Article Per Year (5 Year)
p-Index From 2021 - 2026
3.235
P-Index
This Author published in this journals
All Journal Jurnal SOLMA JOURNAL OF APPLIED INFORMATICS AND COMPUTING JURIKOM (Jurnal Riset Komputer) INTI Nusa Mandiri Amalee: Indonesian Journal of Community Research & Engagement Jurnal Sistem Komputer dan Informatika (JSON) International Journal of Engineering, Science and Information Technology Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Decode: Jurnal Pendidikan Teknologi Informasi Indonesian Community Journal Jurnal Pengabdian, Riset, Kreativitas, Inovasi, dan Teknologi Tepat Guna (Parikesit) Jurnal Teras Pengabdian Masyarakat Scientific: Journal of Computer Science and Informatics Indonesian Applied Research Computing and Informatics
Afril Efan Pajri
Universitas Nahdatul Ulama Sunan Giri
Agriculture, Biological Sciences & Forestry Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Public Health Social Sciences Transportation Other

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

Found 23 Documents
Search

 1   2   3 
Sistem Cerdas Deteksi Asap Rokok Secara Real-Time Berbasis Sensor MQ-2 dan Mikrokontroler ATMEGA 16 untuk Keamanan Ruangan Sutriawan, Sutriawan; Afril Efan Pajri; Taufik Azhary
Jurnal Teknologi Sistem Informasi dan Sistem Komputer TGD Vol. 8 No. 1 (2025): J-SISKO TECH EDISI JANUARI
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/jsk.v8i1.10604

Abstract

Asap rokok sangat berbahaya bagi kesehatan manusia karena mengandung zat yang mematikan, seperti nikotin salah satunya. Walaupun asap rokok ini berbahaya,kebutuhan akan rokok tidak dapat dihentikan karena besarnya permintaan konsumen dan kebanyakan orang tidak peduli akan efek negatif asap rokok. Banyak cara yang dilakukan untuk meminimalisir bahaya asap rokok bagi perokok pasif, salah satunya dengan cara membuat stiker atau pun larangan untuk tidak merokok. Namun ternyata cara ini kurang efektif karena masih ada orang yang merokok walaupun sudah mengetahui larangan tersebut. maka penelitian ini bagaimana membuat sistem detektor asap menggunakan sensor MQ-2 berbasis mikrokontroler Atmega 16. Tujuan dari penelitian ini adalah membangun sebuah alat untuk mendeteksi asap sehingga jika asap semakin menggumpal dan banyak maka akan muncul informsi busher. sumber kaidah, konsep dan teori-teori yang mendukung dalam penyelsaian masalah dalam penelitian ini. Pada tujuan ini ditentukan tujuan yang akan dicapai, terutama dalam mengatasi masalah yang ada
Tensile and Flexural Properties of Epoxy Nanocomposites Reinforced with Cellulose Nanocrystals Azhary, Taufik; Pajri, Afril Efan
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.892

Abstract

Composite materials are extensively utilized across various fields such as engineering, aviation, automotive, construction, and healthcare. This widespread application highlights their superior properties, often absent in the individual constituent materials. Additionally, composites offer the advantage of being easily fabricated to meet specific requirements, and incorporating natural fibers as reinforcement has gained significant interest due to their environmental friendliness and abundance. Among these, nanocellulose is a promising green material due to its unique characteristics. Specifically, cellulose nanocrystals (CNC), nanoscale derivatives of nanocellulose, have attracted considerable attention as reinforcement agents in composite fabrication. This interest stems from CNC's notable advantages, including excellent mechanical properties, a high crystallinity index, plentiful availability, low weight, and eco-friendly nature. This study was undertaken to investigate the impact of varying concentrations of cellulose nanocrystal (CNC) (0, 0.5, 0.75, 1 wt%) on the mechanical properties, specifically the tensile and flexural properties, of epoxy resin/cellulose nanocrystal (E/CNC) nanocomposites. The materials employed in this research include epoxy resin, hardener, and cellulose nanocrystals. The fabrication of the E/CNC nanocomposites was carried out through a straightforward mixing method, wherein the constituent materials were blended following the defined experimental parameters, followed by the molding process. The findings of this study indicate that the incorporation of cellulose nanocrystals (CNC) significantly enhances the mechanical properties of E/CNC nanocomposites. The E/0.75CNC nanocomposite showed optimal tensile strength (39.91 MPa; +4.95%), while E/1CNC exhibited superior flexural strength (65.78 MPa; +5.08%) compared to the unmodified epoxy baseline.
RANCANG BANGUN APLIKASI PREDIKSI TAGIHAN AIR BERBASIS WEB MENGGUNAKAN REGRESI LINIER BERGANDA Arum , Arum Fatmawati; Pajri, Afril Efan; Sahri
INTI Nusa Mandiri Vol. 20 No. 1 (2025): INTI Periode Agustus 2025
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v20i1.6899

