Search

Implanted biomedical devices (IBDs) help patients make their lives easier by continuously monitoring undesired signs and detecting their diseases. However, the operation of these IBDs relies on battery power, which often suffers from a limited lifespan. Wireless power transfer (WPT) is a promising solution for this challenge. WPT technology facilitates the wireless recharging of IBD batteries, thus eliminating the need for surgical battery replacement procedures. This paper introduces a near-field inductive coupling-based WPT (IC-WPT) system operating within the 13.56 MHz radio band, explicitly designed for IBD applications. Various single-layer spiral coil topologies were precisely created and simulated, including octagonal, circular, and rectangular configurations. The design and simulation of these coils were carried out using the finite element-based ANSYS HFSS software. The investigation of the IC-WPT system showed the effect of the distance and frequency on the coupling between the implanted coil and transmitter coils and system efficiency. Results demonstrated that the rectangular coil achieved higher transfer efficiency, ranging from 84.4% at a 2 mm distance to 71.9% at a 10 mm distance compared to octagonal and circular coils. The model confirms its effectiveness based on the result of the proposed IC-WPT. [ABSTRACT FROM AUTHOR]

Wireless power transmission (WPT) revolutionizes convenience by eliminating physical connections, enabling seamless charging for various devices. WPT faces challenges related to efficiency loss over distance, as energy transmission weakens with increased separation between transmitter and receiver. This paper aims to design and practically implement a WPT-based magnetic resonator coupling (MRC) technique to transfer energy from a transmitter coil to a receiver coil for supplying temperature and humidity environmental sensors by power using a zero voltage switching (ZVS) model. The system comprises three main circuits: receiver, transmitter, and monitoring environment. The transmitter circuit operates at a frequency of 17 kHz using the ZVS model. The receiver and transmitter coils are hand-twisted and made of 15 American Wire Gauges (AWG). Built-in environmental circuitry with a DHT11 sensor and Arduino Uno microcontroller makes it easy to monitor temperature and humidity under environmental conditions. Different impedance loads of 50, 100, 150, and 200 ohms were tested in the system at 1 and 10 cm distances between the receiver and transmitter coils. The results have shown that the system worked fairly when using 50-ohm resistors spaced between 1 and 4 cm between the transmitter and receiver coils, providing a voltage of over 4 volts and a current of over 70 mA. As a result, these parameters enable suitable environment monitoring circuits comprising the Arduino Uno microcontroller and the DHT11 sensor. Furthermore, the system attained a notable efficiency of 95% based on real measurements when the distance between the two coils was 1 cm and the resistive load value was 50 ohms. Moreover, this system shows exceptional performance compared to previous related research and shows notable improvement. [ABSTRACT FROM AUTHOR]

Osteoarthritis (OA), a prevalent degenerative joint disease, triggers significant global impairment. Timely intervention relies on accurate early diagnosis. Recent advancements employ deep learning (DL) models that integrate patient clinical data with Imaging techniques like X-rays, MRI, and CT scans, enhancing OA detection and assessment. This review surveys recent research on DL techniques for OA detection, highlighting the development of convolutional neural networks (CNNs) and innovative architectures. CNNs analyze medical images, automatically extracting features indicative of OA progression. Models combining patient demographic information, clinical history, symptoms, joint biomechanics, and imaging data show improved OA onset and progression prediction compared to imaging alone. Transfer learning fine-tuning CNNs pre-trained on datasets like ImageNet enhances feature extraction and classification accuracy. Hybrid models, merging CNNs with traditional machine learning (ML) methods like SVM, capitalize on the strengths of both approaches. Despite progress, challenges include reliance on training data volume and quality, class imbalance, and limited model generalization across diverse datasets. DL holds promise for automated and objective OA diagnosis, severity grading, treatment planning, and prognostication. However, further research with multi-modal datasets and optimized model architectures is essential to realize its clinical utility and generalizability for OA management fully. This review synthesizes the field's current state, outlining future directions in this evolving application at the intersection of artificial intelligence and musculoskeletal health. [ABSTRACT FROM AUTHOR]

