Abdolhossein Fathi | Razi University of Kermanshah, Iran (original) (raw)

Papers by Abdolhossein Fathi

Signal, image and video processing, Feb 15, 2024

Today, pervasive systems have become an inseparable part of computer science and engineering. The... more Today, pervasive systems have become an inseparable part of computer science and engineering. These systems provide automated connection with remote access and seamless transmission of biological and other data upon request. The health domain is one of the most important application of these systems. Moreover, heart is the most important part of human body and cardiac diseases are the second leading cause of death. Therefore, different tools and methods have been invented for the rapid investigation and early detection of cardiac diseases and the cardiac operations. These methods aim to obtain structural and operational information about the heart. Any changes in the form of cardiac signals can indicate a disease or abnormal behavior of the heart. Therefore, early detection of these changes can be significant to prevent and treat cardiac diseases. This paper proposes a method to detect atrial arrhythmia, which is one of the most common cardiac anomalies. The proposed approach can be...

A recommender system is a guide and assistance for choosing the required product or service for i... more A recommender system is a guide and assistance for choosing the required product or service for improving the electronic commerce systems. Most of the recommender systems use the history of customer purchase and a few are based on Semantic relatedness of purchased commodities. In this paper a semantic recommender system based on Ant Colony and Ontology dependencies is used for improvement of electronic commerce. This system comprises heuristic, stochastic, reinforcement learning in Ant Colony theory and semantic dependency in ontology characteristics. The presented system is able to recommend similar, complement and bundled products. This characteristic can overcome problems such as cold start, scalability and scarcity of information. In this paper applied tests results show the performance and efficiency of presented algorithms.

Journal of Mechanics in Medicine and Biology, 2020

Purpose: Selecting the proper electrodes to capture EEG signals is a critical issue that affects ... more Purpose: Selecting the proper electrodes to capture EEG signals is a critical issue that affects overall classification accuracy. Using the pre-selected electrodes is impractical due to the variety of responses to a stimulus among individuals. Thus, discarding electrodes may lead to a loss of useful information. Methods: In this work, a novel algorithm is proposed to help address this problem by manipulating the feature values of each electrode individually according to its activity ratio. Plus, to improve EEG feature vectors that correspond to the electrodes’ energetic levels, the algorithm amplifies or dampens the feature values according to the energy ratio of each electrode individually. The algorithm was examined using a public dataset and statistical features. The test was performed using two different groups of electrodes: the first in a more specific area over the motor cortex with seven channels and the second in the area over and close to the motor cortex with twenty-one c...

Signal, Image and Video Processing, 2018

Since electrocardiogram (ECG) is a unique physiological signal which is existing only in the live... more Since electrocardiogram (ECG) is a unique physiological signal which is existing only in the live people, it has been used in the novel biometric systems to identify people and to counter forge and fraud attacks. Most of existing methods suffer from restriction in detection of various points within ECG signal. In this paper, a new ECG-based identification algorithm is presented. In this method at first, the most important and reliable fiducial point (R peak in each ECG rhythm) is discovered. Then, to reduce redundant information the ECG signal is quantized. Finally, the ECG samples between two successive fiducial R points will be normalized and coded with character strands symbolically. These codes will be extracted at different times for each person and store as biometric feature. After extracting symbolic code of ECG signals, dynamic time warping technique is employed to calculate the similarity between input user symbolic code and reference codes of authorized users. The identity of input ECG is related to the authorized user that has maximum similarity. The proposed method has been tested over 100 subjects, and its identification accuracy was about 99.4%.

