The domain adaptation issues in semantic communications become critical when transmitter and receiver operate across different multiple domains or when input data during inference have different distributional characteristics than the data used to train semantic encoders and decoders. In this paper, we introduce the Multidomain Adaptive Deep Semantic Communication (MA-DeepSC) framework, designed to enhance semantic communications across multiple domains. Our framework consists of two core components: the Multidomain Adaptive Semantic Coding Network (MASCN), inherently designed to adapt semantic encoding and decoding across multiple domains, and the multidomain data adaptation network (MDAN), which transforms actual observable data into the data on which the system was initially trained, thus obviating the need for retraining the existing pre-trained semantic coding network. We validate our approach through experiments on digit datasets and CelebA, observing significant outperformance over existing techniques. In addition, we analyze the strategic benefits and drawbacks of both MASC and MDAN, assessing their applicability under various scenarios. The source code for MA-DeepSC is available at https://github.com/wongdongwook/JSAC_MA-DeepSC.

Federated learning (FL) is a framework for realizing distributed machine learning in an environment where training samples are distributed to each device. Recently, FL has employed over-the-air computation enabling all devices to transmit learning model updates simultaneously. This work proposes a communication-efficient sparse one-bit analog aggregation (SOBAA) method, incorporating new power control, layer-wise scaled one-bit quantization, layer-wise sparsification, and an error-feedback mechanism. We derive a tight upper bound of the expected convergence rate of the proposed SOBAA as a closed-form expression. From this expression, we explicitly identify the relationship between the convergence rate and compression and aggregation errors. Based on the theoretical convergence analysis, we formulate a joint optimization problem of the compression ratio and power control to minimize compression and aggregation errors, leading to the fastest convergence. In each communication round, the optimization problem is decomposed, and solved in a computationally efficient and feasible way. From this solution, we characterize the trade-off between learning performance and communication cost. Through extensive experiments on well-known MNIST and CIFAR-10 datasets, we confirm that the proposed method provides an enhanced trade-off performance between test accuracy and communication costs and a faster convergence rate than the other state-of-the-art methods. In addition, it is proven that the proposed method is more effective for more complex datasets and learning models.

Mobile chargers (MCs) equipped with radio-frequency (RF)-based wireless power transfer (WPT) modules have been suggested as a possible solution to battery constraints in wireless rechargeable sensor networks (WRSNs). In RF-based WPT, charging efficiency decreases significantly as the charging distance increases. Therefore, single charging consumes less energy than multicharging because it can generally charge a sensor node at a closer range. However, when the density of nodes is high, multicharging may achieve higher efficiency. We propose an energy-efficient adaptive directional charging (EEADC) algorithm that considers the density of sensor nodes to adaptively choose single charging or multicharging. The EEADC exploits directional antennas to concentrate the energy and improve energy efficiency and identifies the optimum charging points and beam directions to minimize energy consumption. In the EEADC, clustering is performed by considering the density of the sensor nodes. After clustering, the clusters are classified into single-charging/multicharging clusters according to the number of sensor nodes in each cluster. Next, the charging strategy is determined according to the type of cluster. In the case of a multicharging cluster, the problem is nonconvex. Therefore, a discretized charging strategy decision (DCSD) algorithm is proposed. The performance evaluation indicates that EEADC outperforms two existing methods in terms of power consumption and charging delay by 10% and 9%, respectively.