| Judul | Abstract | Halaman |
|---|
| Frontal Face Detection using Haar Wavelet Coefficients and Local Histogram Correlation | Face detection is the main building block on which all automatic systems dealing with human faces is built. For example, a face recognition system must rely on face detection to process an input image and determine which areas contain human faces. These areas then become the input for the face recognition system for further processing. This paper presents a face detection system designed to detect frontal faces. The system uses Haar wavelet coefficients and local histogram correlation as differentiating features. Our proposed system is trained using 100 training images. Our experiments show that the proposed system performed well during testing, achieving a detection rate of 91.5%. | 157-172 |
| Lossless Compression Performance of a Simple Counter-Based Entropy Coder | This paper describes the performance of a simple counter based entropy coder, as compared to other entropy coders, especially Huffman coder. Lossless data compression, such as Huffman coder and arithmetic coder, are designed to perform well over a wide range of data entropy. As a result, the coders require significant computational resources that could be the bottleneck of a compression implementation performance. In contrast, counter-based coders are designed to be optimal on a limited entropy range only. This paper shows the encoding and decoding process of counter-based coder can be simple and fast, very suitable for hardware and software implementations. It also reports that the performance of the designed coder is comparable to that of a much more complex Huffman coder. | 173-184 |
| A Cognitive Skill Classification Based on Multi Objective Optimization Using Learning Vector Quantization for Serious Games | Nowadays, serious games and game technology are poised to transform the way of educating and training students at all levels. However, pedagogical value in games do not help novice students learn, too many memorizing and reduce learning process due to no information of player’s ability. To asses the cognitive level of player ability, we propose a Cognitive Skill Game (CSG). CSG improves this cognitive concept to monitor how players interact with the game. This game employs Learning Vector Quantization (LVQ) for optimizing the cognitive skill input classification of the player. CSG is using teacher’s data to obtain the neuron vector of cognitive skill pattern supervise. Three clusters multi objective target will be classified as; trial and error, carefully and, expert cognitive skill. In the game play experiments employ 33 respondent players demonstrates that 61% of players have high trial and error, 21% have high carefully, and 18% have high expert cognitive skill. CSG may provide information to game engine when a player needs help or when wanting a formidable challenge. The game engine will provide the appropriate tasks according to players’ ability. CSG will help balance the emotions of players, so players do not get bored and frustrated. | 185-202 |
| Improve the Robustness of Range-Free Localization Methods on Wireless Sensor Networks using Recursive Position Estimation Algorithm | The position of a sensor node at wireless sensor networks determines the received data sensing accuracy. By the knowledge of sensor positioning, the location of target sensed can be estimated. Localization techniques used to find out the position of sensor node by considering the distance of this sensor from the vicinity reference nodes. Centroid Algorithm is a robust, simple and low cost localization technique without dependence on hardware requirement. We propose Recursive Position Estimation Algorithm to obtain the more accurate node positioning on range-free localization technique. The simulation result shows that this algorithm has the ability on increasing position accuracy up to 50%. The trade off factor shows the smaller the number of reference nodes the higher the computational time required. The new method on the availability on sensor power controlled is proposed to optimize the estimated position. | 203-222 |
| Opinion Mining for User Generated Design by Social Networking Service and Japanese Manga | The growth of Social Networking Service (SNS) has created a new potential in marketing. While users communicate and interact via SNS, the list of their conversation, which is called casual data can be used to determine their needs or aspirations. SNS can be very useful for product/service developers, especially when developing new ideas or simply evaluating the feasibility of their existing products/services. Furthermore, SNS provides a unique system that enables expressive and two-way communication between its users. SNS is known for its effectiveness in delivering fresh news and information, thus it can be used as promotional media. Although several online services that utilize SNS and casual data have been provided, the purpose of those services is still unclear and ineffective. In those services, users were only asked for their opinions without receiving sufficient feedbacks. Therefore, to solve these problems we propose an innovative way of utilizing SNS and casual data in designing user generated design. In our proposed system, users can directly contribute to the product/service development process in an interesting way. We designed an online service, which allows users to posts manga that describes their original idea. While contributing to the product/service development, they can also benefit from expressing their hobbies and receiving feedbacks from other users. | 223-240 |
