This paper aims to present a universal mask that enables all adult patients to use it. This mask has a universal size and head gear. It has many options; from among we list the embedded SpO2 and EEG electrode connections. This mask enables also the input of oxygen, nebulizer, air CPAP and medication. A mechanical switch is used to select between air CPAP and nebulizer.
The Kalman Filter (KF) is a powerful state estimation technique developed for linear time-varying systems and has recently extended for estimating nonlinear time varying dynamical systems. However, a major challenge for this technique is the choice of the tuning filter parameters that often necessitates a long and tedious process, particularly for large nonlinear systems. In the present work, we propose a new method based on Adaptive Design Optimization (ADO) method in which the tuning parameters are autonomous designed, within the forward Kalman pass, based on sensitivity analysis of the model. The method is applied for the model inversion in a hemodynamic model for which the hidden states (hemodynamic variables) along with unknown neuronal activity (NA) input are estimated based on simulated noisy BOLD signal observations. The proposed approach is demonstrated to produce more confident estimates and better convergence without the need of an iterative tuning process from the designer.
The aim of this investigation is to design and construct a demonstrative prototype of a low cost foot planter-pressure scanner that can assess health care providers in diagnosing and monitoring patients who are suffering from foot disorders. The prototype will be designed from a matrix of force sensitive sensors that measure the spread of forces on the plantar surface of the foot. Suitable Graphical User Interface (GUI) software is designed in order to fit with health care provider requirements.
Melanoma is one type of skin cancer that usually develops from prolonged exposure to UV light. The latter triggers mutations that lead skin cells to multiply rapidly and form malignant tumors. If not cured, Melanoma can result in one's death. Hence, an early detection of this deadly cancer is important to prevent it. Certain lesion characteristics such as Asymmetry, Border, Color and Diameter segmentation (ABCD rule), can indicate the presence of Melanoma. In this work, we investigate the use of geometric features to differentiate between a benign lesion and a malignant one. The k-Nearest Neighbors (k-NN) machine learning algorithm is used to classify 15 lesions based on their ABD features. An accuracy of 89% was obtained on the testing set. The results indicate that this technique may be used to detect Melanoma skin cancer.
Articular cartilage is a stratified tissue with distinct layers expressing different protein types/amounts and having different cell morphologies. Research on articular cartilage has shown that compression, hydrostatic pressure, and hypoxic conditions tend to give the articular cartilage the properties of the middle and bottom layers of the natural tissue, while surface motion and normoxic conditions induce a superficial zone cartilage phenotype. Our objective is to build a bioreactor that can control all of these parameters in order to test for different values and find optimal ranges to create an engineered cartilage tissue with ideal characteristics. Thus we built a four-chamber bioreactor that can apply hydrostatic pressure, compression, shear and torsion, in addition to controlling oxygen tension supplied to the cartilage. The mechanical simulation is applied using a gear-rack mechanism having a frequency of 0.5Hz. The oxygen tension is controlled by electric valves connected to O 2 and N 2 bottles coming to the bioreactor's chambers, oxygen and pressure sensors are used in the process. The bioreactor is controlled and coded using Arduino software. After building the bioreactor, a Matlab computer vision test was done to check for the precision of the mechanism, and finally injurious and proliferation tests were performed to check for the effectiveness of the bioreactor. Results of the precision testing showed a 4% error for a 1mm displacement. Results of the injurious tests showed significant numbers of dead cells for compressive forces larger than 10 MPa. In conclusion, our newly developed system is capable of delivering a variety of mechanical stimuli and oxygen tension simulating those in native cartilage. The importance of this system lies in its applicability to cartilage but also to other mechanoresponsive and oxygen sensitive tissues such as bone, muscle, tendons, ligaments, and blood vessels. In the future, we plan to improve our bioreactor by using a cam-follower mechanism for higher precision.
We describe an experimental and educational tool based on the design and development of a robotic arm controlled by EMG surface signals, captured at the biceps brachii muscle and digitally processed. We present the hardware design for the biosignal pre-processing and describe the post-processing and the microcontroller for three servomotors. The design has been used in classroom to promote and integrate different BME curriculum knowledge.
