Papers by FARDIN ABDALI-MOHAMMADI
New Representation in GP for Ensemble Classification of Human Motions Based on Inertial Signals
New Representation in Genetic Programming for Ensemble Classification of Human Motions Based on I... more New Representation in Genetic Programming for Ensemble Classification of Human Motions Based on Inertial Signals
Razi Online Persian Character Recognition
TELKOMNIKA (Telecommunication Computing Electronics and Control), 2020
With the increased use of computers, electronic devices and human interaction with computer in th... more With the increased use of computers, electronic devices and human interaction with computer in the broad spectrum of human life, the role of controlling emotions and increasing positive emotional states becomes more prominent. If a user's negative emotions increase, his/her efficiency will decrease greatly as well. Research has shown that colors are to be considered as one of the most influential basic functions in sight, identification, interpretation, perception and senses. It can be said that colors have impact on individuals' emotional states and can change them. In this paper, by learning the reactions of users with different personality types against each color, communication between the user's emotional states and personality and colors were modeled for the variable "emotional control". For the sake of learning, we used a memory-based system with the user's interface color changing in accordance with the positive and negative experiences of users with different personalities. The end result of comparison of the testing methods demonstrated the superiority of memory-based learning in all three parameters of emotional control, enhancement of positive emotional states and reduction of negative emotional states. Moreover, the accuracy of memory-based learning method was almost 70 % percent.
Computers in Biology and Medicine, 2013
Automatic measurement and quantification of blood vessels' features and detection of vessel landm... more Automatic measurement and quantification of blood vessels' features and detection of vessel landmarks are key steps in the computer-aided diagnosis and diseases monitoring. This work proposes a novel and robust method for detecting vessel landmarks, i.e. bifurcation and crossovers, and measurement of different features, i.e. vessel orientation and vessel diameter as well as bifurcation angle, from the detected vessel network using simple and efficient local vessel pattern operator. The proposed method is applied to the publicly available DRIVE, STARE and ARIA databases and compared with existing stateof-the-art approaches. It shows higher accuracy in detection of vessel landmark and estimation of vessel features.
Electroencephalography Feature Enhancement Based on Electrode Activity Ratio for Identification
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...
Neural Computing and Applications, May 24, 2019
Nowadays, digitizer pens have become front end of many digital devices. The increasing use of thi... more Nowadays, digitizer pens have become front end of many digital devices. The increasing use of this technology has necessitated the need for producing pen-based virtual keyboard systems. Despite attempts to create such systems in English, their absence for Persian/Arabic languages is an obvious defect. The goal of this paper is presenting an online continuous Persian/Arabic character recognition method. A character in Persian/Arabic language is made of two types of signs or strokes: main body and delayed strokes (which may be zero or more sign). In this paper, a set of novel and discriminative spatial features are defined for these strokes. These features then are used in a novel algorithm to create a genetic programming-based decision tree called GPDT. The GPDT and spatio-temporal features are utilized by nondeterministic finite automata (NDFA) to recognize group-related strokes and related characters. The reason for using spatio-temporal features is the sameness of the main body of some Persian/Arabic letters (e.g., " ﺡ ، ﺥ ، ﺝ ، ﭺ "). There are also two other issues related to recognizing Persian/Arabic letters: unknown number of delayed stroke segments and the sameness of delayed strokes placement, which are removed by using an NDFA. In fact, after identifying group of main body with the help of GPDT, each recognized stroke makes a move in NDFA to stop in a character state (final state on the end of a path in NDFA). The proposed algorithm recognizes continuous Persian/Arabic letters and digits with a 92.43% accuracy and isolated letters and digits with 97.52% accuracy.
2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), 2020
Peptide-binding proteins prediction is important in understanding biological interaction, protein... more Peptide-binding proteins prediction is important in understanding biological interaction, protein performance analysis, cellular processes, drug design, and even cancer prediction, so using experimental predictive methods, despite their operational capabilities, has limitations such as being costly and need to spend more time, differences between unrecognized protein structures and sequences, so design and development of computational systems for maintenance, optimal models for representing biological knowledge, management and the analysis of big biological data is so important that the authors used machine learning-based techniques such as Support Vector Machine (SVM),Random Forest (RF),Decision Tree (C4.5), Decision Tree (ID3),Gradient Boosting classifiers, which evaluated experimental results to optimize Support Vector Machine(SVM) classifier (Radial Basis Function kernel) with significant evaluation parameters such as accuracy(ACC) is equal to 0.7401 and 0.7599 for 10-fold cross validation and independent test set and also specificity (SPE) is equal to 0.7966 and 0.8088 for 10-fold cross validation and independent test set (respectively) by using various Structure-Based and Sequence-Based features.
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.
The Eyelids Distance Detection in Gray Scale Images
Abstract-in this paper a new method for finding the distance between eyelids, in order to determi... more Abstract-in this paper a new method for finding the distance between eyelids, in order to determine the open or closed state of eye, has been introduced. For this aim, first the gray scale image of eye region is converted into a binary image. Next, a differential variance projection ...
Recently, researchers have shown an increased interest in kinship verification via facial images ... more Recently, researchers have shown an increased interest in kinship verification via facial images in the field of computer vision. The matter of fact is that kinship verification is done according to similarities of parent and child faces. To this end, we need more local features extraction. All the methods reviewed so far, however, suffer the fact that they have divided images into distinct block, to extract more local features. The main problem has two aspects: aimless division and features extraction from unnecessary regions that lead to overlapping, noise and reduction of classification rate. In this paper, at first, the main parts of face such as eyes, nose and mouth are detected along with the whole face image. Then they will be used for feature extraction. In order to reduce feature vectors redundancy, new method of feature selection named as Kinship Feature Selection (KinFS), based on Random Subset Feature Selection (RSFS) algorithm is proposed. This method reduces the redundancy and improves verification rate by selecting effective features. The experiment results show that purposeful feature extraction by proposed KinFS method are efficient in improving kinship verification rate.
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.
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%.
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.
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...
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).
Efficient lossless multi-channel EEG compression based on channel clustering
Biomedical Signal Processing and Control, 2017
Abstract With the growth of telemedicine systems, transferring a large number of medical signals ... more Abstract With the growth of telemedicine systems, transferring a large number of medical signals such as for an EEG is a critical challenge. Intelligent analyzing systems, responsible for analyzing medical signals, are a very important part of any telemedicine system. These systems need data with high quality in order to detect abnormal events and diseases. Lossless compression methods play an important role when coding medical signals for telemedicine systems since the data remains unchanged. Multi-channel EEG signals for medical applications are usually acquired by a number of electrodes placed on different parts of the scalp. According to electrode placements, it is necessary to take into account their multi-channel structure to propose efficient compression methods. This paper uses inter-channel and intra-channel correlations to propose an efficient and simple lossless compression method. In the first stage, a differential pulse code modulation technique is used as a preprocessing step for extracting intra-channel correlation. Subsequently, channels are grouped in different clusters, and the centroid of each cluster is calculated and coded by arithmetic coding. In the second stage, the difference between the centroid and the data of channels in each cluster is calculated and compressed by arithmetic coding. The proposed method is capable of lossless EEG signal compression with a higher compression rate than existing methods.
A Genetic Algorithm-Based Feature Selection for Kinship Verification
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.
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.
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.
ANTSREC: A Semantic Recommender System Based on Ant Colony Meta-Heuristic in Electronic Commerce
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.
Uploads
Papers by FARDIN ABDALI-MOHAMMADI