Article Per Year (5 Year)
p-Index From 2021 - 2026
3.055
P-Index
This Author published in this journals
All Journal KOMPUTEK Jurnal Mantik Prima Abdika: Jurnal Pengabdian Masyarakat Abditeknika - Jurnal Pengabdian Kepada Masyarakat Jurnal Surya Informatika Transaction on Informatics and Data Science
Subowo, Edy
Unknown Affiliation
Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Social Sciences Other

Published : 23 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 23 Documents
Search

 1   2   3 
Implementation of deep learning-based currency recognition systems on visual data with adam optimizer Subowo, Edy
Jurnal Mantik Vol. 8 No. 3 (2024): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v8i3.5723

Abstract

With the rising demand for automated financial systems, a reliable currency identification system is crucial. The dataset comprises images of currency notes, preprocessed and augmented to improve model performance. A convolutional neural network (CNN) model, built with TensorFlow and Keras, captures spatial hierarchies in the images. The Adam optimizer is employed to improve the efficiency of the training process, offering adaptive learning rates that accelerate convergence. The data is split into training and validation sets to evaluate accuracy and loss metrics over multiple epochs. Data augmentation techniques, such as random flipping, rotation, and zooming, are applied to enhance model robustness against variations in image quality and orientation. The model achieves over 90% accuracy by the final epoch, optimized with Adam, and is saved in formats such as TensorFlow SavedModel, TensorFlow.js, and Lite for web and mobile deployment. For example, the model is saved with model.save('saved_model/my_model') and can be reloaded using tf.keras.models.load_model('saved_model/my_model') for further evaluation. This system demonstrates the potential of deep learning with Adam optimization in automating financial processes, reducing errors, and improving transaction efficiency. Future work may focus on further optimization and real-time inference
Corpus Development and NER Model for Identification of Legal Entities (Articles, Laws, and Sanctions) in Corruption Court Decisions in Indonesia Subowo, Edy; Bukhori, Imam; warto
Transactions on Informatics and Data Science Vol. 2 No. 1 (2025)
Publisher : Department of Informatics, Faculty of Da'wah, UIN Saizu Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24090/tids.v2i1.13592

Abstract

This study aims to develop an annotated corpus and a deep learning-based Named Entity Recognition (NER) model to identify legal entities in Indonesian corruption court rulings. The corpus was constructed from 450 Supreme Court documents related to the Anti-Corruption Laws (Laws No. 31/1999), collected via web scraping, with semi-automatic annotation (regex) and validation by legal experts. A total of 12,000 entities (Article, Laws, Sanctions) were tagged in IOB format, creating the first specialized dataset for Indonesian corruption laws. The NER model combines the IndoBERT (pre-trained language model) architecture with a CRF layer, fine-tuned to handle legal text complexities such as hierarchical article references (paragraphs, clauses) and amended laws citations (jo.). Evaluation using 10-fold cross-validation revealed that the model achieved an F1-score of 92.3%, outperforming standalone CRF (85.1%) and BiLSTM+CRF (88.7%), particularly in detecting ARTICLE entities (F1: 93.8%). Error analysis highlighted challenges in recognizing SANCTIONS entities (F1: 87.4%) due to sentence structure variability and conjunctions. The model’s implementation could accelerate judicial decision analysis, identify violation patterns, and support sanctions recommendation systems for laws enforcement. This research also provides legal entity annotation guidelines adaptable to other legal domains. Future work should expand to other laws (e.g., ITE Laws, Criminal Code) via transfer learning and integrate knowledge graphs to enhance entity relation detection.
Algoritma Support Vector Machine untuk Analisis Sentimen Ulasan Aplikasi AXISnet di Google Play Store Subowo, Edy
KOMPUTEK Vol. 8 No. 1 (2024): April
Publisher : Universitas Muhammadiyah Ponorogo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24269/jkt.v8i1.2653

