Claim Missing Document
Check
Articles

PELATIHAN PEMBUATAN DESAIN GRAFIS MULTIMEDIA INTERAKTIF DI SMA NEGERI 13 PALEMBANG Tandoballa, Lucky; Wahyuni, Sri; Agustria, Kevin; Hartati, M. Kom, Ery
Aptekmas Jurnal Pengabdian pada Masyarakat Vol 7 No 3 (2024): APTEKMAS Volume 7 Nomor 2 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Most importance of digital technology in the 4.0 era and 5.0 society, with a focus on the graphic design profession, which works with various visual media such as illustration, typography, photography, animation and video to create creative works such as brochures and advertisements. Presenting interesting and informative information through infographics is key to conveying messages to readers using apps like Canva. Canva, founded in 2012 by Melanie Perkins, is an online graphic design tool that allows users to easily create and edit designs. The use of Canva in the world of education, such as at SMA Negeri 13 Palembang, helps students understand how to use technology for various purposes, including learning, business, and creating personal biodata. Canva's main features include many available templates, although some of them cost money and require Internet support. This community service activity is effective in introducing and teaching the use of Canva to create presentations, posters, animations and personal biodata. The event ended with a group photo session, and the participants hoped that a similar program would be held again to deepen their understanding of Canva features.
PENERAPAN DIGITAL MARKETING TERHADAP UMKM SEBAGAI PEMASARAN DALAM MENGHADAPI REVOLUSI Kelly, Angel; Hartati, Ery; Felicia; Ariansyah, Nova; Djunaidi, Sherdian
Aptekmas Jurnal Pengabdian pada Masyarakat Vol 7 No 3 (2024): APTEKMAS Volume 7 Nomor 2 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/apts.v7i2.8737

Abstract

Micro, Small and Medium Enterprises (MSMEs) play a vital role in the economy and have great potential for significant growth. However, even though the digital era has penetrated various sectors, there are still many MSMEs that have not taken advantage of the marketing opportunities offered by digital marketing. Data from Kompas.id in 2022 reveals that around 65 million MSMEs have not adopted digital marketing strategies, which is largely due to a lack of technological understanding among business actors. Therefore, this Community Service Activity aims to provide direct training and guidance to MSMEs, such as Lin's Culinary, in utilizing social media such as Instagram and the graphic design tool Canva. It is hoped that through this activity, MSME owners can increase their understanding and skills in utilizing digital platforms for marketing purposes, and can increase the competitiveness and sustainability of their businesses. Keywords: Canva, Digital Marketing, Instagram, MSMEs
PELATIHAN DESAIN UNTUK PEMBUATAN MEDIA PEMBELAJARAN DAN PROMOSI DI VIHARA SUTRA MAITREYA Andreas, Kevin; Bertnas Valentino, Calvin; Hartati, Ery; Fernando; Wijaya, Frisky
Aptekmas Jurnal Pengabdian pada Masyarakat Vol 7 No 3 (2024): APTEKMAS Volume 7 Nomor 2 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/apts.v7i2.8752

Abstract

The rapid advancement of technology has created new demands for engaging and interactive learning media and promotional materials. In the educational context, attractive and interactive learning media can help increase learners' interest and understanding of the subject matter. However, many community organizations, such as the youth at Vihara Sutra Maitreya Palembang, lack the skills to leverage digital tools for creating visually appealing content. This community service project aimed to address this issue by providing training on using the Canva application to 14 youth members of Vihara Sutra Maitreya Palembang for designing learning media and promotional materials. The training was conducted in-person and adopted a persuasive approach, combining theoretical sessions on graphic design concepts, demonstrations of Canva's features, hands-on practice, and discussions. Based on the evaluation of the training using the Likert scale, participants gave a very good rating with an overall average score of 86.23%. Quantitative targets were achieved, with 92.85% demonstrating a good understanding of the material, all participants producing at least one usable design, and 100% active participation. This initiative successfully enhanced the vihara youth's ability to create attractive visual content for educational and promotional purposes within their community while leveraging technological advancements.
Klasifikasi Sampah Daur Ulang Menggunakan Dukungan Vektor Machine Dengan Fitur Pola Biner Lokal Leonardo, Leonardo; Yohannes, Yohannes; Hartati, Ery
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 1 No 1 (2020): Oktober 2021 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1263.533 KB) | DOI: 10.35957/algoritme.v1i1.440

