Kabir Mamun

CSP-TSM: Optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI

BACKGROUND Classification of electroencephalography (EEG) signals for motor imagery based brain computer interface (MI-BCI) is an exigent task and common spatial pattern (CSP) has been extensively explored for this purpose. In this work, we focused on developing a new framework for classification of EEG signals for MI-BCI. METHOD We propose a single band CSP framework for MI-BCI that utilizes the concept of tangent space mapping (TSM) in the manifold of covariance matrices. The proposed method is named CSP-TSM. Spatial filtering is performed on the bandpass filtered MI EEG signal. Riemannian tangent space is utilized for extracting features from the spatial filtered signal. The TSM features are then fused with the CSP variance based features and feature selection is performed using Lasso. Linear discriminant analysis (LDA) is then applied to the selected features and finally classification is done using support vector machine (SVM) classifier. RESULTS The proposed framework gives improved performance for MI EEG signal classification in comparison with several competing methods. Experiments conducted shows that the proposed framework reduces the overall classification error rate for MI-BCI by 3.16%, 5.10% and 1.70% (for BCI Competition III dataset IVa, BCI Competition IV Dataset I and BCI Competition IV Dataset IIb, respectively) compared to the conventional CSP method under the same experimental settings. CONCLUSION The proposed CSP-TSM method produces promising results when compared with several competing methods in this paper. In addition, the computational complexity is less compared to that of TSM method. Our proposed CSP-TSM framework can be potentially used for developing improved MI-BCI systems.

Design and development of low cost voice control smart home device in the South Pacific

To accomplish control tasks, an emerging innovative method of automation is voice control. In conjunction with Lab VIEW [1] and Windows Speech recognition [2], the two most human interactive activities; drawing of curtains and switching on and off of lights are controlled. This will help in improving living standard by making living easier for elderly people, reducing frustration and increasing independence at senior homes in the South pacific. The price comparison indicates that 81.25% saving can be made with this product in regards to energy consumption.

Remote patient physical condition monitoring service module for iWARD hospital robots

In this paper an intelligent system for remote patient physical condition monitoring service module for an Intelligent Robot Swarm for Attendance, Recognition, Cleaning and Delivery (iWARD) [1] is reported. The system algorithm and module software is implemented in C/C++, and the Orca robotics [2] components use the OpenCV[3] image analysis and processing library. The system is successfully tested on Linux (Ubuntu) platform as well as on a web server. The patient condition monitoring system can remotely measure the following body conditions: body temperature (BTemp), heart rate (HR), electrocardiogram (ECG), respiration rate (RR), body acceleration (BA) using sensors attached to the patients body. The system also includes an RGB video camera and a 3D laser sensor, which monitor the environment in order to find any patient lying on the floor. The system deals with various image-processing and sensor fusion techniques. The iWARD patient condition monitoring module evaluation tests were carried out in front of thirty healthcare professionals (doctors, nurses, nursing lecturers and healthcare assistances etc) during the final review meeting of the consortium and in two teaching hospitals (in Newcastle and San Sebastian, 2009) in Europe. The post iWARD system improved upon the prototype by adding a 3D laser sensor and replacing the original camera with a high quality Pan-Tilt-Zoom (PTZ) camera and implementing the identity detection methods. This allowed for the use of more robust patient condition monitoring algorithms. The outcomes of this research have significant contribution to the robotics application area in the hospital environment.

Application of cepstrum analysis and linear predictive coding for motor imaginary task classification

In this paper, classification of electroencephalography (EEG) signals of motor imaginary tasks is studied using cepstrum analysis and linear predictive coding (LPC). The Brain-Computer Interface (BCI) competition III dataset IVa containing motor imaginary tasks for right hand and foot of five subjects are used. The data was preprocessed by applying whitening and then filtering the signal followed by feature extraction. A random forest classifier is then trained using the cepstrum and LPC features to classify the motor imaginary tasks. The resulting classification accuracy is found to be over 90%. This research shows that concatenating appropriate different types of features such as cepstrum and LPC features hold some promise for the classification of motor imaginary tasks, which can be helpful in the BCI context.

