Now showing 1 - 10 of 17
  • Publication
    Classifying white blood cells from a peripheral blood smear image using a histogram of oriented gradient feature of nuclei shapes
    Researchers developed various methods and algorithms to classify white blood cells (WBCs) from blood smear images to assist hematologists and to develop an automatic system. Furthermore, the pathological and hematological conditions of WBCs are related to diseases that can be analyzed accurately in a short time. In this work, we proposed a simple technique for WBC classification from a peripheral blood smear image based on the types of cell nuclei. The developed algorithms utilized a histogram of oriented gradient (HOG) feature typically known for application in human disease detection. The segmentation of WBC nuclei utilizes a YCbCr color space and K-means clustering techniques. The HOG feature contains information about the cell nuclei shapes, which then is classified using a support vector machine (SVM) and backpropagation artificial neural network (ANN). The results show that the proposed HOG feature is useful for WBC classification based on the shapes of nuclei. We are able to categorize the type of a WBC based on its nucleus shape with more than 95% accuracy.
  • Publication
    Electromyography Signal Pattern Recognition for Movement of Shoulder
    ( 2021-11-25) ; ; ;
    Muhammad Asymawi Mohd Reffin
    ;
    ;
    Chong Yen Fook
    Pectoralis major and deltoid are two muscles that are associated with the movement of the shoulder. Electromyography (EMG) signal acquired from these two muscles can be used to classify the movement of the shoulder based on pattern recognition. In this paper, an experiment for EMG data collection involves eight healthy male subjects who perform four shoulder movements which are flexion, extension, internal rotation and external rotation. Feature extraction of EMG data is done using root mean square (RMS), variance (VAR) and zero crossing (ZC). For pattern recognition, the classifiers that are used are Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA). Classification results shows highest accuracy on ZC feature using an SVM classifier with cubic kernel. The study on shoulder movement using EMG of pectoralis and deltoid muscles could be extended on arm amputees based on hypothesis that the EMG signal could be utilized for control of robotic prosthetic arm.
      1
  • Publication
    An Open-Source, Miniature UV to NIR Spectrophotometer for measuring the transmittance of liquid materials
    ( 2022-01-01) ; ; ;
    Fook Chong Yen
    ;
    Basri Noor Cahyadi
    The primary disadvantages of commercial spectrophotometers are expensive, heavy, and not portable. Furthermore, conventional instruments are only suitable to be used in a specialized laboratory. Even though some commercially available small-size instruments or devices are available, the price is still high. Therefore, a low-cost device is necessary without sacrificing accuracy and sensitivity. In this work, a low-cost, configurable, open-source and accurate portable spectrophotometer device was developed for education and laboratory analytical use. Commercially available photodetector is utilized as main component of the device due to broad spectral range from ultraviolet to near infra-red. The device performs well over a wide range of spectral wavelengths with small errors. We presume that the use of this work can offer a alternative for affordable and accurate device that is comparable to the commercially available products which also suitable for many applications.
      1
  • Publication
    Classification of White Blood Cells Based on Surf Feature
    Conventional blood analysis using blood smear image were performed manually by experts in hematology is tedious and highly depending on the level of experience. Currently, computer-assist technology is developed to reduce the time-consuming process and improved accuracy. As an example, various image processing techniques used to quantify such as white blood cells (WBCs) morphological conditions or classification in the blood smear image, which assist experts in developing confidence decision making in the analysis of cells conditions linked to the specific diseases. However, the WBCs shape features are arbitrary than the red blood cells (RBCs) because of the maturation state, cell orientations or positions, cell color variations, and the quality of the image captured influences the performance of classification accuracy. Therefore, we proposed a scale and rotation invariance feature for WBCs classification using speed up robust feature (SURF). SURF is suitable to be applied in identifying objects even though the orientation, scale, and position are varying, such as WBCs in microscopic blood smear images. We analyzed the classification performances using a support vector machine (SVM) and an artificial neural network (ANN) of WBCs types in the microscopic image based on the cell nucleus. The results show that the purposed SURF feature method has an excellent performance of accuracy for both methods and suitable to be utilized for the application of cell types classification.
      1
  • Publication
    We-VoltamoStat: A wearable potentiostat for voltammetry analysis with a smartphone interface
    ( 2023-09-01)
    Ibrahim N.F.A.
