The development of wearable sensor devices brings significant benefits to patients by offering real-time healthcare via wireless body area networks (WBANs). These wearable devices have gained significant traction due to advantageous features, including their lightweight nature, comfortable feel, stretchability, flexibility, low power consumption, and cost-effectiveness. Wearable devices play a pivotal role in healthcare, defence, sports, health monitoring, disease detection, and subject tracking. However, the irregular nature of the human body poses a significant challenge in the design of such wearable systems. This manuscript provides a comprehensive review of recent advancements in wearable and flexible smart sensor devices that can support the next generation of such sensor devices. Further, the development of direct ink writing (DIW) and direct writing (DW) methods has revolutionised new high-resolution integrated smart structures, enabling the design of next-generation soft, flexible, and stretchable wearable sensor devices. Recognising the importance of keeping academia and industry informed about cutting-edge technology and time-efficient fabrication tools, this manuscript also provides a thorough overview of the latest progress in various fabrication methods for wearable sensor devices utilised in WBAN and their evaluation using body phantoms. An overview of emerging challenges and future research directions is also discussed in the conclusion.

Long short-term memory (LSTM) networks are extensively used in various sequential learning tasks, including speech recognition. Their significance in real-world applications has prompted the demand for cost-effective and power-efficient designs. This paper introduces LSTM architectures based on distributed arithmetic (DA), utilizing circulant and block-circulant matrix-vector multiplications (MVMs) for network compression. The quantized weights-oriented approach for training circulant and block-circulant matrices is considered. By formulating fixed-point circulant/block-circulant MVMs, we explore the impact of kernel size on accuracy. Our DA-based approach employs shared full and partial methods of add-store/store-add followed by a select unit to realize an MVM. It is then coupled with a multi-partial strategy to reduce complexity for larger kernel sizes. Further complexity reduction is achieved by optimizing decoders of multiple select units. Pipelining in add-store enhances speed at the expense of a few pipelined registers. The results of the field-programmable gate array showcase the superiority of our proposed architectures based on the partial store-add method, delivering reductions of 98.71% in DSP slices, 33.59% in slice look-up tables, 13.43% in flip-flops, and 29.76% in power compared to the state-of-the-art.

Photovoltaic (PV) systems are one of the promising renewable energy sources that have many industrial applications; one of them is water pumping systems. This paper proposes a new application of a PV system for water pumping using a three-phase induction motor while maximizing the daily quantity of water pumped while considering maximizing both the efficiency of the three-phase induction motor and the harvested power from the PV system. This harvesting is performed through maximum power point tracking (MPPT) of the PV system. The proposed technique is applied to a PV-powered 3 phase induction motor water pumping system (PV-IMWPS) at any operating point. Firstly, an analytical approach is offered to find the optimal firing pattern of the inverter (V-F) for the motor through optimal flux control. This flux control is presented for maximizing the pump flow rate while achieving MPPT for the PV system and maximum efficiency of the motor at any irradiance and temperature. The provided analytical optimal flux control is compared to a fixed flux one to ascertain its effectiveness. The obtained feature of the suggested optimal flux control validates a significant improvement in the system performances, including the daily pumped quantity, motor power factor, and system efficiency. Then converting the data from the first analytical step into an intelligent approach using an adaptive neuro-fuzzy inference system (ANFIS). This ANFIS is trained offline with the input (irradiance and temperature) while the output is the inverter pattern to enhance the performance of the proposed pumping system, PV-IMWPS.

