Asnor Juraiza Ishak

Pressure Sensor: State of the Art, Design, and Application for Robotic Hand

We survey the state of the art in a variety of force sensors for designing and application of robotic hand. Most of the force sensors are examined based on tactile sensing. For a decade, many papers have widely discussed various sensor technologies and transducer methods which are based on microelectromechanical system (MEMS) and silicon used for improving the accuracy and performance measurement of tactile sensing capabilities especially for robotic hand applications. We found that transducers and materials such as piezoresistive and polymer, respectively, are used in order to improve the sensing sensitivity for grasping mechanisms in future. This predicted growth in such applications will explode into high risk tasks which requires very precise purposes. It shows considerable potential and significant levels of research attention.

A sensitivity study of piezoresistive pressure sensor for robotic hand

In this paper, we have studied and surveyed the field of robotic hand and the works that have been done in this area related to types of materials such as piezoresistive, piezoelectric and capacitive as well as a few types of pressure sensors. It indicates that piezoresistive pressure sensor is the best technique that can be used to implement a robotic hand for pick and place application. An adequate experiment of pressure sensor interfacing and calibration have been done in this paper. As a preliminary result of the works, output voltage (V) of the pressure sensor versus applied force input (N) are presented. Furthermore, this framework can be used to derive a new approach of pressure sensor distribution on the robotic hand based on complex algorithm of controlling applied pressures.

Real-Time Monitoring System for Parking Space Management Services

Real-Time Monitoring System for Parking Space Management Services is the evolution of traditional parking system that it does not only provide live information to users in order to make it easy for them to look for vacant parking lot, it also give authority to operators to monitor and perform simulations to illustrate the real parking system. The purpose of this project is to apply the principles of queue theory into parking system modeling. The queue system model enables the predictions of arrival and service time in the system through analysis and calculations. Aside of it, Graphical User Interface (GUI) is also designed and integrated into the parking system in order to allow parking zone operators to monitor the status of the parking lots and view the statistics of arrival rate, service time and so on. This project focuses on the system modeling and software development and implementation. It is expected that this project will be able to assist parking zone operators in designing their system that will work efficiently and generate high income. It will also provide convenience to the operators in managing the parking zone remotely. Users will also experience a time-saving and stress-free parking zone.

Classification of surface electromyographic signal using fuzzy logic for prosthesis control application

This paper describes the classification stage of an electromyographic (EMG) control system for prosthetic hand application. Moving ApEn was used as main method to extract features from the two channels of surface EMG signal at the forearm of the upper limb. A fuzzy logic system is used to classify the extracted information in discriminating the final grip posture. The results demonstrate the ability of the system to classify the information related to different grip postures.

Wavelet-based feature extraction technique for fruit shape classification

For export, papaya fruit should be free of defects and damages. Abnormality in papaya fruit shape represents a defective fruit and is used as one of the main criteria to determine suitability of the fruit to be exported. This paper describes a wavelet-based technique used to perform feature extraction to extract unique features which are then used in the classification task to discriminate deformed papaya fruits from well formed fruits using image processing approach. The extracted features, when used in the classification task using linear discriminant analysis (LDA), afford accuracy of more than 98%.

Weed detection system using support vector machine

In the oil palm plantation in Malaysia, typically blanket spraying is applied to a whole field without regard to the species and location of the weeds in the field. This practice is uneconomical since some areas where no or few weeds exist will receive just as much herbicides as those areas with high densities of weed infestation. Many of these chemical are soil-applied herbicides which easily absorb to ground water and surface water supplies. To control the weed grow and to solve the problems, automatic weed detection system need to be employed. This paper presents the results of automatic classification of broad and narrow weed using feature vector extracted using a combination of Gabor filter and FFT, and classifier using the support vector machine (SVM) Results obtained revealed that the proposed technique results in higher classification accuracy compared to other techniques.

Multichannel EMG data acquisition system: Design and temporal analysis during human ankle joint movements

This paper presents the implementation of four channel Electromyography (EMG) signal acquisition system for acquiring the EMG signal of the lower limb muscles during ankle joint movements. Furthermore, some post processing and statistical analysis for the recorded signal were presented. Four channels were implemented using instrumentation amplifier (INA114) for pre-amplification stage then the amplified signal subjected to the band pass filter to eliminate the unwanted signals. Operational amplifier (OPA2604) was involved for the main amplification stage to get the output signal in volts. The EMG signals were detected during movement of the ankle joint of a healthy subject. Then the signal was sampled at the rate of 2 kHz using NI6009 DAQ and Labview used for displaying and storing the acquired signal. For EMG temporal representation, mean absolute value (MAV) analysis algorithm is used to investigate the level of the muscles activity. This data will be used in future as a control input signal to drive the ankle joint exoskeleton robot.

Impact of feature extraction techniques on classification accuracy for EMG based ankle joint movements

EMG based control becomes the core of the pros-theses, orthoses and rehabilitation devices in the recent research. Though the difficulties of using EMG as a control signal due to the complexity nature of this signal, the researchers employed the pattern recognition technique to overcome this problem. The EMG pattern recognition mainly consists of four stages; signal detection and preprocessing feature extraction, dimensionality reduction and classification. However, the success of any pattern recognition technique depends on the feature extraction and dimensionality reduction stages. In this paper time domain (TD) with 6th order auto regressive (AR) coefficients features and three techniques of dimensionality reduction; principal component analysis (PCA), uncorrelated linear discriminant analysis (ULDA) and fuzzy neighborhood preserving analysis with QR decomposition (FNPA-QR) were demonstrated. The EMG data were recorded from the below knee muscles of ten intact-subjects. Four ankle joint movements are classified using three classifiers; LDA, k-NN and MLP. The results show the superiority of TD&6th AR with FNPA-QR and k-NN combination with (96.20% ± 4.1) accuracy.

Weed Detection utilizing Quadratic Polynomial and ROI Techniques

Machine vision for selective weeding or selective herbicide spraying relies substantially on the ability of the system to analyze weed images and process the extracted knowledge for decision making prior to implementing the identified control action. To control weed, different weed type would require different herbicide formulation. Consequently the weed must be identified and classified accordingly. In this work, weed images were classified as either broad or narrow weed type. A fundamental problem in weed image recognition using planar curve analysis is to detect curve. It is difficult to successfully extract curve from the image of weed edges since the appropriate scale to use for extraction is not known a priori. As such, this paper considers a curve detection method based on the quadratic polynomial technique which include the use of the region-of- interests (ROI) technique. The ROI technique creates image subsets by selecting regions of the displayed image. The ROIs are typically used to extract statistics for image operations such as classification. As such, the objective of this paper is to present a novel application of curve detection feature extraction technique in weed classification.

Recommended surface EMG electrode position for wrist extension and flexion

To obtain a high-quality surface electromyography (EMG) recording, the signal must be acquired as far as possible from the muscle innervation and tendon zone. This study presents a technique to indicate better electrode positions for surface EMG of the upper limb muscles during wrist extension and flexion. Ten volunteers participated in this research. Surface EMG signals were collected from flexor carpi radialis and extensor carpi radialis muscles. Three different electrode positions with 2 cm internal distance between the bipolar electrodes were investigated. The duration of muscle contraction was selected using the mean absolute value method for quantification, and the qualitative signal was observed through visual inspection. The power spectral density and signal-to-noise ratio were applied to compare and select the most feasible electrode position. The optimal signal from the flexor carpi radialis muscles was presented at 90%. The optimal position for the extensor carpi radialis muscles was shown at 90% of the electrode position over the forearm length. The presented method should be observed as an important step in every surface EMG application and research to ensure high quality of the signal.