Zainul Abidin Md Sharrif

Image processing of an agriculture produce: Determination of size and ripeness of a banana

Over the last several decades, customers’ lifestyles and needs have gone through tremendous changes. These changes are new challenges for the farmers whose produce has to meet the customers’ demands. The ability to classify agriculture produce based on size and quality is not only going to help the farmer but also the customer. This will help the farmer to grade the fruit, the seller to price it optimally and the customer value for money. Bananas are classified according to sizes, shapes, textures, colors and taste. The process of getting the size and ripeness of a banana is done from its image using the Image Processing Toolbox in MATLAB. These features are important to determine the optimal size and ripeness. From the size, the grade and type of the banana can be determined. The percentage of ripeness can be determined by evaluating the individual pixels of the image.

Agricultural produce Sorting and Grading using Support Vector Machines and Fuzzy Logic

Agriculture sector was accorded a very different treatment in the Ninth Malaysia Plan (9MP) where this sector is being revitalized to become a part of the economic growth engine. The Information and Communication Technology (ICT) application is going to be implemented as a solution in improving the status of the agriculture sector. The idea of integrating ICT with agriculture sector motivates the development of an automated system for sorting and grading of agriculture produce. Currently, the grading is done based on observations and through experience. The developed system starts the grading process by capturing the fruits image using a regular digital camera or mobile phone camera. Then, the image is transmitted to the processing level where feature extraction, classification and grading is done using MATLAB. In this paper, the focus is more on agricultural produce Sorting and Grading technique. The agricultural produce is classified based on fruit shape and size using Support Vector Machines (SVMs) and its grade is determined using Fuzzy Logic (FL) approach. The results obtained are very promising.

Analysis on RF emission of electrical appliances

With the increased number of electrical appliances in our daily life, Radio Frequency (RF) emission of electrical appliances and its general effects have imposed a great challenge to researchers dealing with human health and power quality of electrical supplies. Even though studying the general effects of the RF emission from electrical appliances is important, it would be beneficial to study the characteristics of the generated signals and how they differ from one appliance to another. Hence, the aim of this paper is to investigate the signal structure and magnitude variation of the RF signals emitted from electrical appliances. Six electrical appliances were tested and their RF emission was recorded consecutively. The emitted signals were captured using an Active-loop antenna with a range of 1 KHz to 30 MHz and a spectrum analyzer of Agilent E4411B model. Experiment results showed that all the tested appliances emit noticeable and unique RF signals when operating.

Shape-based sorting of agricultural produce using support vector machines in a MATLAB / SIMULINK environment

The ability to sort agricultural produce automatically is very important. This paper addresses one way to identify agricultural produce based on their shape. The techniques used are based on support vector machines. The images of the produce are loaded into MATLAB and the features extracted using image processing techniques based on edge detection. These features are then input to a classifier; i.e., a support vector machine, for identification. A regular digital camera is used for acquiring the image, and all manipulations are performed in a MATLAB / SIMULINK environment. The results obtained are an improvement over a previous technique.

Design and development of a fully automated consumer-based wireless communication system for fruit grading

As a smart consumer, there is always a need for us to identify the quality of the goods we want to buy, such as trying to choose the better mango amongst the others in a fruit market. With the popularity of the mobile phone and the maturity in wireless messaging technology, it is no more a dream for us to get the information we want anywhere, anytime. This paper proposes a new mobile data service that includes signal processing service via MMS (Multimedia Messaging Service) and SMS (Short Messaging Service). This paper discusses the study, design, construction and analysis of a fully automated consumer-based prototype wireless system which interconnects signal processing tools with consumers using MMS and SMS technology. The system with signal processing application processes the information sent by the consumer using MMS. Then it sends back the grading result to the consumer using SMS.

Real-time implementation of a Fuzzy Inference System for banana grading using DSP TMS320C6713 platform

Fuzzy Logic theory has been applied in various fields and technologies. One of the Fuzzy Logic application is to grade the agriculture produce based on its size. Currently, the grading is done based on observations and through experience. For further improvement, a high speed grading system using a Fuzzy Inference System is designed to grade the agriculture produce. In this research, a banana fruit was chosen to show the viability of this system. The Fuzzy Inference System grades a banana based on the extracted features that are obtained using Image Processing techniques of several images of each fruit. Since, this grading process requires a high speed processor, a typical computer platform is not a perfect choice. Therefore in this paper, we design and implement a grading system that uses a high speed digital signal processor. Hence, DSP TMS320C6713 was chosen for the implementation process. This paper discusses the implementation process of a fuzzy logic program on DSP TMS320C6713 platform.

Measurement and estimation of electric field emission of a vacuum cleaner

Electric field emission of electrical appliances has become an important problem, especially when testing for safety and compliance with regulations of electromagnetic compatibility (EMC). To confirm the safety and compliance of an electrical appliance, it is important to measure the levels of the emitted electric and magnetic fields from this appliance and compare them to the exposure limit values set by the international standards. Moreover, modeling these emitted fields can aid understanding their characteristics and ease investigating how different systems react to such emission. However, a good model depends mainly on the accuracy and robustness of the measurement methodology. Hence, the aim of this paper is to present a measurement methodology and a frequency domain model for the emitted electric field of vacuum cleaners using system identification tools. The proposed model is a data-driven model where the recorded signal is used to construct the model using polynomial model estimation methods. Measurement setup, related work and the model equation are presented accordingly.

Detection of VLF and LF emissions of fluorescent light for efficient management of power consumption

In this research work, a detection probe of Very Low Frequency and Low Frequency (LF) emissions of fluorescent light is developed by using low cost loop antenna. The developed loop antenna is able to operate at VLF and LF bandwidth. The developed antenna is tested and measured with signal generator and oscilloscope in order to verify the usefulness of antenna. The developed antenna is subsequently used to detect the signal emitted by the fluorescent light. The antenna probe is located at different distance in order to obtain the peak voltage of received signal. Besides that, the fluorescent light is switch on and off respectively in order to verify the source of signal. From the oscilloscope, the received signal is operating at approximately 28 KHz. Hence, the developed antenna probe can be used for efficient management of power consumption as 28 KHz signal is detected if the light is on.

Design of a VLSI digit slicing Fast Fourier Transform processor

Abstract The discrete Fourier Transform plays an important role in analysis, design and the implementation of digital signal processing algorithms and systems. Currently, there are many existing efficient algorithms for computing the discrete Fourier transform which in time with advances in the VLSI technology has benefited many researchers. In this paper we discuss the implementation of a prototype FFT chip based on the proposed Digit Slicing Architecture [1]. The paper begins with a brief discussion of the digit slicing technique. Discussion on the basic building blocks of the Digit Slicing FFT, implementation of a prototype Digit Slicing FFT on a VLSI CAD package environment (CIRCAD II) then follows. The paper is concluded by a brief discussion on the speed of conversion, flexibility and practicability of the design compared to a general DSP processor.