Distributed arithmetic (DA) is an efficient look-up table (LUT) based approach. The throughput of DA based implementation is limited by the LUT size. This paper presents two high-throughput architectures (Type I and II) of non-pipelined DA based least-mean-square (LMS) adaptive filters (ADFs) using two’s complement (TC) and offset-binary coding (OBC) respectively. We formulate the LMS algorithm using the steepest descent approach with possible extension to its power-normalized LMS version and followed by its convergence properties. The coefficient update equation of LMS algorithm is then transformed via TC DA and OBC DA to design and develop non-pipelined architectures of ADFs. The proposed structures employ the LUT pre-decomposition technique to increase the throughput performance. It enables the same mapping scheme for concurrent update of the decomposed LUTs. An efficient fixed-point quantization model for the evaluation of proposed structures from a realistic point-of-view is also presented. It is found that Type II structure provides higher throughput than Type I structure at the expense of slow convergence rate with almost the same steady-state mean square error. Unlike existing non-pipelined LMS ADFs, the proposed structures offer very high throughput performance, especially with large order DA base units. Furthermore, they are capable of performing less number of additions in every filter cycle. Based on the simulation results, it is found that $256^{\mathrm {th}}$ order filter with $8^{\mathrm {th}}$ order DA base unit using Type I structure provides $9.41 \times $ higher throughput while Type II structure provides $16.68 \times $ higher throughput as compared to the best existing design. Synthesis results show that $32^{\mathrm {nd}}$ order filter with $8^{\mathrm {th}}$ order DA base unit using Type I structure achieves 38.76% less minimum sampling period (MSP), occupies 28.62% more area, consumes 67.18% more power, utilizes 49.06% more slice LUTs and 3.31% more flip-flops (FFs), whereas Type II structure achieves 51.25% less MSP, occupies 21.42% more area, consumes 47.84% more power, utilizes 29.10% more slice LUTs and 1.47% fewer FFs as compared to the best existing design.

The integration of Edge Computing (EC) and Energy Harvesting (EH) technologies has facilitated the growth of the Internet of Things (IoT), allowing for the interconnectivity of a wide range of devices. The integration of this technology has not only enhanced energy sustainability but also significantly extended the battery life of these devices. Adopting Renewable Energy (RE) sources has become more widespread in energy systems as a strategy to reduce carbon emissions. Low energy consumption and constrained battery capacity for IoT devices are concerns related to offloading. The unpredictability of RE quality makes it difficult for edge servers to maintain high quality of service in EH-EC systems, which impedes effective energy conservation for IoT. To solve an optimization problem, RE Predictions with a Deep Reinforcement Learning algorithm named (REP-DRL) are proposed. Accurately, REP-DRL used the actor-critic technique to identify the best approach for predicting RE and optimal offloading decisions. The approach improves IoT device processing and expands the system state to offload experiences per time slot. To store excess energy during periods of abundance and use it during times of higher demand, the service offloading process is modeled based on the predicted amount of RE, to find the best service offloading technique and improve energy sustainability for IoT. By determining the most efficient service offloading approach using the predicted RE amount, this solution increases the energy sustainability of the IoT ecosystem. Finally, the simulation results show that the REP-DRL system utilizes local computing to conserve power when both the battery level and projected EH are low, showcasing its capacity to adapt to varying operating conditions and optimize the utilization of resources.

High route loss and line-of-sight requirements are two of the fundamental challenges of millimeter-wave (mm-wave) communications that are mitigated by incorporating sensor technology. Sensing gives the deep reinforcement learning (DRL) agent comprehensive environmental feedback, which helps it better predict channel fluctuations and modify beam patterns accordingly. For multi-user massive multiple-input multiple-output (mMIMO) systems, hybrid precoding requires sophisticated real-time low-complexity power allocation (PA) approaches to achieve near-optimal capacity. This study presents a unique angular-based hybrid precoding (AB-HP) framework that minimizes radio frequency (RF) chain and channel estimation while optimizing energy efficiency (EE) and spectral efficiency (SE). DRL is essential for mm-wave technology to make adaptive and intelligent decision-making possible, which effectively transforms wireless communication systems. DRL optimizes RF chain usage to maintain excellent SE while drastically lowering hardware complexity and energy consumption in an AB-HP architecture by dynamically learning optimal precoding methods using environmental angular information. This article proposes enabling dual optimization of EE and SE while drastically lowering beam training overhead by incorporating maximum reward beam training driven (RBT) in the DRL. The proposed RBT-DRL improves system performance and flexibility by dynamically modifying the number of active RF chains in dynamic network situations. The simulation results show that RBT-DRL-driven beam training guarantees good EE performance for mobile users while increasing SE in mm-wave structures. Even though total power consumption rises by 45%, the SE improves by 39%, increasing from 14 dB to 20 dB, suggesting that this strategy could successfully achieve a balance between performance and EE in upcoming B5G networks.