Search

Effectively improving the optimization performance of artificial electric field algorithm (AEFA) and broadening its application domain can aid in providing robot path planning in 3-D complex scenes. This article effectively proposes an improved AEFA (I-AEFA) and creatively applies it to robot path planning. The algorithm introduces three mechanisms to enhance the exploration ability and convergence accuracy of the population: parameter adaptation, reverse learning, and Cauchy mutation. Next, the benchmark terrain model accurately models the 3-D environment, and the global path planning problem is solved using a combination of I-AEFA and cubic spline interpolation. Then, a large number of virtual simulation experiments are conducted to evaluate the algorithm's three improved mechanisms, various control point counts, as well as single and multirobot configurations before migrating the algorithm to the graphical modeling and analysis software for hardware-in-the-loop simulation experiments. Finally, the experimental results are analyzed qualitatively and quantitatively using a variety of visualization techniques and two nonparametric test methods, demonstrating that the I-AEFA proposed in this article has good optimization performance and is highly effective, reliable, and scalable for solving robot path planning problems.

Compared with a single robot, a multirobot system exhibits better performance when dealing with different complex tasks. Recently, the application of multirobot systems to hunt targets has become a research hotspot, but it also faces many challenges such as excessive system communication, poor collaboration performance, and limited practical testing. Based on previous research on gene regulatory networks (GRNs), this study innovatively proposes an adaptive cooperative GRN (AC-GRN) optimized by an elastic deformation algorithm for multirobot hunting. It uses the protein concentration diffusion mechanism to integrate various situational information of the task environment; during the generation and construction of the hunting pattern, it can adaptively measure the weight of information from different sources in the environment to complete the hunting task more efficiently, accurately, and robustly. Finally, we conduct four sets of simulation experiments to validate the feasibility, efficiency, and stability of the proposed AC-GRN model. Simultaneously, the Kilobot robots are used for practical testing, which further proves the advantages and practicality of the model.

• MHPD is proposed to evaluate the spreading influence of nodes on hypergraphs. • The most influential nodes are selected by the MHPD-greedy and MHPD-heuristic. • The time cost and performance of the proposed methods are theoretically analyzed. • The proposed methods significantly outperform baselines on accuracy and efficiency. • Visualization and statistics are utilized to verify the effectiveness of the methods. Influence maximization problem (IM) has been extensively applied in fields such as viral marketing, rumor control, and infectious disease prevention. However, research on the IM problem has primarily focused on ordinary networks, with limited attention devoted to hypergraphs. Firstly, we propose an efficient evaluation method, i.e., the multiple-hop probability dissemination method (MHPD), aiming to accurately and rapidly evaluate the propagation capacity of selected nodes. The MHPD method is a universal approach that is applicable to various network types, including hypergraphs, and it accommodates multiple probabilistic spreading models. Then, based on MHPD, we propose two novel algorithms for solving IM problem, i.e., MHPD-greedy and MHPD-heuristic. MHPD-greedy employs MHPD to evaluate the marginal benefits of nodes and iteratively adds nodes with the maximum marginal benefit to the seed set. MHPD-heuristic utilizes MHPD to evaluate the propagation capacity of each node and select the top- K nodes as the seeds. Experimental results on eight real-world hypergraphs and eight synthetic hypergraphs demonstrate that MHPD is capable of achieving near-identical accuracy in evaluating the propagation capability of both individual nodes and seed sets, while only incurring an average time overhead of merely 0.25 % compared to Monte Carlo method. In comparison with seven cutting-edge algorithms, MHPD-heuristic demonstrates superior solution accuracy. Notably, MHPD-greedy maintains 98.81 % of the solution accuracy while requiring only 0.11 % of the time cost compared to the Greedy method. Furthermore, MHPD-greedy achieves an average performance improvement of 23.4 % over the best baseline algorithm. [ABSTRACT FROM AUTHOR]

