Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Clean Energy and Smart Technology TECHNOMEDIA : Informatics and Computer Science
Muhammad Alif Muwafiq Baihaqy
Unknown Affiliation
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Mechanical Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
SISTEM DETEKSI DAN KLASIFIKASI PENYAKIT TANAMAN PADI BERDASARKAN DAUN MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN ARSITEKTUR ResNet-50 Zulian Firmansyah; Dian Asmarajati; Muslim Hidayat; Nur Hasanah; Muhammad Alif Muwafiq Baihaqy; Nulngafan; Saifu Rohman
Tekompedia : Jurnal Ilmiah Ilmu Komputer Vol 2 No 2 (2025): Juli
Publisher : CV Nature Creative Innovation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58641/technomedia.v2i2.150

Abstract

Diagnosa penyakit padi secara konvensional dinilai bergantung pada pengamatan manual yang lambat dan kurang akurat maka diperlukan solusi yang lebih efisien dan objektif dengan pemanfaatan kecerdasan buatan. Penelitian ini bertujuan untuk mengembangkan sistem deteksi penyakit tanaman padi menggunakan bagian dari kecerdasan buatan yaitu metode Convolutional Neural Network (CNN) dengan arsitektur ResNet-50. Sistem dirancang untuk mendeteksi enam penyakit padi berdasarkan citra daun yaitu Blast, Bacterial Blight, Brown Spot, Tungro, False Smut dan Cercospora. Dataset berasal dari kombinasi data publik (kaggle.com) dan citra lapangan yang diambil langsung di daerah Kabupaten Wonosobo. Model dikembangkan dan di modifikasi dengan penambahan GlobalAveragePooling, Dense layer dengan aktivasi ReLU dan regularisasi L2, serta Dropout untuk mengurangi overfitting. Lapisan output menggunakan softmax untuk klasifikasi multi kelas. Evaluasi model menggunakan metrik akurasi, presisi, recall, dan F1-score. Model dapat menunjukkan akurasi pengujian yang tinggi sebesar 79.52% dan performa efektif dengan akurasi 92% pada Classification Report. Hasil deteksi langsung ditampilkan pada sistem berbasis web berupa skala probabilitas penyakit yang terdeteksi.
CHALLENGES IN DATA SECURITY: TECHNOLOGICAL AND REGULATORY CHALLENGES IN THE PROTECTION OF PERSONAL DATA IN THE DIGITAL ERA Asnawi, Muhamad Fuat; Muhammad Alif Muwafiq Baihaqy; Saifu Rohman; Nur Hasanah; Dian Asmarajati
Clean Energy and Smart Technology Vol. 4 No. 1 (2025): October
Publisher : Nacreva Publisher

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

Abstract

This study examines the challenges of personal data security in the digital era, focusing on encryption technology and the role of artificial intelligence (AI) in protecting personal data in an increasingly complex digital environment. Adopting a Systematic Literature Review (SLR) method, this study examines 91 articles obtained from IEEE Xplore and ScienceDirect to identify trends and challenges in personal data security, particularly in the context of cloud computing and the Internet of Things (IoT). The results show that although encryption technology and AI offer advanced solutions, major challenges remain in the implementation of global regulations such as GDPR and differences in policies and infrastructure across countries. This study also discusses potential solutions such as blockchain and the implementation of adaptive encryption to address weaknesses in personal data security.
IMPLEMENTATION OF CONVOLUTIONAL NEURAL NETWORK (CNN) ALGORITHM IN MOBILE APPLICATION-BASED VOICE EMOTION CLASSIFICATION SYSTEM Naufal Ammar Raihan; Muhamad Fuat Asnawi; Iman Ahmad Ihsannuddin; Nahar Mardiyantoro; Muhammad Alif Muwafiq Baihaqy
Clean Energy and Smart Technology Vol. 4 No. 2 (2026): April
Publisher : Nacreva Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58641/cest.v4i2.211

Abstract

The ability of machines to recognize emotions from voice is known as Speech Emotion Recognition (SER). This study developed a voice emotion classification system using a Convolutional Neural Network (CNN) and implemented it in the form of an Android mobile application. The main problem raised is how to recognize human emotions through voice signals accurately, efficiently, and in real-time on mobile devices. The study was conducted with two training stages, namely pre-training using the RAVDESS dataset and fine-tuning with the IndoWaveSentiment dataset. Audio data was converted into a 128×128×1 Mel-spectrogram to be input to the CNN. The CNN model consists of three convolution and pooling blocks, as well as dense and softmax layers. After training, the model was converted to TensorFlow Lite format and integrated with the Android application through a client-server architecture using Flask. The test results showed that the system was able to recognize neutral, happy, disappointed, and surprised emotions with a high level of accuracy both on test data but not as good on live recorded voice. The system also features a SQLite-based history feature. Test results showed 96% accuracy on external test data and 55% on live recorded audio, with an average accuracy of 75.5%. This indicates the model performs very well in structured conditions, but still needs improvement for real-world input.
Co-Authors Asnawi, Muhamad Fuat dian asmarajati Iman Ahmad Ihsannuddin muhamad Fuat Asnawi Muslim Hidayat Nahar Mardiyantoro Naufal Ammar Raihan Nulngafan NUR HASANAH Saifu Rohman Zulian Firmansyah