Exploiting Movable-Element STARS for Rate Splitting Multiple Access

This paper investigates a movable-element simultaneously transmitting and reflecting reconfigurable intelligent surface (ME-STARS) assisted rate-splitting multiple access (RSMA) system under imperfect channel state information (CSI). Unlike conventional STARS with fixed element positions, the elements of ME-STARS can be repositioned within a predefined region, providing additional spatial degrees of freedom for improving the cascaded transmitter--STARS--user channels. To exploit this flexibility while accounting for CSI uncertainty, we formulate a robust sum-rate maximization problem that jointly optimizes the transmit beamforming, common-rate allocation, reflection and transmission coefficients, and ME-STARS element positions, subject to transmit-power, user-rate, minimum inter-element spacing, and movement-region constraints. The resulting problem is highly non-convex due to the strong coupling among the design variables and the position-dependent channels. To address this challenge, an iterative optimization framework is developed in which the transmit beamforming, STARS coefficients, and element positions are successively optimized through tractable convex reformulations. In particular, the element positions are updated sequentially using a majorization--minimization (MM) framework, where quadratic surrogate functions are constructed from the first- and second-order derivatives of the position-dependent channels while preserving the minimum inter-element spacing constraint. Simulation results demonstrate that the proposed ME-STARS design consistently outperforms the considered benchmark schemes. Moreover, the performance gains remain significant under increasing CSI uncertainty, highlighting the effectiveness of element repositioning for robust RSMA transmission.

Differentiable Clone-Structured Causal Graphs for End-to-End Cognitive Map Learning from Image Sequences

How can an agent build a structured map of its world from nothing but an ongoing sequence of raw sensory input and its own movements, especially when natural variation means exact sensory patterns rarely repeat? The Clone-Structured Causal Graph algorithm (CSCG), a normative hippocampus model, shows how an interpretable map can be learned from aliased observations. However, CSCG requires a predefined discrete alphabet, and its expectation-maximization formulation is not easily combined with existing neural network modules, preventing the end-to-end processing of raw image sequences. We remove this barrier by reformulating CSCG as a single, fully differentiable module, gradCSCG, and coupling it to a learned vector-quantized variational autoencoder (VQ-VAE) perceptual front-end. A soft emission forward pass allows the map-learning objective to flow back into perception, while a set of loss-balancing mechanisms mitigates module collapse during joint training. We demonstrate, first, that gradient training reproduces CSCG's results on original symbolic grid worlds by recovering room topology from heavily aliased observations. Second, we show that map recovery remains robust on MNIST image sequences, where each visit to a location yields a newly sampled image of its assigned digit. Across four heavily aliased environments, the end-to-end pipeline successfully uncovers the underlying adjacency graph with high edge precision and recall, directly from visual input. This work provides a proof of principle that CSCG can serve as a composable building block in a deep learning architecture.

Adaptive UAV Communications for URLLC: From Preplanned Designs to Real-Time Intelligence

Unmanned aerial vehicles (UAVs) are emerging as a key enabler of next-generation wireless networks, particularly for applications that require ultra-reliable and low-latency communication (URLLC), such as emergency response, industrial automation, and autonomous systems. In these scenarios, maintaining reliable connectivity under strict transmission time constraints is challenging due to dynamic environments, mobility, and limited onboard energy. In particular, communication performance and energy are closely coupled with UAV movement, making trajectory design a critical component of system operation. Most existing approaches rely on offline joint communication and trajectory optimization, where the UAV trajectory and communication parameters are optimized prior to execution based on assumed system information. Although effective under ideal assumptions, such designs cannot adapt to real-time variations in user demand, channel conditions, or environmental disturbances, which are particularly critical in URLLC settings. To address these challenges, this article investigates model predictive control (MPC) as an adaptive framework for UAV-enabled communications. Using a receding-horizon strategy, MPC enables the UAV to continuously update its trajectory based on real-time information, improving reliability and robustness in dynamic environments. Representative application scenarios are discussed to highlight the role of MPC in UAV-enabled URLLC systems. Furthermore, a case study is presented to illustrate key design trade-offs and performance insights under finite blocklength-based URLLC transmission, followed by a discussion on open challenges and future research directions for practical and scalable MPC-enabled UAV communication systems.

