Garuda - Garba Rujukan Digital

ANALISIS PEMILIHAN CLUSTER OPTIMAL DALAM SEGMENTASI PELANGGAN TOKO RETAIL Murpratiwi, Santi Ika; Agung Indrawan, I Gusti; Aranta, Arik
Jurnal Pendidikan Teknologi dan Kejuruan Vol 18, No 2 (2021): Edisi Juli 2021
Publisher : Universitas Pendidikan Ganesha

Saat ini pemanfaatan data menjadi fokus dalam bidang pemasaran khususnya untuk menyusun strategi. Agar strategi pemasaran bisa tepat sasaran dibutuhkan segmentasi pelanggan. Data mining khususnya clustering mampu membantu proses segmentasi pelanggan. Dalam penelitian ini, data mining diimplementasikan untuk segmentasi pelanggan UD. XYZ dengan metode K-Means, K-medoids, dan Means.. Tujuan penelitian ini adalah mencari metode dan nilai k terbaik yang dihasilkan dari tiga metode clustering. Penelitian ini menyajikan proses Data Mining dengan menggabungkan model RFM dengan algoritma clustering K-Medoids, X-Means, dan K-Means. Dataset yang telah diimplementasikan ke dalam model RFM digunakan sebagai bahan pengolahan data. Data transaksi dengan jumlah 153.492 diimplementasikan ke dalam model RFM menjadi 10.145 data untuk dilakukan identifikasi pelanggan potensial. Inisialisasi cluster awal pada metode K-Medoids, X-Means, dan K-Means dilakukan secara random. Nilai k dalam penelitian ini diinisialisasi dari 1 sampai 10. Nilai k diimplementasikan secara berulang dan dihitung validasi cluster menggunakan metode David Bouldin Index (DBI) dan jaraj rata-rata cluster dengan centroid. Hasil penelitian menunjukkan K-medoids memiliki nilai validitas yang lebih baik dibandingkan dengan X-Means dan K-Means. Rata-rata nilai DBI yang dihasilkan metode K-Medoids adalah 0,540778. Jumlah cluster terbaik yang dihasilkan adalah 5 cluster, hal ini ditentukan dengan mempertimbangkan jumlah persebaran data pada k = 5 yang menghasilkan nilai sama pada metode K-Medoids, X-Means, dan K-Means. Tingkatan pelanggan yang terbentuk adalah About To Sleep, Customer Needing Attention, Recent Customer, Potential Loyalist, dan Loyal Customers.

Rancang Bangun Aplikasi Transliterasi Aksara Bali Menjadi Huruf Latin Menggunakan Metode Rule Based Pada UTF-16 Berbasis Android Aranta, Arik; Andika, I Gede
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol. 6 No. 3 (2023): Jurnal RESISTOR Edisi Desember 2023
Publisher : Prahasta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31598/jurnalresistor.v6i3.1426

Balinese script is a script that has been used by Balinese tribes since ancient times, as evidenced by thediscovery of 2,103 ancient lontars using Balinese script in Klungkung, Bali. Currently, Google alreadyhas a virtual keyboard that can be downloaded to a smartphone. This Google keyboard already hasBalinese script mode that the letters was based on Unicode, but it still doesn't have a feature that canread Balinese script into Latin letters. By combining these two problems, a study was designed aboutmaking applications that can preserve Balinese script by utilizing the Balinese script keyboard featureprovided by Google to be transliterated into Latin letters. In this study, a rule based method is used toperform transliteration in order to be able to adjust to the rules of reading Balinese script correctly. It isalso used to provide ID for each Balinese character using hexadecimal based on the UnicodeTransformation Format-16 code for each character. The application was built by implementing of total940 rules and 33.253 words, after testing the application the result obtained from the transliterasionreach 99.4% of succeed from 1104 Balinese script words.