Abstract

Aplikasi AXISnet, yang tersedia di Google Play Store, beroperasi sebagai penyedia layanan internet. Meskipun mengumpulkan 10 juta unduhan, peringkatnya berada di 4,3. Dalam ekosistem toko aplikasi, penilaian pengguna dilengkapi dengan ulasan terperinci. Ulasan ini, seringkali tidak terstruktur, merangkum sentimen dan tingkat kepuasan pengguna, sehingga sangat memengaruhi pilihan calon pengguna. Untuk mengukur sentimen pengguna terhadap aplikasi AXISnet, digunakan analisis sentimen menggunakan algoritma Support Vector Machine. Dengan menggunakan metode Knowledge Discovery in Database (KDD), penelitian ini meneliti kumpulan data yang mencakup 61.895 ulasan aplikasi AXISnet. Diantaranya, 31.742 ulasan cenderung positif, sementara 30.153 ulasan mencerminkan sentimen negatif. Selain itu, evaluasi tersebut menghasilkan tingkat akurasi sebesar 86%, yang menggambarkan presisi model secara keseluruhan dalam tugas klasifikasi. Model ini menunjukkan presisi sebesar 87%, yang menyoroti keakuratannya dalam mengidentifikasi hal-hal positif yang sebenarnya di antara hal-hal positif yang diprediksi. Dengan perolehan sebesar 83%, model tersebut menunjukkan kemampuannya dalam mengklasifikasikan kejadian positif aktual secara akurat. Skor F1, yang menunjukkan rata-rata harmonis antara presisi dan perolehan, mencapai 85%, menandakan kinerja seimbang antara mengidentifikasi kelas positif dengan benar dan meminimalkan positif palsu.
Education for Pregnant Women and Cadres as an Effort to Optimize the Achievement of Exclusive Breastfeeding in Stunting Prevention Kristiyanti, Rini; Khanifah, Milatun; Subowo, Edy; Kusuma, Nur Intan
Prima Abdika: Jurnal Pengabdian Masyarakat Vol. 3 No. 4 (2023): Volume 3 Nomor 4 Tahun 2023
Publisher : Program Studi Pendidikan Guru Sekolah Dasar Universitas Flores Ende

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37478/abdika.v3i4.3396

Abstract

Exclusive breastfeeding for the first six months of a baby's life is the gold standard in infant and child feeding recommended by WHO and UNICEF. Breast milk contains the complete nutrition that babies need. Only breastfeeding for infants aged 0-6 months is sufficient for all the nutritional needs of infants. This program aimed to increase mothers' understanding of the importance of exclusive breastfeeding, increase mothers' self-efficacy for breastfeeding, and mothers' readiness to face the breastfeeding process. The program is carried out by providing education, demonstrations, and breastfeeding assistance, as well as evaluation monitoring. The activity was attended by nine third-trimester pregnant women and 11 cadres, all of whom were unemployed. Providing education and training about the importance of breastfeeding for reducing can increase knowledge about exclusive breastfeeding. Breastfeeding self-efficacy was also measured and obtained an average score of 34 out of a total score of 56. The variation in breastfeeding self-efficacy was 4,153, with a minimum score of 34 and a maximum of 39. The results of breastfeeding assistance and evaluation showed that mothers can breastfeed well and only give breast milk to the baby. This program is expected to contribute to increasing breastfeeding coverage to reduce stunting in children.
Pelatihan Artificial Intelligence untuk Tenaga Pendidik dan Guru Sekolah Dasar Muhammadiyah (Online Thematic Academy Kominfo RI) Subowo, Edy; Dhiyaulhaq, Naufal; Khasanah, Ika Wahyu
Abditeknika Jurnal Pengabdian Masyarakat Vol. 2 No. 2 (2022): Oktober 2022
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/abditeknika.v2i2.1372

Abstract

Kementerian Kominfo melalui Badan Penelitian dan Pengembangan Sumber Daya Manusia berupaya melakukan pemerataan literasi dan meningkatkan kompetensi bidang TIK di seluruh wilayah dan kalangan masyarakat. Pelatihan Artificial Intelligence merupakan program pelatihan yang bertujuan untuk meningkatkan pengetahuan, keterampilan, sikap, serta daya saing SDM bidang teknologi informasi dan komunikasi sebagai bagian dari program pembangunan prioritas nasional terutama kepada generasi muda dimulai dari murid Sekolah Dasar, dalam hal ini melalui guru yang berinteraksi dengan siswanya. Pengenalan AI bagi tenaga pendidik dilakukan secara online dengan platform aplikasi Zoom dengan pengajar bersertifikat dari Kominfo dan dilakukan dalam lima pertemuan meliputi pengenalan AI, aplikasi penunjang pembelajaran seperti Stratch, Quizizz, Teachable Machine, dan Poseblock. Bagi peserta yang lulus pelatihan akan mendapatkan e-Sertifikat dari Kominfo. Diharapkan dengan pelatihan ini memberikan pemahaman mengenai pembelajaran Berbasis Artificial Intelligence bagi pengajar sehingga dapat disalurkan kepada murid-murid yang diajarnya. Peserta mengerjakan PraTest dengan Materi terkait pemanfaatan Kecerdasan Buatan untuk menunjang pembelajaran di Sekolah Dasar, sedangkan di akhir sesi dilakukan PostTest dengan materi yang sama dan soal yang berbeda, dengan pelatihan, peserta mendapatkan skor yang meningkat dengan rata – rata peningkatan skor adalah 37 point atau meningkat 76%
SISTEM PENDUKUNG KEPUTUSAN PENILAIAN DOSEN POLITEKNIK MUHAMMADIYAH PEKALONGAN MENGGUNAKAN KUESIONER BERBASIS WEB Subowo, Edy; Rizqi, Fitriya
Jurnal Surya Informatika Vol. 2 No. 1 (2016): Jurnal Surya Informatika, Vol . 2, No. 1, Mei 2016
Publisher : Universitas Muhammadiyah Pekajangan Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.48144/suryainformatika.v2i1.311