Abstract

Garbage is one of the problems that always arise in Indonesia and even in the world. Increasingly, the production of waste is increased along with the increase in population and consumption. Therefore, need a prevention to stop wasting or producing garbage through recycle. This research do garbage recycle classification of cardboard, glass, metal, paper and plastic by using Local Binary Pattern (LBP) texture feature extraction methode and Support Vector Machine (SVM) as classification methode. For examination technic and dataset distribution is using K-Fold Cross Validation methode type Leave One Out (LOO). From examination result had been done were using fold 5 until fold 10. Polynomial kernel get highest accuracy result from every fold used with mean point 87.82%. Based on SVM classification examination result whether linear kernel, polynomial nor gaussian by using fold 5 until fold 10. The best accuracy point for cardboard garbage is 96.01%. For glass garbage, the best accuracy point is 90.62%. Then, metal garbage get the best accuracy point 89.72%. While paper garbage with highest accuracy point 96.01%. And plastic garbage with highest accuracy point 87.64%.
Identifikasi Aksara Katakana Menggunakan Convolutional Neural Network Arsitektur LeNet Winardi, Eric Agustian; Hartati, Ery
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 2 No 2 (2022): April 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (513.031 KB) | DOI: 10.35957/algoritme.v2i2.2359

Abstract

Penelitian ini mengangkat topik terkait dengan identifikasi menggunakan objek aksara katakana. Pada penelitian ini menggunakan beberapa Optimizer, namun belum diketahui penggunaan Optimizer dan Pooling Layer yang memiliki tingkat pengenalan yang terbaik dalam penelitian tersebut. Penelitian ini menggunakan Optimizer Adam, SGD dan RMSprop, kemudian Pooling Layer menggunakan Average dan Max Pooling. Data yang digunakan sebanyak 2070 citra yang terdiri dari 920 citra latih, 690 citra validasi dan 460 citra uji dengan total 46 kelas. Metode pengenalan menggunakan Convolutional Neural Network arsitektur LeNet, dengan input berupa citra yang telah melalui proses preprocessing menggunakan metode otsu dari citra aksara katakana. Skenario pengujian terdiri dari 6 skenario dengan Optimizer dan Pooling Layer yang berbeda-beda. Tingkat akurasi tertinggi didapatkan pada skenario pertama menggunakan Adam dan Average Pooling sebesar 90% dengan hasil pengenalan sebanyak 414 dari 460 data uji. Hasil dari penelitian ini dapat digunakan sebagai referensi pada penelitian lanjutan dengan metode ataupun objek yang sama.
PENGGUNAAN ALGORITMA RANDOM FOREST DALAM KLASIFIKASI BUAH SEGAR DAN BUSUK Santoso, Felix; Hartati, Ery
Algoritme Jurnal Mahasiswa Teknik Informatika Vol 3 No 1 (2022): Oktober 2022 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v3i1.3404

Abstract

Buah-buahan merupakan salah satu makanan yang sering dikonsumsi oleh berbagai kalangan umur karena sumber berbagai mineral, vitamin dan serat pangan. Untuk memperoleh manfaat yang terdapat pada buah, masyarakat harus mengonsumsi buah yang segar dan belum busuk. Secara fisik, kesegaran buah dapat dilihat karena tanda-tanda yang ada pada buah segar atau buah busuk mudah diamati.LBP (Local Binary Pattern) adalah metode ekstraksi fitur tekstur yang sederhana,namun efisien dalam mempresentasikan ciri tekstur, sedangkan HSV (Hue, Value dan Saturation) merupakan ruang warna yang cocok untuk mengidentifikasi warna-warna dasar yang akan digunakan dalam penelitian sebagai warna identifikasi cahaya dan bisa menoleransi perubahan intensitas cahaya. Penelitian ini menggunakan public dataset buah segar dan buah busuk. Proses di mulai dari resize menjadi ukuran 300 x 300 pixel dan selanjutnya dilakukan ekstraksi fitur LBP dan dilanjutkan dengan ekstraksi fitur HSV. Hasil ekstraksi fitur LBP dan HSV di gunakan sebagai input klasifikasi menggunakan algoritma random forest dengan nilai n_estimator 500,1000,1500,dan 2000. Hasil pengujian menggunakan algoritma random forest menghasilkan nilai Accuracy tertinggi sebesar 95,92% dengan nilai n_estimator 2000.
Pemanfaatan Wodershare Filmora Dalam Meningkatkan Kemampuan Sumber Daya Manusia Di Dinas Sosial Provinsi Sumatera Selatan Hartati, Ery; Ricoida, Desy Iba; Fransen, Lisa Amelia
FORDICATE Vol 1 No 1 (2021): November 2021
Publisher : Universitas Multi Data Palembang, Fakultas Ilmu Komputer dan Rekayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (338.85 KB) | DOI: 10.35957/fordicate.v1i1.1627

