Performance comparison of machine learning driven approaches for classification of complex noises in quick response code images.

Quick response codes (QRCs) are found on many consumer products and often encode security information. However, information retrieval at receiving end may become challenging due to the degraded clarity of QRC images. This degradation may occur because of the transmission of digital images over noise channels or limited printing technology. Although the ability to reduce noises is critical, it is just as important to define the type and quantity of noises present in QRC images. Therefore, this study proposed a simple deep learning-based architecture to segregate the image as either an original (normal) QRC or a noisy QRC and identifies the noise type present in the image. For this, the study is divided into two stages. Firstly, it generated a QRC image dataset of 80,000 images by introducing seven different noises (speckle, salt & pepper, Poisson, pepper, localvar, salt, and Gaussian) to the original QRC images. Secondly, the generated dataset is fed to train the proposed convolutional neural network (CNN)-based model, seventeen pre-trained deep learning models, and two classical machine learning algorithms (Naïve Bayes (NB) and Decision Tree (DT)). XceptionNet attained the highest accuracy (87.48%) and kappa (85.7%). However, it is worth noting that the proposed CNN network with few layers competes with the state-of-the-art models and attained near to best accuracy (86.75%). Furthermore, detailed analysis shows that all models failed to classify images having Gaussian and Localvar noises correctly.

A Conceptual Multi-Layer Framework for the Detection of Nighttime Pedestrian in Autonomous Vehicles Using Deep Reinforcement Learning.

The major challenge faced by autonomous vehicles today is driving through busy roads without getting into an accident, especially with a pedestrian. To avoid collision with pedestrians, the vehicle requires the ability to communicate with a pedestrian to understand their actions. The most challenging task in research on computer vision is to detect pedestrian activities, especially at nighttime. The Advanced Driver-Assistance Systems (ADAS) has been developed for driving and parking support for vehicles to visualize sense, send and receive information from the environment but it lacks to detect nighttime pedestrian actions. This article proposes a framework based on Deep Reinforcement Learning (DRL) using Scale Invariant Faster Region-based Convolutional Neural Networks (SIFRCNN) technologies to efficiently detect pedestrian operations through which the vehicle, as agents train themselves from the environment and are forced to maximize the reward. The SIFRCNN has reduced the running time of detecting pedestrian operations from road images by incorporating Region Proposal Network (RPN) computation. Furthermore, we have used Reinforcement Learning (RL) for optimizing the Q-values and training itself to maximize the reward after getting the state from the SIFRCNN. In addition, the latest incarnation of SIFRCNN achieves near-real-time object detection from road images. The proposed SIFRCNN has been tested on KAIST, City Person, and Caltech datasets. The experimental results show an average improvement of 2.3% miss rate of pedestrian detection at nighttime compared to the other CNN-based pedestrian detectors.

Screening Lung Diseases Using Cascaded Feature Generation and Selection Strategies.

The global pandemic COVID-19 is still a cause of a health emergency in several parts of the world. Apart from standard testing techniques to identify positive cases, auxiliary tools based on artificial intelligence can help with the identification and containment of the disease. The need for the development of alternative smart diagnostic tools to combat the COVID-19 pandemic has become more urgent. In this study, a smart auxiliary framework based on machine learning (ML) is proposed; it can help medical practitioners in the identification of COVID-19-affected patients, among others with pneumonia and healthy individuals, and can help in monitoring the status of COVID-19 cases using X-ray images. We investigated the application of transfer-learning (TL) networks and various feature-selection techniques for improving the classification accuracy of ML classifiers. Three different TL networks were tested to generate relevant features from images; these TL networks include AlexNet, ResNet101, and SqueezeNet. The generated relevant features were further refined by applying feature-selection methods that include iterative neighborhood component analysis (iNCA), iterative chi-square (iChi2), and iterative maximum relevance-minimum redundancy (iMRMR). Finally, classification was performed using convolutional neural network (CNN), linear discriminant analysis (LDA), and support vector machine (SVM) classifiers. Moreover, the study exploited stationary wavelet (SW) transform to handle the overfitting problem by decomposing each image in the training set up to three levels. Furthermore, it enhanced the dataset, using various operations as data-augmentation techniques, including random rotation, translation, and shear operations. The analysis revealed that the combination of AlexNet, ResNet101, SqueezeNet, iChi2, and SVM was very effective in the classification of X-ray images, producing a classification accuracy of 99.2%. Similarly, AlexNet, ResNet101, and SqueezeNet, along with iChi2 and the proposed CNN network, yielded 99.0% accuracy. The results showed that the cascaded feature generator and selection strategies significantly affected the performance accuracy of the classifier.

Towards Environmental RF-EMF Assessment of mmWave High-Node Density Complex Heterogeneous Environments.

