Split Federated Learning is a system-efficient federated learning paradigm that leverages the rich computing resources at a central server to train model partitions. Data heterogeneity across silos, however, presents a major challenge undermining the convergence speed and accuracy of the global model. This paper introduces Step-wise Momentum Fusion (SMoFi), an effective and lightweight framework that counteracts gradient divergence arising from data heterogeneity by synchronizing the momentum buffers across server-side optimizers. To control gradient divergence over the training process, we design a staleness-aware alignment mechanism that imposes constraints on gradient updates of the server-side submodel at each optimization step. Extensive validations on multiple real-world datasets show that SMoFi consistently improves global model accuracy (up to 7.1%) and convergence speed (up to 10.25×). Furthermore, SMoFi has a greater impact with more clients involved and deeper learning models, making it particularly suitable for model training in resource-constrained contexts.

Due to the dual functionality of lighting and localization, received signal strength (RSS) based visible light positioning (VLP) has become a promising high-precision indoor positioning method in industrial environments by leveraging pervasively available lighting infrastructure. However, its widespread deployment is hindered by two key challenges: 1) the need for densely sampled fingerprint datasets, and 2) performance degradation due to LED aging in a long-lasting deployment. To address these limitations, we develop a data-efficient VLP method with an online calibration strategy that automatically compensates for gradual light intensity decay caused by LED aging, maintaining robustness without manual re-fingerprinting. Extensive simulations demonstrate that the proposed approach maintains centimeter-level precision across varying LED usage durations. A lightweight on-device model deployed on the Raspberry Pi Pico microcontroller achieves 1.62 cm mean positioning error with 8.39 ms inference latency, demonstrating the practicality of our approach for long-lasting indoor positioning in industrial and IoT scenarios. The source code is publicly available at https://github.com/joeywli/VLP.

6G will require on-device antenna systems to operate at ultra-high frequency bands, achieve robust beamforming on the compact user devices, and be blockage-robust. Conventional edge-mounted antennas on devices have limited apertures, suffer from the 'death grip' caused by user-induced blockage, and have poor scalability at mmWave and sub-THz bands. To address these issues, motivated by the rapid evolution of transparent materials and antennas, we propose ScreenAnt in this work - which integrates a transparent antenna array onto the screens of future mobile devices. Specifically, we propose using a transparent on-screen uniform planar array and develop a framework to model its electromagnetic property, spatial configuration, and blockage robustness under realistic user-induced blockage. We also design a gradient-ascent-based algorithm to efficiently optimize power and phase control of on-screen antennas to maximize ScreenAnt's spectral efficiency. Our thorough simulations show that the proposed ScreenAnt can increase the uplink spectral efficiency by over 50% compared to edge-mounted antennas at 28 GHz, and by more than 150% at 300 GHz. ScreenAnt also demonstrates strong robustness against user-induced blockage, paving the way for practical and high-capacity 6G user device designs.

With the development of communication networks and Artificial Intelligence (AI) technologies, Digital Twin (DT) now emerges to support various applications such as engineering, monitoring, controlling, healthcare and the optimization of cyber-physical systems. There is an increasing demand to create DTs that can represent physical entities for improving operational efficiency. A conventional DT consists of monitoring, imitation, and feedback control. However, conventional DTs cannot ensure efficient real-time imitation due to the high dynamics of physical systems such as UAV-based target tracking scenario. To address this issue, we propose a federated DT framework to support the imitation of mobile systems. It can guarantee real-time and accurate imitations under the prerequisite of comprehensive information acquired by a cooperative collection algorithm with the aid of UAVs. The framework can rapidly aggregate local DT models using an attention-based mechanism to improve mobile imitation accuracy. Additionally, we propose a multimodal-based DT inspection algorithm that can correct the postures of UAVs affected by winds for reliable imitations. We implement the framework in Gazebo. Our system simulations demonstrate the efficiency of the proposed federated DT framework. Our solution can reduce the imitation latency by an average of 68.4%, meanwhile, can improve the imitation accuracy by 16.4% on average when compared to traditional centralized and distributed imitation schemes.