High blood sugar levels for an extended time lead to the development of diabetic foot, which is a major medical problem among people with diabetes. Continuous care and management are essential to avoid potential physical complications. Nerve and blood vessel dysfunction caused by diabetic foot disease can lead to skin problems and ulcers, necessitating medical intervention. Diabetes increases the risk of foot-related complications, requiring prompt identification and resolution to prevent serious complications. The goal is to create a system consisting of a wireless sensor network or a system based on the use of thermal imaging for real-time monitoring of individuals with diabetes. This network will collect important physiological data, such as temperature, pressure, and humidity, using machine learning algorithms to predict diabetic foot complications. Automation will enhance forecasting accuracy and efficiency. An in-depth review of prior research on early detection methods for diabetic foot was undertaken to identify the most effective approach. Through rigorous comparative analysis, the proposed machine learning model demonstrates the superiority of the convolutional neural network (CNN) over other deep learning classifiers, achieving an accuracy rate of 98.27%. Different methodologies of ML, including regression (LR) and random forest (RF) classifiers, have also shown predictive solid performance, reaching up to 97% accuracy in forecasting diabetic foot disease. In conclusion, there is an urgent need for an advanced diabetic foot health monitoring system. The review highlights the need for additional research to overcome persistent challenges and unleash the full potential of machine learning models in enhancing diabetic foot disease prediction and treatment. [ABSTRACT FROM AUTHOR]

Diabetic foot is a severe medical problem that occurs as a result of high blood sugar levels. It is a common complication in diabetics. Diabetes can lead to complications, especially in the form of diabetic foot problems. If these problems are not detected and treated promptly, they can worsen, leading to severe consequences. Screening methods for the disease can be conventional and do not predict diabetic foot in the early stages. These prompted researchers to find an alternative solution to detect diabetic foot early and non-surgically. Researchers have sought other non-invasive methods to diagnose and predict diabetic feet using image processing techniques and machine learning algorithms. This study presents a comparative performance between six machine learning algorithms (Neural Network, Random Forest, Adaboost, Naïve Bayes) based on a dataset of images of normal and diabetic feet. The results show that Neural Network has an accuracy of 95.6%, the highest performance among other algorithms used in this study. [ABSTRACT FROM AUTHOR]

Pre- and post-Earthquake warning system are essential for saving living, reducing and preventing the damage of landslides. WSNs are a high-potential innovation that has been successfully implemented in many real-time applications, especially landslide monitoring. This paper proposes a low-cost earthquake warning system that can detect earthquake events and monitor the status of buildings in real-time using LoRa (long-range) technology in addition to monitoring the reliability of the communication system. The vibration sensor (sw-420) and accelerometer sensor (ADXL 345) are connected to Arduino UNO, and the data collected by Arduino are sent through the LoRa transmitter module. Then, it was received through another Arduino UNO that was equipped with a LoRa receiver module. Several cases are adopted on the Electrical Engineering Technical College site with different parameters and communication paths (LOS & NLOS) to analyze the communication reliability between transmitter and receiver sides in addition to the packet received ratio. The results showed that the system is more reliable for detecting earthquakes, especially with an LOS communication system with RSSI less than -148dBm. [ABSTRACT FROM AUTHOR]

Parkinson's disease is a degenerative condition that greatly affects the population, especially the elderly. The main cause is the gradual death of melanocytes in the brain, which produces dopamine and transmit nerve signals during motor and cognitive activities. The disease has various symptoms, including motor and non-motor, which appear after the level of dopamine in the melanocytes reaches less than 40% of its normal levels. Early detection of the disease is crucial to prevent patients from reaching catastrophic stages that affect their quality of life. Artificial intelligence technologies, such as machine learning, deep learning, and the Internet of Things (IOT), provide important benefits in predicting, detecting, and tracking disease progression. This review examines previous literature on AI techniques and their use in finding successful solutions to reduce disease progression. Researchers focused on prediction and early detection using medical technologies such as brain MRI scans. In contrast, others focused on clinical symptoms such as acoustic measurements, gait analysis, and electroencephalography, in addition to exploiting IOT technologies to track disease progression. All studies used approved criteria to test the efficiency of the models. proposed classifications, such as classification accuracy, sensitivity, and specificity, to determine their effectiveness in controlling the disease. The review findings highlight the status of intelligent systems and models proposed in the literature and identify their advantages, disadvantages, difficulties, and potential paths forward. These cutting-edge monitoring and prediction systems have the potential to transform the treatment of Parkinson's disease and provide invaluable assistance to patients and medical professionals, if technological advances continue. [ABSTRACT FROM AUTHOR]

