Search

Automatic speech recognition (ASR) plays a pivotal role in our daily lives, offering utility not only for interacting with machines but also for facilitating communication for individuals with partial or profound hearing impairments. The process involves receiving the speech signal in analog form, followed by various signal processing algorithms to make it compatible with devices of limited capacities, such as cochlear implants (CIs). Unfortunately, these implants, equipped with a finite number of electrodes, often result in speech distortion during synthesis. Despite efforts by researchers to enhance received speech quality using various state-of-the-art signal processing techniques, challenges persist, especially in scenarios involving multiple sources of speech, environmental noise, and other adverse conditions. The advent of new artificial intelligence (AI) methods has ushered in cutting-edge strategies to address the limitations and difficulties associated with traditional signal processing techniques dedicated to CIs. This review aims to comprehensively cover advancements in CI-based ASR and speech enhancement, among other related aspects. The primary objective is to provide a thorough overview of metrics and datasets, exploring the capabilities of AI algorithms in this biomedical field, and summarizing and commenting on the best results obtained. Additionally, the review will delve into potential applications and suggest future directions to bridge existing research gaps in this domain.

The increasing prevalence of non-invasive, portable Electroencephalography (EEG) sensors for neuro-physiological measurements has propelled EEG-based assessments of cognitive load (CL) into the spotlight. In this study, we harnessed the capabilities of a four-channel, wearable EEG device that captured brain activity data during two distinct CL states: Baseline (representing a non-CL, resting state) and the Stroop Test (a CL-inducing state). The primary objective of this study is to estimate the CL index through an innovative approach that employs a hybrid, cluster-based, unsupervised learning technique seamlessly integrated with a 1D Convolutional Neural Network (CNN) architecture tailored for automated feature extraction, rather than conventional supervised algorithms, which facilitated in the acquisition of latent complex patterns without the need for manual categorization. The approach was rigorously evaluated using stratified cross-validation, with several assessment criteria assessing both its quality and predictive capability to estimate the CL index. The results obtained (e.g., homogeneity score of 0.7, adjusted rand index of 0.78, silhouette coefficient of 0.5, and an accuracy rate of 93.2%) demonstrate that our module exhibits superiority over supervised approaches. These results are indicative that the adoption of multi-channel wearable EEG devices may facilitate real-time CL estimation, minimizing the need for extensive human intervention, and reducing potential bias, paving the way for more objective and efficient CL assessments.

Brain magnetic resonance imaging (MRI) offers intricate soft tissue contrasts that are essential for diagnosing diseases and conducting neuroscience research. At 7 Tesla (7T) magnetic field intensity, MRI enables increased resolution, enhanced tissue contrast, and improved SNR, compared to MRI collected from the commonly employed 3 Tesla (3T) MRI scanners. However, the exorbitant expenses associated with 7T MRI scanners hinder their broad use in research and clinical facilities. Efforts are underway to develop algorithms that can generate 7T MRI from 3T MRI to achieve better image quality without the need for 7T MRI machines. In this study, we have adopted a cycle consistent generative adversarial network (CycleGAN)-based approach for 3T MRI to 7T MRI translation, and vice versa, using a recently published dataset of paired T1-weighted MR images collected at 3T and 7T from a total of ten subjects. Various CycleGAN architectures were experimented with and compared on this dataset. The best performing CycleGAN architecture successfully produced the reconstructed images with a high level of accuracy based on different quantitative and qualitative evaluation criteria. Utilizing a post-processing technique, the best performing model generated 7T MRI from 3T MRI with a structural similarity index measure (SSIM) of 83.80%, peak SNR (PSNR) of 26.25, normalized mean squared error (NMSE) of 0.0088 and normalized mean absolute error (NMAE) of 0.0630. Utilizing CycleGAN to convert images from 3T to 7T MRI has shown a substantial improvement in MRI resolution, setting the stage for advancements in more informative and precise diagnostic imaging.

Mulberry leaves serve as the primary food source for Bombyx mori silkworms, crucial for silk thread production. However, mulberry trees are highly susceptible to diseases, spreading rapidly and causing significant losses. Manual disease identification across large farms is arduous and time-consuming. Leveraging computer vision for early disease detection and classification can mitigate up to 90% of production losses. This study collected leaves from two regions of Bangladesh, categorized as healthy, leaf rust-affected, and leaf spot-affected. With a total of 1091 images, split into training (764), testing (218), and validation (109) sets for 5-fold cross-validation, preprocessing and augmentation yielded 6,000 images, including synthetics. This study compares ResNet50, VGG19, and MobileNetV3Small on a specific task following architecture modifications. Four convolutional layers with different output channels (512, 128, 64, and 32) were added to baseline models. We assessed how these architectural changes affected model correctness, computing efficiency, and convergence rates. Comparing three pretrained convolutional neural networks (CNNs) - MobileNetV3Small, ResNet50, and VGG19 - augmented with four additional layers, the modified MobileNetV3Small excelled in precision, recall, F1-score, and accuracy, achieving notable results of 97.0%, 96.4%, 96.4%, and 96.4%, respectively, across cross-validation folds. An efficient smartphone application employing the proposed model for mulberry leaf disease recognition was developed. Overall, the model outperformed existing State of the Art (SOTA) approaches, showcasing its effectiveness in disease identification. The interpretative Grad-CAM visualization images match sericulture specialists’ assessments, validating the model’s predictions. These results imply that, this eXplainable AI (XAI) approach with a modified deep learning architecture can appropriately classify mulberry leaves.