    ;
    ; ; ;
    Wahab A.A.
    ;
    Manaf A.A.
    ;
    Wearable technology, such as electronic components integrated into clothing or worn as accessories, is becoming increasingly prevalent in fields like healthcare and biomedical monitoring. These devices allow for continuous monitoring of important biomarkers for medical diagnosis, monitoring of physiological health, and evaluation. However, an open-source wearable potentiostat is a relatively new technology that still faces several design limitations such as short battery lifetime, bulky size, heavy weight, and the requirement for a wire for data transmission, which affects comfortability during long periods of measurement. In this work, an open-source wearable potentiostat device named We-VoltamoStat is developed to allow interested parties to use and modify the device for creating new products, research, and teaching purposes. The proposed device includes improved and added features, such as wireless real-time signal monitoring and data collection. It also has an ultra-low power consumption battery estimated to deliver 15 mA during operating mode for 33 h and 20 min and 5 mA during standby mode for 100 h without recharging. Its convenience for wearable applications, tough design, and compact size of 67x54x38 mm make it suitable for wearable applications. Cost-effectiveness is another advantage, with a price less than 120 USD. Validation performance tests indicate that the device has good accuracy, with an R2 value of 0.99 for linear regression of test accuracy on milli-, micro-, and nano-Ampere detection. In the future, it is recommended to improve the design and add more features to the device, including new applications for wearable potentiostats.
      1
  • Publication
    Classification of electromyography signal from residual limb of hand amputees
    Several researchers had worked on collecting electromyography (EMG) signal from amputees and come out with dataset that could be utilized for study in EMG signal processing and classification for decoding of amputee movement intention. This paper presents the work on classification of EMG signal based on the residual limb of amputees with intuitive hand movement based on interactive exercises. Dataset is obtained from NINAPRO public database website where 11 amputee subjects performed intuitive exercise of 17 hand gestures and EMG signal is acquired from the residual arm. Eight feature extraction methods are performed to obtain the EMG feature which are Mean, Minimum, Median, Skewness, Kurtosis, Approximate Entropy, Fuzzy Entropy and Kolmogorov Complexity. Two classifiers are used for EMG classification which are k-Nearest Neighbour and Ensemble classifier. Results shows average accuracy of 87.65% with Ensemble classifier for classification of movement exercise with all features of EMG is used as input to classifier.
      1
  • Publication
    Intraocular MEMS Capacitive Pressure Sensor
    Microelectromechanical system (MEMS) sensors are suitable for measuring intraocular pressure (IOP). IOP measurement is useful for monitoring diseases such as glaucoma. The average pressure range for healthy persons is within 10–20 mmHg. A pressure beyond this range could damage the eye nerves and causes of blindness. Thus, a sensor for measuring the pressure should provide excellent accuracy and sensitivity. Intraocular capacitive pressure sensors are widely used in measurement of IOP. They offer high sensitivity and low noise, including invariance to temperature. Thus, the capacitive pressure sensor is performed better than other types of sensing methods. In this work, capacitive pressure sensors are designed and analyzed using FEM. The sensitivity and performance of a corrugated diaphragm, slot-type, square, and circular types of sensors designed are analyzed. Different shape of the sensor provides a different characteristic such as sensors pressure sensitivity, mechanical stress, and maximum deflection. As a result, corrugated diaphragm and slot-type sensors designed performs better than the flat diaphragm and non-slotted sensors designed. We show that four slotted non-corrugated square and circular designs have a high sensitivity, which is 0.157 mF higher than the eight slotted design. However, for corrugated design, eight slotted shows sensitivity is 0.147 mF higher and linearity analysis than four slotted sensor design. Circular shape design for eight slotted design, on the other hand, have 0.631 mF higher than the four slotted design. Corrugated design is more sensitive when a load is applied, while slotted design reduces the effect of residual stress and stiffness of the diaphragm. Thus, it is an advantage of using the FEM method for further analysis of sensor performance optimization.
