In this paper, we introduce an advanced architecture of K-Means clustering-based polynomial Radial Basis Function Neural Networks (p-RBFNNs) designed with the aid of SSOA (Space Search Optimization Algorithm) and develop a comprehensive design methodology supporting their construction. In order to design the optimized p-RBFNNs, a center value of each receptive field is determined by running the K-Means clustering algorithm and then the center value and the width of the corresponding receptive field are optimized through SSOA. The connections (weights) of the proposed p-RBFNNs are of functional character and are realized by considering three types of polynomials. In addition, a WLSE (Weighted Least Square Estimation) is used to estimate the coefficients of polynomials (serving as functional connections of the network) of each node from output node. Therefore, a local learning capability and an interpretability of the proposed model are improved. The proposed model is illustrated with the use of nonlinear function, NOx called Machine Learning dataset. A comparative analysis reveals that the proposed model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

Recently, recommender systems have been widely applied in E-commerce websites to help their customers find the items what they want. A recommender system should be able to provide users with useful information regarding their interests. The ability to immediately respond to the changes in user's preference is a valuable asset of recommender systems. This paper proposes a novel recommender system which aims to effectively adapt and respond to the immediate changes in user's preference. The proposed system combines IEC (Interactive Evolutionary Computation) with a content-based filtering method and also employs data grouping in order to improve time efficiency. Experiments show that the proposed system makes acceptable recommendations while ensuring quality and speed. From a comparative experimental study with an existing recommender system which uses the content-based filtering, it is revealed that the proposed system produces more reliable recommendations and adaptively responds to the changes in any given condition. It denotes that the proposed approach can be an alternative to resolve limitations (e.g., over-specialization and sparse problems) of the existing methods.

HMMs (Hidden Markov Models) are widely used for biological signal, such as EEG (electroencephalogram) sequence, analysis because of their ability to incorporate sequential information in their structure. A recent trends of research are going after the biological interpretable HMMs, and we need to control the complexity of the HMM so that it has good generalization performance. So, an automatic means of optimizing the structure of HMMs would be highly desirable. In this paper, we described a procedure of classification of motor imagery EEG signals using HMM. The motor imagery related EEG signals recorded from subjects performing left, right hand and foots motor imagery. And the proposed a method that was focus on the validation of the HSA (Harmony Search Algorithm) based optimization for HMM. Harmony search algorithm is sufficiently adaptable to allow incorporation of other techniques. A HMM training strategy using HSA is proposed, and it is tested on finding optimized structure for the pattern recognition of EEG sequence. The proposed HSA-HMM can performs global searching without initial parameter setting, local optima, and solution divergence.

The HIV (Human Immunodeficiency Virus) causes AIDS (Acquired Immune Deficiency Syndrome). The process of infection and mutation by HIV can be described by a 3rd order state equation. For this HIV model that includes the dynamics of the mutant virus, we present a parameter estimation scheme using two state variables sporadically measured, out of the three, by employing a genetic algorithm. It is assumed that these non-uniformly sampled measurements are subject to random noises. The effectiveness of the proposed parameter estimation is demonstrated by simulations. In addition, the estimated parameters are used to analyze the equilibrium points of the HIV model, and the results are shown to be consistent with those previously obtained.

The flexibility and evolvability are critical characteristics of modern manufacturing to adapt to changes from products and disturbances in the shop floor. The technologies inspired from biology and nature enable to equip the manufacturing systems with these characteristics. This paper proposes an ant colony inspired autonomous manufacturing system in which the resources on the shop floor are considered as the autonomous entities. Each entity overcomes the disturbance by itself or negotiates with the others. The swarm of cognitive agents with the ant-like pheromone based negotiation mechanism is proposed for controlling the shop floor. The functionality of the developed system is proven on the test bed.

This paper considers a data fitting problem for rational function models using the LM (Levenberg-Marquardt) optimization method. Rational function models have various merits on representing a wide range of shapes and modeling complicated structures by polynomials of low degrees in both the numerator and denominator. However, rational functions are nonlinear in the parameter vector, thereby requiring nonlinear optimization methods to solve the fitting problem. In this paper, we propose a data fitting method for rational function models based on the LM algorithm which is renowned as an effective nonlinear optimization technique. Simulations show that the fitting results are robust against the measurement noises and uncertainties. The effectiveness of the proposed method is further demonstrated by the real application to a 3D depth camera calibration problem.

Neural network technique is widely employed in the fields of signal processing, control systems, pattern recognition, etc. Learning of neural networks is an important procedure to accomplish dynamic system modeling. This paper presents a novel learning approach for differential neural network models based on the Kalman-Bucy filter theory. We construct an augmented state vector including original neural state and parameter vectors and derive a state estimation rule avoiding gradient function terms which involve to the conventional neural learning methods such as a back-propagation approach. We carry out numerical simulation to evaluate the proposed learning approach in nonlinear system modeling. By comparing to the well-known back-propagation approach and Kalman-Bucy filtering, its superiority is additionally proved under stochastic system environments.

Target tracking performance improvement using multi-sensor data fusion is a challenging work. However, biases in the measurements should be removed before various data fusion techniques are applied. In this paper, a bias removing algorithm using measurement data from multi-radar tracking systems is proposed and evaluated by computer simulation. To predict bias estimation performance in various geometric relations between the radar systems and target, a system observability index is proposed and tested via computer simulation results. It is also studied that target tracking which utilizes multi-sensor data fusion with bias-removed measurements results in better performance.