Importance of Computational Intelligent in Proteomics

Computational Intelligent (CI) techniques have become an apparent need in many bioinformatics applications. In this article, we make the interested reader aware of the necessity of CI, providing a basic taxonomy of proteomics, and discussing their use, variety and potential in a number of both common as well as upcoming proteomics application.

Mechatronic design solution for fuel level monitoring using pressure sensor

Liquid levels are measured in a variety of industrial applications, and are often measured manually, which can be labor-intensive as well as time-consuming. Rapid advances in electronic technologies have made a variety of inexpensive sensing, monitoring, and control capabilities available. A mechatronic design solution is produced to solve a practical problem faced by Generation Strategic Business Area at Cawaira power-station, a substation of Fiji Electricity Authority (FEA). A monitoring system is developed, designed and evaluated for automatic measurement and controlling of fuel levels in the fuel supply tanks at this sub-station. The design was demonstrated using a hardware model. The system is composed of a pressure sensor, a microcontroller, solenoid valves and a liquid pump. The pressure sensor measures the pressure inside the air column submerged in the tank, which is then calibrated to display level. The system is designed to read real-time data to measure the fuel level inside the tank as well as programmed with critical event alarms which trigger upon the occurrence of an event such as low fuel inside the tank, reaching maximum safety limit and leakage in the fuel pipe line. The system is being tested using the fabricated model and the system measurement results are verified to those measured manually. This system is inexpensive, easy to build, install, and maintain. In addition to monitoring liquid level, the system could be adapted to a variety of other measurements.

Identifying Energy Trends in Fiji Islands

This chapter intends to simulate the current situation of Fiji Electricity Authority’s transmission network of Viti Levu by using the load flow method and investigate the situation of the overall system. The first part of the chapter focuses on finding out the problems faced by Fiji Electricity Authority with the reliability of the network. After inspecting regions vulnerable to faults, different scenarios have been tested in steady state with different loads in various parts of Viti Levu. Reaction of the network was observed to determine the highest load level that the network can support before collapsing. The second part of chapter proposes recommendations to improve the reliability of the network. These recommendations are tested using the ETAP software in the form of scenarios by incorporating different possible choices with the current network, and the results obtained from each scenario are analyzed. This chapter concludes with the listing of recommendations that can be made in order to do further analysis for future expansion of the network through renewable energy sources (RES).

Development of an automated multi-level car parking system

With the increased development of mechatronics system and scarcity of land space, this paper introduces and prospects an engineering application to solve or reduce the mentioned issue by designing and implementing automated multi-level car parking system. The paper discusses the research antiquity, brief model methodology, software implementation, design analysis and recommendations.

Designing of a mobile irrigation system

This research looks at the design and construction of an Arduino controlled prototype of irrigation system based on a mobile platform/vehicle for agricultural sector. The vehicle is designed to be controlled through an Infrared (IR) remote control with a range of at least 5 meters. The vehicle uses an ultrasonic sensor to avoid collisions and obstacles. This system is mostly manually controlled and the only automatic feature is the spray technique. There is also an option to manually position the sprayer using the remote control to spray either water/pesticide. Two servo motors are used to achieve horizontal and vertical positioning of the spraying nozzle. The vehicle also carries a storage tank through which water/pesticide can be sprayed using DC motor pump controlling via a micro controller. The vehicle has four large wheels controlled by 2 DC motors and these allow the vehicle mobility over rough terrain.

Automatic PCB drilling machine

This paper describes the design and implementation of an automatic PCB drilling machine that can be used for drilling prototype PCB boards. The Model design is described first, and then the paper moves on to the electronic hardware designing phase where each component is explained and then moves on to explain the program logic written for the automatic PCB drilling machine.