Advanced Materials Research Vols. 931-932

Abstract: The classification of ground-based cloud images has received more attention recently. The result of this work applies to the analysis of climate change; a correct classification is, therefore, important. In this paper, we used 18 texture features to distinguish 7 sky conditions. The important parameters of two classifiers are fine-tuned in the experiment, namely, k-nearest neighbor (k-NN) and artificial neural network (ANN). The performances of the two classifications were compared. Advantages and limitations of both classifiers were discussed. Our result revealed that the k-NN model performed at 72.99% accuracy while the ANN model has higher performance at 86.93% accuracy. We showed that our result is better than previous studies. Finally, seven most effective texture features are recommended to be used in the field of cloud type classification.

Abstract: In this paper we present a new system to classify TV programs into predefined categories based on the analysis of their audio and video contents. This is very useful in intelligent display and storage systems that can select channels and record or skip contents according to the consumer's preference. Distinguishable patterns exist in different categories of TV programs in terms of human faces and audio. In this paper four categories divided into news, cartoon, variety and sport are of interest. News and variety have differences between frames less than sport and cartoon. For audio feature, we apply short time energy, zero crossing, spectral centroid and short time Fourier transform for feature extraction. For face feature, in the first step, Haar like feature is employed for face detection and eigenface is then applied for feature extraction. Then, neural network is implemented for classification. From experimental results, classification rate of 95% accuracy which is better than the other paper is achievable.

Abstract: The work proposes the new method to increase an efficiency of a Content-based Image Retrieval (CBIR) system. For combining many image features, the optimal weight of each feature is required. To find the optimal value of the feature, this work uses Genetic Algorithm (GA). An image is represented as color, shape and texture features. The experiment compares the results from the system with equal weight values and the system with the weights provided by GA. Evaluation shows the robustness and efficiency of the proposed technique.

Abstract: The Cholangiocarcinoma (CCA) is a serious public health problem. The Periductal fibrosis (PDF) ultrasound images are applied for CCA surveillance because it is no side effect of radiation with patients, easy to portability and low cost. In contrast, the common problem of ultrasound images are speckle noise in which decreases the PDF detection performance. In this paper proposes a hybrid noise reduction method in the PDF detection system. The proposed noise reduction method by applying the Median filter and Fast Fourier transform based on PDF ultrasound images. The experimental results give the best performance for PDF detection system. A success rate of proposed method achieved at 70.89%.

Abstract: In this paper, an effective method for Thai face cartoon detection and recognition is used based on haar like feature and eigenface model. The basic idea of this method is to detection and recognition a cartoon Thai from the database based on a cartoon drawn by an artist. This method consists of three steps. We first manually, haar like feature is applied for Thai face cartoon detection. Second, those faces are extracted feature using eigenface. Final, those features are recognized using Euclidean distance. For experimental result, detection rate of 95% and recognition rate of 97%.

Abstract: Since a pick-and-place task plays an important role in an automatic process, it normally requires machine vision to locate an object for grasping. This paper presents a practicable method used to visually guide an object grasping a group of small, 1.1 mm diameter, screws by using an inexpensive webcam with a resolution of 640 x 480. A basic feedforward neural network is utilized to make a fitting function which associates pixel coordinates of the camera to the physical coordinates of the robot while the method of linear least squares is used for comparison in parallel. The result from the feedforward neural network shows that fifty screws can be completely manipulated from a tray after their physical coordinates are loaded into the robot while the result from the method of linear least squares shows failure when picking two of the samples.

Abstract: Reaching an agreement between negotiators is a complex process. The complexity of the problem is depicted by the difference preference of negotiators, the size of the solution space and the negotiation procedure. The aim of this study is to develop an automated negotiation method using a genetic algorithm as a mechanism. The proposed method uses theestimation of the zone of agreementtoguide negotiation. Time and joint utility are used as performance indicators. The result shows that the proposed method hasa better time usage than others.However, our method could have poor value of joint utility in some cases. A likely explanation is that the progress rate of the negotiators affects the joint payoff.

Abstract: This paper proposed data mining techniques to improve efficiency and reliability in diabetes classification. The real data set collected from Sawanpracharak Regional Hospital, Thailand, was fist analyzed by using gain-ratio feature selection techniques. Three well known algorithms; naïve bayes, k-nearest neighbors and decision tree, were used to construct classification models on the selected features. Then, the popular ensemble learning; bagging and boosting were applied using the three base classifiers. The results revealed that the best model with the highest accuracy was bagging with base classifier decision tree algorithm (95.312%). The experiments also showed that ensemble classifier models performed better than the base classifiers alone.

Abstract: RSA, a public key cryptosystem, was proposed to protect the information in the insecure channel. The security of RSA relies on the difficulty of factoring the modulus which is the product of two large primes. We proposed Modified Fermat Factorization Version 2 (MFFV2) modified from Modified Fermat Factorization (MFF) to break RSA. The key of MFFV2 is to decrease the number of times of MFF for computing an integers square root. However, MFFV2 is still time-consuming to some extent due to computation time of the subtraction of two integers for all iterations. Thus, this paper aims to propose Modified Fermat Factorization Version 3 (MFFV3) to increase the computation speed when compared with MFFV2. For MFFV3, we can ignore computing the difference between two integers when we know that the subtractions result is certainly not a perfect square. Hence, we develop the Differences Least Significant Digit Table (DLSDT), the information table used to analyze the least significant digit of the subtractions result. Experimental results show that the computation time of MFFV3 for factoring the modulus is substantially reduced in comparison to MFF and MFFV2 respectively.

Abstract: The secure remote biometric authentication protocol proposed in this paper solves the problem from the nature of the biometric data. The proposed protocol preserves the privacy of the users biometric data when it is transmitted in the protocol. The liveness property of the protocol guarantees that the biometric data used to authenticate the user comes from the live presentation of the user. The most important property related with the intentional authentication; it confirms that the purpose of the user authentication correspondences to the users purpose. The proposed secure remote biometric authentication protocol promises three properties so that the user is confident with the security level that the protocol offers and it guarantees that the protocol does not manipulate with an intruder.