Carbon dioxide (CO₂) enrichment in an agricultural environment has been shown to enhance the efficiency of crop photosynthesis, increasing crop yield and product quality. There is a problem of the excessive use of CO₂ gas when the CO₂ is enriched for crops, such as soybean and other field crops. Given the application of micro-nanobubbles (MNBs) in agricultural production, this research takes CO₂ as the gas source to prepare the micro-nanobubble water by the dissolved gas release method, and the response surface methodology is used to optimize the preparation process. The results show that the optimum parameters, which are the gas–liquid ratio, generator running time, and inlet water temperature for the preparation of CO₂ micro-nanobubble water, are 2.87%, 28.47 min, and 25.52 °C, respectively. The CO₂ content in the MNB water prepared under the optimum parameters is 7.64 mg/L, and the pH is 4.08. Furthermore, the particle size of the bubbles is mostly 255.5 nm. With the extension of the storage time, some of the bubbles polymerize and spill out, but there is still a certain amount of nanoscale bubbles during a certain period. This research provides a new idea for using MNB technology to increase the content and lifespan of CO₂ in water, which will slow the release and increase the utilization of CO₂ when using CO₂ enrichment in agriculture.

KSII Transactions on Internet and Information Systems TIIS Paper Details

A nonparametric variable step-size subband adaptive filtering algorithm for acoustic echo cancellation

Imbalanced data classification is the task of classifying datasets where there is a significant disparity in the number of samples between different classes. This task is prevalent in practical scenarios such as industrial fault diagnosis, network intrusion detection, cancer detection, etc. In imbalanced classification tasks, the focus is typically on achieving high recognition accuracy for the minority class. However, due to the challenges presented by imbalanced multi-class datasets, such as the scarcity of samples in minority classes and complex inter-class relationships with overlapping boundaries, existing methods often do not perform well in multi-class imbalanced data classification tasks, particularly in terms of recognizing minority classes with high accuracy. Therefore, this paper proposes a multi-class imbalanced data classification method called CSDSResNet, which is based on a cost-sensitive dual-stream residual network. Firstly, to address the issue of limited samples in the minority class within imbalanced datasets, a dual-stream residual network backbone structure is designed to enhance the model’s feature extraction capability. Next, considering the complexities arising from imbalanced inter-class sample quantities and imbalanced inter-class overlapping boundaries in multi-class imbalanced datasets, a unique cost-sensitive loss function is devised. This loss function places more emphasis on the minority class and the challenging classes with high inter-class similarity, thereby improving the model’s classification ability. Finally, the effectiveness and generalization of the proposed method, CSDSResNet, are evaluated on two datasets: ‘DryBeans’ and ‘Electric Motor Defects’. The experimental results demonstrate that CSDSResNet achieves the best performance on imbalanced datasets, with macro_F1-score values improving by 2.9% and 1.9% on the two datasets compared to current state-of-the-art classification methods, respectively. Furthermore, it achieves the highest precision in single-class recognition tasks for the minority class.

The measurement of pig backfat thickness (PBFT) has to stand up to challenges with the reliability, accuracy, and convenience. Acquiring PBFT timely and precisely from a finite distance is extremely necessary to improve the process of pig production and implement effective management. In an attempt to alleviate these problems, an online handheld terminal was designed with a new method based on ultrasonic technology for measuring PBFT during the process of pig breeding, which can overcome the difficulties encountered in other destructive means. The terminal comprised three main components: a main microcontroller unit (MCU) to measure PBFT, a RFID module to identify each pig and send data (e.g. identity, measurement time and PBFT) to a server via wireless transmission module, and an ultrasonic transducer to drive and receive signals between them. A measurement error within 0-1 mm was acquired through testing three groups of samples. Results indicated that this handheld terminal had a required accuracy and proved that the ultrasonic wave processing method can be deployed in a mobile terminal for PBFT measurement. It also provided a feasible nondestructive alternative to measure PBFT. Associated with information management software platform, this method may ultimately help pig production farmers measure the PBFT accurately and conveniently, and improve the pig production efficiency. Keywords: pig backfat thickness, nondestructive measurement, ultrasonic technology, online terminal, pig production DOI: 10.25165/j.ijabe.20181102.3278 Citation: Zhang G H, Gao W L, Tao S, Yu L N, Zhang G F, Luo X. Online ultrasonic terminal for measuring pig backfat thickness. Int J Agric & Biol Eng, 2018; 11(2): 190–195.