement, is designed to further confirm real targets and eliminate false targets. Experiments conducted on various real IR maritime image sequences demonstrate the applicability and robustness of ASTTC, which performs more satisfactorily than the existing methods in detection accuracy.

Efficient Model Selection in Switching Linear Dynamic Systems by Graph Clustering

The computation required for a switching Kalman Filter (SKF) increases exponentially with the number of system operation modes. In this paper, a computationally tractable graph representation is proposed for a switching linear dynamic system (SLDS) along with the solution of a minimum-sum optimization problem for clustering to reduce the switching mode cardinality offline, before collecting measurements. It is shown that upon perfect mode detection, the induced error caused by mode clustering can be quantified exactly in terms of the dissimilarity measures in the proposed graph structure. Numerical results verify that clustering based on the proposed framework effectively reduces model complexity given uncertain mode detection and that the induced error can be well approximated if the underlying assumptions are satisfied.

Decomposed Dissimilarity Measure for Evaluation of Digital Image Denoising

Decomposed Dissimilarity Measure for Evaluation of Digital Image Denoising

Infrared Detection of Small Moving Target Using Spatial–Temporal Local Vector Difference Measure

It is intractable for infrared (IR) search and tracking systems to detect small moving IR targets with competitive accuracy and low computation time. A common method is enhancing targets and suppressing the clutter in background, but pixel values of background and small targets are close to each other, so most of the current classic suppressing models are not suitable. In order to effectively resolve this problem, a novel spatial–temporal vector difference measure is proposed for moving object detection in IR videos. First, to enhance targets, a new local vector dissimilarity measure is used to describe the dissimilarity between a small target and its surrounding background and to calculate the spatial saliency map. Then, the local mean of successive frames is formed as a temporal vector, and we calculate the temporal saliency map using the range of the corresponding vector. Afterward, the fusion saliency map is measured by taking both feature maps into account. Finally, small objects are extracted by an adaptive segmentation method. Extensive qualitative and quantitative experimental results demonstrate that the proposed model is more efficient and reaches competitive accuracy in terms of F-measure in the public dataset compared to state-of-the-art spatial–temporal algorithms.

Fast Task-Specific Region Merging for SAR Image Segmentation

In existing superpixel-wise segmentation algorithms, superpixel generation most often is an isolated preprocessing step. The segmentation performance is determined to a certain extent by the accuracy of superpixels. However, it is still a challenge to develop a stable superpixel generation method. In this article, we attempt to incorporate the superpixel generation and merging steps into an end-to-end trainable deep network. First, we employ a recently proposed differentiable superpixel generation method to over-segment the single-polarization synthetic aperture radar (SAR) image. It outputs the statistical likelihood that each pixel belongs to different superpixels. In superpixel merging part, as one of our main contributions, we propose a superpixel-wise statistical dissimilarity measure method for converting the soft superpixels set into a self-connected weighted graph. More importantly, inspired by the concept of the number of walks in graph theory, we define the <inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>-order connectivity of each vertex. This definition can intelligently indicate the potential soft cluster centers and class assignments in graph. This merging method is differentiable, computationally simple, and free of empirical parameters. The superpixel generation and merging phases can be implemented under a unified deep network. The benefit is that our method can iteratively adjust the shapes of the superpixels according to the boundaries and segmentation results during training, until the satisfactory segmentation results are captured. Experimental results on real SAR images demonstrate that the segmentation precision of our proposed method is superior to other state-of-the-art methods in terms of precision and computational efficiency.

Infrared Detection of Small-Moving Targets Using Spatial Local Vector Difference and Temporal Sample Consensus Measures

Detection small moving targets in infrared sequences with accuracy and low computation time is challenging work in infrared search and tracking systems. A frequent approach for this task is to strengthen small weak targets and diminish the clutter of background. However, the background and small targets’ pixel values are close to each other and thus only a few background suppressing models are suitable to infrared small target segmentation. To efficiently resolve the problem that most of the classic approaches cannot manage low signal to noise ratio and weak objects without details, a novel spatial-temporal local difference measure is introduced for moving objects segmentation in infrared sequences. First of all, to strengthen targets, a new local vector dissimilarity measure is employed to demonstrate the difference between the weak target and their surrounding backgrounds and calculate the spatial saliency feature figure. Then the local sample consensus of succession images is used to compute the temporal varying feature figure. Afterward, the combined saliency feature map is measured by taking spatial and temporal feature images into account. Finally, the small moving targets are segmented employing an adaptive threshold approach. Abundant quantitative and qualitative experimental results have demonstrated that the introduced approach is remarkable and has a superior accuracy in terms of performance on both public and real datasets in comparison to the state-of-the-art spatial and temporal models.

