To see the other types of publications on this topic, follow the link: KNIME Analytics Platform.
Journal articles on the topic 'KNIME Analytics Platform'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'KNIME Analytics Platform.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Andrey Vladimirovich, Kulev, and Kulev Maxim Vladimirovich. "ANALYSISOFTHELEVELOFTRAININGOF STUDENTS OF TRANSPORT DIRECTIONS IN THE KNIME ANALYTICS PLATFORM SOFTWARE ENVIRONMENT." World of transport and technological machines 1(79), no. 4 (2022): 119–24. http://dx.doi.org/10.33979/2073-7432-2022-1(79)-4-119-124.
Full textAbstract:
The aim of the work is to analyze the data and visualize the results of compliance with the requirements of employers and students' knowledge of transport areas at OSU named after I.S. Turgenev in the KNIME Analytics Platform software environment. To achieve the goal in the article, a working project was developed in the KNIME Analytics Platform; the main requirements of employers to applicants for the position of a logistician were identified; the analysis of the content of the work program of the discipline «Transport logistics» was carried out; a conclusion was made on the conformity of the level of training of students in transport areas at the Oryol State University named after I.S. Turgenev to the requirements of employers.
2
Магамедова, Д. М., А. И. Джангаров та Д. Ш. Калхиташвили. "Структура платформы Knime Analytics Platform и ее возможности". ТЕНДЕНЦИИ РАЗВИТИЯ НАУКИ И ОБРАЗОВАНИЯ 80, № 2 (2021): 125–27. http://dx.doi.org/10.18411/trnio-12-2021-92.
Full textAbstract:
Стремительное развитие технологий, постоянный обмен информацией и значительное увеличение передаваемых данных привело к появлению множества алгоритмов по их обработке, платформ для реализации самих алгоритмов и к прочному закреплению понятия «большие данные (Big data)» в современном обществе. Рынок труда пополнился новыми профессиями, такими как: специалист по обработке данных, анализу данных, архитектор данных и др. В статье рассматривается одна из платформ, обладающей современными программными инструментами для анализа данных.
3
Egorova, Daria K., and Roman V. Denisov. "Visual Scenario Development Platform Used to Model Real Estate Market Processes." Ogarev-online 13, no. 1 (2025): 53–63. https://doi.org/10.15507/2311-2468.013.202501.053-063.
Full textAbstract:
Introduction. The real estate market is a key sector of the economy with high price dynamics, dependence on macroeconomic factors and complexity of forecasting. Traditional analysis methods require a lot of time and resources, which limits their application. Using low-code platforms allows you to reduce the cost of developing models and make analysis tools accessible to specialists without advanced programming skills. The purpose of the study is to demonstrate the use of KNIME to predict the value of real estate and their classification. In addition, it is necessary to assess how accurate the models are and how useful they are in practice. Materials and Methods. Real estate market processes were modeled using KNIME Analytics Platform for visual scenario development. Real estate data is collected using the Cyanparser Python library, and regression analysis and data visualization methods are implemented in KNIME Analytics Platform. Results. Linear and polynomial regression of real estate prices according to specified parameters is constructed, clusterization of real estate objects and visualization of the results are performed. Clustering revealed three groups of objects correlating with location and infrastructure. Discussion and Conclusion. KNIME has confirmed its effectiveness as a low-code tool for analyzing the real estate market. The materials of the article can be useful for understanding the dynamics of the real estate market and forecasting its future trends.
4
BUNYAKINA, EKATERINA V., and MAXIM I. GALCHENKO. "APPLICATION OF H2O FRAMEWORK IN TIME SERIES PROCESSING." H&ES Research 12, no. 4 (2020): 56–64. http://dx.doi.org/10.36724/2409-5419-2020-12-4-56-64.
