Diabetes mellitus is a chronic metabolic disorder caused by the pancreas that does not produce enough insulin, so the body works to be disturbed. But by knowing the symptoms that exist, prevention of diabetes mellitus disease can be done as early as possible with the help of expert systems.One method of expert system used to diagnose symptoms of Diabetes Mellitus is Certainty Factor. The process undertaken in this research starts from literature studies, system design, system implementation and the last is testing the system. In the system design process is done by designing the database required by the expert system and also design the system interface design. After the design process is done then the next step is to implement the design into an expert system application. By using this method, the system gives results of possible symptoms experienced, presentation of beliefs, and treatment solutions based on the facts and the value of confidence given by users in filling out questions that have been given by the system.The results of this system are used to help medical personnel and patients in order to identify the symptoms of diabetes mellitus
The existence of customers for the course of a business is very important. Customers have a tendency to continue to subscribe to the company or to stop subscribing. One technique that can be used to identify trends in customer loyalty is data classification. Based on customer-owned data the company can do data processing or data mining by classifying loyal and non-loyal customers. There are many methods that can be applied for data classification, including the Naïve Bayes algorithm and C4.5. Both of these methods produce different accuracy when used for the data classification process. Two scenarios are used in the process of testing both algorithms, scenarios for dividing data in testing and training data and testing scenarios using cross validation. The results of these two scenarios show that the C4.5 method is superior to the Naïve Bayes method with scenario 1 accuracy of 78.6086% and scenario 2 accuracy of 78.61%.
Stroke is one of the deadly diseases. This is illustrated in stroke deaths in Indonesia which reached a death rate of 131.8 cases. Some of the things that cause a stroke to become a disease with the highest mortality rate are related to transitions in human life in 4 aspects, namely epidemiology, demography, technology, and economics, socio-culture. Of the many influencing aspects, one of the transition points of human life in the technological aspect can be an alternative solution and prevention. Aspects of technology with the utilization of data can be used as a preventive measure for stroke. One approach is to use data mining techniques, which can provide an initial picture regarding the chances of getting a stroke so that it can be used as an early warning for patients. With so many techniques in data mining, this study used a classification or grouping approach using 2 algorithms, namely K-Nearest Neighbor and one of the Neural Network groups, namely Multi-Layer Perceptron. This research will focus on finding the accuracy and best results of the two algorithms in classifying. The final result of this study is that the K-Nearest Neighbor algorithm has a better accuracy of 95% compared to the Multi-Layer Perceptron which produces an accuracy of 88%
Sentimen adalah proses komputasional dalam mengidentifikasi dan mengategori opini-opini dalam bentuk potongan teks, khususnya untuk mengukur maksud si pembuat potongan teks terhadap topik tertentu, dapat bernada positif, negatif, atau netral. Dalam konteks layanan perusahaan, sentimen yang sering muncul biasanya adalah sentiment yang bernilai positif dalam bentuk pujian dan apresiasi maupun sentiment bernilai negatif dalam bentuk complain. Ketika komplain dilakukan oleh pelanggan, maka pihak perusahaan harus dapat melakukan tindakan untuk menanggulangi komplain tersebut, yang dimungkinkan dapat berimbas terhadap kredibilitas perusahaan, bahkan dapat berimbas pada harga saham. Sosial media menjadi tempat yang dapat digunakan untuk menyampaikan keluhan maupun review positif dari pelanggan terhadap layanan yang diberikan oleh perusahaan. Proses analisis sentimen pelanggan terhadap layanan perusahaan perlu dilakukan untuk mengetahui seberapa besar jumlah sentimen yang muncul menggunakan metode KNN dengan studi kasus pada perusahaan telekomunikasi di Indonesia. Kemudian dilakukan analisis regresi untuk menilai apakah jumlah sentimen pelanggan berpengaruh terhadap harga saham perusahaan. Penelitian ini menghasilkan sentimen positif sebesar 16% , sentimen negatif sebesar 78 % dan sentimen netral sebesar 6%. Metode KNN menghasilkan akurasi paling tinggi sebesar 79,06% pada cross validation = 4. Jumlah sentimen negatif dan harga saham memiliki nilai regresi dan nilai korelasi sebesar 0,46 atau dengan kata lain tidak memiliki keterikatan satu sama lain. Sentimen positif menghasilkan nilai regresi dan korelasi sebesar 0,02 dengan artian memiliki keterikatan satu sama lain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.