Platform KNIME Research Articles

Forecasting urban forest recreation areas in Turkey using machine learning methods

Recreation is the process of revitalizing and renewing human existence through optional activities, serving as a broad description. It has prominently arisen as a reaction to personal requirements for stress reduction, especially in developed urban areas. Engaging in this recreational activity provides a way to utilize one's spare time, providing refreshment for both the physical and mental aspects, whether done alone or with others, in countryside or city environments. Urban forests are important leisure places within city environments. An expanded presence of urban forest places can greatly enhance the general well-being of society. The estimation of urban forest areas in the future may receive increased attention, leading to measures to extend current areas or prepare for future activities and services. We utilized official statistics from the years 2013 to 2021, sourced from the Republic of Turkey official website. Ministry of Agriculture and Forestry's General Directorate of Forestry. We used statistics that contained information about urban forests, classified as Type D recreational areas, to create a dataset. We performed provincial-level area projections for the year 2021. Using the KNIME platform, we used three different analysis techniques: linear regression analysis, gradient-boosted regression trees and artificial neural networks. It is seen that the results of linear regression and artificial neural networks are close to each other and give good results. The peak performance was attained using artificial neural networks, resulting in an R2 score of 0.99. This study differs from other similar projects by concentrating on calculating urban forest recreational spaces per province throughout Turkey, using data provided by government agencies. The accomplishments highlight the ability to make reliable predictions about future forest resources by using analogous forecasts in the upcoming years.

Predicting Peptide Permeability Across Diverse Barriers: A Systematic Investigation.

Peptide-based therapeutics hold immense promise for the treatment of various diseases. However, their effectiveness is often hampered by poor cell membrane permeability, hindering targeted intracellular delivery and oral drug development. This study addressed this challenge by introducing a novel graph neural network (GNN) framework and advanced machine learning algorithms to build predictive models for peptide permeability. Our models offer systematic evaluation across diverse peptides (natural, modified, linear and cyclic) and cell lines [Caco-2, Ralph Russ canine kidney (RRCK) and parallel artificial membrane permeability assay (PAMPA)]. The predictive models for linear and cyclic peptides in Caco-2 and RRCK cell lines were constructed for the first time, with an impressive coefficient of determination (R2) of 0.708, 0.484, 0.553, and 0.528 in the test set, respectively. Notably, the GNN framework behaved better in permeability prediction with larger data sets and improved the accuracy of cyclic peptide prediction in the PAMPA cell line. The R2 increased by about 0.32 compared with the reported models. Furthermore, the important molecular structural features that contribute to good permeability were interpreted; the influence of cell lines, peptide modification, and cyclization on permeability were successfully revealed. To facilitate broader use, we deployed these models on the user-friendly KNIME platform (https://github.com/ifyoungnet/PharmPapp). This work provides a rapid and reliable strategy for systematically assessing peptide permeability, aiding researchers in drug delivery optimization, peptide preselection during drug discovery, and potentially the design of targeted peptide-based materials.

ENHANCING IIOT SECURITY WITH MACHINE LEARNING AND DEEP LEARNING FOR INTRUSION DETECTION

The rapid growth of the Internet of Things (IoT) and digital industrial devices has significantly impacted various aspects of life, underscoring the importance of the Industrial Internet of Things (IIoT). Given its importance in industrial contexts that affect human life, the IIoT represents a key subset of the broader IoT landscape. Due to the proliferation of sensors in smart devices, which are viewed as points of contact, as the gathering of data and information regarding the IIoT systems and devices operating on the IoT, there is an urgent requirement for developing effective security methods to counter such threats as well as protecting IIoT systems. In this study, we develop and evaluate a well-optimized intrusion detection system (IDS) based on deep learning (DL) and machine learning (ML) techniques to enhance IIoT security. Leveraging the Edge-IIoTset dataset, specifically designed for IIoT cybersecurity evaluations, we focus on detecting and mitigating 14 distinct attack types targeting IIoT and IoT protocols. These attacks are categorized into five threat groups: information collection, malware, DDoS, man-in-the-middle attacks, and injection attacks. We conducted experiments using machine learning algorithms (k-nearest neighbors, decision tree) and a neural network on the KNIME platform, achieving a remarkable 100% accuracy with the decision tree model. This high accuracy demonstrates the effectiveness of our approach in protecting industrial IoT networks.

