Search

Vipul Vilas Wagh,1 Tanvi Kottat,1 Suchita Agrawal,2 Shruti Purohit,2 Tejaswini Arun Pachpor,3,4 Leelavati Narlikar,5 Vasudeo Paralikar,2 Satyajeet Pramod Khare1 1Symbiosis School of Biological Sciences, Symbiosis International (Deemed University), Pune, MH, India; 2Psychiatry Unit, KEM Hospital Research Centre, Pune, MH, India; 3Department of Biosciences and Technology, School of Science and Environment Studies, Dr. Vishwanath Karad MIT World Peace University, Pune, MH, India; 4Department of Biotechnology, MES Abasaheb Garware College, Pune, MH, India; 5Department of Data Science, Indian Institute of Science Education and Research, Pune, MH, IndiaCorrespondence: Vasudeo Paralikar; Satyajeet Pramod Khare, Email paralikarv2010@gmail.com; satyajeetkhare@gmail.comIntroduction: Stigma contributes to a significant part of the burden of schizophrenia (SCZ), therefore reducing false positives from the diagnosis would be liberating for the individuals with SCZ and desirable for the clinicians. The stigmatization associated with schizophrenia advocates the need for high-precision diagnosis. In this study, we present an ensemble learning-based approach for high-precision diagnosis of SCZ using peripheral blood gene expression profiles.Methodology: The machine learning (ML) models, support vector machines (SVM), and prediction analysis for microarrays (PAM) were developed using differentially expressed genes (DEGs) as features. The SCZ samples were classified based on a voting ensemble classifier of SVM and PAM. Further, microarray-based learning was used to classify RNA sequencing (RNA-Seq) samples from our case-control study (Pune-SCZ) to assess cross-platform compatibility.Results: Ensemble learning using ML models resulted in a significantly higher precision of 80.41% (SD: 0.04) when compared to the individual models (SVM-radial: 71.69%, SD: 0.04 and PAM 77.20%, SD: 0.02). The RNA sequencing samples from our case-control study (Pune-SCZ) resulted in a moderate precision (59.92%, SD: 0.05). The feature genes used for model building were enriched for biological processes such as response to stress, regulation of the immune system, and metabolism of organic nitrogen compounds. The network analysis identified RBX1, CUL4B, DDB1, PRPF19, and COPS4 as hub genes.Conclusion: In summary, this study developed robust models for higher diagnostic precision in psychiatric disorders. Future efforts will be directed towards multi-omic integration and developing “explainable” diagnostic models. Keywords: Schizophrenia, peripheral blood, gene expression, machine learning, ensemble learning

Myocardial infarction (MI) is a serious cardiovascular disease with a high mortality rate worldwide. Early detection and consistent treatment can significantly reduce mortality from cardiovascular diseases. However, there is a need for efficient models that can enable the early detection of heart disease without relying on trained clinical experts. MI studies using phonocardiogram (PCG) signals and implementing ensemble learning models are still relatively scarce, often resulting in poor accuracy and low detection rates. This study aims to implement an ensemble learning model for the classification of MI using PCG signals into different classes. In this stage of research, several classification algorithms, including Random Forest and Logistic Regression, serve as basic models for ensemble learning, utilizing features extracted from audio signals. Evaluation of the model's performance reveals that the stacking model achieves an accuracy of 96%. These results demonstrate that our system can appropriately and accurately classify MI within PCG data. We believe that the findings of this study will enhance the diagnosis and treatment of heart attacks, making them more effective and accurate.

The first step in developing the prevention and safety plan for cities is to identify the existing hazards and crises and to prioritize the risk factors according to historical records and scientific studies to explain the probability of danger. Flood is one of the most high-risk natural hazards that should be given particular attention in crisis management. The study aims to model and predict flood hazard according to the characteristics of Nowshahr port city in Mazandaran province using machine learning models. The criteria and indicators affecting flood hazard, including climate criteria (6-hour rainfall indicator), hydrological criteria (surface runoff height indicators, drainage density, and groundwater depth), topographic criteria (slope and altitude indicators), Soil science criteria (soil type indicator) and land use criteria (land use type indicator) were identified based on the literature review. The indicators were then converted into raster data in the ArcGIS environment and finally standardized by fuzzy method for using in models. K-nearest neighbor models (Fine KNN, Cubic KNN, Cosine KNN, Weighted KNN), decision tree (Fine tree, Medium tree, Coarse tree), ensemble learning (Subspace KNN)) and WLC were used in the present study for flood risk zoning. ROC method was used to validate the models and choose the best one based on assessing the accuracy and area below the diagram of the flood. The layers were prepared in the ArcGIS environment and transferred into MATLAB to perform the modelling process and define the coefficients. The results show that the ensemble learning model with an accuracy of 0.96 and the area below the graph of 0.90 is the best and the WLC model with the accuracy of 0.61 and the area below the graph of 0.62 is the weakest model of flood hazard prediction in Nowshahr. Therefore, the output result of the Ensemble (Subspace KNN) algorithm was chosen to present the final flood risk map.

In this paper, an ensemble of clustering trees (ECTs) is adopted to improve the performance of the Fuzzy Min–Max (FMM) network with individual clustering trees. The key advantage of combining FMM and ECT together is to formulate an accurate and useful learning model that is able to perform online clustering and to explain its predictions. The online clustering capability is inherited from the FMM hyperboxes, while the explanatory capability arises from the underlying decision trees of ECT. Four different mean measures, namely harmonic, geometric, arithmetic, and root mean square, are incorporated into FMM for computing its hyperbox centroids. A series of benchmark and real-world data sets are used for evaluating the FMM-ECT performance. The results are analyzed and compared with those from other models. The outcomes indicate that FMM-ECT is able to achieve comparable clustering performances, with the advantage of providing explanations of its predictions using a decision tree. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) has been widely studied since it can be used for various applications. However, most of FER techniques focus on discriminating typical facial expressions such as six basic facial expressions. Spontaneous facial expressions are not limited to such typical ones because the intensity of a facial expression varies depending on the intensity of an emotion. In order to utilize FER for real-world applications, therefore, it is necessary to discriminate slight difference of facial expressions. In this paper, we propose an effective FER method to recognize spontaneous facial expressions using ensemble learning which combines a number of naive Bayes classifiers. In addition, a method to estimate the intensity of facial expression is also proposed by using the classification results of the classifiers. The effectiveness of these methods are evaluated through an FER experiment and an experiment to estimate the intensity of facial expressions using a data set including spontaneous facial expressions.

The f-divergence, which is defined by using a class of convex functions, is used as a generalized phenotype of discriminant measures between two probability distributions. In this paper, we derive a new class of discriminant measures defined on the set of all positive finite measures using the invariance of the f-divergence. This is a class of discriminant measures different from ones which have often been used. We mention some aspects of its effectiveness concerning the extension of discriminant measures by showing that the proposed class includes measures that facilitate statistical data processing and are suitable for the explicit formulation and analysis of the ensemble learning method. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 88(4): 35–42, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.20128 [ABSTRACT FROM AUTHOR]