Analisis Gejala Covid-19 di RSUD Yogyakarta dengan Menggunakan Metode K-Means, Fuzzy C-Means dan K-Medoid Clustering

In general, in 2019-2020 fruit production in Kotawaringin Timur district has decreased. Based on the data on fruit production, the amount of fruit production decreased, resulting in scarce fruit stocks and expensive fruit prices. Based on these problems, fruit production will be grouped according to the type of production in East Kotawaringin district using data mining techniques with clustering techniques using the K-Means algorithm and K-Medoids algorithm in order to optimize and increase fruit production. The results of grouping fruit production will be divided into 3 clusters, namely the highest cluster, the medium cluster, and the lowest cluster, making it easier for the Food and Agriculture Security Service in East Kotawaringin district to calculate and increase agricultural yields, especially in the horticulture sector. Based on the test results using data in 2019-2022, totaling 29 data in the Rapidminer application version 9.9 by comparing the DBI (Davies Bouldin Index) values of the two algorithms with so that the conclusion in determining the best value for the number of clusters (K) is that the fourth experiment shows 0.296 DBI (Davies Bouldin Index) values with six clusters. If the DBI value is smaller or closer to 0, then the cluster results obtained are more optimal. The results obtained in the K-Means algorithm get a smaller DBI (Davies Bouldin Index) value with a value of 0.296 while the K-Medoids algorithm results with a DBI (Davies Bouldin Index) value of 0.507. The best algorithm for clustering fruit production in Kotawaringin Timur district is the K-Means algorithm based on the DBI values obtained.

The sale of staple food products at Nafhanmart Store, Cirebon Regency, includes essential household items such as rice, cooking oil, sugar, and flour, which maintain stable demand as basic necessities. This study focuses on improving sales clustering models at Nafhanmart using the Fuzzy C-Means (FCM) algorithm, a prominent method in data mining. Key factors influencing sales include price, sales volume, demand, and remaining stock. Accurate clustering analysis is vital for strategic inventory management and profit maximization. The research applies the Knowledge Discovery in Database (KDD) methodology, encompassing data selection, preprocessing, transformation, FCM implementation, and evaluation using the Davies-Bouldin Index (DBI). Attributes analyzed include price, sales volume, demand, and remaining stock. The FCM algorithm clusters data based on patterns, with DBI evaluating clustering quality and determining optimal clusters. Data analysis and visualization were conducted using RapidMiner. Results show that the FCM algorithm achieves optimal clustering quality with a DBI score of 0.452 for two clusters, outperforming three clusters (DBI 0.474) and four clusters (DBI 0.536). Price and demand are identified as critical factors influencing clustering outcomes. These findings enhance the clustering model, offering actionable insights for inventory management and sales strategy, while showcasing the FCM algorithm's adaptability for other SMEs to support data-driven decision-making.

Diarrhea is an endemic disease that contributes to the high mortality rate in Indonesia, especially among children under five. The Kuningan District Health Office had difficulties in monitoring and supervising the spread of diarrheal diseases. This study aims to produce a mapping scheme of priority areas in handling the prevention and control of the spread of diarrheal disease in children under five in Kuningan Regency. The method used is the Data Mining Clustering method by comparing two algorithms, namely the K-Means algorithm and the K-Medoids algorithm. Determination of the optimum number of clusters using the Elbow and Silhouette Coefficient methods. With this method, the result is that in the K-Means algorithm the optimum number of clusters is 3 clusters while the K-Medoids algorithm is 2 clusters. The best cluster evaluation uses the Davies-Bouldin Index (DBI) method and the results show that the K-Means DBI value is always smaller than the K-Medoids algorithm in either 2 clusters or 3 clusters, this shows that the K-Means algorithm is better than the K-Medoids algorithm. Based on these results, it is recommended to map priority areas for handling diarrheal diseases using the K-Means algorithm with 3 clusters, namely medium priority areas consisting of 9 regions, high priority areas consisting of 3 regions and low priority areas consisting of 25 regions. The results of the mapping can be used as input for the Kuningan District Health Office to develop strategies for preventing and preventing diarrheal diseases in children under five.