Online Model Predictive Control for Trajectory and Beamforming Optimization in UAV-Enabled URLLC

This paper investigates joint trajectory and active beamforming design for unmanned aerial vehicle (UAV)-enabled ultra-reliable low-latency communication (URLLC) systems under finite blocklength (FBL) transmission. Unlike conventional Shannon-capacity formulations, the FBL regime introduces a signal-to-interference-plus-noise ratio (SINR)-dependent dispersion penalty that increases the sensitivity of reliability to mobility-induced channel variations. To address this challenge, we develop a propulsion-aware model predictive control (MPC) framework that performs receding-horizon joint trajectory and multi-user beamforming optimization while enforcing FBL-based rate constraints. The resulting long-horizon nonconvex problem is decomposed into beamforming and trajectory subproblems using alternating optimization. Concave surrogate is constructed for the Shannon-capacity term, while convex approximations are derived for the dispersion term and the nonlinear propulsion power model, yielding tractable convex subproblems solved iteratively. Compared with an offline MPC baseline, where the predictive problem is solved once over the entire mission horizon without feedback updates, and a conventional offline trajectory-beamforming optimization, the proposed closed-loop framework achieves disturbance-resilient mission completion under UAV position disturbances. Simulation results show that, compared with maximum ratio transmission (MRT) and equal-power allocation, the proposed interference-aware design significantly improves URLLC reliability under stringent minimum rate constraints. The results also quantify the impact of antenna scaling, transmit power, and transmission time on FBL performance, providing insights for reliability-centric UAV-enabled wireless networks in 5G and beyond.

When Movable Antennas Meet RSMA and RIS: Robust Beamforming Design With Channel Uncertainty

In this work, we propose an intelligent optimization framework for a multi-user communication system integrating movable antennas (MAs) and a reconfigurable intelligent surface (RIS) under the rate-splitting multiple access (RSMA) protocol. The system sum-rate is maximized through joint optimization of transmit precoding vectors, RIS reflection matrix, common-rate allocation, and MA positions, subject to quality-of-service (QoS), power-budget, common-rate decoding, and mutual coupling constraints. Imperfect channel state information (CSI) is considered for all links, where robustness is ensured by modeling channel estimation errors within a bounded uncertainty region, guaranteeing worst-case performance reliability. The resulting non-convex problem is solved using an alternating optimization framework. The precoding subproblem is reformulated as a semidefinite programming (SDP) problem via linear matrix inequalities derived using the S-procedure. The RIS reflection matrix is optimized using successive convex approximation (SCA), yielding an equivalent SDP formulation. The MA position optimization is addressed through SCA combined with block coordinate descent (BCD) method. Numerical results validate the effectiveness of the proposed framework and demonstrate fast convergence.

Robust Design of Beyond-Diagonal Reconfigurable Intelligent Surface Empowered RSMA-SWIPT System Under Channel Estimation Errors

This work explores the integration of rate-splitting multiple access (RSMA), simultaneous wireless information and power transfer (SWIPT), and beyond-diagonal reconfigurable intelligent surface (BD-RIS) to enhance the spectral-efficiency, energy-efficiency, coverage, and connectivity of future sixth-generation (6G) communication networks. Specifically, with a multiuser BD-RIS-empowered RSMA-SWIPT system, we jointly optimize the transmit precoding vectors, the common rate proportion of users, the power-splitting ratios, and scattering matrix of BD-RIS node, under the assumption of imperfect channel state information (CSI). Additionally, to better capture practical hardware behavior, we incorporate a nonlinear energy harvesting model under energy harvesting constraints. We design a robust optimization framework to maximize the system sum-rate, while explicitly accounting for the worst-case impact of CSI uncertainties. Further, we introduce an alternating optimization framework that partitions the problem into several blocks, which are optimized iteratively. More specifically, the transmit precoding vectors are optimized by reformulating the problem as a convex semidefinite programming through successive-convex approximation (SCA), whereas the power-splitting problem is solved using the MOSEK-enabled CVX toolbox. Subsequently, to optimize the scattering matrix of the BD-RIS, we first employ SCA to reformulate the problem into a convex form, and then design a manifold optimization strategy based on the Conjugate-Gradient method. Finally, numerical simulation results reveal that the proposed scheme provides significant performance improvements over existing benchmarks and demonstrates rapid convergence within a reasonable number of iterations.

