International Journal of Advances in Intelligent Informatics
Not a member yet
235 research outputs found
Sort by
Alignment control using visual servoing and mobilenet single-shot multi-box detection (SSD): a review
Full text linkThe concept is highly critical for robotic technologies that rely on visual feedback. In this context, robot systems tend to be unresponsive due to reliance on pre-programmed trajectory and path, meaning the occurrence of a change in the environment or the absence of an object. This review paper aims to provide comprehensive studies on the recent application of visual servoing and DNN. PBVS and Mobilenet-SSD were chosen algorithms for alignment control of the film handler mechanism of the portable x-ray system. It also discussed the theoretical framework features extraction and description, visual servoing, and Mobilenet-SSD. Likewise, the latest applications of visual servoing and DNN was summarized, including the comparison of Mobilenet-SSD with other sophisticated models. As a result of a previous study presented, visual servoing and MobileNet-SSD provide reliable tools and models for manipulating robotics systems, including where occlusion is present. Furthermore, effective alignment control relies significantly on visual servoing and deep neural reliability, shaped by different parameters such as the type of visual servoing, feature extraction and description, and DNNs used to construct a robust state estimator. Therefore, visual servoing and MobileNet-SSD are parameterized concepts that require enhanced optimization to achieve a specific purpose with distinct tools
Covid-19 detection from chest x-ray images: comparison of well-established convolutional neural networks models
Full text linkCoronavirus disease 19 (Covid-19) is a pandemic disease that has already killed hundred thousands of people and infected millions more. At the climax disease Covid-19, this virus will lead to pneumonia and result in a fatality in extreme cases. COVID-19 provides radiological cues that can be easily detected using chest X-rays, which distinguishes it from other types of pneumonic disease. Recently, there are several studies using the CNN model only focused on developing binary classifier that classify between Covid-19 and normal chest X-ray. However, no previous studies have ever made a comparison between the performances of some of the established pre-trained CNN models that involving multi-classes including Covid-19, Pneumonia and Normal chest X-ray. Therefore, this study focused on formulating an automated system to detect Covid-19 from chest X-Ray images by four established and powerful CNN models AlexNet, GoogleNet, ResNet-18 and SqueezeNet and the performance of each of the models were compared. A total of 21,252 chest X-ray images from various sources were pre-processed and trained for the transfer learning-based classification task, which included Covid-19, bacterial pneumonia, viral pneumonia, and normal chest x-ray images. In conclusion, this study revealed that all models successfully classify Covid-19 and other pneumonia at an accuracy of more than 78.5%, and the test results revealed that GoogleNet outperforms other models for achieved accuracy of 91.0%, precision of 85.6%, sensitivity of 85.3%, and F1 score of 85.4%
An approach for linguistic multi-attribute decision making based on linguistic many-valued logic
Full text linkThere are various types of multi-attribute decision-making (MADM) problems in our daily lives and decision-making problems under uncertain environments with vague and imprecise information involved. Therefore, linguistic multi-attribute decision-making problems are an important type studied extensively. Besides, it is easier for decision-makers to use linguistic terms to evaluate/choose among alternatives in real life. Based on the theoretical foundation of the Hedge algebra and linguistic many-valued logic, this study aims to address multi-attribute decision-making problems by linguistic valued qualitative aggregation and reasoning method. In this paper, we construct a finite monotonous Hedge algebra for modeling the linguistic information related to MADM problems and use linguistic many-valued logic for deducing the outcome of decision making. Our method computes directly on linguistic terms without numerical approximation. This method takes advantage of linguistic information processing and shows the benefit of Hedge algebra
Portfolio optimization based on self-organizing maps clustering and genetics algorithm
Full text linkIn this modern era, gaining additional income is necessary to fulfill daily needs since inflation is unavoidable. Investing in stocks can give passive income to help people deal with the increasing prices of necessities. However, selecting stocks and constructing a portfolio is the major problem in investing. This research will illustrate the stock selection method and the optimization method for optimizing the portfolio. Stock selection is carried out by clustering using Self-organizing Maps (SOM). Clustering will show the best stocks formed for a portfolio to be optimized. The best stocks that have the best performance are selected from each cluster for the portfolio. The best performance of the stock can be determined using the Sharpe Ratio. Optimization will be carried out using a Genetic Algorithm. The optimization is carried out using software R i386 3.6.1. The optimization results are then compared to the Markowitz Theory to show which method is better. The expected return on the portfolio generated using Genetic Algorithm and Markowitz Theory are 3.348458 and 3.347559975, respectively. While, the value of the Sharpe Ratio is 0.1393076 and 0.13929785, respectively. Based on the results, the best performance of the portfolio is the portfolio produced using Genetic Algorithm with the greater value of the Sharpe Ratio. Furthermore, the Genetics Algorithm optimization is more optimal than the Markowitz Theory
Prediction of player position for talent identification in association netball: a regression-based approach
Full text linkAmong the challenges in industrial revolutions, 4.0 is managing organizationsรขโฌโข talents, especially to ensure the right person for the position can be selected. This study is set to introduce a predictive approach for talent identification in the sport of netball using individual player qualities in terms of physical fitness, mental capacity, and technical skills. A data mining approach is proposed using three data mining algorithms, which are Decision Tree (DT), Neural Network (NN), and Linear Regressions (LR). All the models are then compared based on the Relative Absolute Error (RAE), Mean Absolute Error (MAE), Relative Square Error (RSE), Root Mean Square Error (RMSE), Coefficient of Determination (R2), and Relative Square Error (RSE). The findings are presented and discussed in light of early talent spotting and selection. Generally, LR has the best performance in terms of MAE and RMSE as it has the lowest values among the three models