Pembentukan Portofolio Saham Menggunakan Klastering Time Series K-Medoid dengan Ukuran Jarak Dynamic Time Warping

This research will present the formation of stock portfolios by preprocessing data using time series clustering with a distance measure of Dynamic Time Warping (DTW). First, stocks are grouped into several clusters using the Partitioning Around Medoids (PAM) time series cluster based on the DTW distance measure. After the clustering process, stocks are selected to represent each cluster to build the optimum portfolio. The stock selected from each cluster is the one with the highest Sharpe ratio. The optimal portfolio is determined using three portfolio models, namely: the classic MV portfolio model, the FMCD robust MV portfolio model and the S robust portfolio model. Using this procedure, an optimum portfolio can be obtained efficiently if there are many stocks involved in the portfolio formation process. Sharpe ratio is used to measure the performance of the portfolios. The results of the empirical study show that the portfolio performance generated using the PAM time series clustering with DWT distance dissimilarity measure combined with the classic MV portfolio model outperforms the resulting portfolio performance in combination with other models.

Research on driving behaviour assessment based on evidence theory in 5G‐VANET

With the rapid development of 5G and vehicular ad hoc network (VANET), the data fusion plays an increasingly important role in the driving behaviour assessment. However, the unreasonable distribution of conflicting evidence remains a significant issue for decision fusion based on evidence theory. By analysing the parameter information of driving behaviour recognition, this paper proposed a new weighted evidence combination approach to fuse the highly conflicting information. In short, the proposed combination method not only retains the excellent mathematical characteristics of Dempster's combination rule, but also fully considers the mutual relations between evidences and the influence of the characteristics of evidence body. Firstly, a new dissimilarity measure is put forward to quantify the conflict degree between the evidences. Furthermore, the uncertainty measure and internal conflict are adopted to determine the weight of each evidence. Based on the weighted averaging combination method, the reasonable combined results are obtained. According to the experimental results, the proposed method has better performance than the existing methods, and provides an effective solution for driving behaviour assessment.

Spectral Clustering of Mixed-Type Data

Cluster analysis seeks to assign objects with similar characteristics into groups called clusters so that objects within a group are similar to each other and dissimilar to objects in other groups. Spectral clustering has been shown to perform well in different scenarios on continuous data: it can detect convex and non-convex clusters, and can detect overlapping clusters. However, the constraint on continuous data can be limiting in real applications where data are often of mixed-type, i.e., data that contains both continuous and categorical features. This paper looks at extending spectral clustering to mixed-type data. The new method replaces the Euclidean-based similarity distance used in conventional spectral clustering with different dissimilarity measures for continuous and categorical variables. A global dissimilarity measure is than computed using a weighted sum, and a Gaussian kernel is used to convert the dissimilarity matrix into a similarity matrix. The new method includes an automatic tuning of the variable weight and kernel parameter. The performance of spectral clustering in different scenarios is compared with that of two state-of-the-art mixed-type data clustering methods, k-prototypes and KAMILA, using several simulated and real data sets.

Perbandingan Performansi Model pada Algoritma K-NN terhadap Klasifikasi Berita Fakta Hoaks Tentang Covid-19

During Covid-19 pandemic, there was various hoax news about Covid-19. There are truth-clarification platforms for hoax news about Covid-19 such as Jala Hoax and Saber Hoax which categorize into misinformation and disinformation. Classification of supervised learning methods is applied to carry out learning from fact labels. Dataset is taken from Jala Hoax and Saber Hoax as many as 559 data which are made into Class 1 (Misleading Content, Satire/Parody, False Connection), Class 2 (False Context, Imposter Content), Class 3 (Fabricated and Manipulated Content). K-Nearest Neighbor (K-NN) is used to classify categories of misinformation and disinformation. Dissimilarity measure Jaccard Distance is compared with Euclidean, Manhattan, and Minkowski and uses k-value variance in the K-NN to determine the performance comparison results for each test. Results of Jaccard Distance at the value of k = 4 get a higher value than other model with an accuracy 0.696, precision 0.710, recall 0.572, and F1-Score. Maximum results tend to be on label of the most data class in Class 1 (Misleading Content, Satire or Parody, False Connection) with a total of 58 correct data from 61 test data.