Osteoarthritis is a degenerative joint disease that commonly affects the elderly population. The Kellgren-Lawrence grading system serves as the benchmark for evaluating OA severity through the analysis of radiographs. However, this method relies heavily on physician expertise, resulting in variability. To address this issue, machine Learning methods have been explored for automated OA diagnosis and grading. This study compares different Machine Learning models (Neural Network, Random Forest, and Logistic Regression) were deployed for classifying osteoarthritic knee radiographs. The models were trained and tested on a dataset of normal and osteoarthritic knee X-ray images from Kaggle. The results demonstrate that Logistic Regression achieved the highest classification accuracy of 88.6%, sensitivity of 84%, precision of 88.6%, specificity of 88.6%, and AUC of 95.2%, compared to the Neural Network and Random Forest models. The study validates the efficacy of the Logistic Regression model through comparison with previous works. The key contributions include the implementation of multiple Machine Learning algorithms, determining Logistic Regression as the optimal method for early OA detection, and superior accuracy compared to prior research models. The study indicates that Logistic Regression is a promising approach for automated classification and grading of knee osteoarthritis severity. [ABSTRACT FROM AUTHOR]

Parkinson's Disease (PD) is a neurological disease that affects the nervous system of the human body. Parkinson's disease is considered a silent disease that does not show symptoms at the beginning of the patient's infection with the disease. Therefore, the diagnosis of the disease is very late, perhaps after months or even years. Hence, treating and controlling the disease is a challenge, so early detection is crucial to improving the quality of life and treatment of patients on the one hand and the possibility of recovery on the other hand. This research proposes a model based on Machine Learning (ML) algorithms. This model uses peoples' voice measurements collected and obtained from the Kaggle dataset (for, where 195 audio recordings were examined, to determine whether they have the disease or not. The proposed model was used to classify 1,000 important patient features. Neural Networks, Multilayer Perceptron (MLP), Random Forest (RF), Logistic Regression (LR), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and Decision Trees (DT) were among the machine learning methods used. With a classification accuracy of 95.5%, the MLP algorithm outperformed other methods that achieved lower classification accuracy, as the RF algorithm achieved a classification accuracy of 88.4%, LR achieved 87.7%, GB 91.5%, KNN 86%, and DT achieved classification accuracy, reached 86.8%, according to the data. This work provides the option of creating a model by comparing several ML algorithms, selecting the most accurate one for classification, and using acoustic measurement analysis to identify PD. [ABSTRACT FROM AUTHOR]

Pneumonia is a prevalent lung disease worldwide, and timely recognition is crucial. Machine learning has been increasingly applied in various fields, including healthcare, but it has limitations when dealing with a small dataset for training models. In this study, we focused on diagnosing pneumonia using X-ray images and developed an approach that employs the ANN algorithm. We used a small dataset of RGB images to test, train, and validate the ANN, and we tested the algorithm with 15 neurons. This paper examined 500 patient X-ray pictures from the Kaggle dataset for normal and abnormal cases. Ten thousand pixels were selected from these images, with 7,000 pixels allocated for training the ANN and 1,500 pixels each for testing and validation. The outcomes showed that the ANN with 15 neurons achieved remarkable performance on all performance indices, including specificity, F1-score, accuracy, sensitivity, and precision, with a score of 99.9%. Furthermore, the suggested approach outperformed the current solution for pneumonia diagnosis utilizing the ANN model. [ABSTRACT FROM AUTHOR]

