Mobile Edge Computing (MEC) has been widely employed to support various Internet of Things (IoT) and mobile applications. By leveraging the advantages of easily deployed and flexibility of Unmanned Aerial Vehicle (UAV), one of MEC primary functions is employing UAVs equipped with MEC servers to provide computation supports for the offloaded tasks by mobile users in temporally hotspot areas or some emergent scenarios, such as sports game areas or destroyed by natural disaster areas. Despite the numerous advantages of UAV carried with a MEC server, it is restricted by its limited computation resources and sensitive energy consumption. Moreover, due to the complexity of UAV-assisted MEC system, its computational resource optimization and energy consumption optimization can not be achieved well in traditional optimization methods. Furthermore, the computational cost of the MEC system optimization is often exponentially growing with the increase of the MEC servers and mobile users. Therefore, it is considerably challenging to control the UAV positions and schedule the task offloading ratio. In this paper, we proposed a novel Deep Reinforcement Learning (DRL) method to optimize UAV trajectory controlling and users’ offloaded task ratio scheduling and improve the performance of the UAV-assisted MEC system. We maximized the system stability and minimized the energy consumption and computation latency of UAV-assisted the MEC system. The simulation results show that the proposed method outperforms existing work and has better scalability.

In this paper, the design of a mid-infrared four-band ultra-narrowband wave-absorbing sensor based on the localized equi-excited exciton resonance of graphene metamaterials is presented. The designed super-surface unit has a geometrically symmetric structure and is insensitive to incident light sources with different polarization directions. The absorbing sensor has four resonant wavelengths located at λ₁ = 3.172 μm, λ₂ = 3.525 μm, λ₃ = 3.906 μm, and λ₄ = 4.588 μm, with absorption efficiencies of 99.94%, 99.46%, 99.55%, and 98.16%, respectively. In addition, the dynamic tuning of the resonant wavelength and absorption efficiency can be realized by changing the gate voltage or through chemical doping of graphene. Moreover, the wave-absorbing performance can maintain stable absorption over a wide range of incidence angles from 0 to 50°. Finally, the wave-absorbing sensor was subjected to different ambient refractive indices, and the refractive index sensitivities corresponding to the four resonant wavelengths were obtained as 587.5 nm/RIU, 700.0 nm/RIU, 850.0 nm/RIU, and 900.0 nm/RIU, with FOM values of 48.96 RIU⁻¹, 58.34 RIU⁻¹, 53.13 RIU⁻¹, and 28.13 RIU⁻¹, respectively, all of which have superior sensing characteristics. Therefore, this paper enriches the variety of mid-infrared absorber sensors and has a broad application prospect in the fields of wave absorption, sensing, and detection.

Fuzzy neural networks have shown considerable promise in tackling problems characterized by uncertainty and complexity, especially in data-driven domains. In medical image segmentation, inherent uncertainties in raw images and manual annotations often hinder performance. To address these challenges, we propose a novel fuzzy neural network architecture that integrates convolutional structures with fuzzy logic. The convolutional layers extract multi-scale, pixel-level discriminative features, while the fuzzy logic component explicitly handles uncertainties to improve segmentation reliability. We evaluate the proposed model on retinal vessel segmentation tasks using the publicly available DRIVE and STARE datasets, where it achieved mean accuracy, sensitivity and specificity of 97.10%, 81.50%, 98.36% and 97.40%, 82.15%, 98.36% for segmenting the retinal vessel. Experimental results demonstrate the superior performance and effectiveness of the proposed fuzzy convolutional neural network model in automated retinal segmentation.