Patients with hyperglycemia require routine glucose monitoring to effectively treat their condition. We have developed a lightweight wristband device to capture Photoplethysmography (PPG) signals. We collected PPG signals, demographic information, and blood pressure data from 139 diabetic (49.65%) and non-diabetic (50.35%) subjects. Blood glucose was estimated, and diabetic severity (normal, warning, and dangerous) was stratified using Mel frequency cepstral coefficients, time, frequency, and statistical features from PPG and their derivative signals along with physiological parameters. Bagged Ensemble Trees outperform other algorithms in estimating blood glucose level with a correlation coefficient of 0.90. The proposed model’s prediction was all in Zone A and B in the Clarke Error Grid analysis. The predictions are thus clinically acceptable. Furthermore, K-nearest neighbor model classified the severity levels with an accuracy of 98.12%. Furthermore, the proposed models were deployed in Amazon Web Server. The wristband is connected to an Android mobile application to collect real-time data and update the estimated glucose and diabetic severity every 10-seconds, which will allow the users to gain better control of their diabetic health.

The emergence of COVID-19 resulted in significant shortages of mechanical ventilators globally. This prompted investigations into developing new, cost-effective methods for producing ventilators. Different types of ventilators, such as positive pressure ventilators (PPVs), conventional negative pressure ventilators (NPVs), and biphasic cuirass ventilators (BCVs), were considered. However, PPVs were found to pose health risks and were expensive to manufacture. Thus, this study introduces ExoventQ, an innovative respiratory support device inspired by traditional NPV designs. ExoventQ was meticulously designed, simulated, implemented, and tested in two modes: continuous negative extrathoracic pressure (CNEP) and cyclic negative pressure ventilation (CNPV). It consists of three main components: a pressure vessel, a pumping system, and a control panel. Each component was designed with attention to pressure distribution, material, safety, cost, and portability. Through ANSYS stress analysis, ExoventQ was developed with a squircle-shaped polycarbonate vessel capable of withstanding up to 50 millibar (mbar) of vacuum pressure. This design also prevents airway tilting when placed on its side, providing more comfort for the patient. Pressure regulation inside the vessel is achieved through a bypass butterfly valve controlled by a servo motor. The user interface is implemented on a Raspberry Pi touchscreen, enabling input through rotating knobs and displaying output for monitoring. Safety measures include audio and visual alarms, along with a power switch that halts ventilation if the vacuum in the vessel drops below 40 mbar. The successful design and implementation of ExoventQ have the potential to enable mass production of safe and affordable NPVs to address pulmonary complications.

Virtual reality (VR) is the employment of computer devices to simulate real or imaginary environments. Conventional user interfaces stress the usage of screen displays to interact with the developed environment. The prospect of VR enables the user to be virtually inside the environment. Cave automatic virtual reality environment (CAVE) is one kind of room-shaped VR technology that displays the environment on its walls. We observe some common limitations in the existing CAVE technology, such as fixed space requirements, and the difficulty in moving it. In this paper, we present a novel mobile-CAVE system that uses light-weighted materials and portable powered devices. It solves the limitation of re-using the allocated space by packing it and the ability to move it easily. We have assessed our technology by performing usability analysis, power consumption, and mobility experimental study. The profound experiments demonstrated the efficiency of the proposed technology in comparison with the former CAVE system.

Chest surface vibrations induced by cardiac activities can provide valuable insights into various heart conditions. Seismocardiogram (SCG) and Gyrocardiogram (GCG) signals, collectively referred to as Mechanocardiograms (MCG) and collected using a chest-mounted accelerometer and gyroscope, respectively, have the potential to serve as an effective alternative to Electrocardiograms (ECG) for continuous cardiac monitoring. In many cases, both modalities (MCG and ECG) can be used in tandem to monitor cardiac functions in both healthy subjects and Intensive Care Unit (ICU) patients. Direct acquisition of ECGs can be challenging in certain scenarios, such as with wearable devices, or due to issues with disconnections arising from loose contact surfaces or gel corrosion during long-term usage. ECG considered the gold standard for heart monitoring, is essential for a comprehensive assessment of cardiac parameters and patient health. MCGs have the potential to reliably estimate ECGs and can replace direct ECG acquisition procedures in such cases. In this study, we introduce M2ECG, a 1D-segmentation-based approach for translating ECG signals from the corresponding MCG signals acquired by an Inertial Measurement Unit (IMU) attached to the chest wall. Using the proposed SA-UNet, we achieved an average Pearson Correlation Coefficient (PCC) of 81.76% on a subject-independent test set. We also compared the estimated heart rates (HR) from the reconstructed ECGs to the ground truth ECGs to validate our model’s performance. The overall HR correlation achieved on the subject-independent test set was around 94.167%. The highest correlation of the HR and HRV calculated from the translated and the ground truth ECGs were around 99.073% and 96.289%, respectively for the best test case. The strong correlation observed in cardiac parameters (HR, HRV) underscores the effectiveness of MCG, suggesting its potential use for continuous monitoring of cardiac patients.