KNIME workflows for applications in medicinal and computational chemistry

Artificial intelligence (AI) has huge potential to accelerate drug discovery, but challenges remain in implementing AI algorithms that can be used by the broad scientific community. Identification of molecular features and their subsequent use in training of machine learning models may permit prediction of new molecules with enhanced properties. Predictive modeling is particularly applicable to analysis of structure-activity relationships (SARs) and would be a useful tool in the hands of laboratory medicinal chemists. This requires a software platform that is chemically intuitive while providing the user with access to AI methods. The KNIME platform provides such an environment through inclusion of broad chemical toolsets and a user-friendly approach for utilization of machine learning for analysis of SAR data. Here, we illustrate use of KNIME for this purpose, with a focus on discovery of features of highly potent tau inhibitors from a series of structurally diverse polyphenols. Workflows are described that enable implementation of AI tools in KNIME for diverse SAR projects.

Abstract 4937: Potential therapeutic targets with anti-inflammatory activity spectrum(COX-2/PGE2) of compounds associated with anti-cancer activityagainst oral and colorectal cancers

Abstract Introduction: COX-2 and PGE2 are prevalent inflammatory cytokines that exert influence on several cancer-related pathways throughout the gastrointestinal tract, spanning from oral cancers to colorectal cancers. One of the tactics being developed for the treatment of oral and colorectal malignancies is the identification of drugs that can selectively target receptors associated with COX-2 and PGE2. Materials and Methods: The objective was to identify potential therapeutic targets for oral cancer and colorectal cancer, specifically focusing on drugs that act as inhibitors or antagonists of the COX2/PGE2 pathway and its related receptor. A method for systematic data mining was created with a total of 32 targets associated with the COX-2/PGE2 pathway which were identified using the KEGG database. These targets were shown to be linked to both the oral cancer pathway and the colorectal cancer pathway. The compounds of interest were obtained from the Chembl25 database and their similarity was assessed using the Tanimoto similarity index, which was generated based on the Morgan fingerprints. The study employed molecular docking techniques to examine the interaction between the chosen drugs and the anticipated targets. A systematic data mining approach and computational methodology were devised utilizing the KNIME platform. Results: A total of 16,900 compounds were extracted for a set of 32 targets. Following the implementation of rule-based filters, the number of compounds was reduced to 13,800. The compounds that have a similarity index greater than 0.7 were chosen for inclusion in final analysis. Among various targets examined, empirical evidence was found to support the inhibition of expected target for PI-3 kinase-mTOR, GSK-3CD1, GSK3-AKT and PI3kinase-AKT pair. However, no evidence was found to support the inhibition of GSK3-Ikappa B-kinase. In order to examine the likelihood of the compound's interaction with anticipated target, molecular docking was employed to explore the interaction of one inhibitor compound for each pair. This investigation was conducted in contrast to the existing inhibitor compound and the subsequent findings were analyzed and discussed. Conclusion: The implemented data mining technique has demonstrated a notable decrease in the duration needed for comparable investigations, enabling the execution of experiments including numerous targets and a substantial number of ligands within a cumulative timeframe of 30 minutes. The findings of this study have the potential to be utilized in the identification of targets and the discovery of lead compounds for the purpose of managing oral as well as colorectal malignancies. Citation Format: Saravanan Sampoornam Pape. Potential therapeutic targets with anti-inflammatory activity spectrum(COX-2/PGE2) of compounds associated with anti-cancer activityagainst oral and colorectal cancers [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4937.

