Widespread proliferation of wireless coverage has enabled culmination of number of advanced location-based services (LBS). Continuous tracking of accurate physical location is the foundation of these services, which is a challenging task especially indoors. Multitude of techniques and algorithms have been proposed for indoor positioning systems (IPS’s). However, accuracy, reliability, scalability and, adaptability to the environment still remain as challenges for widespread deployment. Especially, unpredictable radio propagation characteristics in vastly varying indoor environments plus access technology limitations contribute to these challenges. Machine learning (ML) approaches have been widely attempted recently to overcome these challenges with reasonable success. In this paper, we aim to provide a comprehensive survey of ML enabled localization techniques using most common wireless technologies. First, we provide a brief background on indoor localization techniques. Afterwards, we discuss various ML techniques (supervised and unsupervised) that could alleviate different challenges in indoor localization including Non-line-of-sight (NLOS) issue, device heterogeneity and environmental variations with reasonable complexity. The trade-offs among multitude of issues are discussed using numerous published results. We also discuss how the ML algorithms can be effectively used for fusing different technologies and algorithms to achieve a comprehensive IPS. In essence, this survey will serve as a reference material to acquire a detailed knowledge on recent development of machine learning for accurate indoor positioning.

Unmanned Aerial Vehicle (UAV) has emerged as a promising technology to provide wireless signals from air to the ground users in specific scenarios such as earthquakes, tsunamis and other disasters. The performance of the UAV is degraded when the signals are blocked by obstacles in dense urban scenarios. To address this issue and enhance the signal quality available to the ground users, Reconfigurable Intelligent Surface (RIS) has emerged as a new technological paradigm. It offers an intelligent configuration for the signal propagation environment by redirecting the signals to the users. In this article, we solve a non-convex optimization problem of RIS-assisted UAV network by jointly optimizing the RIS phase shift and 3D trajectory of UAV to maximize the energy efficiency of a rotatory-wing UAV. The considered optimization problem is solved using Deep Reinforcement Learning (DRL) based techniques in an on-line fashion to reduce the computational complexity. We leverage Twin-delayed Deep Deterministic Policy Gradient (TD3) to solve the problem by considering the UAV trajectory as a set of continuous actions. For comparison, we also use the Soft Actor-Critic (SAC), Deep Deterministic Policy Gradient (DDPG) and Double Deep Q-Network (DDQN) for continuous and discrete optimization of the UAV trajectory, respectively. Extensive simulations show that the TD3 outperforms all the considered DRL techniques with the highest energy efficiency and throughput, and the lowest propulsion energy.

To cope with the increasing global demand of energy and significant energy wastage caused by the use of different home appliances, smart load monitoring is considered a promising solution to promote proper activation and scheduling of devices and reduce electricity bills. Instead of installing a sensing device on each electric appliance, non-intrusive load monitoring (NILM) enables the monitoring of each individual device using the total power reading of the home smart meter. However, for a high-accuracy load monitoring, efficient artificial intelligence (AI) and deep learning (DL) approaches are needed. To that end, this paper thoroughly reviews traditional AI and DL approaches, as well as emerging AI models proposed for NILM. Unlike existing surveys that are usually limited to a specific approach or a subset of approaches, this review paper presents a comprehensive survey of an ensemble of topics and models, including deep learning, generative AI (GAI), emerging attention-enhanced GAI, and hybrid AI approaches. Another distinctive feature of this work compared to existing surveys is that it also reviews actual cases of NILM system design and implementation, covering a wide range of technical enablers including hardware, software, and AI models. Furthermore, a range of new future research and challenges are discussed, such as the heterogeneity of energy sources, data uncertainty, privacy and safety, cost and complexity reduction, and the need for a standardized comparison.

