Sum Of Euclidean Distances Research Articles

Deep corner prediction to rectify tilted license plate images

Skewness and obliqueness of vehicle plate images influence license plate recognition. The more tilted plate images are, the harder the recognition task is. To this end, if plate images are preprocessed to be aligned and rectified, the recognition performance would improve. We propose deep neural network models that can locate four corner plate positions, which can then be used to perform the perspective transformation that can be used to rectify plates. Such a transformation is called homography. The models consist of two sequential parts: a feature extraction part having convolution and a regression part with fully connected layers. The models are open in the sense that the feature extraction part can host other well-known models such as Mobilenet as long as they have the feature capture capability. We devise a loss function as the sum of Euclidean distance between predicted coordinates and ground truth and discuss image augmentation schemes. The experiment results show that the models with well-known object detection models are able to predict corner positions with relatively high precision.

Research on the Optimal Aggregation Method of Decision Maker Preference Judgment Matrix for Group Decision Making

The main focus of this paper is to present a new aggregation method of judgment matrices, which is based on the optimal aggregation model and the efficient aggregation algorithm. The reciprocal elements in the decision maker judgment matrices are mapped into the corresponding points on the two-dimensional coordinates. We can express the differences between different decision makers' preferences by the Euclidean distance among these points. We use the plant growth simulation algorithm (PGSA) to obtain the optimal aggregation points which can reflect the opinions of the entire decision makers group. The aggregation matrix of decision maker preference is composed of these optimal aggregation points and the consistency test has been passed. Compared with the weighted geometric mean method (WGMM) and minimum distance method (MDM), the sum of Euclidean distances from the aggregation points to other given points in this paper is minimal. The validity and rationality of this method are also verified by the analysis and comparison of examples, which provides a new idea to solve the group decision making (GDM) problems.

Multimode Process Monitoring Based on Geodesic Distance

A novel monitoring strategy is proposed for multimode process in which mode clustering and fault detection based on geodesic distance (GD) are integrated. To start with, the empowered adjacency matrix of normalized training dataset is obtained and improved Dijkstra algorithm (IDA) is utilized to calculate the geodesic distance between each sample data so as to characterize the shortest distance of the nonlinear data within local areas accurately. Next, GD matrix algorithm is presented as an optimal clustering solution for a multimode process dataset. Then, the GDS model is established in each operating mode. Monitoring statistics based on the power of geodesic distance are structured based on square sum of Euclidean distances. Once the test data is detected as fault data, mode location based on deviation coefficient is conducted to narrow the scope of the inspection fault. Finally, the validity and usefulness of the proposed GDMPM monitoring method are demonstrated through the Tennessee Eastman (TE) benchmark process.

Location of supplementary feed and water troughs on the sward affects movement and spatial distribution of Brahman cattle (Bos indicus)

The grazing dynamics of animals differ depending on whether they are raised on rangeland or sward areas. Grazing patterns of cattle raised on rangeland can be modified by the location of supplement feed and water troughs. However, no information about the use of this strategy is available for swards. Thus, the effects of the location of supplementary feed and water troughs in small (7500 m2) irrigated swards on movement, behavior and distribution were studied in a herd of 15 Brahman cows. The herd grazed on five swards in rotation, for seven days on each sward, so that each sward then had 28 days of rest. There were four rotations, giving four replicates of each of five treatments. For each rotation, one of the following treatments was randomly assigned to each sward. Supplementary feed and water troughs were: T1 in the same corner of the sward; T2 separate, each in the middle of one of the shorter sides of the sward; T3 separate in diagonally opposite corners; T4 separate in adjacent corners; T5 together in the sward center. The behavior and location of each cow was registered on a daily basis, every 2 h from 9:00 to 15:00 h, 7 days/week, using instantaneous scan sampling during the 140 days that the experiment lasted. Total distance traveled of each cow (i.e. the sum of Euclidean distances between the four subsequent positions of each cow within each day) was longer in T2 and T3 than in T5 (159.8, 162.5 vs 119.5 m respectively; p = 0.006), with the rest of the treatments showing intermediate values. The distance to the nearest cow was longer in T1 vs. T2 and T3 (6.2 vs 4.0 and 4.7 m, respectively; p = 0.007). Similarly, the herd home range was greater in T1 vs. T2 (792.6 vs. 574.7 m2, respectively; p = 0.01). Regardless of the treatment, social disruption occurred on day 1, which gradually decline through the week of grazing. The results show that the location of supplementary feed and water troughs affects the movement and cattle distribution in small (<1 ha) irrigated swards. This might have practical applications in the design of grazing strategies and in the animal welfare of cattle maintained on small swards.