Full textAbstract:
Currently, one of the most popular advanced analytics area is time series analysis. Stored data of measuring instruments, detectors of various kinds can serve as examples of generating this kind of data. There are quite a few integrated platforms proposals on the market for building deep learning models. In this situation, the H2O platform (framework) is a unique offer, due to its free, comprehensive, low entry threshold and scalability. Particular interest in the framework is also dictated by the fact that the developers have provided the opportunity to access the platform algorithms in R and Python using libraries, as well as the availability of the Sparkling Water application for Apache Spark. In the KNIME Analytics Platform 4.X, the KNIME Labs — Deep Learning node group has well-tuned nodes that can invoke the corresponding H2O algorithms. Currently, not all H2O algorithms have been implemented yet, but the KNIME development process allows us to expect that everything remaining will be implemented soon. The article provides general information, as well as an example of using the platform for the task of time series forecasting. The order of the functions in the code, the basic settings, as well as the call features that occur when working on a single PC while working in R are shown. The process of interaction with the web interface and the implementation of functions in the statistical programming language R is described. The use of simulation results, namely, relative importance, is demon strated. predictors in H2O to simplify the data set and increase the rate of convergence of the algorithm.
5
Mazanetz, Michael P., Charlotte H. F. Goode, and Ewa I. Chudyk. "Ligand- and Structure-Based Drug Design and Optimization using KNIME." Current Medicinal Chemistry 27, no. 38 (2020): 6458–79. http://dx.doi.org/10.2174/0929867326666190409141016.
Full textAbstract:
In recent years there has been a paradigm shift in how data is being used to progress early drug discovery campaigns from hit identification to candidate selection. Significant developments in data mining methods and the accessibility of tools for research scientists have been instrumental in reducing drug discovery timelines and in increasing the likelihood of a chemical entity achieving drug development milestones. KNIME, the Konstanz Information Miner, is a leading open source data analytics platform and has supported drug discovery endeavours for over a decade. KNIME provides a rich palette of tools supported by an extensive community of contributors to enable ligandand structure-based drug design. This review will examine recent developments within the KNIME platform to support small-molecule drug design and provide a perspective on the challenges and future developments within this field.
6
Liawrungrueang, Wongthawat, Sung Tan Cho, Vit Kotheeranurak, Alvin Pun, Khanathip Jitpakdee, and Peem Sarasombath. "Artificial neural networks for the detection of odontoid fractures using the Konstanz Information Miner Analytics Platform." Asian Spine Journal 18, no. 3 (2024): 407–14. http://dx.doi.org/10.31616/asj.2023.0259.
Full textAbstract:
Study Design: An experimental study.Purpose: This study aimed to investigate the potential use of artificial neural networks (ANNs) in the detection of odontoid fractures using the Konstanz Information Miner (KNIME) Analytics Platform that provides a technique for computer-assisted diagnosis using radiographic X-ray imaging.Overview of Literature: In medical image processing, computer-assisted diagnosis with ANNs from radiographic X-ray imaging is becoming increasingly popular. Odontoid fractures are a common fracture of the axis and account for 10%–15% of all cervical fractures. However, a literature review of computer-assisted diagnosis with ANNs has not been made.Methods: This study analyzed 432 open-mouth (odontoid) radiographic views of cervical spine X-ray images obtained from dataset repositories, which were used in developing ANN models based on the convolutional neural network theory. All the images contained diagnostic information, including 216 radiographic images of individuals with normal odontoid processes and 216 images of patients with acute odontoid fractures. The model classified each image as either showing an odontoid fracture or not. Specifically, 70% of the images were training datasets used for model training, and 30% were used for testing. KNIME’s graphic user interface-based programming enabled class label annotation, data preprocessing, model training, and performance evaluation.Results: The graphic user interface program by KNIME was used to report all radiographic X-ray imaging features. The ANN model performed 50 epochs of training. The performance indices in detecting odontoid fractures included sensitivity, specificity, F-measure, and prediction error of 100%, 95.4%, 97.77%, and 2.3%, respectively. The model’s accuracy accounted for 97% of the area under the receiver operating characteristic curve for the diagnosis of odontoid fractures.Conclusions: The ANN models with the KNIME Analytics Platform were successfully used in the computer-assisted diagnosis of odontoid fractures using radiographic X-ray images. This approach can help radiologists in the screening, detection, and diagnosis of acute odontoid fractures.
7
Maraza-Quispe, Benjamin, Ricardo Carlos Quispe-Figueroa, Manuel Alejandro Valderrama-Solis, and Benjamin Maraza-Quispe. "Dashboard proposal implemented according to an analysis developed in the KNIME platform." World Journal on Educational Technology: Current Issues 13, no. 4 (2021): 617–34. http://dx.doi.org/10.18844/wjet.v13i4.6233.