Network modularity is a key feature for efficient information processing in the human brain. This information processing is however dynamic and networks can reconfigure at very short time period (few hundreds of millisecond). This requires neuroimaging techniques with sufficient time resolution. Here the dense electroencephalography (EEG) source connectivity methods were used to identify cortical networks with excellent time resolution (in the order of millisecond). Functional networks were identified during picture naming task. Two categories of visual stimuli were presented: meaningful (tools, animals...) and meaningless (scrambled) objects.In this paper, we report the reconfiguration of brain network modularity for meaningful and meaningless objects. Results showed mainly that networks of meaningful objects were more modular than those of meaningless objects. Networks of the ventral visual pathway were activated in both cases; however a strong occipito-temporal functional connectivity appeared for meaningful object but not for meaningless object. We believe that this approach will give new insights into the dynamic behavior of the brain networks during fast information processing.
Magnetic Resonance Imaging is the most popular imaging technique used to in brain lesion diagnosis. Brain lesions due to Stroke appear as a gray region similar in color to some normal tissues like gray matter. Manual extraction of brain lesion is time-consuming. On the other side, current automated methods require either multispectral MR images or extensive time of training. To avoid these problems, this paper suggests a novel automated brain lesion recognition method that uses single spectral MR images to efficiently extract brain lesions with a reasonable amount of time and with acceptable accuracy. By applying this method, it can distinguish brain lesions automatically. The principle of operation and mathematical characterization of the suggested algorithm are given in details. The results of the proposed algorithm using a single T1 weighted MR images for stroke subjects and for healthy subjects with simulated brain lesions are presented. Results showed that the suggested window-based entropy comparison method could identify a lesion with a minimum size of 10×10×10 mm and with an average accuracy of 3 voxels and success rate of 91%.
As any technology, medical equipment provides benefits to patients, but they also present significant risks that can affect and threaten patient safety. In healthcare organizations, clinical engineering departments play a big role in maintaining the safety and reliability of medical equipment. In order to mitigate failures of such equipment and control risks, a proper Medical Equipment Management Program (MEMP) and a monitoring system should be established. The purpose of this paper is to forecast risks by using Failure Mode and Effect Analysis (FMEA) method and apply it on Monte Carlo simulation which adds risks analysis to Excel® by @RISK tool. The data of some medical devices is extracted from a hospital's maintenance management system and are identified according to their likelihood, severity, and difficulty of detection. However, the results of this mathematical simulation are integrated in a probability distribution function, and then this is integrated in the existing Hospital Institution Quality Management (HIQMA) system that enables us to identify medical equipment risks that affect patients, staff, and the work environment and mitigate them by providing contingency plans, policies, strategies, and other tactics.
This paper presents a Face Detection System with Expression Recognition using Artificial Neural Networks. It is an automated vision system designed and implemented using MATLAB. The Face Detection with Expression Recognition system accomplishes facial expression recognition through two phases. The captured image is processed first to detect the face, and then the facial expression is recognized. These two phases are completed in five stages. The first two stages of the system deal with detecting and cropping the face using image processing, in particular the Viola-Jones object detection framework. The third stage deals with converting the colors of the cropped image from RGB into gray scale and applying the appropriate smoothing filter. The fourth stage consists of feature extraction using Artificial Neural Networks, so as the extracted features are compared with training samples. The final stage classifies the given outputs and shows facial expression recognition results. It then determines whether the subject is happy, angry or in neutral state. The Artificial Neural Network uses Multi-Layer-Perceptron (MLP) with back propagation algorithm for features extraction and classification. It has 4097 input nodes, one hidden layer with 50 neurons, and one output layer. Testing results show that this system can be used for interpreting three facial expressions: happiness, anger and neutral. It extracts accurate outputs that can be employed in other fields of studies such as psychological assessment. Finally, the high precision of the results allow future development of different applications which respond to spontaneous facial expressions in real time.
