Sharif Digital Repository

The artificial neural network-group contribution (ANN-GC) method is applied to estimate the standard enthalpy of combustion of pure chemical compounds. A total of 4590 pure compounds from various chemical families are investigated to propose a comprehensive and predictive model. The obtained results show the squared correlation coefficient (R 2) of 0.999 99, root mean square error of 12.57 kJ/mol, and average absolute deviation lower than 0.16% for the estimated properties from existing experimental values  

Evaluation of the reaction force on a tool which is used for exertion of force on biomaterials such as biological cells or soft tissues has applications in virtual reality based medical simulators or haptic tools. In this study, two least square based support vector machine (SVM) models have been constructed to predict the indentation or reaction force on mouse oocyte and embryo cells in cell injection experiment. Inputs of these two models are geometrical parameters of indented cell, namely dimple radius (a), dimple depth (w) and radius of the semicircular curve (R). Experimental data for calibration and prediction of the models have been captured from literatures. The performance of the... 

Realistic simulation of tool-tissue interactions can help to develop more effective surgical training systems and simulators. This study uses a finite element and meshless modeling approach to simulate the grasping procedure of a large intra-abdominal organ, i.e. a kidney, during laparoscopic surgery. Results indicate that the accuracy of the meshless method is comparable with that of the finite element method, with root mean square errors in the range of 0.8 to 2.3 mm in different directions. For the model presented in this study, the computational cost of the meshless method was much less than that of the finite element model  

Quantum metrology calculates the ultimate precision of all estimation strategies, measuring what is their root-mean-square error (RMSE) and their Fisher information. Here, instead, we ask how many bits of the parameter we can recover; namely, we derive an information-theoretic quantum metrology. In this setting, we redefine "Heisenberg bound" and "standard quantum limit" (the usual benchmarks in the quantum estimation theory) and show that the former can be attained only by sequential strategies or parallel strategies that employ entanglement among probes, whereas parallel-separable strategies are limited by the latter. We highlight the differences between this setting and the RMSE-based... 

We report the design, fabrication and error analysis of a sun sensor array composed of six photodiodes. The sensor estimates the direction of the sun using a linear least squares method. The performance of the sensor is deteriorated by three major sources: fabrication errors, scattered environmental light, and inexact modeling of photodiodes. Using a calibration procedure and modeling the uniform component of the environmental light, we mitigate the first two errors and significantly reduce root mean squared error from 2.63° to 0.83°. For a Field of View (FOV) of 110°, the maximum estimation error also drops from 3.8° to 1.6°. Through exact mathematical modeling of photodiodes, we... 

To date various commercial systems have been used in the GAIT analysis. These systems have some difficulties for clinical use, such as interfering with normal movement and high prices. The possibility of utilization of Kinect as a sensor for GAIT analysis has been studied in this research. The accuracy of Kinect in calculation of GAIT parameters such as lower limb joint angles, stride time, and stride length were computed during normal walking. The effects of the sensor's position and direction relative to the walkway were also investigated. The Kinect sensor was installed at different positions toward the motion path. In each position the data was recorded by both Kinect and a commercial... 

A number of geometrically-detailed passive finite element (FE) models of the lumbar spine have been developed and validated under in vitro loading conditions. These models are devoid of muscles and thus cannot be directly used to simulate in vivo loading conditions acting on the lumbar joint structures or spinal implants. Gravity loads and muscle forces estimated by a trunk musculoskeletal (MS) model under twelve static activities were applied to a passive FE model of the L4-L5 segment to estimate load sharing among the joint structures (disc, ligaments, and facets) under simulated in vivo loading conditions. An equivalent follower (FL), that generates IDP equal to that generated by muscle... 

A number of geometrically-detailed passive finite element (FE) models of the lumbar spine have been developed and validated under in vitro loading conditions. These models are devoid of muscles and thus cannot be directly used to simulate in vivo loading conditions acting on the lumbar joint structures or spinal implants. Gravity loads and muscle forces estimated by a trunk musculoskeletal (MS) model under twelve static activities were applied to a passive FE model of the L4-L5 segment to estimate load sharing among the joint structures (disc, ligaments, and facets) under simulated in vivo loading conditions. An equivalent follower (FL), that generates IDP equal to that generated by muscle... 

In wideband interferometric direction finding ambiguity is inevitable due to practical antenna array dimensions. A new algorithm for wideband interferometer direction finding is developed to resolve the ambiguity problem with minimum number of antennas. The method is based on direction finding by three antennas arranged at the three vertices of a triangle named the base-triangle. A two dimensional matrix of ambiguous angles is generated. The ambiguity problem is resolved by an auxiliary base-triangle formed by a fourth antenna in the arrangement. The common angle between the two ambiguous directions derived from the two base-triangles, is the desired angle. As such a four antenna array is... 

