Claim Missing Document
Check
Articles

Found 40 Documents
Search

Deep residual bidirectional long short-term memory fusion: achieving superior accuracy in facial emotion recognition Munsarif, Muhammad; Ku-Mahamud, Ku Ruhana
Bulletin of Electrical Engineering and Informatics Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i3.9090

Abstract

Facial emotion recognition (FER) is a crucial task in human communication. Various face emotion recognition models were introduced but often struggle with generalization across different datasets and handling subtle variations in expressions. This study aims to develop the deep residual bidirectional long short-term memory (Bi-LSTM) fusion method to improve FER accuracy. This method combines the strengths of convolutional neural networks (CNN) for spatial feature extraction and Bi-LSTM for capturing temporal dynamics, using residual layers to address the vanishing gradient problem. Testing was performed on three face emotion datasets, and a comparison was made with seventeen models. The results show perfect accuracy on the extended Cohn-Kanade (CK+) and the real-world affective faces database (RAF-DB) datasets and almost perfect accuracy on the face expression recognition plus (FERPlus) dataset. However, the receiver operating characteristic (ROC) curve for the CK+ dataset shows some inconsistencies, indicating potential overfitting. In contrast, the ROC curves for the RAF-DB and FERPlus datasets are consistent with the high accuracy achieved. The proposed method has proven highly efficient and reliable in classifying various facial expressions, making it a robust solution for FER applications.
Segmentasi Pemain Bola Dengan Arsitektur U-Net Fajar Bima Laksono; Hannan Isnaen, Muhammad; Okta Wijaya, Risky; Munsarif, Muhammad
Infoman's : Jurnal Ilmu-ilmu Informatika dan Manajemen Vol. 18 No. 2 (2024): Infoman's
Publisher : LPPM & Fakultas Teknologi Informasi UNSAP

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

Abstract

Segmentasi merupakan teknik pada pengolahan citra digital yang memfokuskan pada pembagian objek ke dalam beberapa bagian dan pemisahan antara region (objek) dengan latar belakang. Dalam konteks ini, Ada tiga jenis karakteristik gambar yang signifikan, yaitu titik, garis, dan tepi. Segmentasi citra sendiri dapat dikelompokkan menjadi tiga kategori utama, yaitu identifikasi objek, identifikasi semantik, dan identifikasi instan.. Pada penelitian ini, fokusnya adalah pada segmentasi pemain bola menggunakan pendekatan deep learning, khususnya dengan metode Convolutional Neural Network (CNN) dan arsitektur U-Net. CNN merupakan salah satu metode neural network pada deep learning dan machine learning yang baik dalam hal akurasi pada pengenalan citra, sedangkan U-Net biasa Digunakan pada segmentasi citra yang berjenis semantik. Segmentasi semantik, adalah citra yang dibagi menjadi kategori objek dan bukan objek. Proses segmentasi pemain bola melibatkan tahap encoder dan decoder citra sebelum dimanfaatkan dalam proses pelatihan model, tahap pengujian melibatkan penerapan model CNN-U-Net untuk melakukan klasifikasi citra, menghasilkan. yang terdiri dari 11 kelas yaitu Bilah Gawang, Wasit, Iklan, Lapangan, Bola, Pelatih & Ofisial, Penonton, Kiper A, Kiper B, Tim A, dan Tim B Output tersebut akan dievaluasi dengan menghitung akurasi untuk memastikan performa model.
Hyperparameter optimization of convolutional neural network using grey wolf optimization for facial emotion recognition Munsarif, Muhammad; Saman, Muhammad; Ernawati, Ernawati; Santosa, Budi
Indonesian Journal of Electrical Engineering and Computer Science Vol 40, No 2: November 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v40.i2.pp898-906

Abstract

Facial emotion recognition (FER) is a challenging task in computer vision with wide applications in areas such as human-computer interaction, security, and healthcare. To improve the performance of convolutional neural networks (CNN) in FER, a novel approach combining CNN with grey wolf optimization (GWO) was proposed to optimize key hyperparameters. The CNN-GWO model was fine-tuned by adjusting hyperparameters such as the number of convolutional layers, kernel size, number of filters, and learning rate. This model was evaluated using the CK+ dataset and achieved an accuracy of 90.97%, demonstrating its competitive performance compared to existing methods. The optimized hyperparameters included three convolutional layers, 35 filters, a kernel size of 5, a learning rate of 0.045990, a dropout rate of 0.4988, and a max pooling size of 3. These results confirm that GWO is effective in optimizing CNN for FER tasks, providing an efficient solution to enhance model accuracy. This approach shows promising potential for future FER applications, highlighting GWO as a valuable optimization technique for CNN architectures.
Peningkatan Kompetensi Guru di SMK Muhammadiyah 2 Malang melalui Pelatihan Pengembangan Media Pembelajaran Berbasis Kecerdasan Buatan Faiq Madani; Ahmad Ilham; Muhammad Sam’an; Rima Dias Ramadhani; Akhmad Fathurrohman; Safuan Safuan; Muhammad Munsarif; Lukman Assaffat; Wendy Sarasjati; Dhendra Marutho
Nusantara: Jurnal Pengabdian kepada Masyarakat Vol. 6 No. 1 (2026): Februari: NUSANTARA Jurnal Pengabdian Kepada Masyarakat
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/nusantara.v6i1.7796