Abstract

The management of water billing in the PAMSIMAS service in Sidobandung Village is still conducted manually and does not provide early information regarding bill estimates, often resulting in delayed payments by customers. This study aims to design and develop a web-based water bill prediction application using the Multiple Linear Regression (MLR) method, capable of delivering fast, accurate, and accessible billing estimates. The dataset used in this research consists of historical monthly water usage and billing data from January to December 2024, with a structure comprising 231 rows of customer data and 30 feature columns. The research stages include data preprocessing, model training using MLR, integration of the model into a web-based system, and evaluation of prediction results using the Mean Squared Error (MSE) and R-squared ( ) metrics. Evaluation results showed that the model achieved an MSE of 18,882 and an  of 0,8, indicating a fairly good and stable prediction performance. The system allows customers to log in, view predicted water bills for the 13th month based on previous data, and access graphical visualizations of usage and cost trends. Meanwhile, the admin can efficiently manage customer data through a dedicated dashboard. With the implementation of this application, the management and prediction process of water billing becomes more transparent, efficient, and helps customers in planning their water expenses more precisely .
Klasisifikasi Tingkat Kemiskinan Di Indonesia Menggunakan Algoritma Naives Bayes Suci Mulyani; Pajri, Afril Efan; Fikram, Muhammad
Scientific: Journal of Computer Science and Informatics Vol. 1 No. 2 (2024): Juli 2024
Publisher : Universitas Muhammadiyah Bima

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34304/scientific.v1i2.333

Abstract

Abstrak penelitian ini dilatarbelakangi oleh urgensi klasifikasi tingkat kemiskinan yang akurat sebagai landasan pengambilan keputusan dan penyaluran bantuan yang tepat sasaran. Penelitian ini bertujuan untuk membangun model klasifikasi tingkat kemiskinan menggunakan algoritma Naïve Bayes yang diimplementasikan dalam software RapidMiner. Metode penelitian yang digunakan meliputi pengumpulan data dari berbagai sumber, pra-pemrosesan data untuk membersihkan dan mentransformasi data, implementasi algoritma Naïve Bayes untuk membangun model klasifikasi, serta evaluasi kinerja model menggunakan metrik akurasi, presisi, dan recall. Hasil penelitian menunjukkan bahwa model yang dibangun mencapai akurasi sebesar 96.12%, dengan kemampuan identifikasi yang baik pada kelompok tidak miskin (presisi 100%) dan kelompok miskin (recall 100%). Meskipun demikian, presisi pada kelompok miskin masih perlu ditingkatkan (75%) untuk meminimalkan kesalahan klasifikasi dan memastikan bantuan yang diberikan lebih efektif dan tepat sasaran.
Optimalisasi Manajemen Operasional dan Pemasaran Digital untuk Meningkatkan Daya Saing Produk Upcycling di BUMDes Berkaho Pungpungan Sahri, Sahri; Tawakkal, M. Iqbal; Pajri, Afril Efan
Jurnal SOLMA Vol. 14 No. 3 (2025)
Publisher : Universitas Muhammadiyah Prof. DR. Hamka (UHAMKA Press)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22236/solma.v14i3.20263

Abstract

Background: Program menghadapi permasalahan rendahnya efisiensi produksi serta terbatasnya akses pasar pada produk upcycling BUMDesa Berkaho. Hal ini disebabkan kurangnya pemanfaatan teknologi dan strategi pemasaran yang belum optimal. Tujuan: Program ini bertujuan untuk meningkatkan daya saing produk upcycling di BUMDes Berkaho melalui optimalisasi manajemen operasional dan pemasaran digital. Metode: Metode yang digunakan berbasis Participatory Learning and Action (PLA) yang mencakup sosialisasi, pelatihan, penerapan teknologi, monitoring dan evaluasi, serta perencanaan keberlanjutan. Pelatihan difokuskan pada peningkatan keterampilan manajerial, penggunaan alat produksi tepat guna, serta pemanfaatan media sosial sebagai sarana promosi. Hasil: Hasil kegiatan menunjukkan adanya peningkatan kapasitas pengurus dan anggota BUMDesa dalam mengelola usaha, melakukan diversifikasi produk, dan terlibat aktif dalam pemasaran digital. Kesimpulan: Program ini berkontribusi dalam memberdayakan potensi lokal melalui pemanfaatan teknologi dan kolaborasi masyarakat, serta membangun fondasi usaha desa yang lebih berkelanjutan dan adaptif terhadap dinamika pasar.
Pelatihan Strategi Pemasaran Digital untuk Meningkatkan Daya Saing UMKM Desa Ngeper, Kabupaten Bojonegoro di Era Ekonomi Digital Sahri Sahri; M. Iqbal Tawakkal; Afril Efan Pajri; Nanda Sahita; Pepbelia Veronyca
I-Com: Indonesian Community Journal Vol 5 No 2 (2025): I-Com: Indonesian Community Journal (Juni 2025)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/i-com.v5i2.7476