Analyzing credit card fraud cases with supervised machine learning methods: logistic regression and Naive Bayes

Frauds involving credit cards are simple and effortless to target. With the rise of online payment credit cards have had a huge role in our daily life and economy for the past two decades and it is an important task for companies to identify fraud and non-fraud transactions. As the number of credit cards grows every day and the volume of transactions increases quickly in tandem, fraudsters who wish to exploit this market for illegitimate gains have come to light. Nowadays, it’s quite easy to access anyone’s credit card information, which makes it simpler for card fraudsters to do their crimes. Thanks to advances in technology, it is now possible to determine whether information gained with malicious intent has been used by looking at the costs and time involved in altering account transactions. The Credit Card Fraud analysis data set, which is obtained from the Kaggle database, is used in the modeling process together with The Logistic regression method and Naive Bayes algorithms. Using the Knime platform, we are going to apply machine learning techniques to practical data in this study. The goal of this study is to identify who performed the transaction by examining the periods when people use their credit cards. The Logistic regression approach and the Naive Bayes method both had success rates of 99.83%, which is the highest. The two methods’ results are based on Cohen’s kappa, accuracy, precision, recall, and other metrics.

MiRGediNET: A comprehensive examination of common genes in miRNA-Target interactions and disease associations: Insights from a grouping-scoring-modeling approach

In the broad and complex field of biological data analysis, researchers frequently gather information from a single source or database. Despite being a widespread practice, this has disadvantages. Relying exclusively on a single source can limit our comprehension as it may omit various perspectives that could be obtained by combining multiple knowledge bases. Acknowledging this shortcoming, we report on miRGediNET, a novel approach combining information from three biological databases. Our investigation focuses on microRNAs (miRNAs), small non-coding RNA molecules that regulate gene expression post-transcriptionally. We delve deeply into the knowledge of these miRNA's interactions with genes and the possible effects these interactions may have on different diseases. The scientific community has long recognized a direct correlation between the progression of specific diseases and miRNAs, as well as the genes they target. By using miRGediNET, we go beyond simply acknowledging this relationship. Rather, we actively look for the critical genes that could act as links between the actions of miRNAs and the mechanisms underlying disease. Our methodology, which carefully identifies and investigates these important genes, is supported by a strategic framework that may open up new possibilities for comprehending diseases and creating treatments. We have developed a tool on the Knime platform as a concrete application of our research. This tool serves as both a validation of our study and an invitation to the larger community to interact with, investigate, and build upon our findings. miRGediNET is publicly accessible on GitHub at https://github.com/malikyousef/miRGediNET, providing a collaborative environment for additional research and innovation for enthusiasts and fellow researchers.

A visual-based toolkit to support mobility data analytics

The Knowledge Discovery from Data (KDD) process is widely used across various domains to get valuable insights from data. Many platforms, like KNIME or RapidMiner, offer effective tools for KDD analysts, allowing them to perform data analytics tasks in a visual fashion, without writing code. In recent years, the increasing availability of mobility data has led to a surge in KDD-based initiatives from both industry and academia in the Intelligent Transportation Systems (ITS) domain. Still, KDD platforms lack comprehensive support for some typical mobility data manipulation tasks. As a result, mobility data analysis still requires a significant coding phase, with reduced productivity and hindered replicability of results.To address this gap, this paper presents a novel solution aimed at supporting ITS data analysts in defining KDD processes more efficiently. More in detail, we extended the KNIME platform by introducing a collection of new components explicitly tailored to facilitate some peculiar KDD tasks from mobility data. These components encompass critical functionalities such as map coverage analysis, trajectory partitioning and map-matching.To showcase the effectiveness of the proposed solution, we used it to replicate a study published in the ITS data analytics domain. Thanks to our proposal, such replication can be accomplished in a few minutes and with just a few clicks, without any manual coding, resulting in a pipeline that is easier to understand, distribute and re-execute, also for domain experts with no programming experience.Our solution is open-source and freely downloadable from the Knime Hub. In this way, we aim to foster data-driven research and practice in the ITS field, by providing researchers and practitioners with more effective analytics tools to handle mobility data.