Achieving accurate and low-latency spectrum sensing on resource-constrained devices is essential but very difficult. Traditional In-phase and Quadrature (I/Q)-based and the ShortTime Fourier Transform (STFT)-based methods fail to balance the computational overhead and classification accuracy. In this paper, we propose a novel framework -Spectrum Painting (SP)- which enables on-device signal classification with low latency and high accuracy. We design new signal processing methods to compress spectrograms while keeping global signal features and augmenting the salient features of small objects. SP achieves high-accuracy signal classification, assisted further by our proposed Dual-channel Convolutional Neural Network (DualCNN). We collect diverse datasets to evaluate the proposed SP, including synthesized data, and testbed data (from up to 18 commodity devices) obtained from real-world environments in the wild and office settings. Experimental results of SP running on Raspberry Pi 4B show a great reduction in latency up to 20 × while maintaining a 95% accuracy. Furthermore, SP demonstrates superior performance within both the centralized learning architecture and the Federated Learning (FL) architecture. For example, the challenging cross-environment evaluation of the SP in the iid-FL scenario yields a substantial accuracy improvement, on average from 24.6% to 83.8%.

This paper presents a novel transparent amplifying intelligent surface (TAIS) architecture for uplink enhancement in indoor-To-outdoor mmWave communications. The TAIS is an amplifier-based transmissive intelligent surface that can refract and amplify the incident signal, instead of only refracting it with adjustable phase shift by most passive reconfigurable intelligent surfaces (RIS). With advanced indium tin oxide film and printing technology, TAIS can be fabricated on the windows without any visual effects. This paper primarily focuses on exploiting the TAIS-based architecture to boost the uplink spectral efficiency (SE) in indoor-To-outdoor mmWave communications. By jointly optimizing the TAIS's phase shift matrix and transmit power of the user equipment, the uplink SE can be maximized by exploiting the nonlinearity in the TAIS's amplification process. The key enabler is that we drive the optimal phase shift matrix that maximizes the SE and deduces its closed-form representation. The SE maximization is then proved to be transferred to the transmit power optimization problem. Another important enabler is that we design a low-complexity algorithm to solve the optimization problem using the difference of convex programming. Moreover, the asymptotic spectral efficiency under nonlinear amplification and power scaling law with infinitely large elements under both the sparse and rich scattering channel models are analyzed. Simulation results show that our proposed TAIS can increase the SE by up to 24.7% as compared to its alternative methods.

Visible light positioning (VLP) based on the received signal strength (RSS) can leverage a dense deployment of LEDs in future lighting infrastructure to provide accurate and energy-efficient indoor positioning. However, its positioning accuracy heavily depends on the density of collected fingerprints, which is labor-intensive. In this work, we propose a data pre-processing method, including data cleaning and data augmentation, to construct reliable and dense fingerprint samples, thereby alleviating the impact of noisy samples as well as reducing labor intensity. Extensive experiments demonstrate that our proposed method achieves an average positioning error of 1.7 cm, utilizing a sparse dataset that reduces the fingerprint collection effort by 98 percent. Running a tinyML-based model for VLP on the Arduino Nano microcontroller, we also show the possibilities for deploying RSS fingerprint-based VLP systems on resource-constrained embedded devices for real-world applications.

Federated Learning (FL) is an important privacy-preserving learning paradigm that plays an important role in the Intelligent Internet of Things. Training a global model in FL, however, is vulnerable to the data noise across the clients. In this paper, we introduce FedTrans, a novel client-transparent client utility estimation method designed to guide client selection for noisy scenarios, mitigating performance degradation problems. To estimate the client utility, we propose a Bayesian framework that models client utility and its relationships with the weight parameters and the performance of local models. We then introduce a variational inference algorithm to effectively infer client utility at the FL server, given only a small amount of auxiliary data. Our evaluation results demonstrate that leveraging FedTrans to select the clients can improve the accuracy performance (up to 7.8%), ensuring the robustness of FL in noisy scenarios.

