Claim Missing Document
Check
Articles

Found 5 Documents
Search

Klasifikasi Teks Bahasa Indonesia Pada Corpus Tak Seimbang Menggunakan NWKNN Ridok, Achmad; Latifah, Retnani
Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) 2015
Publisher : Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (604.819 KB)

Abstract

Pada umumnya pengklasifikasian teks mengasusumsikan data latih terdistribusikan sama rata pada setiap kategori. Padahal pada kenyataannya kumpulan data yang tidak seimbang sering kali muncul. Penelitian ini mencoba menerapkan algoritma Neighbor Weighted K-Nearest Neighbor (NWKNN) untuk mengklasifikasikan dokumen teks berbahasa Indonesia dengan corpus yang tidak seimbang. Algoritma ini memberikan bobot yang kecil untuk tetangga – tetangga yang berasal dari kategori yang besar dan memberikan bobot yang besar pada tetangga – tetangga yang berasal dari kategori yang kecil. Hasil uji coba sistem pada 785 dokumen dari 8 kategori dengan rasio dokumen latih 75% dan dokumen uji 25% serta exponent = 2 dan threshold document frequency = 5, menunjukkan nilai rata - rata precision, recall dan F1 measure masing-masing sebesar 84.2%, 86.7% dan 84.3%. Hasil perbandingan dengan algoritma KNN menunjukkan nilai recall dan F1 measure NWKNN masing-masing lebih tinggi sebesar 6.9% dan 2.6% daripada nilai recall dan F1 measure KNN.
Functional Requirement Design for Optimizing Tourism Promotion of DKI Jakarta based on Descriptive Research Method Wastam, Jumail; Prasetya, Eka Budhy; Latifah, Retnani
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 2, May-2018
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (801.069 KB) | DOI: 10.22219/kinetik.v3i2.600

Abstract

This study presents data collected as sample from two places of tourism spots, TMII and MONAS. Furthermore, additional data has also been collected from public places such as campuses to support current data collection. The data is collected in order to recognize the visitors’ responses according to their tourism information needs in preparing their traveling activities. Descriptive research method adopted using self-designed questionnaires focusing on “what” is applied to investigate the questions which are related with the topic of the study. The results of data analysis would be referred as foundation in designing the system functionalities required to develop an application for the future development. Furthermore, more data is observed from some data resources such as Central Bureau of Statistics (BPS) of DKI Province and Global Destination Cities Index to recognize the performance of DKI Jakarta in receiving visitors within the last three years compared to other cities in some neighboring countries such as Bangkok, Kuala Lumpur and Singapore. Thirty respondents are involved in the study to identify what potential information which can be explored. The information which is related to visitors’ travel preparation becomes imperative to be analyzed to optimize the tourism promotion. Descriptive research method helps researchers in obtaining data on functional needs according to the current state of society, in the scope of travel activities and preparations. The system design viewed from the functional needs shows what people can do based on the results of the analysis.
Penentuan Jenis Strategi Pemasaran Menggunakan Metode SWOT dan QSPM Pada UMKM Fashion di Kelurahan Penggilingan Berbasis Teknologi Rully Mujiastuti; Retnani Latifah; Hendra Hendra
Jurnal Ilmiah FIFO Vol 11, No 1 (2019)
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/fifo.2019.v10i1.006

