Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mega Novita has a total of 123 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Physics-Informed Descriptor Engineering and Explainable Machine Learning Reveal the Quantum Mechanical Origins of Electronic Dielectric Response in Oxide Materials

    by Mega Novita, Alok Singh Chauhan, Nancy Agarwal, Deepak Gupta, Wardatul Jannah, Imadudin Harjanto

    A physics-informed machine-learning model was created to forecast the dielectric constant of oxide materials. The study explores the physicochemical descriptors that govern the response of the materials. A set of 3304 non-metallic oxide compounds was built using the Materials Project database. A comprehensive feature space with 23 original and composition-derived variables as well as 10 physics-informed engineered variables representing electronic, thermodynamic, structural, magnetic, and chemical descriptors was constructed. This workflow included model benchmarking, hyperparameter optimization, repeated training (10 times) and testing, consensus feature selection, and SHapley Additive exPlanations (SHAP) analysis. Optimized XGBoost model was the model with the best overall predictive ability. A reduced representation of 25 descriptors was obtained by consensus-based feature selection that performed close to the complete 33-descriptor representation (MAE = 0.611, RMSE = 1.052, and R2 = 0.699). The SHAP analysis revealed that the descriptors associated with chemical properties, electronic excitation and atomic packing were key to the model predictions. The results indicate that the electronic dielectric response is related to a combination of a few physicochemical aspects instead of a single descriptor. The proposed framework offers an intuitive, data-centric method for examining the evolution of dielectric properties, and it can be used to screen and hypothesize oxide materials with desired electronic dielectric response.

  • Open Access

    Developing an Iconic Tuberose-Based Tourism Model through Multi-Year Community Empowerment in Doplang Village

    by Mega Novita, Senowarsito Senowarsito, Rifki Hermana, Sutomo Sutomo

  • Open Access

    Transformasi UMKM Desa Doplang melalui Koperasi Digital, Produk Wellness, IoT Smart Watering, dan Branding Wisata

    by Mega Novita, Senowarsito Senowarsito, Rifki Hermana, Sutomo Sutomo

    Desa Doplang di Kabupaten Semarang memiliki potensi besar pada komoditas bunga sedap malam, namun pemanfaatannya selama ini terbatas pada produk hias dengan nilai ekonomi rendah. UMKM setempat menghadapi kendala inovasi produk, akses pasar, dan kelembagaan ekonomi yang lemah. Program pengabdian multi-tahun sebelumnya (2023–2024) telah menghasilkan pelatihan dasar dan diversifikasi produk awal, tetapi aspek keberlanjutan kelembagaan, penerapan teknologi hemat sumber daya, dan strategi branding desa wisata belum terwujud optimal. Artikel ini bertujuan mendeskripsikan transformasi UMKM Desa Doplang pada tahun 2025 sebagai puncak program pemberdayaan melalui penguatan koperasi digital, pengembangan produk wellness, dan inovasi IoT smart watering. Kegiatan dilaksanakan dengan pendekatan partisipatif melibatkan UMKM, PKK, Karang Taruna, Pokdarwis, dan BumDes, melalui tahapan sosialisasi, pelatihan, penerapan teknologi, pendampingan, dan evaluasi. Hasil kegiatan menunjukkan terbentuknya koperasi digital SIRATIH dengan anggota awal pelaku UMKM desa sebagai wadah distribusi dan transaksi kolektif, peluncuran tiga produk wellness baru (lilin aromaterapi, body butter, dan lulur) yang memperluas portofolio UMKM, serta implementasi prototipe IoT smart watering yang mampu mengurangi penggunaan air hingga sekitar 20% pada lahan uji coba. Selain itu, booklet promosi wisata Jendela Doplang diterbitkan untuk memperkuat citra desa sebagai destinasi wisata berbasis wellness. Program ini membuktikan bahwa integrasi kelembagaan digital, inovasi produk, dan penerapan teknologi tepat guna mampu memperkuat daya saing UMKM sekaligus mendorong keberlanjutan ekonomi lokal. Implikasi lebih luas dari program ini adalah perlunya dukungan lintas sektor untuk mempercepat sertifikasi produk dan replikasi model ke desa lain yang memiliki potensi serupa.


