The rapid advancements in wireless technologies have led to numerous research studies that provide evidence of the successful utilization of wireless signals, particularly, WiFi signals for human activity sensing in the indoor environment. As a promising technology, WiFi-based human sensing can be utilized for a variety of applications such as smart healthcare, smart homes, security, industry, office indoor environments etc., due to the availability of rich infrastructure. Furthermore, compared to other radio frequency (RF) based systems such as radio detection and ranging (RADAR) and radio frequency identification (RFID), WiFi is non-invasive, has low-cost, and provides ubiquitous coverage in the indoor setup. However, due to the limited accuracy and high complexity of the model-based approaches for human sensing, the systems empowered by the deep learning (DL) techniques have achieved remarkable performance gains and showed more robustness in dealing with complicated human sensing tasks. The article explores the physical layer parameters used in WiFi sensing such as received signal strength indicator (RSSI) and channel state information (CSI), the estimated parameters such as angle-of-arrival (AoA) and Doppler shift (DS) along with frequency modulated continuous wave (FMCW) RADAR technology. Moreover, the preliminary signal processing stages that are applied to the received WiFi signals in the DL assisted systems are discussed. This article provides a comprehensive literature survey on the recent advances in DL-empowered WiFi sensing focusing on human activity recognition and movement tracking followed by fall detection, single task-multi task classification, crowd monitoring and sensing, indoor localization, gaits recognition, and pose estimation. Furthermore, the paper highlight the challenges in the existing literature and discusses the possible future research directions in WiFi-based human sensing assisted by DL techniques.
Sustainable agriculture is a pivotal driver of a nation’s economic growth, especially considering the challenge of providing food for the world’s expanding population. Agriculture remains a cornerstone of many nations’ economies, so the need for intelligent, sustainable farming practices has never been greater. Agricultural industries worldwide require sophisticated systems that empower farmers to manage their crops efficiently, reduce water wastage, and optimize yield quality. Yearly, substantial crop losses occur due to unpredictable environmental changes, with improper irrigation practices being a leading cause. In this paper, we introduce an innovative irrigation time control system for smart farming. This system leverages fuzzy logic to regulate the timing of irrigation in cotton crop fields, effectively curbing water wastage while ensuring that crops receive neither too little nor too much water. Additionally, our system addresses a common agricultural challenge: whitefly infestations. Users can adjust climatic parameters, such as temperature and humidity, through our system, which minimizes both whitefly populations and water consumption. We have developed a portable measurement technology that includes air humidity sensors, temperature sensors, and rain sensors. These sensors interface with an Arduino platform, allowing real-time climate data collection. This collected climate data is then sent to the fuzzy logic control system, which dynamically adjusts irrigation timing in response to changing environmental conditions. Our system incorporates an algorithm that generates highly effective (IF-THEN) fuzzy logic rules, significantly improving irrigation efficiency by reducing overall irrigation duration. By automating the irrigation process and precisely delivering the right amount of water, our system eliminates the need for human intervention, rendering the agricultural system more dependable in achieving successful crop yields. Water supply commences when the environmental conditions reach specific thresholds and halts when the requisite climate conditions are met, maintaining an optimal environment for crop growth.
The next generation of mobile networks is predicted to deliver high data speeds, lower latency, and increase the spectral and energy efficiency of wireless communication systems. Several technologies are being investigated for usage in 5G networks. Massive multiple-input multiple-output (mMIMO) systems are one of the most promising technologies for enabling 5G. Even after the recent advancements and research, numerous challenges still exist for channel estimation for mMIMO systems. In the context of pilot contamination and feedback overhead, this study tracks the most recent developments in research on mMIMO system difficulties. The primary goals of this study are to identify the problems with channel estimation, provide a summary of the cutting-edge solutions suggested in the literature, and then discuss newly emerging open research issues that must be taken into account for the implementation of beyond-5G networks.
Emerging vehicle-to-everything (V2X) networks employ machine learning (ML) techniques to provide adaptive, reliable, secure, and low-latency communication. Previously proposed fitting-based path loss and rule-based jamming detection schemes in vehicular networks lack accuracy due to the highly mobile and complex vehicular environment. Standalone ML models are utilized for different regression and classification problems in vehicular networks; however, these models still provide limited accuracy in the case of limited datasets. This paper proposes a hybrid learning framework for jamming detection and path loss predictions based on the successive usage of multiple deep neural networks (DNN) blocks, in which each block extends the feature set of the succeeding block for efficient and fast learning. The proposed hybrid DNN model for jamming detection comprises three DNN blocks, i.e., a multi-layer perceptron (MLP) block and two sequential learning blocks with bidirectional LSTM and GRU layers. Similarly, for path estimation, the proposed hybrid model includes one MLP block followed by two bagged tree-based learning blocks. The proposed models for jamming and path loss prediction are trained and tested on a real-world dataset. In IEEE 802.11p link, the proposed hybrid model has been demonstrated to classify injected jamming signals with a significantly improved accuracy of 90.4% compared to existing benchmarks, including the random forest (RaFo) classifier and deep convolutional neural network. Similarly, the proposed hybrid DNN model for path loss estimation outperforms existing RaFo and fitting-based models, with a mean absolute error reduction of 4.5dB and 0.9dB in the case of V-VLC and IEEE 802.11p links, respectively.
The joint optimization of spectral efficiency (SE) and energy efficiency (EE) through power allocation (PA) techniques is a critical requirement for emerging fifth-generation and beyond networks. The trade-off between SE and EE becomes challenging in the massive multiple-input-multiple-output (MIMO) equipped base stations (BSs) in multi-cell cellular networks. Various algorithmic approaches including genetic algorithms and convex optimization have been considered to optimize the trade-offs between SE and EE in cellular networks. However, these methods suffer from high computational costs. A promising deep reinforcement learning technique is capable of addressing the computational challenges of single-objective optimization problems in wireless networks. Furthermore, multi-objective reinforcement learning has been employed for multi-objective optimization problems and can be utilized to jointly enhance the SE and EE in cellular networks. In this paper, we propose a downlink (DL) transmit PA method based on a multi-objective asynchronous advantage single actor-multiple critics (MO-A3Cs) architecture. The proposed architecture aims to optimize SE and EE trade-offs in massive MIMO-assisted multi-cell networks. Furthermore, we also propose a Bayesian rule-based preference weight updating mechanism, multi-objective advantage function, and balanced-reward aggregation method to effectively train and avoid biased objective reward during the training process of the proposed model. Extensive simulations depict that the proposed model is better capable of dealing with the joint optimization of SE and EE in dynamic changing scenarios. Compared to the existing benchmarks such as Pareto front approximation-based multi-objective, reinforcement learning-based single objective, and iterative methods, the proposed approach provides a better SE-EE trade-off by achieving a higher EE in multi-cell massive MIMO networks.