M. F. Saaid

Bus detection device for the blind using RFID application

This paper outlines a bus detection mechanism for the blind in travelling from one place to another. In order to get transportation independently, the blind use auditory touched clues like walking stick or white cane. The limitation of the walking stick is that a blind person must come into close proximity with their surroundings to determine the location of an obstacle. For that basis, various devices have been developed such as the Sonicguide, the Mowat sensor, the Laser cane and the Navbelt [4]. However, these device can only assist the blind at a pedestrian crossing. Therefore, the project is aims to develop a bus detection prototype using Radio Frequency Identification (RFID) for the blind. The paper covers brief idea about the blind and RFID system, review relevant papers and summary of current research. The review of RFID system compare between families of auto-ID technology, the basic principle of RFID, the type of RFID tagging and the antenna characteristic. The summary of current research discussed about the development of prototype, the database system, the output mechanism and integration between hardware and software. Database management will provided. The information such as bus route, final destination and bus number are also provided. This paper also describes the future work intended to be done.

Radio Frequency Identification Walking Stick (RFIWS): A device for the blind

The paper outlines the project undertaken in developing prototype of Radio Frequency Identification Walking Stick (RFIWS). The device intended to assist the blind during walking on a sidewalk. Many of the blind people used the traditional method like dog and old design of walking stick as their guide to walk on the sidewalk. The limitation of this method is the blind people must walk closely to the border of the sidewalk and use the walking stick to find out their current location. This will be exposing the blind to the risk like fallout from the sidewalk. The application of RFID will enhance the conventional method in term of detecting and estimating the distance between the blind and the sidewalk border. The project objective is to develop a walking stick prototype by utilizing Radio Frequency Identification (RFID). A review of assistive technology was presented in this paper together with RFID application in China, France and Thailand. This paper also describes a RFID function and its components explicitly a tag, reader and middleware include a relevant frequency for RFID. The experimental works intended in this project will cover antenna polarization, tag performance, tag orientation sensitivity and tag communication distance for ultra high frequency (UHF). The project also includes development of hardware, software and integration of hardware and software.

Detection of cardiomyopathy using multilayered perceptron network

Cardiomyopathy refers to gradual weakening of the muscular walls of the cardiac chambers. Due to the hypertrophic condition of the muscular walls, damage and stretching of the muscle may lead to arrhythmias, which is detectable using the ECG. In the past, any deviations from a healthy rhythm provide cardiologists with accurate information regarding the heart condition. However, cardiologists are prone to making inaccurate interpretation from the visual observation, leading to erroneous diagnosis. Hence, this paper proposes a computerized method for accurate analysis and detection of cardiomyopathy disease using MLP network. Data for normal, cardiomyopathy, and other arrhythmias were obtained from the PTB Diagnostic ECG database. The raw signals were preprocessed for high-frequency noise removal using median and moving average filters. Baseline corrections were conducted using two-stage polynomial fitting method. Nine time-based features were extracted from the three bipolar limb leads. A total of 600 beats were used to train, validate and test five different MLP network structures. Four different learning algorithms were implemented to obtain the best classification accuracy and fastest convergence rate. Results show that the Levenberg-Marquardt algorithm shows the highest average classification accuracy of 98.9% for the different structures with the fastest average convergence rate of 12 epochs.

Identification of cardiomyopathy disease using hybrid multilayered perceptron network

Cardiomyopathy is a progressive disease that affects the muscular walls of the heart. The resultant hypertrophic condition of the cardiac chambers alters the capability of the heart to contract which will then lead to deterioration of cardiac output. The abnormality can manifest itself in the form of an arrhythmic signal detectable by electrocardiogram (ECG). Hence, this paper proposes the hybrid multilayered perceptron (HMLP) network for identification of cardiomyopathy disease. Initially, raw signals were acquired from the PTB Diagnostic ECG database for healthy, cardiomyopathy and other arrhythmias. The ECG underwent a signal preprocessing stage for noise reduction and baseline correction. Then, nine time-based sub-wave descriptors from the bipolar limb leads were retrieved via the median threshold approach. 600 beat samples were then utilized to train, test and validate the performance of the HMLP network. The HMLP network structures were tested for five variations of hidden nodes with four different learning algorithms. Findings indicate that the best convergence rate and detection accuracy are achievable with the Levenberg-Marquardt algorithm. Hence, the results suggest the potential application of HMLP for classification of arrhythmias.

Robust arrhythmia classifier using hybrid multilayered perceptron network

The paper describes a robust approach to model cardiac arrhythmias using the hybrid multilayered perceptron (HMLP) network. Healthy, cardiomyopathy, as well as left and right bundle branch block electrocardiograms (ECG) was obtained from the PTB Diagnostic ECG database. The signals were initially pre-processed for noise removal and baseline correction. 24 morphological descriptors from the bipolar limb leads were used as input to the neural network. 400 beat samples were obtained for each condition. Results show that the Levenberg-Marquardt algorithm attains the fastest convergence. Varying the number of hidden nodes however, has no significant effect on the classification accuracy. Performance comparison shows that the HMLP network is more robust and gives better classification accuracy over the multilayered perceptron (MLP) network. The error convergence meanwhile, indicates a leveled performance.

