Hossein Ebrahimpour-Komleh

Hossein Ebrahimpour-Komleh
University of Kashan · Department of Computer Engineering

Phd + Postdoc

About

89
Publications
17,099
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
817
Citations
Additional affiliations
October 2007 - present
University of Kashan
Position
  • Assisstant Professor , Teaching [Undergraduate level :] Artificial Intelligence [Graduate level :] Neural networks, Advanced Mathematics for Computer Eng. , Parallel Algorithms, Image Processing, Data mining [Postgraduate level:] Advanced Pattern Recognition , Computer Vision, Machine Learning, Soft Computing
April 2005 - April 2007
The University of Newcastle, Australia
Position
  • PostDoc Position
April 2005 - April 2007
The Commonwealth Scientific and Industrial Research Organisation, sydney, Australia
Position
  • Visiting Scientist

Publications

Publications (89)
Thesis
Full-text available
In recent years, the improvement of medical imaging techniques helps doctors to diagnose tumors. Early detection of tumors will increase the chance of treatment and plays an essential role in patient survival. In this thesis project we would like to find how to be an expert in medical image analysis by explaining fundamental concepts like medical i...
Chapter
Learning in feed-forward neural networks is a crucial and challenging task. Gradient descent-based approaches are among the most commonly employed learning algorithms but suffer from difficulties such as ending up in local optima. To cope with this, swarm intelligence (SI) algorithms can be employed. Memetic algorithms integrate an SI technique wit...
Article
Full-text available
For Multi-label classification, redundant and irrelevant features degrade the performance of classification. To select the best features based on several conflicting objectives, feature selection can be modeled as a large-scale optimization problem. However, most existing multi-objective feature selection methods select the features based on minimi...
Article
Full-text available
Purpose: Pandemic COVID-19 has created an emergency for the medical community. Researchers require extensive study of scientific literature in order to discover drugs and vaccines. In this situation where every minute is valuable to save the lives of hundreds of people, a quick understanding of scientific articles will help the medical community. A...
Article
Full-text available
The most important action in treating diabetic retinopathy is early diagnosis and its progression degree. This paper presents a two-dimensional Deep Belief Network based on Mixed-restricted Boltzmann Machine capable of receiving multiple two-dimensional inputs. Using multiple inputs provides more appropriate prior information for learning. In this...
Chapter
The performance of most data science algorithms, and in particular machine learning algorithms, is largely dependent on the performance of their optimisation algorithm. In other words, without an effective optimisation algorithm there is no effective data science algorithm. Conventional optimisation algorithms suffer from drawbacks such as a tenden...
Article
Clustering is a commonly employed approach to image segmentation. To overcome the problems of conventional algorithms such as getting trapped in local optima, in this paper, we propose an improved automatic clustering algorithm for image segmentation based on the human mental search (HMS) algorithm, a recently proposed method to solve complex optim...
Article
Multi-label classification is a machine learning task to construct a model for assigning an entity in the dataset to two or more class labels. In order to improve the performance of multi-label classification, a multi-objective feature selection algorithm has been proposed in this paper. Feature selection as a preprocessing task for Multi-label cla...
Chapter
Image segmentation is an essential step in image processing and computer vision with many image segmentation algorithms having been proposed in the literature. Among these, clustering is one of the prominent approaches to achieve segmentation. Traditional clustering algorithms have been used extensively for this purpose, although they have disadvan...
Article
Full-text available
Data classification is a fundamental task in data mining. Within this field, the classification of multi-labeled data has been seriously considered in recent years. In such problems, each data entity can simultaneously belong to several categories. Multi-label classification is important because of many recent real-world applications in which each...
Chapter
Representation learning techniques, as a paradigm shift in feature generation, are considered as an important and inevitable part of state of the art pattern recognition systems. These techniques attempt to extract and abstract key information from raw input data. Representation learning based methods of feature generation are in contrast to handy...
Article
Keywords are a collection of important words in a document that are the core topic of the discussion. This paper proposes a hybrid method for automatically extracting keywords from Persian documents and web pages. In the proposed method, firstly, based on linguistic knowledge, processing was performed at word and letter levels to optimize of the an...
Article
Full-text available
Automated segmentation of abnormal tissues in medical images assists both physicians and medical researchers in the process of diseases diagnostic and research activities respectively. Intelligent techniques of automated segmentation are gaining more popularity in contrast to non-intelligent ones. In these techniques, quality representation of pixe...
Article
Full-text available
This paper develops a new variation of deep belief networks which is evaluated on the basis of supervised classification of human actions and activities. The proposed multi-input 1-dimensional deep belief network (M1DBN) can work based on three inputs which contain different information structures. The multi input features helps M1DBN automatically...
Chapter
Full-text available
Finding the optimal connection weights in a neural network is one of the most challenging tasks in machine learning and pattern recognition. The main disadvantage of conventionally used algorithms such as back-propagation is that they show a tendency of getting trapped in local rather than global optima. To address this, population-based metaheuris...
Article