Mutual funds are a container that can be used to accommodate funds from the public which will later be distributed to the owners of the company. The ease of investing in share prices cannot be separated from the ease of obtaining information. The share price that is very popular with the public is the share price for banks, whether privately owned or government owned. However, even though banks are very close and popular with capital market players, this does not rule out the possibility of a decline in share prices. This problem is not a problem that can be considered trivial and ignored, if you continuously experience losses from the capital market it will certainly give rise to distrust or a lack of interest in the public to participate in investing in companies. Predictions for stock prices must be done well and correctly and get accurate results, therefore it is necessary to use a special technique or method to help carry out the prediction process until results are obtained with a good level of accuracy. The expected prediction process is in line with the concept of data mining. The process of applying clustering for predictions is also considered very suitable, this is because in stock prices there is no target class for each data. The K-Means algorithm and K-Medoids algorithm are part of cluster data mining to be used to make predictions based on cluster formation. The purpose of the comparison is to get more reliable results, where these results can be seen from better algorithm performance. The performance measurement process for the K-Means and K-Medoids algorithms will later be assessed based on the Davies Bouldin Index (DBI). The results of the research show that the performance results of the K-Means algorithm are better than the K-Medoids algorithm. This is proven by the DBI value obtained from the K-Means algorithm being no more than 0.6, while in the K-Medoids algorithm the DBI value obtained is up to 5.822. Overall, each stock data has an optimal cluster based on the clustering process with the K-Means algorithm. The optimal cluster results in BMRI stock data, the optimal cluster is at K=4 with a DBI value of 0.501. In the BBNI stock data, the optimal cluster is at K=4 with a DBI value of 0.500. In the BBCA stock data, the optimal cluster is at K=3 with a DBI value of 0.441. In the BNGA stock data, the optimal cluster is at K=2 with a DBI value of 0.263. In the BDMN stock data the optimal cluster is at K=2 with a DBI value of 0.028 and in the MEGA stock data the optimal cluster is at K=4 with a DBI value of 0.353.

This paper presents a fuzzy clustering-based technique for image segmentation. Many attempts have been put into practice to increase the conventional fuzzy c-means (FCM) performance. In this paper, the sensitivity of the soft membership function of the FCM algorithm to the outlier is considered and the new exponent operator on the Euclidean distance is implemented in the membership function to improve the outlier rejection characteristics of the FCM. The comparative quantitative and qualitative studies are performed among the conventional k-means (KM), moving KM, and FCM algorithms; the latest state-of-the-art clustering algorithms, namely the adaptive fuzzy moving KM , adaptive fuzzy KM, and new weighted FCM algorithms; and the proposed outlier rejection FCM (ORFCM) algorithm. It is revealed from the experimental results that the ORFCM algorithm outperforms the other clustering algorithms in various evaluation functions.

The Yogyakarta Special Region faces a decline in water quality, with river conditions as a significant factor. Previous studies highlight clustering techniques use K-Means and Fuzzy C-Means (FCM) as effective for water quality assessment, but comparison between these algorithms has not been conducted. This study investigates: How do K-Means and FCM algorithms perform and which algorithm provides optimal outcomes in clustering 10 river water quality in the Yogyakarta Special Region from 2020-2023 based on pollution index? The hypothesis suggests K-Means outperforms FCM due to its centroid-based optimization. Evaluation using the Calinski-Harabasz Index (CHI), Davies Bouldin Index (DBI), and Dunn Index (DI) showed that K-Means has higher CHI and DI values and lower DBI values, indicating better-defined clusters than FCM. The clustering results identified Cluster 2 as the group with the highest pollution level, followed by Clusters 4, 1, 0, and 3. Cluster 2 has the highest pollution index value consistently, indicating the urgency of priority intervention. These findings can be used to formulate river pollution mitigation policies. With these results, the study not only demonstrates the optimal algorithm in water quality clustering, but also provides data-based recommendations for more effective environmental management in Yogyakarta and other areas with similar characteristics.

The goal of this study is to categorize the findings of a survey on the application of the MBKM policy that DIKTI performed via universities that had been awarded research funding. The survey results have not been categorized, making it difficult for the institution to determine if the MBKM policy has been implemented in accordance with the MBKM standards released by the Higher Education. The K-Mean and K-Medoids Algorithms are used in this study technique to solve data grouping issues and validate clustering outcomes using the Davies-Bouldin Index (DBI). 400 data points total were processed from 16 variables in this investigation. The findings of this investigation were tested using several clusters. After analyzing clusters using DBI, the K-Mean algorithm discovered that cluster 5 had K-Medoids of 0.9 and a value of 0.823. Therefore, it is advised to employ 5 clusters with the K-Mean Algorithm for grouping data from the MBKM survey findings.