Kernel-based hard clustering methods with kernelization of the metric and automatic weighting of the variables

This paper presents kernel-based hard clustering methods with kernelization of the metric and automatic weighting of the variables. The proposed methodology is supported by the fact that a kernel function can be written as a sum of kernels evaluated separately on each variable. Thus, in the proposed algorithms dissimilarity measures are obtained as sums of Euclidean distances between patterns and centroids computed individually for each variable by means of kernels. The main advantage of this approach over the conventional approach is that it allows the use of kernelized adaptive distances, which are suitable to learn the weights of the variables dynamically, improving the performance of the algorithms. Moreover, various partition and cluster interpretation tools are introduced. Experiments with a number of benchmark datasets corroborate the usefulness of the proposed algorithms and the merit of the partition and cluster interpretation tools.

Kernel fuzzy c-means with automatic variable weighting

This paper presents variable-wise kernel fuzzy c-means clustering methods in which dissimilarity measures are obtained as sums of Euclidean distances between patterns and centroids computed individually for each variable by means of kernel functions. The advantage of the proposed approach over the conventional kernel clustering methods is that it allows us to use adaptive distances which change at each algorithm iteration and can either be the same for all clusters or different from one cluster to another. This kind of dissimilarity measure is suitable to learn the weights of the variables during the clustering process, improving the performance of the algorithms. Another advantage of this approach is that it allows the introduction of various fuzzy partition and cluster interpretation tools. Experiments with synthetic and benchmark datasets show the usefulness of the proposed algorithms and the merit of the fuzzy partition and cluster interpretation tools.

Comparing Frei-Chen & Sobel Edge Detector in Face Emotion Recognition with Euclidean Distance and LVQ Network

In this paper, to increase the execution speed in face emotion recognition instead Sobel edge detector of Frei-Chen edge detector is used. The advantages Frei-Chen method are accurate and better detection, low overhead, detect corners beside with edges and less sensitive to noise than other edge detector. The Frei-Chen algorithm works on a part of image with size 3*3 similarly like the Sobel filter but instead of two masks of 4 masks are used. Of important characteristics this filter can be pointed to 4 masks of unique. For edge detection suitable masks are selected and selected mask is applied on image. This filter such as sobel filter can be used for multi-channel images. Furthermore we know Facial expression gives important information about emotion of a person. Face emotion recognition is one of important issues that widely attended in recent years. It can be used in areas of security, control, entertainment and machine vision. Nowadays for emotion recognition use of science image processing, speech signal processing, gesture signal processing and physiological signal processing. Use of image processing science than other methods can be very useful and helpful. Our proposal uses of an objective function for minimization of sum of Euclidean distance from the given points to the eye and lip curve that PSO algorithm will be used to optimize objective function. We recommend use of ellipse form as eye and lip in face emotion recognition. Face emotion recognition process like presented previous papers involves three stages pre-processing, feature extraction and classification. One of biggest problems in classification of emotions is overlap in range of values. To increase success rate in face emotion recognition we in this paper for another experience of neural networks use of LVQ neural network. We also show experiments face emotion recognition with Sobel filter and Frei-Chen filter. The results show that using Frei-Chen filter against Sobel filter reduces run time. Keywords: Projection Profile, Particle Swarm Optimization (PSO), Euclidean Distance Measurement LVQ Network and Frei-Chen Edge Detector.

Nanostructural ZnO based coplanar gas sensor arrays from the injection of metal chloride solutions: Device processing, gas-sensing properties and selectivity in liquors applications

A new coplanar gas sensor array of ZnO was fabricated by injecting different volumes of 0.01 mol/L AlCl 3, CuCl 2, SnCl 4, TiCl 4, PdCl 2 and WCl 6 solutions and post treatment to improve the selectivity in liquor. The new four-sensor array was optimized by maximizing Sum of Euclidean distances (SED) of the gases of liquor. The morphology of films was characterized by field-emission scanning electron microscopy (FESEM). The results showed that ZnO nanostructures were formed on the surface of films after the injecting process. Nanowires, 100 nm in diameter and 3 μm in length, were found when the solutions included AlCl 3, CuCl 2, SnCl 4 and PdCl 2. However, when the injecting solution was TiCl 4, nanotowers with 500 nm in diameter and 4 μm in length appeared. No new structures appeared when the WCl 6 solution was injected. The results of testing gases of liquor revealed that the injecting process could improve the response of the sensors array effectively. Through calculating the value of the SED, the best array was confirmed whose SED value would be three times the worst one.