Full textAbstract:
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.
8
Maraza-Quispe, Benjamin, Ricardo Carlos Quispe-Figueroa, Manuel Alejandro Valderrama-Solis, and Benjamin Maraza-Quispe. "Dashboard proposal implemented according to an analysis developed on the KNIME platform." World Journal on Educational Technology: Current Issues 13, no. 4 (2021): 816–37. http://dx.doi.org/10.18844/wjet.v13i4.6267.
Full textAbstract:
The objective of the research is to develop a methodology to analyse a set of data extracted from a learning management system, 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 analysing 9,257 records extracted through simple random sampling from a population of 100,000 records. The indicators analysed were number of accesses, course grades, time spent, number of courses enrolled and number of activities developed. The results show that the data analysis was carried out on the (o Konstanz Information Miner (KNIME) data mining analysis platform, and 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 customised dashboard for teachers to identify observable behavioural patterns that allow them to make decisions to improve the teaching–learning processes of students.
 Keywords: Analytics, dashboard, KNIME Learning, personalised, teaching
9
R, Chitra A., and Dr Arjun B. C. "Performance Analysis of Regression Algorithms for Used Car Price Prediction: KNIME Analytics Platform." International Journal for Research in Applied Science and Engineering Technology 11, no. 2 (2023): 1324–31. http://dx.doi.org/10.22214/ijraset.2023.49180.
Full textAbstract:
Abstract: In the recent years people’s willingness towards used car has increased. This has reflected in selling and buying of such cars. With the advance in technology online portal for marketing of used cars has come into effect. Many online portals focus to connect available used cars with user needs, present trends and various selection criteria. Using Machine Learning Algorithms such as Linear Regression, Tree Ensemble (Regression), Random forest (Regression), Gradient Boosted Tree(Regression), Simple Regression tree provided by KNIME Analytics Platform used car price predicted is performed. Analysis shows that Gradient Boosted Tree(Regression) prediction is closest to the target.
10
Marlinda, Linda, Evita Fitri, Siti Nurhasanah Nugraha, Faruq Aziz, and Santoso Setiawan. "Decision Tree Algorithm to Measure Employee Performance Discipline." Sinkron 7, no. 4 (2022): 2223–30. http://dx.doi.org/10.33395/sinkron.v7i4.11796.
Full textAbstract:
Performance appraisal is done to measure the performance of an employee on the work done. The company conducts performance appraisals on employees at least every six months, involving all employees. This study uses the Absenteeism_at_work dataset. The purpose of this research is to analyze the performance of the Decision Tree algorithm in the classification process. Classification will be grouped into two, namely: disciplined and undisciplined The classification process will be carried out using K-Nime. Algorithm performance measurement using Knime Analytics Platform is open-source software for creating data science models. Knime builds data understanding and designs data science workflows and reusable components using accuracy, recall, and precision parameters. From the research conducted, the results of the Decision Tree algorithm have an accuracy rate of 94.6% while the label No. 5.4%. Based on the nineteen attributes proposed, it can be concluded that the Decision Tree algorithm has better performance.
11
An, Jun Young, Hoseok Seo, Young-Gon Kim, Kyu Eun Lee, Sungwan Kim, and Hyoun-Joong Kong. "Codeless Deep Learning of COVID-19 Chest X-Ray Image Dataset with KNIME Analytics Platform." Healthcare Informatics Research 27, no. 1 (2021): 82–91. http://dx.doi.org/10.4258/hir.2021.27.1.82.
Full text
12
Печерина, А. В. "The impact of coronavirus infection on the socio-economic indicators of the region." МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ 10, no. 3(38) (2022): 28–29. http://dx.doi.org/10.26102/2310-6018/2022.38.3.028.