In the national development process, the village occupies a very important position. This is because it is the smallest government structure and has direct contact with the community. Seeing the importance of its role in national development, one of which is Gorontalo Province, based on directions from the central government, is trying to implement the Village Fund Allocation (ADD) policy for all villages in Gorontalo Province. In distributing the allocation of funds, it is necessary to map the status of the Village to find out the amount that must be given. This test uses the average execution time and the Davies Bouldin Index (DBI). After testing it is known that the K-Medoid Algorithm has a better DBI value than the K-Means Algorithm with the DBI value of the K-Medoid Algorithm being 0.050. On the other hand, the K-Means Algorithm has a better average execution time than the K-Medoid Algorithm, where the average execution time is 1 second.

The Covid-19 pandemic has made many changes in the patterns of community activity. Large-Scale Social Restrictions were implemented to reduce the number of transmission of the virus. This clearly affects the mode of transportation. The mode of transportation makes new regulations to reduce the number of passenger capacities in each fleet, for example, TransJakarta services. This study will categorize the TransJakarta corridors before and during the Covid-19 pandemic. The clustering method of K-Means and K-Medoids is used to obtain accurate calculation results. The calculations are performed using Microsoft Excel, Rapid Miner, and Python programming language. The clustering results obtained that using K-Means algorithm before Covid-19 pandemic, an optimum number of clusters is 3 clusters with DBI (Davies Bouldin Index) value is 0.184, and during Covid-19 pandemic, the optimum number of clusters is 2 clusters with DBI value is 0.188. Meanwhile, when using the K-Medoids algorithm before the Covid-19 pandemic, an optimum number of clusters is 3 clusters with the DBI value is 0.200, and during the Covid-19 pandemic, an optimum number of clusters is 4 clusters with the DBI value is 0.190. The final cluster is determined using the majority voting approach from all the tools used.

Universitas ‘Aisyiyah Yogyakarta is one of the private universities in Yogyakarta. The large number of private universities in Yogyakarta has intensified the competition for new student admissions. In this situation, every university requires the right strategy to attract prospective students. One of the strategies used by Universitas ‘Aisyiyah Yogyakarta to capture the interest of potential students is by conducting direct promotions to schools in Yogyakarta, Java, and Sumatra. In the admission process for new students in the Information Technology Study Program, a common problem arises, which is the number of prospective students who do not complete re-registration each year. These students pass the selection and are declared accepted, but they do not proceed with re-registration. The school presentation strategy contributes to student admissions, making it a good strategy, but it requires significant operational costs. Promotion area segmentation is needed so that this strategy can be more targeted, resulting in more efficient spending. Segmenting or grouping promotion areas can be addressed using data mining techniques, specifically clustering. This study aims to segment promotion areas using clustering algorithms, namely K-Means and K-Medoids, along with the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. The evaluation of DBI (Davies-Bouldin Index) showed that the K-Means algorithm performed better than the K-Medoids algorithm. The comparison between the K-Means and K-Medoids algorithms was assessed based on the DBI evaluation results, with the smallest DBI value observed in the K-Means algorithm. The DBI value for K-Medoids was 0.196, while for K-Means it was 0.170.

Education is a mandatory right of all citizens and the key to the nation's superiority in global competition that must get top priority to be examined critically and comprehensively. It is known that compulsory education is at least 12 years, but not all people can do it because of minimal economic conditions. In past years, COVID-19 has also had an impact on the economy, school dropout rates, and falling academic achievement, for example in Central Kalimantan. The size of Central Kalimantan, however, makes it difficult for the government to identify the areas with the worst levels of education. To determine which regions fall into the low and high education categories, it is required to group the province's educational levels. This study also compares two algorithms by measuring their accuracy. By looking at which algorithm has the lowest Davies Bouldin Index (DBI) value, the best degree of performance can be ascertained. To process the data from as many as 1,565 sources, data mining techniques, including the clustering method, were used. K-Means and K-Medoids algorithms were employed in this work as clustering techniques. Based on the outcomes of the cluster created, both algorithms are also put to the test for performance. The results of this study obtained 6 clusters in K-Means with the lowest DBI value of -0.439, while the results in K-Medoids were in 3 clusters with the lowest DBI of -0.866. Based on accuracy testing using DBI, it is known that K-Means results are more optimal with the lowest DBI value in the grouping of education levels compared to K-Medoids. It is also known from the formation of 6 clusters of the K-Means algorithm that the low education level is in cluster_0 which is 1484 villages and the higher education level is as many as 3 villages in cluster_3.