Blind or visually impaired people face several challenges in safely navigating their environments due to their lack of inclusive real-time obstacle detection and surrounding information aid. In this paper, a smart stick for visually impaired people was designed and practically implemented. The smart stick system contains heart rate, ultrasound, and moisture sensors. The system's core utilizes an Arduino Nano microcontroller programmed in C++ and GPS, GSM/GPRS, a vibration motor, a buzzer, and a battery. Ultrasound and soil moisture sensors are used to detect the obstacles and the nature of the floor faced by the visually impaired person during navigation in various environments. The heart rate was employed to monitor the health condition of the visually impaired. Moreover, the position of the visually impaired individual was tracked in real-time based on GPS, and the geolocations were transmitted to the family members through the GSM/GPRS network to facilitate the monitoring of the user. The vibration motor and buzzer alert the user to unwanted environments, like obstacles, wet surfaces, or elevated heart rates. The performance of the alert decision was enhanced by utilizing an Artificial Neural Network (ANN) implemented in Matlab software. The analysis results revealed exceptionally high correlation coefficients (R²) across all datasets: 0.997 for training, 0.988 for testing, 0.982 for validation, and 0.994 for all combined datasets, as determined by the applied ANN. Furthermore, the alert decision error was enhanced to 4.096×10-5. This error revealed that applying ANN resulted in a remarkable reduction in errors relative to those obtained from statistical analysis of differences among the smart stick system and benchmark systems. [ABSTRACT FROM AUTHOR]

Asthmatics often endure severe recurrent attacks, which repeatedly interfere with daily life. To meet this challenge, the Asthma Attack Prediction System (AAPS) was developed with a unique U-shaped design. The system comes with an attack prediction (AP) algorithm, using a combination of biosensors to predict attacks by monitoring cough sounds, throat movements, and heart rate – an alternative way to detect asthma severity an integrated smartphone is a remarkable feat. In emergencies, AAPS can mechanically alert hospitals through SMS, ensuring well-timed intervention. Calibration and validation against business gadgets revealed superb accuracy, with coronary heart charge measurements hitting 99.03% accuracy and cough sounds with throat movement sensors recording 93.75% and 95.83% accuracy, respectively. This gave an impressive 96.2% overall detection precisely. These consequences pass beyond previous studies and highlight advances in assault prediction, portability-making plans, and implementation. [ABSTRACT FROM AUTHOR]

Cardiovascular disease (CVD) is a life-threatening medical condition caused by high blood sugar, high blood pressure, alcohol, smoking, and congenital abnormalities. There are several ways to diagnose CVD, such as stethoscopes, electrocardiography (ECG), phonocardiography (PCG), and computed tomography (CT). Some of these devices are inaccurate and require medical expertise. In stethoscopes, the doctor's skill determines heart sound interpretation and external disturbances can affect their effectiveness. Additionally, ECG and PCG cannot provide complete heart health information. CT scans, however, emit radiation that can harm patients. This study examines various CVD early detection and prediction methods to find the best one for patients and doctors. Previous research has identified methods, including artificial intelligence (AI) algorithms and wireless sensors. The study also seeks to identify the best model and examine CVD detection challenges. Comparing previous research, the modified scalp swarm optimization method and adaptive fuzzy neurological system (MSSO-ANFIS) had the highest rating accuracy, 97.45%. Researchers' CVD detection difficulties were also highlighted in the paper. In conclusion, the use of echocardiography devices provides comprehensive and accurate information about the heart, including details such as the shape of the heart, the thickness of the heart muscle, and heart sounds. [ABSTRACT FROM AUTHOR]

This research presents an accurate remote monitoring prototype for the elderly biomedical signals. A MAX30102 sensor was interfaced with the Arduino Nano 33 BLE Sense microcontroller (nRF52840). The measurement accuracy was validated relative to the Benchmark (Pulse Oximeter) depending on the mean absolute error (MAE). Experimental results show that the proposed current system obtained an MAE of 3.904 and 1.156 for heart rate and SpO2, respectively, suggesting a close agreement between the Benchmark and the proposed system. The proposed prototype has an accuracy of about 99 and 98.3 for heart rate and SpO2, respectively. The suggested system is monitoring in real-time, accurate, applicable, low-cost, and effective resources for transmitting data. Moreover, the proposed system can be used in many applications and for parameters other than heart rate and SpO2 with simple modification (e.g., gait rehabilitation, heartbeat rate, and electrocardiography for observing the health care system, respiratory rate, muscle action, and elderly fall detection). [ABSTRACT FROM AUTHOR]

