SVM-based ontology matching approach

There are a lot of heterogeneous ontologies in semantic web, and the task of ontology mapping is to find their semantic relationship. There are integrated methods that only simply combine the similarity values which are used in current multi-strategy ontology mapping. The semantic information is not included in them and a lot of manual intervention is also needed, so it leads to that some factual mapping relations are missed. Addressing this issue, the work presented in this paper puts forward an ontology matching approach, which uses multi-strategy mapping technique to carry on similarity iterative computation and explores both linguistic and structural similarity. Our approach takes different similarities into one whole, as a similarity cube. By cutting operation, similarity vectors are obtained, which form the similarity space, and by this way, mapping discovery can be converted into binary classification. Support vector machine (SVM) has good generalization ability and can obtain best compromise between complexity of model and learning capability when solving small samples and the nonlinear problem. Because of the said reason, we employ SVM in our approach. For making full use of the information of ontology, our implementation and experimental results used a common dataset to demonstrate the effectiveness of the mapping approach. It ensures the recall ration while improving the quality of mapping results.     

A critical review of the most popular types of neuro control

In this review article, the most popular types of neural network control systems are briefly introduced and their main features are reviewed. Neuro control systems are defined as control systems in which at least one artificial neural network (ANN) is directly involved in generating the control command. Initially, neural networks were mostly used to model system dynamics inversely to produce a control command which pushes the system towards a desired or reference value of the output (1989). At the next stage, neural networks were trained to track a reference model, and ANN model reference control appeared (1990). In that method, ANNs were used to extend the application of adaptive reference model control, which was a well‐known control technique. This attitude towards the extension of the application of well‐known control methods using ANNs was followed by the development of ANN model‐predictive (1991), ANN sliding mode (1994) and ANN feedback linearization (1995) techniques. As the first category of neuro controllers, inverse dynamics ANN controllers were frequently used to form a control system together with other controllers, but this attitude faded as other types of ANN control systems were developed. However, recently, this approach has been revived. In the last decade, control system designers started to use ANNs to compensate/cancel undesired or uncertain parts of systems' dynamics to facilitate the use of well‐known conventional control systems. The resultant control system usually includes two or three controllers. In this paper, applications of different ANN control systems are also addressed. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

An efficient initialization approach of Q-learning for mobile robots

This article demonstrates that Q-learning can be accelerated by appropriately specifying initial Q-values using dynamic wave expansion neural network. In our method, the neural network has the same topography as robot work space. Each neuron corresponds to a certain discrete state. Every neuron of the network will reach an equilibrium state according to the initial environment information. The activity of the special neuron denotes the maximum cumulative reward by following the optimal policy from the corresponding state when the network is stable. Then the initial Q-values are defined as the immediate reward plus the maximum cumulative reward by following the optimal policy beginning at the succeeding state. In this way, we create a mapping between the known environment information and the initial values of Q-table based on neural network. The prior knowledge can be incorporated into the learning system, and give robots a better learning foundation. Results of experiments in a grid world problem show that neural network-based Q-learning enables a robot to acquire an optimal policy with better learning performance compared to conventional Q-learning and potential field-based Qlearning.     

Passive internet-based crane teleoperation with haptic aids

Crane operation is a challenging task, due to the combined problem of obstacle avoidance and load swing suppression in underactuated conditions. This paper presents a human-machine interface that increases the operator’s perception of a gantry crane’s workspace. With this aim, a virtual environment resembling the workspace is connected with a haptic device. This allows the user to receive not only visual but also tactile feedback, thus increasing maneuvering safety. Additionally, this capability is integrated in a teleoperation setup, adopting a passivity-based control approach that guarantees overall stability. This includes also the design of controllers by means of the IDA-PBC method. Experimental results carried out with a laboratory crane show its feasibility for internet-based teleoperation and demonstrate the improvements on the system performance.     

Path tracking control of Lagrange systems with obstacle avoidance

This paper addresses a path tracking problem with obstacle avoidance for Lagrange systems. The proposed method is based on field potential methods in combination with navigation functions for obstacle avoidance. First, it is shown that a simple combination of the navigation function with the conventional path tracking controller does not work. Therefore, in order to cope with this problem, a new feedback law is proposed for a path parameter which characterizes the reference path. It is proved that the proposed controller achieves both path following and collision avoidance. Moreover, since the method adopts bounded navigation functions, the proposed controllers generate bounded input signals even when target systems approach obstacles. Finally, an experimental evaluation is performed with a two-link manipulator to illustrate the effectiveness of the proposed method.     