Journal of Medical Systems, 2015

LISTA DE CUADROS pág. Cuadro 1. Documentos recuperados para la búsqueda. Cuadro 2. Trabajos sobre... more LISTA DE CUADROS pág. Cuadro 1. Documentos recuperados para la búsqueda. Cuadro 2. Trabajos sobre frameworks para IoT hallados Cuadro 3. Trabajos sobre framework para desarrollos específicos. Cuadro 4. Trabajos sobre plataformas Hardware y software Cuadro 5.Normatividad identificada para dispositivos vestibles Cuadro 6. Fases y actividades del proyecto Cuadro 7. Técnicas e instrumentos de recolección de información. Cuadro 8. Documentos recuperados para revisión Cuadro 9. Determinación de componente en arquitecturas halladas. Cuadro 10. aplicaciones para arquitecturas halladas. Cuadro 11. Componentes funcionales presentes en las arquitecturas halladas. Cuadro 12. Requisitos encontrados en cada arquitectura Cuadro 13. Funcionalidades importantes de dispositivo IoT vestible Cuadro 14. Componentes de Hardware requeridos. Cuadro 15. Escenarios de simulación Cuadro 16. Componentes modificados para el prototipado 100 Cuadro 17. Extracto datos descargados de Thingspeak visualizados en Excel Cuadro 18. Detalles de problema a bordar en prueba de concepto Cuadro 19. Datos fuera de parámetro Cuadro 20. Errores fuera de parámetro y porcentaje de la muestra LISTA DE ANEXOS pág. Anexo 1. Modelo de dominio IoT vestible Anexo 2. Modelo de componentes de arquitectura genérica Anexo 3. Diagrama de despliegue de arquitectura genérica Anexo 4. Modelo de arquitectura en Simulink con bloques funcionales Anexo 5. Modelo de arquitectura en Simulink con submodelos Anexo 6. Entorno de simulación Anexo 7. Elementos adjuntos para el modelo de arquitectura en Simulink. Anexo 8. Elementos adjuntos para el entorno de simulación Anexo 9. Elementos adjuntos para el entorno de prototipado. RESUMEN Framework para el diseño, simulación y prototipado funcional de dispositivos IoT vestibles.

Signal, Image and Video Processing, Jul 23, 2014

Human-computer interface systems provide an alternative input modality to allow people with sever... more Human-computer interface systems provide an alternative input modality to allow people with severe disabilities to access computer systems. One of the inexpensive and unobtrusive methods for this purpose is image-based eye blinks detection. Currently, available human-computer interface systems are often intrusive, limit in head rotation, require special hardware, and have special lighting or manual initialization. This paper presented a new robust method for real-time eye blinks detection. This method enables interaction using "blink patterns," which are sequences of long and short blinks interpreted as semiotic messages. The precise location of the eye is determined automatically through multi-cues, accompanied by integration of eye variance feature and Gaussian Mixture Model classifier. The detected eye window is converted into a binary image. The eyelid's distance is extracted by applying a variance projection derivative function. By following the eyelid's distance in a finite-state machine, the blink patterns can be detected. The performance of the presented algorithm is evaluated using several frame streams. The experimental results show a robust eye blink pattern detection system in real environments.

Computers in Biology and Medicine, Aug 1, 2017

Compression algorithm is an essential part of Telemedicine systems, to store and transmit large a... more Compression algorithm is an essential part of Telemedicine systems, to store and transmit large amount of medical signals. Most of existing compression methods utilize fixed transforms such as DCT and wavelet and usually cannot efficiently extract signal redundancy especially for non-stationary signals such as EEG. In this paper, we first propose learning-based adaptive transform using combination of DCT and artificial neural network (ANN) reconstruction technique. This adaptive ANN-based transform is applied to the DCT coefficients of EEG data to reduce its dimensionality and also to estimate the original DCT coefficients of EEG in the reconstruction phase. To develop a new near lossless compression method, the difference between the original DCT coefficients and estimated ones are also quantized. The quantized error is coded using Arithmetic coding and sent along with the estimated DCT coefficients as compressed data. The proposed method was applied to various datasets and the results show higher compression rate compared to the state-of-the-art methods.