The densification of multiple wireless communication systems that coexist nowadays, as well as the 5G new generation cellular systems advent towards the millimeter wave (mmWave) frequency range, give rise to complex context-aware scenarios with high-node density heterogeneous networks. In this work, a radiofrequency electromagnetic field (RF-EMF) exposure assessment from an empirical and modeling approach for a large, complex indoor setting with high node density and traffic is presented. For that purpose, an intensive and comprehensive in-depth RF-EMF E-field characterization study is provided in a public library study case, considering dense personal mobile communications (5G FR2 @28 GHz) and wireless 802.11ay (@60 GHz) data access services on the mmWave frequency range. By means of an enhanced in-house deterministic 3D ray launching (3D-RL) simulation tool for RF-EMF exposure assessment, different complex heterogenous scenarios of high complexity are assessed in realistic operation conditions, considering different user distributions and densities. The use of directive antennas and MIMO beamforming techniques, as well as all the corresponding features in terms of radio wave propagation, such as the body shielding effect, dispersive material properties of obstacles, the impact of the distribution of scatterers and the associated electromagnetic propagation phenomena, are considered for simulation. Discussion regarding the contribution and impact of the coexistence of multiple heterogeneous networks and services is presented, verifying compliance with the current established international regulation limits with exposure levels far below the aforementioned limits. Finally, the proposed simulation technique is validated with a complete empirical campaign of measurements, showing good agreement. In consequence, the obtained datasets and simulation estimations, along with the proposed RF-EMF simulation tool, could be a reference approach for the design, deployment and exposure assessment of the current and future wireless communication technologies on the mmWave spectrum, where massive high-node density heterogeneous networks are expected.

Deterministic and Empirical Approach for Millimeter-Wave Complex Outdoor Smart Parking Solution Deployments.

The characterization of different vegetation/vehicle densities and their corresponding effects on large-scale channel parameters such as path loss can provide important information during the deployment of wireless communications systems under outdoor conditions. In this work, a deterministic analysis based on ray-launching (RL) simulation and empirical measurements for vehicle-to-infrastructure (V2I) communications for outdoor parking environments and smart parking solutions is presented. The study was carried out at a frequency of 28 GHz using directional antennas, with the transmitter raised above ground level under realistic use case conditions. Different radio channel impairments were weighed in, considering the progressive effect of first, the density of an incremental obstructed barrier of trees, and the effect of different parked vehicle densities within the parking lot. On the basis of these scenarios, large-scale parameters and temporal dispersion characteristics were obtained, and the effect of vegetation/vehicle density changes was assessed. The characterization of propagation impairments that different vegetation/vehicle densities can impose onto the wireless radio channel in the millimeter frequency range was performed. Finally, the results obtained in this research can aid communication deployment in outdoor parking conditions.

Non-Invasive Real-Time Monitoring of Glucose Level Using Novel Microwave Biosensor Based on Triple-Pole CSRR.

Planar microwave sensors are considered an attractive choice to noninvasively probe the dielectric attributes of biological tissues due to their low cost, simple fabrication, miniature scale, and minimum risk to human health. This paper develops and measures a novel microwave biosensor for non-invasive real-time monitoring of glucose level. The design comprises a rectangular plexiglass channel integrated on a triple-pole complementary split ring resonator (TP-CSRR). The proposed sensor operates in the centimeter-wave range 1-6 GHz and is manufactured using PCB on top of an FR4 dielectric substrate. The sensor elements are excited via a coupled microstrip transmission-line etched on the bottom side of the substrate. The integrated CSRR-based sensor is used as a near-field probe to non-invasively monitor the glucose level changes in the blood mimicking solutions of clinically relevant concentrations to Type-2 normal diabetes (70-120 mg/dL), by recording the frequency response of the harmonic reflection and transmission resonances. This indicates the sensor's capability of detecting small variations in the dielectric properties of the blood samples that are responsive to the electromagnetic fields. The proposed sensor is verified through practical measurements of the fabricated design. Experimental results obtained using a Vector Network Analyzer (VNA) demonstrate a sensitivity performance of about 6.2 dB/(mg/ml) for the developed triple-pole sensor that significantly outperforms the conventional single-pole and other proposed sensors in the literature in terms of the resonance amplitude resolution.

Low-cost portable microwave sensor for non-invasive monitoring of blood glucose level: novel design utilizing a four-cell CSRR hexagonal configuration.

