K-means Clustering Method Research Articles

Performance Evaluation of Simple K-Mean and Parallel K-Mean Clustering Algorithms: Big Data Business Process Management Concept

Data is the most valuable asset in any firm. As time passes, the data expands at a breakneck speed. A major research issue is the extraction of meaningful information from a complex and huge data source. Clustering is one of the data extraction methods. The basic K-Mean and Parallel K-Mean partition clustering algorithms work by picking random starting centroids. The basic and K-Mean parallel clustering methods are investigated in this work using two different datasets with sizes of 10000 and 5000, respectively. The findings of the Simple K-Mean clustering algorithms alter throughout numerous runs or iterations, according to the study, and so iterations differ for each run or execution. In some circumstances, the clustering algorithms’ outcomes are always different, and the algorithms separate and identify unique properties of the K-Mean Simple clustering algorithm from the K-Mean Parallel clustering algorithm. Differentiating these features will improve cluster quality, lapsed time, and iterations. Experiments are designed to show that parallel algorithms considerably improve the Simple K-Mean techniques. The findings of the parallel techniques are also consistent; however, the Simple K-Mean algorithm’s results vary from run to run. Both the 10,000 and 5000 data item datasets are divided into ten subdatasets for ten different client systems. Clusters are generated in two iterations, i.e., the time it takes for all client systems to complete one iteration (mentioned in chapter number 4). In the first execution, Client No. 5 has the longest elapsed time (8 ms), whereas the longest elapsed time in the following iterations is 6 ms, for a total elapsed time of 12 ms for the K-Mean clustering technique. In addition, the Parallel algorithms reduce the number of executions and the time it takes to complete a task.

Safety Margin Evaluation of Pedestrian Crossing through Critical Thresholds of Surrogate Measures of Safety: Area with Zebra Crossing versus Area without Zebra Crossing

Although many studies have been carried out on pedestrian crossing safety, comprehensive research evaluating vehicle–pedestrian conflict in areas with zebra crossing (AWZCs) versus areas without zebra crossing (AWOZCs) is still neglected. In the present study, through a naturalistic driving study (NDS), drivers’ behavior was recorded in AWZCs and AWOZCs. Vehicle–pedestrian conflicts were evaluated by examining the evasive maneuver behavior of drivers and pedestrians based on surrogate measures of safety (SMoS). The severity of conflicts was categorized by a K-means clustering method into three specific groups based on the critical thresholds of SMoS. The evasive maneuvers performed by pedestrians and drivers were classified into three levels: normal, slight, and serious. In conflicts resulting in normal and serious maneuvers, drivers would attempt to prevent collisions by changing the speed and direction of the vehicle. Moreover, a pedestrian at the slight level of conflict was the determinative factor in reducing the possibility of collisions by performing actions such as returning to the curb of the street or increasing walking speed. Also, the results showed that pedestrians were more likely to cross with a smaller margin of safety in AWOZCs than in AWZCs. This study explains how both pedestrians and drivers play a crucial role in preventing collisions during different levels of conflict. Given this finding, conducting future research to evaluate the interaction between drivers and pedestrians may lead to establishing a basic framework for designing an algorithm to detect the possibility of a pedestrian collision.

Optimal PV Placement to Reduce Power Loss and Improve Voltage in Distribution Network System Using K-means Clustering Method

Placing the PV in the right location will maintain the utility voltage, but if the placement of PV in the wrong location will cause the stability of the system to be affected. In this study, optimization of PV placement uses the K-means Clustering method. This method will group each node in the system from the point of view of operating characteristics LSF (loss sensitivity factor) and dV (voltage deviation). The results of grouping each bus with the K-means Clustering method will be the basis for determining the location of PV placement in the IEEE 37 and 69 bus distribution systems. In this method, grouping results are used based on the size of the proximity and have the same characteristics with each other. In determining the optimal location for PV placement, the addition of PV will reduce power losses and improve voltage. Optimal PV location placement in the IEEE 37 bus distribution system is placed on 3 buses with a power capacity of 60% where the value of power losses drops to 176.2 kW and the voltage profile is the best but there are some buses that are still under voltage and overvoltage. Meanwhile, the most optimal PV location for the IEEE 69 bus distribution system is placed on a 6 bus with a power capacity of 60% where the value of power losses drops to 149.5 kW and the voltage profile of each bus is in normal condition..

