Wisnu Jatmiko

A pso-based mobile robot for odor source localization in dynamic advection-diffusion with obstacles environment: theory, simulation and measurement

This paper provides a combination of chemotaxic and anemotaxic modeling, known as odor-gated rheotaxis (OGR), to solve real-world odor source localization problems. Throughout the history of trying to mathematically localize an odor source, two common biometric approaches have been used. The first approach, chemotaxis, describes how particles flow according to local concentration gradients within an odor plume. Chemotaxis is the basis for many algorithms, such as particle swarm optimization (PSO). The second approach is anemotaxis, which measures the direction and velocity of a fluid flow, thus navigating upstream within a plume to localize its source. Although both chemotaxic and anemotaxic based algorithms are capable of solving overly-simplified odor localization problems, such as dynamic-bit-matching or moving-parabola problems, neither method by itself is adequate to accurately address real life scenarios. In the real world, odor distribution is multi-peaked due to obstacles in the environment. However, by combining the two approaches within a modified PSO-based algorithm, odors within an obstacle-filled environment can be localized and dynamic advection-diffusion problems can be solved. Thus, robots containing this modified particle swarm optimization algorithm (MPSO) can accurately trace an odor to its source

A PSO-based Mobile Sensor Network for Odor Source Localization in Dynamic Environment: Theory, Simulation and Measurement

This paper presents a problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Most work on chemical sensing with mobile robots assume an experimental setup that minimizes the influence of turbulent transport by either minimizing the source-to-sensor distance in trail following or by assuming a strong unidirectional air stream in the environment, including our previous work. However, not much attention has been paid to the natural environment problem. Modification Particle Swarm Optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charged PSO, which is another extension of the PSO, has also been applied to solve dynamic problems. Odor source localization is an interesting application in dynamic problems. We will adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles. Before applying the algorithm for real implementation, some important hardware conditions must be considered. Firstly, to reduce the possibility of robots leaving the search space, a limit to the value of velocity vector is needed. The value of vector velocity can be clamped to the range [-Vmax, Vmax]; in our case for the MK-01 Robot, the maximum velocity is 0.05 m/s. Secondly, in the standard PSO algorithm there is no collision avoidance mechanism. To avoid the collision among robot we add some collision avoidance functions. Finally, we also add some sensor noise, delay and threshold value to model the sensor response. Then we develop odor localization algorithm, and simulations to show that the new approach can solve such dynamic environment problems.

Artificial odor discrimination system using multiple quartz resonator sensors and various neural networks for recognizing fragrance mixtures

An electronic odor discrimination system had been developed by using four quartz resonator-sensitive membranes basic-resonance frequencies at 10 MHz as a sensor and analyzed the measurement data through a back propagation (BP) as the pattern recognition system. The developed system showed high recognition probability to discriminate various single odors to its high generality properties; however, the system had a limitation in recognizing the fragrances mixture. This system also had other disadvantages, such as classifying the unknown category of odor as the known category of odor. In order to improve the performance of the proposed system, development of the sensor and other neural networks (NNs) are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from four quartz resonator-basic resonance frequencies at 10 MHz with new 16 quartz resonator-basic resonance frequencies at 20 MHz, but also by replacing the pattern classifier from BP NNs with the variance of BP, probabilistic NNs, and fuzzy-neuro learning vector quantization (FNLVQ). Matrix similarity analysis (MSA) is then proposed to increase the accuracy of the FNLVQ, to become FNLVQ-MSA neural systems in determining the best exemplar vector, for speeding up its convergence. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing the fragrance mixtures, in addition to recognizing the unknown fragrance mixtures. The use of new sensing systems and FNLVQ-MSA has produced higher capability, compared to the previously mentioned system.

Distributed odor source localization in dynamic environment

This paper addresses the problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Modification particle swarm optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charge PSO, which is another extension of the PSO has also been applied to solve dynamic problem. Odor source localization is an interesting application in dynamic problem. We adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles. Then we develop odor localization algorithm, and simulations to show that the new approach can solve such a kind of dynamic environment problem

A Mobile Robots PSO-based for Odor Source Localization in Dynamic Advection-Diffusion Environment

This paper presents a problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Odor source localization is an interesting application in dynamic problems. Modified particle swarm optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charged PSO which is another extension of the PSO has also been applied to solve dynamic problems. We adopted two types of modified concepts of PSO for a new algorithm in order to control autonomous vehicles in more realistic environment where a speed limitation of the robot behavior and collision avoidance mechanism should be taken into consideration as well as the effect of noise and threshold value for the odor sensor response, also positioning error of GPS sensor of robot. Simulations illustrate that the new approach can solve such dynamic problems in advection-diffusion odor model environment

A Particle Swarm-based Mobile Sensor Network for Odor Source Localization in a Dynamic Environment

This paper addresses the problem of odor source localization in a dynamic environment, which means the odor distribution is changing over time. Modification Particle Swarm Optimization is a well-known algorithm, which can continuously track a changing optimum over time. PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Charge PSO, which is another extension of the PSO has also been applied to solve dynamic problem. Odor source localization is an interesting application in dynamic problem. We will adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles. Before applying the algorithm in a real implementation, some important hardware parameters must be considered. Firstly, to reduce the possibility of robots leaving the search space it is needed to limit the value of vector velocity. The value of vector velocity can be clamped to the range [-Vmax, Vmax]; in our case for the MK-01 Robot, the maximum velocity is 0.05 m/s. Secondly, in PSO algorithm standard there is no collision avoidance mechanism. To avoid the collision among robot we add some collision avoidance functions. Finally, we also add some sensor noise, delay and threshold value to model the sensor response. Then we develop odor localization algorithm, and simulations to show that the new approach can solve such a kind of dynamic environment problem.