Abstract

Lack of skills in the ability to edit videos and has become anobstacle for the Human Resources department at the Social Service ofSouth Sumatra Province in presenting information that is attractiveand interesting to the public. Therefore, training in the use ofWodershare Filmora software is needed to improve the skills of theHuman Resources department in video editing. From the trainingprovided, it was seen that the participants were enthusiastic inparticipating and practicing directly the software used and increasingtheir understanding of using the Wodershare Filmora software. It ishoped that in the future the training can be carried out on a scheduledbasis so that the material presented can be more in-depth and theability of the trainees to increase.
Pelatihan Digital Marketing Dengan Market Place Toko Talk Pada Usaha Kuliner RM Pondok Kolam Sangabut Hartati, Ery; Gasim, Gasim; Inayatullah, Inayatullah; Michael, Michael
FORDICATE Vol 1 No 2 (2022): April 2022
Publisher : Universitas Multi Data Palembang, Fakultas Ilmu Komputer dan Rekayasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (716.697 KB) | DOI: 10.35957/fordicate.v1i2.2414

Abstract

Tri Dharma perguruan tinggi adalah kewajiban bagi setiap dosen yang harus dijalankan setiap semester dalam tahun ajaran. Adapun Tri Dharma Perguruan Tinggi meliputi pengajaran, penelitian, dan pengabdian kepada masyarakat. Pengabdian kepada masyarakat memberikan esensi penting secara sosial agar memberikan manfaat secara langsung bagi masyarakat umum. Selain itu juga memberikan pengalaman bagi dosen yang bersangkutan agar dapat melakukan inovasi pengetahuan. Pengabdian kepada masyarakat ini dilaksanakan di RM Kuliner dan Pemancingan Sangabut Kayu Agung. Pengabdian ini dilaksanakan oleh dosen lingkungan Universitas MDP dengan persetujuan dari Rektor Universitas MDP. Usaha yang akan hadir yaitu para Usaha Kuliner untuk mengikuti Workshop Pemanfaatan Digital marketing dan Pembuatan Laporan Keuangan Bagi Usaha Usaha Kuliner. Dalam pelatihan ini nanti diharapkan para usaha dapat melakukan pembuatan Digital marketing dan Pembuatan Laporan Keuangan guna membantu dalam kegiatan operasional usaha mereka dan selain itu juga dapat lebih meningkatkan kompetensi para Usaha Kuliner RM Pondok Kolam Sangabut di Kota Kayu Agung.
Perangkat Lunak untuk Memprediksi Harga Cryptocurrency Menggunakan Algoritma Support Vector Regression Cerwyn Asyraq; Ery Hartati
Jurnal Ilmiah Teknik Informatika dan Komunikasi Vol. 5 No. 3 (2025): November: Jurnal Ilmiah Teknik Informatika dan Komunikasi 
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juitik.v5i3.1699

Abstract

Cryptocurrency is a digital asset that continues to gain popularity due to its decentralized nature and potential for profit, but its high price volatility poses significant challenges for investors. This study aims to develop a price prediction software for Ethereum cryptocurrency using the Support Vector Regression (SVR) algorithm. Historical price data were collected, preprocessed, normalized using MinMaxScaler, and divided into training and testing datasets. The SVR model was optimized using the GridSearch method to obtain the best hyperparameters. Model performance was evaluated using MAE, RMSE, and MAPE, resulting in 199.61 (7.60%), 227.57 (8.66%), and 8.64%, respectively, indicating good predictive accuracy. The software was developed with the Flask framework and tested using Blackbox testing and stress testing via Locust, showing stable system performance with efficient response time. The developed software can serve as a decision-support tool for investors to predict Ethereum prices over various time ranges from 1 to 30 days or more
Klasifikasi Fraud Pada Transaksi Finansial Melalui Integrasi TabTransformer dan Oversampling Generatif CTGAN Prana Welas Sukma, Tangguh; Hartati, Ery
TIN: Terapan Informatika Nusantara Vol 6 No 8 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v6i8.9056

