Article Per Year (5 Year)
p-Index From 2021 - 2026
3.512
P-Index
This Author published in this journals
All Journal Jurnal Informasi dan Teknologi Journal of Computer Networks, Architecture and High Performance Computing Informanika Jurnal Pengabdian Masyarakat (ABDIRA) Jurnal Minfo Polgan (JMP) Dedikasi: Jurnal Pengabdian Kepada Masyarakat Jurnal Informatika dan Komputer (JIK) Jurnal Sistem Informasi Mahakarya (JSIM) Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer ALKHIDMAH: Jurnal Pengabdian dan Kemitraan Masyarakat
Defi Pujianto
Universitas Mahakarya Asia
Religion Aerospace Engineering Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Environmental Science Languange, Linguistic, Communication & Media Library & Information Science Mathematics Nursing Social Sciences Other

Published : 20 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 20 Documents
Search

 1   2 
SISTEM INFORMASI PERSEDIAAN AMENITIES HOUSEKEEPING DI HOTEL BUKIT INDAH LESTARI MENGGUNAKAN EMBARCADERO XE2 & MY SQL Resta Dwi Duta Taruna Dika; Defi Pujianto; Dian Meilantika
JSIM : Jurnal Sistem Informasi Mahakarya Vol 6 No 1 (2023): Jurnal Sistem Informasi Mahakarya (JSIM)
Publisher : LPPM universitas Mahakarya Asia

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

Abstract

Teknologi komputer sebagai pengolah data kini berkembang semakin pesat, sehingga dapat memudahkan proses penginputan data menjadi sebuah informasi. Teknologi komputer sebagai pengolah data menjadi sebuah kebutuhan yang primer dalam kehidupan, misalnya pada instansi pemerintahan, instansi pendidikan, komunikasi, jasa pelayanan, bisnis maupun ekonomi.Semua aspek kehidupan membutuhkan komputer sebagai alat bantu dalam menyelesaikan pekerjaan, Untuk memperoleh data-data diperlukan, penelitian dilakukan dengan beberapa metode yaitu, metode intereview, metode studi dokumen, dan metode observasi. Tahapan yang dilakukan dalam pembuatan sistem informasi yaitu Diagram konteks, Data Flow Diagram (DFD), Entity Relationship Diagram (ERD), rancangan tabel, Relasi Antar tabel, dan Rancangan Form. Hasil Dari penelitian ini adalah sistem informasi persediaan amenities housekeeping Bukit Indah lestari menggunakan Embarcadero XE2 yang dihrapkan dapat memberi kemudahaan bagi admin Housekeeping dalam mengelolah input data, proses data, pencarian dan laporan.
The Influence of QRIS Digitalization, Technology and Digitalization Lifestyle, Digital Financial Literacy, and Financial Inclusion On Bank Customers Decision Mahrizal, Mahrizal; Judijanto, Loso; Indrapraja, Rachmadi; Alfiana; Pujianto, Defi
Jurnal Informasi dan Teknologi 2023, Vol. 5, No. 4
Publisher : SEULANGA SYSTEM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60083/jidt.v5i4.426

Abstract

This study looks at how consumer decisions are impacted by the digitalization of QRIS, financial literacy, and financial inclusion through lifestyle. The participants in this study are clients of Sharia Bank. Non-probability sampling combined with a purposeful sampling approach was the sample strategy employed in this study. A sample of one hundred participants was used by the researchers. This study included both primary and secondary data. In order to acquire the primary data required by the researchers, the data collection strategy used in this study is the distribution of questionnaires. In this quantitative study, the Partial Least Squares (PLS) method of moderated regression analysis (MRA) and descriptive statistical analysis were employed as data analysis techniques. Based on the test results and discussions that have been described, the following conclusions can be drawn: The digitalization of QRIS has a direct influence on customers' decisions to make transactions using QRIS. Financial literacy has a direct influence on customer decisions. Decisions made by customers are directly impacted by financial inclusion. Decisions about transactions are directly influenced by lifestyle. The digitalization of QRIS does not directly impact lifestyle. Lifestyle is not immediately impacted by financial knowledge. There is no direct correlation between financial inclusion and lifestyle. Lifestyle cannot moderate the relationship between QRIS digitization and consumer decisions, nor does it have an indirect effect. Lifestyle cannot moderate the relationship between financial literacy and client decisions, nor does it have an indirect influence. Lifestyle cannot moderate the relationship between financial inclusion and customers' decisions to transact via QRIS, nor does it have an indirect influence.
APLIKASI E-BOOK BERBASIS ANDROID UNTUK MENDUKUNG PEMBELAJARAN INTERAKTIF DI SMK SENTOSA BHAKTI Pujianto, Defi
JIK : Jurnal Informatika dan Komputer Vol. 15 No. 2 (2024): Jurnal Informatika dan Komputer (JIK)
Publisher : Universitas Mahakarya Asia

