Sharif Digital Repository

In this paper a novel fuzzy approach exploiting Active Learning Method is employed in order to estimate the immeasurable states required to control a non-observable double inverted pendulum. Active Learning Method (ALM) is a fuzzy modeling method which exploits Ink Drop Spread (IDS) as its main engine. IDS is a universal fuzzy modeling technique which is very similar to the way human brain processes different phenomena. The ALM system is trained by the data obtained from Linear Quadratic Regulator (LQR) controller. LQR uses an optimal control approach which under certain conditions guarantees robustness. Instead of an expert's knowledge, the LQR controller output is used as a priori... 

This paper describes a genetic-fuzzy system adapted to find efficient partitions on data domains for IDS (Ink Drop Spread). IDS is the engine of Active Learning Method (ALM), a methodology of soft computing. IDS extracts useful information from a system subjected to modeling. Proposed method, called GIDS (Genetic IDS), uses genetic algorithm which optimizes the parameters of membership functions that represent the partitions on data planes. Obtained Results showed that using genetic algorithm to find the partitions has better accuracy than the previous generic IDS methods. © 2008 IEEE  

This paper presents a new and simple algorithm for partitioning the input domain for implementation of Active Learning Method (ALM) algorithm. ALM is a pattern-based algorithm for soft computing which uses the Ink Drop Spread (IDS) algorithm as its main engine for feature extraction. In this paper a simple algorithm is introduced with a few computation cost. In order to evaluate the performance of the proposed algorithm, it is applied to two applications, system modeling and pattern recognition. Simulation results show the effectiveness of our algorithm in specifying the appropriate points for dividing the inputs domains  

This paper introduces an innovative adaptive controller based on the actor-critic method. The proposed approach employs the ink drop spread (IDS) method as its main engine. The IDS method is a new trend in softcomputing approaches that is a universal fuzzy modeling technique and has been also used as a supervised controller. Its process is very similar to the processing system of the human brain. The proposed actor-critic method uses an IDS structure as an actor and a 2-dimensional plane, representing control variable states, as a critic that estimates the lifetime goodness of each state. This method is fast, simple, and away from mathematical complexity. The proposed method uses the... 

The electrohydrodynamic (EHD) 3D printing technology is an Additive Manufacturing (AM) method that can be used in the manufacture of submicron-size structures. In this process, which is based on the formation of Taylor jet from a metallic ink, the investigation of particles reaction and aggregate formation in ink during printing is of great importance. In this paper, a new Finite Element model based on particle tracing in fluids is presented that couples the different physics that govern an EHD phenomenon. Vortex flow caused by boundary shear stress was observed in the ink jet; which was more like the Marangoni phenomenon in a stationary drop. By experimentally validating the presented model... 

Inkjet printing of colloidal metals is an attractive method for direct patterning of electrically conductive structures and interconnects in electronic devices, owing to low-cost, low-waste and simplicity of the process. In the present work, mixtures of well-dispersed silver nanoparticles and ethylene glycol were prepared for the inkjet printing process. Three different surfactants including PVP, MSA and AOT were added to study the stability of the nanosilver colloids. The effect of high-intensity ultrasonic treatment and temperature on the rheological properties was investigated utilising a rheometer in plate-plate geometry. It is shown that the viscosity of the ink increases with... 

In this paper we proposed a new real-time learning method. The engine of this method is a fuzzy-modeling technique which is called ink drop spread (IDS). IDS method has good convergence and is very simple and away from complex formula. The proposed method uses a reinforcement learning approach by an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the IDS by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. It is shown that the system can adapt itself, commencing with random actions. © 2008 IEEE  

This paper presents a new inference algorithm for Active Learning Method (ALM). ALM is a pattern-based algorithm for soft computing which uses the Ink Drop Spread (IDS) algorithm as its main engine for feature extraction. In this paper a fuzzy number is extracted from each IDS plane rather than the narrow path and spread as in previous approaches. In order to compare performance of the proposed algorithm with the original one, two functions which are widely used in literature are modeled as the benchmark. Simulation results show that the proposed algorithm is as effective as previous one in the modeling task  

Ink drop spread (IDS) is the engine of an active learning method, which is the methodology of soft computing. IDS, as a pattern-based processing unit, extracts useful information from a system that is subjected to modeling. In spite of its excellent potential to solve problems such as classification and modeling compared with other soft-computing tools, finding its simple and fast hardware implementation is still a challenge. This paper describes a new hardware implementation of the IDS method that is based on the memristor crossbar structure. In addition to simplicity, being completely real time, having low latency, and the ability to continue working properly after the occurrence of power... 

Proposing an efficient algorithm with an appropriate hardware implementation has always been an interesting and a rather challenging field of research in Artificial Intelligence (AI). Fuzzy logic is one of the techniques that can be used for accurate and high-speed modeling as well as controlling complex and nonlinear systems. The “defuzzification” process during the test phase as well as the repetitive processes in order to find the optimal parameters during the training phase, lead to some serious limitations in real-time applications and hardware implementation of these algorithms. The proposed algorithm employs Ink Drop Spread (IDS) concept to mimic the functionality of human brain. In... 

Three-dimensional macroporous fluorine-doped tin oxide (p-FTO) films were successfully deposited using commercial ink of FTO powder and SnCl2 salt via Dr. Blade method. Various features of p-FTO thin films were studied as a function of the ink composition and sintering temperature. The morphological studies corroborated formation of porous, uniform, and crack-free FTO films after annealing at 300 °C for 10 min in air. X-ray diffraction pattern demonstrated development of highly crystalline FTO films. The lowest sheet resistance of 47 Ω/□ was obtained for the p-FTO film with a thickness of 21 μm. The capacitance of thin p-FTO films was investigated using a three-electrode system and the... 

Inkjet-printing (IJP) technology is recognized as a significant breakthrough in manufacturing high-performance electrochemical energy storage systems. In comparison to conventional fabrication protocols, this printing technique offers various advantages, such as contact-less high-resolution patterning capability; low-cost, controlled material deposition; process simplicity; and compatibility with a variety of substrates. Due to these outstanding merits, significant research efforts have been devoted to utilizing IJP technology in developing electrochemical energy storage devices, particularly in supercapacitors (SCs). These attempts have focused on fabricating the key components of SCs,... 

In this work, synthesis of CuIn0.75Ga0.25S2 (CIGS) nanoparticles, the formation of stable dispersion, deposition of high-quality films and, fabrication of thin-film Perovskite solar cells are reported. The stability of nanoparticle ink is crucial in the formation of device-quality films. The chalcogenide-based materials are widely used in thin-film solar cells; in particular, Cu(In,Ga)S2 are used as an absorber and hole transporting layer. In the present study, the nanoparticles of about 20 nm size and bandgap of 1.5 eV are synthesized using a heat-up method. A variety of solvents are used as dispersing media and the stability of the inks is evaluated by precise optical monitoring. We... 

Human Brain is one of the most wonderful and complex systems which is designed for ever; A huge complex network composed of neurons as tiny biological and chemical processors which are distributed and work together as a super parallel system to do control and vital activities of human body. Brain learning simulation and hardware implementation is one of the most interesting research areas in order to make artificial brain. One of the researches in this area is Active Learning Method in brief ALM. ALM is an adaptive recursive fuzzy learning algorithm based on brain functionality and specification which models a complex Multi Input Multi Output System as a fuzzy combination of Single Input...