Projection based method for segmentation of human face and its evaluation

We detect facial features and then circumscribe each facial feature with the smallest rectangle possible by using vertical and horizontal gray value projections of pixels. The result is evaluated with respect to the manually located enclosing rectangle on the images of a publicly available database.     

Passenger Flow Prediction Based on Newly Adopted Algorithms

Passenger flow forecasting is an essential part of transportation systems. Neural networks in the transportation field have been applied to passenger demand prediction. In this paper, we developed two hybrid methods, known as parlimentary optimization algorithm-artificial neural network (POA-ANN), and intelligent water drops algorithm-ANN (IWD algorithm-ANN). In addition, we applied the proposed algorithms to illustrate the effect of precise prediction for passenger queues. We mainly focus on predicting passenger demand by comparing the genetic algorithm-ANN (GA-ANN) with POA-ANN and IWD-ANN. The results of prediction methods suggest that both POA-ANN and IWD-ANN provide a better forecasting performance, which is obtained via mean square error (MSE), than GA-ANN in the field of passenger flow prediction. This study illustrates that the newly adopted algorithms exhibit good performance for passenger prediction.     

Scalar estimation and control with noisy binary observations

We consider a simple one-dimensional system whose observations are sent to a state estimator over a noisy binary communication link. The interesting thing about the system is that it is unstable. The problem is to design an encoding scheme and a decoder such that the estimation error is stable. We explicitly construct a simple but efficient estimator for the binary symmetric channel (BSC). We are not aware of any such previous "codes" for the BSC. We compare our results to the nonconstructive bounds of Sahai.     

Supplier selection with an integrated methodology in unknown environment

This paper proposes an integrated methodology and its solution for supplier selection problem. A two-stage stochastic programming model and fuzzy TOPSIS methods are consolidated in this methodology. After pre-research phase, in the second part of the methodology, fuzzy TOPSIS is used for ranking potential suppliers considering qualitative data under fuzzy environment. In the third part of the methodology a group of ranked potential suppliers are included in a two-stage stochastic programming model for evaluation. In the two-stage stochastic programming model demand is assumed as uncertain and different scenarios are generated for this parameter. With this methodology, supplier evaluation procedure can be done in unknown environment. Our methodology is interested with a problem in multi-product, multi-period and multi-sourcing environment.     

On the Distribution of Photon Counts with Censoring in Two-Photon Laser Scanning Microscopy

We address the problem of counting emitted photons in two-photon laser scanning microscopy. Following a laser pulse, photons are emitted after exponentially distributed waiting times. Modeling the counting process is of interest because photon detectors have a dead period after a photon is detected that leads to an underestimate of the count of emitted photons. We describe a model which has a Poisson \((\alpha )\) number N of photons emitted, and a dead period \(\Delta \) that is standardized by the fluorescence time constant \(\tau (\delta = \Delta /\tau )\), and an observed count D. The estimate of \(\alpha \) determines the intensity of a single pixel in an image. We first derive the distribution of D and study its properties. We then use it to estimate \(\alpha \) and \(\delta \) simultaneously by maximum likelihood. We show that our results improve the signal-to-noise ratio, hence the quality of actual images.     

A deep learning-based CEP rule extraction framework for IoT data

The Journal of Supercomputing - With the recent developments in Internet of Things (IoT), the number of sensors that generate raw data with high velocity, variety, and volume is tremendously...     

Neural network based modeling of a large steam turbine-generatorrotor body parameters from on-line disturbance data

A novel technique to estimate and model rotor-body parameters of a large steam turbine-generator from real time disturbance data is presented. For each set of disturbance data collected at different operating conditions, the rotor body parameters of the generator are estimated using an output error method (OEM). Artificial neural network (ANN) based estimators are later used to model the nonlinearities in the estimated parameters based on the generator operating conditions. The developed ANN models are then validated with measurements not used in the training procedure. The performance of estimated parameters is also validated with extensive simulations and compared against the manufacturer values     

Control structure selection of increased-pressure extractive distillation process for DMC-MeOH azeotropic mixture

Producing dimethyl carbonate (DMC) as a green chemical with the desired purity is important in the industry. Although studies on the steady-state design of energy-efficient extractive distillation processes are important for the purification of DMC-methanol (DMC-MeOH) azeotropic mixtures, the dynamic controllability of these processes is also critical in the case of feed condition changes, and it should be investigated carefully. Results of the limited studies in the literature show that changing the operating pressures in extractive distillation processes might have different effects on the dynamic controllability of different systems. Thus, in this study, alternative control strategies are developed for a recently proposed increased-pressure extractive distillation process to separate DMC-MeOH mixture. All control structures are designed using inferential temperature controllers, which have a general acceptance in industrial applications. Effects of different ratio controllers are investigated by evaluating the dynamic responses of control structures for disturbances in feed flowrate and composition. Two metrics including integral absolute error and steady-state deviation of purities are used in the evaluation of alternatives. Results of dynamic simulations show that a control structure including reflux ratio controller is not a suitable strategy for this process. It is demonstrated that a control structure including reflux to feed ratio controller for both distillation columns is necessary for the robust and efficient control of a pressure-increased extractive distillation process. These efficient dynamic results support the economic advantage of increased-pressure extractive distillation process separating DMC-MeOH azeotropic mixtures.