Abstract

Pelaku UMKM di Desa Ngeper, Kecamatan Padangan, Kabupaten Bojonegoro, menghadapi kendala dalam memasarkan produk secara digital akibat minimnya pengetahuan dan keterampilan di bidang digital marketing. Kegiatan pengabdian ini bertujuan untuk meningkatkan kapasitas pelaku usaha dalam memanfaatkan media digital guna memperluas pasar dan daya saing. Metode pelaksanaan menggunakan pendekatan ABCD (Asset-Based Community Development) yang menekankan pada penguatan potensi lokal melalui tahapan Discovery, Dream, Design, dan Delivery. Kegiatan Pelatihan diikuti oleh UMKM yang ada di desa ngeper sebanyak 21 Peserta. Pelatihan dilaksanakan selama dua hari dan mencakup materi strategi pemasaran online, pembuatan akun bisnis, konten promosi, serta praktik langsung. Hasil kegiatan menunjukkan peningkatan signifikan dalam pemahaman dan keterampilan peserta, yang dibuktikan melalui hasil post-test dan partisipasi aktif selama pelatihan, Rata-rata nilai post-test mengalami kenaikan sebesar 25 poin atau sekitar 45%. Kegiatan ini mendorong transformasi digital UMKM secara berkelanjutan dan membangun sinergi antara perguruan tinggi, pemerintah desa, dan masyarakat.
Sentiment Analysis of President Prabowo's Performance on Twitter (X) with a Comparative Study of SVM, XGBoost, and AdaBoost Maruf, Anang; Pajri, Afril Efan; Liana, Putri
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.12138

Abstract

This study was conducted to understand how Twitter (X) users respond to President Prabowo's performance through machine learning-based sentiment analysis. Data was collected using a dataset crawling approach, then processed through a series of pre-processing stages such as cleansing, case folding, tokenisation, stopword removal, and stemming before being converted into a numerical representation with TF-IDF. The class imbalance problem was addressed by applying SMOTE so that the model could learn more evenly. Three classification algorithms, SVM, XGBoost, and AdaBoost, were tested with the help of GridSearchCV to obtain the best parameter configuration. The research evaluation showed that the XGBoost algorithm was able to provide the best performance with an accuracy of 0.8443, followed by the SVM algorithm with an RBF kernel, which achieved an accuracy of 0.8135. The AdaBoost algorithm came in third with an accuracy of 0.7868. These findings indicate that the boosting approach, especially XGBoost, is better able to handle complex language patterns and high-dimensional text data characteristics. Overall, this study provides an overview of public opinion trends on social media and can be used as a reference for the development of sentiment analysis models in future research.
Classification Of Student Depression Using Support Vector Machine Modelling and Backward Elimination Sabar, Rohmat Abidin; Pajri, Afril Efan; Budiani, Jauhara Rana
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.12203

Abstract

Depression among university students has become a serious mental health concern that can negatively affect academic performance and overall well-being. Early detection of Depression is essential to provide timely support and preventive interventions. This study proposes a machine learning approach to classify student Depression using a Support Vector Machine (SVM) combined with Backward Elimination (BE) for feature selection. The dataset used in this research was obtained from a public repository and consists of 502 student records with multiple psychological and demographic attributes. Data preprocessing included categorical encoding and Min–Max normalization, followed by an 80:20 split for training and testing. Experimental results show that the baseline SVM model achieved an accuracy of 0.9208, while the application of Backward Elimination improved the performance to 0.9604. In addition, precision, recall, and F1-score also showed notable improvements, indicating a reduction in misclassification, particularly for non-depressed students. These findings demonstrate that integrating feature selection with SVM can enhance classification performance and provide a more efficient model for supporting early Depression detection among university students.
Development of Personalized Recommendation System for Online Educational Content Based on Machine Learning Dwi Remawati; Khairunnisa; Afril efan Pajri; Kumaratih Sandradewi; Sri Hariyati Fitriasih
Indonesian Applied Research Computing and Informatics Vol. 1 No. 1: July (2025)
Publisher : PT. Teras Digital Nusantara