Nowadays, medical image modalities are almost available everywhere. These modalities are bases of diagnosis of various diseases sensitive to specific tissue type. Usually physicians look for abnormalities in these modalities in diagnostic procedures. Count and volume of abnormalities are very important for optimal treatment of patients. Segmentatio...
Preprint
Full-text available
Finding the optimal connection weights in a neural network is one of the most challenging tasks in machine learning and pattern recognition. The main disadvantage of conventionally used algorithms such as back-propagation is that they show a tendency of getting trapped in local rather than global optima. To address this, population-based metaheuris...
Article
Multilevel thresholding is one of the principal methods of image segmentation. These methods enjoy image histogram for segmentation. The quality of segmentation depends on the value of the selected thresholds. Since an exhaustive search is made for finding the optimum value of the objective function, the conventional methods of multilevel threshold...
Article
Image segmentation is one of the fundamental techniques in image analysis. One group of segmentation techniques is based on clustering principles, where association of image pixels is based on a similarity criterion. Conventional clustering algorithms, such as k-means, can be used for this purpose but have several drawbacks including dependence on...
Conference Paper
In this study we consider multi-view capabilities of convolutional neural networks as one of the best methods of representation learning. Multi-view learning as a machine learning technique deals with the task of learning from multiple distinct views or multiple distinct feature sets. Moreover, multi-view feature learning attempts to abstract and s...
Article
Full-text available
In the present study, a new algorithm is developed for neural network training by combining a gradient-based and a meta-heuristic algorithm. The new algorithm benefits from simultaneous local and global search, eliminating the problem of getting stuck in local optimum. For this purpose, first the global search ability of the grey wolf optimizer (GW...
Article
Full-text available
Multi-objective optimization is an inseparable area of optimization and plays a crucial role in terms of practicality. Almost all multi-objective optimization problems in the real world are suitable as opposed to goals with several ideal models around. Rather than one optimal solution, these issues have a set of optimal solutions known as the Paret...
Chapter
Digital technologies are one of the main components in smart cities. Images are one of the principal data types in digital technologies. Images can be seen in a variety of applications such as intelligent transport systems, tourism applications, and real-time science understanding. Therefore, it is important to provide efficient image processing al...
Chapter
Diabetic retinopathy is proved to be one of the most important eye disorders in recent decades that late diagnosis of it may cause low vision or even blindness. Specialist are able to detect retinopathy in retinal images using machine learning as a decision support system which helps accelerate and facilitate the diagnosis. The automated diabetic r...
Article
Full-text available
Population-based metaheuristic algorithms have become popular in recent years with them getting used in different fields such as business, medicine, and agriculture. The present paper proposes a simple but efficient population-based metaheuristic algorithm called Human Mental Search (HMS). HMS algorithm mimics the exploration strategies of the bid...
Chapter
Classification of biomedical data plays a significant role in prediction and diagnosis of disease. The existence of redundant and irrelevant features is one of the major problems in biomedical data classification. Excluding these features can improve the performance of classification algorithm. Feature selection is the problem of selecting a subset...
Article
Full-text available
Multilevel thresholding is one of the most broadly used approaches to image segmentation. However, the traditional techniques of multilevel thresholding are time-consuming, especially when the number of the threshold values is high. Thus, population-based metaheuristic (P-metaheuristic) algorithms can be used to overcome this limitation. P-metaheur...
Chapter
Full-text available
Diabetic retinopathy is proved to be one of the most important eye disorders in recent decades that late diagnosis of it may cause low vision or even blindness. Specialists are able to detect retinopathy in retinal images using machine learning as a decision support system which helps accelerate and facilitate the diagnosis. The automated diabetic...
Article
Full-text available
Feature selection problem is one of the most important issues in machine learning and statistical pattern recognition. This problem is important in many applications such as text categorization because there are many redundant and irrelevant features in these applications which may reduce the classification performance. Indeed, feature selection is...
Article
Full-text available
For many years, researchers have studied high accuracy methods for recognizing the handwriting and achieved many significant improvements. However, an issue that has rarely been studied is the speed of these methods. Considering the computer hardware limitations, it is necessary for these methods to run in high speed. One of the methods to increase...
Chapter
Medical diagnosis is a most important problem in medical data mining. The possible errors of a physician can reduce with the help of data mining techniques. The goal of this chapter is to analyze and compare predictive data mining techniques in the medical diagnosis. To this purpose, various data mining techniques such as decision tree, neural netw...
Conference Paper
Full-text available
Abstract—Image thresholding considered as a popular method for image segmentation. So far, many approaches have been proposed for image thresholding. Maximum entropy thresholding has been widely applied in the literature. This paper proposes a multilevel image thresholding (MECOAT) using cuckoo optimization algorithm (COA). COA is a new nature base...
Conference Paper
Full-text available
Chronic kidney disease is a universal common obstacle which its outcomes can be prevented or delayed by early detection and cure. Classification of kidney disease is vital for global improvement and accomplishment of practical guidance. Therefore, data mining and machine learning techniques can be used to discover knowledge and identify patterns fo...