Cardiovascular Diseases (CVD) have become increasingly common around the world in recent times. Diagnosing these diseases is difficult due to traditional diagnostic methods such as stethoscopes and auscultation. This study aimed to detect and predict these diseases before the patient's condition worsens. Machine learning (ML) techniques were used, including Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), and Decision Tree (DT). A Kaggle dataset of 1,000 samples and 14 clinical features was trained and tested. Furthermore, the performance metrics of these algorithms were examined. According to the results, RF performs better in terms of F1-score, accuracy, sensitivity, specificity, precision, training time, and testing time, with scores of 97.8%, 98%, 98.2%, 97.6%, 97.8%, 0.182 sec, and 0.030 sec, respectively. In conclusion, it was noted that modern diagnostic methods provide comprehensive and exact information about the heart. [ABSTRACT FROM AUTHOR]

This review paper finely analyzes eye-to-text communication and explores the development and evaluation of an advanced eye-controlled communication system. The study focuses on the algorithms for eye tracking and gaze estimation, the Artificial Neural Networks (ANNs), and the training process for converting eye movements into textual output. The article highlights Computer Vision (CV) algorithms utilized for real-time eye tracking and gaze estimation, emphasizing the robustness and accuracy of the algorithms. The authors detail the techniques employed, including pupil detection, iris segmentation, and gaze estimation, highlighting their effectiveness in capturing and analyzing eye movements. Moreover, the article discusses challenges faced during training that provide insights into potential improvements for future work. The review paper presents comprehensive experimental results, including ANN comparisons with existing methods such as gaze estimation error and user satisfaction, thoroughly assessing the system's capabilities. The system enables users to express themselves and interact with digital devices more independently, enhancing the Quality of Life (QoL) for individuals with limited motor abilities. This review aims to pinpoint the deficiencies left unaddressed by researchers, including issues such as head motion, low illumination, low-resolution cameras, and user fatigue. These identified shortcomings emphasize the pressing demand for eye-to-text communication systems. [ABSTRACT FROM AUTHOR]

Inductive wireless power transfer (IWPT) is a method introduced for transferring energy. IWPT technology is generally characterized by high transfer efficiency and high output power at low distances. The extensive use of gasoline leads to the emission of gases harmful to the environment, which leads to global warming. Therefore, traditional energy resources must be minimized and their effects on the environments should be reduced. Therefore, alternative solutions such as electric vehicles (EVs) or EV-based wireless power transfer (WPT) are adopted. In this research, IWPT-based EV was reviewed and compared. In addition, the WPT was classified according to the transfer distances. Several performance metrics of previous scholars related to charging the battery of EVs were explored and compared in terms of transfer power, efficiency and distance between receiver and transmitter coils and the oscillating frequency. In addition, the application of WPT was highlighted. Moreover, the advantage and disadvantages of IWPT were explored. [ABSTRACT FROM AUTHOR]

The Inductive Wireless Power Transmission (IWPT) technology is an advanced and important technology. Through which it is possible to reduce the dangers of wires to humans through electrical contact, as well as to avoid the electrical complexity and their valuable use in difficult-to-reach areas such as high locations, roadways, and so forth. In this study, IWPT technology was designed using electromagnetic induction technology for wirelessly charging the car battery with high efficiency. The design of system is by Pspise software. The transmitter side was designed as an E-type Power Amplifier (PA) that includes IRFP260 switch and 526 µH throttle. The transmitting inductance coil is 97 µH and internal resistance (30.19 mΩ). While receiving side has a coil is designed with a value of (92 µH) and internal resistance of 30.19 mΩ. The recircuit was also designed. Several distances of 15, 30, 40, 50, 60, 70, 80, 90 and 100 cm were chosen. The results have shown that the high efficiency of 97%, with an excellent quality factor is 1400, and very little power loss were obtained from this design at a distance of 15 cm. [ABSTRACT FROM AUTHOR]

Sleep apnea disorder is one of the most widespread respiratory syndromes, interrupting breathing by preventing air from entering the lungs. This paper documents the design and implementation of a cost-effective and easy-to-conduct screening method for detecting and predicting sleep apnea events using a small number of sensors and a small, lightweight wearable device. The proposed sleep apnea system comprises sensors for heart rate, SpO2, and chest movement, an Arduino Uno microcontroller and a Bluetooth low-energy module. Sensory data were collected while the test subject was sleeping and compared with the benchmark home sleep apnea test device. Statistical analyses confirmed the performance of this study's system, with experimental results closely conforming to the Benchmark; the proposed system's accuracy was 99.94% for heart rate and SpO2 measurements, according to a Bland-Altman test requiring at least 95% concordance. [ABSTRACT FROM AUTHOR]

