IoT-enable monitoring can provide valuable information for the shellfish quality evaluation during cold storage condition. However, IoT based information storage relies on the centralized platform, it is possible to tamper. In this paper, we establish blockchain based multi-sensors (WSN) monitoring system to collect quality parameters and verify captured information for improving transparency and trust during cold storage. The implementation of the K-means and SVM algorithms were used in quality evaluation applications to classify and predict the quality loss of frozen shellfish. The results show blockchain based WSN monitoring can achieve the dynamic indicators continuous monitoring and ensures the data security and reliability. The proportion of the training set and the test set in the allowable deviation range is 88.89% and 87.17%. The root mean square error (RMSE) of training set and test set are 0.1502 and 0.1793 by SVM model. The performance of the K-means and SVM model has higher accuracy than BP model. This paper could help to reduce the risk of food losses and improve quality and safety management of frozen shellfish during cold storage.

Salmon is a highly perishable food due to temperature, pH, odor, and texture changes during cold storage. Intelligent monitoring and spoilage rapid detection are effective approaches to improve freshness. The aim of this work was an evaluation of IoT-enabled monitoring system (IoTMS) and electronic nose spoilage detection for quality parameters changes and freshness under cold storage conditions. The salmon samples were analyzed and divided into three groups in an incubator set at 0 °C, 4 °C, and 6 °C. The quality parameters, i.e., texture, color, sensory, and pH changes, were measured and evaluated at different temperatures after 0, 3, 6, 9, 12, and 14 days of cold storage. The principal component analysis (PCA) algorithm can be used to cluster electronic nose information. Furthermore, a Convolutional Neural Networks and Support Vector Machine (CNN-SVM) based algorithm is used to cluster the freshness level of salmon samples stored in a specific storage condition. In the tested samples, the results show that the training dataset of freshness is about 95.6%, and the accuracy rate of the test dataset is 93.8%. For the training dataset of corruption, the accuracy rate is about 91.4%, and the accuracy rate of the test dataset is 90.5%. The overall accuracy rate is more than 90%. This work could help to reduce quality loss during salmon cold storage.

Organic production, as a sustainable food production system, is designed to implement all agroecological principles that enable the preservation of human and animal health, environmental protection, and positive impact on society and the ecosystem while achieving significant economic benefits. Demand for organic food products is constantly growing, and the land area under organic production is continuously increasing. The problem in this sector is that producers of organic products face many administrative and systemic obstacles that prevent the faster development of this sector. On the other hand, consumers do not have complete confidence in the current mechanisms of control of organic production, so in the sale on the food markets and in the rest of the market, fake and unverified organic products can be found. Based on sensor data from the production field, this paper presents the SAFE platform as a solution for the described problem. The data necessary for producers to carry out the certification process are harmonized with the current legislation for organic food production. The SAFE platform uses blockchain technology to secure data consistency and history since it makes it impossible to change data history. The results of a survey about the SAFE platform are presented. The proposed solution stimulates the development and improvement of agricultural production by organic production methods, accompanied by increasing capacity in organic production.

(1) Background: At present, physiological stress detection technology is a critical means for precisely evaluating the comprehensive health status of live fish. However, the commonly used biochemical tests are invasive and time-consuming and cannot simultaneously monitor and dynamically evaluate multiple stress levels in fish and accurately classify their health levels. The purpose of this study is to deploy wearable bioelectrical impedance analysis (WBIA) sensors on fish skin to construct a deep learning-based stress dynamic evaluation model for precisely estimating their accurate health status. (2) Methods: The correlation of fish (turbot) muscle nutrients and their stress indicators are calculated using grey relation analysis (GRA) for allocating the weight of the stress factors. Next, WBIA features are sieved using the maximum information coefficient (MIC) in stress trend evaluation modeling, which is closely related to the key stress factors. Afterward, a convolutional neural network (CNN) is utilized to obtain the features of the WBIA signals. Then, the long short-term memory (LSTM) method learns the stress trends with residual rectification using bidirectional gated recurrent units (BiGRUs). Furthermore, the Z-shaped fuzzy function can accurately classify the fish health status by the total evaluated stress values. (3) Results: The proposed CNN-LSTM-BiGRU-based stress evaluation model shows superior accuracy compared to the other machine learning models (CNN-LSTM, CNN-GRU, LSTM, GRU, SVR, and BP) based on the MAPE, MAE, and RMSE. Moreover, the fish health classification under waterless and low-temperature conditions is thoroughly verified. High accuracy is proven by the classification validation criterion (accuracy, F1 score, precision, and recall). (4) Conclusions: the proposed health evaluation technology can precisely monitor and track the health status of live fish and provides an effective technical reference for the field of live fish vital sign detection.

The shell-closing strength (SCS) of oysters is the main parameter for physiological activities. The aim of this study was to evaluate the applicability of SCS as an indicator of live oyster health. This study developed a flexible pressure sensor system with polydimethylsiloxane (PDMS) as the substrate and reduced graphene oxide (rGO) as the sensitive layer to monitor SCS in live oysters (rGO-PDMS). In the experiment, oysters of superior, medium and inferior grades were selected as research objects, and the change characteristics of SCS were monitored at 4 °C and 25 °C. At the same time, the time series model was used to predict the survival rate of live oyster on the basis of changes in their SCS characteristics. The survival times of superior, medium and inferior oysters at 4 °C and 25 °C were 31/25/18 days and 12/10/7 days, respectively, and the best prediction accuracies for survival rate were 89.32%/82.17%/79.19%. The results indicate that SCS is a key physiological indicator of oyster survival. The dynamic monitoring of oyster vitality by means of flexible pressure sensors is an important means of improving oyster survival rate. Superior oysters have a higher survival rate in low-temperature environments, and our method can provide effective and reliable survival prediction and management for the oyster industry.