Sharif Digital Repository

k-medoids algorithm is a partitional, centroid-based clustering algorithm which uses pairwise distances of data points and tries to directly decompose the dataset with n points into a set of k disjoint clusters. However, k-medoids itself requires all distances between data points that are not so easy to get in many applications. In this paper, we introduce a new method which requires only a small proportion of the whole set of distances and makes an effort to estimate an upperbound for unknown distances using the inquired ones. This algorithm makes use of the triangle inequality to calculate an upper-bound estimation of the unknown distances. Our method is built upon a recursive approach to... 

Feature selection is a fundamental problem in machine learning and data mining. The majority of feature selection algorithms are designed for running on a single machine (centralized setting) and they are less applicable to very large datasets. Although there are some distributed methods to tackle this problem, most of them are distributing the data horizontally which are not suitable for datasets with a large number of features and few number of instances. Thus, in this paper, we introduce a novel vertically distributable feature selection method in order to speed up this process and be able to handle very large datasets in a scalable manner. In general, feature selection methods aim at... 

Due to rapid development of manufacturing process, composite materials with porosity have attracted commercially notices in advanced engineering applications. For this regard, buckling and vibrational characteristics of a porous composite cylindrical nanoshell reinforced with GPLs is investigated in this paper. The material properties of piece-wise graphene-reinforced composites (GPLRC) are assumed to be graded in the thickness direction of a cylindrical nanoshell and are estimated using a nanomechanical model. The novelty of our work is including the effects of porosity and GPLRC on natural frequency, critical axial load and critical temperature of the GPLRC cylindrical nanoshell. The... 

In the present work, an amperometric inhibition biosensor for the determination of sulfide has been fabricated by immobilizing Coprinus cinereus peroxidase (CIP) on the surface of screen printed electrode (SPE). Chitosan/acrylamide was applied for immobilization of peroxidase on the working electrode. The amperometric measurement was performed at an applied potential of -150. mV versus Ag/AgCl with a scan rate of 100. mV in the presence of hydroquinone as electron mediator and 0.1. M phosphate buffer solution of pH 6.5. The variables influencing the performance of sensor including the amount of substrate, mediator concentration and electrolyte pH were optimized. The determination of sulfide... 

In this article, wave propagation characteristics of a size-dependent laminated composite nanostructure coupled with a piezoelectric actuator (PA) is investigated. In order to consider the effects of small scale, the governing equations of the laminated composite nanostructure coupled with PA are derived using Hamilton’s principle based on the nonlocal strain gradient theory (NSGT). The differential equations of motion are solved with the assistance of the analytical method. Afterward, a parametric study is carried out to investigate the effects of the PA thickness, wave number, angular velocity and the ply angle on the value of phase velocity. The results show that the ply angle plays an... 

In the present research, human errors existed in tasks of operators working in two control rooms (Northern and Southern control rooms) in the Tehran oil refinery are identified and evaluated. Then, corrective strategies and actions are advised to decrease errors. At first, using hierarchical task analysis (HTA) method, four positions including shift controller, head operators, control room's operators, and outside operators are analyzed. Afterwards, human errors in the considered positions are identified and assessed using technique for retrospective and predictive analysis of cognitive errors (TRACEr). Results present 670 internal errors and 738 external errors in the Northern sector while... 

One of the methods for providing private parking is to use the mechanized parking within neighborhoods or housing units that are common in today's world. But, unfortunately, due to lack of appropriate rules and technical, administrative and legal guidelines, this approach has not yet been used. Hence the necessity of investigating and formulating laws, programs and specific criteria for mechanized private parking in terms of legal, technical, traffic, urbanization aspects (location, neighborhood, architecture, building standards and national regulations, economic aspects, etc.) have been a motivation for conducting this study. In this research, after studying and investigating previous...