Joint stiffness affects over 350 million people worldwide, creating demand for intelligent systems for detection and monitoring. Patients with joint stiffness need continuous rehab guided by experts, highlighting the need for tele-rehabilitation. This work presents a flexible, biodegradable, and economical strain sensor for joint stiffness monitoring, fabricated through a simple, cost-effective method. The sensor uses cotton fabric as a substrate and conductive paste from recycled dry-cell electronic waste for electrodes. A modified interdigitated capacitive (MIDC) structure is used, achieving high sensitivity with a GF value of 1006, response and recovery times of 0.38 sec. On-body testing on wrist, knee, and elbow joints yielded a minimum resolution of 5°. The proposed MIDC strain sensor is ideal for joint stiffness monitoring in tele-rehabilitation.

The use of Reconfigurable intelligent surface (RIS) technology has gained significant attention in wireless communication systems due to its ability to manipulate the impinging electromagnetic waves. However, the energy consumption of RIS deployment and operation has been a major concern. To address this issue, we aim to analyze RIS self-sustainability techniques including photovoltaic solar panels and wireless power transfer (WPT) for providing energy to the RIS, in the absence of grid power. We first analyze energy efficiency of RIS to determine most energy efficient way to operate RIS. Then we analyze the power consumption of RIS and its distribution over active components of RIS. Combined with energy efficient operation of RIS and reduction in power consumption from identified active components we propose energy-efficient self-sustained RIS through WPT. We also present measurement results for power consumption optimized 1-bit RIS design of size$\mathbf{27}\times \mathbf{28}$. We propose that if RIS power consumption is improved then near future WPT techniques can be readily utilized for self-sustainable RIS operation.

Microwave Imaging (MWI) has emerged as a potential candidate for brain stroke detection due to its low cost, time efficiency and accurate nature when compared to other screening techniques. TinyML is a revolutionary technique for utilizing AI in portable and low-powered devices. The need for more compact and concise systems grows by the day in order to provide smart services, particularly in the medical arena. This paper tries to fulfil these requirements by presenting the first-ever portable MWI-based TinyML brain stroke detection system with high accuracy. The head-imaging dataset, utilized here for the training of models, provides open-source data generated by our prototype head imaging system consisting of a low-cost vector network analyzer, single-board computer, rotating motor setup, and a Vivaldi antenna. The Tiny ML model is a compressed-size model of our proposed Deep Learning (DL) framework that obtains an accuracy of 93% on testing data with an F1-score of 0.929 deployed on the single-board computer. The compressed model obtained by pruning or quantization is not only small in size but also retains the above 90% accuracy of the DL model. This work reassures the possibility of successful deployment of Tiny ML- based solutions in microwave imaging systems for medical diagnostic applications in low-resource settings.

Breast Microwave Imaging (BMI) has emerged as a competitive and potentially disruptive alternative to conventional breast cancer screening techniques owing to its desirable features and improved detection rate. In this paper, we apply various artificial intelligence, and deep learning approaches for automatic breast tumor detection, classification and localization in an open-source experimental BreastCare dataset obtained using our pre-clinical, portable and cost-effective BMI system. We compare the effectiveness of various cutting-edge machine-learning detection algorithms to assess the usefulness of the obtained data-set. Also, we present a deep learning framework that outperforms state-of-the-art microwave imaging methods and ML algorithms for tumor detection, localization, and characterization. The proposed framework gives promising results using our BMI system's measured reflection coefficients ($S_{11}$). This work shows the potential advantages of applying cutting-edge deep learning algorithms in practical BMI systems.

Owing to ample potential and versatile capabilities of artificial intelligence to solve intricate scientific problems, two regression-based artificial neural network (ANN) models are proposed to design and optimize nano-structured meta-atoms. The proposed forward predicting ANN depicts that considering the complete structural and material information of the cylindrical nano-pillar meta-atoms could predict the corresponding electromagnetic (EM) response (amplitude and phase of transmission) with a mean squared error (MSE) as low as$\mathbf{2.1}\times \mathbf{10}^{-\mathbf{3}}$. Thus, it replaces the conventional EM simulations performed using high-end commercial software's, while significantly saving time and computational resources. Inverse design deep-learning model is also presented, which is connected with the pre-trained forward model and trained in a tandem architecture to provide an optimum set of dimensions and material, given the target response as its input. Furthermore, a comparative study regarding the number of hidden layers of the ANN and the amount of training dataset size is performed for the proposed forward and tandem inverse models to analyze the effect of considering extra underlying physics related information, i.e., wavelength regime and the EM spectral information. This study reveals that considering the extra information can lead to a significant reduction in the obtained MSE. Specifically, the proposed model could achieve a decent MSE even with a smaller amount of training dataset. Hence, the use of artificial intelligence models significantly reduces the training time and computational complexity of the proposed solution.

Future communication systems are expected to employ Reconfigurable intelligent surfaces (RIS) for real-time manipulation of channel to achieve unprecedented efficiency and quality of service (QoS) improvement. Here, we have designed a practical RIS-enabled communication setup to demonstrate beam steering and multi-beam forming in near-to far-field trials. The design of RIS as a component of wireless communication system has many variables that dictate path loss compensation capability of RIS. We investigate RIS path loss compensation by varying RIS size with point source and plane wave source using a 1-bit RIS of size$27\times 28$unit-cells. It is observed that RIS size has less significance compared to phase quantization, in the near field while the effect of RIS size is dominant in the far field. The reported results provide useful insights for design of RIS-enabled wireless communication systems.

Reconfigurable Intelligent Surfaces (RIS), which comprise of large number of unit cells (meta-atoms), reflect the incoming wave according to desired radiation patterns. As the number of unit cells increase, complex radiation patterns can be generated. Similarly, a unit cell allowing more phase control and larger phase difference helps in the generation of complex radiation patterns at the surface level. However, the control circuit complexity and energy requirements also increase. In many practical applications, only a handful of radiation patterns may suffice. Additionally, the overall problem of finding the appropriate unit cell control state to generate any desired radiation patterns has combinatorial complexity. In this paper, we propose a benchmarking framework and suitable performance metrics that enable us to determine and compare the capabilities of RISs made from different unit cells. The proposed framework is numerically tested on three 40x40 RISs made from optimized and unoptimized unit cells of various resolutions reported in the literature. While the performance of RIS made from 1-bit unoptimized unit cell was overall poor, it was able to successfully generate some simple but useful benchmarking patterns. Thus, our framework provides a mechanism to identify the best candidate unit cell for a given set of requirements. The proposed framework has a potential to revolutionize future research and development on unit cell and RIS design.