The use of deep learning (DL) for the analysis and diagnosis of biomedical and health care problems has received unprecedented attention in the last decade. The technique has recorded a number of achievements for unearthing meaningful features and accomplishing tasks that were hitherto difficult to solve by other methods and human experts. Currently, biological and medical devices, treatment, and applications are capable of generating large volumes of data in the form of images, sounds, text, graphs, and signals creating the concept of big data. The innovation of DL is a developing trend in the wake of big data for data representation and analysis. DL is a type of machine learning algorithm that has deeper (or more) hidden layers of similar function cascaded into the network and has the capability to make meaning from medical big data. Current transformation drivers to achieve personalized health care delivery will be possible with the use of mobile health (mHealth). DL can provide the analysis for the deluge of data generated from mHealth apps. This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL. We highlight the implementation of DL in health care, which we categorize into biological system, electronic health record, medical image, and physiological signals. In addition, we discuss some inherent challenges of DL affecting biomedical and health domain, as well as prospective research directions that focus on improving health management by promoting the application of physiological signals and modern internet technology.

This paper proposes a low-profile and highly efficient endfire radiating travelling-wave antenna based on spoof surface plasmon polaritons (SSPPs) transmission line. The aperture is approximately $0.32\lambda_{0}\times 0.01\lambda_{0}$ where $\lambda_{0}$ is the space wavelength at the operational frequency 8 GHz. This antenna generates near-endfire radiation beams within 7.5-8.5 GHz. The maximum gain and total efficiency reaches 9.2 dBi and 96%, respectively. Measurement results are finally given to validate the proposed SSPPs antenna.

A Goubau-line leaky-wave antenna (LWA) with a large scanning angle is presented in this letter. In contrast to the conventional Goubau-line leaky wave with a small scanning angle range, this letter employed a periodically bending Goubau line, which not only brings in a periodic perturbation for leaky-wave radiation, but also enhances the scanning range due to the increased delay for each line element. The simulation and experimental results show that the proposed LWA provides 90% radiation efficiency and 7-10 dBi radiation gain from backfire to endfire through broadside as frequency changes. The proposed antenna features good radiation performance and has a compact and low-profile configuration.

This paper proposes a method of using a highly efficient spoof surface plasmon polariton (SSPP) endfire sensor for monitoring of aqueous glucose solutions and on-body glucose measurements. Occupying an area of around (52mm x 24mm), the proposed sensor radiates an endfire beam into a glucose water solution with a substantially reduced effective aperture. At the CPW port of the sensor, a pair of triangular ground planes was added to suppress the sidelobes, which have been proven to be counter-productive in glucose sensing. The slow wave nature of the proposed SSPP endfire sensor has further advantageously enabled the glucose concentrations to be measured with an increased sensitivity. The guiding body of the sensor was designed to simulate an electromagnetic beam propagating in a dense dielectric medium with a group velocity comparable to the phase velocity of light propagating in a glucose solution. Consistent with the results of our analysis, the experimental results of this work revealed that the gradual transition of slow electromagnetic wave from the SSPP endfire sensor to the glucose water solution has successfully enabled the glucose concentrations of a solution to be measured and displayed in the form of highly observable resonant frequency shifts in S11 parameters. The proposed design has achieved a high sensitivity of 150 MHz/mgmL-1 during onbody measurements.

Graphene-based materials have gained a lot of scientific interest in the research era of modern technology, which can be quite flexible. Graphene has become popular as a potential material for the manufacture of a wide range of technologies due to its remarkable electrical, mechanical, and optical traits. Due to these excellent characteristics, the derivatives of graphene can be functionalized in various applications including environmental, medical, electronic, defence applications, and many more. In this review paper, we discussed the different synthesis methods for the extraction of graphene and its derivatives. The different traits of graphene and its derivatives such as structural, mechanical, and optical were also discussed. An extensive literature review on the application of graphene-based composites is presented in this work. We also outlined graphene’s potential in the realm of environmental purification through different techniques such as filtration, adsorption, and photocatalysis. Lastly, the challenges and opportunities of graphene and its derivatives for advanced environmental applications were reported.

Diabetes is one of the most persistent and common immedicable diseases characterized by elevated levels of blood glucose, rendering the early detection and diagnosis of diabetes utmost important. Irrespective of currently available invasive and minimally invasive techniques, the non-invasive glucose measurement has drawn lot of attentionon in present years, and continues to open up new areas for further research. This review provides a comprehensive overview of the developments over the last decade in the area of non-invasive blood glucose monitoring research, with particular reference given to the use of radio frequency electromagnetic wave (EM) for blood glucose sensing. The majority of the glucose sensors described in this paper have been proven to be reliable by Clarke Error Grid analysis or similar methods but, amid all other known challenges such as reproducibility, specificity and sensitivities, these glucose sensors were based on an expensive vector network analyzer (VNA). Finally, we conclude with a positive note that the non-invasive blood glucose monitoring research is beginning to be acknowledged not only on a global scale but also in applied physics and biomedical fields; however, more research is needed to overcome the challenges related to hardware alternative to a VNA and system integration involving enhancement of specificity and sensitivity.