Klasifikasi Multi Output pada Harga Smartphone Menggunakan Learning Vector Quantization (LVQ) dan Backpropagation (BP)

Dinita Rahmalia (Universitas Islam Darul Ulum Lamongan)
Mohammad Syaiful Pradana (Universitas Islam Darul Ulum Lamongan)
Teguh Herlambang (Universitas Nahdlatul Ulama Surabaya)

Systemic: Information System and Informatics Journal
Vol. 6 No. 2 (2020): Desember

There are many smartphones with various price sold in market. The price of smartphone is affected by some components such as weight, internal storage, memory (RAM), rear camera, front camera and brands. There are two methods for classifying price class of smartphone in market such as Learning Vector Quantization (LVQ) and Backpropagation (BP). From classifying price class of smartphone in market using LVQ and BP, there are the differences on the both of them. LVQ classifies price range of smartphone by euclidean distance of weight and data on its iteration. BP classifies price range of smartphone by gradient descent of target and output on its iteration. In multi output classification, one object may have multi output. Based on simulation results, BP gives the better accuracy and error rate in training data and testing data than LVQ.