Optimization of the Number of Clusters of the K-Means Method in Grouping Egg Production Data in Indonesia

The need for eggs that continues to increase will not increase with large egg production so that there is a shortage of egg supplies which results in high egg prices. It is necessary to group egg production in Indonesia to find out which areas fall into the high cluster and which areas fall into the low cluster. This study aims to classify the egg production of laying hens in Indonesia. The method used is the K-Means Clustering method which is a popular clustering method. To find out how optimal the number of clusters in the K-Means method is for grouping egg production in Indonesia, the researcher evaluates the DBI value of each number of existing clusters. In this study, 8 clusters were used, namely 2 clusters, 3 clusters, 4 clusters, 5 clusters, 6 clusters, 7 clusters, 8 clusters, and 9 clusters. The results of measuring the DBI value are the number of clusters 2 = 0.215, the number of clusters 3 = 0.149, the number of clusters 4 = 0.146, the number of clusters 5 = 0.157, the number of clusters 6 = 0.180, the number of clusters 7 = 0.205, the number of clusters 8 = 0.192 and the number of clusters 9 = 0.154. This study shows that the best number of clusters is the number of clusters 4 with the smallest DBI value of 0.146.

Cooperative Computation and Cache Scheduling for UAV-Enabled MEC Networks

Since the flight of Unmanned Aerial Vehicle (UAV) greatly consumes the limited on-board energy and affects the ability to afford computation services, it is urgent and challenging to minimize UAV’s endurance time while satisfying varieties of constraints from the UAVs and users, such as energy budgets, cache capacities, computation resources, and latency requirements. In this paper, the UAVs are endowed with the capability to temporarily buffer some offloaded tasks and process them later, then adopt cooperative computation and cache scheduling to minimize their total endurance time. Following this, the formulated problem is a mix-integer nonlinear programming problem, which can be further transformed into three more tractable subproblems: 1) PO, offloading decision and scheduling strategy for computing & caching; 2) PH, hovering trajectory design; 3) PC, computation resource allocation, and then iteratively tackled in a sequence. Due to the high complexity of solving PO, the low-complexity algorithm based on the K-means clustering and Penalty Method is proposed to reduce complexity and facilitate the processing procedure, which can save about 91.04%-189.36% running time and ONLY sacrifice 8.05%-22.08% of the total endurance time. Simulation results show that cooperative computation and cache scheduling has a great effect on saving endurance time.

Enhancing Clustering Performance Using Topic Modeling-Based Dimensionality Reduction

Mainly in the present times, the description of the services and their working procedure have been established in natural text language. We have obtained service groups based on their similarities to reduce search space and time in service innovation. Major topic models such as LSA, LDA, and CTM policies have not been able to show effective performance due to the short description and limited description of services in text form, the reduction or absence of words that occur. To solve the issues created by brief text, the Dirichlet Multinomial Mixer model (DMM) with features representation using the Gibbs algorithm has been developed to reduce dimensionality in clustering and enhance performance. The launch results prove that DMM-Gibbs can give better results than all other methods with agglomerative or K-means clustering methods by sampling. Evaluations with internal and external criteria were used to calculate clustering performance based on these two values. Using this standard model, the dimensionality can be reduced to 93.13% and better clustering performance can be achieved.

Pemetaan Terhadap Penyebaran Unit Cabang Kantor Pos Di Kabupaten Wonogiri

The Post Office is one of the public facilities for the community because it serves service facilities in the form of postal services, package delivery, logistics and reliable financial services. However, the lack of information makes access to the location of post office services not informed of the location distribution. The purpose of this research is to create a mapping application for branch post office units to make it easier for the general public to get information about the nearest post office unit, using the K-Means Clustering Method. Users can choose which post office unit they want to choose based on their criteria. In functional testing (Blackbox) it was found that the system had been running according to the system design plan that had been made previously, while the validity test using the Silhouette Coefficient method showed the average value for cluster 1 was 0.282674, cluster 2 was 0.297377, and cluster 3 is 0.423516, which means the object is in a good or appropriate group because the Silhouette Coefficient value in each cluster is closer to 1, which means the better the grouping of data in one cluster.Keywords : K-Means Clustering, Post Office, Silhouette Coefficient