Full textAbstract:
Новая коронавирусная инфекция (COVID-19), возникшая в городе Ухань в Китае в начале декабря 2019 года, быстро распространилась почти во всех странах мира и стала шоком для мировой экономики. В статье освещаются важнейшие проблемы, которые обусловлены пандемией коронавируса. Автором рассматривается влияние новой коронавирусной инфекции Covid-19 на некоторые социально-экономические показатели отдельного региона Российской Федерации, а также Российской Федерации в целом. Для этого была разработана аналитическая процедура на бесплатной платформе для анализа данных с открытым исходным кодом Knime Analytics Platform, которая, в свою очередь, значительно упростила обработку данных и визуализацию результатов. Платформа позволяет разрабатывать воспроизводимые и масштабируемые рабочие процессы, интегрируя широкий спектр инструментов анализа. В основу анализа легли данные, извлеченные с сайта Центра пространственно-временных инноваций университета Гарвард (NSF Spatiotemporal Innovation Center), и статистические данные, извлеченные с сайта Федеральной службы государственной статистики. Полученные данные были визуализированы и сделаны выводы о зависимости роста заболеваемости новой коронавирусной инфекцией Covid-19 и стоимости фиксированного набора потребительских товаров и услуг для межрегиональных сопоставлений покупательной способности населения. The new coronavirus infection (COVID-19) which emerged in Wuhan, China, in early December 2019 quickly spread to almost every country in the world and shocked the global economy. This article highlights the most important problems that are caused by the coronavirus pandemic. The author discusses the impact of the new coronavirus infection Covid-19 on some socio-economic indicators of a particular region of the Russian Federation as well as the Russian Federation as a whole. In order to do that, an analytical procedure was developed using Knime Analytics Platform (the free and open source data analysis platform), which, in turn, greatly simplified data processing and visualization of results. The platform makes it possible to develop reproducible and scalable workflows by integrating a wide range of analysis tools. The analysis was based on the data extracted from the website of the Center for Spatiotemporal Innovation at Harvard University (NSF Spatiotemporal Innovation Center) and the statistical data extracted from the website of the Federal State Statistics Service. We visualized the data and drew conclusions about COVID-2019 incidence rate and the cost of a constant set of consumer products and services for the purposes of inter-regional comparisons of purchasing power.
13
Benjamín, Maraza-Quispe, Enrique Damián Valderrama-Chauca, Lenin Henry Cari-Mogrovejo, Jorge Milton Apaza-Huanca, and Jaime Sanchez-Ilabaca. "A Predictive Model Implemented in KNIME Based on Learning Analytics for Timely Decision Making in Virtual Learning Environments." International Journal of Information and Education Technology 12, no. 2 (2022): 91–99. http://dx.doi.org/10.18178/ijiet.2022.12.2.1591.
Full textAbstract:
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.
14
Copmans, Daniëlle, Thorsten Meinl, Christian Dietz, et al. "A KNIME-Based Analysis of the Zebrafish Photomotor Response Clusters the Phenotypes of 14 Classes of Neuroactive Molecules." Journal of Biomolecular Screening 21, no. 5 (2015): 427–36. http://dx.doi.org/10.1177/1087057115618348.
Full textAbstract:
Recently, the photomotor response (PMR) of zebrafish embryos was reported as a robust behavior that is useful for high-throughput neuroactive drug discovery and mechanism prediction. Given the complexity of the PMR, there is a need for rapid and easy analysis of the behavioral data. In this study, we developed an automated analysis workflow using the KNIME Analytics Platform and made it freely accessible. This workflow allows us to simultaneously calculate a behavioral fingerprint for all analyzed compounds and to further process the data. Furthermore, to further characterize the potential of PMR for mechanism prediction, we performed PMR analysis of 767 neuroactive compounds covering 14 different receptor classes using the KNIME workflow. We observed a true positive rate of 25% and a false negative rate of 75% in our screening conditions. Among the true positives, all receptor classes were represented, thereby confirming the utility of the PMR assay to identify a broad range of neuroactive molecules. By hierarchical clustering of the behavioral fingerprints, different phenotypical clusters were observed that suggest the utility of PMR for mechanism prediction for adrenergics, dopaminergics, serotonergics, metabotropic glutamatergics, opioids, and ion channel ligands.
15
Neimark, A. E., M. A. Molotkova, E. O. Makarova, and M. I. Galchenko. "PROGNOSTIC VALUE OF THE ABCD AND IMS FOR EVALUATION OF TYPE 2 DIABETES MELLITUS REMISSION AFTER BARIATRIC SURGERY." Translational Medicine 10, no. 3 (2023): 136–45. http://dx.doi.org/10.18705/2311-4495-2023-10-3-136-145.