This article presents a novel design of portable planar microwave sensor for fast, accurate, and non-invasive monitoring of the blood glucose level as an effective technique for diabetes control and prevention. The proposed sensor design incorporates four cells of hexagonal-shaped complementary split ring resonators (CSRRs), arranged in a honey-cell configuration, and fabricated on a thin sheet of an FR4 dielectric substrate.The CSRR sensing elements are coupled via a planar microstrip-line to a radar board operating in the ISM band 2.4-2.5 GHz. The integrated sensor shows an impressive detection capability and a remarkable sensitivity of blood glucose levels (BGLs). The superior detection capability is attributed to the enhanced design of the CSRR sensing elements that expose the glucose samples to an intense interaction with the electromagnetic fields highly concentrated around the sensing region at the induced resonances. This feature enables the developed sensor to detect extremely delicate variations in the electromagnetic properties that characterize the varying-level glucose samples. The desired performance of the fabricated sensor is practically validated through in-vitro measurements using a convenient setup of Vector Network Analyzer (VNA) that records notable traces of frequency-shift responses when the sensor is loaded with samples of 70-120 mg/dL glucose concentrations. This is also demonstrated in the radar-driven prototype where the raw data collected at the radar receiving channel shows obvious patterns that reflect glucose-level variations. Furthermore, the differences in the sensor responses for tested glucose samples are quantified by applying the Principal Component Analysis (PCA) machine learning algorithm. The proposed sensor, beside its impressive detection capability of the diabetes-spectrum glucose levels, has several other favorable attributes including compact size, simple fabrication, affordable cost, non-ionizing nature, and minimum health risk or impact. Such attractive features promote the proposed sensor as a possible candidate for non-invasive glucose levels monitoring for diabetes as evidenced by the preliminary results from a proof-of-concept in-vivo experiment of tracking an individual's BGL by placing his fingertip onto the sensor. The presented system is a developmental platform towards radar-driven wearable continuous BGL monitors.

End-to-End Noise Model for Intra-Body Terahertz Nanoscale Communication.

In vivo wireless nanosensor networks (iWNSNs) are paving the way toward transformative healthcare solutions. These networks are expected to enable a plethora of applications, including drug-delivery, bio-sensing, and health monitoring. With the development of miniature plasmonic signal sources, antennas, and detectors, wireless communications among intrabody nanodevices will expectedly be enabled in the terahertz (THz) frequency band (0.1-10 THz). Several propagation models were recently developed to analyze and assess the feasibility of intra-body electromagnetic (EM) nanoscale communication. The emphasis of these works has mainly been on understanding the propagation of EM signals through biological media, with limited focus on the intra-body noise sources and their impact on the system performance. In this paper, a stochastic noise model for iWNSNs is presented in which the individual noise sources that impact intra-body systems operating in the THz frequency band are analyzed. The overall noise contributions are composed of three distinctive constituents, namely, Johnson-Nyquist noise, black-body noise, and Doppler-shift-induced noise. The probability distribution of each noise component is derived, and a comprehensive analytical approach is developed to obtain the total noise power-spectral density. The model is further validated via 2-D particle simulations as the active transport motion of particles is conveyed in the presented framework. The developed models serve as the starting point for a rigorous end-to-end channel model that enables the proper estimation of data rate, channel capacity, and other key parameters, which are all factors of the noise environment.

Photothermal Modeling and Analysis of Intrabody Terahertz Nanoscale Communication.

Wireless communication among implanted nano-biosensors will enable transformative smart health monitoring and diagnosis systems. The state of the art of nano-electronics and nano-photonics points to the terahertz (THz) band (0.1-10 THz) and optical frequency bands (infrared, 30-400 THz, and visible, 400-750 THz) as the frequency range for communication among nano-biosensors. Recently, several propagation models have been developed to study and assess the feasibility of intra-body electromagnetic (EM) nanoscale communication. These works have been mainly focused on understanding the propagation of EM signals through biological media, but do not capture the resulting photothermal effects and their impact both on the communication as well as on the body itself. In this paper, a novel thermal noise model for intra-body communication based on the diffusive heat flow theory is developed. In particular, an analytical framework is presented to illustrate how molecules in the human body absorb energy from EM fields and subsequently release this energy as heat to their immediate surroundings. As a result, a change in temperature is witnessed from which the molecular absorption noise can be computed. Such analysis has a dual benefit from a health as well as a communication perspective. For the medical community, the presented methodology allows the quantization of the temperature increase resulting from THz frequency absorption. For communication purposes, the complete understanding of the intra-body medium opens the door toward developing modulations suited for the capabilities of nano-machines and tailored to the peculiarities of the THz band channel as well as the optical window.

Terahertz Channel Model and Link Budget Analysis for Intrabody Nanoscale Communication.

Nanosized devices operating inside the human body open up new prospects in the healthcare domain. Invivo wireless nanosensor networks (iWNSNs) will result in a plethora of applications ranging from intrabody health-monitoring to drug-delivery systems. With the development of miniature plasmonic signal sources, antennas, and detectors, wireless communications among intrabody nanodevices will expectedly be enabled at both the terahertz band (0.1-10 THz) as well as optical frequencies (400-750 THz). This result motivates the analysis of the phenomena affecting the propagation of electromagnetic signals inside the human body. In this paper, a rigorous channel model for intrabody communication in iWNSNs is developed. The total path loss is computed by taking into account the combined effect of the spreading of the propagating wave, molecular absorption from human tissues, as well as scattering from both small and large body particles. The analytical results are validated by means of electromagnetic wave propagation simulations. Moreover, this paper provides the first framework necessitated for conducting link budget analysis between nanodevices operating within the human body. This analysis is performed by taking into account the transmitter power, medium path loss, and receiver sensitivity, where both the THz and photonic devices are considered. The overall attenuation model of intrabody THz and optical frequency propagation facilitates the accurate design and practical deployment of iWNSNs.