ANALISIS PEMILIHAN CLUSTER OPTIMAL DALAM SEGMENTASI PELANGGAN TOKO RETAIL Murpratiwi, Santi Ika; Agung Indrawan, I Gusti; Aranta, Arik
Jurnal Pendidikan Teknologi dan Kejuruan Vol. 18 No. 2 (2021): Edisi Juli 2021
Publisher : Universitas Pendidikan Ganesha

Saat ini pemanfaatan data menjadi fokus dalam bidang pemasaran khususnya untuk menyusun strategi. Agar strategi pemasaran bisa tepat sasaran dibutuhkan segmentasi pelanggan. Data mining khususnya clustering mampu membantu proses segmentasi pelanggan. Dalam penelitian ini, data mining diimplementasikan untuk segmentasi pelanggan UD. XYZ dengan metode K-Means, K-medoids, dan Means.. Tujuan penelitian ini adalah mencari metode dan nilai k terbaik yang dihasilkan dari tiga metode clustering. Penelitian ini menyajikan proses Data Mining dengan menggabungkan model RFM dengan algoritma clustering K-Medoids, X-Means, dan K-Means. Dataset yang telah diimplementasikan ke dalam model RFM digunakan sebagai bahan pengolahan data. Data transaksi dengan jumlah 153.492 diimplementasikan ke dalam model RFM menjadi 10.145 data untuk dilakukan identifikasi pelanggan potensial. Inisialisasi cluster awal pada metode K-Medoids, X-Means, dan K-Means dilakukan secara random. Nilai k dalam penelitian ini diinisialisasi dari 1 sampai 10. Nilai k diimplementasikan secara berulang dan dihitung validasi cluster menggunakan metode David Bouldin Index (DBI) dan jaraj rata-rata cluster dengan centroid. Hasil penelitian menunjukkan K-medoids memiliki nilai validitas yang lebih baik dibandingkan dengan X-Means dan K-Means. Rata-rata nilai DBI yang dihasilkan metode K-Medoids adalah 0,540778. Jumlah cluster terbaik yang dihasilkan adalah 5 cluster, hal ini ditentukan dengan mempertimbangkan jumlah persebaran data pada k = 5 yang menghasilkan nilai sama pada metode K-Medoids, X-Means, dan K-Means. Tingkatan pelanggan yang terbentuk adalah About To Sleep, Customer Needing Attention, Recent Customer, Potential Loyalist, dan Loyal Customers.

ANALISIS SENTIMEN MASYARAKAT TERHADAP KEBIJAKAN PENERAPAN PPKM DI MEDIA SOSIAL TWITTER DENGAN MENGGUNAKAN METODE XGBOOST Widiarta, I Putu Angga Purnama; Dwiyansaputra, Ramaditia; Aranta, Arik
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 5 No 2 (2023): September 2023
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v5i2.342

Corona Virus Disease (Covid-19) is a virus that causes respiratory infections in humans. Indonesia is a country that has been infected with this virus, the implementation of restrictions on community activities (PPKM) is implemented by the government as a policy to reduce the spread of Covid-19. Pros and cons arise due to the impact of the policy. Therefore, assessing how public opinion or sentiment is towards this policy is important to do. This study aims to implement the XGBoost algorithm in the sentiment classification process. Sentiment analysis targets public opinion on Twitter, the dataset used is 1958 positive tweets and 3980 negative tweets. At the preprocessing stage, case-folding, stopwords removal, tokenizing, and stemming are carried out. Giving weights to terms uses the Term Frequency-Relevance Frequency method to turn each term into a number. In the final stage, classification is carried out by implementing the XGBoost method with optimal hyperparameter scores. K-fold cross validation is used to evaluate model performance. Based on the evaluation results, the best performance was obtained by a model with a hyperparameter value with an n_estimator of 1000, a learning_rate of 0.1, a max_depth of 6, a subsample of 1, a gamma of 0 and utilizing the stem-ming process in preprocessing with an accuracy value of 85.27%. precision of 86.07%, and recall of 85.23%.

