With the rapid emergence of deep learning (DL) technology, it has been successfully used in various fields including aquaculture. This change can create new opportunities and a series of challenges for information and data processing in smart fish farming. This paper focuses on the applications of DL in aquaculture, including live fish identification, species classification, behavioral analysis, feeding decision-making, size or biomass estimation, water quality prediction. In addition, the technical details of DL methods applied to smart fish farming are also analyzed, including data, algorithms, computing power, and performance. The results of this review show that the most significant contribution of DL is the ability to automatically extract features. However, challenges still exist; DL is still in an era of weak artificial intelligence. A large number of labeled data are needed for training, which has become a bottleneck restricting further DL applications in aquaculture. Nevertheless, DL still offers breakthroughs in the handling of complex data in aquaculture. In brief, our purpose is to provide researchers and practitioners with a better understanding of the current state of the art of DL in aquaculture, which can provide strong support for the implementation of smart fish farming.

Deep learning for smart fish farming: applications, opportunities and challenges

Towards automated aquaponics: A review on monitoring, IoT, and smart systems

Application of machine learning in intelligent fish aquaculture: A review

Microbial biofilms have caused serious concerns in healthcare, medical, and food industries because of their intrinsic resistance against conventional antibiotics and cleaning procedures and their capability to firmly adhere on surfaces for persistent contamination. These global issues strongly motivate researchers to develop novel methodologies to investigate the kinetics underlying biofilm formation, to understand the response of the biofilm with different chemical and physical treatments, and to identify biofilm-specific drugs with high-throughput screenings. Meanwhile microbial biofilms can also be utilized positively as sensing elements in cell-based sensors due to their strong adhesion on surfaces. In this perspective, we provide an overview on the connections between sensing and microbial biofilms, focusing on tools used to investigate biofilm properties, kinetics, and their response to chemicals or physical agents, and biofilm-based sensors, a type of biosensor using the bacterial biofilm as a biorecognition element to capture the presence of the target of interest by measuring the metabolic activity of the immobilized microbial cells. Finally we discuss possible new research directions for the development of robust and rapid biofilm related sensors with high temporal and spatial resolutions, pertinent to a wide range of applications.

https://oist.repo.nii.ac.jp/?action=repository_action_common_download&item_id=2602&item_no=1&attribute_id=22&file_no=1

Detection and Characterization of Bacterial Biofilms and Biofilm-Based Sensors.

Dissolved oxygen is an important index to evaluate water quality, and its concentration is of great significance in industrial production, environmental monitoring, aquaculture, food production, and other fields. As its change is a continuous dynamic process, the dissolved oxygen concentration needs to be accurately measured in real time. In this paper, the principles, main applications, advantages, and disadvantages of iodometric titration, electrochemical detection, and optical detection, which are commonly used dissolved oxygen detection methods, are systematically analyzed and summarized. The detection mechanisms and materials of electrochemical and optical detection methods are examined and reviewed. Because external environmental factors readily cause interferences in dissolved oxygen detection, the traditional detection methods cannot adequately meet the accuracy, real-time, stability, and other measurement requirements; thus, it is urgent to use intelligent methods to make up for these deficiencies. This paper studies the application of intelligent technology in intelligent signal transfer processing, digital signal processing, and the real-time dynamic adaptive compensation and correction of dissolved oxygen sensors. The combined application of optical detection technology, new fluorescence-sensitive materials, and intelligent technology is the focus of future research on dissolved oxygen sensors.

Review of Dissolved Oxygen Detection Technology: From Laboratory Analysis to Online Intelligent Detection.

Research of dissolved oxygen prediction in recirculating aquaculture systems based on deep belief network

Traditional planting and aquaculture has the problem of large consumption of water resources and land resources, and the water environmental pollution is also a difficult problem facing human beings. Population growth and food safety issues have promoted the concept of aquaponics——a recycling ecological planting and breeding mode. It combines hydroponics and recirculating aquaculture technology to realize water resources and nutrient recycling, low pollution and high productivity and efficiency. In this paper, hydroponics as the main vegetable cultivation method in aquaponics and the main equipment of water treatment in recirculating aquaculture are introduced, and the traditional equipment and its development prospects are analyzed. The greenhouse environments, water quality and nutrient circulation involved in intelligent monitoring and control of aquaponic systems are systematically analyzed and summarized. This paper summarizes the current development of technology and methods in aquaponics and provides prospects for future development trends. With the development of technology, in the future, the aquaponics system will become more intelligent, intensive, accurate and efficient.

/pdf/equipment-and-intelligent-control-system-in-aquaponics-a-4t6pjkdlxo.pdf

Equipment and Intelligent Control System in Aquaponics: A Review


 Motor is widely used in industrial production, but the frequent motor bearing fault brings great safety hazard to the production. Traditional fault diagnosis methods often require prior signal processing knowledge and are inefficient. In order to solve this problem, the artificial intelligence fault diagnosis method has been applied in motor bearing fault diagnosis. With the help of the original motor running state signal collected by the sensors, non-invasive real-time detection of motor bearing fault can be realized. This paper presents an improved CNN-LSTM network based on hierarchical attention mechanism(CALSTM) for motor bearing fault diagnosis. In this artificial intelligence method, the fault characteristics of the original data can be learned by convolutional neural network, and then the importance of the features can be obtained by using hierarchical attention mechanism. Finally, the weighted results are sent to the LSTM network for time dimension selection. This method does not need signal processing and adaptively weights the features of each sample learned by the neural network, which enhances the explanatory ability of the learning process of the neural network. When carry out experiments on CWRU data set, and the experimental results indicate that, compared with several common models, CALSTM method has a better diagnosis effect, and the overall accuracy of the model reached 99.22%.

/pdf/an-improved-cnn-lstm-network-based-on-hierarchical-attention-wiqwgppg0e.pdf

An Improved CNN-LSTM Network Based On Hierarchical Attention Mechanism For Motor Bearing Fault Diagnosis

The invention provides a circulating pump bearing fault diagnosis method and system. In the system, a data acquisition module acquires three-phase current and vibration signals of a circulating pump motor, sends the three-phase current and vibration signals into a fault diagnosis module and also collects liquid level signals of a circulating water culture pond through a liquid level sensor; the fault diagnosis module is used for classifying circulating pump bearing faults and fault degrees through a stacked noise reduction self-encoder network optimized through an artificial bee colony algorithm; a warning module gives different warning signals according to different fault types and fault degrees; a regulation and control module can obtain four conditions according to the result of the fault diagnosis module and can obtain four kinds of regulation and control commands according to the liquid level information of the culture pond; and a general control module is used for monitoring andcontrolling the overall system, and the commands sent by the general control module are on the highest priority. Compared with a traditional network, a fault diagnosis algorithm model has the advantages that noise interference is reduced, the fault types can be quickly and accurately classified, the safety of a circulating water culture system is ensured, and circulating water culture earnings areincreased.

Li Wenshu

Papers

Review of Dissolved Oxygen Detection Technology: From Laboratory Analysis to Online Intelligent Detection.

Research of dissolved oxygen prediction in recirculating aquaculture systems based on deep belief network

Equipment and Intelligent Control System in Aquaponics: A Review

An Improved CNN-LSTM Network Based On Hierarchical Attention Mechanism For Motor Bearing Fault Diagnosis

Circulating pump bearing fault diagnosis method and system