Theme Identification using Machine Learning Techniques

With the abundance of online research platforms, much information presented in PDF files, such as articles and journals, can be obtained easily. In this case, students completing research projects would have many downloaded PDF articles on their laptops. However, identifying the target articles manually within the collection can be tiring as most articles consist of several pages that need to be analyzed. Reading each article to determine if the article relates theme and organizing the articles based on themes is time and energy-consuming. Referring to this problem, a PDF files organizer that implemented a theme identifier is necessary. Thus, work will focus on automatic text classification using the machine learning methods to build a theme identifier employed in the PDF files organizer to classify articles into augmented reality and machine learning. A total of 1000 text documents for both themes were used to build the classification model. Moreover, the pre-preprocessing step for data cleaning and TF-IDF feature extraction for text vectorization and to reduce sparse vectors were performed. 80% of the dataset were used for training, and the remaining were used to validate the trained models. The classification models proposed in this work are Linear SVM and Multinomial Naïve Bayes. The accuracy of the models was evaluated using a confusion matrix. For the Linear SVM model, grid-search optimization was performed to determine the optimal value of the Cost parameter.

Age-Invariant Face Recognition to Aid Visually Impaired People

Este trabalho propõem uma abordagem para auxiliar pessoas com deficiência visual no reconhecimento de pessoas independente da idade. O objetivo é desenvolver um sistema que utilize uma abordagem de reconhecimento facial, com foco na invariância na idade, que retorne bons resultados comparados aos resultados obtidos na revisão da literatura. A abordagem estudada utiliza Redes Neurais Convolucionais profundas CCNs, pré-treinadas pelo conjunto de dados VGGFace2, para extrair descritores de características de imagens de faces e classificar com o algoritmo de classificação Linear SVM. Como pode ser visto no decorrer do trabalho, a abordagem retornou 89,9% de acurácia, utilizando o conjunto de dados FG-NET, com 1002 imagens. E utilizando o conjunto de dados CACD, que contém 163.446 imagens divididas em quatro subconjuntos diferentes, três conjuntos para treino e um para teste, a abordagem retornou 85,2%, 82,4% e 88,2% de acurácia para cada modelo treinado com um conjunto de treinamento diferente.

Non-Destructive Detection of Asymptomatic Ganoderma boninense Infection of Oil Palm Seedlings Using NIR-Hyperspectral Data and Support Vector Machine

Breeding programs to develop planting materials resistant to G. boninense involve a manual census to monitor the progress of the disease development associated with various treatments. It is prone to error due to a lack of experience and subjective judgements. This study focuses on the early detection of G. boninense infection in the oil palm seedlings using near infra-red (NIR)-hyperspectral data and a support vector machine (SVM). The study aims to use a small number of wavelengths by using 5, 4, 3, 2, and 1 band reflectance as datasets. These results were then compared with the results of detection obtained from the vegetation indices developed using spectral reflectance taken from the same hyperspectral sensor. Results indicated a kernel with a simple linear separation between two classes would be more suitable for G. boninense detection compared to the others, both for single-band reflectance and vegetation index datasets. A linear SVM which was developed using a single-band reflectance at 934 nm was identified as the best model of detection since it was not only economical, but also demonstrated a high score of accuracy (94.8%), sensitivity (97.6%), specificity (92.5%), and area under the receiver operating characteristic curve (AUC) (0.95).

Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study

ObjectivesThis study aimed to develop a computed tomography (CT)-based radiomics model to predict central lymph node metastases (CLNM) preoperatively in patients with papillary thyroid carcinoma (PTC).MethodsIn this retrospective study, 678 patients with PTC were enrolled from Yantai Yuhuangding Hot3spital (n=605) and the Affiliated Hospital of Binzhou Medical University (n=73) within August 2010 to December 2020. The patients were randomly divided into a training set (n=423), an internal test set (n=182), and an external test set (n=73). Radiomics features of each patient were extracted from preoperative plain scan and contrast-enhanced CT images (arterial and venous phases). One-way analysis of variance (ANOVA) and least absolute shrinkage and selection operator algorithm were used for feature selection. The K-nearest neighbor, logistics regression, decision tree, linear-support vector machine (linear-SVM), Gaussian-SVM, and polynomial-SVM algorithms were used to establish radiomics models for CLNM prediction. The clinical risk factors were selected by ANOVA and multivariate logistic regression. Incorporated with clinical risk factors, a combined radiomics model was established for the preoperative prediction of CLNM in patients with PTCs. The performance of the combined radiomics model was evaluated using the receiver operating characteristic (ROC) and calibration curves in the training and test sets. The clinical usefulness was evaluated through decision curve analysis (DCA).ResultsA total of 4227 radiomic features were extracted from the CT images of each patient, and 14 non-zero coefficient features associated with CLNM were selected. Four clinical variables (sex, age, tumor diameter, and CT-reported lymph node status) were significantly associated with CLNM. Linear-SVM led to the best prediction model, which incorporated radiomic features and clinical risk factors. Areas under the ROC curves of 0.747 (95% confidence interval [CI] 0.706–0.782), 0.710 (95% CI 0.634–0.786), and 0.764 (95% CI 0.654–0.875) were obtained in the training, internal, and external test sets, respectively. The linear-SVM algorithm also showed better sensitivity (0.702 [95% CI 0.600–0.790] vs. 0.477 [95% CI 0.409–0.545]) and accuracy (0.670 [95% CI 0.600–0.738] vs. 0.642 [95% CI 0.569–0.712]) than an experienced radiologist in the internal test set in the combined radiomics model. The calibration plot reflected a favorable agreement between the actual and estimated probabilities of CLNM. The DCA indicated the clinical usefulness of the combined radiomics model.ConclusionThe combined radiomics model is a non-invasive preoperative tool that incorporates radiomic features and clinical risk factors to predict CLNM in patients with PTC.

An Effective Text Classifier using Machine Learning for Identifying Tweets’ Polarity Concerning Terrorist Connotation

Terrorist groups in the Arab world are using social networking sites like Twitter and Facebook to rapidly spread terror for the past few years. Detection and suspension of such accounts is a way to control the menace to some extent. This research is aimed at building an effective text classifier, using machine learning to identify the polarity of the tweets automatically. Five classifiers were chosen, which are AdB_SAMME, AdB_SAMME.R, Linear SVM, NB, and LR. These classifiers were applied on three features namely S1 (one word, unigram), S2 (word pair, bigram), and S3 (word triplet, trigram). All five classifiers evaluated samples S1, S2, and S3 in 346 preprocessed tweets. Feature extraction process utilized one of the most widely applied weighing schemes tf-idf (term frequency-inverse document frequency).The results were validated by four experts in Arabic language (three teachers and an educational supervisor in Saudi Arabia) through a questionnaire. The study found that the Linear SVM classifier yielded the best results of 99.7 % classification accuracy on S3 among all the other classifiers used. When both classification accuracy and time were considered, the NB classifier demonstrated the performance on S1 with 99.4% accuracy, which was comparable with Linear SVM. The Arab world has faced massive terrorist attacks in the past, and therefore, the research is highly significant and relevant due to its specific focus on detecting terrorism messages in Arabic. The state-of-the-art methods developed so far for tweets classification are mostly focused on analyzing English text, and hence, there was a dire need for devising machine learning algorithms for detecting Arabic terrorism messages. The innovative aspect of the model presented in the current study is that the five best classifiers were selected and applied on three language models S1, S2, and S3. The comparative analysis based on classification accuracy and time constraints proposed the best classifiers for sentiment analysis in the Arabic language.