IMPLEMENTASI METODE PROTOTYPE DALAM SISTEM ABSENSI SISWA SMK NEGERI 1 SIKUR Tyas, Tiya Suryaning; Afwani, Royana; Murprawati, Santi Ika; Aranta, Arik
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 6 No 1 (2024): March 2024
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v6i1.366

The incorporation of information technology is critically important in various aspects of life, with education being no exception. Technology has demonstrated its efficacy in supporting the operations of numerous institutions, including educational establishments. Nevertheless, despite the swift progress of technology, many institutions, particularly schools, still adhere to traditional systems in their daily operations. This includes the procedure for tracking student attendance, which can result in inefficiencies. This research endeavors to address this issue by conceptualizing, constructing, and implementing a web-based system for managing student attendance, focusing on streamlining the process of recording and handling attendance data. This system utilizes web technology and a database to establish a platform, with CodeIgniter4 serving as the fundamental framework for website development, following the prototype method. The research is carried out at SMKN 1 SIKUR and the system will record student attendance data, which will be stored in the database of SMK N 1 Sikur, and is expected to replace the current method of recording student attendance. The percentage of respondents with a "strongly agree" opinion increased from 36% to 52% after the update to the previous prototype. It is hoped that further development can be undertaken to facilitate direct implementation.

RANCANG BANGUN ALGORITMA KONVERSI SUARA BERBAHASA INDONESIA MENJADI TEKS LATIN BERBAHASA SASAK MENGGUNAKAN METODE DICTIONARY BASED Shabrina, Marwati Maryam; Aranta, Arik; Irmawati, Budi
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 6 No 1 (2024): March 2024
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v6i1.371

As time goes by, the use of the Sasak language among the people of Lombok is decreasing. In fact, the Sasak language is the identity of the island of Lombok which needs to be preserved as a heritage for the younger generation. The increasingly rapid development of technology has encouraged the emergence of innovation in creating various inventions that can facilitate human activities. One innovation that can be developed is speech to text technology. This technology can recognize human voices and then convert them into text. This is of interest to the author in designing a system that implements Google’s speech to text API to translate Indonesian words or sentences into Sasak. The translation from Indonesian to Sasak was carried out by applying a dictionary based system to produce an appropriate translation. The testing process was carried out by translating 25 sentences taken from the Sasak-Indonesian Dictionary and consisting of 117 words. In this research, there were two stages of testing carried out. The first test was carried out to determine the accuracy of the results of the Indonesian translation into Sasak using the dictionary based method. The second test was carried out to determine the accuracy of the Google Speech API in recognizing voice input and then converting it into text. From the first test, the system accuracy results in translating Indonesian to Sasak using the dictionary based method were 100% and the error rate was 0%. Meanwhile, from the second test, the results showed that the system could implement the Google Speech API to translate Indonesian words or sentences into Sasak with an accuracy of 99.14%.

ANALISIS SENTIMEN PENGGUNA PLATFORM MEDIA SOSIAL X PADA TOPIK PEMILIHAN PRESIDEN 2024 MENGGUNAKAN PERBANDINGAN MODEL MONOLINGUAL DAN MULTILINGUAL BERT Nurhasiyah, Nurhasiyah; Dwiyansaputra, Ramaditia; Ika Murpratiwi, Santi; Aranta, Arik
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 1 (2025): JATI Vol. 9 No. 1
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i1.12430