Full textAbstract:
Background. Significant proportion of patients with obesity and type 2 diabetes mellitus (DM) have significant weight loss and improved metabolic outcomes as a result of bariatric surgery. To predict the effect of surgical treatment of DM, several scales have been proposed, including ABCD and IMS.Objective. To estimate accuracy of the ABCD and IMS scales in predicting DM remission in patients undergoing bariatric surgery.Design and methods. 38 patients with type 2 diabetes were identified after bariatric surgery with a follow-up period of at least 1 year. The KNIME Analytics Platform 4.3.6 (KNIME AG, Switzerland) was used for data processing.Results. 12.8 % of patients achieved partial remission, 52.6 % complete remission, and 31.6 % did not achieve remission. According to the IMS, no significant results were detected in the remission groups. IMS scale have a low predictive value. A significant result was obtained for the ABCD after CAIM binning. For the binary classification (“Remission”/”Haven’t remission”): AUC = 0.98 and Cohen’s kappa k = 0.86 for probability treshold 0.55399, that maximized F-measure (0.96) were obtained. So, ABCD predictive value is high.Conclusion. The ABCD have a better predictive value. Ease of use, good prognostic effect allows us to recommend ABCD before bariatric treatment.
16
Jaradat, Ameera S., Malek M. Barhoush, and Rawan S. Bani Easa. "Network intrusion detection system: machine learning approach." Indonesian Journal of Electrical Engineering and Computer Science 25, no. 2 (2022): 1151. http://dx.doi.org/10.11591/ijeecs.v25.i2.pp1151-1158.
Full textAbstract:
The main goal of intrusion detection system (IDS) is to monitor the network performance and to investigate any signs of any abnormalities over the network. Recently, intrusion detection systems employ machine learning techniques, due to the fact that machine learning techniques proved to have the ability of learning and adapting in addition to allowing a prompt response. This work proposes a model for intrusion detection and classification using machine learning techniques. The model first acquires the data set and transforms it in the proper format, then performs feature selection to pick out a subset of attributes that worth being considered. After that, the refined data set was processed by the Konstanz information miner (KNIME). To gain better performance and a decent comparative analysis, three different classifiers were applied. The anticipated classifiers have been executed and assessed utilizing the KNIME analytics platform using (CICIDS2017) datasets. The experimental results showed an accuracy rate ranging between (98.6) as the highest obtained while the average was (90.59%), which was satisfying compared to other approaches. The gained statistics of this research inspires the researchers of this field to use machine learning in cyber security and data analysis and build intrusion detection systems with higher accuracy.
17
Jaradat, Ameera S., Malek M. Barhoush, and Rawan Bani Easa. "Network intrusion detection system: machine learning approach." Indonesian Journal of Electrical Engineering and Computer Science 25, no. 2 (2022): 1151–58. https://doi.org/10.11591/ijeecs.v25.i2.pp1151-1158.
Full textAbstract:
The main goal of intrusion detection system (IDS) is to monitor the network performance and to investigate any signs of any abnormalities over the network. Recently, intrusion detection systems employ machine learning techniques, due to the fact that machine learning techniques proved to have the ability of learning and adapting in addition to allowing a prompt response. This work proposes a model for intrusion detection and classification using machine learning techniques. The model first acquires the data set and transforms it in the proper format, then performs feature selection to pick out a subset of attributes that worth being considered. After that, the refined data set was processed by the Konstanz information miner (KNIME). To gain better performance and a decent comparative analysis, three different classifiers were applied. The anticipated classifiers have been executed and assessed utilizing the KNIME analytics platform using (CICIDS2017) datasets. The experimental results showed an accuracy rate ranging between (98.6) as the highest obtained while the average was (90.59%), which was satisfying compared to other approaches. The gained statistics of this research inspires the researchers of this field to use machine learning in cyber security and data analysis and build intrusion detection systems with higher accuracy.
18
Garmpis, Spyridon, Manolis Maragoudakis, and Aristogiannis Garmpis. "Assisting Educational Analytics with AutoML Functionalities." Computers 11, no. 6 (2022): 97. http://dx.doi.org/10.3390/computers11060097.