In response to the growing waste problem caused by industrialization and modernization, the need for an automated waste sorting and recycling system for sustainable waste management has become ever more pressing. Deep learning has made significant advancements in image classification, making it ideally suited for waste sorting applications. This application depends on the development of a suitable deep learning model capable of accurately categorizing various categories of waste. In this study, we present RWC-Net (recyclable waste classification network), a novel deep learning model designed for the classification of six distinct waste categories using the TrashNet dataset of 2,527 images of waste. The performance of our model is subjected to intensive quantitative and qualitative evaluations and is compared to various state-of-art waste classification techniques. The proposed model outperformed several state-of-the-art models by obtaining a remarkable overall accuracy rate of 95.01 percent. In addition, it receives high F1-scores for each of the six waste categories: 97.24% for cardboard, 96.18% for glass, 94% for metal, 95.73% for paper, 93.67% for plastic, and 88.55% for litter. The reliability of the model is demonstrated qualitatively through the saliency maps generated by Score-CAM (class activation mapping) model, which provide visual insights into its performance across various waste categories. These results highlight the model’s accuracy and demonstrate its potential as an effective automated waste classification and management solution.

Rotating machines require bearings to operate smoothly. However, wear, misalignment, and poor lubrication can degrade bearings over time. Fault diagnosis models identify and classify bearing faults. A fault diagnosis model trained in a specific working condition may not perform well in different working conditions. Real-world datasets are mixed with various work environment conditions; therefore, validating a model using different working conditions datasets is necessary. In this study, raw vibrational accelerometer data of variable working conditions is preprocessed using the window length and stride method to generate a data format suitable for evaluating the proposed model. This model employs the Transfer learning-based VGG16 model as the feature extractor and random forest as the classifier, and it has proven to be highly effective. This proposed fault diagnosis model adapts to different work environments and enhances fault classification at variable working conditions. The performance of the proposed model is evaluated using various metrics such as confusion matrix heatmap, t-SNE plot, precision-recall curve and learning curve. Results obtained from these metrics indicate that this model performs well compared to others. The overall accuracy of the model is 99.90%, and both the training and testing of this model are fast. It is evident from the learning curve evaluation that this model is free from over- or under-fitting issues. Overall, this model is reliable and suitable for classifying bearing faults at different working conditions and can be useable for real world purposes.

Tomatoes are the most widely grown crop in the world, and they may be found in a variety of forms in every kitchen, regardless of cuisine. It is, after potato and sweet potato, the most widely farmed crop on the planet. Cotton is another essential cash crop because most farmers grow it in huge quantities. However, many diseases reduce the quality and quantity of tomato and cotton crops, resulting in a significant loss in production and productivity. It is critical to detect these disorders at an early stage of diagnosis. The purpose of this work is to categorize 14 classes for both cotton and tomato crops, with 12 diseased classes and two healthy classes using a deep learning-based lightweight 2D CNN architecture and to implement the model in an android application named “Plant Disease Classifier” for smartphone-assisted plant disease diagnosis system, the results of the experiments reveal that the proposed model outperforms the pre-trained models VGG16, VGG19 and InceptionV3 despite having fewer parameters. With slightly larger parameters than MobileNet and MobileNetV2, proposed model also attains considerably larger accuracy than these models. The classification accuracy varies between 57% and 92% for these models, and the proposed model’s average accuracy is 97.36%. Also, the precision, recall, F1-score of the proposed model is 97 % and Area Under Curve (AUC) score of the model is 99.9% which is an indicator of the very good performance of the model. Class activation maps were shown using the Gradient Weighted Class Activation Mapping (Grad-CAM) technique to visually explain the disease detected by the proposed model, and a heatmap was produced to indicate the responsible region for classification. The app works very impressively and classified the correct disease in a shorter period of time of about 4.84 ms due to the lightweight nature of the model.

Congenital heart defects (CHDs) are a leading cause of death in infants under 1 year of age. Prenatal intervention can reduce the risk of postnatal serious CHD patients, but current diagnosis is based on qualitative criteria, which can lead to variability in diagnosis between clinicians. Objectives: To detect morphological and temporal changes in cardiac ultrasound (US) videos of fetuses with hypoplastic left heart syndrome (HLHS) using deep learning models. A small cohort of 9 healthy and 13 HLHS patients were enrolled, and ultrasound videos at three gestational time points were collected. The videos were preprocessed and segmented to cardiac cycle videos, and five different deep learning CNN-LSTM models were trained (MobileNetv2, ResNet18, ResNet50, DenseNet121, and GoogleNet). The top-performing three models were used to develop a novel stacking CNN-LSTM model, which was trained using five-fold cross-validation to classify HLHS and healthy patients. The stacking CNN-LSTM model outperformed other pre-trained CNN-LSTM models with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for video-wise classification, and with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for subject-wise classification using ultrasound videos. This study demonstrates the potential of using deep learning models to classify CHD prenatal patients using ultrasound videos, which can aid in the objective assessment of the disease in a clinical setting.

