Dynamic decomposition graph convolutional neural network for SSVEP-based brain-computer interface.

The SSVEP-based paradigm serves as a prevalent approach in the realm of brain-computer interface (BCI). However, the processing of multi-channel electroencephalogram (EEG) data introduces challenges due to its non-Euclidean characteristic, necessitating methodologies that account for inter-channel topological relations. In this paper, we introduce the Dynamic Decomposition Graph Convolutional Neural Network (DDGCNN) designed for the classification of SSVEP EEG signals. Our approach incorporates layerwise dynamic graphs to address the oversmoothing issue in Graph Convolutional Networks (GCNs), employing a dense connection mechanism to mitigate the gradient vanishing problem. Furthermore, we enhance the traditional linear transformation inherent in GCNs with graph dynamic fusion, thereby elevating feature extraction and adaptive aggregation capabilities. Our experimental results demonstrate the effectiveness of proposed approach in learning and extracting features from EEG topological structure. The results shown that DDGCNN outperforms other state-of-the-art (SOTA) algorithms reported on two datasets (Dataset 1: 54 subjects, 4 targets, 2 sessions; Dataset 2: 35 subjects, 40 targets). Additionally, we showcase the implementation of DDGCNN in the context of synchronized BCI robotic fish control. This work represents a significant advancement in the field of EEG signal processing for SSVEP-based BCIs. Our proposed method processes SSVEP time domain signals directly as an end-to-end system, making it easy to deploy. The code is available at https://github.com/zshubin/DDGCNN.

A Circular Formation Method for Biomimetic Robotic Fish Inspired by Fish Milling.

Circular motion phenomena, akin to fish milling, are prevalent within the animal kingdom. This paper delineates two fundamental mechanisms underlying such occurrences: forward following and circular topological communication. Leveraging these pivotal concepts, we present a multi-agent formation circular model based on a second-order integrator. This model engenders the attainment of homogeneous intelligence convergence along the circumferential trajectory. The convergence characteristics are intricately linked to the number of agents and the model parameters. Consequently, we propose positive and negative solutions for ascertaining the convergent circle property and model parameters. Furthermore, by integrating our proposed formation control methodology with a robotic fish dynamics model, we have successfully implemented simulations and experiments, demonstrating the circular formation of multiple biomimetic robotic fish. This study provides a mathematical explication for the circular motion observed in animal groups and introduces a novel approach to achieving circular formation in multiple robots inspired by biological phenomena.

Alterations in the "Gut-Liver Axis" on Rats with Immunological Hepatic Fibrosis.

There remains a lack of standard models that have all the characteristics of human diseases. Especially in immunological hepatic fibrosis, the bovine serum albumin (BSA)-induced liver fibrosis models have the same developmental mechanisms as human liver fibrosis models, but have received little attention. We standardized a BSA-induced liver fibrosis model in rats and thoroughly assessed its pathological characteristics. We also used 16S sequencing to assess homeostasis of the intestinal microflora of rats with BSA-induced liver fibrosis and detected various differential metabolites in the serum of these rats using ultrahigh-performance liquid chromatography-tandem mass spectrometry (UHPLC-MS/MS). We observed stable and unambiguous histological changes in liver tissue morphology and remarkably high concentrations of inflammatory markers in the serum of BSA-induced liver fibrosis rats. In keeping with the fact that BSA induction can cause gut microbiota disorders in rats. UHPLC-MS/MS analysis of rat serum samples in positive-ion mode and negative-ion mode revealed 17 and 25 differential metabolites, respectively. Network analysis revealed that phenylalanine or tyrosine metabolites (e.g., PAGln) were the predominant metabolites in the sera of BSA-induced liver fibrosis rats. Taken together, our results suggest that disorders of amino acid metabolism caused by the gut microbiota may play an important role in the progression of immunological hepatic fibrosis.

Design and Realization of a Novel Robotic Manta Ray for Sea Cucumber Recognition, Location, and Approach.

