12 Articles Published

1. JOINT DESIGN OF DELAY CONSTRAINT AND ENERGY SAVING FOR EFFICIENT PACKET TRANSMISSIONS IN SMARTPHONES

Authors: JENN-WEI LIN , J. MORRIS CHANG

Abstract: In this paper, delay constraint and energy saving are jointly studied for efficiently transmitting packets in smartphones. We propose a new energy-saving transmission mechanism. The proposed mechanism first utilizes the lazy transmission concept to estimate the last transmission interval of each packet. Before transmitting a packet p, we also adopt the accompanied transmission concept to involve more other packets tobe transmitted with packet p. The well-known knapsack problem can be applied to solve the selection of accompanied packets under a given bandwidth capacity. Finally, simulation experiments are performed to demonstrate the effectiveness of the proposed mechanism in the delay performance and energy conservation.

Keywords: energy saving, delay constraint, smartphone, knapsack problem.

Pages: 1 - 5 | DOI: 10.15224/978-981-07-7227-7-01

2. A NEW BMI BASED METHOD FOR WHEELCHAIR ROBOT NAVIGATION

Authors: MITSUKI KITANI , GENCI CAPI , MARSEL MANO

Abstract: Recent research has shown that Brain Machine Interface (BMI) can be used to assist disable people in navigating a robotic wheelchair by using voluntary mental intentions. BMI based navigation is a very challenging task. In this paper we present a novel adaptive method to improve BMI based robotic wheelchair navigation. The robot is controlled by an adaptive navigation platform that provides the user with scalablenavigation assistance. The platform is able to detect and avoid collisions by using a laser range finder sensor. Furthermore, by using computer vision it can read assistive information for visually impaired people (tactile pav-ing) on the floor and autonomously navigate the robot following tactile paving directions. Based on user intentions and environment context, the robot navigation adaptively changes between assisted andunassisted mode. Experimental results show that with the assis-tance of the adaptive navigation platform the robot navigation im-proves significantly. Furth

Keywords: Brain machine interface, rehabilitation, robot navigation

Pages: 6 - 10 | DOI: 10.15224/978-981-07-7227-7-02

3. ADAPTIVE HUMANOID ROBOT ARM MOTION GENERATION BY EVOLVED NEURAL CONTROLLERS

Authors: GENCI CAPI , MARSEL MANO , MITSUKI KITANI

Abstract: Adaptive Humanoid Robot Arm Motion Generation by Evon this paper, we present a new method for humanoid robot arm motion planning satisfying multiple constraints. In our method, the humanoid robot arm motion generation is formulated as an optimization problem. Four different constraints, which cover a wide range of humanoid robot tasks, are considered: minimum time, minimum distance, robot hand acceleration and constant joint angular velocity. Results show that arm motions have different characteristics. In order to further verify the performance of humanoid robot arm motions, they are transferred in humanoid robot mobile platform. lved Neural Controllers

Keywords: Humanoid mobile robot, motion planning, neural networks, genetic algorithms

Pages: 11 - 16 | DOI: 10.15224/978-981-07-7227-7-03

4. A NOVEL RECONSTRUCTION METHOD USING THE PHASE ONLY INFORMATION OF THE COMPUTER GENERATED HOLOGRAM

Authors: ALI DURSUN , GULHAN USTABAS KAYA , ZEHRA SARAC

Abstract: The studies that have been carried out so far, the reconstruction process of the phase hologram can be realized by a single phase hologram. In this study, on the basis of a single phase hologram, this process will be carried out with the phase information which is obtained from a single hologram. To reconstruct the test object image, two different methods will be used: (1) the image will be reconstructed with using single phase information of single hologram, (2) the image will be reconstructed with using single phase information of more than one hologram ( In this study 4 holograms are used. ) This method is same of the phase shifting hologram using with 4 holograms. In this study, only used numbers of holograms and also their expressions are different. This method is used in this study for the first time. To obtain the single phase value for holograms, with using different methods, the Fourier transform algorithm will be used. Consequently, the simulations will be achieved in Matlab

Keywords: reconstruction, single phase, single hologram

Pages: 17 - 20 | DOI: 10.15224/978-981-07-7227-7-04

5. SENTIMENT ANALYSIS: STATE OF THE ART

Authors: JEREMY ELLMAN , TAWUNRAT CHALOTHORN

Abstract: We presented the state of art of sentiment analysis which contained about the purpose of sentiment analysis, levels of sentiment analysis and processes that could be used to measure polarity and classify labels. Moreover, brief details about some resources of sentiment analysis are included.