  • Open Access

    Implementation and Comparative Analysis of CNN and Transfer Learning Models (EfficientNetB0, MobileNetV2, and ResNet50) for Rice Leaf Disease Detection Based on Digital Images

    by Tri Wahyu Utami, Mega Novita, Khoiriya Latifa

    Rice leaf diseases significantly reduce agricultural productivity, making early and accurate detection essential, particularly in rice-producing regions such as Indonesia. This study proposes an automated rice leaf disease detection system based on Convolutional Neural Networks (CNN) and transfer learning. The dataset, obtained from the Mendeley Data Repository, consists of 6,889 images classified into eight categories: Bacterial Leaf Blight, Brown Spot, Healthy Rice Leaf, Leaf Blast, Leaf Scald, Narrow Brown Leaf Spot, Rice Hispa, and Sheath Blight. The dataset was divided into 70% training, 15% validation, and 15% testing. A baseline CNN model and three pre-trained models—EfficientNetB0, MobileNetV2, and ResNet50—were evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The baseline CNN achieved a test accuracy of 48.26%, while EfficientNetB0 achieved 58.41%. In contrast, MobileNetV2 and ResNet50 demonstrated significantly better performance, with test accuracies of 79.98% and 76.60%, respectively. MobileNetV2 exhibited the most balanced performance across all classes, showing superior generalization capability and computational efficiency. The best-performing model was integrated into a Streamlit-based application, enabling real-time rice leaf disease detection through image upload. The results confirm that transfer learning substantially improves classification accuracy and robustness compared to conventional CNNs. This study highlights the potential of lightweight deep learning models for practical implementation in smart agriculture systems and provides a reliable solution for automated rice disease detection in real-world conditions.


  • Open Access

    Ultra-Low-Cost Hybrid OCR–LLM Architecture for Production Grade E-KTP Extraction

    by Anjar Tiyo Saputro, Bambang Agus Herlambang, Mega Novita

    Purpose: The purpose of this study is to be able to avoid limitations of inexpensive ID card data extraction services and preserve privacy, which can simultaneously achieve reliable operation even under an environment with minimum infrastructure, in particular if no dependency on GPU-based servers are required. Method: The proposed approach is a microservice pipeline with three stages: (1) local lightweight pre-processing on devices, (2) Tesseract CPU-based OCR. js, (3) fast text tokenization through a small premature external LLM. The system is developed as TypeScript backend utilizing the Hono framework with all image processing taking place locally in order to keeping user data private. Result: The result of the experimental evaluations with real ID card samples is that the system can run stably in low-performance VPS (1 vCPU, 1 GB RAM) with operation cost approximately IDR 2.5047 per extraction process and its accuracy level is acceptable for use in a production environment. Moreover, the results indicate that system latency is dominated by LLM inference at the cloud. Novelty: The main contribution and novelty of this study is that we demonstrate, for the first time, a cost-effective (privacy-preserving) OCR-LLM hybrid pipeline without demanding expensive GPU models at large scale which makes our system suitable under limited storage and resource constraints on-premises or edge environments in small organizations including micro-SaaS services.

  • Effect of Modified Kimpul Flour Substitution and Glycerol Monostearate Concentration on The Physicochemical and Sensory Properties of Sweet Bread

    by Siti Nurlaela Setianingsih, Rizky Muliani Dwi Ujianti, Iffah Muflihati, Fafa Nurdyansyah, Mega Novita, Diva Julia Paramita, Shindi Nofitasari, Dola Mareta Anggarini, Abdillah Fathan Generus Annajah

    Wheat flour is the primary ingredient in sweet bread production, yet its import-dependent supply in countries like Indonesia prompts the need for alternative local ingredients. Kimpul tuber (Xanthosoma sagittifolium), rich in carbohydrates, presents a promising substitute, though its native starch properties are less suitable for baking. This study aimed to evaluate the effect of substituting wheat flour with heat moisture treatment (HMT)-modified kimpul flour and the addition of glycerol monostearate (GMS) on the physicochemical and sensory properties of sweet bread. A factorial completely randomized design was applied using three wheat-to-kimpul flour ratios (3:1, 1:1, and 1:3) and three GMS concentrations (2%, 3%, and 4%). Results showed that higher kimpul flour substitution increased moisture and carbohydrate content but reduced protein and fat levels. Textural properties such as hardness and adhesiveness also increased with kimpul content, but these were mitigated by the addition of GMS, particularly at 3%. The optimal formulation 1:1 wheat-to-kimpul ratio with 3% GMS produced sweet bread with the best overall sensory acceptance. The findings suggest that HMT-modified kimpul flour combined with GMS can serve as a functional and acceptable alternative to wheat flour in bread production. This supports food diversification strategies and promotes the utilization of local tuber-based flours in bakery applications.