Abstract

Media in delivering advice and criticism in the universities is needed in order to improve the quality of teaching and learning activities. The submission of suggestions and criticisms can be used in the media lecturer assessment questionnaire. At Polteknik, the problems in making the questionnaire is still using paper media and collecting the questionnaire manually, so it makes less efficient in time, otherwise there was no follow-up as suggestions and criticisms for the lecturer. Therefore, the authors used the Decision Support System methods to solve these problems. In this study, the authors have made a DSS application questionnaire which can simplify the process of assessment as lecturers, using the web media and the statements made it directly after the accumulation of assessment. Further, the application can display graphs for easy admin ratings lecturer in knowing the results of the questionnaire. Keywords : questionnaire, assessment, decision support system. ABSTRAKSI Media dalam menyampaikan saran dan kritik di dalam perguruan tinggi sangat dibutuhkan guna meningkatkan kualitas dalam kegiatan belajar mengajar. Penyampaian saran dan kritik dapat menggunakan media kuesioner penilaian dosen. Permasalahan di polteknik dalam membuat kuesioner masih menggunakan media kertas dan pengumpulan hasil kuesioner secara manual sehingga kurang efisien dalam waktu, selain itu tidak ada tindak lanjut seperti saran dan kritik terhadap dosen yang bersangkutan. Oleh karena itu penulis menggunakan metode Sistem Pendukung Keputusan untuk menyelesaikan permasalahan tersebut. Pada penelitian ini, penulis telah membuat aplikasi SPK kuesioner yang dapat menyederhanakan proses penilaian dosen seperti, menggunakan media web dan laporan secara langsung sesudah dilakukan akumulasi penilaian. Selain itu aplikasi ini dapat menampilkan grafik penilaian dosen untuk memudahkan admin dalam mengetahui hasil kuesioner. Kata Kuci : kuesioner, penilaian, sistem pendukung keputusan
SISTEM INFORMASI PETERNAKAN AYAM BROILER DI KABUPATEN PEKALONGAN BERBASIS WEB DAN ANDROID Subowo, Edy; Saputra, Meidika
Jurnal Surya Informatika Vol. 6 No. 1 (2019): Jurnal Surya Informatika, Vol . 6, No. 1, Mei 2019
Publisher : Universitas Muhammadiyah Pekajangan Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.48144/suryainformatika.v6i1.336

Abstract

Ayam broiler atau yang disebut juga ayam ras pedaging (broiler) adalah jenis ras unggulan hasil persilangan dari bangsa-bangsa ayam yang memiliki daya produktivitas tinggi, terutama dalam memproduksi daging ayam. Dari survei yang dilakukan pada beberapa peternakan ayam broiler di Kabupaten Pekalongan, proses penyampaian informasi dan tanya jawab mengenai peternakan ayam broiler masih dilakukan secara konvensional, sehingga menyulitkan bagi calon peternak yang ingin memulai bisnis peternakan ayam broiler. Maka dari itu terbuka peluang untuk mambangun sebuah aplikasi berupa sistem informasi untuk mengetahui informasi dan forum diskusi online mengenai peternakan ayam broiler. Diharapkan aplikasi ini nantinya dapat menjadi salah satu sumber informasi yang dapat digunakan oleh masyarakat khususnya bagi para calon peternak ayam broiler untuk mendapatkan informasi yang dibutuhkan secara lebih mudah dan informatif. Hasil dari penelitian ini yaitu berupa sistem informasi peternakan ayam broiler di Kabupaten Pekalongan dalam bentuk aplikasi Android yang dibangun menggunakan framework React Native, selain itu juga dalam bentuk aplikasi website untuk admin, penyuluh, dan peternak yang penulis bangun menggunakan framework AngularJS. Kata Kunci : Android, Ayam Broiler, Peternakan, dan React Native. ABSTRACT Broiler chickens, or broilers, are superior breeds of hybrids from chicken nations that have high productivity, especially in producing chicken meat. From a survey conducted on several broiler farms in Pekalongan Regency, the process of delivering information and question and answer about broiler farms is still done conventionally, making it difficult for prospective farmers who want to start a broiler farm business. Therefore there is an opportunity to build an application in the form of an information system to find out information and online discussion forums about broiler chicken farms. It is expected that this application can later become one of the sources of information that can be used by the community, especially for prospective broiler breeders to get the information needed more easily and informally. The results of this study are in the form of an information system for broiler farms in Pekalongan Regency in the form of an Android application that was built using the React Native framework, in addition in the form of website applications for admin, extension and breeders that the authors build using the AngularJS framework. Keywords: Android, Broiler Chicken, Livestock, and React Native.
SISTEM INFORMASI GEOGRAFIS WISATA DAN EVEN WISATA KABUPATEN PEKALONGAN BERBASIS ANDROID Manggala, Kevin Haritsi; Khambali, Ahmad; Subowo, Edy
Jurnal Surya Informatika Vol. 7 No. 1 (2019): Jurnal Surya Informatika, Vol . 7, No. 1, November 2019
Publisher : Universitas Muhammadiyah Pekajangan Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.48144/suryainformatika.v7i1.342