Audio-Visual Emotion Recognition System using Multi-Modal Features

Due to the highly variant face geometry and appearances, Facial Expression Recognition (FER) is still a challenging problem. CNN can characterize 2-D signals. Therefore, for emotion recognition in a video, the authors propose a feature selection model in AlexNet architecture to extract and filter facial features automatically. Similarly, for emotion recognition in audio, the authors use a deep LSTM-RNN. Finally, they propose a probabilistic model for the fusion of audio and visual models using facial features and speech of a subject. The model combines all the extracted features and use them to train the linear SVM (Support Vector Machine) classifiers. The proposed model outperforms the other existing models and achieves state-of-the-art performance for audio, visual and fusion models. The model classifies the seven known facial expressions, namely anger, happy, surprise, fear, disgust, sad, and neutral on the eNTERFACE’05 dataset with an overall accuracy of 76.61%.

Audio-Visual Emotion Recognition System Using Multi-Modal Features

Due to the highly variant face geometry and appearances, Facial Expression Recognition (FER) is still a challenging problem. CNN can characterize 2-D signals. Therefore, for emotion recognition in a video, the authors propose a feature selection model in AlexNet architecture to extract and filter facial features automatically. Similarly, for emotion recognition in audio, the authors use a deep LSTM-RNN. Finally, they propose a probabilistic model for the fusion of audio and visual models using facial features and speech of a subject. The model combines all the extracted features and use them to train the linear SVM (Support Vector Machine) classifiers. The proposed model outperforms the other existing models and achieves state-of-the-art performance for audio, visual and fusion models. The model classifies the seven known facial expressions, namely anger, happy, surprise, fear, disgust, sad, and neutral on the eNTERFACE’05 dataset with an overall accuracy of 76.61%.

Applying nonlinear measures to the brain rhythms: an effective method for epilepsy diagnosis

Background Epilepsy is a neurological disorder from which almost 50 million people have been suffering. These statistics indicate the importance of epilepsy diagnosis. Electroencephalogram (EEG) signals analysis is one of the most common methods for epilepsy characterization; hence, various strategies were applied to classify epileptic EEGs. Methods In this paper, four different nonlinear features such as Fractal dimensions including Higuchi method (HFD) and Katz method (KFD), Hurst exponent, and L-Z complexity measure were extracted from EEGs and their frequency sub-bands. The features were ranked later by implementing Relieff algorithm. The ranked features were applied sequentially to three different classifiers (MLPNN, Linear SVM, and RBF SVM). Results According to the dataset used for this study, there are five classification problems named ABCD/E, AB/CD/E, A/D/E, A/E, and D/E. In all cases, MLPNN was the most accurate classifier. Its performances for mentioned classification problems were 99.91%, 98.19%, 98.5%, 100% and 99.84%, respectively. Conclusion The results demonstrate that KFD is the highest-ranking feature; In addition, beta and theta sub-bands are the most important frequency bands because, for all cases, the top features were KFDs extracted from beta and theta sub-bands. Moreover, high levels of accuracy have been obtained just by using these two features which reduce the complexity of the classification.

Algorithms for Classification of Signals Derived From Human Brain

Comparison of the Accuracy of different off-line methods for classification Electroencephalograph (EEG) signals, obtained from Brain-Computer Interface (BCI) devices are investigated in this paper. BCI is a technology that allows people to interact directly or indirectly with their environment only by using brain activity. But, the method of signal acquisition is non-invasive, resulting in significant data loss. In addition, the received signals do not contain only useful information. All this requires careful selection of the method for the classification of the received signals. The main purpose of this paper is to provide a fair and extensive comparison of some commonly employed classification methods under the same conditions so that the assessment of different classifiers will be more convictive. In this study, we investigated the accuracy of the classification of the received signals with classifiers based on AdaBoost (AB), Decision Tree (DT), k-Nearest Neighbor (kNN), Gaussian SVM, Linear SVM, Polynomial SVM, Random Forest (RF), Random Forest Regression ( RFR ). We used only basic parameters in the classification, and we did not apply fine optimization of the classification results. The obtained results show suitable algorithms for the classification of EEG signals. This would help young researchers to achieve interesting results in this field faster.