Sharif Digital Repository

The challenges of water resources sustainable development are enormous. Around the globe, the increasing use of water coupled with environmental deterioration calls for sustainable development of the limited water resources. As a significant part of the world's population still lacks access to safe water and adequate sanitation, and as global urbanization continues to increase, continuous, comprehensive, coordinated and cooperative water resources management is required for the sustainable future of urban areas. The objective of this study was to assess water resources sustainable development for selected urban areas around the world. Using centralized databases of international agencies for... 

A discussion regarding speech accents will be given while describing a set of statistical signal processing methods for the modeling, analysis, synthesis, and morphing of English language accents. Accent morphing deals with the changing of the accent of a speech to a different accent. Accent itself is a distinctive pattern of pronunciation of speech within a community of people who belong to a national, geographic, or socioeconomic grouping. Then, the signal processing methodology for speech accent processing will be reviewed while the concept of an accent profile has been presented  

This paper addresses the problem of finding the nearest neighbor (or one of the R-nearest neighbors) of a query object q in a database of n objects, when we can only use a comparison oracle. The comparison oracle, given two reference objects and a query object, returns the reference object most similar to the query object. The main problem we study is how to search the database for the nearest neighbor (NN) of a query, while minimizing the questions. The difficulty of this problem depends on properties of the underlying database. We show the importance of a characterization: combinatorial disorder D which defines approximate triangle inequalities on ranks. We present a lower bound of Ω(Dlog... 

A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as the group of database images labeled with a common semantic label. It is shown that, by establishing this one-to-one correspondence between semantic labels and semantic classes, a minimum probability of error annotation and retrieval are feasible with algorithms that are 1) conceptually simple and 2) computationally efficient. In this article, a content-based image retrieval and annotation architecture is proposed. Its attitude is decreasing the semantic gap by partitioning the image to its semantic regions and using... 

In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central machine is then responsible for learning the structure based on received messages from the other nodes. We present a set of communication-efficient strategies, which are theoretically proved to convey sufficient information for reliable learning of the structure. In particular, our analyses show that even if each machine sends only the signs of its local data samples to the central node, the tree structure can still be recovered with high accuracy. Our... 

In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central machine is then responsible for learning the structure based on received messages from the other nodes. We present a set of communication-efficient strategies, which are theoretically proved to convey sufficient information for reliable learning of the structure. In particular, our analyses show that even if each machine sends only the signs of its local data samples to the central node, the tree structure can still be recovered with high accuracy. Our... 

In this paper, learning of tree-structured Gaussian graphical models from distributed data is addressed. In our model, samples are stored in a set of distributed machines where each machine has access to only a subset of features. A central machine is then responsible for learning the structure based on received messages from the other nodes. We present a set of communication-efficient strategies, which are theoretically proved to convey sufficient information for reliable learning of the structure. In particular, our analyses show that even if each machine sends only the signs of its local data samples to the central node, the tree structure can still be recovered with high accuracy. Our... 

It is of fundamental importance to find algorithms obtaining optimal performance for learning of statistical models in distributed and communication limited systems. Aiming at characterizing the optimal strategies, we consider learning of Gaussian Processes (GP) in distributed systems as a pivotal example. We first address a very basic problem: how many bits are required to estimate the inner-products of some Gaussian vectors across distributed machines? Using information theoretic bounds, we obtain an optimal solution for the problem which is based on vector quantization. Two suboptimal and more practical schemes are also presented as substitutes for the vector quantization scheme. In... 

Content-based image retrieval (CBIR) makes use of image features, such as color, texture or shape, to index images with minimal human intervention. Content-based image retrieval can be used to locate medical images in large databases. In this paper, the fundamentals of the key components of content-based image retrieval systems are introduced first to give an overview of this area. Then, a case study which describes the methodology of a CBIR system for retrieving human brain magnetic resonance images, is presented. The proposed method is based on Adaptive Neuro-fuzzy Inference System (ANFIS) learning and could classify an image as normal and tumoral. This research uses the knowledge of CBIR... 

Content-based image retrieval (CBIR) has been one of the most active areas of research. The retrieval principle of CBIR systems is based on visual features such as colour, texture and shape or the semantic meaning of the images. A CBIR system can be used to locate medical images in large databases. This paper presents a CBIR system for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the support vector machine (SVM) learning method. This system can retrieve similar images from the database in two groups: normal and tumoural. This research uses the knowledge of the CBIR approach to the application of medical decision support and discrimination... 

Content-based image retrieval (CBIR) has turned into an important and active potential research field with the advance of multimedia and imaging technology. It makes use of image features, such as color, texture and shape, to index images with minimal human intervention. A CBIR system can be used to locate medical images in large databases. In this paper we propose a CBIR system which describes the methodology for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the Adaptive neuro-fuzzy inference system (ANFIS) learning to retrieve similar images from database in two categories: normal and tumoral. A fuzzy classifier has been used, because of the... 

