Data Acquisition System and Pattern Image Generations for Hand Grip Device

Grip pattern is essential to understand how an object being held in hand. One of the solutions is to use the pressure sensing glove to capture the gripping pressure distributed on the surface of the palm. The objective of this project is to develop a data acquisition system for a gripping device that can capture the grip patterns when a person is gripping an object. The design comprises of Velostat sheet, rows, and columns of conductive threads, that are sandwiched and layered to form a glove with pressure sensor grids. Arduino is used to generate the signals for data acquisition and interface with the MATLAB program through serial communication. On the MATLAB, the sensor data are organized and represented in hand pattern color image. Voltage Divider Rule (VDR) was used in an experiment with different resistor values and the effect of the image patterns were observed. Another experiment has been designed to find out the grip consistency. The results show that resistor values 330ohm can cause the image pattern create noises. Meanwhile, 4.7kohm resistance value is sufficient to eliminate most of the noises made in the pattern images. In this paper, different grip images can be obtained from different grip activities, such as holding toothbrush, lifting dumbbell, and pressing syringe. Future works can be done in resolution improvement and grip pattern recognition.

Real Time Fire Detection System with Image Processing

Fire detectionsystemby image processing is a growing research in this era. There are many methods used to detect fire out, butstill need to develop an accurate method to detect fire without false alarms. This is due to the fact that many methods used RGB colour mode for detection. In this paper, mainly focuson detecting the fire effectively using thermal video from a thermal camera while in the same time the system will alert the people if fire was detected,and also observed the speed of the fire.This will enormouslybenefitto the fire fighters.With thissystem, thefire can be detected effectively while alerting the people and giving valuable information to the fire fighters fortheir job more effectively.

Conditional Noise Filter for MRI Images with Revised Theory on Second-order Histograms

Previous research by the author has the theory that histograms of second-order derivatives are capable of determining differences between pixels in MRI images for the purpose of noise reduction without having to refer to ground truth. However, the methodology of the previous research resulted in significant false negatives in determining which pixel is affected by noise. The theory has been revised in this article through the introduction of an additional Laplace curve, leading to comparisons between the histogram profile and two curves instead of just one. The revised theory is that differences between the first curve and the histogram profile and the differences between the second curve and the profile can determine which pixels are to be selected for filtering in order to improve image clarity while minimizing blurring. The revised theory is tested with a modified average filter versus a generic average filter, with PSNR and SSIM for scoring. The results show that for most of the sample MRI images, the theory of pixel selection is more reliable at higher levels of noise but not as reliable at preventing blurring at low levels of noise.

Development of Brain Balancing System for Left and Right Hemispheres

This paper presents the design of Mini Brain Games (MBGs) to improve either the left or right hemisphere of the brain. The MBG includes spot the difference, piano, block view, word building, word scrambler, sudoku, left hand control, memory card, flash card, crossword, math logic and mnemonics technique used for the order of operations in algebra, the planets in solar system, and resistor color code. Stroop test and brain dominance test are used to measure the level of balance between the two hemispheres of the brain before and after the exercise program. The mini brain games designed in the Brain Balancing System Windows Application are shown to improve the balance between the left and right hemisphere of the brain. The results show that the mini brain games are indeed able to assist in the left or right brain development. The largest improvement achieved is that the percentage of dominance between the two brain hemispheres is reduced by 18.18%. The smallest improvement achieved was that the difference between the two brain hemispheres was reduced by 9.08%.

Development of Continuous Blood Pressure Measurement System Using Photoplethysmograph and Pulse Transit Time

It is not only a problem for old age anyone. So, blood pressure is the one provides importance information with vital signs about cardiovascular health using oscillometric method. Unfortunately, this method required inflation and following deflation of the cuff. This method only gives instantaneous blood pressure and continuous measurement is not available. It is not available to the patients that required long term monitoring. To overcome this problem, the development of Continuous Non-Invasive Blood Pressure (NIBP) algorithm based on Pulse Transit Time (PTT) using two channel Photoplethysmograph (PPG) is proposed in this study. PPG is a non-invasive device for detecting blood volume changes can be affected by various physiological factors, analysis of the PPG signal can provide sufficient information on the human health condition; more specifically their cardio-vascular related performance. Literatures show that the PTT has linear relationship with blood pressure. Nevertheless, the determination of the model structure, order and real-time implementation to offer a continuous measurement of the PTT still remains challenging tasks in this area. PTT can be as index to monitor cardiovascular disease. In this project, dynamic model based on pulse transit time will be proposed to continuously monitor blood pressure by using PPG signals. Different kind of resolutions in microcontroller combined with PPG sensor will be used as well. MATLAB software is also been applied for PTT calculation based on two PPG sensors. PPG is method for detect blood volume changes with optical source transmitter send from one end and received the signal from another by receiver through body tissue as medium. MATLAB functions as Digital Signal Processing (DSP) for signals received in computer. Linear Regression technique and Fung's algorithm are applied to obtain the best fit line for all the points in order to systolic and diastolic blood pressure measurement. The results showed that the algorithm based on pulse transit time has been developed for the assessment of blood pressure and justify patient’ condition with 86.34% and 88.20% accuracy. Finally, this technique is a simple, user friendly and operator independent PPG system suitable for long term and wearable blood pressure monitor.

