Euclidean Distance Formula Research Articles

Unbalanced Data Clustering with K-Means and Euclidean Distance Algorithm Approach Case Study Population and Refugee Data

There is a lot of data that does not have a pattern and unbalanced that is difficult to classify, such as the total population of each country in the world is very varied especially when compared with the number of refugees from each of these countries, China and India numbered more than 2 billion people but the number of refugees is only 0, 01%, while Syria around 70% of the 18 million more residents are refugees. By using the K-Means algorithm, we can group countries that have similar characteristics of population and number of refugees, the average percentage of refugees to the population in each cluster is the character of the cluster. The methodology used in this study are: measures the distance of the data using the Euclidean distance formula, runs the K-Means algorithm, calculate the percentage value of each cluster and find conclusions from the characteristics of the clusters formed. We found how machine learning made a pattern of data without political and social issues, the result is K-Means describing machine learning can grouped every country in cluster that make sense.

Optimization of distance formula in K-Nearest Neighbor method

K-Nearest Neighbor (KNN) is a method applied in classifying objects based on learning data that is closest to the object based on comparison between previous and current data. In the learning process, KNN calculates the distance of the nearest neighbor by applying the euclidean distance formula, while in other methods, optimization has been done on the distance formula by comparing it with the other similar in order to get optimal results. This study will discuss the calculation of the euclidean distance formula in KNN compared with the normalized euclidean distance, manhattan and normalized manhattan to achieve optimization results or optimal value in finding the distance of the nearest neighbor.

Multi-spectral image change detection based on single-band iterative weighting and fuzzy C-means clustering

ABSTRACT In the present study, an improved iteratively reweighted multivariate alteration detection (IR-MAD) algorithm was proposed to improve the contribution of weakly correlated bands in multi-spectral image change detection. In the proposed algorithm, each image band was given a different weight through single-band iterative weighting, improving the correlation between each pair of bands. This method was used to obtain the characteristic difference in the diagrams of the band that contain more variation information. After removing Gaussian noise from each feature-difference graph, the difference graphs of each band were fused into a change-intensity graph using the Euclidean distance formula. Finally, unsupervised fuzzy C-means (FCM) clustering was used to perform binary clustering on the fused difference graphs to obtain the change detection results. By comparing the original multivariate alteration detection (MAD) algorithm, the IR-MAD algorithm and the proposed IR-MAD algorithm, which used a mask to eliminate strong changes, the experimental results revealed that the multi-spectral change detection results of the proposed algorithm are closer to the actual value and had higher detection accuracy than the other algorithms.

An Energy-Balanced Trust Cloud Migration Scheme for Underwater Acoustic Sensor Networks

As a candidate trust management scheme, trust models based on the cloud theory are always taken into account when detecting malicious attacks in Underwater Acoustic Sensor Networks (UASNs). To evaluate the trust values of nodes accurately, the evidence of trust ought to be collected frequently. As a result, continual trust update results in excessive energy consumption or premature death of some sensor nodes that are close to the trust cloud node. To address the above issues, in this paper, we propose an Energy-balanced Trust Cloud Migration scheme (ETCM) for UASNs, which consists of Destination Node Determination (DND), trust cloud migration and trust cloud update. Particularly, DND is performed hierarchically to obtain the destination node for trust cloud migration by selecting the candidate destination clusters, determining the destination cluster and the destination node, respectively. First, the candidate destination clusters are selected based on the distribution for the overall residual energy in UASNs using the simulated annealing algorithm. Then, an indicator of Cluster Ability (CA) is proposed to seek the destination cluster. Particularly, to calculate CA, the improved standardized Euclidean distance formula is employed to evaluate the connectivity between clusters and their neighboring clusters. Finally, on the basis of the defined node density reachability and the residual energy, the Node Ability (NA) is presented to indicate the capacity of nodes for trust cloud storage, calculation and update. The destination node in the destination cluster can be determined as the new trust cloud node using the NA. Simulation results demonstrate that the proposed ETCM scheme can balance energy consumption, increase node survival ratio and prolong lifetime effectively.

