Human facial expression recognition using curvelet feature extraction and normalized mutual information feature selection

To recognize expressions accurately, facial expression systems require robust feature extraction and feature selection methods. In this paper, a normalized mutual information based feature selection technique is proposed for FER systems. The technique is derived from an existing method, that is, the max-relevance and min-redundancy (mRMR) method. We, however, propose to normalize the mutual information used in this method so that the domination of the relevance or of the redundancy can be eliminated. For feature extraction, curvelet transform is used. After the feature extraction and selection the feature space is reduced by employing linear discriminant analysis (LDA). Finally, hidden Markov model (HMM) is used to recognize the expressions. The proposed FER system (CNF-FER) is validated using four publicly available standard datasets. For each dataset, 10-fold cross validation scheme is utilized. CNF-FER outperformed the existing well-known statistical and state-of-the-art methods by achieving a weighted average recognition rate of 99 % across all the datasets.     

Frequency identification of Hammerstein-Wiener systems with backlash input nonlinearity

International Journal of Control, Automation and Systems - The problem of system identification is addressed for Hammerstein-Wiener systems that involve memory operator of backlash type bordered by...     

Porous dye affinity beads for nickel adsorption from aqueous solutions: A kinetic study

We investigated a new adsorbent system, Reactive Red 120 attached poly(2‐hydroxyethyl methacrylate ethylene dimethacrylate) [poly(HEMA–EDMA)] beads, for the removal of Ni²⁺ ions from aqueous solutions. Poly(HEMA–EDMA) beads were prepared by the modified suspension copolymerization of 2‐hydroxyethyl methacrylate and ethylene dimethacrylate. Reactive Red 120 molecules were covalently attached to the beads. The beads (150–250 μm), having a swelling ratio of 55% and carrying 25.5 μmol of Reactive Red 120/g of polymer, were used in the removal of Ni²⁺ ions. The adsorption rate and capacity of the Reactive Red 120 attached poly(HEMA–EDMA) beads for Ni²⁺ ions was investigated in aqueous media containing different amounts of Ni²⁺ ions (5–35 mg/L) and having different pH values (2.0–7.0). Very high adsorption rates were observed at the beginning, and adsorption equilibria were then gradually achieved in about 60 min. The maximum adsorption of Ni²⁺ ions onto the Reactive Red 120 attached poly(HEMA–EDMA) beads was 2.83 mg/g at pH 6.0. The nonspecific adsorption of Ni²⁺ ions onto poly(HEMA–EDMA) beads was negligible (0.1 mg/g). The desorption of Ni²⁺ ions was studied with 0.1M HNO₃. High desorption ratios (>90%) were achieved. The intraparticle diffusion rate constants at various temperatures were calculated as k_20°C = 0.565 mg/g min^0.5, k_30°C = 0.560 mg/g min^0.5, and k_40°C = 0.385 mg/g min^0.5. Adsorption–desorption cycles showed the feasibility of repeated use of this novel adsorbent system. The equilibrium data fitted very well both Langmuir and Freundlich adsorption models. The pseudo‐first‐order kinetic model was used to describe the kinetic data. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 100:5056–5065, 2006     

Synthesis and characterization of poly(ethylene glycol dimethacrylate–1‐vinyl‐1,2,4‐triazole) copolymer beads for heavy‐metal removal

We prepared poly(ethylene glycol dimethacrylate–1‐vinyl‐1,2,4‐triazole) [poly(EGDMA–VTAZ)] beads (average diameter = 150–200 μm) by copolymerizing ethylene glycol dimethacrylate (EGDMA) with 1‐vinyl‐1,2,4‐triazole (VTAZ). The copolymer composition was characterized by elemental analysis and found to contain five EGDMA monomer units for each VTAZ monomer unit. The poly(EGDMA–VTAZ) beads had a specific surface area of 65.8 m²/g. Poly(EGDMA–VTAZ) beads were characterized by Fourier transform infrared spectroscopy, elemental analysis, surface area measurements, swelling studies, and scanning electron microscopy. Poly(EGDMA–VTAZ) beads with a swelling ratio of 84% were used for the heavy‐metal removal studies. The adsorption capacities of the beads for Cd(II), Hg(II), and Pb(II) were investigated in aqueous media containing different amounts of these ions (5–750 mg/L) and at different pH values (3.0–7.0). The maximum adsorption capacities of the poly(EGDMA–VTAZ) beads were 85.7 mg/g (0.76 mmol/g) for Cd(II), 134.9 mg/g (0.65 mmol/g) for Pb(II), and 186.5 mg/g (0.93 mmol/g) for Hg(II). The affinity order toward triazole groups on a molar basis was observed as follows: Hg(II) > Cd(II) > Pb(II). pH significantly affected the adsorption capacity of the VTAZ‐incorporated beads. The equilibrium data were well fitted to the Redlich–Peterson isotherm. Consideration of the kinetic data suggested that chemisorption processes could have been the rate‐limiting step in the adsorption process. Regeneration of the chelating‐beads was easily performed with 0.1M HNO₃. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 102: 4276–4283, 2006     