      1
  • Publication
    Numerical Simulation of Transdermal Iontophoretic Drug Delivery System
    Transdermal Iontophoretic Drug Delivery System (TIDDS) is a non-invasive method of systemic drug delivery that involves by applying a drug formulation to the skin. The drug penetrates through the stratum corneum, epidermis and dermis layers. Once the drug reaches the dermal layer, it is available for systemic absorption via dermal microcirculation. However, clinical testing of new drug developed for the iontophoretic system is a long and complex process. Recently, most of those major pharmaceutical companies have attempted to consider computer-based bio-simulation strategies as a means of generating the data necessary to help make a better decision. In this work, we used computational modelling to investigate the TIDDS behaviour. Our interest is to study the efficacy of drug diffusion through transdermal delivery, including the thermal effect on the skin. We found that drug will be delivered more efficiently if the electrical potential and the position of electrodes are optimum. We analysed the drug diffusion time of the system using 1,3 and 5 mA DC source. In addition, we also modify the electrode distance from 10 mm to 30 mm long and analysed the effect of delivery time and d effect to the skin thermal. We conclude that, a high electrical current, as instance, a 5 mA DC, delivered the drug faster into the skin but increased the skin temperature because of skin joule heating effect. However, a 30 mm electrodes distance setting decreased the skin temperature significantly than the 10 mm distance with more than 9.7 °C under 5 mA DC and 60 minutes of operation. TIDDS enhanced drug delivery compared to oral consumption and might be suitable used for localizing treatments such as chronic disease. This work provides great potential and is useful to efficiently design of iontophoretic drug delivery system including new drugs delivery applications.
      1
  • Publication
    Single Channel Magnetic Induction Measurement for Meningitis Detection
    ( 2021-01-01)
    Aiman Abdulrahman Ahmed
    ;
    ;
    Ali M.H.
    ;
    Pusppanathan J.
    ;
    Rahim R.A.
    ;
    Muji S.Z.M.
    ;
    ; ; ; ;
    Ahmad Faizal Salleh
    Bacterial meningitis is one of the most common and prominent infections which infects the central nervous system through the tissue layers and membranes that cover our brain and spinal cord. It is a staggering and fatal illness that kills patients within hours. The number of meningitis cases that has been recorded annually around the world are one million cases and 135,000 deaths. Early detection and start of sufficient treatment are considered as the main determinants for better result. MIT mechanism is noncontact electrodes of impedance measurement. This mechanism uses induction principle instead of contact electrodes to get the required information. This paper presents an overview on the potential of Magnetic induction tomography (MIT) in detecting meningitis disease. In MIT principle, single channel measurement process which consist of transmitter (Tx) and receiver (Rx) coil has been studied. In this field is disclosed about passive electrical field (PEP) which focuses on the three parameters which are dielectric permittivity, electrical conductivity, and magnetic permeability. In addition, this research project involves experimental setup. The applied frequency is between 1–10 MHz. Finally, in this project, the performance of the square coil with 12 number of turns (5Tx–12Rx) with 10 MHz frequency has been identified as the suitable transmitter-receiver pair and the optimum frequency for detecting the conductivity property distribution of brain tissues.
      1
  • Publication
    Design and evaluation of Magnetic Induction Spectroscopy probe for pH measurement in fetal hypoxia using COMSOL Multiphysics Simulation
    ( 2022-01-01)
    Siti Fatimah Abdul Halim
    ;
    Zakaria M.H.
    ;
    ;
    Aiman Abdulrahman Ahmed
    ;
    ; ;
    Jaysuman Bin Pusppanathan
    ;
    ;
    Siti Zarina Mohd Muji
    ;
    Ruzairi Abdul Rahim
    Fetal Blood Sampling (FBS) is the term used to describe the current method of monitoring the foetal condition within the mother’s womb. FBS required the medical officer to make a small incision on the foetus’s head in order to collect blood for analysis of the blood pH level in order to prevent acidosis or foetal hypoxia. The FBS method, on the other hand, is invasive and increases the risk of infection for both mother and child. Magnetic Induction Spectroscopy (MIS) is a novel method for diagnosing the foetus’s pH level that is non-invasive and non-intrusive. A single channel MIS system is composed of a transmitter (TX), a receiver (RX), and an electrical circuit that generates and receives magnetic fields in response to the conductivity of the sample (blood) due to the presence of weak electrolytes (H+ and OH-). The purpose of this research is to develop and evaluate five different designs of TX-RX coils. The coils are designed using the Planar Zero Flow Coil (PZFC) concept, which allows for multiple coil configurations and input-output configurations. The results show that Design 2 open set model was the optimal coil design for MIS system probe, as well as some contributions to the pH evaluation process.
      7  5