Abstract

The purpose of this research is to build Pekalongan Regency Tourism Geographic Information and Tourism Event System application based on android that can facilitate Pekalongan regency community in knowing tourist attractions in Pekalongan regency and upcoming tourism events. The absence of an integrated system regarding tourist attractions and tourism events makes people less aware of the location of tourist objects and tourism events to be held, therefore a system is needed to display information about tourist maps containing the location of tourist attractions, user locations and travel routes to tourist attractions and upcoming tourism events. In developing this system, the author uses the waterfall system development method. This system uses the Google API to display tourist maps, and uses the Java programming language from the Android Studio platform and uses cloud firestore from Firebase. The conclusion of the results of this study is that the Tourism and Event Geographic Information System Application of Pekalongan Regency can help facilitate the public in knowing the location of tourism and upcoming tourism events.
SISTEM INFORMASI GEOGRAFIS WISATA GUNUNG DI PEKALONGAN BERBASIS ANDROID Saifudin, Saifudin; Fatkhudin, Aslam; Subowo, Edy
Jurnal Surya Informatika Vol. 7 No. 1 (2019): Jurnal Surya Informatika, Vol . 7, No. 1, November 2019
Publisher : Universitas Muhammadiyah Pekajangan Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.48144/suryainformatika.v7i1.344

Abstract

Selain terkenal dengan batiknya, Pekalongan juga terkenal dengan destinasi wisata, keindahan seni dan budayanya. Keindahan alam yang ada di kota yang terletak di kawasan jalur pantai utara jawa ini, juga memiliki segudang destinasi wisata alam yang ditawarkan, seperti curug, pantai dan pegunungan. Pariwisata lokal dapat membuat perekonomian warga meningkat dan juga bisa menjadi media promosi untuk kekayaan lokal. Tetapi dengan banyaknya destinsai wisata tersebut, masih banyak yang belum terekspose dan minim informasi seperti obyek wisata mengenai gunung-gunung di Pekalongan. Padahal di era digital ini seharusnya informasi bisa terbuka lebar kemedia masa baik itu media cetak maupun media elektronik. Selain itu perkembangan teknologi terutama pada ponsel, sekarang ini sudah menjadi smartphone dengan menggunakan teknologi sistem operasi Android yang bersifat open source sehingga memungkinkan masyarakat untuk ikut mengembangkan sistem operasi tersebut maupun membuat aplikasi yang ada di dalamnya Berdasarkan permasalahan di atas, maka dibuatlah aplikasi Sistem Informasi Geografis Wisata Gunung Di Pekalongan berbasis android. Hasil dari penelitian ini adalah aplikasi Sistem Informasi Geografis Wisata Gunung Di Pekalongan yang dapat memberikan informasi kepada masyarakat tentang wisata gunung, manfaat pendakian, prediksi cuaca, safery and rescue, mudah, cepat dan efektif sehingga dapat membantu wisatawan untuk mengenal wisata gunung di Pekalongan. Kata Kunci : Sistem Informasi, Wisata, Android dan Android Studio Abstract Besides being famous for its batik, Pekalongan is also famous for its tourist destinations, the beauty of its art and culture. The natural beauty in the city, which is located in the north coast of Java, also has a myriad of natural tourist destinations on offer, such as waterfalls, beaches and mountains. Local tourism can make the people's economy increase and can also be a media campaign for local wealth. But with many tourist destinations, there are still many who have not been exposed and lack information such as tourism objects in the mountains in Pekalongan. Even though in this digital era, information should be widely available both in print and electronic media. Besides technological developments, especially on cellphones, now it has become a smartphone using Android operating system technology that is open source, allowing people to participate in developing the operating system and making applications that are in it. Based on the problems above, the application of the Geographic Tourism Information System in Pekalongan is based on Android. The results of this study are the application of Geographic Information System for Mountain Tourism in Pekalongan that can provide information to the community about mountain tourism, the benefits of climbing, weather prediction, safery and rescue, easy, fast and effective so that it can help tourists to know mountain tourism in Pekalongan. Keywords : Information System, Tourism, Android, and Android Studio
SISTEM INFORMASI PEMBAYARAN SEWA KIOS DAN LOOS DI PASAR KARANGANYAR BERBASIS WEB DAN ANDROID Triwinarni, Indah; Khambali, Ahmad; Subowo, Edy
Jurnal Surya Informatika Vol. 9 No. 1 (2020): Jurnal Surya Informatika, Vol . 9, No. 1, November 2020
Publisher : Universitas Muhammadiyah Pekajangan Pekalongan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.48144/suryainformatika.v9i1.409