A Contactless Visitor Access Monitoring System

This project presents a contactless visitor access monitoring in small premises which implemented deep learning model in face recognition, develop the graphical user interface (GUI) for new visitor registration and visitor identification. Five stages of monitoring process are designed in the contactless visitor access monitoring (CVAM) GUI, the first step is to give instructions to the admin user regarding the monitoring process, the second step is to perform face recognition, the third step is to scan the body temperature, the fourth step is to perform mask detection on the visitor, and the final stage is to record visitor access time. Another visitor registration (VisReg) GUI is designed to register new visitors into the system. In VisReg, admin user is required to pre-process face images with MTCNN technique and generate new classifier with a ResNet pre-trained model. The contactless visitor access monitoring process is demonstrated. The face recognition gives an accuracy of 82%, while the mask detection gives an accuracy of 95% when tested with the validation dataset. It can be concluded that the visitor monitoring process can be carried out in a contactless way to eliminate the close contact between the security officers, receptionist, and visitors.

Protein Concentration Determination in Latex Glove Using Biocompatibility Morphological Mean Test

Latex gloves are seen as an indispensable item in the healthcare field because it offers superior protection for both the medical staff and patient against harmful substances. However, latex gloves with high protein concentration have a high possibility to induce latex allergy which in the worst case can lead to a life-threatening condition. To minimize the occurrence of an allergy reaction, the computerized Biocompatibility Morphological Mean (BMM) test for protein detection is proposed. This test initially goes through the chemical process to determine the protein that resides in the glove sample. After that, the sample is electronically converted into a digital image. Finally, the image undergoes color image processing for calculating the color difference values. These values are then plotted on a standard curve. A high correlation coefficient (R2>0.97) of the standard curve gives better accuracies. The proposed method only takes about 40 minutes to complete the test, while existing methods need at least 6 hours.

Testing of Auditory Clinical Alarms in ICU/CCU

Almost all medical devices in ICU/CCU have a built-in clinical alarm system to alert when there are changes in a patient’s condition. The objective of this study is to investigate the effectiveness of the existing alarm system in ICU/CCU. Two summative usability tests were conducted to test the effectiveness of existing and new alarm signals based on IEC 60601-1-8:2006 standard. Further formative test is conducted to study the perception of urgency associated with a number of tones in the alarm signals. The findings indicate that the existing auditory alarm signal in ICU/CCU does not indicate the urgency of the alarm conditions. The simulation test indicates that the respondents preferred 282Hz, 500Hz and 800Hz for low, medium and high-risk alarm respectively. The one-sample proportion z test on urgency mapping indicates that the proportion of responses for the highest risk is more than 50% for a single tone test signal. These results show that a single tone test signal being perceived as the highest risk is regardless of frequency. It can be concluded the auditory alarm designed based on this IEC 60608-1-8:2006 standard is not effective. As such it is proposed that the incorporation of the new alarm frequencies and tones will improve the effectiveness of the alarm signal

Performance Evaluation of Capacitive Based Force Sensor for Electroencephalography Head Caps

Accurate electrode signal measurement using EEG head caps can only be achieved through sufficient contact or force. A flexible force sensor is required to obtain accurate force measurement underneath EEG head caps. In this study, we evaluate the performance of a capacitive based sensor including its accuracy, repeatability, hysteresis, and stability. The result shows that accuracy error and repeatability error were 3.03±2.8 % and 3.84±2.92 %, respectively. The stability errors were 2.37±0.15 %(10 gram), 2.54±0.00 % (50 gram), 2.37±0.15 % (100 gram), 5.07±1.16 % (150 gram), 7.27±0.39 % (200 gram). The hysteresis error of the sensor was 4.48±0.47 %. Based on the results, the capacitive based force sensor provides sufficiently low errors in accuracy, repeatability, stability, and hysteresis and is thus suitable for measuring adduction force in EEG cap applications

Development of Visual-based Rehabilitation Using Sensors for Stroke Patient

This project concerns on the development of applications using sensors for the rehabilitation of stroke patients. Thus, the leap motion sensor is employed for the finger motor rehabilitation training while the Microsoft Kinect sensor is utilized for the upper limb motor rehabilitation. Two applications which are named ‘Pick and Place’ and ‘Stone Breaker’ are developed. For the first application, the patient is required to pick up the virtual blocks and stack it up. The ‘Stone Breaker’ game requires the patient to move the upper limb in controlling the paddle movement in the game. At the end of the project, it is able to achieve the dominant objective of the project when the tested patient shows significant improvement in both the application