Pemilihan Presiden 2024 di Indonesia merupakan topik penting yang banyak dibahas di media sosial, terutama platform X (sebelumnya Twitter). Media sosial ini menyediakan ruang bagi jutaan pengguna untuk berbagi opini yang dapat diolah menjadi data sentiment. Namun, menganalisis opini dalam jumlah besar membutuhkan model yang tepat. Penelitian ini bertujuan untuk menganalisis sentimen publik terkait topik tersebut menggunakan perbandingan model monolingual (IndoBERT) dan multilingual (mBERT), model digunakan untuk mengklasifikasikan sentiment positif, netral, dan negatif. Penelitian dilakukan dengan metode BERT yang meliputi data crawling, preprocessing, labeling, data spliting, implementation model dan evaluation. Dataset terdiri dari 10.140 tweet yang melalui proses preprocessing berupa cleaning, case folding, dan tokenizing, dan proses pelabelan sentiment (positif, netral, negatif). Hasil penelitian menunjukkan bahwa model IndoBERT memiliki akurasi tertinggi sebesar 84% dengan presisi 75%, recall 80%, dan F1-Score 78%, sedangkan mBERT mencatat akurasi 81%, presisi 69%, recall 78%, dan F1-Score 73%. Model IndoBERT terbukti lebih unggul dalam memahami konteks bahasa Indonesia dibandingkan mBERT,terutama pada sentiment positif dan negatif, itu karena keterbatasan dalam menangkap konteks khusus Bahasa Indonesia. Evaluasi menggunakan confusion matrix untuk mendukung pernyataan ini. Hasil penelitian ini diharapkan dapat membantu pengembangan teknologi pemrosesan bahasa alami (NLP) untuk mendukung pemahaman opini publik, terutama di sektor sosial-politik Indonesia.

ANALISIS SENTIMEN PADA PENGGUNA APLIKASI X TERHADAP PEMILIHAN UMUM PRESIDEN 2024 MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN) Nurfauziyah, Nurfauziyah; Dwiyansaputra, Ramaditia; Ika Murpratiwi, Santi; Aranta, Arik
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 9 No. 1 (2025): JATI Vol. 9 No. 1
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v9i1.12437

Pemilihan Umum Presiden 2024 menjadi perhatian besar masyarakat Indonesia, terutama di media sosial seperti Aplikasi X. Media sosial menyediakan data yang kaya akan opini publik, namun analisis sentimen terhadap teks tidak terstruktur menghadapi tantangan, seperti pola bahasa informal dan campuran bahasa. Penelitian ini bertujuan menganalisis sentimen publik terkait Pemilu 2024 menggunakan Convolutional Neural Network (CNN). Dataset terdiri dari 10.250 tweet yang dikumpulkan melalui Twitter API selama Juni–September 2024. Data diproses melalui pembersihan, tokenisasi, stemming, pelabelan sentimen menggunakan VADER, dan pelatihan model CNN. Penelitian ini mencakup enam percobaan, termasuk penghapusan stopwords, penggunaan bobot TF-IDF, dan modifikasi arsitektur CNN. Hasil terbaik diperoleh dari kombinasi CNN dan TF-IDF dengan akurasi 84%, precision 83%, recall 83%, dan F1-score 83%. Distribusi sentimen menunjukkan 45,42% positif, 37,53% negatif, dan 17,04% netral. Penelitian ini mengonfirmasi efektivitas CNN dengan TF-IDF dalam menganalisis sentimen dari teks kompleks di media sosial.

RANCANG BANGUN SISTEM INFORMASI PEMESANAN TIKET TRAVEL BERBASIS WEBSITE MENGGUNAKAN METODE EXTREME PROGRAMMING (STUDI KASUS: FAJRI JAYA TRAVEL) Sansabila, Rosa; Albar, Moh. Ali; Aranta, Arik
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 7 No 2 (2025): September 2025
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v7i2.481

Fajri Jaya Travel is a transportation service provider based in West Nusa Tenggara. In conducting its business activities, the company still uses the manual method, where prospective passengers are required to either visit the ticket agent in person or contact them by phone to book tickets or inquire about schedules, ticket prices, or seat availability. This method is inefficient and time-consuming, especially for people living far from ticket agents or having difficulties accessing information quickly. Furthermore, this approach is susceptible to recording errors, such as incorrect passenger data or duplicate seat numbers. To address this issue, this study aims to develop an online ticket booking system for Fajri Jaya Travel. This system will allow prospective passengers to obtain departure schedules and book tickets through a website, without the need to visit a ticket agent in person and minimizing data entry errors. This system is built using the Bootstrap and Laravel frameworks with the Extreme Programming development method. The system was tested using Black Box Testing to assess functionality and the Mean Opinion Score method to evaluate user satisfaction, resulting in average scores of 4.4 from administrators, 4.0 from drivers, and 4.55 from general users, indicating a high level of satisfaction.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search