The high low price of gold influenced by many factors such as economic conditions, inflation rate, supply and demand and much more. The Naïve Bayes algorithm is capable of generating a classification that is used to predict future opportunities. By using the Naïve Bayes Classifier algorithm obtained a prediction of gold prices that can help decision makers in determining whether to sell or buy gold. By using the Naïve Bayes Classifier algorithm obtained a prediction of gold prices that can help decision makers in determining whether to sell or buy gold. Gold data will be processed using Rapidminer software. Stages of processing are reading training data, calculating the mean and standard deviation, entering the test data and finding the density value of gauss and then looking for probability value. Based on the calculation that has been done, Naïve Bayes Classifier method is able to predict the price of gold for 1 day ahead or every day. With the results of this calculation is expected to help gold investment actors in increasing accuracy to predict gold prices for decision making.
This study aims to present diagnose of melanoma skin cancer at an early stage. It applies feature extraction method of the first order for feature extraction based on texture in order to get high degree of accuracy with method of classification using artificial neural network (ANN). The method used is training and testing phases with classification of Multilayer Perceptron (MLP) neural network. The results showed that the accuracy of test image with 4 sets of training for image not suspected of melanoma and melanoma with the lowest accuracy of 80% and the highest accuracy of 88.88%, respectively. The 4 sets of training used consisted of 23 images. Of the 23 images used as a training consisted of 6 as not suspected of melanoma images and 17 as suspected melanoma images.
Tujuan dari penelitian ini adalah untuk membangun aplikasi Sistem Pakar untuk diagnosis penyakit Osteoporosis. Penelitian ini menggunakan metode Certainty Factor karena dalam metode ini terdapat suatu nilai berupa nilai kepercayaan (Measure Of Belief) dan nilai ketidakpercayaan (Measure Of Disabelief) pada suatu gejala, dimana nantinya nilai tersebut dapat menghasilkan nilai CF (Certainty Factor) sebagai tolak ukur, semakin besar nilai CF (Certainty Factor) yang diperoleh maka semakin besar peluang penyakit itu akan menyerang kita, dimana hasilnya ditampilkan dalam bentuk kondisi pengguna yang terkait dengan penyakit Osteoporosis. Hasil penelitian ini juga dilengkapi dengan solusi penyakit dan perawatan yang ditampilkan dalam bentuk website dengan menggunakan pemrograman PHP dan juga berguna untuk melakukan diagnosa awal terhadap suatu penyakit yang dirasakan oleh user, sehingga membantu user dalam mengenali gejala-gejala penyakit Osteoporosis yang mereka rasakan, serta dengan adanya sistem pakar ini dapat dijadikan solusi alternatif bagi masyarakat untuk melakukan diagnosa dini terhadap gejala-gejala penyakit Osteoporosis yang mereka rasakan sebelum melakukan konsultasi langsung dengan pakar dalam hal ini dokter spesialis tulang. Sistem ini mampu menyimpan representasi pengetahuan pakar berdasarkan nilai kepercayaan (certainty factor) dengan keakuratan sebesar 80%.
Retail is one or more activities that add value to the product to the consumer either for family needs or for personal use. Retail can sell products depending on current market needs. The goods we enjoy today are not apart from retail services, retail helps producers / distributors and consumers so that every need will be fulfilled. In this problem the author tries to do retail store research in the city of Padang. This research aims to help retail stores to forecast procurement of goods. Artificial Neural Network Backpropagation can make the forecasting process for procurement of goods for the next period of time on each item on the retail and will ultimately be useful for retail store managers. The forecasting process begins with determining the variables that will be required in the network pattern, then the pattern of established network will be continued on the network training process by using backpropagation algorithm. After doing the network training process the researchers will do a comparison with some pattern of network that has been formed. The last process undertaken in this research is the process of determining the best network pattern of the average value of errors obtained from each training network pattern. In the final result of the forecasting process, the results of the calculation have a total error of = 3.57%. Judging from the forecasting process that will be done not only used to predict the procurement of goods but also can predict sales figures in retail stores. In principle, this research can help to determine the procurement of goods in the sales process that will minimize the losses that occur in every sales activity.
Abstrak Data rekam medis adalah catatan khusus pasien yang sedang, seringkali data rekam medis hanya menjadi data yang menumpuk dan tidak dilakukan penelusuran untuk menghasilkan pengetahuan yang berguna bagi rumah sakit. Penelitian ini bertujuan mengolah tumpukan data rekam medis untuk mengklasifikasikan jenis penyakit yang terjadi pada rumah sakit berdasarkan pada kode penyakit internasional (International Classification of Disease) ICD-10. Metode yang digunakan dalam penelitian ini adalah metode algoritma C4.5 dengan menggunakan atribut kode penyakit internasional sebagai atribut label tujuan sebanyak 21 kelompok penyakit internasional, yaitu: A00-B99 sampai dengan Z00-Z99. Penilitian ini menghasilkan pohon keputusan dari 21 berupa value atribut tujuan kode penyakit, algoritma C4.5 dapat merepresentasikan sebanyak 14 value atribut tujuan kode penyakit dan persentasi data yang terbaca lebih dari 66%. Kesimpulan dari penelitian ini yaitu algoritma C4.5 membantu mengklasifikasikan kode penyakit internasional berdasarkan ICD-10 dan membentuk pohon keputusan yang dapat memberikan informasi penyakit apa saja yang sering terjadi pada rumah sakit Kata kunci: data mining, klasifikasi, C4.5, rekam medis, ICD-10
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.