Smart Packaging from Durian Seed Starch for Real-Time Quality Classification using DenseNet-121

Putri Nutriastuti; Euis Nursaadah; Azvadennys Vasiguhamiaz; Aceng Ruyani; Nurhamidah Nurhamidah; M. Lutfi Firdaus

doi:10.30829/zero.v10i1.28580

Smart Packaging from Durian Seed Starch for Real-Time Quality Classification using DenseNet-121

Putri Nutriastuti, Euis Nursaadah, Azvadennys Vasiguhamiaz, Aceng Ruyani, Nurhamidah Nurhamidah, M. Lutfi Firdaus

Abstract

This study used smart packaging made from durian seed starch with butterfly pea flower extract and applied the DenseNet121 deep learning model for real-time quality classification. Colorimetric analysis revealed a significant transition from Hue ~92° to Hue ~289° as food quality deteriorated due to pH changes. This study aimed to introduce a non-destructive vision-based classification framework utilizing the DenseNet121 deep learning architecture to demonstrate its effectiveness as a real time food freshness monitor. The dataset was divided into 70% training set, 20% validation set, and 10% test set to ensure robust model development. Performance was evaluated using accuracy, precision, recall, and F1 score. This methodology integrated physicochemical (pH) analysis with the development of a DenseNet121 architecture based Deep Learning model to classify food freshness phases. The results showed that edible films derived from durian seed starch and butterfly pea flower extract were capable of being indicators of food freshness. The dataset consisted of 160 images captured during a 12day experiment, which was expanded using stochastic data augmentation to improve model generalization. Computationally, the model achieved convergence with a training accuracy of 96% with loss 0.14 and achieved an internal testing accuracy of 0.94. Although testing on an external dataset recorded an accuracy of 0.78 due to environmental variability. This study proposes the first integration of durian seed starch based smart packaging with DenseNet121 architecture for automatic freshness classification of lempuk durian, providing a new approach for continuous food quality monitoring. These findings provide a quantitative basis for the application of applied mathematics and computer vision in sustainable food logistics.

Keywords

DenseNet121; Digital Image Analysis; Edible film; Food safety; Smart packaging.

Full Text:

PDF

References

E. Mocsari and S. S. Stone, “Dense Net,” Cvpr, vol. 39, no. 9, pp. 1442–1446, 2017, doi: 10.1109/CVPR.2017.243.

A. C. Chan, “From tensors to novelties: Low-dimensional representations for anomaly detection in multispectral imagery,” Machine Learning Applications, vol. 23, p. 100858, 2026, doi: 10.1016/j.mlwa.2026.100858.

M. Shanmugavelu and M. Sannasy, “A scheme of opinion search & relevant product recommendation in social networks using stacked DenseNet121 classifier approach,” Automatika, vol. 64, no. 2, pp. 248–258, 2023, doi: 10.1080/00051144.2022.2140389.

L. Zhu, P. Spachos, E. Pensini, and K. N. Plataniotis, “Deep learning and machine vision for food processing: A survey,” Current Research in Food Science, vol. 4, pp. 233–249, 2021, doi: 10.1016/j.crfs.2021.03.009.

C. R. Utami, W. Zuhdi, and A. N. R. Ida, “Characteristics and application of edible film from durian seed-corn starch with butterfly pea flower extract,” Asian Journal of Dairy and Food Research, vol. 44, no. 1, pp. 1–9, 2025, doi: 10.18805/ajdfr.drf-499.

C. Assyifa, Fatima, I. A. Franella, F. Halqiah, I. Sulaiman, and D. Yunita, “Application of anthocyanin extract from butterfly pea flower (Clitoria ternatea) as a freshness indicator,” Jurnal Teknologi Industri Pangan Unisri, vol. 10, no. 2, pp. 137–147, 2023, doi: 10.33061/jitipari.v10i2.11078.

K. N. Rahman, S. C. Banik, R. Islam, and A. Al Fahim, “A real time monitoring system for accurate plant leaves disease detection using deep learning,” Crop Design, vol. 4, no. 1, p. 100092, 2025, doi: 10.1016/j.cropd.2024.100092.