Nearest Excellent Potential Location Using Distance Algorithm

This study aims to find the proper distance calculation method that will be applied to the Sidoarjo on Hands (SoH) application. This study was conducted by comparing three distance algorithms namely Euclidean Distance, Manhattan Distance, and Haversine Formula. The results showed that the Euclidean Distance method was the proper method because this method had has the smallest Mean Absolute Deviation (MAD) with 1.71 in amount.

Mining and analyzing process similarity of product module for DPIPP based on PLM database

A distributed parametrized intelligent product platform (DPIPP) on basis of product lifecycle management database has been proposed to reveal the interrelationships between product attributes (i.e., structure, function or process) in recent years. Product modules in DPIPP are classified according to composition and structure of products. Components belonging to different product modules may have an identical or similar process route and could be manufacture with the same type of equipment. Mining and analysing the process similarity of product modules can effectively reduce production cost and improve production efficiency. In this paper, a novel product data mining approach with an improved Euclidean distance formula is proposed to research the product module process similarity, which aims to illustrate the effect of the structural change on the product process, then provide theoretical support for improving production patterns and reducing production costs to adapt to mass customization. The feasibility and effectiveness of the method are verified via the analysing of the process similarities among three different types of valves.

Why We Should Stop Using the Kogut and Singh Index

The Kogut and Singh (J Int Bus Stud 19(3):411–432, 1988) index is the most widely used construct to measure cultural distance in international business and management research. We show that this index is incorrectly specified and captures the squared cultural distance. This inaccuracy is problematic because it means that the empirical findings on the effects of cultural distance presented in different strands of international business research are likely to be misleading. We specify the correct form of the distance measure based on the Euclidean distance formula and demonstrate the implications of using the incorrectly specified Kogut and Singh (1988) index.

Multi-Spectral Image Change Detection Based on Band Selection and Single-Band Iterative Weighting

Iteratively reweighted multivariate alteration detection algorithm has the phenomena of broken patches, much noise, and small change area that are difficult to detect, and the overall detection rate is low. In order to solve this problem, this paper proposes a multi-spectral image change detection algorithm based on band selection and single-band iterative weighting. Because the change information of the multi-spectral image is concentrated in some bands, the background and noise information of the rest bands are more, which may have a negative effect on the final result. Therefore, the band with more change information is selected first, and the iterative weighting of a single band can better suppress the noise and background information, so as to obtain a higher band correlation and facilitate the extraction of change information. This method is used to obtain the characteristic difference graph of the selected band with more change information. After Gaussian denoising of each characteristic difference graph, the Euclidean distance formula is used to fuse the difference graph of each band into a change intensity graph. Finally, the unsupervised $k$ -means clustering algorithm is used to perform binary-valued clustering on the fused difference graph to obtain the change detection results. As a practical application, the superior performance of our proposed method was demonstrated through a large number of comparative tests.

A New Transfer Learning Algorithm in Semi-Supervised Setting

Transfer Learning is an effective method of dealing with real-world problems where the training and test data are drawn from different distributions. Transfer learning methods use a labeled source domain to boost the task in a target domain that may be unsupervised or semi-supervised. However, the previous transfer learning algorithms use Euclidean distance or Mahalanobis distance formula to represent the relationships between instances and to try and capture the geometry of the manifold. In many real-world scenarios, this is not enough and these functions fail to capture the intrinsic geometry of the manifold that the data exists in. In this paper, we propose a transfer learning framework called Semi-Supervised Metric Transfer Learning with Relative Constraints (SSMTR), that uses distance metric learning with a set of relative distance constraints that capture the similarities and dissimilarities between the source and the target domains better. In SSMTR, instance weights are learned for different domains which are then used to reduce the domain shift while a Relative Distance metric is learned in parallel. We have developed SSMTR for classification problems as well, and have conducted extensive experiments on several real-world datasets; particularly, the PIE Face, Office-Caltech, and USPS-MNIST datasets to verify the accuracy of our proposed algorithm when compared to the current transfer learning algorithms.