Optimal matching between spatial datasets under capacity constraints

Consider a set of customers (e.g., WiFi receivers) and a set of service providers (e.g., wireless access points), where each provider has a capacity and the quality of service offered to its customers is anti-proportional to their distance. The Capacity Constrained Assignment (CCA) is a matching between the two sets such that (i) each customer is assigned to at most one provider, (ii) every provider serves no more customers than its capacity, (iii) the maximum possible number of customers are served, and (iv) the sum of Euclidean distances within the assigned provider-customer pairs is minimized. Although max-flow algorithms are applicable to this problem, they require the complete distance-based bipartite graph between the customer and provider sets. For large spatial datasets, this graph is expensive to compute and it may be too large to fit in main memory. Motivated by this fact, we propose efficient algorithms for optimal assignment that employ novel edge-pruning strategies, based on the spatial properties of the problem. Additionally, we develop incremental techniques that maintain an optimal assignment (in the presence of updates) with a processing cost several times lower than CCA recomputation from scratch. Finally, we present approximate (i.e., suboptimal) CCA solutions that provide a tunable trade-off between result accuracy and computation cost, abiding by theoretical quality guarantees. A thorough experimental evaluation demonstrates the efficiency and practicality of the proposed techniques.

Multilevel Assessment of Fish Species Traits to Evaluate Habitat Degradation in Streams of the Upper Midwest

AbstractWe used species traits to examine the variation in fish assemblages for 21 streams in the Northern Lakes and Forests Ecoregion along a gradient of habitat disturbance. Fish species were classified based on five species trait‐classes (trophic ecology, substrate preference, geomorphic preference, locomotion morphology, and reproductive strategy) and 29 categories within those classes. We used a habitat quality index to define a reference stream and then calculated Euclidean distances between the reference and each of the other sites for the five traits. Three levels of species trait analyses were conducted: (1) a composite measure (the sum of Euclidean distances across all five species traits), (2) Euclidean distances for the five individual species trait‐classes, and (3) frequencies of occurrence of individual trait categories. The composite Euclidean distance was significantly correlated to the habitat index (r = −0.81; P = 0.001), as were the Euclidean distances for four of the five individual species traits (substrate preference: r = −0.70, P = 0.001; geomorphic preference: r = −0.69, P = 0.001; trophic ecology: r = −0.73, P = 0.001; and reproductive strategy: r = −0.64, P = 0.002). Although Euclidean distances for locomotion morphology were not significantly correlated to habitat index scores (r = −0.21; P = 0.368), analysis of variance and principal components analysis indicated that Euclidean distances for locomotion morphology contributed to significant variation in the fish assemblages among sites. Examination of trait categories indicated that low habitat index scores (degraded streams) were associated with changes in frequency of occurrence within the categories of all five of the species traits. Though the objectives and spatial scale of a study will dictate the level of species trait information required, our results suggest that species traits can provide critical information at multiple levels of data analysis.

Multivariate multiple regression prediction models: a Euclidean distance approach.

An extension of a multiple regression prediction model to multiple response variables is presented. An algorithm using least sum of Euclidean distances between the multivariate observed and model-predicted response values provides regression coefficients, a measure of effect size, and inferential procedures for evaluating the extended multivariate multiple regression prediction model.

A Newton Acceleration of the Weiszfeld Algorithm for Minimizing the Sum of Euclidean Distances

The Weiszfeld algorithm for continuous location problems can be considered as an iteratively reweighted least squares method. It generally exhibits linear convergence. In this paper, a Newton algorithm with similar simplicity is proposed to solve a continuous multifacility location problem with the Euclidean distance measure. Similar to the Weiszfeld algorithm, the main computation can be solving a weighted least squares problem at each iteration. A Cholesky factorization of a symmetric positive definite band matrix, typically with a small band width (e.g., a band width of two for a Euclidean location problem on a plane) is performed. This new algorithm can be regarded as a Newton acceleration to the Weiszfeld algorithm with fast global and local convergence. The simplicity and efficiency of the proposed algorithm makes it particularly suitable for large-scale Euclidean location problems and parallel implementation. Computational experience suggests that the proposed algorithm often performs well in the absence of the linear independence or strict complementarity assumption. In addition, the proposed algorithm is proven to be globally convergent under similar assumptions for the Weiszfeld algorithm. Although local convergence analysis is still under investigation, computation results suggest that it is typically superlinearly convergent.

On the Euclidean assignment problem

The Euclidean assignment problem is a special case of bipartite matching and can be described as follows. For given sets R and B each containing n points in the unit square, find a bijection p: R → B that maximizes (minimizes) the sum of Euclidean distances between pairs of points assigned to each other. We describe a linear time heuristic which solves the maximization case with absolute error of order O(n 5 6 ) for any problem instance. If R and B are uniformly distributed in the unit square it is further shown that the maximal value z satisfies z/ n → (√2 + log(1 + √2))⧸3 almost surely as n → ∞. In this case the heuristic is asymptotically optimal. The approach can also be applied to the minimization case but the results do not seem as promising.