Signal, Image and Video Processing, Jul 23, 2016

In this study, a new compression algorithm for ECG signal is proposed based on selecting importan... more In this study, a new compression algorithm for ECG signal is proposed based on selecting important subbands of wavelet packet transform (WPT) and applying subband-dependent quantization algorithm. To this end, first WPT was applied on ECG signal and then more important subbands are selected according to their Shannon entropy. In the next step, content-based quantization and denoising method are applied to the coefficients of the selected subbands. Finally, arithmetic coding is employed to produce compressed data. The performance of the proposed compression method is evaluated using compression rate (CR), percentage root-mean-square difference (PRD) as signal distortion, and wavelet energy-based diagnostic distortion (WEDD) as diagnostic distortion measures on MIT-BIH Arrhythmia database. The average CR of the proposed method is 29.1, its average PRD is <2.9 % and WEDD is <3.2 %. These results demonstrated that the proposed method has a good performance compared to the state-ofthe-art compression algorithms.

Journal of Medical Systems, Jul 26, 2019

New biometric identification techniques are continually being developed to meet various applicati... more New biometric identification techniques are continually being developed to meet various applications. Electroencephalography (EEG) signals may provide a reasonable option for this type of identification due its unique features that overcome the lacks of other common methods. Currently, however, the processing load for such signals requires considerable time and labor. New methods and algorithms have attempted to reduce EEG processing time, including a reduction of the number of electrodes and segmenting the EEG data into its typical frequency bands. This work complements other efforts by proposing a genetic algorithm to reduce the number of necessary electrodes for measurements by EEG devices. Using a public EEG dataset of 109 subjects who underwent relaxation with eye-open and eye-closed stimuli, we aimed to determine the minimum set of electrodes required for optimum identification accuracy in each EEG sub-band of both stimuli. The results were encouraging and it was possible to accurately identify a subject using about 10 out of 64 electrodes. Moreover, higher frequency bands required a fewer number of electrodes for identification compared with lower frequency bands.

Signal, Image and Video Processing, Jun 21, 2022

vices take advantage of pervasive systems. Pervasive systems in non-hospital settings aim at bett... more vices take advantage of pervasive systems. Pervasive systems in non-hospital settings aim at better managing of chronic care patients. They also control health delivery costs and increase the quality of life and quality of health services. Furthermore, they can lead us to avoid serious complications. To this end, it is mainly required to monitor the patient's vital signals (i.e. ECG, blood pressure, heart rate, breath rate, oxygen saturation and perspiration).

Neural Computing and Applications, Aug 9, 2012

Automatic extraction of blood vessels is an important step in computer-aided diagnosis in ophthal... more Automatic extraction of blood vessels is an important step in computer-aided diagnosis in ophthalmology. The blood vessels have different widths, orientations, and structures. Therefore, the extracting of the proper feature vector is a critical step especially in the classifierbased vessel segmentation methods. In this paper, a new multi-scale rotation-invariant local binary pattern operator is employed to extract efficient feature vector for different types of vessels in the retinal images. To estimate the vesselness value of each pixel, the obtained multi-scale feature vector is applied to an adaptive neuro-fuzzy inference system. Then by applying proper top-hat transform, thresholding, and length filtering, the thick and thin vessels are highlighted separately. The performance of the proposed method is measured on the publicly available DRIVE and STARE databases. The average accuracy 0.942 along with true positive rate (TPR) 0.752 and false positive rate (FPR) 0.041 is very close to the manual segmentation rates obtained by the second observer. The proposed method is also compared with several stateof-the-art methods. The proposed method shows higher average TPR in the same range of FPR and accuracy.

