Fathinul Syahir Ahmad Saad

Improved Maturity and Ripeness Classifications of Magnifera Indica cv. Harumanis Mangoes through Sensor Fusion of an Electronic Nose and Acoustic Sensor

In recent years, there have been a number of reported studies on the use of non-destructive techniques to evaluate and determine mango maturity and ripeness levels. However, most of these reported works were conducted using single-modality sensing systems, either using an electronic nose, acoustics or other non-destructive measurements. This paper presents the work on the classification of mangoes (Magnifera Indica cv. Harumanis) maturity and ripeness levels using fusion of the data of an electronic nose and an acoustic sensor. Three groups of samples each from two different harvesting times (week 7 and week 8) were evaluated by the e-nose and then followed by the acoustic sensor. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were able to discriminate the mango harvested at week 7 and week 8 based solely on the aroma and volatile gases released from the mangoes. However, when six different groups of different maturity and ripeness levels were combined in one classification analysis, both PCA and LDA were unable to discriminate the age difference of the Harumanis mangoes. Instead of six different groups, only four were observed using the LDA, while PCA showed only two distinct groups. By applying a low level data fusion technique on the e-nose and acoustic data, the classification for maturity and ripeness levels using LDA was improved. However, no significant improvement was observed using PCA with data fusion technique. Further work using a hybrid LDA-Competitive Learning Neural Network was performed to validate the fusion technique and classify the samples. It was found that the LDA-CLNN was also improved significantly when data fusion was applied.

Hand-Held Electronic Nose Sensor Selection System for Basal Stamp Rot (BSR) Disease Detection

Electronic Nose (e-nose) is an intelligent instrument that is able to classify different types of odours. The e-nose applications include food quality assurance, fragrance industry, medical diagnosis, environmental monitoring, agricultural industry and homeland security. The current e-nose design trend are portable, small size, low power consumption, high processing power using embedded controller and easy to operate to enable it to perform the designed tasks effectively. This paper deals with the design issues of a hand-held e-nose based on sensor selection and optimum embedded controller capabilities. A summary of proposed hardware and software solutions are provided with emphasis on data processing. The data processing utilizes multivariate statistical analysis i.e. Principal Component Analysis (PCA), Hierarchical Cluster Analysis (HCA) and Linear Discriminate Analysis (LDA). The developed instrument was tested to discriminate the Ganoderma boninense fruiting body (basidiocarp). Initial results show that the instrument is able to discriminate the samples based on their odour chemical fingerprint profile.

Shape and weight grading of mangoes using visible imaging

Automatic grading of Harumanis mangoes by its shape and weight analysis.The Fourier descriptor method was developed to grade the shape of Harumanis mango.The cylinder method was developed to grade the weight of Harumanis mango.Multi-classification using Support Vector Machine and Discriminant analysis. This paper presents the work on the use of visible imaging as a tool in grading the mangoes. A Fourier-descriptor method was applied on mango images acquired by a CCD camera, to grade the fruits by their shapes. The method was able to correctly classify 98.3% using DA and 100% using SVM. It is also possible to estimate the weight of the mangoes from their images by applying the Cylinder approximation analysis method. The scatter plot between the estimated and actual values of the weight shows high correlation, with R2 equal to 94.0%. The high prediction accuracy obtained shows that this simple formula is adequate for the prediction of fruit weight and volume (measured volume using the cylinder method). The correlation formula derived based on the collected data is determined as w=2.256V-157.7 where w is estimated weight in grams and V is estimated volume. Overall result for weight grading using our proposed method yields 95% accuracy.

P2.1.7 Exploring MIP Sensor of Basal Stem Rot (BSR) Disease in Palm Oil Plantation

In Malaysia, the production of palm oil is hampered by the infection of Basal Stem Rot (BSR) disease. Unfortunately, the existing BSR detection techniques are complex, time-consuming and still not fully developed. So, this research proposes an investigation to identify the volatile compounds (biomarkers) of the infected oil palm trees. The biomarkers will be proposed to develop specific Molecularly Imprinted Polymer (MIP) sensors. The sensor will be used for the development of ‘Application Specific Electronic Nose’ (ASEN). The samples were taken from healthy and infected BSR disease tree. Fourier Transform Infrared (FTIR) and Headspace Gas Chromatography Mass Spectrometry (GC-MS) analysis is used to identify the biomarkers. The results show that the technique has successfully detected and identified the volatile compounds biomarkers for BSR disease of infected oil palm tree.

Track Cyclist Performance Monitoring System Using Wireless Sensor Network

The right training programs are an important factor to increase the cycling performance among the professional track cyclist. Over the years, the cyclist performance was based on the feedback from bicycle’s kinematics and physiological condition. The advancement in sensor technologies allows the optimization of the training program; by combining both information from the cyclist’s physiological condition and kinematic data from the bicycle. The physiological conditions such as heart rate variability (HRV) and forehead temperate can be combined with bicycle kinematic data such as speed and distance to provide accurate assessment of the track cyclist’s condition and training program intensity. A system that combines data from physiological signal and bicycle kinematic has been developed for this purpose. Wearable physiological body sensors and bicycle kinematic sensors are deployed using wireless sensor network (WSN). HRV provide using photoplethysmography (PPG) technique that capture signal from cyclist’s finger, which provide 3 % error rate refer to heart rate belt. Data handling and communication was developed based on Zigbee protocol whereby the WSN centralized base-station was supported by two repeater node which was used to extend signal coverage in Velodrome to prevent data losses. With two repeater nodes and adjustment on the routing protocol, the packet drops were reduced from 46 to 3 %. The propagation study was carried out in the Velodrome with environment temperature range from 28 to 30 °C and humidity was observed at 85 %. The optimization of network topology by considering the connectivity among the wireless nodes is crucial in order to reduce data losses.

