An expert egg grading system based on machine vision and artificial intelligence techniques

The main purpose of this research was design and development of an intelligent system based on combined fuzzy logic and machine vision techniques for grading of egg using parameters such as defects and size of eggs. The detected defects were internal blood spots, cracks and breakages of eggshell. The Hue-Saturation-Value (HSV) color space was found useful in obtaining visual features during Image Processing (IP) stage. The fuzzy inference system (FIS) was designed based on triangular and trapezoidal membership functions, fuzzy rules with logical operator of AND inference system of Mamdani and method of center average for defuzzifier. The evaluation results of IP algorithms showed that use of IP technique has good performance for defects and size detection. The Correct Classification rate (CCR) was 95% for size detection, 94.5% for crack detection and 98% for breakage detection. The overall accuracy FIS model in grading of the eggs was 95.4.     

LIQUID-LIQUID MIXING IN STIRRED VESSELS: A REVIEW

Liquid-liquid mixing is a key process in industries that is commonly accomplished in mechanical agitation systems. Liquid-liquid mixing performance in a stirred tank can be evaluated by various parameters, namely minimum agitation speed, mixing time, circulation time, power consumption, drop size distribution, breakup and coalescence, interfacial area, and phase inversion. The importance of these liquid-liquid mixing parameters, the measurement method, and the results are discussed briefly. Input parameters such as impeller type, power number, flow pattern, number of impellers, and dispersed phase volume fraction, in addition to physical properties of phases such as viscosity and density, are reviewed. Scale-up aspects are also included.     

A robust algorithm for a class of optimal control problems subject to regional stability constraints and disturbances

A robust globally convergent algorithm for solving the optimization control problem (OCP) in both state feedback controller and observation control system is investigated. Finding the OCP adjoint parameter for computing the optimal observer gain and feedback gain vectors are desired. First, the optimal control problem considering stability of degree constrains and disturbance that affects the dynamics of system is converted into a two-point boundary value problem (TPBVP). Then, we apply the He’s polynomials based on homotopy perturbation method (HPM) as an efficient method to find both optimal gains. The algorithm will be modified do decrease the number of iterations required to attain a desired control problem cost function. As a result lower computational complexity is required when compared with other state of the art methods. Applying the HPM makes the solution procedure become easier, simpler and more straightforward. In the proposed method the control problem can be solved with lower amplitudes of the input signal (control effort), comparing with analytical method. Lower control efforts may also help to avoid saturation effects, and to restrain the system to work within linear operating areas of the state space. On the other hand, there is a tradeoff between control effort and the degree of optimality obtained. For demonstrating the simplicity and efficiency of the proposed optimal control method, the algorithm is compared with a control architecture using the Kalman filter estimator and a controller gain designed by the Lyapunov’s second method.     

Automatic segmentation of digitized data for reverse engineering applications

Reverse engineering is the process of developing a Computer Aided Design (CAD)model and a manufacturing database for an existing part. This process is used in CAD modeling of part prototypes, in designing molds, and in automated inspection of parts with complex surfaces. The work reported in this paper is on the automatic segmentation of 3-Dimensional (3-D) digitized data captured by a laser scanner or a Coordinate Measuring Machine (CMM) for reverse engineering applications. Automatic surface segmentation of digitized data is achieved using a combination of region and edge based approaches. It is assumed that the part surface contains planar as well as curved surfaces that are embedded in a base surface. The part surface should be visible to a single scanning probe (21/2D object). Neural network algorithms are developed for surface segmentation and edge detection. A back propagation network is used to segment part surfaces into surface primitives which are homogenous in their intrinsic differential geometric properties. The method is based on the computation of Gaussian and mean curvatures of the surface. They are obtained by locally approximating the object surface using quadratic polynomials. The Gaussian and mean curvatures are used as input to the neural network which outputs an initial region-based segmentation in the form of a curvature sign map. An edge based segmentation is also performed using the partial derivatives of depth values. Here, the output of the Laplacian operator and the unit surface normal are computed and used as input to a Self-Organized Mapping (SOM) network. This network is used to find the edge points on the digitized data. The combination of the region based and the edge based approaches, segment the data into primitive surface regions. The uniqueness of our approach is in automatic calculation of the threshold level for segmentation, and on the adaptability of the method to various noise levels in the digitized data. The developed algorithms and sample results are described in the paper     

A modified particle swarm optimization for disaster relief logistics under uncertain environment

Relief logistics is one of the most important elements of a relief operation. This paper investigates a relief chain design problem where not only demands but also supplies and the cost of procurement and transportation are considered as the uncertain parameters. Furthermore, the model considers uncertainty for the locations where those demands can arise and the possibility that a number of the facility could be partially destroyed by the disaster. The proposed model for this study is formulated as a mixed-integer nonlinear programming to minimize the sum of the expected total cost (which includes costs of location, procurement, transportation, holding, and shortage) and the variance of the total cost. The model simultaneously determines the location of relief distribution centers and the allocation of affected area to relief distribution centers. Furthermore, an efficient solution approach based on particle swarm optimization is developed in order to solve the proposed mathematical model. At last, computational results for several instances of the problem are presented to demonstrate the feasibility and effectiveness of the proposed model and algorithm.     

