International Journal of Advances in Intelligent Informatics
Not a member yet
235 research outputs found
Sort by
The improvement of uncertainty measurements accuracy in sensor networks based on fuzzy dempster-shafer theory
Full text linkThreat Assessment is one of the most important components in combat management systems. However, uncertainty is one of the problems that occur in the input data of these systems that have been provided using several sensors in sensor networks. In literature, there are some theories that state and model uncertainty in the information. One of the new methods is the Fuzzy Dempster-Shafer Theory. In this paper, a model-based uncertainty is presented in the air defense system based on the Fuzzy Dempster-Shafer Theory to measure uncertainty and its accuracy. This model uses the two concepts naming of the Fuzzy Sets Theory, and the Dempster-Shafer Theory. The input parameters to sensors are fuzzy membership functions, and the basic probability assignment values are earned from the Dempster-Shafer Theory. Therefore, in this paper, the combination of two methods has been used to calculate uncertainty in the air defense system. By using these methods and the output of the Dempster-Shafer theory are calculated and presented the uncertainty diagrams. The advantage of the combination of two theories is the better modeling of uncertainties. This makes that the output of the air defense system is more reliable and accurate. In this method, the air defense system’s total uncertainty is measured using the best uncertainty measure based on the Fuzzy Dempster-Shafer Theory. The simulation results show that this new method has increased the accuracy to 97% that is more computational toward other theories. This matter significantly increases the computational accuracy of the air defense system in targets threat assessment
Classification of wood defect images using local binary pattern variants
Full text linkThis paper presents an analysis of the statistical texture representation of the Local Binary Pattern (LBP) variants in the classification of wood defect images. The basic and variants of the LBP feature set that was constructed from a stage of feature extraction processes with the Basic LBP, Rotation Invariant LBP, Uniform LBP, and Rotation Invariant Uniform LBP. For significantly discriminating, the wood defect classes were further evaluated with the use of different classifiers. By comparing the results of the classification performances that had been conducted across the multiple wood species, the Uniform LBP was found to have demonstrated the highest accuracy level in the classification of the wood defects
Predicting breast cancer recurrence using principal component analysis as feature extraction: an unbiased comparative analysis
Full text linkBreast cancer recurrence is among the most noteworthy fears faced by women. Nevertheless, with modern innovations in data mining technology, early recurrence prediction can help relieve these fears. Although medical information is typically complicated, and simplifying searches to the most relevant input is challenging, new sophisticated data mining techniques promise accurate predictions from high-dimensional data. In this study, the performances of three established data mining algorithms: Naïve Bayes (NB), k-nearest neighbor (KNN), and fast decision tree (REPTree), adopting the feature extraction algorithm, principal component analysis (PCA), for predicting breast cancer recurrence were contrasted. The comparison was conducted between models built in the absence and presence of PCA. The results showed that KNN produced better prediction without PCA (F-measure = 72.1%), whereas the other two techniques: NB and REPTree, improved when used with PCA (F-measure = 76.1% and 72.8%, respectively). This study can benefit the healthcare industry in assisting physicians in predicting breast cancer recurrence precisely
Self-supervised pre-training of CNNs for flatness defect classification in the steelworks industry
Full text linkClassification of surface defects in the steelworks industry plays a significant role in guaranteeing the quality of the products. From an industrial point of view, a serious concern is represented by the hot-rolled products shape defects and particularly those concerning the strip flatness. Flatness defects are typically divided into four sub-classes depending on which part of the strip is affected and the corresponding shape. In the context of this research, the primary objective is evaluating the improvements of exploiting the self-supervised learning paradigm for defects classification, taking advantage of unlabelled, real, steel strip flatness maps. Different pre-training methods are compared, as well as architectures, taking advantage of well-established neural subnetworks, such as Residual and Inception modules. A systematic approach in evaluating the different performances guarantees a formal verification of the self-supervised pre-training paradigms evaluated hereafter. In particular, pre-training neural networks with the EgoMotion meta-algorithm shows classification improvements over the AutoEncoder technique, which in turn is better performing than a Glorot weight initialization
A new family of kernels from the beta polynomial kernels with applications in density estimation
Full text linkOne of the fundamental data analytics tools in statistical estimation is the non-parametric kernel method that involves probability estimates production. The method uses the observations to obtain useful statistical information to aid the practicing statistician in decision making and further statistical investigations. The kernel techniques primarily examine essential characteristics in a data set, and this research aims to introduce new kernel functions that can easily detect inherent properties in any given observations. However, accurate application of kernel estimator as data analytics apparatus requires the kernel function and smoothing parameter that regulates the level of smoothness applied to the estimates. A plethora of kernel functions of different families and smoothing parameter selectors exist in the literature, but no one method is universally acceptable in all situations. Hence, more kernel functions with smoothing parameter selectors have been propounded customarily in density estimation. This article proposes a distinct kernel family from the beta polynomial kernel family using the exponential progression in its derivation. The newly proposed kernel family was evaluated with simulated and life data. The outcomes clearly indicated that this kernel family could compete favorably well with other kernel families in density estimation. A further comparison of numerical results of the new family and the existing beta family revealed that the new family outperformed the classical beta kernel family with simulation and real data examples with the aid of asymptotic mean integrated squared error (AMISE) as criterion function. The information obtained from the data analysis of this research could be used for decision making in an organization, especially when human and material resources are to be considered. In addition, Kernel functions are vital tools for data analysis and data visualization; hence the newly proposed functions are vital exploratory tools
