Shah Rizam Mohd Shah Baki

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.

Non-destructive classification of watermelon ripeness using Mel-Frequency Cepstrum Coefficients and Multilayer Perceptrons

We present a non-destructive watermelon classification method using Mel-Frequency Cepstrum Coefficients (MFCC) and Multi-Layer Perceptron (MLP) neural network. Acoustic signals were collected from thumping noises of ripe and unripe watermelon fruits. MFCC was then used to convert the signals into MFCC coefficients. The coefficients were then used to train a MLP, and the MLP gives the final decision on the watermelon ripeness state. In our paper, we describe the methods used to obtain the acoustic samples, as well as the evaluation of several MLP structures and parameters to obtain the best MLP classifier. Our results show that the proposed method was able to discriminate between ripe and unripe watermelons with 77.25% accuracy.

Representation of Elaeis Guineensis nutrition deficiency based on image processing approach

Nutrient deficiencies are one of the common issues faced by Elaeis Guineensis or widely known as oil palm. In this paper, image processing technique is utilized to develop method that is able to represent symptoms of nutrient disease such as nitrogen, potassium and magnesium. Hence, algorithm is developed to process the captured images of the diseased leaves through image segmentation and feature extraction based on nonlinear spatial filtering, YCbCr colour and gray scale morphology method. Experimental results demonstrated that the developed algorithm is capable to represent nutrient deficiencies as visualized by expert vision.

Watermelon maturity level based on rind colour as categorization features

This paper proposed categorization of watermelon maturity level based on rind colour. 30 samples are used to develop the new algorithm. Firstly, image of the fruit is captured in RGB format using a digital camera. The RGB image then is converted into gray scale image to undergo pre-processing. Here, the watermelon is extracted from the unwanted background by scanning the image for connected pixels or blobs, followed by the elimination of the unwanted blobs having certain area, leaving the desired object intact. Masking process is performed to obtain image of the watermelon with a black background. The colour components of the masked image namely red, green and blue are extracted and used as features in determining the maturity level of the watermelon. Another 30 samples are used to test the technique to validate the proposed method. Initial results attained proved that this method is appropriate and at par as compared to opinion from the human expert.

Review on performance of Thermal Energy Storage system at S & T Complex, UiTM Shah Alam, Selangor

This paper presents on the performance of Thermal Energy Storage (TES) system at Complex Science and Technology, University Teknologi MARA Shah Alam Selangor. Various technical aspects and criteria for thermal energy storage systems and applications are discussed and energy saving techniques and environmental impacts of these systems are highlighted with illustrative examples. This study describes the result of the operation of the TES system. The data obtained were observed and analyzed to measure the cooling load demand capacity, electrical load, and building load profile of S & T Complex in certain duration. The results show that, the operation of TES is not fully utilized. The ice charging process does not constantly meet the nominal tank capacity of 10,800 RTh. Energy consumption is higher since the chiller has to top up the remaining cooling capacity during peak period. Also, in this paper the Building Energy Index of S & T is calculated as 201.48kWh/m2/year. In conclusion, data retrieve will be valuable assets as to forecast and predict the amount of energy use for future benefits.

An approach of halal poultry meat comparison based on mean-shift segmentation

This study describes a method to identify slaughtered poultry based on Islamic way. This is done based on evaluation the meat color in order to determine if the poultry is slaughtered based on Islamic way or vice versa. Firstly, the intensity color level that represented the chest meat of the poultry is determined under controlled illumination and camera positioning. Next, LUV color space is used to determine the color tone of the pixel based on mean shift method. Initial results showed that the proposed method that based on mean shift segmentation proven that Halal flesh images owned extremely high value of U component as compared to Non-halal flesh. Thus the proposed method is capable to identify poultry slaughtered using Islamic Law or otherwise.

Air-conditioning energy consumption of an education building and it's building energy index: A case study in engineering complex, UiTM Shah Alam, Selangor

This paper presents the Air Conditioning energy consumption of an education building and its Building Energy Index at Engineering Complex formerly Science and Technology (S & T) Complex building, University Teknologi MARA Shah Alam Selangor. A fact has shown that the buildings are responsible for using a vast amount of energy. The energy consumption in buildings is increased by air conditioning system. To implement actions to save energy in buildings, it is necessary to measure and study its energy efficiency. This study describes the result of user attitudes towards air conditioning usage, electric energy consumption pattern and building energy index in building. Through the site survey, the results show that, the operation of air conditioning system was unsatisfying. In conclusion, the air conditioning energy consumption can be reduced by several proposed measures. The proposed measures are categorized into two ways: by improving user attitude towards using air conditioning through awareness and technical improvement.

Classification of Elaeis Guineensis disease-leaf under uncontrolled illumination using RBF network

This paper proposes the novel technique of processing the leaf images from inconsistent illumination, as opposed to controlled environment approach used by conventional laboratory setup nowadays. The effect of daylight illumination creates major obstacle due to the changes of leaf appearance under different illumination that will affect the subsequent preprocessed image specifically when extracting the features such as spots and colours using RGB colour, histogram based texture and Gray Level Co-occurrence Matrices (GLCM). The key highlighted idea of processing the image under normal daylight involves colour manipulation technique to disclose the hidden RGB colour into its original colour, therefore the leaf images can be processed not limited to controlled environment setup. Once the illumination effect is alleviated, the oil palm leaf-diseased region can be automatically classified into three different types of disease namely nitrogen (N), potassium (K) and magnesium (Mg) deficiencies. The classification technique via Radial Basis Function Network (RBFN) classifier is examined and validated using an input from a database of oil palm diseased-leaf (or scientifically known as Elaeis Guineensis) to confirm the high degree of classifier capability to recognize the disease according to the deficiency type. The experimental result showed that various lighting conditions measured in terms of illumination affected the formed pattern on the leaf surface due to the leaf images dependency on the intensity of illumination presented at that time hence disturbing the image quality. Classification of the various deficiencies demonstrated the correct classification rate as high as 70.69%, showing that the inconsistent illumination could provide good accuracy in classifying the deficient-leaf.

Energy efficiency benchmarking in UiTM engineering complex Shah Alam

Energy efficiency implementing strategy requires various approaches for different condition to increase the effectiveness. The energy efficiency normally refers energy usage without wastage. Normally, certain reference or benchmarking to certain standard will be used such as building energy index (BEI). Two new indexes were introduced in this paper namely Effective Building Energy Index (EBEI) and Specific Building Energy Index (SBEI). This paper presents the benchmarking additional approach so as to reduce energy wastage in Engineering Complex, UiTM Shah Alam. BEI for this complexs was found to be 149 kWh/m2.year and EBEI is found to be 186 kWh /m2.year. The SBEI was found to be 0.207 kWh/m2.year for an occupant. With various approach discussed in this paper, an expected energy reduction of 20% can be achieved.

Optimization of water quality monitoring based on fuzzy algorithms

Water quality resembles physical, chemical and biology features of the water. Water quality level is used to determine the suitability and safeness for general usage. Hence in this study, fuzzy algorithms are developed to evaluate water quality based on three features namely power of hydrogen (pH), dissolved oxygen (DO) as well as temperature. Firstly, sensors of pH and DO are connected to stamp circuit that acted as universal asynchronous receiver / transmitter (UART) whilst temperature sensor is connected to a microcontroller. Next, fuzzy algorithms are developed based on water quality standards from the Department of Environmental Malaysia for decision making. Thus, both hardware and software are integrated and initial findings showed that the proposed system is apt for monitoring of water quality.