Item recommendation based on context-aware model for personalized u-healthcare service

A personalized service in the ubiquitous environment is to provide services or items, which reflect personal tastes, attitudes, and contexts. It is impossible to reflect the context information generated in u-healthcare environments due to the existing recommendation system performing the recommendation using the information directly input by users and application usage record only. This study develops a context-aware model using the context information provided by the context information model. The study applies it to the extraction of the missing value in a collaborative filtering process. The context-aware model reflects the information that selects items by users according to the appropriate context using the C-HMM and provides it to users. The solution of the missing value in the preference significantly affects the recommendation accuracy in a preference based item supply method. Thus, this study developed a new collaborative filtering for ubiquitous environments by reflecting the missing preference value and reflecting it to the collaborative filtering using the context-aware model. Also, the validity of this method will be evaluated by applying it to menu services in u-healthcare services.     

Adsorption and desorption kinetics of hydrocarbons in FCC catalysts studied using a tapered element oscillating microbalance (TEOM). Part 2: numerical simulations

The factors affecting the adsorption and desorption kinetics in a TEOM are reviewed in detail with particular attention given to the assumptions required to obtain physical transport parameters from the data. Two models are presented to simulate TEOM adsorption data in the case that concentration differences down the catalyst bed can be neglected, as is appropriate when the amount of catalyst used is small, the carrier gas flowrate is large, and/or the adsorbate partial pressure is low. In the first model, the effective diffusion coefficient, D_e, is taken to be constant. In the second model, the effective diffusion coefficient is assumed to obey the Darken equation, D_e=D₀/(1−θ). The TEOM results obtained on n-hexane, n heptane, n-octane, toluene and p-xylene on a commercial FCC catalyst and on pure rare-earth exchanged zeolite Y under non-reacting conditions (373-) are analysed in detail. It is found that intracrystalline diffusion is not the limiting factor affecting the overall rates of adsorption and desorption for the systems studied. Instead, it is the transport of molecules between the adsorbed and vapour phases at the edge of zeolite crystallites that is the limiting transport step affecting the overall kinetics. For the FCC catalyst, the limiting step is the transport of molecules at the zeolite-matrix interface rather than, say, the matrix-vapour interface. Local rate constants for the desorption of the hydrocarbons at the rate-controlling interface have been obtained.     

Case-based context ontology construction using fuzzy set theory for personalized service in a smart home environment

To provide context-based personalized services utilizing smart appliances in a smart home environment, we propose a framework for PersonAlized Service disCovery Using FuZZY-based CBR and Context Ontology (PASCUZZY). Basically, the PASCUZZY framework is implemented on case-based context ontology. To generate and manage the case instances on the case-based context ontology, we adopt the fuzzy set theory to transpose numerical-type context data sensed from the surrounding environment. The context is transposed to linguistic-type context instances on the context ontology. In addition, to formalize and manage the context and services as multi-attributed data, the context ontology was developed reflecting the structure of cases borrowed from case-based reasoning. Furthermore, we propose adaptation methods to adjust the generic fuzzy membership functions depending on the inhabitants’ context. It is performed by modifying the values of the membership number and/or modifying the numbers of the linguistic terms that are based on the inhabitants’ context to affect the membership numbers. The adapted membership functions return the personalized degree of memberships depending on the specialized context of a specific fuzzy variable. Inevitably, the number of cases on the case-based context ontology will be increased from time to time. We apply Ward’s method not only to reduce the search effort via a hierarchical clustering on the case-based context ontology but also to find the most similar service as a solution to the new context. To verify the superiority of the PASCUZZY framework, we perform two kinds of evaluations. First, we evaluate the effectiveness of the adaptation of the fuzzy membership functions. Second, we verify the effectiveness of the application of a clustering method to the case instances of the case-based context ontology to identify the most similar service. Results of the experiment verified the effectiveness and superiority of the PASCUZZY framework.     

A fully autonomous kernel-based online learning neural network model and its application to building cooling load prediction

Building cooling load prediction is critical to the success of energy-saving measures. While many of the computational models currently available in the industry have been developed for this purpose, most require extensive computer resources and involve lengthy computational processes. Artificial neural networks (ANNs) have recently been adopted for prediction, and pioneering works have confirmed the feasibility of this approach. However, users are required to predetermine an ANN model’s parameters. This hinders the applicability of the ANN approach in actual engineering problems, as most engineers may be unfamiliar with soft computing. This paper proposes a fully autonomous kernel-based neural network (AKNN) model for noisy data regression prediction. No part of the model’s mechanism requires human intervention; rather, it self-organises its structure according to the training samples presented. Unlike the other existing autonomous models, the AKNN model is an online learning model. It is particularly suitable for online steps-ahead prediction. In this paper, we benchmark the AKNN model’s performance according to other ANN models. It is also successfully applied to predicting the cooling load of a commercial building in Hong Kong. The occupancy areas and concentration of carbon dioxide inside the building are successfully adopted to mimic the building’s internal cooling load. Training data was adopted from actual measurements taken inside the building. Its results show reasonable agreement with actual cooling loads.     