Abstract

This study aims to evaluate the effectiveness of the Artificial Intelligence-Based Learning Media Development Program (P3MP-AI) in enhancing teachers’ technological and pedagogical competencies at SMK Muhammadiyah 2 Malang. The program employed a descriptive approach using both quantitative and qualitative methods, including pre-test and post-test assessments, as well as direct observation of the training process. A total of 30 teachers from various disciplines actively participated in the program conducted on August 12, 2025. The evaluation results revealed an increase in the participants’ average scores from 100 to 130 out of a maximum of 150, indicating a significant improvement in their understanding of AI concepts and applications in education. Beyond competency enhancement, the training also fostered teachers’ confidence, creativity, and ability to integrate AI-based tools into interactive learning media. However, several challenges were identified, such as limited technological resources and time constraints in classroom implementation. Overall, this program has made a tangible contribution to strengthening teachers’ digital literacy and can serve as a replicable professional development model for other vocational schools seeking to advance AI-based educational transformation.
Analysis of the Integrated E-Mesp 4CS Mobile Instrument Eny Winaryati; Muhammad Munsarif; Iwan Junaedi; Utomo; Alya Dwi Arianty; Asiva Khoirunisa; Kafitra Marna Ibrahim
Jurnal Penelitian Pendidikan IPA Vol 11 No 11 (2025): November
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v11i11.12980

Abstract

The need for valid and contextually relevant supervision instruments remains a key challenge in realizing 21st-century education that integrates the 4Cs skills (critical thinking, creativity, collaboration, and communication) with the Profil Pelajar Pancasila. This study aimed to develop and evaluate the feasibility of the Integrated E-MESp 4Cs Mobile as a digital instrument for academic supervision. Using a research and development (R&D) approach with qualitative data collection, this study conducted Focus Group Discussions, in-depth interviews, and document analyses involving teachers, principals, supervisors, and education experts. The data was analyzed through interactive qualitative procedures, including data reduction, presentation, and verification. The results show that the E-MESp 4Cs Mobile instrument is feasible and relevant to be used as an integrated supervision tool that combines 4Cs indicators with the dimensions of the Pancasila Student Profile. Stakeholders also emphasized the need for standardization aligned with national guidelines and the potential use of artificial intelligence to support data-based supervision and policy recommendations. Overall, the E-MESp 4Cs Mobile instrument demonstrates strong potential to enhance teacher supervision practices, support deep learning, and strengthen the development of humanistic, inclusive, and character-oriented graduates.
Optimizing the compact convolution transformer for enhanced pneumonia detection Muhammad Munsarif; Norshuhani Zamin; Muhammad Sam’an
International Journal of Advances in Intelligent Informatics Vol 12, No 2 (2026): May 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v12i2.1805

Abstract

Pneumonia detection through medical imaging, especially using CT scans or X-rays, presents notable challenges due to the subtle and often unclear signs of the disease. This paper introduces a novel neural network model, the Compact Convolutional Transformer (CCT), designed to address these challenges by optimizing detection accuracy. The CCT model incorporates configuration dropout in its convolutional layers to enhance both robustness and precision.Experiments conducted on a dataset of 5,856 chest X-ray images from pediatric patients aged one to five years demonstrated the model's effectiveness, achieving a remarkable 97% accuracy, 97% recall, 98% precision, and an F1-score of 98%. When compared to state-of-the-art models like DarkNet-53 and VGG-19 + GradCAM, which achieved F1-scores of 97.3% and 95.61% respectively, the CCT model consistently matched or outperformed them, particularly when dealing with smaller and more complex datasets. Even models such as CNN + Bayesian Network, which used larger datasets, only reached an F1-score of 96.3%.These results underscore the superior efficiency and accuracy of the CCT model, highlighting its potential for broader applications in medical diagnostics and image analysis, especially in pneumonia detection.
Hyperparameter optimization of deep residual recurrent fusion models for facial emotion recognition Muhammad Munsarif; Ku Ruhana Ku-Mahamud
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 15, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v15.i3.pp2581-2594