A development of an automatic microcontroller system for Deep Water Culture (DWC)

Hydroponics method of growing plants is using mineral nutrient solution in water, without soil. Terrestrial plants may be grown with their roots in the mineral nutrient solutions only or in an inert medium. One of the hydroponic types was Deep Water Culture (DWC). Deep Water Culture (DWC) is a hydroponic technique that supplies water which contain nutrient direct to the roots of the plant continuously. This technique will ensure the roots of the plant always submerge in water and oxygen. The advantage of DWC system is highly oxygenated uses less fertilizer and low maintenance cost and monitoring time. In this research, pH value is automatically controlled by pH sensor where a sensor reads the value of water with nutrient in the reservoir and maintained to the requirements needed using solution mixer in the valve. Other than that, water in reservoir is continuously maintained through level control which triggers valve to control water flow into or out from the reservoir. The water level monitoring is important to maintain a suitable water level in reservoir. The methodology in this project consists of six stages namely details of study, hardware identification, software identification, hardware and software interfacing, analysis and troubleshooting, data and result collection. From the experimental test, there is a need of 5.64 ml changes in both acidity and alkalinity range in every 0.312 pH and 0.244 pH.

A statistical approach for orchid disease identification using RGB color

This paper presented a statistical approach for recognition of orchid diseases using RGB color analysis. As for features, the scale infection and black leaf spot disease of the orchid have been chosen in this study. Orchid plant with these two category disease samples were taken from a local home orchid collector and captured using digital camera in a controlled environment. The RGB components are extracted as features and statistical analysis specifically error plot and T-Test are utilized for differentiation between orchid either with scale or black leaf spot disease. Initial findings showed that the proposed method is capable to differentiate these two category diseases.

Investigation on Elman neural network for detection of cardiomyopathy

Deterioration of structure and function of heart muscle is indicative of a degenerative disease known as cardiomyopathy. As a result, the hypertrophic condition of the heart often revealed itself in the form of abnormal sinus rhythm that can be detected via an electrocardiogram (ECG). In order to reduce the risk of misinterpretation by cardiologists, a variety of computational methods have been suggested for automated classification of arrhythmias. This paper proposes to explore Elman neural network for detecting cardiomyopathy. A total of 600 ECG beat samples were acquired from an established online database. Initially, the signals were filtered to eliminate high-frequency interference and perform baseline rectification. Nine time-based descriptors from leads I, II and III were used for training, testing and validation of the network structures. A total of five hidden-node node structures were tested with four different learning algorithms. Results show that all the network structure managed to achieve more than 90% classification accuracy. The fastest convergence was achieved with the Levenberg-Marquardt algorithm with an average of 16 epochs.

Vehicle location finder using Global position system and Global System for Mobile

Each year, the number of stolen vehicle is on the rise. Usually, to prevent theft, a physical type countermeasure is used such as padlock, disk break lock and other more which is a preventive action but it is not enough safe. The objective of this study is to create a controllable system that can display the location of a vehicle using Global position system (GPS) to pin point the location and Global System for Mobile (GSM) as a mean for communicating with the vehicle for ease of finding after a theft attempt. The system is made to test the accuracy of the location that is send to the user when the vehicle is in motion and stationary in the city and suburb. The system is made by combining a micro controller with GPS and GSM, then comparing it with other similar device available in the market like Garmin and a reference website to find the radius of error. The study of proposed device begins by studying IEEE journal about alternative product and the vehicle itself. The hardware and program development is done by research and trial and error as the controller do not interact with both module at the same time, after successfully programming both module, it is combined into a single program with addition of interrupt program. The experiment is done in three set of tests so that the system accuracy can be determine when stationary and in motion on vehicle, output controlling is the test to determine if the controller can be made into anti-theft system. The result of the test concludes that the system can provide standard GPS coordinate when requested via Short Message Service (SMS). The system can also be used to control an actuator.

Principal component analysis and arrhythmia recognition using Elman neural network

Cardiac arrhythmia refers to any abnormal electrical activity in the heart that causes irregular heartbeat. Under clinical settings, the arrhythmias can be monitored non-invasively using the electrocardiogram (ECG). Although reliable, the method is still prone to error due to its dependence on visual interpretation. This paper proposes a computerized method for recognition of cardiac arrhythmia using Elman neural network. 1600 ECG beat samples for healthy, cardiomyopathy, and bundle branch block arrhythmias were acquired from the PTB Diagnostic ECG database. Initially, de-noising and baseline wander rectification were performed using digital filters and polynomial fitting technique. 24 morphological features from Lead I, II and III were obtained through the median threshold method. Principal component analysis was then implemented for feature selection. The dataset were reduced to 15 features and is then used to train, test and validate the Elman neural network structure with four different learning algorithms. The overall network performance is then benchmarked with the original 24 dataset. Results show that both settings attained classification accuracies of more than 95%. In addition, PCA has successfully reduced the feature requirements while simultaneously maintaining the network performance.