Robust pose invariant face recognition using coupled latent space discriminant analysis

We propose a novel pose-invariant face recognition approach which we call Discriminant Multiple Coupled Latent Subspace framework. It finds the sets of projection directions for different poses such that the projected images of the same subject in different poses are maximally correlated in the latent space. Discriminant analysis with artificially simulated pose errors in the latent space makes it robust to small pose errors caused due to a subject’s incorrect pose estimation. We do a comparative analysis of three popular latent space learning approaches: Partial Least Squares (PLSs), Bilinear Model (BLM) and Canonical Correlational Analysis (CCA) in the proposed coupled latent subspace framework. We experimentally demonstrate that using more than two poses simultaneously with CCA results in better performance. We report state-of-the-art results for pose-invariant face recognition on CMU PIE and FERET and comparable results on MultiPIE when using only four fiducial points for alignment and intensity features.     

Abrasion Resistance of Field-Assisted Ion-Exchanged Glass

The fracture strength of HF-etched samples was measured as a function of field-assisted K-Na ion exchange depth, as well as the severity of abrasion. As expected, the more severe the abrasion, the greater the depth required to make the strength insensitive to abrasion. An abrasion-independent weakening mechanism that increased with exchange depth was also found to be operative.     

MODELING AND PREDICTIVE CONTROL OF MIMO NONLINEAR SYSTEMS USING WIENER-LAGUERRE MODELS

In this work, a Weiner-type nonlinear black box model was developed for capturing dynamics of open loop stable MIMO nonlinear systems with deterministic inputs. The linear dynamic component of the model was parameterized using orthogonal Laguerre filters while the nonlinear state output map was constructed either using quadratic polynomial functions or artificial neural networks. The properties of the resulting model, such as open loop stability and steady-state behavior, are discussed in detail. The identified Weiner-Laguerre model was further used to formulate a nonlinear model predictive control (NMPC) scheme. The efficacy of the proposed modeling and control scheme was demonstrated using two benchmark control problems: (a) a simulation study involving control of a continuously operated fermenter at its optimum (singular) operating point and (b) experimental verification involving control of pH at the critical point of a neutralization process. It was observed that the proposed Weiner-Laguerre model is able to capture both the dynamic and steady-state characteristics of the continuous fermenter as well as the neutralization process reasonably accurately over wide operating ranges. The proposed NMPC scheme achieved a smooth transition from a suboptimal operating point to the optimum (singular) operating point of the fermenter without causing large variation in manipulated inputs. The proposed NMPC scheme was also found to be robust in the face of moderate perturbation in the unmeasured disturbances. In the case of experimental verification using the neutralization process, the proposed control scheme was found to achieve much faster transition to a set point close to the critical point when compared to a conventional gain-scheduled PID controller.     

INFLUENCE OF DESIGN AND OPERATING CONDITIONS ON THE SYSTEM PERFORMANCE OF A TWO-STAGE ADSORPTION CHILLER

This article aims at clarifying the possible design and operating conditions for silica gel-water adsorption refrigeration cycles driven by near-ambient temperature waste heat sources (between 45 and 75°C) with relatively small regenerating temperature lifts (15 to 45 K). A two-stage silica gel-water advanced adsorption chiller is introduced and a simulation model of the chiller was developed to analyze the influence of operating and design conditions on the system performance (coefficient of performance, COP, and cooling capacity). It was hypothesized that the proposed chiller can be driven by low temperature waste heat at 55°C to produce effective cooling. Simulation results show that the operating conditions such as cycle time and hot and cooling water inlet temperature have an influential effect on cooling capacity and COP. COP is proportional to cycle time and heat transfer coefficient as well as inversely proportional to the cooling water inlet temperature, while there are optimum values of hot water temperature and silica gel weight for maximum COP. Cooling capacity mainly improves with the addition of silica gel weight and decreases as cooling water temperature increases. Simulation results also revealed that the system performance can be improved significantly by setting the design and operating conditions optimally.     