MINING FIRE HOTSPOTS OVER NUSA TENGGARA AND BALI ISLANDS

Forest fires are still one of the most common problems in Indonesia. In fact, many of these forest fires origin from human activities, namely fires that are intentionally raised for a purpose such as widening the land to prepare for the planting season in the Nusa Tenggara Island. Forest fire events can be identified by observing hotspot data which are monitored through remote sensing satellites. Hotspot is an area that has a relatively higher surface temperature than the surrounding area based on certain temperature thresholds monitored by remote sensing satellites. The area is represented as a point that has certain coordinates. The actual fires can be monitored by observing the hotspot attribute, namely Confidence, Brightness Temperature and FRP (Fire Radiate Power). To find the similarities of the three mentioned attributes, the clustering process is carried out to make monitoring easier. The objective of this research is to cluster hotspots in the Nusa Tenggara and Bali Islands from year 2013 to 2018 using the K-Means Clustering Method with 28,519 hot spot data. This could be a benefit for the Ministry of Environment and Forestry in Indonesia to identify the priority level of the area to be monitored. By knowing this result, the ministry can use this data for patrol priority management. This research successfully clustered three types of hotspot classes based on the risk of fire with details as follow; High Risk Class contains 12,212 data with ranges of mean values of confidence in the range of 49.3–100%, brightness in the range of 305.1–421.3o K and FRP in the range of 2.5–714.3; Medium Risk contains 12,250 data mean values of confidence with a range of 20.3–74.3%, brightness in the range of 301.06–341.86o K and FRP in the range of 3.6–141.4; and Low Risk contains 4,057 data with a range of mean values of confidence in the range of 0–39.8%, brightness in the range of 300–365.86oK and FRP in the range of 3.5–275.6. All of the clusters were obtained by the implementation of K-Means clustering over the hotspot data and its parameter as mentioned, respectively. The cluster performance showed the confidential value of 88.45% accuracy using 100 hotspot data from 2019

ANALISIS NILAI AKURASI PENGOLAHAN CITRA PENDETEKSIAN RINTANGAN KERJA TRAKTOR MENGGUNAKAN K-MEANS CLUSTERING

The use of agricultural tractors as mechanical aids for tillage using agricultural tractors can make work lighter, faster, more efficient and do big jobs in a relatively short time. Along with the development of technology, many innovations have been developed by humans, including in the field of digital image processing. Segmentation is one of the methods in digital image processing to distinguish objects in an input image. One of the algorithms that can be used for image segmentation is K-Means. Many algorithms are used in image classification. Algorithms that can be used to complete the supervised classification include Paralleepiped, Minimum Distance, Mahalanobis Distance, Maximum Likelihood, Naive Bayesian, K-Nearest Neighbor. Algorithms that can be used to solve unsupervised classifications include Isodata, K-Means, Improved Split and Merge Classification (ISMC), and Adaptive Clustering (CA). Based on this description, this research was conducted to facilitate the data processing process, it is necessary to have a data grouping system to determine decisions in the analysis to determine the level of accuracy in the detection of obstacles resulting from image processing where obstacles are detected, noise and obstacles are not detected. processed and grouped based on their characteristics so that it is known that the cluster is low, medium cluster and high cluster to be able to analyze the data, it is necessary to have a deeper analysis using the K-Means Clustering method and implement K-Means results into Rapidminer to see the results of visualizing the K-Means algorithm data grouping.

Investigation of spatial correlation on optimal power flow with high penetration of wind power: A comparative study

Spatial correlation is a critical characteristic of adjacent wind farms, but its importance is always ignored in wind power modeling, further resulting in modeling bias. In order to investigate the necessity of involving spatial correlation and validate whether it has effects on power system, this paper proposes a method to construct the spatial correlation model and applies it into an IEEE test system. Specifically, a 7-dimensional t-copula method is used to capture the spatial dependence by forming a multi-variable distribution function, from which different scenarios are generated. Subsequently, a k-means clustering method is used for scenario reduction. As for the case study, a modified IEEE 39-bus test system with 7 wind farms deriving from the AEMO dataset is utilized to conduct optimal power flow under the circumstance with and without considering spatial dependence. Based on this, the cost of generation, including traditional fuel cost and levelized cost of wind power is obtained. Through comparing the cost results and analyzing the gap, it can be concluded that the spatial correlation has significant effects that when levelized cost of wind power exceeds a particular value, the generation cost can be greatly underestimated if ignoring spatial correlation with a high penetration of wind power.