C. Wang et al., “Preparation, characterization, and application of pH-responsive biodegradable intelligent indicator film based on rose anthocyanins,” LWT, vol. 200, p. 116156, 2024, doi: 10.1016/j.lwt.2024.116156.

H. Ren, J. Wang, Z. Miao, F. Li, S. Yu, and P. Wu, “Multi-color composite films constructed by natural colorants and carbon dots: manipulation of color, property characterization, and application in food anti-counterfeiting packaging,” LWT, vol. 230, p. 118243, 2025, doi: 10.1016/j.lwt.2025.118243.

F. W. Hailu, S. W. Fanta, A. A. Tsige, and M. A. Delele, “Development of simple and biodegradable pH indicator films from cellulose and anthocyanin,” Discover Sustainability, vol. 6, no. 1, 2025, doi: 10.1007/s43621-025-00916-4.

Y. A. Septiati, M. Karmini, A. Kamaludin, and F. Fatimah, “Analisis Luas Bukaan Udara Penyimpanan Makanan terhadap Kadar Air dan Total Jamur Makanan Terkemas Bioplastik,” Jurnal Kesehatan Lingkungan Indonesia, vol. 23, no. 2, pp. 226–233, 2024, doi: 10.14710/jkli.23.2.226-233.

J. I. Pitt and A. D. Hocking, Fungi and Food Spoilage 3rd Edition, vol. 53, no. 9. 2009.

S. C. Wattimena and P. J. Patty, “Physical properties of durian (Durio zibethinus Murr) seed starch and its associated edible film,” Jurnal Sains Dasar, vol. 14, no. 2, pp. 1–7, 2025, doi: 10.21831/jsd.v14i2.90720.

C. D. Alfarisi, Y. Fitri, and D. K. Nisa, “Pengaruh Penambahan Tepung Biji Durian pada Pembuatan Bioplastik,” Biosaintropis, vol. 7, no. 1, pp. 44–55, 2021, doi: 10.33474/e-jbst.v7i1.385.

A. Istiani, N. A. Wardani, M. Kafiya, N. A. Hanifah, and Z. Nukhia, “Karakterisasi Edible Film dari Pektin Kulit Durian, Pati Singkong, dan Gliserol,” Eksergi, vol. 21, no. 1, p. 17, 2023, doi: 10.31315/e.v21i1.10949.

W. K. Z. Oktoeberza et al., “Multi-class skin cancer on imbalanced data,” Jurnal Nasional Pendidikan Teknik Informatika, vol. 14, no. 2, pp. 421–431, 2025, doi: 10.23887/janapati.v14i2.85544.

A. L. Zahra, A. A. Arifiyanti, and T. L. I. Sugata, “Implementasi arsitektur CNN DenseNet-121 untuk identifikasi autoimun kulit dengan augmentasi data,” Jurnal Ilmiah Teknik Informatika Komunikasi, vol. 5, no. 2, pp. 94–113, 2025, doi: 10.55606/juitik.v5i2.1026.

S. Niam, I. Ahmad, M. A. Rayhan, S. Mahmood, P. H. Jon, and M. M. Ahmed, “Machine learning-based optimization of alginate, guar gum, and pectin-based edible coatings for extended strawberry shelf life,” LWT, vol. 233, p. 118548, 2025, doi: 10.1016/j.lwt.2025.118548.

T. Dhar et al., “Molecular validation integrated reliable deep learning approach for early blight severity detection in tomato crops under protected cultivation environments,” Results in Engineering, vol. 28, p. 107739, 2025, doi: 10.1016/j.rineng.2025.107739.

D. Chicco and G. Jurman, “The advantages of the matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, pp. 1–13, 2020, doi: 10.1186/s12864-019-6413-7.

S. K. Ray, M. A. Hossain, N. Islam, and M. A. F. M. Rashidul Hasan, “Enhanced plant health monitoring with dual head CNN for leaf classification and disease identification,” Journal of Agriculture and Food Research, vol. 21, p. 101930, 2025, doi: 10.1016/j.jafr.2025.101930.

