Electrical And Electronic Engineering

Sensor-based food intake monitoring has become one of the fastest-growing fields in dietary assessment. Researchers are exploring imaging-sensor-based food detection, food recognition, and food portion size estimation. A major problem that is still being tackled in this field is the segmentation of regions of food when multiple food items are present, mainly when similar-looking foods (similar in color and/or texture) are present. Food image segmentation is a relatively under-explored area compared with other fields. This paper proposes a novel approach to food imaging consisting of two imaging sensors: color (Red–Green–Blue) and thermal. Furthermore, we propose a multi-modal four-Dimensional (RGB-T) image segmentation using a k-means clustering algorithm to segment regions of similar-looking food items in multiple combinations of hot, cold, and warm (at room temperature) foods. Six food combinations of two food items each were used to capture RGB and thermal image data. RGB and the...

Walking in real-world environments involves constant decision-making, e.g., when approaching a staircase, an individual decides whether to engage (climbing the stairs) or avoid. For the control of assistive robots (e.g., robotic lower-limb prostheses), recognizing such motion intent is an important but challenging task, primarily due to the lack of available information. This paper presents a novel vision-based method to recognize an individual’s motion intent when approaching a staircase before the potential transition of motion mode (walking to stair climbing) occurs. Leveraging the egocentric images from a head-mounted camera, the authors trained a YOLOv5 object detection model to detect staircases. Subsequently, an AdaBoost and gradient boost (GB) classifier was developed to recognize the individual’s intention of engaging or avoiding the upcoming stairway. This novel method has been demonstrated to provide reliable (97.69%) recognition at least 2 steps before the potential mode...

Extreme angles in lower body joints may adversely increase the risk of injury to joints. These injuries are common in the workplace and cause persistent pain and significant financial losses to people and companies. The purpose of this study was to predict lower body joint angles from the ankle to the lumbosacral joint (L5S1) by measuring plantar pressures in shoes. Joint angle prediction was aided by a designed footwear sensor consisting of six force-sensing resistors (FSR) and a microcontroller fitted with Bluetooth LE sensors. An Xsens motion capture system was utilized as a ground truth validation measuring 3D joint angles. Thirty-seven human subjects were tested squatting in an IRB-approved study. The Gaussian Process Regression (GPR) linear regression algorithm was used to create a progressive model that predicted the angles of ankle, knee, hip, and L5S1. The footwear sensor showed a promising root mean square error (RMSE) for each joint. The L5S1 angle was predicted to be RMS...

Cerebral palsy (CP) is a group of nonprogressive neuro-developmental conditions occurring in early childhood that causes movement disorders and physical disability. Measuring activity levels and gait patterns is an important aspect of CP rehabilitation programs. Traditionally, such programs utilize commercially available laboratory systems, which cannot to be utilized in community living. In this study, a novel, shoe-based, wearable sensor system (pediatric SmartShoe) was tested on 11 healthy children and 10 children with CP to validate its use for monitoring of physical activity and gait. Novel data processing techniques were developed to remove the effect of orthotics on the sensor signals. Machine learning models were developed to automatically classify the activities of daily living. The temporal gait parameters estimated from the SmartShoe data were compared against reference measurements on a GAITRite mat. A leave-one-out cross-validation method indicated a 95.3% average accur...

For ultra-high field and frequency (UHF) magnetic resonance imaging (MRI), the associated short wavelengths in biological tissues leads to penetration and homogeneity issues at 10.5 tesla (T) and require antenna transmit arrays for efficiently generated 447 MHz B1+ fields (defined as the transmit radiofrequency (RF) magnetic field generated by RF coils). Previously, we evaluated a 16-channel combined loop + dipole antenna (LD) 10.5 T head array. While the LD array configuration did not achieve the desired B1+ efficiency, it showed an improvement of the specific absorption rate (SAR) efficiency compared to the separate 8-channel loop and separate 8-channel dipole antenna arrays at 10.5 T. Here we compare a 16-channel dipole antenna array with a 16-channel LD array of the same dimensions to evaluate B1+ efficiency, 10 g SAR, and SAR efficiency. The 16-channel dipole antenna array achieved a 24% increase in B1+ efficiency in the electromagnetic simulation and MR experiment compared to ...

For human head magnetic resonance imaging at 10.5 tesla (T), we built an 8-channel transceiver dipole antenna array and evaluated the influence of coaxial feed cables. The influence of coaxial feed cables was evaluated in simulation and compared against a physically constructed array in terms of transmit magnetic field (B1+) and specific absorption rate (SAR) efficiency. A substantial drop (23.1% in simulation and 20.7% in experiment) in B1+ efficiency was observed with a tight coaxial feed cable setup. For the investigation of the feed location, the center-fed dipole antenna array was compared to two 8-channel end-fed arrays: monopole and sleeve antenna arrays. The simulation results with a phantom indicate that these arrays achieved ~24% higher SAR efficiency compared to the dipole antenna array. For a human head model, we observed 30.8% lower SAR efficiency with the 8-channel monopole antenna array compared to the phantom. Importantly, our simulation with the human model indicate...

One of the major challenges in the development of wearable antennas is to design an antenna that can at the same time satisfy technical requirements, be aesthetically acceptable, and be suitable for wearable applications. In this paper, a novel wearable antenna is proposed—textile realization of a slotted waveguide antenna. The antenna is realized using conductive fabric to manufacture the walls of a rectangular waveguide in which the slots were cut out. All connections and cuts are sewn with conductive thread taking over advantages of the traditional process of manufacturing textile objects. The developed slotted waveguide array prototype, containing three slots and designed for operation in the 5.8-GHz ISM band, is experimentally characterized and compared to an equivalent metallic antenna. The achieved operating bandwidth is larger than 300 MHz in both cases. The measured gain of a textile slotted waveguide array is around 9 dBi with a radiation efficiency larger than 50% in the ...

The electromagnetic wave propagation around human body torso is modelled by considering elementary electric and magnetic dipoles over an infinite muscle-equivalent cylinder. The poles in the spectral domain Green’s function with smallest imaginary part are found to correspond to creeping wave propagation coefficients which predict the general trend in propagation around human body. In addition, it was found that axial magnetic field component is crucial for communication via creeping waves since it generates modes with smaller field decay compared to axial electric field. The developed model may thus serve as a practical guideline in design of on-body wearable antennas. The theoretical considerations are verified with simulations and measurements on the prototype of PIFA antenna placed on the human body.

Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient’s blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly ...