Bobby D. Gerardo

Pest Detection and Extraction Using Image Processing Techniques

—Detection of pests in the paddy fields is a major challenge in the field of agriculture, therefore effective measures should be developed to fight the infestation while minimizing the use of pesticides. The techniques of image analysis are extensively applied to agricultural science, and it provides maximum protection to crops, which can ultimately lead to better crop management and production. Monitoring of pests infestation relies on manpower, however automatic monitoring has been advancing in order to minimize human efforts and errors. This study extends the implementation of different image processing techniques to detect and extract insect pests by establishing an automated detection and extraction system for estimating pest densities in paddy fields. Experiment results shows that the proposed system provides a simple, efficient and fast solution in detecting pests in the rice fields.

A framework for discovering relevant patterns using aggregation and intelligent data mining agents in telematics systems

The emerging technology in vehicle telematics drives several stakeholders in this field to consider services that could be beneficial for both clients and the telematics service providers. In particular this paper proposes a novel framework for insurance telematics in Korea using a mobile aggregation agent (AA) and intelligent data mining agent (IDMA). To our knowledge, this model is recent of its kind in this country and the base-line information from drivers characteristics serves as reference for the flexible insurance policies. We are able to present a use-case scenario and illustrative examples to demonstrate our model. With this flexible insurance framework, customers can manage their own insurance premiums and lower the cost of motoring. Promising applications of this system to business and industries have been recognized and discussed.

Decision support system for agricultural management using prediction algorithm

Currently climate change is one of the major problems encountered due to the climatic controls interacting in various intensities and in different combinations. The proposed system includes mechanism that accepts/processes gathered data from Agricultural Research Center. The system uses Time Series Analysis; the collection of observations of well-defined data items obtained through repeated measurements over time which utilizes algorithm that is capable of formulating the trend. Upon prediction, the system displays table and graphs along with the recommended crops. The system had successfully determined the trend of rainfall and evaporation using prediction algorithm together with the recommended crops. It was able to display the result of prediction in graphical form and crop classification in tabular form.

Agricultural Crops Classification Models Based on PCA-GA Implementation in Data Mining

Extraction of knowledge in agricultural data is a challenging task, from discovering patterns and relationships and interpretation. In order to obtain potentially interesting patterns and relationships from this data, it is therefore essential that a methodology be developed and take advantage of the sets of existing methods and tools available for data mining and knowledge discovery in databases. Data mining is relatively a new approach in the field of agriculture. Accurate information in characterizing crops depends on climatic, geographical, biological and other factors. These are very important inputs to generate characterization and prediction models in data mining. In this study, an efficient data mining methodology based on PCA-GA is explored, presented and implemented to characterize agricultural crops. The method draws improvements to classification problems by using Principal Components Analysis (PCA) as a pre processing method and a modified Genetic Algorithm (GA) as the function optimizer. The fitness function in GA is modified accordingly using efficient distance measures. The approach is to asses, the PCA-GA hybrid data mining method, using various agricultural field data sets, generate data mining classification models and establish meaningful relationships. The experimental results show improved classification rates and generated characterization models for agricultural crops. The domain model outcome may have benefits, to agricultural researchers and farmers. These generated classification models can also be utilized and readily incorporated into a decision support system.

A Rule-Based Fuzzy Diagnostics Decision Support System for Tuberculosis

The system is specialized for pulmonary physicians focusing on tuberculosis and for patients already diagnosed with tuberculosis. The main focus for the development of the system is on the architecture and algorithm used to find the probable class of tuberculosis a patient may have. The class of tuberculosis is determined by using a rule base populated by rules made for the different classes of tuberculosis. The clinical decision support system integrated with Fuzzy Logic and Rule-based method that generates classes of tuberculosis suits the needs of pulmonary physicians and lessens the time consumed in generating diagnosis.

Development of College Completion Model Based on K-means Clustering Algorithm

 Abstract—The amount of data stored in educational databases is rapidly increasing because of the increase in awareness and application of information technology in the field of higher education. What can be done with these databases is to mine the hidden knowledge in it. This paper is designed to present and justify the capabilities of data mining. The main contribution of this paper is the development of college completion model based on k-means clustering algorithm. The data stored in the Student Information and Accounting System from 2009 to 2013 was used to perform an analysis of study outcome taking into consideration not to include in the final result any identifying information to protect their privacy. The results showed that majority of the students belong to the cluster which needs intervention. The dataset used can be improved by including data of students currently enrolled. The result obtained can be used as a decision support tool. The WEKA software was used to build the college completion model using k-means clustering.

Implementation of Improved DES Algorithm in Securing Smart Card Data

Although smart cards have already provided secure portable storage device, security is still a major concern to electronic data systems. There is a need to improve data security against accidental or unlawful destruction or alteration during transmission or while in storage. The Odd-Even substitution proved to have provided additional confusion technique to DES and was essential in providing adequate security. The limitation of DES to encrypt large data has also been addressed by this research without intensive processing. Unlike the 3DES or AES, the improved DES has lesser computational load.

An Improved Data Encryption Standard to Secure Data Using Smart Cards

This paper is directed towards the development of an improved DES to secure the data using smart cards. An improved Data Encryption Standard has been developed by incorporating an ODD/EVEN bit conversion to the existing DES algorithm. The proposed algorithm is expected to provide greater security to further protect the data in Smart Cards. The data is secured from any illegal retrieval and intended modification. The program simulation also provides a good start to explore for a more robust encryption technique that will not require so much mathematical computations.

ALE-Compliant RFID Middleware for Mobile Environment

Nowadays, many researches are geared towards RFID and mobile technology which are one of the core technologies for realizing ubiquitous computing. In Korea, mobile RFID network services are developed and operated by using mobile networks and mobile devices with a built-in RFID reader. In this paper, we propose a new method of applying RFID middleware based on ALE to mobile RFID network services. For this, we explain a method of mobile RFID code conversion to handle effectively the code in ALE-compliant middleware. By using the proposed method in a mobile RFID network model, application developers and/or contents industries can gather the information from the users of mobile RFID devices in real-time or periodically. Furthermore, it can provide personalized services to users by utilizing it. In this way, we can easily extend ALE-compliant middleware to process not only general but also mobile RFID code.

An Improved Data Mining Mechanism Based on PCA-GA for Agricultural Crops Characterization

In this study, a data mining method based on PCA-GA is presented to characterize agricultural crops. Specifically it draws improvements to classification problems by using Principal Components Analysis (PCA) as a preprocessing method and a modified Genetic Algorithm (GA) as the function optimizer. The GA performs the optimization process, selecting the most suited set of features that determines the class of a crop it belongs to. The fitness function in GA is studied and modified accordingly using efficient distance measures. The soybean dataset is used in the experiment and results are compared with several classifiers. The experimental results show improved classification rates. This lessens the time consumed of agricultural researchers in characterizing agricultural crops.