Decision Support System Metode K-Means Clustering Dalam Memprediksi Tingkat Penjualan Pada Store Ryan Mart

Ryan Mart store is one of the stores located in the god's fence that sells grocery, drinks, food, perfume, and electric tools. Where the Ryan Mart store is currently going to make an application in predicting the level of sales where management of the inventory of goods in the Riyan Mart store, all this time is still felt manually, that is, if the inventory runs out, then orders will be made to the supplier of goods in the city of Bengkulu. . In sales, there needs to be an effectiveness in predicting the level of sales of goods at the Riyan Mart store, an application is needed that can help provide the level of daily sales at the Bengkulu City store Riyan Mart, from applications designed using the K-Means Clustering method it will be known what items should be improved in future sales of goods. The K-Means Clustering method can help predict the level of sales at the Ryan Mart store. days, and then the data will be grouped based on 3 (three) clusters, namely Cluster I (Most Interested Items), Cluster II (Items That Are Least Interested), Cluster III (Items Not Interested). In the implementation of the K-Means Clustering algorithm, it is done by grouping data based on sales of goods, where before grouping the data, it will be added automatically to get the results of the number of sales of each item in the next period, which is 1 year. To assist in the implementation of the K-Means Clustering algorithm, a Visual Basic .Net application was created with the SQL Server 2010 data base.

Pengelompokan Barang Menggunakan Metode K-Means Clustering Berdasarkan Hasil Penjualan Di Toko Widya Bengkulu

The Widya shop sells various kinds of hijab products that are tailored to the needs of fashion development. The Widya Bengkulu store also sells various kinds of women's needs such as clothes, accessories, bags, wallets, soft lenses, cosmetics and other fancy items. So far, Widya Store has not used computers as a data processing medium. All processes of selling goods and inventory of goods are still carried out with book records, and do not yet have an application that can help the process of managing the data of these goods. In addition, in managing inventory, Toko Widya only sees stock based on sales results, if the stock on one of the items runs out, an order will be made to the supplier.
 Implementation of the K-Means Clustering Method in Grouping Goods Based on Sales Results at the Widya Bengkulu Store was made using the Visual Basic .Net programming language and SQL Server 2008 database. In the Grouping of Goods Based on Sales Results at the Widya Bengkulu Store, it will be processed to seek knowledge from chunks of data, namely goods sales data. Cluster I is a Very Selling Item, Cluster II is a Self Selling Item, and Cluster III is a Less Selling Item. Based on the results of the tests that have been carried out, the application of Grouping Goods Based on Sales Results at the Widya Bengkulu Store can provide information on the best-selling items sold at the Widya Store.

PENGELOMPOKKAN BERITA KESEHATAN PADA SOSIAL MEDIA TWITTER DENGAN METODE K-MEANS CLUSTERING

Twitter is one of the most influential social media in the world with 15.7 million users in Indonesia and is ranked 6th as the country with the most Twitter users. Besides being used as social media, Twitter is also used as a medium to read or send news. News information that continues to increase causes users to have difficulty in finding certain news information. One solution that can be applied to overcome this problem is through clustering of news information on Twitter. In this study, the researcher used quantitative research with the K-Means Clustering method, which is one of the clustering methods used in grouping data. The data used in this study is a dataset taken from the UCI Machine Learning Repository, namely Health News in Twitter Data Set as many as 14,970 tweet data. The results showed that the determination of the best cluster using the Elbow method on the dataset resulted in empirical evidence that the best cluster was K=3. The results of grouping health news on Twitter social media using the K-Means Clustering method with K=3 resulted in the number of clusters, namely C1 as many as 4,991 data tweets, C2 as many as 4,482 tweets data, and C3 as many as 5,497 tweets.Keywords: Health News Grouping; Twitter Social Media; Elbow Method; K-Means Clustering Method.

Abnormal dynamic functional connectivity in first-episode, drug-naïve adolescents with major depressive disorder.