Abstract

Deep learning facial emotion recognition (FER) is widely applied in healthcare, education, and human–computer interaction. However, many deep learning models suffer from suboptimal hyperparameter configurations that reduce accuracy and stability. This study proposes three deep residual recurrent fusion models that integrates residual blocks with recurrent neural networks (bidirectional long short-term memory (BiLSTM), long short-term memory (LSTM), and gated recurrent unit (GRU)) to capture both spatial and temporal features. A systematic hyperparameter optimization strategy was applied, tuning kernel size, filter size, recurrent units, batch size, learning rate, dropout, and weight decay to balance generalization and computational efficiency. The models were evaluated on four benchmark datasets: FER2013, FERPlus, RAF-DB, and CK+. The results show that optimized configurations achieved outstanding accuracy, reaching 99.85% on FER2013, 99.99% on FERPlus, and 100% on RAF-DB and CK+. These findings demonstrate that careful hyperparameter tuning significantly enhances feature extraction, mitigates vanishing gradient and overfitting issues, and improves generalization across diverse datasets. The proposed framework highlights the importance of optimization in advancing robust FER systems for real-world applications.
Pelatihan ChatGBT kepada Guru di Majelis Pendidikan Muhammadiah kota semarang untuk Peningkatan literasi digital Muhammad Munsarif; Muhammad Sam'an; Samsudi Raharjo
Jurnal Surya Masyarakat Vol 6, No 2 (2024): Mei 2024
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsm.6.2.2024.269-275

Abstract

The development of artificial intelligence (AI)--based learning models has made significant progress alongside the abundance of data. This enables the creation of complex deep-learning models to tackle increasingly intricate tasks. Evolving machine learning algorithms become a key factor in enhancing AI model capabilities. The demand for smart and efficient solutions from the business sector drives the adoption of AI technology, supported by advances in sensor technology, the Internet of Things (IoT), natural language processing (NLP), and image recognition. This article highlights the potential impact of AI model development on the learning experience, especially at the Elementary (SD), Junior High (SMP), and Senior High School (SMA) levels. Implementing AI models in elementary and secondary schools can support student progress assessment, provide material recommendations based on student understanding, and develop skills. The study discusses a teacher training initiative using ChatGPT to understand and utilize artificial intelligence in education. Training results show that teachers can effectively create varied and engaging learning materials using ChatGPT. Despite AI's benefits, cultural and social values remain irreplaceable, such as ethics towards teachers and social interactions among students. In conclusion, digital literacy training for teachers is essential to enhance their ability to develop modern and effective learning models, with AI as a valuable tool in creating dynamic and interactive learning environments.
Peningkatan Kompetensi Guru di Sekolah Menengah Islam Ihsanul Fikri melalui Pelatihan Pengembangan Media Pembelajaran Berbasis Kecerdasan Buatan: Sebuah Studi Mixed-Methods Rima Dias Ramadhani; Ahmad Ilham; Muhammad Sam’an; Akhmad Fathurohman; Safuan Safuan; Muhammad Munsarif; Lukman Assaffat; Asdani Kindarto; Muhammad Wahyu Anggana; Teguh Firmasyah; M. Amin Syaifani; Afan Arga Ahyana; Adi Nugroho; Janu Yogi Kurnia
Jurnal Surya Masyarakat Vol 7, No 2 (2025): Mei 2025
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsm.7.2.2025.207-214

Abstract

The training program on Artificial Intelligence-based Learning Media Development (P3MP-AI) represents a strategic initiative to enhance the quality of education at the Ihsanul Fikri Integrated Islamic High School. In the rapidly evolving landscape of information technology, the integration of Artificial Intelligence (AI) technology into education has become an urgent necessity. This endeavor aims to address the personalized learning needs, overcome human resource and time constraints, and enhance the overall quality of education in achieving educational goals. Through the Active and Interactive Learning Method (MPB-AI) approach, educators engage in various practical and interactive activities, enabling them to comprehend and applykecerdasan buatanconcepts practically. Evaluation of this training program demonstrates significant achievements in enhancing participants' understanding and skills, as well as a high level of creativity and diversity in AI-based learning media development practices. Thus, this training program has successfully achieved its objectives in improving the quality of education at the Ihsanul Fikri Integrated Islamic High School. Recommendations for future activities include extending the duration of implementation for optimal goal attainment and developing similar activities periodically to continually enhance educators' abilities in delivering more effective and efficient learning experiences.
Pelatihan ChatGBT kepada Guru di Majelis Pendidikan Muhammadiah kota semarang untuk Peningkatan literasi digital Muhammad Munsarif; Muhammad Sam'an; Samsudi Raharjo
Jurnal Surya Masyarakat Vol 6, No 2 (2024): Mei 2024
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsm.6.2.2024.269-275