Electrokinetically driven concentration of particles and cells by dielectrophoresis with DC-offset AC electric field

Insulator-based dielectrophoresis (iDEP) has been successfully used for on-chip manipulations of biological samples. Despite its effectiveness, iDEP typically requires high DC voltages to achieve sufficient electric field; this is mainly due to the coupled phenomena among linear electrokinetics: electroosmosis (EO) and electrophoresis (EP) and nonlinear electrokinetics: dielectrophoresis (DEP). This paper presents a microfluidic technique using DC-offset AC electric field for electrokinetic concentration of particles and cells by repulsive iDEP. This technique introduces AC electric field for producing iDEP which is decoupled from electroosmosis (EO) and electrophoresis (EP). The repulsive iDEP is generated in a PDMS tapered contraction channel that induces non-uniform electric field. The benefits of introducing AC electric field component are threefold: (i) it contributes to DEP force acting on particles, (ii) it suppresses EO flow and (iii) it does not cause any EP motion. As a result, the required DC field component that is mainly used to transport particles on the basis of EO and EP can be significantly reduced. Experimental results supported by numerical simulations showed that the total DC-offset AC electric field strength required to concentrate 15-μm particles is significantly reduced up to 85.9% as compared to using sole DC electric field. Parametric experimental studies showed that the higher buffer concentration, larger particle size and higher ratio of AC-to-DC electric field are favorable for particle concentration. In addition, the proposed technique was demonstrated for concentration of yeast cells.     

A power-free deposited microbead plug-based microfluidic chip for whole-blood immunoassay

We present a deposited microbead plug (DMBP)-based microfluidic chip capable of performing plasma extraction and on-chip immunoassay. The DMBP used as a porous blood filter provides pure blood plasma without the contamination of blood cells or beads. Capillary-driven flow eliminates the requirement of external pumps. The human IgG and goat anti-human IgG sample-to-answer assay was performed in this chip within 600 s using only a 10 μl whole-blood sample. This easy-to-use, rapid, inexpensive, and disposable DMBP-based chip holds a great promise for point-of-care application.     

A simple and cost-effective method for fabrication of integrated electronic-microfluidic devices using a laser-patterned PDMS layer

We report a simple and cost-effective method for fabricating integrated electronic-microfluidic devices with multilayer configurations. A CO₂ laser plotter was employed to directly write patterns on a transferred polydimethylsiloxane (PDMS) layer, which served as both a bonding and a working layer. The integration of electronics in microfluidic devices was achieved by an alignment bonding of top and bottom electrode-patterned substrates fabricated with conventional lithography, sputtering and lift-off techniques. Processes of the developed fabrication method were illustrated. Major issues associated with this method as PDMS surface treatment and characterization, thickness-control of the transferred PDMS layer, and laser parameters optimization were discussed, along with the examination and testing of bonding with two representative materials (glass and silicon). The capability of this method was further demonstrated by fabricating a microfluidic chip with sputter-coated electrodes on the top and bottom substrates. The device functioning as a microparticle focusing and trapping chip was experimentally verified. It is confirmed that the proposed method has many advantages, including simple and fast fabrication process, low cost, easy integration of electronics, strong bonding strength, chemical and biological compatibility, etc.     

Fabrication of a biocompatible flexible electroosmosis micropump

In in-vivo microsystems, one of the components is a biocompatible micropump in order to produce the necessary force to deliver the fluid from the inlet to the outlet. In this contribution, a flexible micropump is fabricated which is aimed to be suitable in drug delivery applications. It provides high degree of biocompatibility, since the only employed materials are implantation grade polydimethylsiloxane elastomer and gold for the electrical interconnects. The working principle of the micropump is based on transverse DC electroosmosis which is a new variant of conventionally applied high voltage DC electroosmosis. This new technique is based on topography irregularities introduced in the channel resulting in a non-uniform charge distribution. The advantage is to drive the micropump using a relatively low DC voltage of 10 V while getting an effective flow speed of 60 μm/s. In order to characterize the flow speed, dyed 3 μm beads are dispersed in the working fluid and their speed is measured by the line scanning technique using a confocal microscope. It is also observed that the flow has a helical profile which is an attractive feature for an efficient micro-mixer in active microfluidics and μ-TAS applications.     

Droplet transportation using a pre-charging method for digital microfluidics

A new droplet-driving scheme for digital microfluidics termed the “pre-charging of a droplet” is demonstrated. In this method, a droplet is initially charged by applying “pre-charging” voltage between the droplet and an electrode buried under dielectric layers. The droplet is then driven to the next electrode by applying “driving” voltage between two adjacent buried electrodes. The concept of pre-charging was proved by the polarity of the charge stored in the droplet. When the droplet is pre-charged with positive voltage, it is driven with negative voltage and vice versa. Therefore, the magnitudes of the pre-charging and driving voltages are identical, but only with the opposite polarity. A 2.5-μL deionized water droplet is pre-charged and driven at a minimal voltage of 12 V. The charge stored in the droplet by this pre-charging method remained for more than 2 min, and the driving actuation could be repeated more than 150 times while the droplet remained its charged state. This method suggests a new means of driving a droplet for digital microfluidics at a relatively low voltage by utilizing both the electrostatic and dielectrophoretic force in the droplet transport process with a simpler structure compared to other single-plate structured devices.