Sea cucumber manual monitoring and fishing present various issues, including high expense and high risk. Meanwhile, compared to underwater bionic robots, employing autonomous underwater robots for sea cucumber monitoring and capture also has drawbacks, including low propulsion efficiency and significant noise. Therefore, this paper is concerned with the design of a robotic manta ray for sea cucumber recognition, localization, and approach. First, the developed robotic manta ray prototype and the system framework applied to real-time target search are elaborated. Second, by improved YOLOv5 object detection and binocular stereo-matching algorithms, precise recognition and localization of sea cucumbers are achieved. Thirdly, the motion controller is proposed for autonomous 3D monitoring tasks such as depth control, direction control, and target approach motion. Finally, the capabilities of the robot are validated through a series of measurements. Experimental results demonstrate that the improved YOLOv5 object detection algorithm achieves detection accuracies (mAP@0.5) of 88.4% and 94.5% on the URPC public dataset and self-collected dataset, respectively, effectively recognizing and localizing sea cucumbers. Control experiments were conducted, validating the effectiveness of the robotic manta ray's motion toward sea cucumbers. These results highlight the robot's capabilities in visual perception, target localization, and approach and lay the foundation to explore a novel solution for intelligent monitoring and harvesting in the aquaculture industry.

Proactivity of fish and leadership of self-propelled robotic fish during interaction.

Fish interacting with biomimetic robotic fish is beneficial for animal behavior research, particularly in the study of collective behavior. Compared with passive-dragging robotic fish, self-propelled robotic fish floats in water, and its movement matches the flow field formed by the caudal fin oscillation, leading to more realistic interaction with animals. In this paper, we propose a self-propelled koi-mimicking robotic fish entity, develop a system for robotic fish and koi fish interaction, and conduct extensive experiments on quantity variation and parameter variation. The results showed that fish exhibited significantly lower proactivity when alone, and the most proactive case is one robotic fish interacting with two real fish. The experiments on parameter variation indicated that fish may respond more proactivity to robotic fish that swim with high frequency and low amplitude, but may also move together with high-frequency and high-amplitude swimming robotic fish. These findings could provide insights into fish collective behavior, guide the design of further fish-robot interaction experiments, and suggest directions for future improvements in goal-oriented robotic fish platforms.

Advances in infrared spectroscopy and hyperspectral imaging combined with artificial intelligence for the detection of cereals quality.

Cereals provide humans with essential nutrients, and its quality assessment has attracted widespread attention. Infrared (IR) spectroscopy (IRS) and hyperspectral imaging (HSI), as powerful nondestructive testing technologies, are widely used in the quality monitoring of food and agricultural products. Artificial intelligence (AI) plays a crucial role in data mining, especially in recent years, a new generation of AI represented by deep learning (DL) has made breakthroughs in analyzing spectral data of food and agricultural products. The combination of IRS/HSI and AI further promotes the development of quality evaluation of cereals. This paper comprehensively reviews the advances of IRS and HSI combined with AI in the detection of cereals quality. The aim is to present a complete review topic as it touches the background knowledge, instrumentation, spectral data processing (including preprocessing, feature extraction and modeling), spectral interpretation, etc. To suit this goal, principles of IRS and HSI, as well as basic concepts related to AI are first introduced, followed by a critical evaluation of representative reports integrating IRS and HSI with AI. Finally, the advantages, challenges and future trends of IRS and HSI combined with AI are further discussed, so as to provide constructive suggestions and guidance for researchers.

A fellow-following-principle based group model and its application to fish school analysis.

Group models based on simple rules are viewed as a bridge to clarifying animal group movements. The more similar a model to real-world observations, the closer it is to the essence of such movements. Inspired by the fish school, this study suggests a principle called fellow-following for group movements. More specifically, a simple-rules-based model was proposed and extended into a set of concrete rules, and two- and three-dimensional group models were established. The model results are intuitively similar to the fish school, and when the group size increases, the milling phase of both the model and fish school tends from unstable to stable. Further, we proposed a novel order parameter and a similarity measurement framework for group structures. The proposed model indicates the intuition similarity, consistency of dynamic characteristics, and static structure similarity with fish schools, which suggests that the principle of fellow-following may reveal the essence of fish school movements. Our work suggests a different approach for the self-organized formation of a swarm robotic system based on local information.

Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network.