Abstract

In this study an analysis of the actual conditions of MSMEs in the Pengilingan Village was carried out. Business people do not know what marketing strategies to do to overcome various emerging problems such as resources, business competition, purchasing power and are dominated by the limitations of technological innovation and the ability to use technology to gain a wider market share. This study uses data processing methods in the form of Strengths, Weaknesses, Opportunities and Threats (SWOT) and Quantitative Strategic Planning Matrix (QSPM). SWOT is used to measure internal conditions, in the form of strengths and weaknesses made in the IFE matrix and external conditions in the form of opportunities and threats made in the EFE matrix. The processing method consists of three stages, namely the input stage, the matching stage and the decision stage. The first stage is given the weight, rating and calculation of the weighted value of the IFE and EFE matrix, the second stage is through the formulation of marketing strategies with the Internal External (IE) and SWOT matrix, and the last stage is the decision stage to choose the existing strategy using the QSPM method. Tests were conducted on 38 data through validity and reliability tests to determine whether the questionnaire instruments used were valid and reliable using Cronbach Alpha correlation. The results obtained are that the reliability of the questionnaire is 0.795 which indicates that the sample has a high scaling consistency. Because the value of Cronbach Alpha is more than 0.6, it can be said that all the questionnaire items tested are reliable. The results obtained are then seen by the correlation with inbound marketing. Obtained the correlation reached 0.942 with a significance level of 1%. From these results it can be concluded that there is a very strong connection between the use of technology and an increase in the number of consumersKey words : Technology, Strategic Planning, Inbound Marketing, UMKM Abstrak Pada penelitian ini dilakukan analisis kondisi aktual UMKM Fashion di Kelurahan Penggilingan. Para pelaku usaha belum mengetahui strategi pemasaran apa yang harus dilakukan untuk mengatasi berbagai permasalahan yang muncul seperti sumber daya, persaingan usaha, daya beli dan didominasi oleh  keterbatasan inovasi teknologi dan kemampuan menggunakan teknologi untuk memperoleh pangsa pasar yang lebih luas. Penelitian ini menggunakan metode pengolahan data berupa Strengths, Weaknesses, Opportunities dan Threats (SWOT) dan Quantitative Strategic Planning Matrix (QSPM).  SWOT digunakan untuk mengukur kondisi internal, berupa kekuatan dan kelemahan yang dibuat dalam matriks IFE dan kondisi eksternal berupa peluang dan ancaman yang dibuat dalam matriks EFE. Metode pengolahannya terdiri dari tiga tahap, yaitu tahap pemasukan (input stage), tahap pencocokan (the matching stage) dan tahap keputusan (decision stage). Pada tahap pertama diberikan bobot, rating dan perhitungan  nilai tertimbang dari matriks IFE dan EFE, tahap kedua melalui perumusan strategi pemasaran dengan matriks Internal Eksternal (IE) dan SWOT, dan tahap terakhir adalah tahap keputusan memilih alternatif strategi yang ada menggunakan metode QSPM. Pengujian dilakukan  terhadap 38 data melalui uji validitas dan reliabilitas  untuk mengetahui apakah instrument kuesioner yang digunakan sudah valid dan reliable dengan  menggunakan korelasi Cronbach Alpha. Diperoleh hasil bahwa reliabilitas dari kuesioner adalah 0.795 yang menunjukkan bahwa sampel memiliki konsistensi penskalaan yang tinggi. Karena nilai Cronbach Alpha lebih dari 0,6 maka dapat dikatakan bahwa semua item kuesioner yang diuji adalah reliable. Hasil yang diperoleh kemudian dilihat dengan korelasinya dengan inbound marketing. Didapat hasil korelasinya mencapai 0.942 dengan taraf keberartian 1%. Dari hasil tersebut dapat disimpulkan bahwa ada keterhubungan yang sangat kuat antara penggunaan teknologi dengan peningkatan jumlah konsumen. Kata Kunci: Teknologi, Strategi pemasaran, Inbound marketing, UMKM 
ANALISIS TENDENSI PORTAL BERITA ONLINE TERHADAP VAKSINASI COVID-19 DI INDONESIA MENGGUNAKAN METODE K-NEAREST NEIGHBOR Adharani, Yana; Saputra, Ambar Dwi; Rosanti, Nurvelly; Latifah, Retnani
Jurnal Sistem Informasi, Teknologi Informatika dan Komputer Volume 13 No 2, Januari Tahun 2023
Publisher : Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/justit.13.2.125-137

Abstract

Di Indonesia per 27 Juli 2021 ada 4.170.155 kasus terkonfirmasi COVID-19. Salah satu cara untuk menekan peningkatan dan penyebaran kasus COVID-19 adalah dengan melakukan vaksinasi. Terkait dengan hal tersebut, ada beberapa berita tentang vaksin COVID-19 di portal berita. Pemberitaan yang diberikan memiliki tendensi positif, negatif maupun netral yang dapat memengaruhi pandangan masyarakat terhadap pemberian vaksin COVID-19. Dalam penelitian ini dilakukan klasifikasi terhadap tendensi pemberitaan portal berita terhadap vaksin COVID-19 menggunakan metode K-Nearest Neigbor (KNN). Pengujian dilakukan terhadap 1000 data dengan 5 kombinasi data training dan testing sebanyak 50 kali dengan nilai k berbeda. Pelabelan data dilakukan secara manual dan otomatis menggunakan sentistrenth_id. Hasil Pengujian pelabelan manual menunjukan tingkat accuracy tertinggi sebesar 78,50% pada k = 6. Untuk pelabelan otomatis diperoleh accuracy tertinggi sebesar 93% pada k = 6. Accuracy tertinggi diperoleh untuk penggunaan data training sebesar 80% dan data testing 20%. Tingkat accuracy yang belum optimal diakibatkan karena jumlah data pada setiap kelas tidak berimbang dan terdapat pelabelan pada data training maupun testing yang tidak akurat. Aplikasi dapat mengidentifikasi kata-kata dominan, baik dalam pemberitaan positif, negatif maupun netral untuk kelas yang teridentifikasi.Kata Kunci: klasifikasi, COVID-19, K-Nearest Neigbor, portal berita, vaksinasi
Pengaruh Jarak Objek Citra pada Model Deteksi dan Klasifikasi Botol Plastik menggunakan YOLO Rosanti, Nurvelly; Latifah, Retnani; Munir, Sirojul; Maududi, Izzuddin Al Qossam
Jurnal Teknologi Terpadu Vol 10 No 1 (2024): Juli, 2024
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v10i1.1247

Abstract

Plastic bottle waste must be separated based on shape and size to facilitate recycling. Sorting plastic bottles can use object detection technology to facilitate classification using images. Image distance capture affects the classification of bottle waste because large bottles will look small when seen from a distance and vice versa. This study aims to create a plastic bottle detection and classification model using the YOLOv8 algorithm with the same bottle shape but different sizes and measure the effect of image distance on the model. Bottles consist of three sizes: large bottles measuring 1500 ml, medium bottles measuring 600 ml, and small sizes 330 ml. Pictures for the bottle image dataset were shot between 80 and 100 centimeters away. Robotoflow was used to produce the dataset. Model performance evaluation used Mean Average Precision, and model testing used a confusion matrix. The test results for the same model with an image capture distance had an accuracy value of 100%. Testing of 80 cm distance images applied to the 100 cm model had an accuracy of 67%. Testing for 100 cm distance images applied to the 80 cm model was still quite good, with an accuracy of 91.6%. The results obtained show that the image distance affects the results of the model that has been built, so use an image that matches the distance applied to the model.