Automatic diagnosis of neuro-degenerative diseases using gait dynamics

Here an approach for the diagnosis of neuro-degenerative diseases based on gait dynamics is proposed. The proposed method uses information from a time series of stride intervals, swing intervals, stance intervals and double support intervals of stride-to-stride measures of footfall contact times using force-sensitive resistors. Different features were extracted from these time series and the best of them were selected for the diagnosis. The support vector machines using different kernels were examined for the diagnosis. The radial basis function kernel obtained the best performance for this aim. The results show that features derived from double support intervals are common effective features for the diagnosis of neuro-degenerative diseases using the gait dynamics.     

Material and velocity effects on cavitation erosion pitting

Cavitation erosion during the incubation period was investigated via pitting tests conducted on three different materials: an Aluminum alloy, a Nickel Aluminum Bronze alloy and a Duplex Stainless Steel. Pitting tests were conducted in a cavitation tunnel in the velocity range 45–90 m/s at a constant cavitation number. The test section was made of a straight nozzle 16 mm in diameter discharged into the radial 2.5 mm space between two flat walls. Cavitation appears in the form of a toroidal cavity attached to the nozzle exit and damage on the samples facing the nozzle is concentrated in a circular ring centered in the cavity closure region. The exposure time was adjusted to avoid pit overlapping. The material surface was examined using a conventional contact profilometer which allowed us to identify the pits, count them, and measure their main characteristics such as depth, surface area, and volume. From these the pitting rate, the coverage rate, and the depth of deformation rate were defined. Pits were classified according to their diameter. For all materials and operating conditions, pitting rate appears to follow an exponential law in relation to the pit diameter. This law depends upon two parameters only, which were identified as the coverage time τ (i.e. the time required for the surface to be covered by erosion pits) and a characteristic pit diameter δ, which corresponds to the pits whose contribution to the coverage process is the highest. Scaling laws for pitting were derived accounting for both material properties and flow velocity, and a procedure to make pitting test results non-dimensional is proposed. The influence of the material on pitting test results was analyzed. It is shown that the damage is not correlated in simple terms with the elastic limit determined from conventional tensile tests and it is conjectured that other parameters such as the strain rate might play a significant role and should be included in the analysis. The effect of flow velocity on both parameters τ and δ was analyzed and a classical power law was found for the influence of the flow velocity on pitting rate for all three materials. Finally, some analysis and discussion is given concerning distributions of pit volume and pit depth.     

Scaling study of cavitation pitting from cavitating jets and ultrasonic horns

Cavitation erosion prediction and characterization of cavitation field strength are of interest to industries suffering from cavitation erosion detrimental effects. One means to evaluate cavitation fields and materials is to examine pitting rates during the incubation period, where the test sample undergoes localized permanent deformations shaped as individual pits. In this study, samples from three metallic materials, an Aluminum alloy (Al 7075), a Nickel Aluminum Bronze (NAB) and a Duplex Stainless Steel (SS A2205) were subjected to a vast range of cavitation intensities generated by cavitating jets at different driving pressures and by an ultrasonic horn. The resulting pitted sample surfaces were examined and characterized with a non-contact 3D optical scanner and the resulting damage computer-analyzed. A statistical analysis of the pit population and its characteristics was then carried out. It was found that the various cavitation field strengths can be correlated to the measured pit distributions and that two characteristic quantities: a characteristic number of pits per unit surface area and unit time, and a characteristic pit diameter or a characteristic pit depth can be attributed to a given “cavitation intensity level”. This characterization concept can be used in the future to study the cavitation intensity of the full scale and to develop methods of full scale predictions based on model scale erosion data.     

Solving a multi-objective job shop scheduling problem with sequence-dependent setup times by a Pareto archive PSO combined with genetic operators and VNS

In this paper, we present a combination of particle swarm optimization (PSO) and genetic operators for a multi-objective job shop scheduling problem that minimizes the mean weighted completion time and the sum of the weighted tardiness/earliness costs, simultaneously. At first, we propose a new integer linear programming for the given problem. Then, we redefine and modify PSO by introducing genetic operators, such as crossover and mutation operators, to update particles and improve particles by variable neighborhood search. Furthermore, we consider sequence-dependent setup times. We then design a Pareto archive PSO, where the global best position selection is combined with the crowding measure-based archive updating method. To prove the efficiency of our proposed PSO, a number of test problems are solved. Its reliability based on some comparison metrics is compared with a prominent multi-objective genetic algorithm (MOGA), namely non-dominated sorting genetic algorithm II (NSGA-II). The computational results show that the proposed PSO outperforms the above MOGA, especially for large-sized problems.     

Constructing a block layout by face area

Solving the facility layout problems by graph theory consists of two stages. In the first stage, a planar graph that specifies desired adjacencies is obtained and in the second stage, a block layout is achieved from the planar graph. In this paper, we introduce face area as a new concept for constructing a block layout. Based on this idea, we present a new algorithm for constructing block layout from a maximal planar graph (MPG). This MPG must be generated from deltahedron heuristic. Constructed block layout by this algorithm satisfies all of adjacency and area requirements.     