Previous neuroimaging studies have identified disrupted large-scale functional brain networks in major depressive disorder (MDD); however, most of them focused on adult patients and were based on static functional connectivity (FC). Thus, we aimed to investigate the patterns of change in dynamic FC in depressed adolescents. Resting-state functional magnetic resonance imaging data were acquired from 60 first-episode, drug-naïve adolescents with MDD and 60 matched healthy controls (HCs). Then, the dynamic FC properties were analyzed using a sliding windows approach, k-means clustering, and graph theory methods. The intrinsic brain FC were clustered into two configuration states-a more frequent and relatively sparsely connected State 1 and a less frequent and more strongly interconnected State 2. Compared with HCs, depressed adolescents had higher reoccurrence fraction and dwell time in State 1, and lower reoccurrence fraction and dwell time in State 2, and higher total number of transitions between the two states. Depressed adolescents showed decreased FC within the default mode network (DMN) and between the DMN and other networks in State 1. Additionally, the MDD group showed higher variances in the global and local efficiency. Furthermore, the duration of illness was positively correlated with the number of state transitions, and the 17-item Hamilton Depression Rating Scale score was positively correlated with the mean dwell time in State 1. This study demonstrated abnormal dynamic FC in depressed adolescents, which provided new insights into the pathophysiological mechanisms of adolescent-onset depression.

Seafood freshness: e-nose data for classification purposes

The aim of this study was to develop an electronic nose system useful for the inspection of different seafood products and specifically designed to be applied as an auxiliary device for the management of seafood in the large-scale distribution chain. Since the freshness is a critical issue in determining the quality of fish it is of great importance to have a simple and rapid analytical method representing a useful tool for assessing the acceptability of the seafood products in the distribution centers or in the supermarkets. In this work a portable e-nose, composed by four selected metal oxide semiconductor sensors, a photoionization detector and two electrochemical cells, was applied to test three different seafood products - sole (Solea senegalensis) fillets, red mullet (Mullus barbatus) fillets and cuttlefish (Seppia officinalis) - during their shelf life from the day of arrival and packaging at the distribution center until beyond the expiration date. The K-means partitional clustering method was applied to group samples into three freshness classes, then confirmed by microbial analysis; two classification models based on k-nearest neighbors (K-NN) and partial least square-discriminant analysis were developed to classify the freshness of the seafood regardless the species and in particular, the KNN model provided 100% overall sensitivity, specificity and precision in prediction thus confirming the applicability of the system to inform retailers on product safety and quality.

Fostering Peer Learning With a Game-Theoretical Approach in a Blended Learning Environment

This study proposes a mechanism and an instructional design in order to foster well-organized peer learning based on game theory (PD_PL). The proposed mechanism uses prisoner’s dilemma (PD), the most widely known example of game theory in a dynamically blended and collaborative learning environment. PD_PL maps the strategy and payoff concepts found in PD onto a peer learning (PL) atmosphere. As is the case in PD, any greater effort made by both participants in PD_PL results in increased learning improvement. PD_PL was run in several sessions consisting of four separate university courses with 142 computer engineering students. We gave a pretest and a posttest before and after the PD_PL sessions, respectively. Then, we used paired Hotelling’s T-Square function to analyze the pretests and posttests and investigate the impacts of PD_PL and the proposed instructional design on students’ learning improvement. We had some missing data because some students were absent from some of the PD_PL sessions. As a requirement of paired Hotelling’s T-Square function, we applied the mean value, median value, k-nearest neighbor (KNN), and fuzzy k-mean clustering (FKM) methods in order to deal with the problem of imputing missing data. The results of paired Hotelling’s T-Square indicate that PD_PL is a successful mechanism for encouraging the active participation of students in the PL process. Further analysis shows that PD_PL had sometimes even enhanced learning by up to 127.69%. We also observed that the senior students used PD_PL more successfully than the first-year students. The results of our subjective evaluation showed that the majority of the respondents found PD_PL to be an attractive and efficient tool for learning enhancement. Anyone interested in instructional designing for PL environments will find this study interesting. The mechanism could also be run in a learning management system (LMS) to prepare an effective situation of collaborative learning situation.

