Klasifikasi Algoritma K-Nearest Neighbor Berbasis Particle Swarm Optimization Untuk Kelayakan Bantuan Rehabilitasi Rumah Tidak Layak Huni Pada Desa Lenek Duren Kecamatan Aikmel Kabupaten Lombok Timur

2019 ◽  
Vol 2 (2) ◽  
pp. 79-85
Author(s):  
Suhartini Suhartini ◽  
◽  
Hariman Bahtiar ◽  
Author(s):  
Dicki Pajri ◽  
Yuyun Umaidah ◽  
Tesa Nur Padilah

Tokopedia is a popular marketplace used by e-commerce in Indonesia. Customers’ perception of Twitter towards Tokopedia can be used as an important source of information and can be processed into useful insights. Sentiment analysis is a solution that can be used to process the customers’ perception using K-Nearest Neighbor based on Particle Swarm Optimization. The purpose of this study is to classify customers’ perception based on positive, neutral, and negative classes. The test is carried out with four different scenarios and k values which are evaluated using a confusion matrix. Evaluation results showed the distribution of the dataset is 90:10 and the value of k = 1 is the best evaluation result, which is 88.11%. The feature selection was used for results by using Particle Swarm Optimization. The Particle Swarm Optimization used 20 iterations and 10 particles. It produced 97.9% the best evaluation accuracy, 96.17% precision, 96.62% recall, and 96.39% f-measure.


Komoditi dan harganya karet mengalami perubahan yang fluktuatif dan menunjukkan pola yang tidak stasioner, di sisi lain pengambilan keputusan bisnis memerlukan data yang akurat dan terukur. Algoritma k-NN merupakan algoritma yang merupakan algoritma unsupervised, dan terbukti baik pada data mining. Sedangkan Particle Swarm Optimization (PSO) menunjukkan performa optimasi yang lebih baik dibandingkan dengan metode yang lain. Penelitian ini bertujuan untuk merancang metode prakiraan yang dapat memperkirakan tingkat harga dan volume permintaan untuk TSR 20. Prakiraan dilakukan menggunakan Jaringan Syaraf Tiruan dengan algoritma propagasi balik, dimana data yang digunakan adalah data perkembangan pasar TSR pada bursa berjangka SICOM.. Berdasarkan tiga indikator pelatihan yang dijadikan acuan dalam pemilihan arsitektur terbaik, spesifikasi ke 15 tidak perlu melakukan pelatihan sampai epoch maksimum. Dalam teknik PSO terdapat beberapa cara untuk melakukan pengoptimasian diantaranya meningkatkan bobot atribut terhadap semua atribut atau variable yang dipakai, menseleksi atribut dan fitur seleksi. Hasil penelitian dari prediksi harga komoditi karet dengan menggunakan model k-NN mendapatkan nilai RMSE sebesar 0,087 sedangkan bila menggunakan k-NN yang dioptimasi dengan menggunakan Particle Swarm Optimization didapatkan nilai RMSE sebesar 0,082 lebih baik dibandingkan dengan hanya menggunakan k-NN saja.


2020 ◽  
Vol 6 (1) ◽  
pp. 95-102
Author(s):  
Atang Saepudin ◽  
Riska Aryanti ◽  
Eka Fitriani ◽  
Dahlia Dahlia