Abstract

Sistem informasi pembayaran sewa kios dan loos di Pasar Karangnyar saat ini masih manual yaitu dengan menggunakan kwitansi dan buku dalam pengarsipan data perusahaan. Tentu saja hal yang demikian akan mempersulit dalam mengontrol data transaksi dan laporan. Pedagang juga harus datang ke kantor untuk memperpanjang sewa kios atau loos setiap bulannya. Keharusan datang ke kantor untuk melakukan pembayaran tagihan sewa itu menjadi kendala pada para pedagang yang tidak bisa datang ke kantor karena alasan tertentu, sehingga terjadinya keterlambatan dalam memproses pembayaran tagihan sewa kios atau loos. Oleh karena itu, maka perlu dibangun sebuah aplikasi yang mampu memberikan suatu sistem pembayaran tagihan sewa kios dan loos.Dalam pembangunan aplikasi ini penulis menggunakan framework React Nativesebagaiaplikasi Android dan Laravel sebagai aplikasi website, bahasa pemprograman PHP sebagai back-end, MySQL sebagai database, serta Expo untuk mem-build aplikasi menjadi bentuk apk. Hasil dari penelitian ini yaitu aplikasi Sistem Informasi Pembayaran Sewa Kios dan Loos di Pasar Karanganyar Berbasis Web dan Android, aplikasi ini dapat membantu melihat tagihan sewa kios dan loss dan melakukan pembayaran tagihan sewa dengan hanya membuka smartphone tanpa harus datang langsung ke kantor Kata Kunci :Sistem Informasi , Kios, Loos, Android, React Native dan Laravel ABSTRACT Stalls and loos rental payment information systems at Karanganyar Market are still manual, using receipts and books in company data archiving. Of course this will make it difficult to control transaction data and reports. Traders must also come to the office to extend the rental of Stalls or loos every year. The necessity to come to the office to pay the rental bill becomes an obstacle for the traders who cannot come to the office for some reason, so there is a delay in processing the payment of the stalls or loos rental bill. Therefore, it is necessary to build an application that is able to provide a bill payment system for rental of stalls and loos. In the development of this application the author uses the React Native framework as an Android and Laravel application as a website application, the PHP programming language as a back-end, MySQL as a database, and Expo to build applications into an apk form. The results of this study are stalls and Loos Rental Information Information System applications in the Karanganyar Market Based on Web and Android, this application can help see rental stalls and loos bills and make rental bill payments by simply opening a smartphone without having to come directly to the office Keywords: Information System, Stalls , Loos, Android, React Native and Laravel.
Co-Authors Aditya Kurniawan Aprilianti, Rafina Risqi Arzha, Fauzan Iryan Asfa, Anabella Ash Shiddiqy, Muhammad Ash-Sabiq, Agus Husein Aslam Fatkhudin Dewi, Alfa Yuliana Dhiyaulhaq, Naufal Fath, Haedar Al Febrianto, Muhammad Yusuf Feriansyah, Arif Haryanto, Jufri Nur Imam Bukhori Khambali, Ahmad Khasanah, Ika Wahyu Kusuma, Nur Intan Manggala, Kevin Haritsi Milatun Khanifah Nur Amanah NUR SALIM, NUR Nuridin Putri, Febriana Maulida Putri, Isna Ribowo, Tohir Jaya Rini Kristiyanti, Rini Rizqi, Fitriya Saifudin Saifudin Saputra, Meidika Syahrudin Syahrudin, Syahrudin Triwinarni, Indah Warto Wati, Sinta Rahma