Browsing by Author "Agahian, Saeid"

Now showing 1 - 6 of 6

Application of Grey Wolf Optimizer to Develop New Global GMPE for Estimating Peak Ground Acceleration
(Springer Int Publ Ag, 2023) Ghalehjough, Babak Karimi; Agahian, Saeid
Ground motion prediction equations (GMPEs) are open challenge problems that have been developed since 1964. Parametric and nonparametric methods predict ground motion characteristics such as peak ground acceleration (PGA), velocity, displacements, and spectral accelerations. In the present study, the grey wolf optimization (GWO) algorithm was used to obtain a new and developed GMPE for predicting PGA. Data from recorded earthquakes from all over the world were collected, and after filtering of M-w and distance parameters, close to 2000 data were used for modelling. Three parameters of M-w (4-7.9), epicentral distance (0.25-115 km) and geological conditions (soft soil, stiff soil, rock) were used as input parameters for estimating PGA. Many previous studies classified geological conditions based on shear wave velocity at the top 30 m (Vs30), without taking into account the effect of Vs30 at each group. In this study, the effects of Vs30 were considered separately for each geological group too. Results showed that PGA decreased by increasing Vs30 and moving from soft soil toward rock. Finally, the relationship was compared with the other two relations suggested for the local region and global earthquakes, and despite the simplicity of the suggested relation gained by the GWO method, it estimated PGA in terms of accuracy to a good and acceptable level.
Battle Royale Optimizer for Training Multi-Layer Perceptron
(Springer Heidelberg, 2022) Agahian, Saeid; Akan, Taymaz
Artificial neural network (ANN) is one of the most successful tools in machine learning. The success of ANN mostly depends on its architecture and learning procedure. Multi-layer perceptron (MLP) is a popular form of ANN. Moreover, backpropagation is a well-known gradient-based approach for training MLP. Gradient-based search approaches have a low convergence rate; therefore, they may get stuck in local minima, which may lead to performance degradation. Training the MLP is accomplished based on minimizing the total network error, which can be considered as an optimization problem. Stochastic optimization algorithms are proven to be effective when dealing with such problems. Battle royale optimization (BRO) is a recently proposed population-based metaheuristic algorithm which can be applied to single-objective optimization over continuous problem spaces. The proposed method has been compared with backpropagation (Generalized learning delta rule) and six well-known optimization algorithms on ten classification benchmark datasets. Experiments confirm that, according to error rate, accuracy, and convergence, the proposed approach yields promising results and outperforms its competitors.
Binbro: Binary Battle Royale Optimizer Algorithm
(Pergamon-Elsevier Science Ltd, 2022) Akan (Rahkar Farshi), Taymaz; Agahian, Saeid; Dehkharghani, Rahim
Stochastic methods attempt to solve problems that cannot be solved by deterministic methods with reasonable time complexity. Optimization algorithms benefit from stochastic methods; however, they do not guarantee to obtain the optimal solution. Many optimization algorithms have been proposed for solving problems with continuous nature; nevertheless, they are unable to solve discrete or binary problems. Adaptation and use of continuous optimization algorithms for solving discrete problems have gained growing popularity in recent decades. In this paper, the binary version of a recently proposed optimization algorithm, Battle Royale Optimization, which we named BinBRO, has been proposed. The proposed algorithm has been applied to two benchmark datasets: the uncapacitated facility location problem, and the maximum-cut graph problem, and has been compared with 6 other binary optimization algorithms, namely, Particle Swarm Optimization, different versions of Genetic Algorithm, and different versions of Artificial Bee Colony algorithm. The BinBRO-based algorithms could rank first among those algorithms when applying on all benchmark datasets of both problems, UFLP and Max-Cut.