A novel two-stage genetic algorithm for a mixed-model U-line balancing problem with duplicated tasks

A widespread supposition on mixed-model assembly line-balancing problems assigns a task, which is shared between two or more models to a single station. Bukchin and Rabinowitch (European Journal of Operational Research, 174:492–508, 2006) relaxed the restriction for mixed-model straight-line assembly line problems and allowed tasks common to multiple models to be assigned to different stations, called task duplication. In this paper, considering the same relaxation but for mixed-model U-shaped assembly lines, a novel genetic algorithm (GA) approach for solving large-scale problems is developed. Although superiorities of U-shaped assembly lines over straight lines have been discussed in several articles, this paper makes the advantage more tangible by providing a quantitative example. This paper also presents a novel two-stage genetic algorithm which is fittingly devised for solving the new proposed model. In order to evaluate the effectiveness of the GA, one small-scale and one medium-scale problem are solved using both the proposed GA and Lingo 8.0 software, and the obtained outcomes are compared. The computational results indicate that the GA is capable of providing high-quality solutions for small- and medium-scale problems in negligible central processing unit (CPU) times. It is worth mentioning that, for large-scale problems, such as Kim and Arcus test problems, no analogous results for those obtained by our proposed GA exist. To conclude, it can be said that the proposed GA performs well and is able to solve large-scale problems within acceptable CPU times.     

Predicting the spontaneous termination of atrial fibrillation based on poincare section in the electrocardiogram phase space

Atrial fibrillation (AF) is a commonly encountered cardiac arrhythmia. Predicting the conditions under which AF terminates spontaneously is an important task that would bring great benefit to both patients and clinicians. In this study, a new method was proposed to predict spontaneous AF termination by employing the points of section (POS) coordinates along a Poincare section in the electrocardiogram (ECG) phase space. The AF Termination Database provided by PhysioNet for the Computers in Cardiology Challenge 2004 was applied in the present study. It includes one training dataset and two testing datasets, A and B. The present investigation was initiated by producing a two-dimensional reconstructed phase space (RPS) of the ECG. Then, a Poincare line was drawn in a direction that included the maximum point distribution in the RPS and also passed through the origin of the RPS coordinate system. Afterward, the coordinates of the RPS trajectory intersections with this Poincare line were extracted to capture the local behavior related to the arrhythmia under investigation. The POS corresponding to atrial activity were selected with regard to the fact that similar ECG morphologies such as P waves, which are corresponding to atrial activity, distribute in a specific region of the RPS. Thirteen features were extracted from the selected intersection points to quantify their distributions. To select the best feature subset, a genetic algorithm (GA), in combination with a support vector machine (SVM), was applied to the training dataset. Based on the selected features and trained SVM, the performance of the proposed method was evaluated using the testing datasets. The results showed that 86.67% of dataset A and 80% of dataset B were correctly classified. This classification accuracy is in the same range as or higher than that of recent studies in this area. These results show that the proposed method, in which no complicated QRST cancelation algorithm was used, has the potential to predict AF termination.     

Constrained optimum surface roughness prediction in turning of X20Cr13 by coupling novel modified harmony search-based neural network and modified harmony search algorithm

Nowadays, manufacturers rely on trustworthy methods to predict the optimal cutting conditions which result in the best surface roughness with respect to the fact that some constraining functions should not exceed their critical values because of current restrictions considering competition found among them in delivering economical and high-quality products to the stringent customers in the shortest time. The present research deals with a modified optimization algorithm of harmony search (MHS) coupled with modified harmony search-based neural networks (MHSNN) to predict the cutting condition in longitudinal turning of X20Cr13 leading to optimum surface roughness. To this end, several experiments were carried out on X20Cr13 stainless steel to attain the required data for training of MHSNN. Feed-forward artificial neural network was utilized to create predictive models of surface roughness and cutting forces exploiting experimental data, and the MHS algorithm was used to find the constrained optimum of surface roughness. Furthermore, simple HS algorithm was used to solve the same optimization problem to illustrate the capabilities of the MHS algorithm. The obtained results demonstrate that the MHS algorithm is more effective and authoritative in approaching the global solution compared with the HS algorithm.     

A DEA approach for comparing solution efficiency in U-line balancing problem using goal programming

Line balancing problem plays an important role in the decision making process to increase efficiency and productivity. Recently, U-shaped layout in many production lines has replaced the traditional straight line layout using just-in-time concept. Here, we propose a model, using multi-objective decision making approach to the U-shaped line balancing problem, to offer enhanced decision maker flexibility, by allowing for conflicting goals. The assembly line operation efficiency is the most significant aim in our study, and this efficiency relates to management of resources and the solution of line balancing problem. First, the U-shaped line balancing problem is solved considering the model's goals. Then, the index function of assembly line balancing is determined and the efficiencies of the optimal solution outputs are evaluated using data envelopment analysis (DEA). Finally, the discrimination weakness and distribution of illogical weight in simple DEA models are resolved using a mixed method.     

An artificial immune algorithm for multiple-route job shop scheduling problem

This paper addresses the multiple-route job shop scheduling problem to minimize makespan. The problem is recognized to be extremely difficult because of its combinatorial nature of integer optimization and the large size of the real problem. The goal is, thus, to obtain near-optimal schedules in a computationally efficient manner. Mathematical formulation of the problem is first presented. Then, an approach based on artificial immune algorithm is proposed. In order to evaluate the effectiveness of the proposed approach, 30 problems in small, medium, and large size are designed and solved using the proposed approach. Problems are also solved using Lingo software and the results are compared. The computational results show that the proposed approach generates high-quality schedules in a timely fashion.