To determine head pose within an MR scanner using measurements of gradient-induced voltage from a multiple coil. A practical implementation of this approach would involve measuring the position-sensitive voltages induced by the imaging gradients rather than additional gradient pulses. This would speed up the model formation phase and increase the temporal resolution of position monitoring. We propose a novel method to measure the gradient-induced voltages in a set of five coils to estimate the position and orientations (POS) into MR scanner. A training set of measurements was first made and then Principal Component Analysis (PCA) was applied to the POS data estimated by using Statistical Parametric Mapping (SPM8), and the principal components were collected into a design matrix. Experimental data were collected and then the coefficients derived from the training set were used to estimate the POS changes and the results compared to movement parameters found using image co-registration. The changes in POS estimated from SPM8 co-registration and from the measured voltages for the phantom and the subject. The differences in the positions were estimated by using SPM8 and the model relating the change in induced voltages to position. The range and root-mean-square (RMS) amplitude of these differences for the phantom/subject data. The results suggest that it is possible to estimate the position and orientation with 0.22mm and 0.24° root-mean-square error using this set-up. The new approach could be used for prospective or retrospective motion correction.

Electrooculography, also known as EOG, is a technique that is used to calculate the corneo-retinal standing potential, which is located between the cornea and the retina of the human eye. Applications of EOG include eye disease diagnosis and eye movement tracking. There has been various research on reading activity detection from EOG signals in controlled laboratory settings. However, determining reading behaviours from data collected from real-world environments remains a challenging problem. Detecting reading in practical scenarios can lead us to track our daily reading activity, thereby improving our learning experience and even workplace productivity. Tracking regular reading behaviour can also lead to further research in cognitive psychology, literacy development, reading motivation, and reading comprehension. In this study, we investigated an electrooculogram dataset that was collected on the field from 10 users who were engaged in their daily activities on two separate days. We propose a pipeline combining the statistical features with deep learning features from pre-trained ImageNet models. To detect the fine-grained reading activities, we adopted a nested classification approach. Initially, we differentiate between reading and not reading and then we employ an additional classification step to discriminate among three distinct types of reading activities. With our pipeline, we could achieve 66.56% accuracy in detecting the reading activities whereas the original dataset publication showed a baseline performance of only 32%.

Physiological signal measurement and processing are increasingly becoming popular in the ambulatory setting as the hospital-centric treatment is moving towards wearable and ubiquitous monitoring. Most of the physiological signals are highly susceptible to various types of noises, especially movement artifacts. The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals are no exception to motion artifacts, which become prominent in the ambulatory setting. Since successful detection of various neurological disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove motion artifacts from these two signal modalities using reliable and robust methods. This paper proposes three novel multiresolution analysis techniques: i) Variational mode decomposition (VMD), ii) VMD in combination with principal component analysis (VMD-PCA), and iii) VMD in combination with canonical correlation analysis (VMD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these novel techniques is validated by computing the difference in the signal to noise ratio ( $\Delta SNR$ ) and percentage reduction in motion artifacts ( $\eta$ ). Among the three proposed novel methods, VMD-CCA decomposed with 15 intrinsic mode functions (IMFs) has shown the best denoising performance for EEG signals producing an average $\Delta SNR$ and $\eta $ values of 23.81 dB and 57.01%, respectively for all 23 EEG recordings. On the other hand, for the available 16 fNIRS recordings, VMD-CCA decomposed with 10 IMFs produced an average $\Delta SNR$ and $\eta $ values of 15.97 dB and 39.01%, respectively. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

Radiographic images are commonly used to detect aseptic loosening of the hip implant in patients with total hip replacement (THR) surgeries. These techniques of manual assessment by medical professionals can suffer from the drawback of low accuracy, poor inter-observer reliability, and delays due to the unavailability of experienced clinicians. Thus, the paper provides a reliable Deep Convolutional Neural Networks (DCNNs) based novel stacking approach (HipXNet) for detecting loosening of the hip implant using X-ray images. Two major investigations were done in this study. Firstly, the performance of four different state-of-the-art object detection YOLOv5 models was evaluated to detect the implant region from the hip X-ray images. Secondly, the study developed a stacking classifier using three different Convolutional neural networks (CNN) models to classify aseptic hip loosening and compared the performance with eight different state-of-the-art CNN networks. Moreover, one publicly accessible dataset with two sub-sets was created for these two experiments, where 200 hip implant X-ray images were collected and annotated by two expert radiologists for implant detection and 206 hip implant X-ray images were collected for loosening detection. YOLOv5m model outperformed the other variants of YOLOv5 to detect the implant region with the precision, recall, mean average precision (mAP)0.5, mAP0.5–0.95 of 100%, 100%, 100%, and 87.8%, respectively. Densenet201 CNN model outperformed other CNN models with the accuracy, precision, sensitivity, F1 score, and specificity of 94.66%, 94.66%, 94.66%, 94.66%, and 94.5%, respectively while the stacking technique with Random Forest meta learner classifier produced the best performance with the accuracy, precision, sensitivity, F1 score and specificity of 96.11%, 96.42%, 96.42%, 96.42%, and 96.74% respectively for loosening detection. The reliability of the performance was confirmed by the popular Score-CAM visualization. This study can help in the early and fast identification of hip implant loosening with the help of simple X-ray images and computed aided diagnosis.