Employing Data Mining Techniques and Machine Learning Models in Classification of Students’ Academic Performance

The study deals with the use of data mining techniques to build a classification model to predict students' academic performance. The research indicates that the use of machine learning models and data mining methods can reveal hidden patterns and relationships in big data, making them indispensable tools in the field of education analysis. Special emphasis was placed on the use of algorithms such as decision trees. The study includes an analysis of factors that affect students' academic performance such as previous academic achievement in educational activities, as well as social and psychological factors. Classification models were applied using the KNIME platform and the WEKA tool to analyse students' performance in three courses: database technology, artificial intelligence, and image processing in the ICT degree program. The results showed that the use of decision trees can effectively classify students' performance and determine the success and failure rate. The cruel outright mistakes, RMS error and relative supreme mistake all showed 0% whereas the kappa esteem got from the analysis extended between 0.991 and 1.00 which significantly concurs with most statistical values.

A machine learning-based KNIME workflow to predict VEGFR-2 inhibitors.

Vascular endothelial growth factors (VEGFs) are specific cytokines involved in angiogenesis and do so via binding to vascular endothelial growth factor receptors (VEGFRs), a type of receptor tyrosine kinase. VEGFs are reported to facilitate angiogenesis in physiological (embryogenesis) and pathological (tumor) conditions. The overexpression of VEGFs and consequently VEGFRs is reported in tumorigenic conditions. Several VEGFR inhibitors currently used as anticancer drugs to prevent angiogenesis are sunitinib, sorafenib, etc. To identify new potential candidates as VEGFR inhibitors, a classification study using a large and diverse dataset of VEGFR inhibitors from the BindingDB database has been conducted. The KNIME platform was used to calculate molecular and fingerprint-based descriptors and several classification algorithms viz. linear regression (LR), k-nearest neighbor (kNN), decision tree (DT), random forest (RF), and gradient boosted tree (GBT) were employed to build the classification model. The model performance was evaluated by accuracy, precision, recall, and F1 score of the test set. The best LR, kNN, DT, RF, and GBT classifiers had the F1 score of 0.81, 0.87, 0.82, 0.87, and 0.87, respectively. The assorted 5120 VEGFR inhibitors were clustered into 10 subsets, and the structural features of each subset were assessed along with the identification of significant fragments in active and inactive compounds. The automated classifier model developed using the KNIME platform could serve as an important platform for screening and designing molecules as VEGFR inhibitors.

A new set of KNIME nodes implementing the QPhAR algorithm.

Dissemination of novel research methods, especially in the form of chemoinformatics software, depends heavily on their ease of applicability for non-expert users with only a little or no programming skills and knowledge in computer science. Visual programming has become widely popular over the last few years, also enabling researchers without in-depth programming skills to develop tailored data processing pipelines using elements from a repository of predefined standard procedures. In this work, we present the development of a set of nodes for the KNIME platform implementing the QPhAR algorithm. We show how the developed KNIME nodes can be included in a typical workflow for biological activity prediction. Furthermore, we present best-practice guidelines that should be followed to obtain high-quality QPhAR models. Finally, we show a typical workflow to train and optimise a QPhAR model in KNIME for a set of given input compounds, applying the discussed best practices.

Automated QSPR modeling and data curation of physicochemical properties using KNIME platform: Prediction of partition coefficients

In the last two decades, the volumes of chemical and biological data are constantly increasing. The problem of converting data sets into knowledge is both expensive and time-consuming, as a result a workflow technology with platforms such as KNIME, was built up to facilitate searching through multiple heterogeneous data sources and filtering for specific criteria then extracting hidden information from these large data. Before any QSAR modeling, a manual data curation is extremely recommended. However, this can be done, for small datasets, but for the extensive data accumulated recently in public databases a manual process of big data will be hardly feasible. In this work, we suggest using KNIME as an automated solution for workflow in data curation, development, and validation of predictive QSAR models from a huge dataset.In this study, we used 250250 structures from NCI database, only 3520 compounds could successfully pass through our workflow safely with their corresponding experimental log P, this property was investigated as a case study, to improve some existing log P calculation algorithms.

Text Mining of Biomedical Articles Using the Konstanz Information Miner (KNIME) Platform: Hemolytic Uremic Syndrome as a Case Study.