New Cloud Consolidation Architecture for Electrical Energy Consumption Management

Cloud computing is taking more extensive space in the research field. Cloud architectures will need to worry about energy in its various forms, to be profitable, on the one hand, and comply with environmental constraints （energy consumption and CO2 emission） on the other hand. VM （virtual machines） consolidation （VMs in this document）, among other techniques, must take into account the consumption of electrical energy, for example, while providing a level of performance that meets the requirements of SLAs （service level agreements）. In our work, we focus on an architecture configuration to manage virtual machines in a data center, in order to optimize the consumption of energy, and meet SLAs＇s constraints at the same time, by grafting a tracing component of the multiple consolidation plans that leads to an optimal configuration to finally give the order of the migration machinery to a minimum number of servers switched on, knowing that VMs （virtual machines） that coexist in the same server, are at risk of congestion and interference.     

Fast modified global k-means algorithm for incremental cluster construction

The k-means algorithm and its variations are known to be fast clustering algorithms. However, they are sensitive to the choice of starting points and are inefficient for solving clustering problems in large datasets. Recently, incremental approaches have been developed to resolve difficulties with the choice of starting points. The global k-means and the modified global k-means algorithms are based on such an approach. They iteratively add one cluster center at a time. Numerical experiments show that these algorithms considerably improve the k-means algorithm. However, they require storing the whole affinity matrix or computing this matrix at each iteration. This makes both algorithms time consuming and memory demanding for clustering even moderately large datasets. In this paper, a new version of the modified global k-means algorithm is proposed. We introduce an auxiliary cluster function to generate a set of starting points lying in different parts of the dataset. We exploit information gathered in previous iterations of the incremental algorithm to eliminate the need of computing or storing the whole affinity matrix and thereby to reduce computational effort and memory usage. Results of numerical experiments on six standard datasets demonstrate that the new algorithm is more efficient than the global and the modified global k-means algorithms.     

Fuzzy DIFACONN-miner: A novel approach for fuzzy rule extraction from neural networks

Artificial neural networks (ANNs) are mathematical models inspired from the biological nervous system. They have the ability of predicting, learning from experiences and generalizing from previous examples. An important drawback of ANNs is their very limited explanation capability, mainly due to the fact that knowledge embedded within ANNs is distributed over the activations and the connection weights. Therefore, one of the main challenges in the recent decades is to extract classification rules from ANNs. This paper presents a novel approach to extract fuzzy classification rules (FCR) from ANNs because of the fact that fuzzy rules are more interpretable and cope better with pervasive uncertainty and vagueness with respect to crisp rules. A soft computing based algorithm is developed to generate fuzzy rules based on a data mining tool (DIFACONN-miner), which was recently developed by the authors. Fuzzy DIFACONN-miner algorithm can extract fuzzy classification rules from datasets containing both categorical and continuous attributes. Experimental research on the benchmark datasets and comparisons with other fuzzy rule based classification (FRBC) algorithms has shown that the proposed algorithm yields high classification accuracies and comprehensible rule sets.     

Machine loading in flexible manufacturing systems considering routeing flexibility

The key competitive strength of a manufacturing system lies in its flexibility, which represents the ability to respond effectively to changing circumstances. Flexible manufacturing systems (FMSs) react appropriately to change. The relevance of a particular type of flexibility depends upon the system and problem being considered. In this paper, the machine loading problem in a flexible manufacturing system is addressed. The loading problem is concerned with the allocation of part operations and required tools to the machines, so as to optimise some objective(s) subject to some technological constraints. Several objectives have been considered in the past such as maximisation of the utilisation of resources, minimisation of processing and tooling costs and maximisation of throughput rates. In such procedures, it is quite probable that a rigid loading schedule is obtained and in cases of machine breakdowns and tool failures alternate routeings are often not available. Therefore, in this paper, we develop a mathematical model which considers maximisation of the production routeings available for the parts and hence increases the routeing flexibility. The model is illustrated by examples.     

Recent developments in the organization goals conformance using ontology

Organizational goals serve as the most important achievement target in every organization. Even though some researchers have developed the concept of the organization goals, but structuring the organization goals model is always questionable by the way it is being used. In this paper, we propose ontology to develop a unified model for the organization goals structure. We review the recent literature on the organization modelling and ontology development as an effort to evaluate the organization goals using a metrics for the achievement of the organization goals. We suggest that the metrics is important to identify the relevant organization data in relation to the organization goals conformance. In order to achieve this purpose, we investigate various associated concepts and organize the literature based on the organization goals, organization ontology and metrics model. We observe our proposed models are important for domain experts and entrepreneurs to evaluate the relevant organization data and to assist them in decision making. In summary, the contribution of this survey may serve as a first step in understanding the evaluation of the organization data for the achievement of the organization goals.     

High-level and long-term noise effect on soft rock building materials

Bulletin of Engineering Geology and the Environment - In recent years, due to an increase in the number of tourists and music concerts in historical areas and a rise in the noise level caused by...