An Effective Method to Safeguard Cyber Security by Preventing Malicious Data

In order to ensure the information security of a network, network security devices have been widely deployed in the information and communication network. Based on the monitoring data collected by network security equipment, network security administrators analyze whether there is an attacking incident or abnormal situation in the current network environment. However, if the original monitoring data collected by network security equipment is tampered with by the attacker, then network security administrators will make a wrong judgment and delay the best time to take protective actions. Therefore, the reliability and authenticity of data generated by network security devices are of the utmost importance. In this paper, we first define a revised Euclidean distance formula for the D-S evidence theory and propose a dual test method for the authenticity of data based on algebra statistics and geometric trends, detecting any malicious tampering on these monitoring data. Utilizing a web application firewall (WAF) device, we carry out a series of experiments to verify the proposed method.

A fuzzy-based failure mode effect and criticality analysis of solar photovoltaic systems

In this research work, a Failure Mode and Effect Analysis (FMEA) has been applied to a Solar Photovoltaic (SPV) system that consists of a photovoltaic module, an inverter, connecting cable, battery and a charge controller. The FMEA is a tool that can gauge the possible failure mode(s) in order to determine the probability of the failure. The traditional (crisp) method of FMEA ranks all failure modes using Risk Priority Number (RPN) according to severity order. However, traditional FMEA has several disadvantages (like chance of error, human intelligence, etc.) which may be overcome by integrating them with artificial intelligence techniques. Therefore, fuzzy logic is implemented to assess and ranks associated with each failure mode of different subassemblies of SPV system. Ranking of all failure modes has been done on the basis of fuzzy RPN, which is calculated by weighted Euclidean distance formula and centroid defuzzification method. It is expected that this work will help the designers and engineers by making them aware of the qualitative analysis of SPV systems.

Strategic consensus between functions and the role of supply chain technology as moderator

Purpose: This study aims to identify whether the degree of fit of the correlation between high supply chain and manufacturing strategy will result in a better performance.Design/methodology/approach: Strategic alignment test between the functions uses 102 SMEs in Yogyakarta as, Indonesia with purposive sampling technique. The data are collected by distributing questionnaires to the companies that qualify the criteria of the sample, respondent target are procurement manager, production and IT.Findings: Samples are grouped into two ideal types of strategies used mean split technique. 53 SMEs adopt ASCS (Agile Supply Chain Strategy) and 49 SMEs adopt LSCS (Lean Supply Chain Strategy). Two of the strategy groups have a low value of misfit score; it means that the degree of fit between supply chain strategy and manufacturing strategy is high. The result of simple regression test by using one side technique shows that a regression coefficient values is negative both in LSCS and ASCS group, but the hypothesis test is only proven on ASCS group while LSCS group is not significant.Research limitations/implications: (1) The empirical finding of bivariate fit model test encourage a research space to explore the other contingent variable besides manufacturing strategy. For example, business and information technology strategy; (2) The measurement of the company performance becomes the objective of the success of the alignment of supply chain strategy with the contingent variable which should be specified using the performance variable of the supply chain.Originality/value: The use of Euclidean distance formula is expected to cover the technical limitations of contingency test by using interaction approach between the complex variables; the value of misfit score reflects the extent to which program alignment between the company functions.

Assessing the Correlation between Skeletal and Corresponding Soft-Tissue Equivalents to Determine the Relationship between CBCT Skeletal/Dental Dimensions and 3D Radiographic Soft-Tissue Equivalents.