Real-time stochastic optimal control for traffic signals of multiple intersections

In this paper, a real-time stochastic optimal control method of traffic signal is modified. In addition, H-GA-PSO algorithm is proposed to search optimal traffic signals based on the stochastic model. The H-GA-PSO algorithm is a modified Hierarchical Particle Swarm Optimization (H-PSO) algorithm based on Genetic Algorithm (GA) processing. Finally, the effectiveness of the stochastic optimal control method with H-GA-PSO algorithm is shown through simulations at multiple intersections using a micro-traffic simulator.     

SVD‐Based Accurate Identification and Compensation of the Coupling Hysteresis and Creep Dynamics in Piezoelectric Actuators

In this paper, the coupling hysteresis and creep in piezoelectric actuators are identified and compensated for accurate tracking. First, we present the coupling hysteresis and creep model in smart actuators. Next, a complete identification strategy is designed according to the properties of the Preisach model. Then, an approach for parameter updating of the coupling model is provided. With the identified hysteresis and creep, the model‐based inversion compensation is designed. Finally, we apply the model identification and compensation to a piezoelectric stage to demonstrate the effectiveness of the proposed approaches. Significant reduction of the tracking error is achieved with the model‐based inversion feedforward compensator in which the relative errors at 10 Hz and 50 Hz are reduced to 1.85% and 4.53%, respectively. In addition, the model‐based feedforward is augmented with an integral feedback controller. With the composite controller, the relative errors at 10 Hz and 50 Hz are reduced to 0.42% and 3.04%, respectively.     

Humidity‐sensitive properties of new polyelectrolytes based on the copolymers containing phosphonium salt and phosphine function

A simple strategy was developed based on a new reactive function‐ and a salt‐containing new monomer, 4‐vinylbenzyl dimethyl 2‐(dimethylphosphino)ethyl phosphonium chloride (VDEPC), to obtain stable humidity‐sensitive membranes. The major ingredient of a humid membrane is crosslinked polyelectrolytes obtained from copolymers of VDEPC/2‐ethylhexyl acrylate (2‐EHA) = 1/0, 4/1, and 2/1. Isothermal humidity absorption experiments were performed for the estimation of humidity‐sensing materials. The crosslinked copolymers prepared from the reaction of VDEPC/2‐EHA = 4/1 with 1,4‐dichlorobutane showed an average impedance of 595, 39.1, and 3.9 KΩ at 30, 60, and 90% RH, respectively. Their hysteresis, temperature dependence, frequency dependence, and response time were measured. The reliability including water resistance and a long‐term stability were estimated for the application of the common humidity sensor. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 89: 1062–1070, 2003     

Formation control of mobile robots with obstacle avoidance based on GOACM using onboard sensors

This paper deals with the problem of formation control for nonholonomic mobile robots under a cluttered environment. When the obstacles are not detected, the follower robot calculates its waypoint to track, based on the leader robot’s state. The proposed geometric obstacle avoidance control method (GOACM) guarantees that the robot avoids the static and dynamic obstacles using onboard sensors. Due to the difficulty for the robot to simultaneously get overall safe boundary of an obstacle in practice, a safe line, which is perpendicular to the obstacle surface, is used instead of the safe boundary. Since GOACM is executed to find a safe waypoint for the robot, GOACM can effectively cooperate with the formation control method. Moreover, the adaptive controllers guarantee that the trajectory and velocity tracking errors converge to zero with the consideration of the parametric uncertainties of both kinematic and dynamic models. Simulation and experiment results present that the robots effectively form and maintain formation avoiding the obstacles.     

Illumination invariant object tracking with adaptive sparse representation

Since the introduction of the sparse representation-based tracking method named ?₁ tracker, there have been further studies into this tracking framework with promised results in challenging video sequences. However, in the situation of large illumination changes and shadow casting, the tracked object cannot be modeled efficiently by sparse representation templates. To overcome this problem, we propose a new illumination invariant tracker based on photometric normalization techniques and the sparse representation framework. With photometric normalization methods, we designed a new illumination invariant template presentation for tracking that eliminates the illumination influences, such as brightness variation and shadow casting. For a higher tracking accuracy, we introduced a strategy that adaptively selects the optimum template presentation at the update step of the tracking process. The experiments show that our approach outperforms the previous ?₁ and some state-of-the-art algorithms in tracking sequences with severe illumination effects.     

Scaled Jacobian transpose based control for robotic manipulators

This paper presents a scaled Jacobian transpose based control method for robotic manipulators as a modification of a conventional Jacobian transpose based method. The proposed method has several advantages such as it shows faster convergence and better tracking performance than the conventional method, furthermore, it does not have any singularity problem similar to the conventional method. The scaled Jacobian transpose is obtained by collecting each pseudoinverse of the column vector of the Jacobian matrix. The proposed method performs a given task well under singular configurations while minimizing the task error. Finally, a few comparative studies with the conventional method are provided to show the effectiveness of the proposed method through simulations.