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

Abstract

Abstract – This Android-based e-book application was developed as an innovative solution to address the limitations of conventional learning methods, which often face challenges related to the availability and accessibility of physical textbooks. This phenomenon reflects a paradigm shift in the education sector, emphasizing the integration of technology to enhance the effectiveness and accessibility of learning processes. With the rising popularity of e-books, new opportunities have emerged to support educational innovation, particularly at SMK Sentosa Bhakti. This research employs a qualitative descriptive method with primary steps including interviews, observations, and reference studies. The research process involves problem identification, goal setting, literature review, application design, and development. Through the implementation of this application, it is expected to have a positive impact on improving the quality of learning at SMK Sentosa Bhakti, facilitating material management by administrators, and enriching students' learning experiences by providing easier and more interactive access to educational resources.
MEMBUAT APLIKASI COMPANY PROFILE UNTUK SMP IT TUNAS CENDIKIA BATURAJA BERBASIS ANDROID MENGGUNAKAN ANDROID STUDIO Dwi Martha, Andre; Kurniawan, Budi; Pujianto, Defi
JSIM : Jurnal Sistem Informasi Mahakarya Vol 7 No 1 (2024): Jurnal Sistem Informasi Mahakarya (JSIM)
Publisher : LPPM universitas Mahakarya Asia

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

Abstract

SMP IT Tunas Cendikia Baturaja merupakan lembaga pendidikan islam dibawah naungan Yayasan Insan Cendikia, dari hasil analisa yang dilakukan terhadap SMP IT Tunas Cendikia Baturaja terdapat sebuah permasalahan dalam memberikan informasi yang kurang efektif dan efisien, karena masih menggunkan brosur dan pamflet yang menyebabkan keterbatasan informasi yang diterima oleh masyarakat. Implementasi aplikasi ini menggunakan bahasa pemrograman Java dan Android Studio sebagai IDE utama untuk menghasilkan aplikasi Android yang fungsional. Dalam tahap pengujian, aplikasi diuji untuk memastikan kinerjadan fungsionalitas yang maksimal serta responsif terhadap berbagai ukuran layar perangkat.Hasil penelitian ini adalah sebuah Aplikasi Company Profile SMP IT Tunas Cendikia Baturaja berbasis Android yang efektif dan efisien, mampu memberikan akses informasi seperti data sekolah, data guru, data gedung, program, fasilitas serta cara pendaftaran secara mudah dan cepat bagi para calon siswa/orang tua siswa di Kabupaten Ogan Komering Ulu.
APPLICATION OF TRANSFORMER MODEL AND WORD EMBEDDING IN SENTIMENT ANALISYS OF INDONESIAN E-COMMERCE APPLICATION REVIEW Kadarsih, Kadarsih; Pujianto, Defi
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 3 (2025): Articles Research July 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v7i3.6354

Abstract

The rapid growth of e-commerce applications in Indonesia has resulted in a large volume of user reviews. The review contains important information that can be used to understand user satisfaction, complaints, and needs. Therefore, sentiment analysis of e-commerce app reviews is important to support future decision-making. This study aims to explore and compare the performance of the Transformer model and various word embedding methods in analyzing the sentiment of reviews of Indonesian e-commerce applications. The methods used involve extracting review data from the Google Play Store, text preprocessing, and text representation using Word2Vec, FastText, and IndoBERT. Next, this combination of embedding was tested using the Gradient Boosting Classifier as a prediction model. The evaluation was carried out by comparing the accuracy, precision, recall, F1-score, as well as the visualization of the confusion matrix and word cloud for each model. The results of the tests that have been carried out show that all three models have a fairly good ability to recognize positive reviews, with the highest accuracy score of 88% achieved by Word2Vec and FastText. While IndoBERT produces a lower accuracy value of 86%, IndoBERT shows a better balance in recall values and f1-scores for minority classes compared to Word2Vec and FastText. In conclusion, the application of the IndoBERT-based Transformer model is more effective in capturing the context and meaning of sentiment in Indonesian-language e-commerce reviews. These findings are expected to be a reference for the development of a more accurate sentiment analysis system for e-commerce applications in Indonesia.
Efektivitas Animasi Iklan Dalam Pencegahan Dan Perlindungan Anak Korban Bullying Pada Dinas Pemberdayaan Perempuan Dan Perlindungan Anak Kabupaten Ogan Komering Ulu Kadarsih, Kadarsih; Saputra, Andika; Romzi, Muhammad; Pujianto, Defi; Rusidi, Rusidi
Jurnal Minfo Polgan Vol. 13 No. 1 (2024): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v13i1.13781