Racial segregation and mental health service use by older adults

Older adults living in racially segregated neighborhoods often lack access to mental health care. This study assessed the role of racial segregation in mental health service use and examined whether the relationship between segregation and mental health service use differs by race/ethnicity. We linked residential segregation data from the National Neighborhood Change Database to the 2015 Medical Expenditure Panel Survey. The sample included 4,023 adults aged 65 and older. We measured mental health service use as visit(s) to a mental health professional and/or use of prescribed medication for mental health (1=yes, 0=no) during the past year. Residential segregation was assessed using a combined measure of isolation (level of interaction with the same racial and ethnic group members) and dissimilarity (evenness of distribution of racial groups). Indices ranged from 0 (integrated) to 1 (segregated). We adjusted for age, sex, race/ethnicity, marital status, education, income, attitude toward health care, health insurance, and mental health status. Multiple logistic regression analyses showed that older adults living in more segregated counties were less likely to use a mental health service than those living in more integrated counties (OR=0.77, p=.04). The relationship did not differ by race/ethnicity. As expected, Blacks and Hispanics underused mental health services compared to Whites. The findings highlight that racial segregation limits access to mental health care. Practitioners and policy-makers should identify mental health needs and service use patterns to target services effectively and efficiently. Future research should explore the intersection of income and mental health care resources in segregated neighborhoods.

Order preserving hierarchical agglomerative clustering

Partial orders and directed acyclic graphs are commonly recurring data structures that arise naturally in numerous domains and applications and are used to represent ordered relations between entities in the domains. Examples are task dependencies in a project plan, transaction order in distributed ledgers and execution sequences of tasks in computer programs, just to mention a few. We study the problem of order preserving hierarchical clustering of this kind of ordered data. That is, if we have a<b in the original data and denote their respective clusters by [a] and [b], then we shall have [a]<[b] in the produced clustering. The clustering is similarity based and uses standard linkage functions, such as single- and complete linkage, and is an extension of classical hierarchical clustering. To achieve this, we develop a novel theory that extends classical hierarchical clustering to strictly partially ordered sets. We define the output from running classical hierarchical clustering on strictly ordered data to be partial dendrograms; sub-trees of classical dendrograms with several connected components. We then construct an embedding of partial dendrograms over a set into the family of ultrametrics over the same set. An optimal hierarchical clustering is defined as the partial dendrogram corresponding to the ultrametric closest to the original dissimilarity measure, measured in the p-norm. Thus, the method is a combination of classical hierarchical clustering and ultrametric fitting. A reference implementation is employed for experiments on both synthetic random data and real world data from a database of machine parts. When compared to existing methods, the experiments show that our method excels both in cluster quality and order preservation.

Rotation transformation-based selective ensemble of one-class extreme learning machines

Extreme learning machine (ELM) possesses merits of rapid learning speed and good generalization ability. However, due to the random initialization of connection weights, the network outputs of ELM are usually unstable. Similar to ELM, one-class ELM (OCELM) also has the disadvantage of output instability. To enhance the stability and generalization performance of OCELM, a selective ensemble of OCELMs based on rotation transformation is proposed. First, principal component analysis (PCA)-based rotation transformation is utilized to construct different transformed training sets. Furthermore, several component OCELMs are trained independently on these training sets. Second, a dissimilarity measure based on angle cosine is used to evaluate the dissimilarity between each pair of OCELMs. The diversity of each component OCELM in the obtained ensemble can be further achieved. Thereafter, the component OCELMs with lower value of diversity are removed from the original ensemble. Finally, the voting strategy is utilized to determine that testing samples belong to the target class or the non-target class. Experimental results on 15 UCI benchmark data sets and one handwritten digit data set show that the proposed method is superior to its related approaches.

A class-specific metric learning approach for graph embedding by information granulation

Graphs have gained a lot of attention in the pattern recognition community thanks to their ability to encode both topological and semantic information. Despite their invaluable descriptive power, their arbitrarily complex structured nature poses serious challenges when they are involved in learning systems. Typical approaches aim at building a vectorial representation of the graph in a suitable embedding space by leveraging on the selection of relevant prototypes that enable the use of common pattern recognition methods. An emerging paradigm able to synthesize prototypes in a data-driven fashion can be found in Granular Computing. Nonetheless, these methods often require a core dissimilarity measure defined directly in the graph domain that usually relies on a set of suitable parameters which are heavily problem-dependent. The automatic selection of these parameters is of utmost importance for building embedding spaces able to preserve the semantic contents between the structured and vector domains. In this paper, we propose an evolutionary-based approach for learning multiple dissimilarity measures tailored on each of the problem-related classes for the classification problem at hand. The learnt class-specific metrics contribute in synthesizing prototypes with high informative content related to each class by means of a Granular Computing approach. Such prototypes induce an embedding space where the graph classification can take place with common pattern recognition techniques for vector data. Tests conducted on publicly available datasets corroborate the effectiveness of the proposed approach both in terms of learning performances and interpretability of the model, as measured by the classification accuracy and number of meaningful prototypes considered in the synthesized model.