Diabetic sensorimotor polyneuropathy (DSPN) is an early indicator for non-healing diabetic wounds and diabetic foot ulcers, which account for one of the most common complications of diabetes, leading to increased healthcare cost, decreased quality of life, infections, amputations, and death. Early detection and intelligent classification tools for DSPN can allow correct diagnosis and treatment of painful diabetic neuropathy as well as a timely intervention to prevent foot ulceration, amputation, and other diabetic complications. Hence, to successfully mitigate the prevalence of DSPN, this study aims to depict an intelligent DSPN severity classifier using Adaptive Neuro Fuzzy Inference System (ANFIS). Michigan Neuropathy Screening Instrumentation (MNSI) was considered as the input for identification and stratification of DSPN. Patients have been classified into four classes: Absent, Mild, Moderate, and Severe. The model accuracy was validated with the results from different machine learning algorithms. The Accuracy, sensitivity, and specificity of the ANFIS model are 91.17±1.18%, 92±2.26%, 96.72±0.93%, respectively. The proposed classifier was used to classify the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trial patients and observed that in the first, eighth, and nineteenth EDIC years 18.31%, 39.45%, and 59.14% patients had different levels of DSPN. This study also investigates the changes in muscle activity during gait from three different lower limb muscles (vastus lateralis (VL), tibialis anterior (TA), and gastrocnemius medialis (GM)) electromyography (EMG) of DSPN patients with different severity levels classified by the proposed classifier and observed that VL and GM muscles show an increase in delay for activation peak and decrease in peak magnitude during gait with the progression of DSPN severity. Based on this observation, the ANFIS model was trained using the extracted EMG features for DSPN severity stratification and showed promising results. Our proposed ANFIS based severity classifier using both MNSI variables and EMG features will help health professionals to diagnose and stratify DSPN severity based on both signs and symptoms and electrophysiological changes due to DSPN.

A non-invasive, low-powered, and portable electromagnetic (EM) head imaging system is presented using metamaterial (MTM) loaded compact directional 3D antenna. The antenna consists of two slotted dipole elements with $2\times 3$ and $3\times 3$ finite MTM array elements in top and ground, respectively, and folded parasitic elements that operate within the frequency range of 1.12 GHz to 2.5 GHz. The MTM array elements are optimized to enhance the overall performance regarding antenna bandwidth, realized gain, efficiency, and directionality in both free space and proximity to the head model. The mathematical modelling is also analyzed to justify the integration of MTM unit cells to the top and ground side of the antenna. The impact of MTM on SAR analysis is also performed. A tissue-mimicking 3D head phantom is fabricated and measured to validate the antenna performance. A nine-antenna portable setup is used with the fabricated phantom to measure and collect the scattering parameters that are later analyzed to detect and reconstruct the haemorrhage images by applying the updated IC-CF-DMAS algorithm. The overall performance demonstrates the feasibility of the proposed system as a portable platform to successfully detect, locate and monitor the haemorrhages inside the head in EM imaging system.

In this paper, the triple reflection band split O circled T (SOCT) shape metamaterial resonator is presented based on the transmission line principle. This paper aims to develop a miniature metamaterial resonator that can simultaneously perform as a reflector and a sensing element in the microwave range. Compare to symmetric and asymmetric structures; the reflection feature is mostly available in a typical resonating structure. The primary motivation beyond the presented work is to achieve high reflection with triple resonance points at 5.8 GHz, 6.37 GHz and 6.57 GHz. The proposed structure achieved Double Negative (DNG) features on this particular resonance with a relative permittivity value ranges −2.17 to −6.62 and relative permeability of −0.73 to −4.15. The scattering parameter performance was verified through simulation and measurement for unit cell and $5\times 8$ array structure. An analytical sensing ability for liquid salinity was performed for potential microwave application, which indicates a potential outcome of the proposed structure in microwave sensing applications.

This paper presents the detection of brain tumors through the YOLOv3 deep neural network model in a portable electromagnetic (EM) imaging system. YOLOv3 is a popular object detection model with high accuracy and improved computational speed. Initially, the scattering parameters are collected from the nine-antenna array setup with a tissue-mimicking head phantom, where one antenna acts as a transmitter and the other eight antennas act as receivers. The images are then reconstructed from the post-processed scattering parameters by applying the modified delay-multiply-and-sum algorithm that contains $416\times 416$ pixels. Fifty sample images are collected from the different head regions through the EM imaging system. The images are later augmented to generate a final image data set for training, validation, and testing, where the data set contains 1000 images, including fifty samples with a single and double tumor. 80% of the images are utilized for training the network, whereas 10% are used for validation, and the rest 10% are utilized for testing purposes. The detection performance is investigated with the different image data sets. The achieved detection accuracy and F1 scores are 95.62% and 94.50%, respectively, which ensure better detection accuracy. The training accuracy and validation losses are 96.74% and 9.21%, respectively. The tumor detection with its location in different cases from the testing images is evaluated through YOLOv3, which demonstrates its potential in the portable electromagnetic head imaging system.

Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve very high accuracy but have low anti-spoofing capability. To address these issues, a novel multimodal biometric system combining EEG and keystroke dynamics is proposed in this paper. A dataset was created by acquiring both keystroke dynamics and EEG signals simultaneously from 10 users. Each user participated in 500 trials at 10 different sessions (days) to replicate real-life signal variability. A machine learning classification pipeline is developed using multi-domain feature extraction (time, frequency, time-frequency), feature selection (Gini impurity), classifier design, and score level fusion. Different classifiers were trained, validated, and tested for two different classification experiments – personalized and generalized. For identification and authentication, 99.9% and 99.6% accuracies are achieved, respectively for the Random Forest classifier in 5 fold cross-validation. These results outperform the individual modalities with a significant margin (~5%). We also developed a binary template matching-based algorithm, which gives 93.64% accuracy 6X faster. The proposed method can be considered secure and reliable for any kind of biometric identification and authentication.