Over the past decade, visible light positioning has become increasingly important for precise localization systems, yet its widespread adoption is limited due to the necessity of modifying existing lighting systems. This paper presents HueLoc, a novel method that bypasses this issue by using inherent features of light, such as the dominant colours in white LED lights, and employs affordable, energy-efficient hue sensors for location services. We propose that by extracting the power at dominant wavelengths of LEDs, these can be uniquely identified using a specifically designed signature. The unique signatures can be used by mobile objects for spatial awareness and further localization using the proposed regression-based learning approach. Our experiments demonstrate that HueLoc attains a location-mapping accuracy of 100% and achieves decimeter-level localization precision with a moving object in uncontrolled lighting conditions. Moreover, these unique signatures can be combined with other RF-based technologies to enhance their localization accuracy. As an example, this paper details the integration of Bluetooth features with light signatures using a three-stage incremental learning approach.

This paper introduces an Integrated Sensing and Communication (ISAC) approach to safeguard communication User Equipment (UE) from approaching objects or people, such as potential blockers, without the need to scan the entire environment, while providing continuous communication services. The proposed UE-centered ISAC system utilizes a communication-centric waveform, transmitted through guard beams to monitor the area within the UE proximity. These guard beams are generated through a multi-beamforming technique employing a shared analog array that also generates the communication beam. The parameters for generating the guard beams are optimized to maximize sensing coverage while adhering to the communication Signal-to-Noise Ratio (SNR) constraints. In comparison to the detection using the communication-beam-only system, our optimized guard beams enhance the detection range and coverage area by over 1.5 times while maintaining the required communication SNR. Our multi-stage sensing pipeline applied to the guard beams significantly reduces the complexity of sensing signal processing required to detect approaching blockers while maintaining accuracy comparable to that of exhaustive scanning based on the grid-searching method. Furthermore, the guard beams approach reduces the impact on communication SNR by 0.7 dB factor compared to exhaustive scanning with a balanced communication-sensing power allocation, offering a less pronounced impact on the communication performance in an ISAC system.

Visible Light Communication (VLC) has emerged in the last few years as a promising technology not only for high-speed communication but also for serving a new generation of Internet of Things (IoT) devices that may leverage the pervasive lighting infrastructures. Integrating VLC in lighting environments for IoT requires the design of networked and intelligent luminaries and new IoT devices, encompassing the development of innovative technologies and new algorithms. A common experimental platform is necessary to lower the entrance barriers of VLC and speed up the research development. In this article, we provide guidelines for prototyping VLC for IoT applications, assisted by the open-source platform OpenVLC. We also introduce the new development on OpenVLC, which guarantees support for more powerful LEDs and much longer distance (extending the communication distance from 6 m to 19 m), dimming adaption, among other features. Its low-cost, open-source, and open-hardware designs allow researchers in the community to swiftly adapt it to suit their research purposes.

The development of the intelligent Internet of Things has facilitated the adoption of high-efficiency Multiple Targets Tracking (MTT) in many civil security applications. However, existing MTT technologies cannot offer full capability in accurate and real-time MTT for civil security. Many attractive applications in the next-generation wireless network, like Unmanned Aerial Vehicle (UAV) swarm, are envisioned to be exploited for enhanced MTT with the advantage of flexibility. Nonetheless, highly dynamic moving targets impose some new challenges. UAVs cannot always perform expected cooperative tracking in conventional architectures as well. To address these problems, we design a tiered Digital Twin-assisted tracking framework in this paper, which leverages multi-grained imitation for real-time and accurate MTT. We imitate a coarse-grained MTT to ensure a high successful tracking ratio. We then design a fine-grained imitation with a reaction-diffusion mechanism to explore the feasible cooperators based on trajectory prediction. Hardware-in-the-loop simulations demonstrate that our tiered framework can reduce 66.7% of the system latency overhead compared to the conventional DDPG benchmark while improving the successful tracking ratio by 30.6%.