Non-Intrusive Load Monitoring (NILM) aims to disaggregate a household’s total aggregated power consumption into appliance-level usage, enabling intelligent energy management without the need for intrusive metering. While deep learning has improved NILM significantly, existing NILM models struggle to capture load patterns across both longer time intervals and subtle timings for appliances involving brief or overlapping usage patterns. In this paper, we propose a novel GRU+BERT hybrid architecture, exploring both unidirectional (GRU+BERT) and bidirectional (Bi-GRU+BERT) variants. Our model combines Gated Recurrent Units (GRUs) to capture sequential temporal dependencies with Bidirectional Encoder Representations from Transformers (BERT), which is a transformer-based model that captures rich contextual information across the sequence. The bidirectional variant (Bi-GRU+BERT) processes input sequences in both forward (past to future) and backward (future to past) directions, enabling the model to learn relationships between power consumption values at different time steps more effectively. The unidirectional variant (GRU+BERT) provides an alternative suited for appliances with structured, sequential multi-phase usage patterns, such as dishwashers. By placing the Bi-GRU or GRU layer before BERT, our models first capture local time-based load patterns and then use BERT’s self-attention to understand the broader contextual relationships. This design addresses key limitations of both standalone recurrent and transformer-based models, offering improved performance on transient and irregular appliance loads. Evaluated on the UK-DALE and REDD datasets, the proposed Bi-GRU+BERT and GRU+BERT models show competitive performance compared to several state-of-the-art NILM models while maintaining a comparable model size and training time, demonstrating their practical applicability for real-time energy disaggregation, including potential edge and cloud deployment scenarios.

In this paper, we design a Reconfigurable Intelligent Surface (RIS)-assisted down-link cellular network for the co-existence of enhanced Mobile Broadband (eMBB) and Ultra Reliable Low Latency Communication (URLLC) services in 6G. A novel hybrid slicing technique comprising Non-orthogonal Multiple Access (NOMA) and puncturing is proposed to schedule the URLLC transmission on top of the already scheduled eMBB traffic. We propose a slot-based eMBB scheduling to schedule the eMBB flows at the beginning of the slot, and a mini-slot-based URLLC scheduling to insert the mini-slots on top of the scheduled eMBB traffic. The overall objective is to maximize the URLLC packets admission rate and minimize the eMBB rate loss while satisfying the Quality of Service (QoS) demands of both eMBB and URLLC services. The eMBB allocation problem is solved using Alternating Optimization (AO) by optimizing the RIS phase shift and eMBB power. The URLLC allocation is achieved using a Deep Reinforcement Learning (DRL)-based Proximal Policy Optimization (PPO) algorithm. The performance of the proposed technique with hybrid network slicing is compared with the NOMA-based and puncturing-based slicing, and other state-of-the-art (SOTA) techniques for URLLC allocation. The comparison results show that the proposed hybrid network slicing outperforms these techniques. Specifically, it is observed that with the worst-case URLLC load, the proposed solution provides 5.31% and 144% improvements in the URLLC packet admission rate and eMBB sum rate, respectively, compared to an optimization-based SOTA URLLC allocation technique. Similarly, there is an improvement of 78.36% in execution time compared to the SOTA URLLC allocation technique based on the heuristic algorithm.

Quantum neural networks (QNNs) have recently attracted remarkable attention as a potential alternative to classical and deep neural network (NN) models particularly under constraints imposed by noisy intermediate-scale quantum (NISQ) devices, which support only shallow circuits with few quantum bits (qubits) and limited variational depth. However, applying QNNs to natural language processing (NLP) remains challenging because text representations are typically high-dimensional, while NISQ classifiers can only encode a small number of features at a time, requiring classical compression to enable stable training and flexible circuit configuration. In addition, many existing studies integrate QNNs into rich-text representation pipelines, where the quantum circuit is often implemented as a variational quantum circuit (VQC). Here, the VQC acts as an additional component within a larger model, and it remains unclear how the quantum component improves the classification task. Therefore, in this work, we propose a fully reproducible and compact QNN pipeline that provides a controlled setting for studying the contribution of the VQC to text classification. The model is trained end-to-end with a lightweight classical compression layer, and the overall study is supported by systematic ablation analyses of the compression layer, the classifier heads under a shared frozen low-dimensional representation, and quantum circuit structure. Our model uses the term frequency-inverse document frequency (TF-IDF) features with linear compression followed by a shallow four-qubit, two-layer VQC, implemented in PyTorch and PennyLane for end-to-end training. It is evaluated on five benchmark text classification datasets against classical baselines, including logistic regression and multilayer perceptron (MLP) models. Experimental results show that the proposed QNN achieves a competitive performance across all evaluated datasets, yielding the best results on three of the five benchmark datasets.