Absorption of carbon dioxide in alkanolamines in the presence of fine activated carbon particles

The rates of absorption of CO₂ into water and 0.1 kmol/m³ aqueous solutions of MEA, DEA and AMP were measured in a stirred cell with a flat gas-liquid interface in the presence of fine activated carbon particles. Experiments showed that the rates of absorption increased significantly with increases in the loading of activated carbon up to about 6 kg/m³ and thereafter remained constant.     

The C-loss function for pattern classification

This paper presents a new loss function for neural network classification, inspired by the recently proposed similarity measure called Correntropy. We show that this function essentially behaves like the conventional square loss for samples that are well within the decision boundary and have small errors, and L₀ or counting norm for samples that are outliers or are difficult to classify. Depending on the value of the kernel size parameter, the proposed loss function moves smoothly from convex to non-convex and becomes a close approximation to the misclassification loss (ideal 0–1 loss). We show that the discriminant function obtained by optimizing the proposed loss function in the neighborhood of the ideal 0–1 loss function to train a neural network is immune to overfitting, more robust to outliers, and has consistent and better generalization performance as compared to other commonly used loss functions, even after prolonged training. The results also show that it is a close competitor to the SVM. Since the proposed method is compatible with simple gradient based online learning, it is a practical way of improving the performance of neural network classifiers.     

Harmony search algorithm for infinite impulse response system identification

In this paper, optimal sets of filter coefficients are searched by a meta-heuristic optimization technique called Harmony Search (HS) algorithm for infinite impulse response (IIR) system identification problem. For different optimization problems, HS algorithm undergoes three basic rules; namely Random Selection (RS), Harmony Memory Consideration (HMC), and Pitch Adjustment (PA) rules, which are inspired from the process that the musicians use to improvise a perfect state of harmony with the consummate skill of blending notes in tune. With the help of the properly selected control parameters, a perfect balance is achieved in exploration and exploitation in searching phases. The detailed analysis of simulation results emphasizes the strength of HS algorithm to find the near-global optimal solution, quality of convergence profile and the speed of convergence while tested against standard benchmark examples for same and reduced order models.     

Influence of Distributed Particle Size on the Determination of the Parabolic Rate Constant for Oxidation by the Powder Method

The established analysis for the study of oxidation using powder specimens is based on the assumption of monosized particles. The experiments, however, are conducted on powders with a distributed particle size. Here we present a statistical approach for the calculation of the rate constant for oxidation. The results of the analysis are applied to new data on oxidation studies of dense powders of silicon carbonitride amorphous ceramics. The monosized model requires a wide range of values for the rate constant to fit the short term and the long-term data, leading to considerable ambiguity in the estimate of the parabolic rate constant, k _p, for oxidation. In contrast the statistical model fits over the entire range of data, yielding a much more reliable value for k _p. For example, the monosized approach gave a value in the range 19.7 × 10⁻¹⁸ < k _p < 2.7 × 10⁻¹⁸ m²/s. In contrast, the statistical model yields a specific value of 4.5 × 10⁻¹⁸ m²/s.     

A method for automatic classification of gender based on text- independent handwriting

Handwriting recognition is used for the prediction of various demographic traits such as age, gender, nationality, etc. Out of all the applications gender prediction is mainly admired topic among researchers. The relation between gender and handwriting can be seen from the physical appearance of the handwriting. This research work predicts gender from handwriting using the landmarks of differences between the two genders. We use the shape or visual appearance of the handwriting for extracting features of the handwriting such as slanteness (direction), area (no of pixels occupied by text), perimeter (length of edges), etc. Classification is carried out using the Support Vector Machine (SVM) as a classifier which transforms the nonlinear problem into linear using its kernel trick, logistic regression, KNN and at the end to enhance the classification rates we use Majority Voting. The experimental results obtained on a dataset of 282 writers with 2 samples per writer shows that the proposed method attains appealing performance on writer detection and text-independent environment.

     

Estimation of impact forces during multi-point collisions involving small deformations

Multibody System Dynamics - Collision between hard objects causes abrupt changes in the velocities of the system, which are characterized by very large contact forces over very small time...