An Efficient Human Action Recognition Framework with Pose-Based Spatiotemporal Features
(Elsevier - Division Reed Elsevier India Pvt Ltd, 2020) Agahian, Saeid; Negin, Farhood; Kose, Cemal
In the past two decades, human action recognition has been among the most challenging tasks in the field of computer vision. Recently, extracting accurate and cost-efficient skeleton information became available thanks to the cutting edge deep learning algorithms and low-cost depth sensors. In this paper, we propose a novel framework to recognize human actions using 3D skeleton information. The main components of the framework are pose representation and encoding. Assuming that human actions can be represented by spatiotemporal poses, we define a pose descriptor consisting of three elements. The first element contains the normalized coordinates of the raw skeleton joints information. The second element contains the temporal displacement information relative to a predefined temporal offset and the third element keeps the displacement information pertinent to the previous timestamp in the temporal resolution. The final descriptor of the whole sequence is the concatenation of frame-wise descriptors. To avoid the problems regarding high dimensionality, Principal Component Analysis (PCA) is applied on the descriptors. The resulted descriptors are encoded with Fisher Vector (FV) representation before they get trained with an Extreme Learning Machine (ELM). The performance of the proposed framework is evaluated by three public benchmark datasets. The proposed method achieved competitive results compared to the other methods in the literature. (C) 2019 Karabuk University. Publishing services by Elsevier B.V.
A Hybrid Imm-Jpdaf Algorithm for Tracking Multiple Sperm Targets and Motility Analysis
(Springer London Ltd, 2022) Tumuklu Ozyer, Gulsah; Ozyer, Baris; Negin, Farhood; Alarabi, Inas; Agahian, Saeid
Semen analysis has received a lot of attention because of its important role in determining infertility in men. It involves several factors, the most important of which are sperm morphology, sperm concentration, and sperm motility. In addition, measurements of sperm cell mobility reflect important parameters in medical diagnosis. As computer-assisted semen analysis systems are very expensive and not prolific, especially in small medical laboratories, semen analysis is often done manually. This is a time-consuming and costly process. Therefore, we have developed an automated system that evaluates sperm motility parameters which can be of great help to clinicians in achieving more accurate results at a lower cost and time. The system tracks the movement of most spermatozoa cells in a semen sample taken from a microscope and then carefully measures all the parameters related to sperm movement to determine the fertility or infertility rate of the subject. Detecting large numbers of sperm cells is challenging because there are a large number of colliding targets that cause false alarms. In this work, the background subtraction method is used to determine the sperms within the video frames, and the joint probabilistic data association filter algorithm is used to estimate the sperm trajectory and to associate different tracks. Since the sperm represents maneuvering movements, the interacting multiple models technique was used along with the JPDAF algorithms to obtain more accurate results. Our evaluations on real and synthetic data reveal the superiority of our method over previous work in sperm cell tracking.
Vision-Assisted Recognition of Stereotype Behaviors for Early Diagnosis of Autism Spectrum Disorders
(Elsevier, 2021) Negin, Farhood; Ozyer, Baris; Agahian, Saeid; Kacdioglu, Sibel; Ozyer, Gulsah Tumuklu
Medical diagnosis supported by computer-assisted technologies is getting more popularity and acceptance among medical society. In this paper, we propose a non-intrusive vision-assisted method based on human action recognition to facilitate the diagnosis of Autism Spectrum Disorder (ASD). We collected a novel and comprehensive video dataset f the most distinctive Stereotype actions of this disorder with the assistance of professional clinicians. Several frameworks as a function of different input modalities were developed and used to produce extensive baseline results. Various local descriptors, which are commonly used within the Bag-of-Visual-Words approach, were tested with Multi-layer Perceptron (MLP), Gaussian Naive Bayes (GNB), and Support Vector Machines (SVM) classifiers for recognizing ASD associated behaviors. Additionally, we developed a framework that first receives articulated pose-based skeleton sequences as input and follows an LSTM network to learn the temporal evolution of the poses. Finally, obtained results were compared with two fine-tuned deep neural networks: ConvLSTM and 3DCNN. The results revealed that the Histogram of Optical Flow (HOF) descriptor achieves the best results when used with MLP classifier. The promising baseline results also confirmed that an action-recognition-based system can be potentially used to assist clinicians to provide a reliable, accurate, and timely diagnosis of ASD disorder.& nbsp; (c) 2021 Elsevier B.V. All rights reserved.