Abstract

Efektivitas Animasi Iklan Dalam Pencegahan Dan Perlindungan Anak Korban Bullying Pada Dinas Pemberdayaan Perempuan Dan Perlindungan Anak Kabupaten Ogan Komering Ulu Penelitian ini bertujuan untuk mengetahui efektivitas Animasi Iklan dalam Pencegahan dan Perlindungan Anak Korban Bullying. Alat bantu dalam bentuk animasi iklan ini dibuat untuk mencegah dan melindungi anak-anak korban bullying khususnya di wilayah Ogan Komering Ulu. Tujuan dari media ini adalah untuk mengajak elemen masyarakat, khususnya orang tua, agar mengetahui dan dapat mencegah kekerasan terhadap anak. Metode yang digunakan adalah perancangan animasi, produksi animasi dan pengujian animasi iklan melalui melalui kuesioner. Teknik pengumpulan data dilakukan dengan purposive sampling. hasil dari analisis data responden dilingkungan Universitas Mahakarya Asia PSDKU Kab Ogan Komering Ulu di peroleh index persentase rata-rata 85,34% dan berada di kategori “Sangat Baik” dalam artian informasi yang disampaikan melalui animasi iklan mudah dipahami.
Performance Analysis of an Offline Text Detection System Based on Edge AI A Case Study of DokuScan Pro Pujianto, Defi; Kadarsih, Kadarsih; Hartati, Sri
Journal of Computer Networks, Architecture and High Performance Computing Vol. 8 No. 1 (2026): Articles Research Januari 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v8i1.7854

Abstract

The growing use of mobile document scanning applications has increased the demand for text detection systems that can operate reliably in offline and on-device environments. Although Edge AI enables local inference without network dependency, system-level empirical evidence regarding its performance under real-world mobile usage conditions remains limited. This study presents a system-level evaluation of an offline Edge AI–based text detection system for mobile document scanning, using DokuScan Pro as a case study. The evaluation was conducted on 40 document images captured under varying lighting conditions, capture angles, and background characteristics. System performance was assessed using precision, recall, F1-score, and inference time to characterize on-device behavior rather than algorithmic novelty. Experimental results show that the system achieved a precision of 1.00, a recall of 0.975, and an F1-score of approximately 0.98, with an average inference time of 63.8 ms per image during fully offline execution on mobile devices. These results indicate stable system-level performance under real-world document scanning conditions with controlled computational overhead. This study provides empirical system-level insights into the feasibility and practical limitations of deploying Edge AI–based text detection in offline mobile document scanning applications, thereby complementing existing model-centric research with evidence from real-world, on-device evaluation.
Pelatihan Menghasilkan Uang Secara Online dengan Bisnis Afiliasi untuk Siswa Magang SMK di Kampus Universitas Mahakarya Asia Kadarsih Kadarsih; Defi Pujianto; Safaruddin Safaruddin
ALKHIDMAH: Jurnal Pengabdian dan Kemitraan Masyarakat Vol. 2 No. 1 (2024): Januari : Jurnal Pengabdian dan Kemitraan Masyarakat
Publisher : LP3M INSTITUT KH YAZID KARIMULLAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59246/alkhidmah.v2i1.774

Abstract

This digital era, the internet has opened up new opportunities in the business world, especially through online business models such as affiliate businesses. These businesses allow individuals to promote other people's products or services and earn commissions from any transactions generated through affiliate links. Affiliate businesses offer potential solutions, but not all internship participants have the understanding and/or skills to take advantage of these opportunities. For this reason, Mahakarya Asia University provides practical training on affiliation. This approach combines theoretical understanding and practical experience, ensuring students increase their knowledge and practical skills.The method of implementing this service involves pre-implementation, implementation and evaluation stages. Identification of problems, interviews with internship supervisors, and socialization of material are carried out at the pre-implementation stage. The training was carried out face-to-face involving 25 vocational school students in the Mahakarya Asia University computer laboratory on September 9 2023. Evaluation is carried out to measure students' success in applying the knowledge and skills acquired during training.The training results show that students are able to register and create a Shopee affiliate account, create affiliate video content, and disseminate affiliate links via social media. Evaluation of participants' understanding showed that most students understood the material and were successful in the practicum. Overall, this affiliate business training is expected to provide additional competency and opportunities to earn income online.
Pelatihan Digital Marketing Sebagai Upaya Peningkatan Pengetahuan Dan Keterampilan Guru Di SMP PGRI 3 Baturaja Suryanto Suryanto; Haris Saputro; Defi Pujianto; Kadarsih Kadarsih; Didik Arifin; Rusidi Rusidi; Ari Sulfani
ALKHIDMAH: Jurnal Pengabdian dan Kemitraan Masyarakat Vol. 2 No. 3 (2024): Juli : Jurnal Pengabdian dan Kemitraan Masyarakat
Publisher : LP3M INSTITUT KH YAZID KARIMULLAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59246/alkhidmah.v2i3.981

