Neural Networks
Mohammad Karimi Moridani; Atiye Hajiali
Abstract
In recent years, the use of intelligent methods for automatic detection of sleep stages in medical applications to increase diagnostic accuracy and reduce the workload of physicians in analyzing sleep data by visual inspection is one of the important issues. The most important step for the automatic ...
Read More
In recent years, the use of intelligent methods for automatic detection of sleep stages in medical applications to increase diagnostic accuracy and reduce the workload of physicians in analyzing sleep data by visual inspection is one of the important issues. The most important step for the automatic classification of sleep stages is the extraction of useful features. In this paper, an EEG-based algorithm for automatic detection of sleep stages is presented using features extracted from the recurrence plot and artificial neural network. Due to the non-stationary of the EEG signal, the recurrence plot was used in this paper for nonlinear analysis and extraction of signal features. Various extracted features have different numerical ranges. Normalization was performed to prevent the undesirable effects of large values of data. As all normalized features could not correctly classify different stages of sleep, effective features were selected. The results of this paper show the selected features and the Multi-Layer Perceptron (MLP) neural network able to achieve the values of 98.54 ± 1.88%, 99.03 ± 1.43%, and 98.32 ± 2.11%, respectively, for specificity, sensitivity, and accuracy between the two types of sleep, i.e., Non-Rapid Eye Movement (Non-REM) and Rapid Eye Movement (REM). Also, the results show that the selection of Pz-Oz channel compared to Fpz-Cz channel leads us to a higher percentage for the separation of stages I-IV, awake, while the separation of REM stage using Fpz-Cz channel is better. The results show that the proposed method has a higher success rate in classifying sleep stages than previous studies. The proposed method could well identify and distinguish all stages of sleep at an acceptable level. In addition to saving time, automatic analysis of sleep stages can help better and more accurate diagnosis and reduce physicians' workload in analyzing sleep data through visual inspection.
Neural Networks
Soroush Babaee Khobdeh; Mohammad Reza Yamaghani; Siavash Khodaparast Sareshkeh
Abstract
Clustering players based on their abilities, a new perspective and an important opportunity to meet needs that in the light of traditional talent identification and player science, which is held periodically and there is not enough time for them to appear. Early recognition of these abilities is a factor ...
Read More
Clustering players based on their abilities, a new perspective and an important opportunity to meet needs that in the light of traditional talent identification and player science, which is held periodically and there is not enough time for them to appear. Early recognition of these abilities is a factor influencing the success of sports teams. Artificial Neural Network (ANN) is a new method of modelling and prediction. The aim of this study was to cluster basketball players based on their individual abilities. For this purpose, Self-Organizing Map (SOM) Neural Networks (NNs) were used. The data set used by 3000 NBA players for 2011 until 2018 is from the Basketball-Reference[1] site. Each player is assigned 30 attributes to reduce them using the Principal Component Analysis (PCA) method and the features for each player were reduced to 12 samples. In order to implement a SOM of features and functions in MATLAB software 65% of the data were used as the network training phase and the remaining 35% were used to the test phase. 12 players’ features as network input and output 9 clusters resulting from the combination of features. After simulation using SOM, accuracy parameter with the help of this system were obtained above 95%. The result of the study showed that the performance of the SOM in clustering basketball players was higher than the K-Means algorithm. The network implemented in this article has a faster speed in the training process and generalizability than similar cases.
Neural Networks
Mahdieh Jahangiri; Ali Farrokhi; Amir Amirabadi
Abstract
This paper describes a new technique for implementing an Artificial Neural Network (ANN) using Field Programmable Gate Array (FPGA). The goal is design the Low Drop Output (LDO) voltage-regulator circuit with the desired features depending on the application. (The first novelty is designing an LDO with ...
Read More
This paper describes a new technique for implementing an Artificial Neural Network (ANN) using Field Programmable Gate Array (FPGA). The goal is design the Low Drop Output (LDO) voltage-regulator circuit with the desired features depending on the application. (The first novelty is designing an LDO with variable features). Voltage regulators bring voltage changes to a stable and acceptable level, especially for products using portable devices. The fragmentary neural network algorithm is modeled using the Xilinx generator system and it can be implemented in Xilinx FPGA (the second novelty is implanting fragmentary ANN in FPGA for parallel computations and real time design). The neural network is trained using the levenberg-Marquardt algorithm which is the data collected from HSPICE software. In Matlab, the tangent-sigmoid function is used as a neuron activation function, but the block set provided by the Xilinx generator system does not have a tangent-sigmoid operator, so the tan-sigmoid operator is modeled on the Maclaurin expansion (the third novelty is using Maclaurin series for approximation function along with the reduction of connections in the neural network to reduce many blocks in FPGA). In this paper, the similarity of the tangent-sigmoid function produced using Matlab and the approximation of the performance of this function using the Maclaurin series are shown. When the inputs are between -0.5 to +0.5, the simulated results show that the absolute error between the values of tan-sigmoid function based on Matlab and Xilinx System Generator using Maclaurin power series are not more than 0.17%. The performance modeling of the system generator with 0.996515% accuracy of Matlab modeling.
Heuristics and Metaheuristics Algorithms
Hadi Roshan; Masoumeh Afsharinezhad
Abstract
Data analytics allows companies mining the patterns and trends in their customers data to implement more effective market segmentation strategies, then customize promotional offers, allocate marketing resources efficiently, and improve customer relationship management. However the implementation of such ...
Read More
Data analytics allows companies mining the patterns and trends in their customers data to implement more effective market segmentation strategies, then customize promotional offers, allocate marketing resources efficiently, and improve customer relationship management. However the implementation of such strategies often hampered by limited budgets and the ever-changing priorities and goals of marketing campaigns. So, This paper suggests and demonstrates the novel approach dividing a broad target market into subsets of consumers who have common needs, interests, and priorities, and then designing and implementing strategies to target them to achieve profit maximization. Therefore, the aims of this study are twofold, first, is to use historical data (such as purchased items and the associative monetary expenses), the proposed model identifies customer segments based on Firefly Algorithm (FA). Second, is the identification of the most profitable segment according to the RFM model (recency, frequency and monetary). In this article real marketing data are used to illustrate the proposed approach.