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

Abstract

The rapid growth of online educational platforms has increased the demand for intelligent recommendation systems that can personalize learning content to match individual learner needs. However, traditional methods such as Content-Based Filtering (CBF) and Collaborative Filtering (CF) often struggle with issues like data sparsity, limited adaptability, and cold-start problems. This study aims to develop a personalized recommendation system for online educational content by integrating Singular Value Decomposition (SVD) with an adaptive feedback loop to improve recommendation relevance and learner engagement. The proposed machine learning-based method captures latent user-item interactions and dynamically updates recommendations based on real-time user feedback. Experimental evaluation using a dataset of simulated learner interactions demonstrates that the proposed model significantly outperforms baseline methods, achieving higher scores in Precision (0.57), Recall (0.53), F1-Score (0.55), Mean Reciprocal Rank (MRR: 0.52), and Engagement Rate (72.1%). These results suggest that combining matrix factorization with adaptive learning can substantially enhance the performance of educational recommender systems, leading to more accurate, timely, and engaging content delivery.
Impact of Data Normalization on K-Nearest Neighbor Classification Performance: A Case Study on Date Fruit Dataset Muhammad Jauhar Vikri; Afril Efan Pajri; Putri Liana
Indonesian Applied Research Computing and Informatics Vol. 1 No. 2: December (2025)
Publisher : PT. Teras Digital Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64479/iarci.v1i2.61

Abstract

Data normalization is a crucial preprocessing step for distance-based classification algorithms such as K-Nearest Neighbor (KNN), as differences in feature scales can significantly affect distance calculations and classification accuracy. This study investigates the impact of data normalization on KNN classification performance using the Date Fruit Dataset as a case study. Three preprocessing scenarios are evaluated: raw data without normalization, Min–Max normalization, and Z-score standardization. In addition, the performance of standard KNN is compared with distance-weighted KNN to assess the contribution of distance weighting under different preprocessing conditions. The experiments are conducted using stratified 10-fold cross-validation, and model performance is evaluated using accuracy and standard deviation. Statistical significance of performance differences is examined using paired t-test, and sensitivity analysis is performed to analyze the effect of varying the number of nearest neighbors. The results show that data normalization leads to a substantial improvement in classification performance compared to raw data. Z-score standardization achieves the highest and most stable accuracy, followed by Min–Max normalization. Distance-weighted KNN consistently produces slightly higher accuracy than standard KNN; however, the improvement is not statistically significant after normalization. Sensitivity analysis indicates that normalized data results in a wider and more stable range of optimal k values. These findings demonstrate that data normalization plays a more dominant role than distance weighting in improving KNN performance. The study provides empirical evidence that proper preprocessing is essential for reliable KNN-based classification and establishes a robust baseline for further enhancements such as feature weighting and metaheuristic optimization.
Co-Authors Alif Yuanita Kartini Amelia Faza Aprillia Dwi Ardianti Arum , Arum Fatmawati Arum Fatmawati Arum Denny Nurdiansyah Diah Fitriani Dwi Remawati Eka Fadlilatus Saadah Eka Fadlilatus Saadah Fatichatur Rochmaniyah Fatichatur Rochmaniyah Fikram, Muhammad Ifnu Wisma Dwi Prastya Ita Aristia Sa'ida Jauhar Vikri, Muhammad Jauhara Rana Budiani, Jauhara Rana Khairunnisa Kholifatus Sholihah Kumaratih Sandradewi Lindya Rossita Handoko M. Iqbal Tawakkal MARATUS SHOLIHAH, SITI Maruf, Anang Meliysa Pasa Bagna Aprilia Said Muhammad Sholihin Muhammad Sholihin Mula Agung Barata Nanda Sahita Pepbelia Veronyca Putri Liana Sabar, Rohmat Abidin Sahri Sahri Sahri Sahri Sahri Sahri Silviana Agustin Sirozul Huda Siti Azizah Aini Siti Shoimah Sri Hariyati Fitriasih Suci Mulyani Sutriawan Taufik Azhary Tawakkal, M. Iqbal Umar Farid Al Faqihi Wella Vernanda Meilasaroh