Low capacity, bulky size and wiring limitations of the conventional wireless multi-channel electroencephalography (EEG) system restrict its use as brain neuromonitoring system. To reduce such restriction, this paper proposes an EEG system based on multi-input multi-output (MIMO) technique and polar coded data. In the proposed system, all the channels are sent and received simultaneously, while the frozen bits of polar codes are used for antenna switching. The results show that a location of the switching code at the noisy frozen bits reduces the performance of the proposed system especially in the case of low signal to noise ratio. To improve the system performance, this work suggests a method to encode the data transmitted through the frozen bits.
Human activity can serve as an identifier of subject health, behavioral patterns, and personal preferences. With the sudden splurge in mobile and wearable devices, activity data has become more readily available to design useful applications that enhance the users' everyday lives without any obtrusive intervention. This paper focuses on the use of a system identification approach to characterize human movement dynamics from accelerometer sensors during physical activity and subsequently to construct user-specific models that can potentially be incorporated in personalized healthcare and safety. The study investigates the human wrist-to-ankle dynamic relationship using various linear prediction model structures. It was found that the ARMAX model structure is the most widely applicable across stereotypical activity patterns (e.g. walking, running). Importantly, and after conducting a series of order selection and validation tests, it was noted that specific activities across multiple individuals can be fit within a common model where the orders are fixed and only the parameters of that model are tuned to individual users. A potential application of these common models to user identification, as reflected through the models' frequency responses, is discussed.
Falling is a serious issue among old aged population; it leads to severe injuries and consequences. Inability to move after a fall means that the subject cannot ask for help by himself, which increases the percentage of fall-induced injuries significantly. The objective of this paper is to design and to implement a fall detection and alert system for the elderly persons. It aims to facilitate the help after a fall, by featuring on-demand or automatic communication between them and caregivers. The system consists of a wearable monitoring device. The device is able to accurately distinguish falls from non-falls of elderly persons and then, by using existing proven technologies (GPS, GSM/GPRS), alerts their caregivers. Upon detecting a fall, the embedded system encompassing the accelerometer sensor, the GPS receiver, the processing unit and the GSM module send a warning message alerting others that a fall occurred along with its orientation. In addition, the device is able to alert caregivers that the user has left his place by sending an SMS containing his location (latitude and longitude coordinates) as soon as he crosses a predefined threshold distance. The developed prototype was evaluated and showed satisfactory performance.
The EHG signals are recorded using a multichannel system positioned on the woman's abdomen for the simultaneous recording of 16 channels of EHG. Several studies calculated the features related to EHG propagation by studying the coupling between all possible channels (bivariate analysis). Using all the possible features extracted to characterize propagation, from all possible combinations of channels, lead to a very large dimension of search and to a complex classification. Therefore, the aim of this paper is the selection of the most relevant channel combinations (using Fscore method), that provide the most useful information to discriminate between pregnancy and labor classes. This channel combination selection step is then followed by a feature selection method named genetic algorithm that is used to select the best features (from the propagation features used in this study) from the selected channel combinations. Additionally, we applied these selection steps on bipolar and monopolar EHG signals in order to see which is the best to use for the bivariate analysis.
With the tremendous Internet proliferation, people started to utilize it in their daily life activities. Electronic health (eHealth) is a promising strategy for delivering health care services over the Internet where patients can interact with their health professionals through videoconference sessions to obtain health advices and follow-up information on their health conditions, and exchange views with their health professionals. In this paper, an e-health videoconferencing platform is described along with its potential usage in the Jordanian healthcare system and, in particular, medical centers and hospitals located in the rural areas. The paper also presented some relevant technical and social challenges.
Determination of seizure origin is often challenging due to the rapid speed at which electrical activity propagates throughout the brain. The Directed Transfer Function (DTF) has been proposed and validated as a quantitative approach to determine the flow of seizure activity. In this work, outflow and inflow features are extracted from the DTF matrix and used as inputs to a Kmeans unsupervised clustering approach. Results demonstrate the ability of the proposed methodology in automatically identifying sources and sinks of seizure activity as well as discriminating primary from secondary generators. Such distinction could lead to more tailored surgical resections.