Implementasi Metode K-Means Sebagai Upaya Penentuan Lokasi Promosi Penerimaan Siswa Baru

Smart Study Center is a computer course located in Kisaran City, Asahan Regency, North Sumatra Province. This computer-based course has promoted to various places, especially around Kisaran City. But sometimes there are obstacles in doing this, because it is not easy to determine the location of the promotion quickly and precisely. Promotion is the communication of information between sellers and potential buyers or others in the channel to influence attitudes and behavior. In addition, the application of information technology in the field of promotion can facilitate the management of information which, if processed properly, can produce new knowledge that is very useful in making future decisions. It takes research and consideration of many aspects which of course will take a lot of time. The majority of the Smart Study Center Kisaran students come from various public and private vocational high schools and high schools in Kisaran City and its surroundings. This is certainly one of the important factors to promote the acceptance of new students in an effort to increase the number of new students every year. With the application of data mining using the K-Means Clustering method on the acceptance of new students in the Smart Study Center Kisaran course by grouping research object items based on their similarity in nature, so that information will be obtained about which areas have high potential to bring in new students. K-Means Clustering can group large enough data quickly and accurately so that decision making in determining the location of the promotion in the next year can be done effectively and efficiently. The data attributes used in this study are the names of majors such as, TKJ, RPL, and Ms Office. The result of this system is the determination of the location of the promotion with 2 clusters i.e. feasible (C1) and unfit (C2)

Sistem Penentuan Konsentrasi Jurusan Bagi Mahasiswa Informatika Menggunakan Metode K-Means Di Institut Asia Malang

Specialization in the concentration of a major is a student's focus on a particular field of study according to his interests. The purpose of specialization is to focus students more on the knowledge gained from previous courses so that they can be more focused. In the Informatics Engineering study program at the Institute of Asia Malang, there are 3 concentrations, namely: Intelligent Systems; Multimedia and Games and, Computer Network Administration. The absence of a system that helps students choose the concentration of majors is quite difficult for students to know their academic abilities. By looking at these problems, this study aims to build a decision-making system in choosing the concentration of majors using the K-Means Clustering method. Where the data value of semester 1 to semester 4 students is used as a variable in the calculation of the k-means clustering method which is implemented using the PHP and MySQL programming languages. Based on the test results, it was found that in cluster 1 there were 3 students who entered the intelligent system concentration. In the second cluster, there are 20 students who are in the Multimedia and Game concentration, in the third cluster there are 56 students who are in the network concentration.

Evaluating the sustainability of Chinese cities: Indicators based on a new data envelopment analysis model

As the second largest economy in the world, China faces serious environmental issues. Currently, how to promote sustainability has become an important priority for policymakers and has attracted great attention from researchers. To evaluate sustainability, this study proposes a new methodological framework. This framework consists of a new data envelopment analysis (DEA) model, concepts of natural and managerial disposability, strong complementary slackness conditions, efficiency Theil index and K-Means clustering method. With the use of this framework, this study obtains unified efficiency measures, technology-based measures, and efficiency inequality measures. These measures assist decision makers in promoting efficiency, mitigating environmental degradation and promoting sustainability. Empirically, this study considers the case of 198 Chinese cities from 2010 to 2016. Five main conclusions are presented. First, Chinese cities improved their unified efficiency scores under both natural and managerial disposability. Second, there is a significant number of occurrences of undesirable congestion, which means that most Chinese cities can save considerable resources during the production process. Third, there is a limited number of occurrences of desirable congestion, implying that only a small portion of Chinese cities have achieved a high level of sustainability. Fourth, efficiency inequality across Chinese cities has gradually decreased over time, where technology diffusion plays an important role. Finally, China faces considerable regional/provincial inequality. Looking ahead, cities that lag behind should put significantly more effort into enhancing both economic prosperity and environmental protection.

Diagnosis of Breast Cancer by K-Mean Clustering and Otsu Thresholding Segmentation Methods

Breast cancer has increased decidedly among women. But with early diagnosis, a positive response to treatment can be given. Researchers are conducting various studies in imaging methods to detect the disease early and accurately. In this study, 9 cancerous images taken from the TCİA image data bank were detected by K-mean clustering and the Otsu threshold method. Performance metrics were evaluated by comparing them with marked reference images (ground truth) by the radiologist. For the clustering process, TPR (True Positive Rate) 0.89, FPR (False Positive Rate) 0.14, similarity 0.67, accuracy 0.87, sensitivity 0.89, exact hit ratio 0.86, specificity 0.87, F Score 0.87 were found, respectively. For Otsu, TPR (True Positive Rate) 0.84, FPR (False Positive Rate) 0.12, similarity 0.73, accuracy 0.84, sensitivity 0.84, exact hit 0.86, specificity 0.87, F Score 0.84 were calculated. The aim of this study is to determine the tumor boundaries more accurately and to use them in imaging devices in the field of health with pixel-based segmentation. As a result, both methods were successful can be used in the field and close to each other.