Objective Compare measurements of skeletal and dental areas on the CBCT to the corresponding soft-tissue measures taken from a 3D Facial Scanner. Methods 30 patients with CBCT and 3D Facial scanner photos were selected from the orthodontic program database. 30 different distance measurements were obtained from CBCT and facial scan. OrthoInsight software was used to obtain the measurements from the facial scan images, and AVIZO software was used for corresponding CBCT landmarks. The Euclidean distance formula was used to determine the distances for the corresponding x, y, and z coordinates of the CBCT. Reliability for CBCT and Facial Scanner was completed by calculating 30 distances for 10 patients, 3 times. Once reliability was determined, all 30 distances were calculated once for CBCT and facial scanner on each patient and descriptive statistics and paired t-test were applied. Results All distances measured presented excellent reliability, the lowest one being the left eye width for the facial scanner (ICC 0.847). The landmark with the highest mean error on the CBCT was 2.0 ± 1.6 mm on the z-axis for the spinal level landmark. The Facial Scanner's largest mean measurement error was 1.5 ± 0.9 mm for the distance of the left corner of the mouth to gonion. All data except width between outer eye corners were statistically significant (p < 0.05). The average differences between facial scan and CBCT measurements ranged between 0.77 mm (left canine to cheekbone) to 26.94 mm (left subnasale to gonion) and are thus comparable. All measurements show a reasonable standard deviation between 2.57 mm (left eye width) to 9.91 mm (left gnathion to EAM). Conclusion Distances obtained from CBCT and facial scan present mild differences giving the perspective of a relationship between them. Understanding this difference and relationship can make it plausible to expect certain underlying skeletal distances under soft-tissue structures.

Underwater Self Deployment of Wireless Sensors for Maximum Coverage and Connectivity using K-Means Clustering

By virtue of abundant research being executed in terrestrial wireless sensor networks, we get enlightened about the different advantages of using wireless sensors and implemented these wireless sensors in underwater to probe the area below the sea for its various applications. The most crucial task in underwater 3D space is the node deployment such that sensors can cover the maximum area while simultaneously maintaining the connectivity with the base station. Due to the advantages of self deployment where no pre calculations and no human interventions are needed, we proposed a distributed move restricted self deployment underwater wireless sensor network. The main emphasis is on maximizing the coverage area by the sensor nodes and simultaneously maintaining the connectivity with the base station. Firstly, the maximum coverage has achieved by removing the interference between the sensor nodes which minimize the coverage overlap and thus more area can be covered which improves the network coverage. Then by using K-Means clustering, all the sensors nodes were divided into clusters, having one centroid for each cluster. Further all these centroids have been interconnected and then by finding the centroid which is nearest to the sink by Euclidean distance formula, we connect it to the sink.

Harnessing mass spectra data using KNN principle

A high level of expertise, rigorous algorithms and methods are needed to adequately mine and harness Mass Spectrometer generated data due to its unique nature and structure. Hitherto, peptide ions are matched with theoretical results and/or public databases in order to identify expressed proteins in analyzed protein source samples, but this is done on a spectrum by spectrum basis. In this study, we present a mechanism that extends the principle of K-nearest neighbor algorithm for mining pools of mass spectrometer saliva data towards discovering and characterizing patterns for diagnosing Alzheimer's disease. The methodology discusses feature selection by correlation matrix, matrix to vector decomposition, an extension of Euclidean distance formula, and successfully classifies donor samples into the three stages of Alzheimer's disease with over 85% accuracy without collaborating clinical records.

Detecting and Identifying Industrial Gases by a Method Based on Olfactory Machine at Different Concentrations

Gas sensors have been widely reported for industrial gas detection and monitoring. However, the rapid detection and identification of industrial gases are still a challenge. In this work, we measure four typical industrial gases including CO2, CH4, NH3, and volatile organic compounds (VOCs) based on electronic nose (EN) at different concentrations. To solve the problem of effective classification and identification of different industrial gases, we propose an algorithm based on the selective local linear embedding (SLLE) to reduce the dimensionality and extract the features of high-dimensional data. Combining the Euclidean distance (ED) formula with the proposed algorithm, we can achieve better classification and identification of four kinds of gases. We compared the classification and recognition results of classical principal component analysis (PCA), linear discriminate analysis (LDA), and PCA + LDA algorithms with the proposed SLLE algorithm after selecting the original data and performing feature extraction. The experimental results show that the recognition accuracy rate of the SLLE reaches 91.36%, which is better than the other three algorithms. In addition, the SLLE algorithm provides more efficient and accurate responses to high-dimensional industrial gas data. It can be used in real-time industrial gas detection and monitoring combined with gas sensor networks.