  • Open Access

    Strengthening Multiculturalism and the Pancasila Student Profile through Global Partnerships and Mobility in Indonesian Higher Education

    by Mega Novita, Riris Setyo Sundari, Nur Hidayat, Saptono Nugrohadi, Rahul Bhandari

    In the era of globalization, integrating international partnerships and mobility within higher education is crucial for fostering innovation, inclusivity, and cross-cultural understanding. This study examines how these elements contribute to the enhancement of the Pancasila Student Profile, which emphasizes character education and student-centered learning, within the framework of Indonesia’s Kurikulum Merdeka. Using an explanatory sequential mixed-methods approach, the research combines qualitative interviews and focus group discussions with quantitative surveys from students and faculty at Universitas PGRI Semarang. The results indicate that 85% of participants gained from cultural exchanges, improving cultural awareness (78%) and collaborative curriculum development (72%). Additionally, international mobility boosted global competence (75%) and reinforced Pancasila values (70%). Key strategies for improvement include enhancing pre-departure orientations, increasing funding for mobility programs, and integrating Pancasila principles into international collaborations. The study highlights the importance of global mobility in strengthening national identity and global competencies. It recommends that higher education institutions prioritize international mobility, integrate global experiences into curricula, and foster an inclusive learning environment.

  • Open Access

    Mental Health Chatbot Application on Artificial Intelligence (AI) for Student Stress Detection Using Mobile-Based Naïve Bayes Algorithm

    by Ekanata Desi Sagita Mariyana, Mega Novita, Nur Latifah Dwi Mutiara Sari

    Purpose: This study aims to design and evaluate a chatbot-based artificial intelligence system to identify stress levels in students using the Naïve Bayes classification method. With increasing mental health concerns among students, early stress detection is considered crucial for timely intervention Methods: This study proposes an AI-based chatbot system to detect student stress levels using a comparative approach between Naïve Bayes and Support Vector Machine (SVM) algorithms. A Kaggle dataset with 15 psychological and academic indicators was preprocessed and balanced using SMOTE. Naïve Bayes showed higher accuracy (90%) than SVM (89%). The trained model was deployed via Flask with Ngrok tunneling and integrated into a Flutter mobile app connected to the Gemini AI API for real-time stress screening. This research offers a practical and scalable solution for early mental health detection in students through intelligent chatbot interaction. Result: The findings show that the Naïve Bayes model achieves a classification accuracy of 90%, slightly surpassing the SVM model, which records an accuracy of 89%. Evaluation through ROC and AUC metrics supports the reliability of Naïve Bayes in detecting stress levels. The integrated chatbot offers a responsive and engaging platform for preliminary mental health assessments. Novelty: This research presents a unique contribution by combining AI-driven stress detection with a real-time chatbot interface, offering an accessible and scalable approach to student mental health support. The integration of machine learning models with conversational AI provides an innovative solution for early intervention. Future developments may involve deep learning and more diverse psychological inputs to further improve accuracy and effectiveness.


  • Open Access

    From Tuberose to Tourism by Leveraging Renewable Energy and Technology for Sustainable Development in Doplang Village

    by Mega Novita, Rifki Hermana, Senowarsito Senowarsito, Sutomo Sutomo, Rahul Bhandari

    This study investigates the integration of solar energy systems in the village of Doplang, Indonesia, to promote sustainable rural tourism centered around its cultural asset–the tuberose (bunga sedap malam). A mixed-method approach evaluates the impact of renewable energy technologies on the community’s readiness for eco-tourism development. Data collection includes semi-structured interviews, field observations, quantitative surveys, gathering insights on community perceptions, energy usage, and cost savings associated with solar battery systems. Interviews with local villagers, business owners, and government representatives provide qualitative insights into attitudes toward solar energy adoption and its implications for tourism practices. Field observations document the current energy infrastructure, while quantitative surveys assess energy needs, post-installation savings, and readiness to adopt solar-powered infrastructure. Preliminary findings indicate that the solar battery system generates 4.8 kWh of energy daily, leading to a 30% reduction in energy consumption and monthly electricity cost savings of IDR 675,000, contributing to an annual reduction of 1.56 tons of carbon emissions. By powering essential infrastructure, such as the village hall and local businesses, the solar system supports the burgeoning eco-tourism sector. The expected return on investment (ROI) within four to five years enhances the village’s economic state. This study highlights the need for policy support, including subsidies and training programs, to facilitate solar energy adoption, offering a scalable model for rural villages in Indonesia.