A controversial issue in artificial intelligence is human emotion recognition. This paper presents a fuzzy parallel cascades (FPC) model for predicting the continuous subjective emotional appraisal of music by time-varying spectral content of electroencephalogram (EEG) signals. The EEG, along with an emotional appraisal of 15 subjects, was recorded during listening to seven musical excerpts. The emotional appraisement was recorded along the valence and arousal emotional axes as a continuous signal. The FPC model was composed of parallel cascades with each cascade containing a fuzzy logic-based system. The FPC model performance was evaluated using linear regression (LR), support vector... 

Charpy impact energy of the produced Al6061-SiCp laminated nanocomposites by mechanical alloying was modeled by adaptive neuro-fuzzy interfacial systems (ANFIS) in both crack divider and crack arrester configurations. The model was constructed by training, validating and testing of 171 gathered input-target data. The thickness of layers, the number of layers, the adhesive type, the crack tip configuration and the content of SiC nanoparticles were five independent input parameters utilized for modeling. The output parameter was Charpy impact energy of the nanocomposites. The performance of the proposed models was evaluated by absolute fraction of variance, the absolute percentage error and... 

In the present study, a prediction model was derived for the effective angle of shearing resistance (φ′) of soils using a novel hybrid method coupling genetic programming (GP) and orthogonal least squares algorithm (OLS). The proposed nonlinear model relates φ′ to the basic soil physical properties. A comprehensive experimental database of consolidated-drained triaxial tests was used to develop the model. Traditional GP and least square regression analyses were performed to benchmark the GP/OLS model against classical approaches. Validity of the model was verified using a part of laboratory data that were not involved in the calibration process. The statistical measures of correlation... 

The current study presents an application of near infrared spectroscopy for identification and quantification of the fraudulent addition of barley in roasted and ground coffee samples. Nine different types of coffee including pure Arabica, Robusta and mixtures of them at different roasting degrees were blended with four types of barley. The blending degrees were between 2 and 20 wt% of barley. D-optimal design was applied to select 100 and 30 experiments to be used as calibration and test set, respectively. Partial least squares regression (PLS) was employed to build the models aimed at predicting the amounts of barley in coffee samples. In order to obtain simplified models, taking into... 

Success in forecasting and analyzing sales for given goods or services can mean the difference between profit and loss for an accounting period and, ultimately, the success or failure of the business itself. Therefore, reliable prediction of sales becomes a very important task. This article presents a novel sales forecasting approach by the integration of genetic fuzzy systems (GFS) and data clustering to construct a sales forecasting expert system. At first, all records of data are categorized into k clusters by using the K-means model. Then, all clusters will be fed into independent GFS models with the ability of rule base extraction and data base tuning. In order to evaluate our K-means... 

Comparative studies between response surface methodology (RSM) and artificial neural network (ANN) methods to find the effects of electrospinning parameters on the porosity of nanofiber mats is described. The four important electrospinning parameters studied included solution concentration (wt.%), applied voltage (kV), spinning distance (cm) and volume flow rate (mL/h). It was found that the applied voltage and solution concentration are the two critical parameters affecting the porosity of the nanofiber mats. The two approaches were compared for their modeling and optimization capabilities with the modeling capability of RSM showing superiority over ANN, having comparatively lower values of... 

In this paper, we propose a novel method for extracting fiducial points (FPs) of electrocardiogram (ECG) signals. We propose the use of multi hidden Markov model (MultiHMM) as opposed to the traditional use of Classic HMM. In the MultiHMM method, each segment of an ECG beat is represented by a separate ergodic continuous density HMM. Each HMM has different state number and is trained separately. In the test step, the log-likelihood of two consecutive HMMs is compared and a path is estimated, which shows the correspondence of each part of the ECG signal to the HMM with the maximum log-likelihood. Fiducial points are estimated from the obtained path. For performance evaluation, the Physionet... 

Developing a computational model for studying tribological performance is essential for computing accurate life cycle of various materials. Caused by the existence of complicated and nonlinear interactions between material surfaces, exact modeling of wear behavior is very difficult. Artificial intelligence (AI) can be used in distinguishing similar patterns in experimental data and predictive modeling of a certain material’s wear behavior. In this paper, artificial neural networks (ANNs) approach, adaptive neural-based fuzzy inference system (ANFIS) technique, and fuzzy clustering method (FCM) are used to develop a simple, accurate, and applicable model for predicting the wear behavior of...