Keywords: sentiment, analysis, natural language processing, nlp, sentiwordne

Pages: 21 - 25 | DOI: 10.15224/978-981-07-7227-7-05

6. AUTOMATIC SMILE AND BLUR DETECTION FOR STILL IMAGES

Authors: EVGENY GERSHIKOV , YOSSI AMOYAL

Abstract: In this work we present an algorithm designed to recognize if the faces in a still image are smiling or not, based on Viola Jones face detection method and an algortihm for smile recognition. The stages of our algorithm are: identification of the faces in the image, detection of the mouth part of each face and then application of a basic algorithm to the mouth part to determine whether the person is smiling or not. A smile is recognized by examining the graph of the grayscale levels across the mouth and looking for two distinct minima. As an additional step of image quality assessment, we measure the level of blurriness of the detected face. Real life images were used for testing the algorithms at different spatial resolutions, levels of blurriness as well as varying contrast and brightness conditions. Our conclusion is that the proposed methods can be beneficial for automatic smile recognition and blur detection in digital cameras or other mobile devices.

Keywords: smile recognition, blur detection, face image processing, automatic image quality assessment

Pages: 26 - 30 | DOI: 10.15224/978-981-07-7227-7-06

7. ENHANCING THE SECURITY OF VISA 3-D SECURE AGAINST SPOOFING ATTACKSPITA JARUPUNPHOL

Authors: PITA JARUPUNPHOL

Abstract: Visa 3-D Secure is an e-payment system based on the integration of SSL/TLS with the three-domain architecture. It employs cryptographic techniques to secure communication links among participants in e-commerce transactions and also provides credit card verification via Visa Secure Server. Although several security vulnerabilities can be addressed, spoofing attacks are still effective and can be considered as potential threats to Visa 3-D Secure. Threats of spoofing and impersonation have become more effective due to advances in computing and communications technologies. However, security mechanisms incompatible with the past e-payment infrastructure are also enabled by these technological advances. PKI-based authentications used in the SET scheme can be considerable in the current era for enhancing the security of Visa 3-D Secure against spoofing attacks.

Keywords: Certification Authorities (CAs), Public Key Infrastructure (PKI), Secure Electronic Transactions (SET), Spoofing Attacks, Visa 3-D Secure

Pages: 31 - 37 | DOI: 10.15224/978-981-07-7227-7-07

8. APPLICATION OF IMPROVED GRAMMATICAL EVOLUTION TO STOCK PRICE PREDICTION

Authors: EISUKE KITA , HIDEYUKI SUGIURA , TAKAO MIZUNO , YUKIKO WAKITA

Abstract: Grammatical Evolution (GE), which is one of the evolutionary computations, aims to find function, program or program segment satisfying the design objective. This paper describes the improvement of the Grammatical Evolution according to Stochastic Schemata Exploiter (GE-SSE) and its application to symbolic regression problem. Firstly, GE-SSE is compared with original GE in symbolic regression problem. The resultsshow that GE-SSE has faster convergence property than original GE. Secondly, GE-SSE is applied for the stock price prediction as the actual application of the GE-SSE.

