Indiscernible marine object counting refers to the counting of marine objects that are visually blended with their surrounding environment. This task encounters critical challenges, including limited visibility in underwater scenes, mutual occlusion and overlap among objects, and the dynamic similarity in appearance, color, and texture between the background and foreground. To address the scarcity of video-based indiscernible object counting datasets, we have established a new dataset comprising 50 videos, from which approximately 800 frames have been extracted and annotated with around 40, 800 point-wise object labels. This dataset represents real underwater environments where indiscernible marine objects are intricately integrated with their surroundings, thereby comprehensively illustrating the aforementioned challenges in marine object counting. To address these challenges, we propose a depth-assisted network with adaptive motion-differentiated feature encoding. The network consists of a backbone encoding module and three branches: a depth-assisting branch, a density estimation branch, and a motion weight generation branch. Depth-aware features extracted by the depth-assisting branch are enhanced via a depth-enhanced encoder to improve object representation. Meanwhile, weights from the motion weight generation branch refine multi-scale perception features in the adaptive flow estimation module. Experiments demonstrate that our method not only achieves state-of-the-art performance on the proposed dataset but also yields competitive results on three video-based crowd counting datasets. The pre-trained model, code, and dataset are publicly available at https://github.com/OUCVisionGroup/VIMOC-Net.

Reconfigurable distributed antenna and reflecting surface (RDARS) has been recently proposed as a promising technology. This architecture enables each element to perform flexibly either in the reflection mode, like the traditional passive reconfigurable intelligent surface (RIS), or in the connection mode, akin to the distributed antenna system (DAS). This dual capability allows RDARS to harness both reflection gain and distribution gain. In this paper, we investigate a dynamic RDARS-aided multiple-input multiple-output communication system, where the optimal configuration of the elements operating in connection mode can provide additional selection gain. Considering the theoretical and practical significances, we address the achievable rate maximization problem by jointly optimizing the mode selection, transmit power allocation and passive beamforming under both perfect and imperfect channel state information (CSI) cases. Due to the involvement of the mode selection design of RDARS, the problem is more challenging than those of the traditional RIS-aided systems with fixed reflection operation. For perfect CSI case, by investigating the inherent properties of the objective function, we propose a greedy-based alternating optimization (AO) algorithm with low-complexity and then extend the proposed algorithm to the general multi-user multi-RDARS scenario. Additionally, we find interesting insights about the mode selection of RDARS in a special scenario with a single-antenna user. The result shows that the RDARS elements leading to the largest distribution gain should be selected to operate in connection mode for the rate maximization. For imperfect CSI case, we develop an efficient alternative direction method of multipliers-based AO algorithm. Numerical results show that RDARS-assisted system outperforms the passive-RIS assisted system and DAS under both perfect and imperfect CSI scenarios with promising reflection, distribution and selection gains.

Reconfigurable distributed antennas and reflecting surface (RDARS) has been recently proposed as a promising technology. This architecture enables each element to operate either in the reflection mode, like the conventional passive reconfigurable intelligent surface (RIS), or in the connection mode, akin to the distributed antenna system (DAS). This dual capability allows RDARS to harness both reflection gain and distribution gain. In this paper, to further unleash the potential of the RDARSaided multiple-input multiple-output (MIMO) communication system in terms of additional selection gain, we formulate an achievable rate maximization problem by jointly designing the mode selection matrix, the power allocation matrix and the reflection coefficient matrix. Due to the mode selection design of RDARS, this problem is more challenging than those of the conventional RIS-aided systems with fixed elements locations. To tackle it, by investigating the beneficial properties of the objective function, we propose a greedy-based alternating optimization (AO) algorithm with low-complexity. Numerical results clearly illustrate the reflection gain, distribution gain and selection gain of RDARS and show that RDARS-assisted system can achieve superior performance than the passive-RIS assisted system and DAS.

Distributed Antenna Systems (DASs) employ multiple antenna arrays in remote radio units to achieve highly directional transmission and provide great coverage performance for future-generation networks. However, the utilization of fully digital or hybrid active antenna arrays results in a significant increase in hardware costs and power consumption for DAS. To address these issues, integrating DAS with Reconfigurable Intelligent Surfaces (RIS) offers a viable approach to ensure coverage and transmission performance while maintaining low hardware costs and power consumption. To incorporate the merits of RIS into the DAS from practical consideration, a novel architecture of “Reconfigurable Distributed Antennas and Reflecting Surfaces (RDARS)” is proposed in this paper. Specifically, based on the design of the additional direct-through state together with the existing high-quality fronthaul link, any element of the RDARS can be dynamically programmed to connect with the base station (BS) via fibers and perform theconnected modeas remote distributed antennas of the BS to receive or transmit signals. Additionally, RDARS also inherits the low-cost and low-energy-consumption benefits of fully passive RISs by default configuring the elements as passive to perform thereflection mode. As a result, RDARS encompasses both DAS and RIS as special cases, offering flexible control over the trade-off betweendistribution gainandreflection gainto enhance performance. To unveil the potential of such architecture, the ergodic achievable rate under the RDARS architecture is analyzed and closed-form expression with meaningful insights is derived. The theoretical analysis proves that the RDARS can achieve a higher achievable rate than both DAS and fully passive RIS with the passive beamforming gain provided by elements actingreflection modewhile combating the “multiplicative fading” suffered by RISs through theconnected modeperformed at the RDARS. Simulation results also demonstrate the superiority of the RDARS architecture over DAS and passive RIS-aided systems and its flexible trade-off between performance and cost. To further validate the feasibility and effectiveness, an RDARS prototype with 256 elements is built for real experiments. Experimental results show that the RDARS-aided system with only one element operating inconnected modecan achieve an additional 21% and 170% throughput improvement over DAS and RIS-aided systems, respectively.

