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.     

Intelligent healthcare service based on context inference using smart device

In the field of “U-Healthcare Service”, many studies have been actively conducted to develop “smart device”-based healthcare applications that enable healthcare providers and patients to be better served through interoperations among various kinds of sensors and wireless network interfaces. In particular, contemporary intelligent healthcare services not only recognize users’ context information through smart devices, computers, and so forth, but also acquire information from heterogeneous sensors to achieve context-aware inference services. Among such information, the weather information is tightly related to diseases such as asthma and allergies. Therefore, there is a high demand for research to utilize the weather information for healthcare services. In this paper, we propose a context inference-based intelligent healthcare service that exploits both the weather conditions information and the diverse healthcare ontologies available on the Internet. The proposed service aims at modeling a context ontology in users’ healthcare service environment and defining the inference rules, thereby accomplishing a satisfactory real-time healthcare service.     

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.     

Defect detection using feature point matching for non-repetitive patterned images

Defect detection is an important technology for the quality control in the production process of wafer, TFT-LCD and PCB. Inspection is performed using the finished product’s image. The images are classified into two different groups—images with a repetitive pattern on a regular cycle and images without a repetitive pattern. A standard object for comparison is required, because manual defect detection is not possible for areas without repetitive patterns. In such areas, defect detection occurs through contrasting a reference pattern to the pattern being inspected. Methods of inspection using reference image have been researched but have limitations due to their requirement of precise alignment of the images. This paper proposes a method of defect detection to overcome such limitation using feature point matching. Feature points are extracted using a corner detector and detects defect by finding a correspondence between two feature point sets. Performance of the proposed method is evaluated by using Wafer SEM images and compared with conventional methods. Experiment results demonstrate the proposed method achieves higher detection accuracy than conventional methods and is less sensitive to alignment error and noise.     

Atmospheric Dependence on Dielectric Loss of 1/6Ba5Nb4O15· 5/6BaNb2O6 Ceramics

Samples of 1/6Ba₅Nb₄O₁₅·5/6BaNb₂O₆ along with the pure end members, Ba₅Nb₄O₁₅ and BaNb₂O₆, were sintered under low oxygen partial pressure. The degradation mechanisms of dielectric loss in this reducing atmosphere have been studied. We found that the degradation occurred primarily due to the formation of oxygen vacancies caused by the reduction of Nb⁵⁺. This was determined by measuring the electrical conductivity, and through X-ray photoelectron spectroscopy. More importantly, the dielectric loss of 1/6Ba₅Nb₄O₁₅·5/6BaNb₂O₆ samples with higher temperature stability was further decreased on sintering in a reducing atmosphere. This observation has been explained by considering the increased porosity and formation of a reduced second phase, Ba_0.65NbO₃.     

Cure kinetics of epoxy formulations of the type used in advanced composites

An analysis of the cure kinetics of three different formulations composed of tetraglycidyl 4,4′-diaminodiphenyl methane (TGDDM) epoxy resin and diaminodiphenyl sulfone (DDS) was performed. A series of isothermal tests was run, and the experimentally obtained results were checked against the proposed kinetic model. An autocatalyzed mechanism with the overall reaction order of 2 was found to adequately describe the cure kinetics. An increase in reaction rate was observed at higher temperature and higher DDS concentration. For a given formulation, the extent of reaction corresponding to the maximum reaction rate was independent of temperature. A secondary exotherm was detected, particularly in formulations with low DDS concentration, at approximately 40% conversion. At that point, the rate of primary amine–epoxide reaction decreases, and other reactions dominate the curing process. Such a mechanism is likely to cause a formation of an inhomogeneous thermoset morphology.     

Latent catalyst effects in halogen‐free epoxy molding compounds for semiconductor encapsulation

Latent catalyst effects were investigated to improve the physical properties of halogen‐free epoxy molding compounds (EMCs) for semiconductor encapsulation. In this study, biphenyl‐type resins were used as the epoxy and hardener resin for halogen‐free EMCs to obtain high flame‐retardant properties and high filler contents. Latent catalyst effects were examined with two kinds of EMC compositions, halogen‐free EMCs and conventional EMC compositions. We used triphenylphosphine‐benzoquinone salt (TPP‐BQ) as a latent catalyst. Spiral flow and gel time were measured to investigate the change in moldability with the latent catalyst. We measured package fail, moisture absorption, and delamination for reliability evaluation and flexural strength, flexural modulus, and adhesion for mechanical properties to examine latent catalyst effects. An improvement in moldability, reliability, and the mechanical properties were observed in two types of halogen‐free EMCs with TPP‐BQ as a latent catalyst. These phenomena were seen in conventional EMCs, including o‐cresol novolac epoxy resin. The cure kinetics of these systems were investigated by differential scanning calorimetry with an isothermal approach to explain these phenomena. The results indicate that the improvement in moldability in halogen‐free EMCs with TPP‐BQ was due to the low conversion rate of this system, and the increase in mechanical properties was attributed to the high conversion of curing reaction. © 2005 Wiley Periodicals, Inc. J Appl Polym Sci 96: 2287–2299, 2005     

Binary blends of nylons with ethylene vinyl alcohol copolymers: Morphological,thermal, rheological,and mechanical behavior

Binary blends of ethylene vinyl alcohol copolymers, containing 62 (EVOH-62) and 71 (EVOH-71) mole percent vinyl alcohols, with nylons (nylon-6, nylon-6/12, and nylon-12) have been prepared from melt mixing in a twin screw compounding machine. Morphological, thermal, rheological, and mechanical properties were determined. EVOH-62/nylon-6 and EVOH-71/nylon-6 blends showed homogeneous phase morphologies in the nylon-6-rich region, and fine phase separations (c.a. 2 × 10^?7 m) in the EVOH-rich region. Melting point depression, positive deviations in viscosity and flexural modulus, and negative deviation in impact strength from the simple additive rule were generally observed. And the results were possibly interpreted in terms of compatibility and increased nylon/EVOH interactions over the nylon/nylon interactions. On the contrary, clean phase separations in large domains were observed from EVOH-71/nylon-6/12 and EVOH-71 /nylon-12 blends. Fibrillation was also obtained from EVOH rich blends. Probably due to the incompatible nature of these blends, yield at low rate of shear and a mechanical property drop were also observed.     

Strain-Induced Deformation in Magnesia–Alumina Layered Composites

Ceramic beams are induced in situ to form complex shapes at elevated temperature without the application of an external stress. This process has been demonstrated for thin alumina substrates coated with a layer of magnesia. The internal strain causing the substrates to deform at elevated temperature arises as a consequence of strain mismatch accompanying the penetration of the coating into the substrate. The magnitude of the deformation depends on the amount of coating applied, on the thickness of the substrate, on the density of the substrate, and on the temperature. During exposure of the beams to elevated temperature, the magnesia coating reacts with the alumina substrate to form the spinel phase; the resulting volume change accompanying the phase transformation is likely the predominant driving force for deformation.     

Transport of oxygen and carbon dioxide through polycarbonate membrane

Sorption equilibria and permeation rates for oxygen and carbon dioxide in polycarbonate membrane were measured at different temperature between 30 and 60°C and at pressures up to 2.5 MPa. The pressure dependence of mean permeability coefficient to oxygen obeyed the conventional dual-mode mobility model, whereas that to carbon dioxide followed a modified dual-mode mobility model with concentration-dependent diffusivities, as that of polystyrene to the same gas did.