Automatic movement analysis utilizing surveillance video is believed to be an important and convenient way for timely delirium detection in an Intensive Care Unit (ICU). However, video-based delirium movement detection (DMD) faces inherent challenges: 1) Irregular movements with large differences in the four limbs of a patient; 2) similar movements in delirium and normal situations, and large movement variations between patients experiencing delirium. To address the challenges 1, this paper proposes a Long-Short-View Aware Multi-Agent Reinforcement Learning (LS-MARL) method to identify the most representative movement snippet for DMD, considering that the global state provided by the long-view is important for guiding the agent's decision-making, but ignored in existing MARL methods. The proposed LS-MARL has two novel designs. First, a novel Teacher Auxiliary Policy (TAP) is developed for direction preperception of the representative movement snippet. Second, a new reward mechanism, Team Intrinsic Reward (TIR), is introduced to quantify the contribution of each agent. Experiments demonstrate that the proposed LS-MARL method outperforms state-of-the-art methods. Furthermore, to handle the second challenge, a new Self-Adjusting Ensemble Learning (SAEL) strategy is built to adaptively integrate an optimal classifier combination from multidomain features, which further improves the performance of classification tasks in the proposed LS-MARL method. • A novel Multi-Agent Reinforcement Learning framework, LS-MARL, is proposed to identify the representative movement snippet. • A TAP network guides agent's decisions by pre-perceiving the direction of the representative snippet. • A TIR mechanism is designed for the proposed LS-MARL to quantify the team and individual contributions among multi-agents. • A new EL strategy, SAEL, is presented to set up an adequate tradeoff between classifier diversity and performance. [ABSTRACT FROM AUTHOR]

Swarm intelligence algorithms are a subset of the artificial intelligence (AI) field, which is increasing popularity in resolving different optimization problems and has been widely utilized in various applications. In the past decades, numerous swarm intelligence algorithms have been developed, including ant colony optimization (ACO), particle swarm optimization (PSO), artificial fish swarm (AFS), bacterial foraging optimization (BFO), and artificial bee colony (ABC). This review tries to review the most representative swarm intelligence algorithms in chronological order by highlighting the functions and strengths from 127 research literatures. It provides an overview of the various swarm intelligence algorithms and their advanced developments, and briefly provides the description of their successful applications in optimization problems of engineering fields. Finally, opinions and perspectives on the trends and prospects in this relatively new research domain are represented to support future developments.

Aluminum-doped zinc oxide (AZO) thin films were prepared by magnetron sputtering method. The influences of deposition pressure, substrate temperature, Ar flow rate and film thickness on optical and electrical properties were investigated using ultraviolet-visible (UV-Vis) spectrometer and Hall measurements. The experimental results revealed that a low resistivity, smaller than 4 × 10-4Ω·cm, was obtained when the deposition pressure was smaller than 0.67 Pa and substrate temperature about 200 °C. Ar flow rate had a small influence on the resistivity but a big influence on the transparency at near infrared range (NIR). We obtained optimized AZO thin films with high ponductivity and transparency at low deposition pressure, small Ar flow and appropriate temperature (around 200 °C). The etching behavior of the AZO thin films deposited at the different Ar flow rates was also studied in this paper. The results show that Ar flow rate is a very important factor affecting the etching behavior.

Crystallization of glass/Aluminum (50, 100, 200 nm) /hydrogenated amorphous silicon (a-Si:H) (50, 100, 200 nm) samples by Aluminum-induced crystallization (AIC) is investigated in this article. After annealing and wet etching, we found that the continuity of the polycrystalline silicon (poly-Si) thin films was strongly dependent on the double layer thicknesses. Increasing the a-Si:H/Al layer thickness ratio would improve the film microcosmic continuity. However, too thick Si layer might cause convex or peeling off during annealing. Scanning electron microscopy (SEM) and Energy Dispersive X-ray spectroscopy (EDX) are introduced to analyze the process of the peeling off. When the thickness ratio of a-Si:H/Al layer is around 1 to 1.5 and a-Si:H layer is less than 200 nm, the poly-Si film has a good continuity. Hall measurements are introduced to determine the electrical properties. Raman spectroscopy and X-ray diffraction (XRD) results show that the poly-Si film is completely crystallized and has a preferential (111) orientation.

ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 200 leading journals. To access a ChemInform Abstract of an article which was published elsewhere, please select a “Full Text” option. The original article is trackable via the “References” option.