Before few decades disabled persons were not able to perform daily tasks such as turning the light on, making a phone call, and even controlling the TV. Disability was an obstacle therefore disabled individuals needed daily monitoring and service. With the evolution of computation power and the progress in neuronal studies, modern technology and science managed to overcome the human disability for example the ability to walk was restored with the help of fully automated prosthetic legs controlled by brain signals.This work aimed to aid the disabled people that are not able to simply grasp a TV remote control to switch the TV on or browse through the channels; therefore a brain machine interface must be implemented. Low cost portable ElectroEncephaloGraph (EEG) system is designed and tested that allow a person to control the TV through his eye blinks. An overall accuracy of 90% has been obtained in testing 5 TV control events. The total price of the prototype did not exceed the 60 USD.
Locked-in syndrome is known to be a condition in which a patient loses the ability to control nearly all voluntary muscles in the body except for the eye. In today's world, healthcare facilities have the means and equipment necessary to help such patients and take care of their needs, which includes medical care and patient comfort. However, such dedicated professional services are not commonly provided at the patient's dwelling, and more can still be done when it comes to patient's comfort and self-reliance. This paper delineates the design and development of an eye-tracking based home automation system that provides the targeted locked-in patient with the ability to control appliances using his/her eyes. In the developed system, eye movement, pupil position, size, and velocity are determined using a built-in laptop camera in conjunction with a series of algorithms coded in MATLAB®. The camera is adjusted in such a way so as to be leveled horizontally with the eye-sight of the patient. Further algorithms are to allow the user to control and move the mouse cursor with his/her eye movements. A specially designed graphical user interface provides the individual with the options as to what he/she wishes to control. An Arduino microcontroller differentiates the received instructions from the user and provides an output to the intended device. The controlled appliances within the patient's habitat are doors, window shutters, lightings, bed control, television set, and heating ventilation and air-conditioning. Further modular improvement of this system could be introduced as need arises. The system was validated using a series of tests on normal control individuals. The validation results show high accuracy and precision. The significance of this system lies in helping locked-in patients gain control over some aspects of their lives; accordingly, they will no longer require continuous assistance to secure their comfort but rather be self-reliant.
The use of packaging material in biomedical sensors is a required criterion to achieve certain properties; the most important one is biocompatibility. Response time of biomedical sensors is highly dependent on the sensor's specifications in addition to the type of packaging materials. Compensation of the time delay in the sensor's response due to the packaging material requires detailed mathematical model of the governing equations in addition to the knowledge of the different packaging layers properties. In this paper, we present the use of extended Kalman filter to estimate the transient response of the sensor without the need to perform such complex mathematical modeling. The idea is to estimate the required response given the measurements model and the packaging effects model to build nonlinear state-measurements equations. The paper also presents the results obtained from simulated and measured selected sensors responses.
Pattern recognition control applied on surface electromyography (EMG) from the extrinsic hand muscles has shown great promise for the control of powered prosthetics for transradial amputees. The use of limb prostheses is essential for maintaining personal independence and a more effective inclusion in society. However, due to their poor control, imposed by the reduced accuracy of hand movement classification, EMG-driven upper limb prostheses are still not widely used. Hence, post-processing techniques were proposed to reduce the misclassification rates. In this paper, we investigate the effect of two post-processing techniques, namely majority vote and Bayesian fusion, on the performance of EMG-based PR systems when applied on amputees. We measured the effectiveness of a number of time and frequency-based feature extraction methods with different post-processing techniques and various numbers of voting decisions. EMG data was collected from four transradial amputees while imagining seven classes of hand movements. Our results suggested that the recently proposed Time Domain Power-Spectral Descriptors (TD-PSD) can significantly enhance the performance of EMG pattern recognition and that the use of the suggested post-processing techniques can further enhance the performance of EMG-based PR systems, with error rates of approximately 5% on average across all amputees. Additionally, in problems with a large number of EMG channels, no significant differences were observed between the performance of both Bayesian fusion and majority vote.