Analisis sentimen adalah proses untuk menentukan konten dataset berbasis teks yang positif atau negatif. Saat ini, opini publik menjadi sumber penting dalam keputusan seseorang dalam menemukan solusi. Algoritma klasifikasi seperti Support Vector Machine (SVM) dan K-Nearest Neighbor (k-NN) diusulkan oleh banyak peneliti untuk digunakan dalam analisis sentimen untuk pendapat ulasan. Namun, klasifikasi sentimen teks memiliki masalah pada banyak atribut yang digunakan dalam dataset. Fitur pemilihan dapat digunakan sebagai proses optimasi untuk mengurangi set fitur asli ke subset yang relatif kecil dari fitur yang secara signifikan meningkatkan akurasi klasifikasi untuk cepat dan efektif. Masalah dalam penelitian ini adalah pemilihan pemilihan fitur untuk meningkatkan nilai akurasi Support Vector Machine (SVM) dan K-Nearest Neighbor (k-NN) dan membandingkan akurasi tertinggi untuk analisis sentimen tweet / komentar yang menggunakan tagar # 2019GantiPresiden. Algoritma perbandingan, SVM menghasilkan akurasi 88,00% dan AUC 0,964, kemudian dibandingkan dengan SVM berdasarkan PSO dengan akurasi 92,75% dan AUC 0,973. Data hasil pengujian untuk akurasi algoritma k-NN adalah 88,50% dan AUC 0,948, kemudian dibandingkan untuk akurasi dengan PSO berbasis k-NN sebesar 75,25% dan AUC 0,768. Hasil pengujian algoritma PSO dapat meningkatkan akurasi SVM, tetapi tidak mampu meningkatkan akurasi algoritma k-NN. Algoritma SVM berbasis PSO terbukti memberikan solusi untuk masalah klasifikasi tweets/ komentar yang menggunakan tagar # 2019GantiPresiden di Twitter agar lebih akurat dan optimal.


2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Xiangrong Zhang ◽  
Licheng Jiao ◽  
Anand Paul ◽  
Yongfu Yuan ◽  
Zhengli Wei ◽  
...  

A semisupervised classification method based on particle swarm optimization (PSO) is proposed. The semisupervised PSO simultaneously uses limited labeled samples and large amounts of unlabeled samples to find a collection of prototypes (or centroids) that are considered to precisely represent the patterns of the whole data, and then, in principle of the “nearest neighborhood,” the unlabeled data can be classified with the obtained prototypes. In order to validate the performance of the proposed method, we compare the classification accuracy of PSO classifier, k-nearest neighbor algorithm, and support vector machine on six UCI datasets, four typical artificial datasets, and the USPS handwritten dataset. Experimental results demonstrate that the proposed method has good performance even with very limited labeled samples due to the usage of both discriminant information provided by labeled samples and the structure information provided by unlabeled samples.


2018 ◽  
Author(s):  
nursetia wati

Completion of studies of students in a timely manner is one measure of the quality of higher education, as well as in finding a job. Anticipation that can be done is by predicting graduation, with these predictions do evaluation efforts in organizing lectures at the faculty or study program. The data in this study is the student data Gorontalo State University Faculty of Education and Faculty of Engineering from 2008 until 2012. From 5104 the total number of records is done with attribute data sorting empty, so the existing data into 2312 record. The algorithm used in this study is a K-Nearest Neighbor which will then be optimized using Particle Swarm Optimization. By using the technique Fold Cross Validation on K-Nearest Neighbor algorithm produces the highest accuracy 88.58 on the value of k = 14. The next test using particle swarm optimization algorithm to get the highest accuracy on the population size = 10 with accuracy of 89.14%.