Novel AQM analysis approach based on similarity and dissimilarity measures of interval set for multi-expert multi-criterion decision making

Interval sets, as a particular knowledge representation, are composed of the lower set and the upper set to represent more general uncertain qualitative information. In this paper, we aim at investigating multi-expert multi-criterion decision making (MEMCDM) based on the interval set information. In the process of MEMCDM, by comparing positive, negative and boundary regions of interval sets, we firstly propose the similarity and dissimilarity measures of interval set to describe the closeness and deviation between interval sets. Secondly, with the aid of dissimilarity, we determine the criterion weight by combining the dissimilarity difference of the judgement matrix and the result of the maximum deviation of dissimilarity. For dealing with the hesitant problem of experts, we design transformation algorithm, which provides technical support for transforming experts' evaluation tables into an interval set information table. In view of the wide applicability of alternative queuing method (AQM), we extend AQM based on 0−1 precedence relationship matrix to address MEMCDM. The 0−1 precedence relationship matrix of AQM exists the incomparable situation, which can lead to the indiscernible alternatives. To reduce indiscernible alternatives and increase efficiency, we design a possibility degree of interval sets and deeply construct precedence relationship matrix. Further, we improve AQM by using possibility degree matrix and aggregating precedence relationship matrix on each alternative by weight arithmetic average (WAA). Finally, we use an example and simulation experiment of former e-commerce platform selection to elaborate and validate our proposed method.

New Method for Sequence Similarity Analysis Based on the Position and Frequency of Statistically Significant Repeats

Background: The analysis of DNA nucleotide sequence similarity among different species is crucial in identifying their functional, structural or evolutionary relationships. The number of bioinformatics tools designed to perform the similarity analysis of nucleotide sequences has been growing rapidly. According to the current literature, alignment-free methods have not been performed on repetitive nucleotide sequence of different lengths. Objective: To develop a new algorithm for determining sequence characteristics and similarity based on statistically significant repetitive elements of different lengths, which are located in analyzed sequences. Methods: This paper presents Repeats-Position/Frequency method (R-P/F method), for determining nucleotide sequence similarity which takes into consideration statistically significant repetitive parts of analyzed sequences. It is based on information theory and the fact that both position and frequency of repeated sequences are not expected to occur with the identical presence in a random sequence of the same length. Nucleotide sequences are presented in rn-dimensional vector space and their hierarchy is constructed by applying hierarchical clustering algorithm. Results: R-P/F method has been validated on multiple data sets of nucleotide sequences and compared with results obtained from alignment-based algorithms BLAST and Clustal Omega, and multiple wellestablished alignment-free dissimilarity measures. Presented method provides results comparable with other commonly used methods focused on resolving the same problem, with the novel view on the used repetitive parts of sequences in these calculations. Conclusion: The presented, novel algorithm for calculating sequence similarity measure is effective in discovering relationships among the sequences and makes a powerful and complementary addition to existing sequence similarity methods.

Proximal and distal movement patterns during a graphomotor task in typically developing children and children with handwriting problems

BackgroundTherapists specializing in handwriting difficulties in children often address motor problems including both proximal and distal movements in the upper extremity. Kinematic measures can be used to investigate various aspects of handwriting. This study examined differences in movement patterns in proximal and distal joints of the upper extremity during graphomotor tasks between typically developing children with and without handwriting problems. Additionally, it explored relationships between movement patterns, speed, and legibility of writing.MethodsForty-one children, aged 7–11 years, were assessed with the Aleph Aleph Ktav Yad Hebrew Handwriting assessment and the Beery Test of Visual Motor Integration and, based on their scores, were divided into a research group (with handwriting difficulties) and a control group (without handwriting difficulties). Upper extremity joint movement patterns were analyzed with a motion capture system. Differences in the quality of shapes traced and copied on a graphics tablet positioned horizontally and vertically were compared. Between-group differences and relationships with speed and legibility were analyzed.ResultsIn both groups, there was greater movement in the distal compared to the proximal joints, greater movement when performing the task in a horizontal compared to a vertical plane, and greater movement when tracing than copying. Joint movements in the arm executed scaled-down versions of the shapes being drawn. While the amount of joint displacement was similar between groups, children in the research group showed greater dissimilarity between the drawn shape and the shape produced by the proximal joints. Finally, the drawing measure on the tablet was a significant predictor of legibility, speed of writing, visual motor integration and motor coordination, whereas the dissimilarity measure of joint movement was a significant predictor of speed of writing and motor coordination.ConclusionsThis study provides support for the role of the distal upper extremity joints in the writing process and some guidance to assist clinicians in devising treatment strategies for movement-related handwriting problems. While we observed differences in proximal joint movements between the children with and without handwriting difficulties, the extent to which they are responsible for the differences in drawing quality remains to be determined. Further studies should use a similar methodology to examine additional tasks such as drawing shapes of varying sizes.