Article
Full-text available
In today’s modern world, there is no place for passwords and security has the highest priority in current systems. Biometrics like face and voice can be circumvented by fraudulent methods but fingerprint has a high security in this aspect. In this paper a new fingerprint matching approach is introduced. The proposed method with various modification...
Conference Paper
Full-text available
Text classification is extensively used to organize documents in a digital form. According to the growth number of digitally documents, automated text classification has become more Heralds in the recent years. High dimensionality of the feature space is a common problem in text classification. Most of them are irrelevant and redundant which may re...
Article
Full-text available
Face Recognition has attracted many researchers in the last three decades. There have been great improvements in controlled environments and static images. But there are still many challenges in uncontrolled environments and online applications. In this paper, a new parallel face recognition approach has been proposed that is almost robust to illum...
Article
Full-text available
Fingerprint as a biometric has the most applications in verification and identification systems, because of its specific properties. In identification systems, input image is compared with all of images stored in the database. In huge databases, the comparison will take large amounts of time; Consider FBI databases, for instance. Image classificat...
Article
Full-text available
Feature subset selection plays an important role in data mining. The aim of feature selection is to remove redundant and irrelevant features without reducing the accuracy. Cuckoo optimization algorithm (COA) is a new population based algorithm which is inspired by the lifestyle of a species of bird called cuckoo. In this paper, we introduce a new a...
Chapter
Full-text available
Medical diagnosis is a most important problem in medical data mining. The possible errors of a physician can reduce with the help of data mining techniques. The goal of this chapter is to analyze and compare predictive data mining techniques in the medical diagnosis. To this purpose, various data mining techniques such as decision tree, neural net...
Chapter
Full-text available
Classification of biomedical data plays a significant role in prediction and diagnosis of disease. The existence of redundant and irrelevant features is one of the major problems in biomedical data classification. Excluding these features can improve the performance of classification algorithm. Feature selection is the problem of selecting a subs...
Article
Full-text available
Introduction: In recent years, hepatitis diseases have become prevalent in the world. The correct diagnosis of hepatitis disease is not a straight task. The goal of this paper is to introduce a new intelligent system for automatic hepatitis diagnosis based on machine learning approaches. Materials and Methods:the proposed approach consists of three...
Article
Full-text available
Fingerprint classification is an important phase in increasing the speed of a fingerprint verification system and narrow down the search of fingerprint database. Fingerprint verification is still a challenging problem due to the difficulty of poor quality images and the need for faster response. The classification gets even harder when just one cor...
Data
Full-text available
Hough transform is one of the most widely used algorithms in image processing. The major problems of Hough's transform are its time consuming and its abundant requirement of computational resources. In this paper, we try to solve this problem by paralleling this algorithm and implementing it on GPUs(Graphic Process unit) using CUDA(Compute Unified...
Article
Full-text available
Hough transform is one of the most widely used algorithms in image processing. The major problems of Hough's transform are its time consuming and its abundant requirement of computational resources. In this paper, we try to solve this problem by paralleling this algorithm and implementing it on GPUs(Graphic Process unit) using CUDA(Compute Unified...
Conference Paper
Full-text available
Feature selection process is one of the main steps in data mining and knowledge discovery. Feature selection is a process to remove redundant and irreverent features without reducing the classification accuracy. This paper tries to select the best features set using imperialist competitive algorithm. Imperialist competitive algorithm is a novel pop...
Article
Full-text available
The illumination variation is one of the main challenges in real-world face recognition systems. Face recognition under uneven illumination is still an open problem. In this paper, we proposed a novel illumination invariant face recognition approach based on Self Quotient Image and weighted Local Binary Pattern. We improved the performance of the s...
Conference Paper
Full-text available
Cuckoo Optimization Algorithm (COA) is a new evolutionary algorithm which is inspired by the life of a species of bird, called cuckoo. COA has presented excellent capabilities in various optimization problems. In this paper, we want to adapt COA to train the weights of feedforward neural networks. For this purpose, COA has been applied on three kno...
Article
Full-text available
In this article, it has been tried to take care of identifying and picking tomato through image–processing method. Through boosting the vision of a computer to gain discipline and arrangement for picking tomato, though there is a chaos in an agriculture setting besides smart processing system is applied which is equipped with wave's length wireless...
Article
Full-text available
In this paper, an effective method for human eye tracking and also decreasing the current challenges and problems in its algorithms, possibly as real time and for unconstrained environments has been proposed. In this method, firstly face has been detected and segmented from the remaining parts to make the searching area in tracking stage, narrower...
Conference Paper
Full-text available
This paper presents a novel face recognition approach, based on Local Binary Pattern (LBP) and Haar wavelet transform. We propose a fast and robust three-layer weighted Haar and weighte