Feature selection to increase the random forest method performance on high dimensional data
Full text linkRandom Forest is a supervised classification method based on bagging (Bootstrap aggregating) Breiman and random selection of features. The choice of features randomly assigned to the Random Forest makes it possible that the selected feature is not necessarily informative. So it is necessary to select features in the Random Forest. The purpose of choosing this feature is to select an optimal subset of features that contain valuable information in the hope of accelerating the performance of the Random Forest method. Mainly for the execution of high-dimensional datasets such as the Parkinson, CNAE-9, and Urban Land Cover dataset. The feature selection is done using the Correlation-Based Feature Selection method, using the BestFirst method. Tests were carried out 30 times using the K-Cross Fold Validation value of 10 and dividing the dataset into 70% training and 30% testing. The experiments using the Parkinson dataset obtained a time difference of 0.27 and 0.28 seconds faster than using the Random Forest method without feature selection. Likewise, the trials in the Urban Land Cover dataset had 0.04 and 0.03 seconds, while for the CNAE-9 dataset, the difference time was 2.23 and 2.81 faster than using the Random Forest method without feature selection. These experiments showed that the Random Forest processes are faster when using the first feature selection. Likewise, the accuracy value increased in the two previous experiments, while only the CNAE-9 dataset experiment gets a lower accuracy. This research’s benefits is by first performing feature selection steps using the Correlation-Base Feature Selection method can increase the speed of performance and accuracy of the Random Forest method on high-dimensional data
Estimating the function of oscillatory components in SSA-based forecasting model
Full text linkThe study of SSA-based forecasting model is always interesting due to its capability in modeling trend and multiple seasonal time series. The aim of this study is to propose an iterative ordinary least square (OLS) for estimating the oscillatory with time-varying amplitude model that usually found in SSA decomposition. We compare the results with those obtained by nonlinear least square based on Levenberg Marquardt (NLM) method. A simulation study based on the time series data which has a linear amplitude modulated sinusoid component is conducted to investigate the error of estimated parameters of the model obtained by the proposed method. A real data series was also considered for the application example. The results show that in terms of forecasting accuracy, the SSA-based model where the oscillatory components are obtained by iterative OLS is nearly the same with that is obtained by the NLM method
Evolutionary deep belief networks with bootstrap sampling for imbalanced class datasets
Full text linkImbalanced class data is a common issue faced in classification tasks. Deep Belief Networks (DBN) is a promising deep learning algorithm when learning from complex feature input. However, when handling imbalanced class data, DBN encounters low performance as other machine learning algorithms. In this paper, the genetic algorithm (GA) and bootstrap sampling are incorporated into DBN to lessen the drawbacks occurs when imbalanced class datasets are used. The performance of the proposed algorithm is compared with DBN and is evaluated using performance metrics. The results showed that there is an improvement in performance when Evolutionary DBN with bootstrap sampling is used to handle imbalanced class datasets
Improving stroke diagnosis accuracy using hyperparameter optimized deep learning
Full text linkStroke may cause death for anyone, including youngsters. One of the early stroke detection techniques is a Computerized Tomography (CT) scan. This research aimed to optimize hyperparameter in Deep Learning, Random Search and Bayesian Optimization for determining the right hyperparameter. The CT scan images were processed by scaling, grayscale, smoothing, thresholding, and morphological operation. Then, the images feature was extracted by the Gray Level Co-occurrence Matrix (GLCM). This research was performed a feature selection to select relevant features for reducing computing expenses, while deep learning based on hyperparameter setting was used to the data classification process. The experiment results showed that the Random Search had the best accuracy, while Bayesian Optimization excelled in optimization time
Fast pornographic image recognition using compact holistic features and multi-layer neural network
Full text linkThe paper presents an alternative fast pornographic image recognition using compact holistic features and multi-layer neural network (MNN). The compact holistic features of pornographic images, which are invariant features against pose and scale, is extracted by shape and frequency analysis on pornographic images under skin region of interests (ROIs). The main objective of this work is to design pornographic recognition scheme which not only can improve performances of existing methods (i.e., methods based on skin probability, scale invariant feature transform, eigenporn, and Multilayer-Perceptron and Neuro-Fuzzy (MP-NF)) but also can works fast for recognition. The experimental outcome display that our proposed system can improve 0.3% of accuracy and reduce 6.60% the false negative rate (FNR) of the best existing method (skin probability and eigenporn on YCbCr, SEP), respectively. Additionally, our proposed method also provides almost similar robust performances to the MP-NF on large size dataset. However, our proposed method needs short recognition time by about 0.021 seconds per image for both tested datasets