Abstract

The development of artificial intelligence (AI)--based learning models has made significant progress alongside the abundance of data. This enables the creation of complex deep-learning models to tackle increasingly intricate tasks. Evolving machine learning algorithms become a key factor in enhancing AI model capabilities. The demand for smart and efficient solutions from the business sector drives the adoption of AI technology, supported by advances in sensor technology, the Internet of Things (IoT), natural language processing (NLP), and image recognition. This article highlights the potential impact of AI model development on the learning experience, especially at the Elementary (SD), Junior High (SMP), and Senior High School (SMA) levels. Implementing AI models in elementary and secondary schools can support student progress assessment, provide material recommendations based on student understanding, and develop skills. The study discusses a teacher training initiative using ChatGPT to understand and utilize artificial intelligence in education. Training results show that teachers can effectively create varied and engaging learning materials using ChatGPT. Despite AI's benefits, cultural and social values remain irreplaceable, such as ethics towards teachers and social interactions among students. In conclusion, digital literacy training for teachers is essential to enhance their ability to develop modern and effective learning models, with AI as a valuable tool in creating dynamic and interactive learning environments.
Co-Authors A. Awoseyi, Ayomikun Abdollahi, Jafar Abul Walid Adi Nugroho Adinullhaq, Juyus Muhammad Afan Arga Ahyana Agatra, Denaya Ferrari Noval Ahmad Ilham Ahmad Ilham Ahmad Ilham Ahmad Miftakhul Akhmad Fathurohman Akhmad Fathurrohman Akhmad Fathurrohman Alfi Widianto Alif Hardika Andrian Fahrezi Ardhani, Yevi Alviatul Arfido Ramadhani Arianty, Alya Dwi ARIF KURNIAWAN Ariyanto, Nova Arnold Adimabua Ojugo Asdani Kindarto Asdani Kindarto Asiva Khoirunisa Budi Santosa Budi Santosa Caesarizky, Ovien Yoga Cornella, Barisma Ami De Rosal Ignatius Moses Setiadi Devy Maharja Pristya Dhendra Marutho Dhendra Marutho Edi Noersasongko Edy Winarno Eny Winaryati Eny Winaryati Ernawati Ernawati Fahrezi, Andrian Faiq Madani Fajar Bima Laksono Febrianto Febrianto Febrianto Febrianto, Febrianto Galih Ratna Hakim, Muhammad Ilham Hannan Isnaen, Muhammad Ilham, Ahmad Irvan Nurmantoro Irvan Nurmantoro Iwan Junaedi Janu Yogi Kurnia Javier Rayhan Jian Janata Juyus Muhammad Adinullhaq Kafitra Marna Ibrahim Kholifatul Afwah Kindarto, Asdani Ku Ruhana Ku-Mahamud Ku-Mahamud, Ku Ruhana Lukman Assaffat Lukman Assaffat Luqman Assaffat Luqman Assaffat M. Amin Syaifani Mahmudah Mahmudah Mardiana Mardiana Meike Amelia Hanifah Melda Saputri Mila Moch Arief Soeleman Mochammad Arief Soeleman Muhammad Sam'an Muhammad Sam'an Muhammad Sam’an Muhammad Sam’an Muhammad Sam’an Muhammad Wahyu Anggana Muthia Aulia Rahma Muza'in, Muhammad Nila Kartika Sari Norshuhani Zamin Norshuhani Zamin Nova Ariyanto Nur Faizah Nurmantoro, Irvan Nurul Farah Izzatuna Okta Wijaya, Risky Pulung Nurtantio Andono Purbandanu, Muhammad Wigig Ramadhani, Arfido Ramadhani, Rima Dias Richmond Ampah-Mensah Rima Dias Ramadhani Safuan Safuan Safuan Safuan Safuan Safuan Safuan Safuan Safuan Safuan Salsabila Rahma Saman, Muhammad Samsudi Raharjo Samsudi Raharjo Sefrina Ainun Shabrina Mirza Siti Muzdalifah Suwahono Suwahono Teguh Firmasyah Tirta Ramadhani Utomo Wendy Sarasjati Wendy Sarasjati Wibowo, Bhanu Lintang Yanuarta, Rizky Yesika Maya Ocktarani Yevi Alviatul Ardhani