ObjectivesAutomated systems for information extraction are becoming very useful due to the enormous scale of the existing literature and the increasing number of scientific articles published worldwide in the field of medicine. We aimed to develop an accessible method using the open-source platform KNIME to perform text mining (TM) on indexed publications. Material from scientific publications in the field of life sciences was obtained and integrated by mining information on hemolytic uremic syndrome (HUS) as a case study.MethodsText retrieved from Europe PubMed Central (PMC) was processed using specific KNIME nodes. The results were presented in the form of tables or graphical representations. Data could also be compared with those from other sources.ResultsBy applying TM to the scientific literature on HUS as a case study, and by selecting various fields from scientific articles, it was possible to obtain a list of individual authors of publications, build bags of words and study their frequency and temporal use, discriminate topics (HUS vs. atypical HUS) in an unsupervised manner, and cross-reference information with a list of FDA-approved drugs.ConclusionsFollowing the instructions in the tutorial, researchers without programming skills can successfully perform TM on the indexed scientific literature. This methodology, using KNIME, could become a useful tool for performing statistics, analyzing behaviors, following trends, and making forecast related to medical issues. The advantages of TM using KNIME include enabling the integration of scientific information, helping to carry out reviews, and optimizing the management of resources dedicated to basic and clinical research.

A Predictive Model Implemented in KNIME Based on Learning Analytics for Timely Decision Making in Virtual Learning Environments

The present research aims to implement a predictive model in the KNIME platform to analyze and compare the prediction of academic performance using data from a Learning Management System (LMS), identifying students at academic risk in order to generate timely and timely interventions. The CRISP-DM methodology was used, structured in six phases: Problem analysis, data analysis, data understanding, data preparation, modeling, evaluation and implementation. Based on the analysis of online learning behavior through 22 behavioral indicators observed in the LMS of the Faculty of Educational Sciences of the National University of San Agustin. These indicators are distributed in five dimensions: Academic Performance, Access, Homework, Social Aspects and Quizzes. The model has been implemented in the KNIME platform using the Simple Regression Tree Learner training algorithm. The total population consists of 30,000 student records from which a sample of 1,000 records has been taken by simple random sampling. The accuracy of the model for early prediction of students' academic performance is evaluated, the 22 observed behavioral indicators are compared with the means of academic performance in three courses. The prediction results of the implemented model are satisfactory where the mean absolute error compared to the mean of the first course was 3. 813 and with an accuracy of 89.7%, the mean absolute error compared to the mean of the second course was 2.809 with an accuracy of 94.2% and the mean absolute error compared to the mean of the third course was 2.779 with an accuracy of 93.8%. These results demonstrate that the proposed model can be used to predict students' future academic performance from an LMS data set.

Dashboard proposal implemented according to an analysis developed in the KNIME platform

The objective of the research is to develop a methodology to analyze a set of data extracted from a Learning Management System (LMS), in order to implement a Dashboard, which can be used by teachers to make timely and relevant decisions to improve the teaching-learning processes. The methodology used consisted of the analysis of 9,257 records extracted through simple random sampling from a population of 100,000 records. The indicators analyzed were: number of accesses, course grades, time spent, number of courses enrolled and number of activities developed. The results show the data analysis in the KNIME data mining analysis platform, the model was implemented in five phases: Requirements definition, model design, development, implementation and evaluation of results. The results are taken as a recommendation to design and implement a customized Dashboard for teachers to identify observable behavioral patterns that allow them to make decisions to improve the teaching-learning processes of students.
 Keywords: Analytics, dashboard, KNIME Learning, personalized, teaching.

Abstract 239: Integrated computational image analysis of cellular and acellular tissue components as a method for detailed tumor tissue mapping and structural patterns recognition