BackgroundTransvaginal insertion of polypropylene mesh was extensively used in surgical procedures to treat pelvic organ prolapse (POP) due to its cost-efficiency and durability. However, studies have reported a high rate of complications, including mesh exposure through the vaginal wall. Developing predictive models via supervised machine learning holds promise in identifying risk factors associated with such complications, thereby facilitating better informed surgical decisions. Previous studies have demonstrated the efficacy of anticipating medical outcomes by employing supervised machine learning approaches that integrate patient health care data with laboratory findings. However, such an approach has not been adopted within the realm of POP mesh surgery.ObjectiveWe examined the efficacy of supervised machine learning to predict mesh exposure following transvaginal POP surgery using 3 different datasets: (1) patient medical record data, (2) biomaterial-induced blood cytokine levels, and (3) the integration of both.MethodsBlood samples and medical record data were collected from 20 female patients who had prior surgical intervention for POP using transvaginal polypropylene mesh. Of these subjects, 10 had experienced mesh exposure through the vaginal wall following surgery, and 10 had not. Standardized medical record data, including vital signs, previous diagnoses, and social history, were acquired from patient records. In addition, cytokine levels in patient blood samples incubated with sterile polypropylene mesh were measured via multiplex assay. Datasets were created with patient medical record data alone, blood cytokine levels alone, and the integration of both data. The data were split into 70% and 30% for training and testing sets, respectively, for machine learning models that predicted the presence or absence of postsurgical mesh exposure.ResultsUpon training the models with patient medical record data, systolic blood pressure, pulse pressure, and a history of alcohol usage emerged as the most significant factors for predicting mesh exposure. Conversely, when the models were trained solely on blood cytokine levels, interleukin (IL)-1β and IL-12 p40 stood out as the most influential cytokines in predicting mesh exposure. Using the combined dataset, new factors emerged as the primary predictors of mesh exposure: IL-8, tumor necrosis factor-α, and the presence of hemorrhoids. Remarkably, models trained on the integrated dataset demonstrated superior predictive capabilities with a prediction accuracy as high as 94%, surpassing the predictive performance of individual datasets.ConclusionsSupervised machine learning models demonstrated improved prediction accuracy when trained using a composite dataset that combined patient medical record data and biomaterial-induced blood cytokine levels, surpassing the performance of models trained with either dataset in isolation. This result underscores the advantage of integrating health care data with blood biomarkers, presenting a promising avenue for predicting surgical outcomes in not only POP mesh procedures but also other surgeries involving biomaterials. Such an approach has the potential to enhance informed decision-making for both patients and surgeons, ultimately elevating the standard of patient care.

In this paper the K-means (KM) and the Fuzzy C-means (FCM) algorithms were compared for their computing performance and clustering accuracy on different shaped cluster structures which are regularly and irregularly scattered in two dimensional space. While the accuracy of the KM with single pass was lower than those of the FCM, the KM with multiple starts showed nearly the same clustering accuracy with the FCM. Moreover the KM with multiple starts was extremely superior to the FCM in computing time in all datasets analyzed. Therefore, when well separated cluster structures spreading with regular patterns do exist in datasets the KM with multiple starts was recommended for cluster analysis because of its comparable accuracy and runtime performances.

Patient histories who use the services of Badan Penyelenggara Jaminan Sosial (BPJS) Kesehatan are stored in medical record data. Each medical record data contains important information that is very valuable and can be processed to explore new knowledge using a data mining approach. This study aims to help Prof. Dr. Tabrani hospital in classifying patient data who use BPJS Kesehatan, so that the pattern of disease spread is known based on class of service. The data used is patient medical record data in 2019 from October to December, the data will be processed using the K-Means Clustering algorithm with a total of 3 clusters. In cluster 0 (H0) there are 3 patients who are dominated by A09.9 disease (Diarrhea / Dysentery) in Class 2 and Class 3, for cluster 1 (H1) there are 5 patients with more diverse types of disease, while for cluster 2 (H2) there are 5 patients who are predominantly K30 disease (Dyspepsia) in Class 1.

The Patient Medical Record Data Search application is used to assist the Bintunan Air Treatment Health Center in finding medical record data with faster time efficiency, where so far the search is still done manually by looking at the books. The Patient Medical Record Data Search application is used to assist the Puskesmas in managing patient data, doctor data and patient medical record data every time for treatment, so that the processed data is stored in the application database. Applications for Searching Patient Medical Record Data at the Bintunan Air Treatment Health Center have implemented one of the search algorithms, namely the Turbo Boyer Moore algorithm, where the search process is carried out per string / word through a shift in data matching between keywords and data in the database. Based on the results of black box testing, the functionality of the Patient Medical Record Data Search Application at the Bintunan Water Treatment Health Center has been running properly and is able to display medical record search results using the Turbo Boyer Moore Algorithm.