BTS (Base Transceiver Station) Route and Site Search Application Using Speech To Text on Android Devices

in order to implement the technology development of a BTS (Base Transceiver Station) device from a project a vendor and operator. Take advantage of the services provided by the Android smartphone, namely Google maps along with voice, namely speech to text, can further help the performance of a survey team at the sub party contractor (subcon) / third part. The results of application testing and analysis show that speech to text testing for noise is: average for distances of 10cm and 35cm with a noise level of 63 dB as much as 79% success, on average for distances of 10cm and 35cm with a noise level of 70 dB as much as 75% success, average for the distance 10cm and 35cm with a noise level of 75 dB for 72% success. Testing time when opening Maps from the text to maps results, it is found that the speed of male voice is faster, namely 1 minute 51 seconds and 1 minutes 68 seconds than women. Finally, testing the comparison of the distance between the application and the calculation through the Euclidean Distence formula, the average distance obtained in the application is 3.65345287 km and the calculation result with the Euclidean Distance formula is 3,66535889 km.

Eye in the Sky: Investigating Spatial Performance Following Perspective Change

Unmanned Aerial Systems (UASs) are becoming more prevalent in civilian use, such as emergency response and public safety. As a result, UASs pose issues of remote perception for human users (Eyerman, 2013). The purpose of this experiment was to test the effects of combining aerial and ground perspectives on spatial judgments of object positions in an urban environment. Participants were shown randomly ordered image pairs of aerial and ground views of objects in a virtual city and were asked to make judgments about where a missing object was in the second image of the pair. Response times and error were collected with error being calculated using the Euclidean distance formula. The results were consistent with previous research and showed that congruent trials (aerial-aerial and ground-ground) resulted in less error and response time. It was also shown that there was a significant four-way interaction between stimulus image, response image, object density, and stimulus duration. The results of this study are intended to provide the basis for future work in understanding the underlying reasons behind spatial errors that might occur during use of UASs and lead to design implementations for interfaces to reduce these errors.

Result Prediction Using K-Nearest Neighbor Algorithm For Student Performance Improvement

Abstract—The examination results have become an integral part of every student’s life. The educational institution’s ranking is greatly influenced by the university results. This paper mainly focuses on the prediction of a student’s university result by making use of different attributes. These attributes might be of quantitative and qualitative type. The quantitative attributes used are Internal Assessments, Attendance percentage, Number of On-Duties taken and Overall Assignments completed. The qualitative attributes include Subject feedback, Faculty feedback, and whether the student is a Day Scholar/Hosteller. Here, we make use of k-Nearest Neighbor algorithm (or k-NN for short) against the historical data of students for more accurate prediction of results. In this method all the attributes considered are converted to the same scale. This algorithm makes use of the Euclidean distance formula which is used to find the nearest record. This algorithm predicts better results which help students maximize their academic output.

Artificial Intelligence approach for Classifying Molecular Dataset using Density based technique with appropriate Euclidean Distance measure

Data mining is the process of extracting hidden analytic information from large databases using multiple algorithms and techniques. Artificial Intelligence is concerned with improving algorithms by employing problem solving techniques used by human beings. In this paper, we implemented a methodology to classify a huge data set into clusters using a standard mathematical equation. A new clustering algorithm is proposed which involuntarily evolves the number of clusters as well as proper partitioning from a data set with artificial intelligence techniques. Here for the assignment of points to different clusters a standard distance calculation measure Euclidean distance formula is used which is intended to overcome point symmetry based clustering. An idea to implement this methodology on chemical/molecular data came from a software program Fast Rigid Exhaustive Docking which generates interactions of new molecules whose biological activity is unknown. The molecular data thus obtained as scores are tabulated as values. This is considered as raw data, which is further preprocessed and hence from one point to other point distance is calculated using Euclidean distance which forms a multi dimensional database with several combinations. Later on clusters are analyzed and pattern recognition is performed by using an algorithm to obtain results. Density based clustering technique is performed for better results on molecular database.In the field of chemistry there is much need of data mining for identifying the best molecule whose biological activity value is unknown. Using Artificial intelligent techniques we predicted the biological activity of a molecule when a dependent core training set is provided and leads to different case studies of test set molecules for which data mining techniques are utilized. As data mining is a wide research area that has many applications so new algorithms like this can create a boon in research areas and hence evaluating best results.