Biocybernetics and Biomedical Engineering, 2018

Breast cancer has high incidence rate compared to the other cancers among women. This disease lea... more Breast cancer has high incidence rate compared to the other cancers among women. This disease leads to die if it does not diagnosis early. Fortunately, by means of modern imaging procedure such as MRI, mammography, thermography, etc., and computer systems, it is possible to diagnose all kind of breast cancers in a short time. One type of BC images is histology images. They are obtained from the entire cutoff texture by use of digital cameras and contain invaluable information to diagnose malignant and benign lesions. Recently by requesting to use the digital workflow in surgical pathology, the diagnosis based on whole slide microscopy image analysis has attracted the attention of many researchers in medical image processing. Computer aided diagnosis (CAD) systems are developed to help pathologist make a better decision. There are some weaknesses in histology images based CAD systems in compared with radiology images based CAD systems. As these images are collected in different laboratory stages and from different samples, they have different distributions leading to mismatch of training (source) domain and test (target) domain. On the other hand, there is the great similarity between images of benign tumors with those of malignant. So if these images are analyzed undiscriminating, this leads to decrease classifier performance and recognition rate. In this research, a new representation learning-based unsupervised domain adaptation method is proposed to overcome these problems. This method attempts to distinguish benign extracted feature vectors from those of malignant ones by learning a domain invariant space as much as possible. This method achieved the average classification rate of 88.5% on BreaKHis dataset and increased 5.1% classification rate compared with basic methods and 1.25% with state-of-art methods.

Pattern Recognition Letters, Jul 1, 2012

ABSTRACT The local binary pattern (LBP) operator is a very effective multi-resolution texture des... more ABSTRACT The local binary pattern (LBP) operator is a very effective multi-resolution texture descriptor that can be applied in many image processing applications. However, existing LBP operators can not use the information of non-uniform patterns efficiently and they are also sensitive to noise. This paper proposes a noise tolerant extension of LBP operators to extract statistical and structural image features for efficient texture analysis. The proposed LBP operator uses a circular majority voting filter and suitable rotation-invariant labeling scheme to obtain more regular uniform and non-uniform patterns that have better discrimination ability and more robustness against noise. Experimental results on the Brodatz, CUReT and MeasTex databases show the improvement of the proposed LBP operator performance, especially when a large number of neighbors are used for extracting texture patterns.

International Journal of Modern Education and Computer Science, Jan 8, 2017

This paper presents a new NoC architecture to improve flexibility and area consumption using a ce... more This paper presents a new NoC architecture to improve flexibility and area consumption using a centralized controller. The idea behind this paper is improving SDN concept in NoC. The NoC routers are replaced with small switches and a centralized controller doing the routing algorithm and making control decisions. As one of the main desirable property of NoC is flexibility, in this work with the help of centralized controller, having different topologies and also having two separate networks in a single platform is possible. The other effects of this new scheme are power and area consumption which are investigated. Performance of the NoC is also studied with an analytical model and compared with the traditional NoC. The proposed NoC is implemented in VHDL, simulated and tested with ISE Xilinx.

Journal of Visual Communication and Image Representation, Jul 1, 2016

Face recognition is an important subject in computer vision and authentication systems. Feature e... more Face recognition is an important subject in computer vision and authentication systems. Feature extraction is one of the main steps in the face recognition systems , which greatly affects recognition accuracy. In the most of the existing methods, only local features in the facial area are extracted and employed in recognizing the person's face. In this article, at first a novel multi-scale and rotation invariant global feature descriptor is introduced by applying the Zernike moment on the outputs of Gabor filters. Then the proposed global feature along with an efficient local feature, the histogram of oriented gradient (HOG), is employed to propose a new face recognition system. The proposed system was tested on three famous face recognition databases, namely ORL, Yale and AR and face recognition rates of 98%, 97.8% and 97.1% were obtained respectively. These rates are higher than other state-of-the-art methods.

IEEE Signal Processing Letters, Dec 1, 2015

One of the new challenges of biometric systems based on face analysis is kinship verification. Li... more One of the new challenges of biometric systems based on face analysis is kinship verification. Little efforts have been done in spite of the importance and functionality of this subject. Most of existing methods have been trying to exploit and represent techniques based on metric learning to increase verification rate, paying no attention to the effect of the features extracted from the faces. Despite the previous methods exploiting simple local features, we have focused on the combination and selection of effective features in this paper. To this end, local and global features were combined to describe the face images in a better way. The effective and discriminative features were selected using the kinship genetic algorithm and then fulfilled kinship verification. The proposed method is tested and analysed on the standard and big datasets KinFaceW-I and KinFaceW-II, and verification rates of 81.3% and 86.15% were obtained respectively.