Odour and Hazardous Gas Monitoring System for Swiftlet Farming Using Wireless Sensor Network (wsn)

Odour and Hazardous Gas Monitoring System for Swiftlet Farming using Wireless Sensor Network (WSN) Syed M. Mamduh*, Ali Y. Md. Shakaff, Shaharil M. Saad, Kamarulzaman Kamarudin, Latifah M. Kamarudin, Ammar Zakaria, H. Kamarudin, A. M. M. Ezanuddin, Fathinul S.A. Sa’ad,, W.M. Nooriman, Abu H. Abdullah Center of Excellence for Advanced Sensor Technology (CEASTech), Universiti Malaysia Perlis (UniMAP), Pusat Pengajian Jejawi 2, Taman Muhibah, Jalan Jejawi-Permatang, 02600, Perlis, Malaysia ceastech@unimap.edu.my

Mobile robot localization system using multiple ceiling mounted cameras

Almost all robotics applications require accurate robot positioning. However, most of the developed methods lacks in ground truth reference to verify its accuracy relative to the real world. This paper proposes an effective vision based system to accurately track mobile robots true position and orientation using multiple overhead cameras. This system is able to track and localize multiple mobile robots simultaneously within a 3m × 6m arena. Images from the cameras are calibrated using calibration grid image to remove fish eye effect and further calibrated based on point coordinates (x, y) to eliminate camera angle distortion error. Each robot is assigned with a symbol marker for identification. A geometric feature based pattern matching algorithm is used to track the markers position and orientation. Data obtained from all four cameras are merged according to its relative offsets to obtain localization in a global coordinate frame. The developed system is able to localize multiple robots with errors of less than 1 cm and 1°.

Multi channel ultrasonic sensing system for wall features extraction

Ultrasonic sensor is one of the most cost-effective sensor used to obtain range information and obstacle avoidance. Due to its simplicity, this sensor is widely used in mobile robot applications to acquire environment features and mapping. Although the sensor can track a still or moving target, it does not provide information on the shape and pattern of the detected object. This paper proposes and highlights a low cost method using an array of ultrasonic sensors to be embedded on multiple robots for wall features extraction. Instead of using a single sensor, multiple sensors are used to increase the accuracy and improve coverage on the field of view of the sensor. More information can be extracted such as bearing angle of walls and possibly the shape of an object. A multiple pulse transmit and instantaneous multiple echo receive approach is implemented. The experimental results prove that this method is able to extract different type of wall features, accurately.

Application Specific Electronic Nose (ASEN) for Ganoderma boninense detection using artificial neural network

Oil palm has many usages and mainly is used in food, detergent and medical products. However, the crop is susceptible to diseases where one of them, the Basal Stem Rot (BSR) disease, is affecting oil palm plantations in Malaysia and Indonesia. Currently, most of the detection techniques in treating the disease require detailed operating procedures and some are still not fully tested. In this paper, the Application Specific Electronic Nose (ASEN) is proposed to be used in Ganoderma boninense detection which is the basidiomycetes fungi of BSR disease. The specific sensor arrays will increase the instrument performance while reducing the cost, processing time and noise. The instrument data processing uses Artificial Neural Network (MLP, PNN and RBF) classification model. Initial results show that the instrument was able to detect the fungus. The instrument provides an effective low cost non-destructive method for the disease detection. This indicates that the instrument can be used as a detection system for plant disease monitoring.

Real-time track cycling performance prediction using ANFIS system

ABSTRACT The next stage performance evaluation of an athlete can be predicted by implementing Artificial Intelligence technique. In track cycling event, coach and sports physician are concerned with the performance of the cyclist. The performance prediction may help to fine-tune the cyclist training intensities and strategies planning. This study was conducted to fulfil the prediction requirement by adopting a Fuzzy Inference System to classify the cyclist current cycling performance state. The six levels of output classification by a Fuzzy Inference System are to indicate the athlete’s current state performance using the body temperature, heart rate variability and speed as input parameters. An Adaptive Neuro-Fuzzy Inference System was applied to predict the cycling speed that can be achieved in the next lap. Using Adaptive Neuro-Fuzzy Inference System method, the average speed for the next laps can be predicted and compared with the actual speed. The regression value with r = 0.9029 indicates the Adaptive Neuro-Fuzzy Inference System is an adequate prediction algorithm to evaluate the cyclist performance. The predicted time to complete compared favourably with the actual finishing time with a ± 13.6% average error. Hence, the developed system is reliable and suitable for sports events that deal with speed and time.