Respiratory ailments such as asthma, chronic obstructive pulmonary disease (COPD), pneumonia, and lung cancer are life-threatening. Respiration rate (RR) is a vital indicator of the wellness of a patient. Continuous monitoring of RR can provide early indication and thereby save lives. However, a real-time continuous RR monitoring facility is only available at the intensive care unit (ICU) due to the size and cost of the equipment. Recent researches have proposed Photoplethysmogram (PPG) and/ Electrocardiogram (ECG) signals for RR estimation however, the usage of ECG is limited due to the unavailability of it in wearable devices. Due to the advent of wearable smartwatches with built-in PPG sensors, it is now being considered for continuous monitoring of RR. This paper describes a novel approach for RR estimation using motion artifact correction and machine learning (ML) models with the PPG signal features. Feature selection algorithms were used to reduce computational complexity and the chance of overfitting. The best ML model and the best feature selection algorithm combination were fine-tuned to optimize its performance using hyperparameter optimization. Gaussian Process Regression (GPR) with Fit a Gaussian process regression model (Fitrgp) feature selection algorithm outperformed all other combinations and exhibits a root mean squared error (RMSE), mean absolute error (MAE), and two-standard deviation (2SD) of 2.63, 1.97, and 5.25 breaths per minute, respectively. Patients would be able to track RR at a lower cost and with less inconvenience if RR can be extracted efficiently and reliably from the PPG signal.

The coronavirus disease 2019 (COVID-19) after outbreaking in Wuhan increasingly spread throughout the world. Fast, reliable, and easily accessible clinical assessment of the severity of the disease can help in allocating and prioritizing resources to reduce mortality. The objective of the study was to develop and validate an early scoring tool to stratify the risk of death using readily available complete blood count (CBC) biomarkers. A retrospective study was conducted on twenty-three CBC blood biomarkers for predicting disease mortality for 375 COVID-19 patients admitted to Tongji Hospital, China from January 10 to February 18, 2020. Machine learning based key biomarkers among the CBC parameters as the mortality predictors were identified. A multivariate logistic regression-based nomogram and a scoring system was developed to categorize the patients in three risk groups (low, moderate, and high) for predicting the mortality risk among COVID-19 patients. Lymphocyte count, neutrophils count, age, white blood cell count, monocytes (%), platelet count, red blood cell distribution width parameters collected at hospital admission were selected as important biomarkers for death prediction using random forest feature selection technique. A CBC score was devised for calculating the death probability of the patients and was used to categorize the patients into three sub-risk groups: low (5% and 50%), respectively. The area under the curve (AUC) of the model for the development and internal validation cohort were 0.961 and 0.88, respectively. The proposed model was further validated with an external cohort of 103 patients of Dhaka Medical College, Bangladesh, which exhibits in an AUC of 0.963. The proposed CBC parameter-based prognostic model and the associated web-application, can help the medical doctors to improve the management by early prediction of mortality risk of the COVID-19 patients in the low-resource countries.

Coronavirus disease 2019 (COVID-19) has rapidly become a global health concern after its first known detection in December 2019. As a result, accurate and reliable advance warning system for the early diagnosis of COVID-19 has now become a priority. The detection of COVID-19 in early stages is not a straightforward task from chest X-ray images according to expert medical doctors because the traces of the infection are visible only when the disease has progressed to a moderate or severe stage. In this study, our first aim is to evaluate the ability of recent state-of-the-art Machine Learning techniques for the early detection of COVID-19 from chest X-ray images. Both compact classifiers and deep learning approaches are considered in this study. Furthermore, we propose a recent compact classifier, Convolutional Support Estimator Network (CSEN) approach for this purpose since it is well-suited for a scarce-data classification task. Finally, this study introduces a new benchmark dataset called Early-QaTa-COV19, which consists of 1065 early-stage COVID-19 pneumonia samples (very limited or no infection signs) labeled by the medical doctors and 12544 samples for control (normal) class. A detailed set of experiments shows that the CSEN achieves the top (over 97%) sensitivity with over 95.5% specificity. Moreover, DenseNet-121 network produces the leading performance among other deep networks with 95% sensitivity and 99.74% specificity.

With an expectation of an increased number of revision surgeries and patients receiving orthopedic implants in the coming years, the focus of joint replacement research needs to be on improving the mechanical properties of implants. Head-stem trunnion fixation provides superior load support and implant stability. Fretting wear is formed at the trunnion because of the dynamic load activities of patients, and this eventually causes the total hip implant system to fail. To optimize the design, multiple experiments with various trunnion geometries have been performed by researchers to examine the wear rate and associated mechanical performance characteristics of the existing head-stem trunnion. The objective of this work is to quantify and evaluate the performance parameters of smooth and novel spiral head-stem trunnion types under dynamic loading situations. This study proposes a finite element method for estimating head-stem trunnion performance characteristics, namely contact pressure and sliding distance, for both trunnion types under walking and jogging dynamic loading conditions. The wear rate for both trunnion types was computed using the Archard wear model for a standard number of gait cycles. The experimental results indicated that the spiral trunnion with a uniform contact pressure distribution achieved more fixation than the smooth trunnion. However, the average contact pressure distribution was nearly the same for both trunnion types. The maximum and average sliding distances were both shorter for the spiral trunnion; hence, the summed sliding distance was approximately 10% shorter for spiral trunnions than that of the smooth trunnion over a complete gait cycle. Owing to a lower sliding ability, hip implants with spiral trunnions achieved more stability than those with smooth trunnions. The anticipated wear rate for spiral trunnions was 0.039 mm3, which was approximately 10% lower than the smooth trunnion wear rate of 0.048 mm3 per million loading cycles. The spiral trunnion achieved superior fixation stability with a shorter sliding distance and a lower wear rate than the smooth trunnion; therefore, the spiral trunnion can be recommended for future hip implant systems.