In this paper, we investigate a novel reconfigurable distributed antennas and reflecting surface (RDARS) aided multi-user massive multiple-input multiple-output (MIMO) system with imperfect channel state information (CSI) and propose a practical two-timescale (TTS) transceiver design to reduce the communication overhead and computational complexity of the system. In the RDARS-aided system, not only distribution gain but also reflection gain can be obtained by a flexible combination of the distributed antennas and reflecting surface, which differentiates the system from the others and also makes the TTS design challenging. To enable the optimal TTS transceiver design, the achievable rate of the system is first derived in closed-form. The rate expression is general and covers that of the distributed antenna systems (DAS) and reconfigurable intelligent surface (RIS) aided systems as special cases. Then the TTS design aiming at the weighted sum rate maximization is considered. To solve the challenging non-convex optimization problem with high order design variables, i.e., the transmit powers and the phase shifts at the RDARS, a block coordinate descent based method is proposed to find the optimal solutions in semi-closed forms iteratively. Specifically, two efficient algorithms are proposed with provable convergence for the optimal phase shift design, i.e., Riemannian Gradient Ascent based algorithm by exploiting the unit-modulus constraints, and Two-Tier Majorization-Minimization based algorithm with closed-form optimal solutions in each iteration. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the superiority of deploying RDARS in massive MIMO systems to provide substantial rate improvement with a significantly reduced total number of active antennas/RF chains and lower transmit power when compared to the DAS and RIS-aided systems.

Reconfigurable intelligent surface (RIS) has emerged as a cost-effective solution for green communications in 6G. However, its further extensive use has been greatly limited due to its fully passive characteristics. Considering the appealing distribution gains of distributed antenna systems (DAS), a flexible reconfigurable architecture called reconfigurable distributed antenna and reflecting surface (RDARS) is proposed. RDARS encompasses DAS and RIS as two special cases and maintains the advantages of distributed antennas while reducing the hardware cost by replacing some active antennas with low-cost passive reflecting surfaces. In this paper, we present a RDARS-aided uplink multi-user communication system and investigate the system transmission reliability with the newly proposed architecture. Specifically, in addition to the distribution gain and the reflection gain provided by the connection and reflection modes, respectively, we also consider the dynamic mode switching of each element which introduces an additional degree of freedom (DoF) and thus results in a selection gain. As such, we aim to minimize the total sum mean-square-error (MSE) of all data streams by jointly optimizing the receive beamforming matrix, the reflection phase shifts and the channel-aware placement of elements in the connection mode. To tackle this nonconvex problem with intractable binary and cardinality constraints, we propose an inexact block coordinate descent (BCD) based penalty dual decomposition (PDD) algorithm with the guaranteed convergence. Since the PDD algorithm usually suffers from high computational complexity, a low-complexity greedy-search-based alternating optimization (AO) algorithm is developed to yield a semi-closed-form solution with acceptable performance. Numerical results demonstrate the superiority of the proposed architecture compared to the conventional fully passive RIS or DAS. Furthermore, some insights about the practical implementation of RDARS are provided.

High-voltage circuit breakers are widely used in new power systems, and have the function of protecting and controlling transmission lines. With the gradual strengthening of the state perception ability of the new power system, the online monitoring ability of the mechanical fault of the high-voltage circuit breaker has been improved, which provides a relatively complete data basis for the fault diagnosis of the high-voltage circuit breaker. This research presents a method for detecting circuit breaker faults using wavelet vibration and convolutional neural network. Firstly, the continuous wavelet transform is carried out on the vibration signal of the high-voltage circuit breaker, and the wavelet energy frequency band is generated by using the discrete wavelet transform, and the characteristics of the vibration signal of the mechanical fault of the high-voltage circuit breaker are extracted. Then, the preprocessed feature maps are input into the convolutional neural network model to realize fault state diagnosis. Finally, in the simulation example, it is verified that the method proposed in this paper can effectively characterize the change of the mechanical state of the high-voltage circuit breaker, and achieve better diagnostic results for different types of faults.