Lower-dimensional projections of cellular expression improves cell type classification from single-cell RNA sequencing

Single-cell RNA sequencing (scRNA-seq) enables the study of cellular diversity at single cell level. It provides a global view of cell-type specification during the onset of biological mechanisms such as developmental processes and human organogenesis. Various statistical, machine and deep learning-based methods have been proposed for cell-type classification. Most of the methods utilizes unsupervised lower dimensional projections obtained from for a large reference data. In this work, we proposed a reference-based method for cell type classification, called EnProCell. The EnProCell, first, computes lower dimensional projections that capture both the high variance and class separability through an ensemble of principle component analysis and multiple discriminant analysis. In the second phase, EnProCell trains a deep neural network on the lower dimensional representation of data to classify cell types. The proposed method outperformed the existing state-of-the-art methods when tested on four different data sets produced from different single-cell sequencing technologies. The EnProCell showed higher accuracy (98.91) and F1 score (98.64) than other methods for predicting reference from reference datasets. Similarly, EnProCell also showed better performance than existing methods in predicting cell types for data with unknown cell types (query) from reference datasets (accuracy:99.52; F1 score: 99.07). In addition to improved performance, the proposed methodology is simple and does not require more computational resources and time. the EnProCell is available at https://github.com/umar1196/EnProCell.

Integration of Beyond Diagonal RIS and UAVs in 6G NTNs: Enhancing Aerial Connectivity

The reconfigurable intelligent surface (RIS) technology shows great potential in sixth-generation (6G) terrestrial and non-terrestrial networks (NTNs) since it can effectively change wireless settings to improve connectivity. Extensive research has been conducted on traditional RIS systems with diagonal phase response matrices. The straightforward RIS architecture, while cost-effective, has restricted capabilities in manipulating the wireless channels. The beyond diagonal reconfigurable intelligent surface (BD-RIS) greatly improves control over the wireless environment by utilizing interconnected phase response elements. This work proposes the integration of unmanned aerial vehicle (UAV) communications and BD-RIS in 6G NTNs, which has the potential to further enhance wireless coverage and spectral efficiency. We begin with the preliminaries of UAV communications and then discuss the fundamentals of BD-RIS technology. Subsequently, we discuss the potential of BD-RIS and UAV communications integration. We then proposed a case study based on UAV-mounted transmissive BD-RIS communication. Finally, we highlight future research directions and conclude this work.

Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques

This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed of two subtasks, namely (i) Relevance Classification of Twitter Posts (RCTP), and (ii) Location Extraction from Twitter Texts (LETT). The RCTP subtask aims at differentiating flood-related and non-relevant social posts while LETT is a Named Entity Recognition (NER) task and aims at the extraction of location information from the text. For RCTP, we proposed four different solutions based on BERT, RoBERTa, Distil BERT, and ALBERT obtaining an F1-score of 0.7934, 0.7970, 0.7613, and 0.7924, respectively. For LETT, we used three models namely BERT, RoBERTa, and Distil BERTA obtaining an F1-score of 0.6256, 0.6744, and 0.6723, respectively.

Energy-Efficient Beamforming and Resource Optimization for AmBSC-Assisted Cooperative NOMA IoT Networks

In this manuscript, we present an energy-efficient alternating optimization framework based on the multi-antenna ambient backscatter communication (AmBSC) assisted cooperative non-orthogonal multiple access (NOMA) for next-generation (NG) internet-of-things (IoT) enabled communication networks. Specifically, the energy-efficiency maximization is achieved for the considered AmBSC-enabled multi-cluster cooperative IoT NOMA system by optimizing the active-beamforming vector and power-allocation coefficients (PAC) of IoT NOMA users at the transmitter, as well as passive-beamforming vector at the multi-antenna assisted backscatter node. Usually, increasing the number of IoT NOMA users in each cluster results in inter-cluster interference (ICI) (among different clusters) and intra-cluster interference (among IoT NOMA users). To combat the impact of ICI, we exploit a zero-forcing (ZF) based active-beamforming, as well as an efficient clustering technique at the source node. Further, the effect of intra-cluster interference is mitigated by exploiting an efficient power-allocation policy that determines the PAC of IoT NOMA users under the quality-of-service (QoS), cooperation, SIC decoding, and power-budget constraints. Moreover, the considered non-convex passive-beamforming problem is transformed into a standard semi-definite programming (SDP) problem by exploiting the successive-convex approximation (SCA) approximation, as well as the difference of convex (DC) programming, where Rank-1 solution of passive-beamforming is obtained based on the penalty-based method. Furthermore, the numerical analysis of simulation results demonstrates that the proposed energy-efficiency maximization algorithm exhibits an efficient performance by achieving convergence within only a few iterations.