Computational Intelligence and Neuroscience

This study presents a reliable method for predicting gas concentration and implementing prewarning analysis. Gas monitoring data are decomposed into intrinsic mode functions (IMFs) with different time scales by using empirical mode decomposition (EMD), which represents the intrinsic features of gas concentration on different time scales. The prediction accuracy is evaluated by the prediction effectiveness, and the IMF phase space parameters and the Gaussian process regression (GPR) hyperparameters are dynamically adjusted to achieve adaptive prediction. Combined with singular value decomposition (SVD) to extract the intrinsic features of gas monitoring data, a prediction and prewarning model is established. The case study shows that the prediction accuracy of the adaptive model is significantly higher than that of direct GPR prediction and that it solves the problem of low prediction accuracy at mutational points in gas concentration time series. The degree of influence of the production process on the variation in gas concentration is quantitatively determined to improve the reliability of prewarning applications.

Multikernel clustering achieves clustering of linearly inseparable data by applying a kernel method to samples in multiple views. A localized SimpleMKKM (LI-SimpleMKKM) algorithm has recently been proposed to perform min-max optimization in multikernel clustering where each instance is only required to be aligned with a certain proportion of the relatively close samples. The method has improved the reliability of clustering by focusing on the more closely paired samples and dropping the more distant ones. Although LI-SimpleMKKM achieves remarkable success in a wide range of applications, the method keeps the sum of the kernel weights unchanged. Thus, it restricts kernel weights and does not consider the correlation between the kernel matrices, especially between paired instances. To overcome such limitations, we propose adding a matrix-induced regularization to localized SimpleMKKM (LI-SimpleMKKM-MR). Our approach addresses the kernel weight restrictions with the regularization term and enhances the complementarity between base kernels. Thus, it does not limit kernel weights and fully considers the correlation between paired instances. Extensive experiments on several publicly available multikernel datasets show that our method performs better than its counterparts.

Osteoporosis is a significant global health concern that can be difficult to detect early due to a lack of symptoms. At present, the examination of osteoporosis depends mainly on methods containing dual-energy X-ray, quantitative CT, etc., which are high costs in terms of equipment and human time. Therefore, a more efficient and economical method is urgently needed for diagnosing osteoporosis. With the development of deep learning, automatic diagnosis models for various diseases have been proposed. However, the establishment of these models generally requires images with only lesion areas, and annotating the lesion areas is time-consuming. To address this challenge, we propose a joint learning framework for osteoporosis diagnosis that combines localization, segmentation, and classification to enhance diagnostic accuracy. Our method includes a boundary heat map regression branch for thinning segmentation and a gated convolution module for adjusting context features in the classification module. We also integrate segmentation and classification features and propose a feature fusion module to adjust the weight of different levels of vertebrae. We trained our model on a self-built dataset and achieved an overall accuracy rate of 93.3% for the three label categories (normal, osteopenia, and osteoporosis) in the testing datasets. The area under the curve for the normal category is 0.973; for the osteopenia category, it is 0.965; and for the osteoporosis category, it is 0.985. Our method provides a promising alternative for the diagnosis of osteoporosis at present.

As part of continuous process improvements to teaching and learning, the management of tertiary institutions requests students to review modules towards the end of each semester. These reviews capture students’ perceptions about various aspects of their learning experience. Considering the large volume of textual feedback, it is not feasible to manually analyze all the comments, hence the need for automated approaches. This study presents a framework for analyzing students’ qualitative reviews. The framework consists of four distinct components: aspect-term extraction, aspect-category identification, sentiment polarity determination, and grades’ prediction. We evaluated the framework with the dataset from the Lilongwe University of Agriculture and Natural Resources (LUANAR). A sample size of 1,111 reviews was used. A microaverage F1-score of 0.67 was achieved using Bi- LSTM-CRF and BIO tagging scheme for aspect-term extraction. Twelve aspect categories were then defined for the education domain and four variants of RNNs models (GRU, LSTM, Bi-LSTM, and Bi-GRU) were compared. A Bi-GRU model was developed for sentiment polarity determination and the model achieved a weighted F1-score of 0.96 for sentiment analysis. Finally, a Bi-LSTM-ANN model which combined textual and numerical features was implemented to predict students’ grades based on the reviews. A weighted F1-score of 0.59 was obtained, and out of 29 students with “F” grade, 20 were correctly identified by the model.

To diagnose an illness in healthcare, doctors typically conduct physical exams and review the patient’s medical history, followed by diagnostic tests and procedures to determine the underlying cause of symptoms. Chronic kidney disease (CKD) is currently the leading cause of death, with a rapidly increasing number of patients, resulting in 1.7 million deaths annually. While various diagnostic methods are available, this study utilizes machine learning due to its high accuracy. In this study, we have used the hybrid technique to build our proposed model. In our proposed model, we have used the Pearson correlation for feature selection. In the first step, the best models were selected on the basis of critical literature analysis. In the second step, the combination of these models is used in our proposed hybrid model. Gaussian Naïve Bayes, gradient boosting, and decision tree classifier are used as a base classifier, and the random forest classifier is used as a meta-classifier in the proposed hybrid model. The objective of this study is to evaluate the best machine learning classification techniques and identify the best-used machine learning classifier in terms of accuracy. This provides a solution for overfitting and achieves the highest accuracy. It also highlights some of the challenges that affect the result of better performance. In this study, we critically review the existing available machine learning classification techniques. We evaluate in terms of accuracy, and a comprehensive analytical evaluation of the related work is presented with a tabular system. In implementation, we have used the top four models and built a hybrid model using UCI chronic kidney disease dataset for prediction. Gradient boosting achieves around 99% accuracy, random forest achieves 98%, decision tree classifier achieves 96% accuracy, and our proposed hybrid model performs best getting 100% accuracy on the same dataset. Some of the main machine learning algorithms used to predict the occurrence of CKD are Naïve Bayes, decision tree, K-nearest neighbor, random forest, support vector machine, LDA, GB, and neural network. In this study, we apply GB (gradient boosting), Gaussian Naïve Bayes, and decision tree along with random forest on the same set of features and compare the accuracy score.

Machine learning algorithms are among the driving forces towards the success of intelligent road network systems design. Such algorithms allow for the design of systems that provide safe road usage, efficient infrastructure, and traffic flow management. One such application of machine learning in intelligent road networks is classifying different road network types that provide useful traffic information to road users. We propose a deep autoencoder model for representation learning to classify road network types. Each road segment node is represented as a feature vector. Unlike existing graph embedding methods that perform road segment embedding using the neighbouring road segments, the proposed method performs embedding directly on the road segment vectors. The proposed method performs embedding directly on the road segment vectors. Comparison with state-of-the-art graph embedding methods show that the proposed method outperforms graph convolution networks, GraphSAGE-MEAN, graph attention networks, and graph isomorphism network methods, and it achieves similar performance to GraphSAGE-MAXPOOL.