Simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) have been considered promising auxiliary devices to enhance the performance of the wireless network, where users located at different sides of the surfaces can be simultaneously served by the transmitting or reflecting signals. In this article, an energy efficiency (EE) optimization problem for non-orthogonal multiple access (NOMA) assisted STAR-RIS downlink network is investigated. Due to the fractional form of the objective function, it is challenging to solve the EE optimization problem using traditional convex optimization solutions. This article proposes a deep deterministic policy gradient (DDPG)-based algorithm to maximize the EE by jointly optimizing the transmission beamforming vectors at the base station and the coefficients matrices at the STAR-RIS. Simulation results demonstrate that the proposed algorithm can effectively maximize the system EE considering the time-varying channels.

We analyze the benefits of simultaneous transmitting and reflecting intelligent reflecting surfaces (STAR-IRSs) for short-packet communications (SPC) with non-orthogonal multiple access (NOMA) and statistical channel state information towards ultra-reliable and low-latency communications. Considering Rician fading and energy splitting protocol, we analyze the performance of STAR-IRS aided NOMA SPC systems with continuous and discrete phase shifts. We first derive new closed-form expressions for the average block error rate (BLER) and diversity order in the finite signal-to-noise ratio (SNR) regime. We then determine the relationship among the average BLER, power allocation, blocklength, and transmission and reflection coefficients. Finally, Monte Carlo simulations are used to verify our theoretical analysis and examine the optimal transmission and reflection coefficients that minimize the common blocklength in the considered system under reliability constraints.

Hyperspectral images are high-dimensional data that capture detailed spectral information across a wide range of wavelengths, enabling the precise identification and analysis of different materials or objects. However, the high dimensionality of the data also introduces information redundancy and increases the computational overhead, making it necessary to perform band selection to retain the most discriminative and informative bands for the target task. Traditional band selection methods, such as ranking-based, searching-based, and clustering-based approaches, often rely on handcrafted features and heuristic rules, which fail to fully exploit the latent information and complex spatial–spectral relationships in hyperspectral images. To address this issue, this paper proposes a two-stage unsupervised band selection method based on deep reinforcement learning. First, we performed noise estimation preprocessing to filter out bands with high noise levels to reduce the interference in the agent’s learning process. Then, the band selection problem was formulated as a Markov Decision Process (MDP), where the agent learned an optimal band selection strategy through interactions with the environment. In the design of the reward function, the Optimal Index Factor (OIF) was introduced as the evaluation metric to encourage the agent to select bands with high information content and low redundancy, and thereby improve the efficiency and quality of the selection process. Experimental results on three hyperspectral datasets demonstrated that the proposed method could effectively improve the performance of the hyperspectral image band selection.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

Most works on reflecting-only intelligent reflecting surface (IRS) are based on the ideal phase shift model (IPSM), which assumes that the reflection amplitude is independent of the phase shift. However, due to hardware limitations, practical IRS generally follows the practical phase shift model (PPSM), where the reflection amplitude is related to the phase shift. This paper analyzes the average block error rate (BLER) of PPSM-based IRS aided short-packet communication (SPC) using statistical channel state information (CSI) over Rician fading. Because the optimal continuous phase shifts at the PPSM-based IRS are difficult to be explicitly solved, we first propose a deep deterministic policy gradient (DDPG) based algorithm to optimize the phase shift design. Then, we derive the average BLER of the considered system. Finally, numerical results verify the effectiveness of the proposed DDPG-based phase shift design. They also show that, different from the IPSM-based IRS, the optimal phase shifts at the PPSM-based IRS are related to the Rician factors.