An attention (A) based convolutional neural network regression (CNNR) model, namely ACNNR, was proposed to combine hyperspectral imaging to predict oil content in single maize kernel. During the period, a reflectance HSI system was used to collect hyperspectral images of embryo side and non-embryo side of single maize kernel, and the performances of CNNR (without attention mechanism), ACNNR and partial least squares regression (PLSR) were compared. For PLSR, a series of spectral preprocessing and dimensionality reduction methods were used to finally determine the optimal hybrid PLSR model. Whereas for CNNR and ACNNR, only raw spectra were used as their inputs. The results showed that embryo side was more suitable for developing regression models; the attentional mechanism was helpful to reduce the error of prediction, making ACNNR performed best (coefficient of determination of prediction = 0.9198). Overall, the proposed method did not require additional processing on raw spectra, and performed well.

Oxidative Coupling of Methane: Examining the Inactivity of the MnOx -Na2 WO4 /SiO2 Catalyst at Low Temperature.

Oxidative coupling of methane (OCM) catalyzed by MnOx -Na2 WO4 /SiO2 has great industrial promise to convert methane directly to C2-3 products, but its high light-off temperature is the most challenging obstacle to commercialization and its working mechanism is still a mystery. We report the discovery of a low-temperature active and selective MnOx -Na2 WO4 /SiO2 catalyst enriched with Q2 units in the SiO2 carrier, being capable of converting 23 % CH4 with 72 % C2-3 selectivity at 660 °C. From experiments and theoretical calculations, a large number of Q2 units in the MnOx -Na2 WO4 /SiO2 catalyst is a trigger for markedly lowering the light-off temperature of the Mn3+ ↔Mn2+ redox cycle involved in the OCM reaction because of the easy formation of MnSiO3 . Notably, the MnSiO3 formation proceeds merely through the SiO2 -involved reaction in the presence of Na2 WO4 : Mn7 SiO12 +6 SiO2 ↔7 MnSiO3 +1.5 O2 . The Na2 WO4 not only drives the light-off of this cycle but also gets it working with substantial selectivity toward C2-3 products. Our findings shine a light on the rational design of more advanced MnOx -Na2 WO4 based OCM catalysts through establishing new Mn3+ ↔Mn2+ redox cycles with lowered light-off temperature.

Design and analysis of a novel tendon-driven continuum robotic dolphin.

In this paper, a novel continuum robotic dolphin termed 'ConRoDolI' is proposed and developed. The biomimetic robot features dual tendon driving continuum mechanisms that are utilized to replicate the twisting and bending motions of the dolphin's caudal vertebrae and thoracic vertebrae. More importantly, a central pattern generator based kinematics is analyzed to yield stable dolphin-like swimming. In the meantime, the relationship between the backbone shape and both the tendon length as well as position and orientation are explored. Furthermore, multimodal swimming gaits are designed to pave the way for a three-dimensional (3D) swimming decoupling solution, involving forwarding swimming, multiple yaw patterns, and multiple pitch patterns. All of these endow the robotic dolphin with 3D maneuverability. Finally, extensive experiments demonstrate the feasibility of the proposed biomimetic mechatronic design and control approach. The forward swimming speed is 0.44 body lengths per second (BL/s). The steering radius of the robot is about 0.11 BL with an angular velocity of 10°/s and the diving speed is about 0.13 BL/s. The average propulsion efficiency is about 0.6 with the maximum is over 0.8. The obtained results shed light on the improvement of aquatic maneuverability associated with new-concept underwater vehicles.

A Novel Visual Sensor Stabilization Platform for Robotic Sharks Based on Improved LADRC and Digital Image Algorithm.

Autonomous underwater missions require the construction of a stable visual sensing system. However, acquiring continuous steady image sequences is a very challenging task for bionic robotic fish due to their tight internal space and the inherent periodic disturbance caused by the tail beating. To solve this problem, this paper proposes a modified stabilization strategy that combines mechanical devices and digital image techniques to enhance the visual sensor stability and resist periodic disturbance. More specifically, an improved window function-based linear active disturbance rejection control (LADRC) was utilized for mechanical stabilization. Furthermore, a rapid algorithm with inertial measurement units (IMUs) was implemented for digital stabilization. The experiments regarding mechanical stabilization, digital stabilization, and target recognition on the experimental platform for simulating fishlike oscillations demonstrated the effectiveness of the proposed methods. The success of these experiments provides valuable insight into the construction of underwater visual sensing systems and also establishes a solid foundation for the visual applications for robotic fish in dynamic aquatic environments.