The current double JPEG compression detection techniques identify whether or not an JPEG image file has undergone the compression twice, by knowing its embedded quantization table. This paper addresses another forensic scenario in which the quantization table of a JPEG file is not explicitly or reliably known, which may compel the forensic analyst to blindly reveal the recompression clues. To do this, we first statistically analyze the theory behind quantized alternating current (AC) modes in JPEG compression and show that the number of quantized AC modes required to detect double compression is a function of both the image’s block texture and the compression’s quality level in a fresh... 

A dense monitoring network is vital for the reliable assessment of PM10 in different parts of an urban area. In this study, a new idea is employed for the re-construction of the 20 shut-down PM10 monitoring stations of Berlin. It endeavours to find the non-linear relationship between the hourly PM10 concentration of both the still operating and the shut-down PM10 monitoring stations by using a fuzzy modelling technique, called modified active learning method (MALM). In addition, the simulations were performed by using not only raw PM10 databases but also log-transformed PM10 databases for skewness reduction. According to the results of hourly PM10 simulation (root mean square error about... 

Graph Matching (GM) plays an essential role in computer vision and machine learning. The ability of using pairwise agreement in GM makes it a powerful approach in feature matching. In this paper, a new formulation is proposed which is more robust when it faces with outlier points. We add weights to the one-to-one constraints, and modify them in the process of optimization in order to diminish the effect of outlier points in the matching procedure. We execute our proposed method on different real and synthetic databases to show both robustness and accuracy in contrast to several conventional GM methods  

Skin detection has different applications in computer vision such as face detection, human tracking and adult content filtering. One of the major approaches in pixel based skin detection is using Bayesian classifiers. Bayesian classifiers performance is highly related to their training set. In this paper, we introduce a new Bayesian classifier skin detection method. The main contribution of this paper is creating a huge database to create color probability tables and new method for creating skin pixels data set. Our database consists of about 80000 images containing more than 5 billions pixels. Our tests shows that the performance of Bayesian classifier trained on our data set is better than... 

Many websites on the Internet offer services to people. They usually ask the users to fill the registration forms for using their services. Unfortunately, some vandalistic persons write programs which make automatic fake registration. For solving this problem, CAPTCHA (Completely Automated Public Turing test to tell Computers and Human Apart) systems are invented. These systems distinguish human users from computer programs. One of the CAPTCHA methods which is designed for Persian and Arabic users is Nastaliq CAPTCHA. In this method, the image of a Persian or Arabic word which is written in Nastaliq font is chosen from a dictionary, and it is shown to the users, then they are asked to type... 

Background: It has been previously shown that palindromic sequences are frequently observed in proteins. However, our knowledge about their evolutionary origin and their possible importance is incomplete. Results: In this work, we tried to revisit this relatively neglected phenomenon. Several questions are addressed in this work. (1) It is known that there is a large chance of finding a palindrome in low complexity sequences (i.e. sequences with extreme amino acid usage bias). What is the role of sequence complexity in the evolution of palindromic sequences in proteins? (2) Do palindromes coincide with conserved protein sequences? If yes, what are the functions of these conserved segments?... 

Dynamic thermal rating (DTR) of transmission system facilities is a way to maximally realize the equipment capacities while not threatening their health. With regards to transmission lines, the allowable current of conductors is forecasted based on the environmental situations expected in some forthcoming time periods. Due to the fact that weather conditions continuously vary, sampling points are very limited against many line spans, and the measurements have an inherent error, uncertainties must be appropriately included in the DTR determination. This paper adopts the fuzzy theory as a strong and simple tool to model uncertainties in the DTR calculation. Since DTR intends to determine the... 

This paper presents a multi-stage algorithm for QRS complex classification into normal and abnormal categories using an unsupervised sequential beat clustering and a cross-distance analysis algorithm. After the sequential beat clustering, a search algorithm based on relative similarity of created classes is used to detect the main normal class. Then other classes are labeled based on a distance measurement from the main normal class. Evaluated results on the MIT-BIH ECG database exhibits an error rate less than 1% for normal and abnormal discrimination and 0.2% for clustering of 15 types of arrhythmia existing on the MIT-BIH database. © 2001 IEEE  

Sequential pattern recognition has long been an important topic of soft computing research with a wide area of applications including speech and handwriting recognition. In this paper, the performance of a novel fuzzy sequential pattern recognition tool named “Fuzzy Elastic Matching Machine” has been investigated. This tool overcomes the shortcomings of the HMM including its inflexible mathematical structure and inconsistent mathematical assumptions with imprecise input data. To do so, “Fuzzy Elastic Pattern” was introduced as the basic element of FEMM. It models the elasticity property of input data using fuzzy vectors. A sequential pattern such as a word in speech or a piece of writing is...