Abstract Tumor microenvironment (TME) represents an integrated system that affects cancer cell behavior and contributes directly to disease outcome. Systemic approach to analysis of TME should uncover its complexity and facilitate discovery of mechanisms orchestrating tumor development and metastasis. Multiplex fluorescence tissue staining followed by spatial analysis of tumor tissue architecture can provide insights to pivotal interactions of cellular and acellular components of TME. Extracellular matrix (ECM is represented mainly by collagen deposition. Number of reports indicates that ECM contribution to TME state not only depends upon amount of accumulated collagen but its geometrical features and spatial orientation of fibers. These characteristics of collagen fibers contribute directly to physical and mechanical properties of tissue and can change tumor growth and metastasis. Current methods of computational image analysis of tissue implement assessment of cellular or acellular components separately. The goal of current work was to develop a new computational tool to perform integrated analysis of fibrous and cellular components of tumor tissue in spatial dependent manner to achieve detailed tumor tissue mapping and structural patterns recognition. To pursue this goal, we generated images of human lung adenocarcinoma tissue characterized by indolent and aggressive behavior. We performed multiplex immunofluorescence staining for following markers: CD3 - marker of T-lymphocytes, PanCytokeratin - marker of epithelial/tumor cells, collagen hybridizing peptide (3Helix) - marker of collagen, DAPI - nuclear counterstain. To develop image analysis pipeline, we utilized an open source graphical interface analytical platform KNIME, where we generated modular workflow. For ECM analysis, we integrated Python written code into KNIME node. Segmentation of collagen fibers was performed using skeletonization with subsequent calculation of geometrical properties (length, alignment, widths) and orientation of each fiber. Data, collected from single cell analysis and ECM architecture assessment, were combined and forwarded to downstream spatial analysis, where distances from cell to cell or cell to ECM were computed and neighborhood analysis was performed. We demonstrated that tumor cells in aggressive adenocarcinoma samples were co-localized with a smaller number of collagen fibers. In addition, length of that fibers was less in comparison to indolent group. Correlation analysis revealed positive correlation between length of collagen fibers and number of tumor cells in indolent group, but we did not observe this phenomenon in indolent group. Developed computational method provides additional dimensionality to tissue image analysis and can reveal underrecognized structural patterns of the tumor microenvironment. Citation Format: Georgii Vasiukov, Tatiana Novitskaya, Maria-Fernanda Senosain, Anna Menshikh, Andries Zijlstra, Sergey Novitskiy, Pierre Massion. Integrated computational image analysis of cellular and acellular tissue components as a method for detailed tumor tissue mapping and structural patterns recognition [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 239.

Abstract 4425: Extracellular matrix segmentation combined with cell classification as a novel method for detailed tumor tissue mapping

Abstract Tumor microenvironment (TME) represents a dynamic niche that regulates cancer cell behavior contributing directly to disease outcome. Systemic approach to analysis of TME should uncover its complexity and facilitate discovery of mechanisms orchestrating tumor development and metastasis. Multiplexed fluorescent tissue stain followed by spatial analysis of tumor tissue architecture can provide insights to pivotal interactions of cellular and acellular components of TME. Extracellular matrix (ECM), one of constitutive of TME, is represented mainly by collagen deposition. Recently it is became increasingly recognized that ECM contribution to TME dynamics not only depend upon amount of accumulated collagen but its geometrical features and spatial orientation of fibers. These characteristics of collagen contribute directly to physical and mechanical properties of tissue and can contribute to tumor growth and metastasis. Current algorithms of tissue stain-based methods include estimation of ECM deposition by measuring percent of positive area and separate to it cell classification and cell count. The goal of current work was to develop a new computational tool to perform spatial distribution analysis based on geometrical features and orientation of collagen fibers in combination with cell class assessment aimed to achieve detailed tumor tissue mapping. To pursue this goal, we generated fluorescent images of human breast tumor tissue, stained for following markers: CD3 - marker of T-lymphocytes, PanCytokeratin - marker of epithelial/tumor cells, collagen hybridizing peptide (3Helix) - marker of collagen, DAPI - nuclear counterstain. To develop image analysis pipeline, we utilized open source graphical interface analytical platform KNIME, where we generated modular workflow. For ECM analysis, we integrated Python written code into KNIME node. Segmentation of collagen fibers was performed using skeletonization with subsequent calculation of geometrical properties (length, alignment, widths) and orientation of each fiber. Data, collected from single cell analysis and ECM architecture assessment, were combined and forwarded to downstream spatial analysis, where distances from cell to cell or cell to ECM were computed and neighborhood analysis was performed. We demonstrate different patterns in tumor microenvironment organization that correlate with cancer outcome. Developed image analysis algorithm provides additional dimensionality to fluorescent tissue stains and can reveal underrecognized patterns of tumor microenvironment that can contribute to better understanding of tumorigenesis and metastasis. Citation Format: GEORGII VASIUKOV, Tatiana Novitskaya, Sergey Gutor, Anna Menshikh, Andries Zijlstra, Sergey Novitskiy. Extracellular matrix segmentation combined with cell classification as a novel method for detailed tumor tissue mapping [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 4425.

