Alexander Agung Santoso Gunawan

Development of coffee maker service robot using speech and face recognition systems using POMDP

There are many development of intelligent service robot in order to interact with user naturally. This purpose can be done by embedding speech and face recognition ability on specific tasks to the robot. In this research, we would like to propose Intelligent Coffee Maker Robot which the speech recognition is based on Indonesian language and powered by statistical dialogue systems. This kind of robot can be used in the office, supermarket or restaurant. In our scenario, robot will recognize user’s face and then accept commands from the user to do an action, specifically in making a coffee. Based on our previous work, the accuracy for speech recognition is about 86% and face recognition is about 93% in laboratory experiments. The main problem in here is to know the intention of user about how sweetness of the coffee. The intelligent coffee maker robot should conclude the user intention through conversation under unreliable automatic speech in noisy environment. In this paper, this spoken dialog problem is treated as a partially observable Markov decision process (POMDP). We describe how this formulation establish a promising framework by empirical results. The dialog simulations are presented which demonstrate significant quantitative outcome.

Handling illumination variation in face recognition using multiscale retinex

Face recognition has an important role in the age of information technology to improve comfort and security. Various face recognition algorithms are proven to be effective if done under a controlled environment. However, recognition performance will decrease significantly in the uncontrolled environment, for example caused by illumination variation. This paper discusses the approach to deal with varying illumination on face recognition with Multi-Scale Retinex method. To verify accuracy of this algorithm, it is used Principal Component Analysis (PCA) and Eulidean distance as algorithms to identify faces. In the experiments, Multi-Scale Retinex is also compared to other normalization methods, such as gamma correction, histogram equalization, Retinex, and Single-Scale Retinex. Based on several face recognition dataset, that is Extended Yale B, Faces95, and Grimace, it can be concluded that the Multi-Scale Retinex method with one scale (Single-Scale Retinex) can properly normalize the illumination on the face image in term of speed and performance.

Tracking efficiency measurement of dynamic models on geometric particle filter using KLD-resampling

Particle filter has appeared as a useful tool for visual object tracking. The efficiency of the particle filter depends mostly on the number of particles used in the estimation. This paper would like to measure the efficiency of particle filter via the Kullback-Leibler distance (KLD). The basis of the method is similar to Foxs KLD-sampling but implemented differently using resampling. The benefit of this approach is that the underlying distribution is exactly the posterior distribution. By means of batch KLD-resampling, we measure the efficiency of several dynamic models by calculating the average number of needed samples. Using experiments, we found (i) the efficiency of particle filter can be measure reliably enough using batch KLD-resampling, (ii) dynamics models affect the efficiency of particle filter, but their performance depends mostly on the case by case situationally.

Fast brain control systems for electric wheelchair using support vector machine

This paper proposes a technology which enables healthy human brain to control electronic wheelchair movement. The method involves acquiring electroencephalograph (EEG) data from specific channels using Emotiv Software Development Kit (SDK) into Windows based application in a tablet PC to be preprocessed and classified. The aim of this research is to increase the accuracy rate of the brain control system by applying Support Vector Machine (SVM) as machine learning algorithm. EEG samples are taken from several respondents with disabilities but still have healthy brain to pick most suitable EEG channel which will be used as a proper learning input in order to simplify the computational complexity. The controller system based on Arduino microcontroller and combined with .NET based software to control the wheel movement. The result of this research is a brain-controlled electric wheelchair with enhanced and optimized EEG classification.

Blind speech separation system for humanoid robot with FastICA for audio filtering and separation

Nowadays, there are many developments in building intelligent humanoid robot, mainly in order to handle voice and image. In this research, we propose blind speech separation system using FastICA for audio filtering and separation that can be used in education or entertainment. Our main problem is to separate the multi speech sources and also to filter irrelevant noises. After speech separation step, the results will be integrated with our previous speech and face recognition system which is based on Bioloid GP robot and Raspberry Pi 2 as controller. The experimental results show the accuracy of our blind speech separation system is about 88% in command and query recognition cases.

Accurate visual tracking by combining Bayesian and evolutionary optimization framework

Visual tracking is the process of locating, identifying, and determining of an object within video frames. From a Bayesian perspective, this is done by estimating the posterior density function. On the other hand, evolutionary optimization perspective would like to generate and select sufficiently optimize solution using two major components: diversification and intensification. This research will develop visual tracking algorithm using a Bayesian approach with evolutionary optimization in order to perform accurate tracking. The main idea is to combine Particle Markov Chain Monte Carlo (Particle-MCMC) as representation of Bayesian approach, with evolutionary optimization that is Particle Swarm Optimization (PSO) in each video frame. The visual tracking is regulated by Particle-MCMC filter algorithm and PSO will work within this filter to get more accurate tracking. Based on the dataset groundtruth, we found the accuracy of tracking can be increased considerably comparing to our previous research.

Multi-sperm tracking using Hungarian Kalman Filter on low frame rate video

One factor of human sperm health is sperm motility. Motility is the ability of sperm to move. Sperm with healthy motility move forward promptly, not inactive and not moving in circles. In this paper, we would like to analyse sperm motility by considering the problem of multi object tracking in video sequences of human sperms. The challenges in multi-sperm tracking are many human sperms have fast and unpredictable movement In addition, the sperm have similar size and shape comparing by each others. To solve this problem, we used sperm detection in each video sequence to get the position of sperms. In the same time, the estimated sperm position is calculated based on previous tracking by using Kalman Filter. Finally the positions of detected sperms are compared to estimation results by using Hungarian assignment method. In this way, the trajectory of each sperm can be conclude. This paper analyze sperm motility qualitatively based on the resulted sperm trajectories. The experiment results were conducted on both open video data and our own low-frame-rate video data. The experiment results shows that the proposed method can handle the challenges in multi sperm tracking, create their trajectory and then analyze their behaviors.

Spatial data mining for predicting of unobserved zinc pollutant using ordinary point Kriging

Due to pollution over many years, large amounts of heavy metal pollutant can be accumulated in the rivers. In the research, we would like to predict the dangerous region around the river. For study case, we use the Meuse river floodplains which are contaminated with zinc (Zn). Large zinc concentrations can cause many health problems, for example vomiting, skin irritations, stomach cramps, and anaemia. However there is only few sample data about the zinc concentration of Meuse river, thus the missing data in unknown regions need to be generated. The aim of this research is to study and to apply spatial data mining to predict unobserved zinc pollutant by using ordinary point Kriging. By mean of semivariogram, the variability pattern of zinc can be captured. This captured model will be interpolated to predict the unknown regions by using Kriging method. In our experiments, we propose ordinary point Kriging and employ several semivariogram: Gaussian, Exponential and Spherical models. The experimental results show that: (i) by calculating the minimum error sum of squares, the fittest theoretical semivariogram models is exponential model (ii) the accuracy of the predictions can be confirmed visually by projecting the results to the map.