Abstract

In the current era of digitalisation, digital marketing skills are crucial across various fields, especially in education. Teachers need to have knowledge and skills in digital marketing to support the promotion and branding of schools. SMP PGRI 3 Baturaja, a private school, faces competition in attracting new students by leveraging digital technology to showcase the school's activities and achievements. The purpose of this training is to enhance the knowledge of SMP PGRI 3 Baturaja teachers about the concepts and strategies of digital marketing and to develop practical skills in using various digital marketing tools and platforms. With this knowledge, it is expected that teachers can effectively improve the promotion and reputation of the school. The training is conducted through interactive and practical workshop sessions, including theoretical presentations, discussions, and hands-on practice. Participants will be provided with material on the basics of digital marketing, content strategies, and the use of social media. Additionally, there will be mentoring sessions for hands-on practice. After attending this training, based on the results of the questionnaires distributed to the participants, 86.7% of participants gained new knowledge about digital marketing, 85.7% acquired skills in copywriting with AI, and 80% gained skills in creating digital marketing content. The training participants were able to implement activities during digital marketing practice. SMP PGRI 3 Baturaja teachers are now more skilled in using various digital platforms to promote school activities and promotions on social media after the training.
Perbandingan Kinerja Isolation Forest Dan Local Outlier Factor (LOF) Dalam Deteksi Anomali Transaksi Digital Hartati, Sri; Pujianto, Defi; Kadarsih
BETRIK Vol. 17 No. 01 (2026): Jurnal Ilmiah BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : PPPM Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/5w76ab74

Abstract

The rapid growth of digital transactions has increased the risk of anomalous activities such as fraud, particularly in highly imbalanced datasets where fraudulent transactions are significantly fewer than normal transactions. This imbalance presents a major challenge in anomaly detection, as models tend to be biased toward the majority class. This study aims to compare the performance of Isolation Forest and Local Outlier Factor (LOF) algorithms in detecting anomalies in digital transaction data.The research adopts an experimental approach using the Credit Card Fraud Detection dataset, which consists of 284,807 transactions, including 492 fraudulent cases. Data preprocessing involves feature normalization using StandardScaler, followed by a stratified train-test split with a ratio of 70:30. Model evaluation is conducted using confusion matrix, precision, recall, and F1-score metrics.The results show that Isolation Forest outperforms LOF. Isolation Forest successfully detects 37 out of 148 fraudulent transactions with a precision of 0.2824, recall of 0.25, and F1-score of 0.2652. In contrast, LOF detects only 2 fraudulent transactions, with a precision of 0.0137, recall of 0.0135, and F1-score of 0.0136. These findings indicate that isolation-based approaches are more effective and robust than density-based methods in handling highly imbalanced datasets.
Co-Authors Abdulloh Fakih Alfiana Amanda Rahayu Astuti ANDIKA SAPUTRA Ari Sulfani Bahru Wandino Budi Kurniawan Budi Kurniawan Dian Meilantika Dian Sri Agustina Didik Arifin Dwi Martha, Andre Haris Saputro Heru Jun Samudra Indrapraja, Rachmadi Judijanto, Loso Kadar sih Kadarsih Kadarsih Kadarsih Kadarsih Kadarsih, Kadarsih Mahrizal Mahrizal Mita Agustina Mudinillah, Adam Muhammad Romzi, Muhammad Nilam Permata Ocha Rosalina Putri Wahyu Kirani Resta Dwi Duta Taruna Dika Rusidi Rusidi Rusidi, Rusidi Safaruddin Safaruddin Salamudin salamudin salamudin Satria Novari sih, Kadar Sri Hartati sri hartati Suryanto Suryanto Wisnumurti Yohana Fransisca Dessy Kristianti