An efficient sequential computation algorithm of kinematic optimal control is suggested for redundancy resolution of freefloating manipulators. Utilization of minimum principle usually requires involved and tedious procedure of differentiation of Hamiltonian. Due to the constraints of momentum conservation, it is not easy to get exact differential equations of boundary value problem for even relatively simple free-floating manipulator models. To overcome this difficulty, we developed an effective sequential algorithm for the computation of terms appeared in the differential equations. The usefulness of suggested approach is verified by simulation of a planar 3-joints free-floating manipulator.

This paper proposes an algorithm to detect the stop line and crosswalk on the road surface using edge information and blob coloring. The detection has been considered as an important area of autonomous vehicle technologies. The proposed algorithm is composed of three phases: 1) hypothesis generation of stop lines, 2) hypothesis generation of crosswalks, and 3) hypothesis verification of stop lines. The last two phases are not performed if the first phase does not provide a hypothesis of a stop line. The last one is carried out by the combination of both hypotheses of stop lines and crosswalks, and determines the stop lines among stop line hypotheses. The proposed algorithm is proven to be effective through experiments with various images captured on the roads.

High precision of planning in the preoperative phase can contribute to increase operational safety during computer-aided spinal fusion surgery, which requires extreme caution on the part of the surgeon, due to the complexity and delicacy of the procedure. In this paper, an advanced preoperative planning framework for spinal fusion is presented. The framework is based on spinal pedicle data obtained from CT (Computed Tomography) images, and provides optimal insertion trajectories and pedicle screw sizes. The proposed approach begins with safety margin estimation for each potential insertion trajectory that passes through the pedicle volume, followed by procedures to collect a set of insertion trajectories that satisfy operation safety objectives. The radius of a pedicle screw was chosen as 70% of the pedicle radius. This framework has been tested on 68 spinal pedicles of 8 patients requiring spinal fusion. It was successfully applied, resulting in an average success rate of 100% and a final safety margin of $2.44{\pm}0.51mm$.

Nowadays many neurological diseases such as stroke and Parkinson diseases are continually increasing. Orthotic devices as well as exoskeletons have been widely developed for supporting movement assistance and therapy of patients. Robotic knee orthosis can compensate stiff-knee gait of the paralyzed limb and can provide patients consistent assistance at wearable environments. With keeping a robotic orthosis wearable, however, it is not easy to develop a compact and safe actuator with fast rotation and high torque for consistent supports of patients during walking. In this paper, we propose a novel kinematic model for a robotic knee orthosis to drive a knee joint with independent actuation during swing and stance phases, which can allow an actuator with fast rotation to control swing motions and an actuator with high torque to control stance motions, respectively. The suggested kinematic model is composed of a hamstring device with a slide-crank mechanism, a quadriceps device with five-bar/six-bar links, and a patella device for knee covering. The quadriceps device operates in five-bar links with 2-dof motions during swing phase and is changed to six-bar links during stance phase by the contact motion to the patella device. The hamstring device operates in a slider-crank mechanism for entire gait cycle. The kinematics and velocity/force relations are analyzed for the quadriceps and hamstring devices. Finally, the adequate actuators for the suggested kinematic model are designed based on normal gait requirements. The suggested kinematic model will allow a robotic knee orthosis to use compact and light actuators with full support during walking.

An essential consideration to differentiate prosthetic hand from robot hand is its convenience and usefulness rather than high resolution or multi-function of the robot hand. Therefore, this study proposes a myoelectric hand with a 2 DOF auto wrist module which has 6 essential functions of the human hand such as open, grasp, pronation, supination, extension, flexion, which improves the convenience of the daily life. It consists of the 3 main parts, the myoelectric sensor for input signal without additional attachment to operate the prosthetic hand, hand mechanism with high-torqued auto-transmission mechanism and self-locking module which guarantee the safety under the abrupt emergency and minimum power consumption, and dual threshold based controller to make easy for adopting the multi-DOF myoelectric hand. We prove the validity of the proposed system with experimental results.

The objectives of this research are development of guidance, navigation and control system for RUAV on virtual instrumentation and real flight test. For this research, the system is divided to DAQ (data acquisition) section, actuator section and controller section. And the hardware and software on each sections are realized on LabVIEW base. Waypoint guidance and control of auto flight are realized using PID gain tuning and waypoint vector tracking guidance algorism. For safe flight test, auto/manual switching module isolated from FCS (Flight Control System) is developed. By using the switch module, swift mode change was achieved during emergency flight case. Consequently, a meter level error of flight performance is achieved.

In this paper, an effective path generation algorithm for obstacle avoidance producing small amount of steering action as possible is proposed. The proposed path generation algorithm can reduce unnecessary steering because of the small lateral changes in generated waypoints when UGV (Unmanned Ground Vehicle) encounters obstacles during its waypoint navigation. To verify this, the proposed algorithm and $A^*$ algorithm are analyzed through the simulation. The proposed algorithm shows good performance in terms of lateral changes in the generated waypoint, steering changes of the vehicle while driving and execution speed of the algorithm. Especially, due to the fast execution speed of the algorithm, the obstacles that encounter suddenly in front of the vehicle within short range can be avoided. This algorithm consider the waypoint navigation only. Therefore, in certain situations, the algorithm may generate the wrong path. In this case, a general path generation algorithm like $A^*$ is used instead. However, these special cases happen very rare during the vehicle waypoint navigation, so the proposed algorithm can be applied to most of the waypoint navigation for the unmanned ground vehicle.