A Mobile Robots PSO-Based for Odor Source Localization in Extreme Dynamic Advection-Diffusion Environment with Obstacle

The odor distribution advection-diffusion environments in obstacle environment have been developed. In real world the odor distribution are changing over time and multi peaks especially in obstacle environments. The purpose of developing this environment is to bridge the gap between the very complex hard to understand real-world problem (odor dispersion model) and all too simple toy problems (dynamic bit matching or moving parabola). Modified particle swarm optimization is a well-known algorithm, which can continuously track a changing optimum over time. We will adopt two types of PSO modification concepts to develop a new algorithm in order to control autonomous vehicles to solve odor source localization in real world environment. Firstly, PSO can be improved or adapted by incorporating the change detection and responding mechanisms for solving dynamic problems. Secondly, charged PSO, which is another extension of the PSO, has also been applied to solve dynamic problems. In order to control autonomous vehicles in more realistic condition from the viewpoint of robotic, where a speed limitation of the robot behavior and collision avoidance mechanism should be taken into consideration as well as the effect of noise and threshold value for the odor sensor response, also positioning error of GPS sensor of robot. Simulations illustrate that the new approach can solve such dynamic environment in advection-diffusion odor model problems even though in obstacle environments.

Artificial odor discrimination system using multiple quartz-resonator sensor and neural network for recognizing fragrance mixtures

Human sensory test is often used for obtaining the sensory quantities of odors; however, the fluctuation of results due to the experts condition can cause discrepancies among panelist. Artificial odor discrimination system is constructed to overcome the limitation of the already existing sensory test systems. Authors have developed an electronic odor discrimination system by using 4 quartz-resonator sensitive membranes as the sensors and had fundamental resonance frequencies 10 MHz. In recognizing and classifying the output pattern, the system used back propagation (BP) neural network as the pattern recognizer. This system can recognize the limited odor mixtures. The capability of the system can be amended by improving the hardware and changing the software of pattern classifier. This paper proposes a new sensing system using 16 multiple quartz resonator sensors array and basic resonance frequencies 20 MHz. Also modify various neural network called probabilistic neural network (PNN) and fuzzy-neuro learning vector quantization (FLVQ) as the automated pattern recognition system. The purpose of the recent study is to construct an artificial odor discrimination system for recognizing the fragrance mixtures. It is found out that the using of new sensing system as in PNN and FLVQ produces higher capability compare to the conventional sensing system with back propagation (BP) neural network.

Optimized probabilistic neural networks in recognizing fragrance mixtures using higher number of sensors

The electronic odor discrimination system have developed. The developed system showed high recognition probability to discriminate various single odors to its high generality properties; however, the system had a limitation in recognizing the fragrances mixture. In order to improve the performance of the proposed system, development of the sensor and other neural network are being sought. This paper explains the improvement of the capability of that system. In this experiment, the improvement is conducted not only by replacing the last hardware system from 4 quartz resonator-basic resonance frequencies 10 MHz with new 16 quartz resonator-basic resonance frequencies 20 MHz, but also by replacing the pattern classifier from back propagation (BP) neural network with variance of back propagation, probabilistic neural network (PNN) and optimized-PNN. The purpose of the recent study is to construct a new artificial odor discrimination system for recognizing fragrance mixtures. The using of new sensing system and employing various neural networks have produced higher capability to recognize the fragrance mixtures compared to the earlier mentioned system

Mel-Frequency Cepstrum Coeffficients as Higher Order Statistics Representation to Characterize Speech Signal for Speaker Identification System in Noisy Environment Using Hidden Markov Model

Sound is an effective and efficient magnitude for biometric characterization. However, the sound is a phenomenon that is a fusion of multidimensional and influenced many aspects, such as speaker characteristics (articulator configuration, emotions, health, age, sex, dialect), languages, and the environment (background and transmission media), so that the system has been developed until now has not been able to work well in real situations. This is the background of this research. In this research, we investigate higher order statistics (HOS) and Mel-Frequency Cepstrum Coefficients (MFCC) as a feature extraction, and integrated with a Hidden Markov Model (HMM) as a classifier to get a more robust speaker identification system, especially for Gaussian Noise. Research carried out more focused on feature extraction part of the speaker identification system. In classifier process stage, we use the HMM. This is a technique that has been widely used in voice processing provides good results. At the beginning, we empirically showed the failure of conventional MFCC using power spectrum in noisy environment. Then proceed with reviewing the matter, and proposed HOS-based extraction techniques to overcome these problems. Next is an experiments to demonstrate the effectiveness of the proposed method. Data used in this study came from 10 people who say the phrase PUDHESA as much as 80 times with different ways of utterance. In this research, we use signals that are spoken with different variations of pressure, duration, emotional, loud and weak. Figure 1 presents the forms of signals for different utterances of a speaker. In accordance with the focus of this research is to build models that are more robust to noise, then we add a Gaussian noise signal to each original signal with a signal-tonoise ratio (SNR) of 20 dB, 10 dB, 5 dB and 0 dB.