Ahmad Ihsan Mohd Yassin

Statistical analysis of parkinson disease gait classification using Artificial Neural Network

The aim of this study is to investigate the parameters that could be used to identify abnormal gait pattern in Parkinsons disease subjects during normal walking. Hence, three types of gait parameters namely basic, kinematic and kinetic are evaluated. Initial findings showed that the average mean of cadence, step length and walking speed for Parkinsons disease patients are lower than normal subjects, while the mean of stride time for Parkinsons disease patients are higher. Further, for kinematic parameter, overall joint angle of hip, knee and ankle mean values are lower for Parkinsons disease patients as compared to normal group. In addition, for kinetic parameter, all mean values of ground reaction force parameters are higher for normal subjects with walking speed contributed as the major determinant. To evaluate the significant features that could be used as identification between PD and normal subjects, statistical analysis is conducted. Hence, based on the statistical analysis results, it was found that step length, walking speed, knee angle as well as vertical parameter of ground reaction force are the four significant features as indicators for classification of subject with Parkinsons disease based on the accuracy attained with Artificial Neural Network as classifier.

Monitoring of Watermelon Ripeness Based on Fuzzy Logic

The aim of this study is to monitor watermelon ripeness based on image processing technique and fuzzy logic as classifier. The RGB color technique is utilized as the extracted features for the watermelon’s rind. Further, the extracted feature is classified using fuzzy logic system to determine the ripeness level of the watermelon. In addition, the same set of watermelons is graded by both human expert and fuzzy logic system for comparison purpose. Results attained demonstrate the ability of the proposed method in grading and classifying ripeness of watermelons.

Optimized Support Vector Machine for classifying infant cries with asphyxia using Orthogonal Least Square

This paper investigates the effect of optimizing Support Vector Machine, with linear and RBF kernels, on its performance in classifying asphyxiated infant cries, with Orthogonal Least Square. Mel Frequency Cepstrum analysis first extracts feature from the infant cry signals. The extracted features are then ranked in accordance to its error reduction ratio with OLS. SVM with linear and RBF kernel then classify the asphyxiated infant cry from the optimized and non-optimized input feature vector. The classification accuracy and support vector number are used to gauge the performance. Experimental result shows that for both kernels, the OLS-optimized SVM achieve equally high classification accuracy with lower support vector number than the non-optimized one. It is also found that the OLS-SVM with RBF kernel outperformed all other methods with classification accuracy of 93.16% and support vector number of 266.2.

MySQL Database for Storage of Fingerprint Data

This project presents MySQL database for storage of fingerprint data. The application of the database is for future process, fingerprint matching. In this project, Matlab R2009 is the software used for fingerprint image enhancement and minutia extraction. MySQL is a relational database management system (RDBMS) that runs as a server providing multi-user access to a number of databases. XAMPP Control Panel V2.5 software is also used for free and open source cross-platform web server package, consisting mainly of the Apache HTTP Server, MySQL database, and interpreters for scripts written in the PHP and Perl programming languages. It is found that this project shows an efficient and practical data storage of fingerprint.

Anomalous gait detection based on Support Vector Machine

Support Vector Machine is amongst the popular machine classifier due to its rigorous theory background and remarkable generalization performance. Hence, in this paper, the performance of SVM is evaluated to classify gait abnormalities due to Parkinson disease based on three kernels namely radial basis function, polynomial as well as linear. In addition, two types of normalization is applied to these gait data namely intra group norm and inter group norm. Initial findings showed that basic spatiotemporal parameters found to be the most significant features. Results also proven that intra group norm and RBF kernel are capable to to be used in detecting anomaly gait pattern between normal and PD patients based on the accuracy rate attained.

Development of an Alzheimer's Disease genetic database for Malaysian patients

Web database is a convenient way of sharing and retrieving data as well as a key component of the information system infrastructure of todays modern research. In medicine, web databases on various diseases are valuable tools to facilitate the search for effective treatment. Alzheimers Disease (AD) is a neurodegenerative disease that has received significant focus in research worldwide. Currently, medical professionals rely on foreign AD databases with no relevant biodiversity with Malaysian patients with different genetic elements. We present the development work of a web database to store genetic information of Malaysian AD patients based on biodiversity. The three-tier architecture was used, consisting of the client-side presentation logic, and server-side business logic and database. It is envisaged that, the proposed web database would assist Malaysian medical professionals in finding the effective treatment for AD.

MAP: The new clustering algorithm based on multitier network topology to prolong the lifetime of wireless sensor network

Wireless sensor network and its applications are interesting research that have been focused recently. Battery consumption of sensor nodes is the main problem in the family of wireless sensor that should be solved. So, to increase the scalability of the network, and to reduce the energy usage for overall sensor operations, clustering techniques and data aggregation are the main focus in this paper. The multi tier techniques has been designed precisely and the selection of the cluster head using Fuzzy Logic based on the three selected parameters are well used along with its limited resources of wireless sensor network. In this study, the main primary and secondary cluster head are the important entities of the algorithm for receiving and transmitting data to the base station. The contribution of this paper is mainly on the selection of a secondary cluster head and the routing protocol which the data transmission will involved the nearest cluster head for both tier one and tier two. Due to multi tier clustering in sensor network, the operations of the sensor network will eventually increase the lifetime of the network compared to LEACH and SEP protocols.

Choice for a support vector machine kernel function for recognizing asphyxia from infant cries

This paper investigates the performance of several kernel functions of support vector machine in detecting asphyxia from infant cries. In this study, Mel frequency cepstrum coefficients derived from the recorded infant cries were used as the input vectors. These input vectors were trained and classified using support vector machine. Four types of kernels - linear, quadratic, polynomial and radial basic function, were experimented and compared. Accuracy, sensitivity and specificity were adopted as criteria to obtain the best kernel. Experimental results showed that radial basic function kernel (σ = 35) is the best kernel with an accuracy of 85.15%, sensitivity of 91% and specificity of 71%.

Real-Time Remote Monitoring with Data Acquisition System

The purpose of this system is to provide monitoring system for an electrical device and enable remote monitoring via web based application. This monitoring system allow the user to monitor the device condition from anywhere as the information will be synchronised to the website. The current and voltage reading of the monitored equipment, ambient temperature and humidity level are monitored and recorded. These parameters will be updated on the web page. All these sensor are connected to the microcontroller and the data will saved in micro secure digital (SD) card and send all the gathered information to a web page using the GPRS service connection synchronously. The collected data will be displayed on the website and the user enable to download the data directly from the website. The system will help user to monitor the devices condition and ambient changes with ease. The system is successfully developed, tested and has been installed at residential area in Taman Cahaya Alam, Section U12, Shah Alam, Selangor, Malaysia.

The Combinations of Selected Parameters to Prolong the Network Lifetime for Cluster Head Selection in Wireless Sensor Network

In Wireless Sensor Network, parameter selection is one of the important considerations to help the usage of the energy while selecting the cluster head in clustering scheme. This paper proposed the right combination of the parameter to select the cluster head in order to minimize the total energy consumption required for data collection and aggregation. We proposed three parameters which are residual energy, centrality and communication cost and blended all together using Fuzzy Logic method. By using these proposed parameters, we will able to compare the energy usage for each of the nodes with LEACH and SEP algorithm. Simulation results show that, the right combination of parameters may produce good results and tends to prolong the lifetime of the sensor network.