Abstract

Extreme class imbalance in the BankSim dataset (1.2% fraud) is a major hurdle to building reliable detection systems. This study proposes the integration of the TabTransformer architecture with the Conditional Tabular GAN (CTGAN) oversampling technique to address majority class bias. Data quality evaluations indicate that CTGAN produces synthetic data with an overall quality score of 90.05% and a column pair correlation trend of 91.63%. Experimental findings prove the proposed model delivers superior performance, achieving an F1-Score of 85.34%, a Recall of 81.39%, and a Balanced Accuracy of 90.64%. These results significantly outperform the SMOTE technique, which recorded an F1-Score of 83.99% but suffered from probability calibration failure with an extreme optimal threshold of 0.98. In contrast, the CTGAN scenario demonstrates efficient decision threshold stability at 0.46. Validation through SHAP analysis confirms that engineered variables such as merchantRisk, custStepDiff, and amtZScoreByCat provide dominant contributions to model predictions. This research concludes that the synergy of the Data-Centric AI paradigm facilitates the creation of robust, precise, and highly accountable classification models for digital banking protection within financial transaction systems.
Co-Authors ., Dewa Adrian Chandra Agustria, Kevin Akhfir, Muhammad Fadly Ukhrowi Amarullah, Rendy Ambrosius Dwi Cahyadi Andreas, Kevin Aneke Windari Ardiansyah, Aldi Ariansyah, Nova Awalludin, Nur Bertnas Valentino, Calvin Budi, Raden George Samuel Candra candra Cerwyn Asyraq Chaesa, Linus Ardel Chandra, Kelvin William Christy, Christy Daniel Udjulawa Deka Putra Pamungkas Derry Alamsyah Dervin Dervin Desy Iba Ricoida Eka Puji Widiyanto Fachtur Rachman Fathimah Azzahra Fatimah Nadia FELICIA Felix Santoso Ferdian Indrahadi Fernando Fernando Feliansyah Fernando Fernando, Fernando Fierdaus Fiernando Alfarizi Fikar Penemuan Firnando, Januar Franko, Billy Fransiska, Julita gasim, Gasim Graciela, Michelle Hafiz Irsyad Hakiki, Muhammad Anugrah Hebert, Hocwin Hermanto , Rio Inayatullah, Inayatullah Intan Sanu Ishak , Alvin Leonardo Ivander Destian Luis Jennifer Jocelyn Jennifer Velensia Santoti Jeovanni Wong Joshua Liu Jumhari Jumhari Kelly, Angel Keristin, Usnia Wati Kesuma, Dorie P. Kevin Antonio Khairani, Siti Kotan, Jendraja Husin Kusuma, Dorie P. Leonardo Leonardo Lim, Farrel Stefanov Lisa Amelia Fransen M Rifqi Virgiansyah M. Kurniawan, M. Maria Elana Maulana, Muhammad Ishaq Md, Ramanda Michael Michael Michael Peter Chandra Micheal Micheal Muhammad Maisep Muhammad Nirraca Mutia, Silvi Nardian Varianto Nataliatara Nataliatara Nicholas Edison Nicholas, Nicholas Nirraca, Muhammad Nurrahman, Wahyu Aji Oktaviani, Ayu Sri Pebrian, Hafizh Peter Reynard Susanto Prana Welas Sukma, Tangguh Prasetyo, Zavier Billy Putra Darmansius, Albertus Dwi Andhika Putra Ganda Dewata Qois Al Qorni Renaldo, Florence Reza Ardana Richie Jonathan Chaniago Ricko Andreas Kartono Ricky Ricky Rikky, Rikky Rionaldo, Daniel Sahpira, Mulia Saputra Edika, Nelson Saputra, Ade Rocky Saputra, Riganda Sasongko, Randie Se, Abd Rosyiid Selvie Selvie Sherdian Djunaidi Sihombing, Mecha Bella Permata Sri Wahyuni Steven Hartanto Sudiadi Sudiadi Sudiadi Sudiadi Suluh Arif Wibowo Tan, Handy Christianto Tandoballa, Lucky Tanzil, Surya Pratama Teo Yulio Sihotang Umar Muhdhor Umi Karolina Vanness Bee Vasco Dee Gamma Bororing Verdy Verrino Adityya Virginia, Callista Widyakusuma, Rafael Lois Wijaya, Frisky Williams Peter Wilyanto, Nicholas Winardi, Eric Agustian Yogie Prakoso Yohannes, Yohannes Yulistia Yulistia