Several previous researches suggested designs for wearable devices to measure, check, and monitor a patient's temperature and measure brain temperature. Scientific studies have shown that using hypothermic devices reduces mortality rates and reduces in the long run. In case of injury, the human brain is weak and affected by fluctuating temperatures, and it is challenging to control brain temperature manually. The Human Brain Hypothermia (HBH) methods were classified in this paper. The techniques and types of cooling systems to reduce brain temperature, including brain cooling, blood cooling, and skin surface cooling, have been reviewed. In addition, the main objective of the reviewed research is to discover the systems and devices that lower the temperature of the human brain and body. Moreover, a comparison of previous works for HBH was achieved in terms of adopted method, sensor type and location, and temperature Hypothermia value. The disadvantages or limitations of the previous studies were critically reviewed. [ABSTRACT FROM AUTHOR]

Efficient children tracking schemes require attaching a wearable device to the target person or embedding a tracking software inside a handheld smartphone. Such schemes provide the person's location and the path from source to destination. Therefore, the increasing interest in children tracking systems has led to a subsequent interest in wearable devices and Device-Free Localization (DFL) tracking systems. Mainly, many types of research were conducted on children tracking systems using different technologies and different types of wearable devices. Many novel ideas and approaches were developed regarding providing safety and supervision for children at home alone, on the roads to schools, or at other social events. Progress and results yielded in reviewed works were highly impressive. In this survey, a comprehensive overview of this evolutionary tracking system is provided to describe essential concepts and studies on Radio Frequency Identification (RFID), Bluetooth, Wireless Fidelity (Wi-Fi), Global System for Mobile Communication (GSM), Global Positioning System (GPS), and ZigBee wireless technologies. However, the main challenges faced by all types of tracking techniques are coverage area, location accuracy, power consumption, and computational cost. This survey is done in a structured manner, in which subjects are categorized according to the wireless technology used in tracking systems. Additionally, it discusses current obstacles within state-of-the-art children tracking systems. [ABSTRACT FROM AUTHOR]

This paper presents the approach used in estimating distance based on the shadowing Model (SM) between two Wireless Sensor Networks (WSNs) in an indoor surrounding. Our work aims to measure the distance between two wireless nodes in indoor environments. The Received-Signal Strength Indicator (RSSI) method of ZigBee wireless- protocol, such as the XBee series S2C module, is adopted to estimate the distance due to its simplicity, and no extra hardware is required. The SM is derived based on curve fitting using RSSI. Besides, the propagation channel factors such as standard deviation and path loss exponent were estimated. The experiment was carried out in the indoor surrounding of the LABs building of the "Electrical Engineering Technical College (EETC)". The experimental results demonstrate that the Mean Absolute Error (MAE) is 8.3 m for a distance range of 0–30 m, and the correlation coefficient (R2) between real and measured distances of 0.58 is obtained. The results denote that the SM is only suitable for a short distance. [ABSTRACT FROM AUTHOR]

In 2019, the world witnessed a rapid spread of the Coronavirus (COVID-19) disease in one of China's cities, Wuhan. The disease was announced in December 2019 to be a springboard for the whole world, where most countries were infected with it. It greatly affected the health of society and became a real danger to humans. Therefore, it is necessary to diagnose the infected people and quarantine them to combat this pandemic and limit its spread. This paper aims to give a review of COVID-19 diagnosis methods. According to the diagnostic methods, the previous works are classified into two categories for diagnosing Coronavirus; X-ray and Computed Tomography (CT)-Scan. Artificial intelligence (AI) is used to improve the diagnosis accuracy of the presented methods. On this basis, automated diagnostic tools have been developed that distinguish people infected with the Coronavirus from other diseases. Moreover, the performance parameters of the previous studies were compared in terms of diagnosis method, adopted algorithm, diagnosis accuracy, sensitivity, and specificity. Furthermore, the challenges and limitations of the existing methods for diagnosing Coronavirus were explored. AI has proven to be a reliable way to diagnose the spread of the epidemic through advanced algorithms based on blind and machine learning, especially the convolutional neural network (CNN), which plays a vital role in extracting sensitivity, specificity, and accuracy. [ABSTRACT FROM AUTHOR]