Cluster analysis and ensemble transfer learning for COVID-19 classification from computed tomography scans
Full text linkThe paper presents a brief analysis of publications utilizing the public SARS-CoV-2 dataset, consisting of patientsรขโฌโข computer tomography scans captured from Brazil hospitals and an experimental setup addressing the found data challenges. The analysis shows that all protocols, with one exception, suffer from data leakage arising from data organization where the patients and their images are not grouped. Each patient is represented with several scans. It can provide misleading results as data of the same individual may occur in both training and test sets. Furthermore, only one paper proposed ensemble learning utilizing as base models VGG-16, ResNet50, and Xception. Therefore, we proposed and experimented with the following strategy to mitigate the found risks of bias: data standardization and normalization to achieve proper contrast and resolution; k-means and group shuffle split to avoid data leakage; augmentation and ensemble transfer learning to deal with limited sample size and over-fitting. Compared with the earlier proposed ensemble approach, the current one stacks VGG-16, Densenet-201, and Inception v3, achieving higher accuracy (99.3 %), second in the related work, and most significantly, it applies augmentation and clustering analysis to avoid overestimation. In contrast, the paper also presented critical metrics in the medical domain: negative prediction value (99.55%), false positive rate (0.89%), false negative rate (0.42%), and false discovery rate (0.83%). The strategy has two main advantages: reducing data pitfalls and decreasing generalization error. It can serve as a baseline to increase the performance quality and mitigate the risk of bias in the field
Deep reinforcement learning autoencoder with RA-GAN and GAN
Full text linkDeep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them
Gender recognition based fingerprints using dynamic horizontal voting ensemble deep learning
No full textDespite tremendous advancements in gender equality, there are still persistent gender disparities, especially in important human activities. Consequently, gender inequality and related concerns are serious problems in our global society. Major players in the global economy have identified the gender identity system as a crucial stepping stone for bridging the enormous gap in gender-based problems. Extensive research conducted by forensic scientists has uncovered a unique pattern in the fingerprint, and these distinguishing characteristics of fingerprints can be utilized to determine the gender of individuals. Numerous research has revealed various fingerprint-based approaches to gender recognition. This research aims to present a novel dynamic horizontal voting ensemble model with a hybrid Convolutional Neural Network and Long Short Term Memory (CNN-LSTM) deep learning algorithm as the base learner to determine human gender attributes based on fingerprint patterns automatically. More than four thousand Live fingerprint images were acquired and subjected to training, testing, and classification using the proposed model. The results of this study indicated over 99% accuracy in predicting a personรขโฌโขs gender. The proposed model also performed better than other state-of-the-art models, such as ResNet-34, VGG-19, ResNet-50, and EfficientNet-B3, when implemented on the SOCOFing public dataset
The mortality modeling of covid-19 patients using a combined time series model and evolutionary algorithm
Full text linkCOVID-19 pandemics for as long as two years ago since 2019 gives many insights into various aspects, including scientific development. One of them is the fundamental research of computer science. This research aimed to construct the best model of COVID-19 patientsรขโฌโข mortality and obtain less prediction errors. We performed the combination methods of time series, SARIMA, and Evolutionary algorithm, PARCD, to predict male patients who died because of COVID-19 in the USA, containing 1.008 data. So, this research proposed that SARIMA-PARCD has a powerful combination for addressing the complex problem in a dataset. The prediction error of SARIMA-PARCD was compared with other methods, i.e., SARIMA, LSTM, and the combination of SARIMA-LSTM. The result showed that the SARIMA-PARCD has the smallest MSE value of 0.0049. Therefore, the proposed method is competitive to implement in other cases with similar characteristics. This combination is robust for solving linear and non-linear problems
Analysis of color features performance using support vector machine with multi-kernel for batik classification
Full text linkBatik is a sort of cultural heritage fabric that originated in many areas of Indonesia. It can be traced back to many different parts of Indonesia. Each region, particularly Semarang in Central Java, Indonesia, has its Batik design. Unfortunately, due to a lack of knowledge, not all residents can recognize the types of Semarang batik. Therefore, this study proposed an automated method for classifying Semarang batik. Semarang batik was classified into five categories according to this method: Asem Arang, Blekok Warak, Gambang Semarangan, Kembang Sepatu, and Semarangan. It is required to analyze the color features based on the color space to develop discriminative features since color was able to differentiate these batik patterns. Color features were produced based on the RGB, HSV, YIQ, and YCbCr color spaces. Four different kernels were used to feed these features into the Support Vector Machine (SVM) classifier: linear, polynomial, sigmoid, and radial basis functions. The experiment was carried out using a local dataset of 1000 batik images classified into five classes (each class contains 200 images). A cross-validation test with a k-fold value of 10 was performed to analyze the method. In each of the SVM Kernels, the results showed that the proposed method achieved an accuracy value of 100% by utilizing the YIQ color space, which was reliable throughout all the tests