Author(s):  
Sucitra Sahara ◽  
Rizqi Agung Permana ◽  
Hariyanto Hariyanto

Abstrak: Virus pada komputer menjadi hal yang membahayakan bagi para pengguna komputer perorangan maupun perusahaan yang telah menerapkan sistem terkomputerisasi. Virus program yang didesain untuk tujuan jahat dapat merusak bagian tertentu dari komputer, bahkan yang paling merugikan adalah dapat merusak data penting pada perusahaan. Dalam hal ini maka diciptakanlah sebuah software anti virus, perkembangan anti virus selalu lebih lambat dari virus itu sendiri, sehingga peneliti akan mengadakan penyeleksian software anti virus pada suatu opini atau berdasarkan komentar masyarakat yang telah menggunakan software anti virus produk tertentu dan dituangkan ke media online seperti komentar pada suatu situs penjualan produk tersebut. Berdasarkan ribuan komentar akan diolah dan dikelompokkan pada jenis kata teks positif dan teks negatif, dan peneliti membuat klasifikasi data dengan menggunakan metode algoritma k-Nearest Neighbor (k-NN), algoritma k-NN adalah salah satu algoritma yang sesuai dalam penelitian kali ini. Peneliti menemukan bahwa algoritma k-NN mampu mengolah data set yang sudah dikelompokan pada teks positif dan negatif khususnya dalam pemilihan teks, dan penerapan metode optimasi Particle Swarm Optimization (PSO) yang dikombinasikan dengan k-NN diharapkan mampu meningkatkan nilai akurasi sehingga datanya lebih kuat dan valid. Sebelum data set diolah menggukanan optimasi PSO hanya menggunakan metode k-NN akurasi data yang diperoleh 70,50% sedangkan hasil akurasi setelah penggunaan metode k-nn dan optimasi PSO didapatkan nilai akurasi sebesar 83,50%. Dapat disimpulkan bahwa penggunaan optimasi PSO dan metode k-NN sangat sesuai pada konsep text mining dan  penyeksian pada data set berupa text. Kata kunci: Analisis Review, Optimasi Particle Swarm Optimization, Metode k-Nearest Neighbor.   Abstract: Viruses on computers become dangerous for individual computer users and companies that have implemented computerized systems. Virus programs that are designed for malicious purposes can damage certain parts of the computer, even the most detrimental is that it can damage important data on the company. In this case an anti-virus software is created, the development of anti-virus is always slower than the virus itself, so researchers will conduct an anti-virus software selection on an opinion or based on public comments that have used a particular product's anti-virus software and poured it into online media such as comment on a product sales site. Of the thousands of comments will be processed and grouped on the type of positive and negative text words, and researchers make data classification using the k-Nearest Neighbor (k-NN) algorithm method, the k-NN algorithm is one of the appropriate algorithms in this study. The researcher found that the k-NN algorithm is able to process data sets that have been grouped in positive and negative texts, especially in text selection, and the application of the Particle Swarm Optimization (PSO) optimization method combined with k-NN is expected to be able to increase the accuracy value so that the data is stronger and valid. Before the data set is processed using PSO optimization only using the k-NN method the accuracy of the data obtained is 70.50% while the accuracy results after the use of the k-nn method and PSO optimization obtained an accuracy value of 83.50%. It can be concluded that the use of PSO optimization and the k-NN method are very compatible with the concept of text mining and correction of text data sets. Keywords: Analysis Review, k-Nearest Neighbor Method, Particle Swarm Optimization optimization


2020 ◽  
Vol 12 (2) ◽  
pp. 168-175
Author(s):  
Sumarni Sumarni ◽  
Suhardi Rustam

Problems the Topic of the final project is a form of scientific writing that contains the results of observations from a study of the problems that occur with the use of methods related to the particular field of science. Every student in every program of study must draw up a final project. However, before embarking on writing the final project, each student must have the topic area as a destination, the step of selection the topic of final project is an initial step before working on the final task. One way to get the final task is to see the value of general courses as well as courses, concentration majors, the value of which dominate the is is decent to scope the research topic. this research is conducted on the application of the method of K-Nearest Neighbor (KNN) for categorization of the value of the courses of concentration for the coverage of the research topic, topic the entire value in the dataset will be classified by KNN and in the optimization with the Particle swarm Optimization algorithm (PSO). The experimental categorization of the final project is built with the training data Mahasiswa Universitas Ichsan Gorontalo that has been classified previously and test data derived from the entire value of the courses is not yet known categories. The results of the experiments, the value of the resulting accuracy of algorithms KNN, namely the value of the best accuracy with K=3, K Folds = 10 has an accuracy that is 72.46% and the Algorithm of KNN-PSO best accuracy with K=3, K Folds = 10 has an accuracy that is 89.86%, shows the accuracy is better by using the optimization algorithm


Sign in / Sign up

Export Citation Format

Share Document