Traditional waste management system operates based on daily schedule which is highly inefficient and costly. The existing recycle bin has also proved its ineffectiveness in the public as people do not recycle their waste properly. With the development of Internet of Things (IoT) and Artificial Intelligence (AI), the traditional waste management system can be replaced with smart sensors embedded into the system to perform real time monitoring and allow for better waste management. The aim of this research is to develop a smart waste management system using LoRa communication protocol and TensorFlow based deep learning model. LoRa sends the sensor data and Tensorflow performs real time object detection and classification. The bin consists of several compartments to segregate the waste including metal, plastic, paper, and general waste compartment which are controlled by the servo motors. Object detection and waste classification is done in TensorFlow framework with pre-trained object detection model. This object detection model is trained with images of waste to generate a frozen inference graph used for object detection which is done through a camera connected to the Raspberry Pi 3 Model B+ as the main processing unit. Ultrasonic sensor is embedded into each waste compartment to monitor the filling level of the waste. GPS module is integrated to monitor the location and real time of the bin. LoRa communication protocol is used to transmit data about the location, real time and filling level of the bin. RFID module is embedded for the purpose of waste management personnel identification.

Coronavirus disease (COVID-19) is a pandemic disease, which has already caused thousands of causalities and infected several millions of people worldwide. Any technological tool enabling rapid screening of the COVID-19 infection with high accuracy can be crucially helpful to the healthcare professionals. The main clinical tool currently in use for the diagnosis of COVID-19 is the Reverse transcription polymerase chain reaction (RT-PCR), which is expensive, less-sensitive and requires specialized medical personnel. X-ray imaging is an easily accessible tool that can be an excellent alternative in the COVID-19 diagnosis. This research was taken to investigate the utility of artificial intelligence (AI) in the rapid and accurate detection of COVID-19 from chest X-ray images. The aim of this paper is to propose a robust technique for automatic detection of COVID-19 pneumonia from digital chest X-ray images applying pre-trained deep-learning algorithms while maximizing the detection accuracy. A public database was created by the authors combining several public databases and also by collecting images from recently published articles. The database contains a mixture of 423 COVID-19, 1485 viral pneumonia, and 1579 normal chest X-ray images. Transfer learning technique was used with the help of image augmentation to train and validate several pre-trained deep Convolutional Neural Networks (CNNs). The networks were trained to classify two different schemes: i) normal and COVID-19 pneumonia; ii) normal, viral and COVID-19 pneumonia with and without image augmentation. The classification accuracy, precision, sensitivity, and specificity for both the schemes were 99.7%, 99.7%, 99.7% and 99.55% and 97.9%, 97.95%, 97.9%, and 98.8%, respectively. The high accuracy of this computer-aided diagnostic tool can significantly improve the speed and accuracy of COVID-19 diagnosis. This would be extremely useful in this pandemic where disease burden and need for preventive measures are at odds with available resources.

Tuberculosis (TB) is a chronic lung disease that occurs due to bacterial infection and is one of the top 10 leading causes of death. Accurate and early detection of TB is very important, otherwise, it could be life-threatening. In this work, we have detected TB reliably from the chest X-ray images using image pre-processing, data augmentation, image segmentation, and deep-learning classification techniques. Several public databases were used to create a database of 3500 TB infected and 3500 normal chest X-ray images for this study. Nine different deep CNNs (ResNet18, ResNet50, ResNet101, ChexNet, InceptionV3, Vgg19, DenseNet201, SqueezeNet, and MobileNet) were used for transfer learning from their pre-trained initial weights and were trained, validated and tested for classifying TB and non-TB normal cases. Three different experiments were carried out in this work: segmentation of X-ray images using two different U-net models, classification using X-ray images and that using segmented lung images. The accuracy, precision, sensitivity, F1-score and specificity of best performing model, ChexNet in the detection of tuberculosis using X-ray images were 96.47%, 96.62%, 96.47%, 96.47%, and 96.51% respectively. However, classification using segmented lung images outperformed that with whole X-ray images; the accuracy, precision, sensitivity, F1-score and specificity of DenseNet201 were 98.6%, 98.57%, 98.56%, 98.56%, and 98.54% respectively for the segmented lung images. The paper also used a visualization technique to confirm that CNN learns dominantly from the segmented lung regions that resulted in higher detection accuracy. The proposed method with state-of-the-art performance can be useful in the computer-aided faster diagnosis of tuberculosis.

