1 H-NMR revealed pyruvate as a differentially abundant metabolite in the venom glands of Apis cerana and Apis mellifera.

As a common defense mechanism in Hymenoptera, bee venom has complex components. Systematic and comprehensive analysis of bee venom components can aid in early evaluation, accurate diagnosis, and protection of organ function in humans in cases of bee stings. To determine the differences in bee venom composition and metabolic pathways between Apis cerana and Apis mellifera, proton nuclear magnetic resonance (1 H-NMR) technology was used to detect the metabolites in venom samples. A total of 74 metabolites were identified and structurally analyzed in the venom of A. cerana and A. mellifera. Differences in the composition and abundance of major components of bee venom from A. cerana and A. mellifera were mapped to four main metabolic pathways: valine, leucine and isoleucine biosynthesis; glycine, serine and threonine metabolism; alanine, aspartate and glutamate metabolism; and the tricarboxylic acid cycle. These findings indicated that the synthesis and metabolic activities of proteins or polypeptides in bee venom glands were different between A. cerana and A. mellifera. Pyruvate was highly activated in 3 selected metabolic pathways in A. mellifera, being much more dominant in A. mellifera venom than in A. cerana venom. These findings indicated that pyruvate in bee venom glands is involved in various life activities, such as biosynthesis and energy metabolism, by acting as a precursor substance or intermediate product.

Improving bee feed recipes to safeguard honeybee colonies during times of food scarcity.

In beekeeping, when natural nectar or pollen sources become limited, it is crucial to provide supplemental bee feed to maintain the viability of the bee colony. This study was conducted during the autumn food shortage season, during which bees were fed with different proportions of modified bee feed. We identified an optimal bee diet by evaluating honeybee longevity, food consumption, body weight, and gut microbe distribution, with natural pollen serving as a control diet. The results indicated that bees preferred a mixture of 65% defatted soy flour, 20% corn protein powder, 13% wheat germ flour, 2% yeast powder, and a 50% sucrose solution. This bee food recipe significantly increased the longevity, feed consumption, and body weight of bees. The group fed the natural pollen diet exhibited a greater abundance of essential intestinal bacteria. The bee diets used in this study contained higher protein levels and lower concentrations of unsaturated fatty acids and vitamins than did the diets stored within the colonies. Therefore, we propose that incorporating both bee feed and natural pollen in beekeeping practices will achieve more balanced nutritional intake.

Attention-Based Fault-Tolerant Approach for Multi-Agent Reinforcement Learning Systems.

The aim of multi-agent reinforcement learning systems is to provide interacting agents with the ability to collaboratively learn and adapt to the behavior of other agents. Typically, an agent receives its private observations providing a partial view of the true state of the environment. However, in realistic settings, the harsh environment might cause one or more agents to show arbitrarily faulty or malicious behavior, which may suffice to allow the current coordination mechanisms fail. In this paper, we study a practical scenario of multi-agent reinforcement learning systems considering the security issues in the presence of agents with arbitrarily faulty or malicious behavior. The previous state-of-the-art work that coped with extremely noisy environments was designed on the basis that the noise intensity in the environment was known in advance. However, when the noise intensity changes, the existing method has to adjust the configuration of the model to learn in new environments, which limits the practical applications. To overcome these difficulties, we present an Attention-based Fault-Tolerant (FT-Attn) model, which can select not only correct, but also relevant information for each agent at every time step in noisy environments. The multihead attention mechanism enables the agents to learn effective communication policies through experience concurrent with the action policies. Empirical results showed that FT-Attn beats previous state-of-the-art methods in some extremely noisy environments in both cooperative and competitive scenarios, much closer to the upper-bound performance. Furthermore, FT-Attn maintains a more general fault tolerance ability and does not rely on the prior knowledge about the noise intensity of the environment.

Sensor Fusion-Based Cooperative Trail Following for Autonomous Multi-Robot System.

Autonomously following a man-made trail in the wild is a challenging problem for robotic systems. Recently, deep learning-based approaches have cast the trail following problem as an image classification task and have achieved great success in the vision-based trail-following problem. However, the existing research only focuses on the trail-following task with a single-robot system. In contrast, many robotic tasks in reality, such as search and rescue, are conducted by a group of robots. While these robots are grouped to move in the wild, they can cooperate to lead to a more robust performance and perform the trail-following task in a better manner. Concretely, each robot can periodically exchange the vision data with other robots and make decisions based both on its local view and the information from others. This paper proposes a sensor fusion-based cooperative trail-following method, which enables a group of robots to implement the trail-following task by fusing the sensor data of each robot. Our method allows each robot to face the same direction from different altitudes to fuse the vision data feature on the collective level and then take action respectively. Besides, considering the quality of service requirement of the robotic software, our method limits the condition to implementing the sensor data fusion process by using the "threshold" mechanism. Qualitative and quantitative experiments on the real-world dataset have shown that our method can significantly promote the recognition accuracy and lead to a more robust performance compared with the single-robot system.

Learning to Cooperate via an Attention-Based Communication Neural Network in Decentralized Multi-Robot Exploration.

In a decentralized multi-robot exploration problem, the robots have to cooperate effectively to map a strange environment as soon as possible without a centralized controller. In the past few decades, a set of "human-designed" cooperation strategies have been proposed to address this problem, such as the well-known frontier-based approach. However, many real-world settings, especially the ones that are constantly changing, are too complex for humans to design efficient and decentralized strategies. This paper presents a novel approach, the Attention-based Communication neural network (CommAttn), to "learn" the cooperation strategies automatically in the decentralized multi-robot exploration problem. The communication neural network enables the robots to learn the cooperation strategies with explicit communication. Moreover, the attention mechanism we introduced additionally can precisely calculate whether the communication is necessary for each pair of agents by considering the relevance of each received message, which enables the robots to communicate only with the necessary partners. The empirical results on a simulated multi-robot disaster exploration scenario demonstrate that our proposal outperforms the traditional "human-designed" methods, as well as other competing "learning-based" methods in the exploration task.

A Study on the Dynamic Tunning Range of CVD Graphene at Microwave Frequency: Determination, Prediction and Application.

In recent years, graphene has shown great application prospects in tunable microwave devices due to its tunable conductivity. However, the electromagnetic (EM) properties of graphene, especially the dynamic tunning characteristics, are largely dependent on experimental results, and thus are unable to be effectively predicted according to growth parameters, which causes great difficulties in the design of graphene-based tunable microwave devices. In this work, we systematically explored the impact of chemical vapor deposition (CVD) parameters on the dynamic tunning range of graphene. Firstly, through improving the existing waveguide method, the dynamic tunning range of graphene can be measured more accurately. Secondly, a direct mathematical model between growth parameters and the tunning range of graphene is established. Through this, one can easily obtain needed growth parameters for the desired tunning range of graphene. As a verification, a frequency tunable absorber prototype is designed and tested. The good agreement between simulation and experimental results shows the reliability of our mathematic model in the rapid design of graphene-based tunable microwave devices.