Irreducible compositions of polynomials over finite fields of even characteristic

This paper presents some results with the constructive theory of synthesis of irreducible polynomials over a Galois field with even characteristic. We prove a theorem that plays an important role for constructing irreducible polynomials. By this theorem two recurrent methods for constructing families of irreducible polynomials of degree $n2^{k}~(k=1,2,\ldots )$ over $\mathbb F _{2^{s}}$ are proposed. It is shown that in this special case, the sequences of irreducible polynomials are N-polynomial of degree $2^{k}$ .     

Improvement in volume resistivity and morphology of a blend of polyolefin elastomer with linear low-density polyethylene

A silane moisture-cured polyolefin elastomer/linear low-density polyethylene (LLDPE) blend was prepared through a two-step silane-grafting method (Sioplas Process) in an industrial scale twin-screw extruder. The silane-grafted compound was used to make wire and cable coatings. In this work, the effect of some interactive parameters on quality of the products prepared by the above method has been studied, while so far, there have been less experimental investigations. The volume resistivity of cross-linked compound was changed from 2.96 × 10¹⁴ to 7.41 × 10¹⁴ Ω cm with increasing LLDPE component by maximum 10 wt%. Surface morphology of the product was corrected with reduction in benzoyl peroxide (BPO) concentration from 0.2 wt% to 0.13 wt%. BPO at this level acted as an initiator in grafting reaction of vinyl trimethoxysilane. The curing condition and specimen preparation method by injection molding and/or extrusion were factors which influenced the hot-set test results at 200 °C. The results of tensile and elongation studies showed a maximum value of 9 MPa and 397% for the tests, after 6 h curing. With increases in curing time at a specified temperature, the gel content of the cross-linked compound was increased and reached its maximum value. The maximum gel content values were found to be approximately 60%, 80%, and 82% at temperatures of 25, 60, and 85 °C, respectively. The hardness, density, and tear strength of the samples did not vary significantly with the curing temperature.

     

Synthesis of Cellulose-graft-Polychloromethylstyrene-graft-Polyacrylonitrile Terpolymer/Organoclay Bionanocomposite by Metal Catalyzed Living Radical Polymerization and Solvent Blending Method

A bionanocomposite of grafted cellulose and organo-modified clay was synthesized through solution intercalation method. For this purpose, chloromethylstyrene was grafted onto cellulose using acryloylchloride and the subsequent free radical polymerization. The synthesized cellulose-graft-polychloromethylstyrene was used as an atom transfer radical polymerization macroinitiator of acrylonitrile in the presence of CuCl/2,2′-bipyridine catalyst system, to prepare the cellulose-graft-polychloromethylstyrene-graft-polyacrylonitrile terpolymer. For preparing the modified clay, Na-montmorillonite was mixed with hexadecyl trimethyl ammonium chloride salt. Finally, cellulose-graft-polychloromethylstyrene-graft-polyacrylonitrile/organoclay bionanocomposite was prepared in CCl₄ by solution intercalation method.     

Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI: a comparison between conventional and fused models

Magnetic Resonance Materials in Physics, Biology and Medicine - Multiparametric MRI (mp-MRI) has been significantly used for detection, localization and staging of Prostate cancer (PCa). However,...     

Using AR,MA, and ARMA Time Series Models to Improve the Performance of MARS and KNN Approaches in Monthly Precipitation Modeling under Limited Climatic Data

Precipitation is one of the most important components of the hydrologic cycle as it is required for multi-objective applications including flood estimation, drought monitoring, watersheds management, hydrology, agriculture, etc. Therefore, its estimation and modeling via a suitable method is a challenging task for hydrologists. The present study seeks to model monthly precipitation at two stations located in Iran. Two artificial intelligence (AI)-based models consisting of multivariate adaptive regression splines (MARS) and k-nearest neighbors (KNN) were used as the modeling techniques. In doing so, nine single-input scenarios under limited climatic data are implemented using minimum, maximum, and mean air temperatures, dew point temperature, station pressure, vapor pressure, relative humidity, wind speed, and antecedent precipitation data. The attained results illustrate that the performance of single MARS and KNN is relatively poor when modeling the monthly precipitation. Additionally, this study develops hybrid models to enhance the precipitation modeling through combining the MARS and KNN models with three diverse types of the time series (TS) models, namely autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA). The most important justification for integrating the models applied is that the AI and TS-based models are respectively capable of modeling the non-linear and linear terms of the hydrological variables such as precipitation. It is therefore necessary to be considered both of the aforementioned terms in the modeling procedure. A performance comparison of the single and hybrid models denotes the higher accuracy of hybrid models than the single ones. However, the hybrid models generated by combining the KNN and the TS models used are the best-performing models.