A wideband grounded coplanar waveguide (GCPW) based patch antenna for head imaging is discussed in this paper. The proposed antenna is integrated with a slotted inverted delta-shaped main radiating patch, coplanar waveguide elements, and slotted partial ground. The prime objective of usages of coplanar waveguide elements is enhancing antenna effectiveness. In the prototype, examined different categories of slots in the ground and particularly rectangular and elliptical-shaped slots are used to improve the radiation directivity, gain, and efficiency. The optimized dimension of the antenna is $50\times 44\times 1.524$ mm3 by using the Rogers RO4350B substrate. The measured and simulated results demonstrate that the proposed prototype has a bandwidth of 2.01 GHz (1.70-3.71 GHz) with nearly directional radiation characteristics. The highest gain of the prototype is 5.65 dBi, and the maximum 93% radiation efficiency over the frequency band. The antenna has a lower group delay, higher fidelity factor (>95%), which are significant factors for microwave head imaging. Various design structures are performed to achieve the most satisfactory result. The proposed prototype is designed and analyzed by 3D CST 2019 simulator software. Later, the antenna is fabricated and measured to examine the performance. Thereafter, a single antenna and twelve-antennas array element are configured and placed surrounding the 3D realistic shaped Hugo head model to validate the effectiveness of the single antenna as well as the designed antennas array. The antenna has satisfactory field penetration into the human head tissues with a safe SAR (specific absorption rate). Less than 0.00233 W/kg SAR is attained over the operating frequency range, which is lower than the reported antennas. The Iteratively Corrected Delay Multiply and Sum (IC-DMAS) imaging algorithm will be applied for imaging purposes. The investigation through the literature of the statistical and measured data evident that the proposed antenna is apposite for the wideband microwave head imaging applications.

A novel modified-segmented split-ring based symmetric metamaterial absorber is introduced in this paper for X, Ku, and K band applications. The perfect absorption was achieved with a total of 1.91 GHz absorption bandwidth using the conventional FR4 substrate without resistive lumped elements. EM waves were applied in TEM mode at both normal and oblique incidence up to 90° and the same absorptance was found at 11.23 GHz, 14.18 GHz, 17.37 GHz, and 19.18 GHz with the maximum of 85.51%, 99.13%, 98.19%, and 90.8% absorptance respectively. This absorption performance was proved for both co- and cross-polarization analysis. Double negative values of permittivity and permeability up to 17.37 GHz and single negative values of either permittivity or permeability at 19.18 GHz were achieved. An equivalent circuit analysis also proved its performance capability, which makes it a perfect metamaterial absorber. Finally, the comparison of the design with recently published works in terms of unit cell size, absorption band, maximum polarization angles, and cross-polarized absorptivity proved it as a better candidate for the potential use as a perfect absorber.

The utility of EEG-fMRI is limited by the large artefact voltages produced in EEG recordings made during concurrent fMRI. Novel approaches for reducing the magnitude and variability of the artefacts are, therefore, required. One such approach involves using an EEG cap incorporating a reference layer (RL), which has similar conductivity to biological tissue and is electrically isolated from the scalp. The RL carries a secondary set of electrodes and leads that precisely overlay on the scalp electrodes so that similar voltages are anticipated to induce at the RL and scalp electrodes in the presence of static and time-varying magnetic fields. RL artefact subtraction (RLAS), which involves taking the difference of the voltages at the two electrodes, should, therefore, attenuate artefacts while leaving neuronal voltages unaffected. Previous experimental work has demonstrated the potential of the RLAS system in removing different types of EEG artefact. However, to get the best performance from the RLAS system, it is important to verify the underlying assumptions of RLAS and to optimize the RLAS system based on electromagnetic simulations. In this paper, electromagnetic modeling was used to simulate the voltages induced in a hemispherical RL and a spherical volume conductor (VC) under the influence of a static magnetic field and time-varying magnetic field gradient. By evaluating the differences in the voltages produced in the RL and VC, as the RL geometry is varied, the efficacy of the RLAS approach is tested and an optimal RL design is identified. The simulations performed accounted for realistic rotations, shifts, nodding, and shaking of the RLAS system with respect to the gradient isocentre, thus giving insight into the optimum RLAS set-up and the potential for improved EEG cap design for an RLAS system.

In this paper, a compact planar ultrawideband (UWB) antenna and an antenna array setup for microwave breast imaging are presented. The proposed antenna is constructed with a slotted semicircular-shaped patch and partial trapezoidal ground. It is compact in dimension: 0.30λ × 0.31λ × 0.011λ, where λ is the wavelength of the lowest operating frequency. For design purposes, several parameters are assumed and optimized to achieve better performance. The prototype is applied in the breast imaging scheme over the UWB frequency range 3.10–10.60 GHz. However, the antenna achieves an operating bandwidth of 8.70 GHz (2.30–11.00 GHz) for the reflection coefficient under–10 dB with decent impedance matching, 5.80 dBi of maximum gain with steady radiation pattern. The antenna provides a fidelity factor (FF) of 82% and 81% for face-to-face and side-by-side setups, respectively, which specifies the directionality and minor variation of the received pulses. The antenna is fabricated and measured to evaluate the antenna characteristics. A 16-antenna array-based configuration is considered to measure the backscattering signal of the breast phantom where one antenna acts as transmitter, and 15 of them receive the scattered signals. The data is taken in both the configuration of the phantom with and without the tumor inside. Later, the Iteratively Corrected Delay and Sum (IC–DAS) image reconstructed algorithm was used to identify the tumor in the breast phantom. Finally, the reconstructed images from the analysis and processing of the backscattering signal by the algorithm are illustrated to verify the imaging performance.