Aisyah Nur Nabila
Politeknik Perkapalan Negeri Surabaya

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Fish Check: Sistem Berbasis Convolutional Neural Network untuk Menilai Kelayakan Konsumsi Ikan Laut di Desa Weru, Kecamatan Paciran, Kabupaten Lamongan: Fish Check: A Convolutional Neural Network-Based System for Assessing the Edibility of Marine Fish in Weru Village, Paciran District, Lamongan Regency Santi Febrianti; Aisyah Nur Nabila; Ratih Berliana; Nuke Amalia; Rudy Suryadi; Riyan Bagus Prihandanu
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 2 (2026): Juni: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i2.1564

Abstract

Conventional assessment of fish freshness remains subjective, resulting in inconsistent evaluations. Advances in computer vision and Convolutional Neural Networks (CNNs) offer an opportunity to develop automated and objective approaches for assessing fish freshness through mobile devices. This study developed Fish Check, a smartphone-based application that utilizes the MobileNetV2 architecture to classify the freshness status of marine fish from digital images captured using a smartphone camera. A dataset comprising 2,400 marine fish images was collected. Image acquisition was conducted under varying lighting conditions, camera angles, and object positions to represent practical field conditions. The proposed approach involved image preprocessing, data augmentation, transfer learning-based model training, and performance evaluation using Accuracy, Precision, Recall, F1-score, and a Confusion Matrix. The optimized MobileNetV2 model was subsequently integrated into a React Native mobile application using TensorFlow Lite to enable efficient real-time inference directly on smartphones. The experimental results showed that the proposed model achieved an Accuracy of 96.39%, Precision of 96.11%, Recall of 96.74%, and F1-score of 96.42% demonstrate that the model can effectively distinguish between fresh and non-fresh marine fish. Overall, Fish Check provides a practical approach for real-time fish freshness assessment by combining a locally collected marine fish image dataset with an efficient deep learning architecture optimized for mobile deployment.
Evaluasi Efisiensi Komputasi Model MobileNetV2 Berbasis TensorFlow Lite untuk Klasifikasi Kesegaran Tiga Spesies Ikan pada Perangkat Edge Aisyah Nur Nabila; Teguh Junian Kuswanto; Santi Febrianti; Nuke Amalia; Riyan Bagus Prihandanu; Rudy Suryadi; Emy Sofia
Jurnal Elektronika dan Teknik Informatika Terapan ( JENTIK ) Vol. 4 No. 2 (2026): Juni: Jurnal Elektronika dan Teknik Informatika Terapan (JENTIK)
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jentik.v4i2.1627

Abstract

Fish freshness classification using computer vision offers a potential approach for rapid visual assessment. However, deploying deep learning models on edge devices requires consideration of both classification performance and computational efficiency. This study evaluates MobileNetV2 implemented with TensorFlow Lite for six-class image classification representing fresh and non-fresh conditions in three fish species: Johnius heterolepis, Rastrelliger brachysoma, and Nemipterus bathybius. The dataset described in this study consists of 372 images, comprising 300 training images and 72 validation images. Based on the confusion matrix presented, the model correctly classified 69 of the 72 validation images, yielding an accuracy of 95.83%. Misclassifications occurred in the non-fresh short mackerel class and the fresh large-scale croaker class. The computational evaluation framework considers model size, inference latency, throughput, and classification accuracy across Float32, Float16, and INT8 configurations. However, the efficiency values currently presented are illustrative scenarios rather than verified measurements obtained from converted models on a specified edge device. Therefore, no definitive conclusion can yet be drawn regarding the most computationally efficient configuration. Further experiments involving actual model conversion, consistent evaluation procedures, and device-level measurements are required. This study highlights the importance of evaluating classification performance alongside computational requirements when developing image-based fish freshness classification systems for edge deployment. The findings should be interpreted within the limitations of the available dataset and its labeling procedure.