M. Mustapha et al., “A hybrid machine learning approach for imbalanced irrigation water quality classification,” Desalination and Water Treatment, vol. 321, 2025, doi: 10.1016/j.dwt.2024.100910.

N. Gul, K. Muzaffar, S. Z. A. Shah, A. Assad, H. A. Makroo, and B. N. Dar, “Deep learning hyperspectral imaging: a rapid and reliable alternative to conventional techniques in the testing of food quality and safety,” Quality Assurance and Safety of Crops and Foods, vol. 16, no. 1, pp. 78–97, 2024, doi: 10.15586/qas.v16i1.1392.

N. Songara and M. K. Jain, Design of qos and energy efficient vm consolidation framework for cloud data centers, vol. 643. 2020. doi: 10.1007/978-981-15-3125-5_19.

M. A. Mir, N. Zaidi, S. K. Chang, N. Abdelli, and K. Andrews, “Artificial intelligence applications in food science: a review of cutting-edge technologies,” Cogent Food and Agriculture, vol. 12, no. 1, p., 2026, doi: 10.1080/23311932.2025.2606439.

L. Kumar, D. Ramakanth, K. Akhila, and K. K. Gaikwad, “Edible films and coatings for food packaging applications: a review,” Environmental Chemistry Letters, vol. 20, no. 1, pp. 875–900, 2022, doi: 10.1007/s10311-021-01339-z.

S. Roy and J.-W. Rhim, “Anthocyanin food colorant and its application in pH-responsive color change indicator films,” Critical Reviews in Food Science and Nutrition, vol. 61, no. 14, pp. 2297–2325, Jul. 2021, doi: 10.1080/10408398.2020.1776211.

C. Wang and C. Liu, “A pH-Sensitive Intelligent Packaging Film Harnessing Anthocyanin for Food Freshness Monitoring,” Food and Bioprocess Technology, vol. 17, no. 12, pp. 5312–5323, 2024, doi: 10.1007/s11947-024-03431-y.

S. Gautam, M. Verma, and T. S. Lakhanpal, “Machine-learning driven design of bio-based active food packaging films with improved mechanical properties,” Sustainable Food Technology, vol. 3, no. 6, pp. 1705–1722, 2025, doi: 10.1039/d5fb00198f.

K. Kalinowska, W. Wojnowski, and M. Tobiszewski, “Smartphones as tools for equitable food quality assessment,” Trends in Food Science and Technology, vol. 111, pp. 271–279, 2021, doi: 10.1016/j.tifs.2021.02.068.

S. Perveen et al., “Utilization of biomaterials to develop the biodegradable food packaging,” International Journal of Food Properties, vol. 26, no. 1, pp. 1122–1139, 2023, doi: 10.1080/10942912.2023.2200606.

D. Sujatha, Dr. R. Sornakeerthi, and Dr.Sithishameem Fathima, “A Review of Fruit Disease Detection Using Deep Learning Models: Trends, Challenges, and Future Direction,” International Journal of Advanced Research and Interdisciplinary Scientific Endeavours, vol. 3, no. 4, pp. 982–990, 2025, doi: 10.61359/11.2206-2554.

P. Treepong and N. Theera-Ampornpunt, “Early bread mold detection through microscopic images using convolutional neural network: Early bread mold detection,” Current Research in Food Science, vol. 7, no. August, p. 100574, 2023, doi: 10.1016/j.crfs.2023.100574.

Y. Tjandra, G. Halim, J. Briano, and M. Tjahjono, “Smartphone-based digital image analysis for qualitative classification of food dyes using machine learning: effects of color space and lighting conditions,” Jurnal Kimia Pendidikan Kimia, vol. 10, no. 2, pp. 309–322, 2025, doi: 10.20961/jkpk.v10i2.107520.

Y. Pan et al., “A smartphone-based non-destructive multimodal deep learning approach using pH-sensitive pitaya peel films for real-time fish freshness detection,” Foods, vol. 14, no. 10, p. 1805, 2025, doi: 10.3390/foods14101805.

DOI: http://dx.doi.org/10.30829/zero.v10i1.28580