Faculty Publications

Now showing 1 - 3 of 3

Machine learning-based detection and classification of lung cancer
(Elsevier, 2022) Dodia, S.; Annappa, A.
Cancer is termed to be one of the life-threatening diseases in the world. Among various types of cancer, the highest mortality and morbidity rate recorded is from lung cancer. Computer-aided diagnosis (CAD) systems are used to identify lung cancer nodules. The development of reliable automated algorithms is important to provide doctors with a second opinion. A lung cancer diagnosis is performed in two steps: lung cancer nodule detection and classification. In nodule detection, from a given computed tomography (CT) scan, the nodules and nonnodules are identified. Once the nodules and nonnodules are identified, the next step is to classify the detected nodules as cancerous and noncancerous. This work explores various machine learning classifiers for lung cancer classification. A majority voting scheme is used to classify nodules. An in-depth analysis of different machine learning algorithms’ performance is presented in this work. © 2023 Elsevier Inc. All rights reserved.
Real-time big data analytics framework with data blending approach for multiple data sources in smart city applications
(West University of Timisoara, 2020) Manjunatha, S.; Annappa, A.
Advancement in Information Communication Technology (ICT) and the Internet of Things (IoT) has to lead to the continuous generation of a large amount of data. Smart city projects are being implemented in various parts of the world where analysis of public data helps in providing a better quality of life. Data analytics plays a vital role in many such data-driven applications. Real-time analytics for finding valuable insights at the right time using smart city data is crucial in making appropriate decisions for city administration. It is essential to use multiple data sources as input for the analysis to achieve better and more accurate data-driven solutions. It helps in finding more accurate solutions and making appropriate decisions. Public safety is one of the major concerns in any smart city project in which real-time analytics is much useful in the early detection of valuable data patterns. It is crucial to find early predictions of crime-related incidents and generating emergency alerts for making appropriate decisions to provide security to the people and safety of the city infrastructure. This paper discusses the proposed real-time big data analytics framework with data blending approach using multiple data sources for smart city applications. Analytics using multiple data sources for a specific data-driven solution helps in finding more data patterns, which in turn increases the accuracy of analytics results. The data preprocessing phase is a challenging task in data analytics when data being ingested continuously in real-time into the analytics system. The proposed system helps in the preprocessing of real-time data with data blending of multiple data sources used in the analytics. The proposed framework is beneficial when data from multiple sources are ingested in real-time as input data and is also flexible to use any additional data source of interest. The experimental work carried out with the proposed framework using multiple data sources to find the crime-related insights in real-time helps the public safety solutions in the smart city. The experimental outcome shows that there is a significant increase in the number of identified useful data patterns as the number of data sources increases. A real-time based emergency alert system to help the public safety solution is implemented using a machine learning-based classification algorithm with the proposed framework. The experiment is carried out with different classification algorithms, and the results show that Naive Bayes classification performs better in generating emergency alerts. © 2020 SCPE.
Machine Learning-Based Identification of Colon Cancer Candidate Diagnostics Genes
(MDPI, 2022) Koppad, S.; Annappa, A.; Nash, K.; Gkoutos, G.V.; Acharjee, A.
Background: Colorectal cancer (CRC) is the third leading cause of cancer-related death and the fourth most commonly diagnosed cancer worldwide. Due to a lack of diagnostic biomarkers and understanding of the underlying molecular mechanisms, CRC’s mortality rate continues to grow. CRC occurrence and progression are dynamic processes. The expression levels of specific molecules vary at various stages of CRC, rendering its early detection and diagnosis challenging and the need for identifying accurate and meaningful CRC biomarkers more pressing. The advances in high-throughput sequencing technologies have been used to explore novel gene expression, targeted treatments, and colon cancer pathogenesis. Such approaches are routinely being applied and result in large datasets whose analysis is increasingly becoming dependent on machine learning (ML) algorithms that have been demonstrated to be computationally efficient platforms for the identification of variables across such high-dimensional datasets. Methods: We developed a novel ML-based experimental design to study CRC gene associations. Six different machine learning methods were employed as classifiers to identify genes that can be used as diagnostics for CRC using gene expression and clinical datasets. The accuracy, sensitivity, specificity, F1 score, and area under receiver operating characteristic (AUROC) curve were derived to explore the differentially expressed genes (DEGs) for CRC diagnosis. Gene ontology enrichment analyses of these DEGs were performed and predicted gene signatures were linked with miRNAs. Results: We evaluated six machine learning classification methods (Adaboost, ExtraTrees, logistic regression, naïve Bayes classifier, random forest, and XGBoost) across different combinations of training and test datasets over GEO datasets. The accuracy and the AUROC of each combination of training and test data with different algorithms were used as comparison metrics. Random forest (RF) models consistently performed better than other models. In total, 34 genes were identified and used for pathway and gene set enrichment analysis. Further mapping of the 34 genes with miRNA identified interesting miRNA hubs genes. Conclusions: We identified 34 genes with high accuracy that can be used as a diagnostics panel for CRC. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results