Keywords: Grammatical Evolution, Stochastic Schemata Exploiter, Symbolic Regression, Stock Price Prediction

Pages: 38 - 41 | DOI: 10.15224/978-981-07-7227-7-08

9. REVERSIBLE IMAGE AUTHENTICATION SCHEME FOR VQ IMAGES USING CODEBOOK CLUSTERING

Authors: JUN-CHOU CHUANG , PEI-YU LIN

Abstract: The paper presented a reversible image authentication scheme for VQ images using codebook clustering. The proposed method not only locates the alterations of VQ images but also recover the indexes of VQ image without any distortion from the marked VQ indexes after the hidden authentication bits have been extracted. The method uses the codebook clustering to generate four fixed-size small codebooks. Those small codebookswere used to encode original image to obtain a watermarked VQ image. The proposed method has two advantages. Firstly, the hidden procedure of the proposed method is the same as VQ encoding. After the image is finished encoded, the watermarked image is generated. Secondly, the proposed method does not cause any distortion of indexes of VQ image after we extract the hidden data from the watermarked VQ image.

Keywords: Reversible data hiding, VQ image authentication, digital watermarking, codebook clustering

Pages: 47 - 51 | DOI: 10.15224/978-981-07-7227-7-10

10. PREDICTING PERSONAL CREDIT RATINGS USING UBIQUITOUS DATA MINING

Authors: JAE KWON BAE

Abstract: Ubiquitous data mining (UDM) is a methodology for creating new knowledge by building an integrated financial database in a ubiquitous computing environment, extracting useful rules by using diverse rule-extraction-based data mining techniques, and combining these rules. In this study, we built six credit rating forecasting models using traditional statistical methods (i.e., logistic regression and Bayesian networks), multilayer perceptron (i.e., MLP), classification tree algorithms (i.e., C5.0), neural network rule extraction algorithms (i.e., NeuroRule), and UDM in order to predict personal credit ratings. To verifythe feasibility and effectiveness of UDM, credit ratings and credit loan data provided by A Financial Group in Korea were used in this study. Empirical results indicated that UDM outperforms other single traditional classifiers such as logistic regression, neural networks, frequency matrix, C5.0, and NeuroRule. UDM always outperforms other single classifiers in credit ratin

Keywords: Ubiquitous data mining (UDM), Ubiquitous computing environment, Credit rating forecasting models, Rule extraction algorithms, Integrated financial database

Pages: 42 - 46 | DOI: 10.15224/978-981-07-7227-7-09Ubiquitous data mining (UDM), Ubiquitous computing environment, Credit rating forecasting models, Rule extraction algorithms, Integrated financial database

11. THE DEVELOPMENT OF DATA WAREHOUSE SYSTEM FOR RICE CULTIVATION

Authors: CHATCHAI JIAMRUM , KRITTIKA PUANNGULUAM , SAISUNEE JABJONE

Abstract: This research aims to develop the data warehouse system for applying to a decision support system based on rice cultivation. The study area is Amphoe Phimai, Nakhon Ratchasima Province, Thailand. The data warehouse system for rice cultivation (DWR) aimed to enhance the analysis of rice cultivation datasets compare to currently used statistical methods. The factor of rice growth has been collected which is proving the rice related information to the agricultural expert in an integrated manner or generating a quality advice. DWR would suggest efficient information for rice growth and monitoring the rice situation by using OLAP. It allows for quick analysis of all possible interesting aggregated data by employing drag-drop and mouse-click and is used into forecast the yield of rice. The assessment of user satisfaction was used to evaluate the system. Then this system was published to the government agencies and the public via the online system. The result of the study showed that the user

Keywords: rice cultivation, data warehouse, decision support system, snowflake schema, OLAP

Pages: 52 - 56 | DOI: 10.15224/978-981-07-7227-7-11

12. APPROACHES TO DESIGN OF EMBEDDED FUNCTION-ORIENTED MICROCONTROLLERS: ARCHITECTURAL SOLUTIONS AND TOOLS

Authors: A.E. VASSILIEV , A.V. DONTSOVA, , D. CABEZAS

Abstract: The article describes hardware-software instrumentation for design and research of function-oriented controllers.

Keywords: function-oriented controllers; embedded system; computer-aided design; programmable logic device

Pages: 57 - 62 | DOI: 10.15224/978-981-07-7227-7-31