Machine Learning Approach Using MLP and SVM Algorithms for the Fault Prediction of a Centrifugal Pump in the Oil and Gas Industry

The demand for cost-effective, reliable and safe machinery operation requires accurate fault detection and classification to achieve an efficient maintenance strategy and increase performance. Furthermore, in strategic sectors such as the oil and gas industry, fault prediction plays a key role to extend component lifetime and reduce unplanned equipment thus preventing costly breakdowns and plant shutdowns. This paper presents the preliminary development of a simple and easy to implement machine learning (ML) model for early fault prediction of a centrifugal pump in the oil and gas industry. The data analysis is based on real-life historical data from process and equipment sensors mounted on the selected machinery. The raw sensor data, mainly from temperature, pressure and vibrations probes, are denoised, pre-processed and successively coded to train the model. To validate the learning capabilities of the ML model, two different algorithms—the Support Vector Machine (SVM) and the Multilayer Perceptron (MLP)—are implemented in KNIME platform. Based on these algorithms, potential faults are successfully recognized and classified ensuring good prediction accuracy. Indeed, results from this preliminary work show that the model allows us to properly detect the trends of system deviations from normal operation behavior and generate fault prediction alerts as a maintenance decision support system for operatives, aiming at avoiding possible incoming failures.

Accessing Public Compound Databases with KNIME.

The KNIME platform offers several tools for the analysis of chem- and pharmacoinformatics data. Unless one has sufficient in-house data available for the analysis of interest, it is necessary to fetch third party data into KNIME. Many data sources offer valuable data, but including this data in a workflow is not always straightforward. Here we discuss different ways of accessing public data sources. We give an overview of KNIME nodes for different sources, with references to available example workflows. For data sources with no individual KNIME node available, we present a general approach of accessing a web interface via KNIME. In addition, we discuss necessary steps before the data can be analysed, such as data curation, chemical standardisation and the merging of datasets.

Distinguishing between intra-genomic helitron families using time-frequency features and random forest approaches

Since its discovery in the promoter of ADC1 (Arginine Decarboxylase 1) gene in Arabidopsis thaliana, the helitron never stopped drawing the attention of researchers. Helitrons belong to the transposable elements (TEs) class II which transpose via a rolling circle mechanism; they are known as potential insertional mutagens. Given that these transposable elements do not have typical characteristics, their identification remains restricted to biological experiments. In addition, their distribution in the same genome is not uniform, which makes their classification a difficult task. Indeed, in the case of helitrons, the frequency of apparition in the same genome differs from one helitron type to another. In this framework, we propose two-steps based on-method to automatically identify and classify the helitron types. The spectral analysis method is then used to characterize these elements. This is done by the Smoothed Discrete Fourier Transform (SDFT) which permits the global localization of latent periodicities in helitrons’ signals. For each helitron type, we prove the presence of various periodicities indicating the existence of microsatellites and minisatellites. As an example, the short repetitive sequences with a size equal to 3 bp are found in the helitrons: HelitronY1_CE and HelitronY1A. In a second step, machine learning is used to classify the helitron families (10 classes) in the C.elegans genome. Subsequently, a prediction method of helitron types is proposed using the combination of features extracted from numerical helitron sequences (the Frequency Chaos Game Signals: FCGS2) and a machine learning technique (the Random Forest: RF). The helitrons features are obtained by the analysis techniques: SDFT (32 values) or CWT (Continuous Wavelet Transform, 64 values). Here, the helitrons database is randomly split into two datasets: training (80%) and testing (20%). As for the machine learning method, we use the Random Forest algorithm under the data analytics platform KNIME. In our prediction system, the features corresponding to the same genome (C.elegans) were proven to be sufficient for successful categorization of helitron families. The accuracy scores over 100 fold cross validation ranged from 78% to 94% with an overall score of 90%.