Full textAbstract:
The plethora of changes that have taken place in policy formulations on higher education in recent years in Greece has led to unification, the abolition of departments or technological educational institutions (TEI) and mergers at universities. As a result, many students are required to complete their studies in departments of the abolished TEI. Dropout or a delay in graduation is a significant problem that results from newly joined students at the university, in addition to the provision of studies. There are various reasons for this, with student performance during studies being one of the major contributing factors. This study was aimed at predicting the time required for weak students to pass their courses so as to allow the university to develop strategic programs that will help them improve performance and graduate in time. This paper presents various components of educational data mining incorporating a new state-of-the-art strategy, called AutoML, which is used to find the best models and parameters and is capable of predicting the length of time required for students to pass their courses using their past course performance and academic information. A dataset of 23,687 “Computer Networking” module students was used to train and evaluate the classification of a model developed in the KNIME Analytics (open source) data science platform. The accuracy of the model was measured using well-known evaluation criteria, such as precision, recall, and F-measure. The model was applied to data related to three basic courses and correctly predicted approximately 92% of students’ performance and, specifically, students who are likely to drop out or experience a delay before graduating.
19
Muzamil Basha, Syed, Dharmendra Singh Rajput, Ravi Kumar Poluru, S. Bharath Bhushan, and Shaik Abdul Khalandar Basha. "Evaluating the Performance of Supervised Classification Models: Decision Tree and Naïve Bayes Using KNIME." International Journal of Engineering & Technology 7, no. 4.5 (2018): 248. http://dx.doi.org/10.14419/ijet.v7i4.5.20079.
Full textAbstract:
The classification task is to predict the value of the target variable from the values of the input variables. If a target is provided as part of the dataset, then classification is a supervised task. It is important to analysis the performance of supervised classification models before using them in classification task. In our research we would like to propose a novel way to evaluated the performance of supervised classification models like Decision Tree and Naïve Bayes using KNIME Analytics platform. Experiments are conducted on Multi variant dataset consisting 58000 instances, 9 columns associated specially for classification, collected from UCI Machine learning repositories (http://archive.ics.uci.edu/ml/datasets/statlog+(shuttle)) and compared the performance of both the models in terms of Classification Accuracy (CA) and Error Rate. Finally, validated both the models using Metric precision, recall and F-measure. In our finding, we found that Decision tree acquires CA (99.465%) where as Naïve Bayes attain CA (90.358%). The F-measure of Decision tree is 0.984, whereas Naïve Bayes acquire 0.7045.
20
Чеботарь, Антон Викторович, and Максим Иванович Гальченко. "CONFORMAL PREDICTION USAGE FOR THE ACUTE PANCREATITIS OUTCOMES FORECAST." СИСТЕМНЫЙ АНАЛИЗ И УПРАВЛЕНИЕ В БИОМЕДИЦИНСКИХ СИСТЕМАХ, no. 1 (April 19, 2021): 111–16. http://dx.doi.org/10.36622/vstu.2021.20.1.015.
Full textAbstract:
Конформное прогнозирование и его частный случай Мондриановская конформная классификация является новым методом, позволяющим повысить валидность результатов. Конформное прогнозирование удобно в применении и позволяет использовать большинство алгоритмов машинного обучения. Одним из отличий от классических методов является то, что алгоритм конформного прогнозирования позволяет использовать скошенные выборки без предварительной корректировки. В работе рассматривается возможность применения данного метода к задаче прогнозирования течения острого панкреатита на небольшой выборке (91 запись). Рассматривается возможность прогнозирования возникновения инфекционного осложнения и летального исхода. Используется реализация метода в KNIME Analytics Platform, выполненная компанией Redfield AB, Швеция, показывается порядок применения узлов, описываются критерии качества для конформной классификации (эффективность и валидность). Результат позволяет говорить о хороших показателях при применении метода в условиях скошенности классов, в случае прогнозирования исхода, без предварительной корректировки выборки и возможности его применения к небольшим выборкам. Для прогноза исхода эффективность составила 0.67 для класса «Выжил» и 0.14 для класса «Летальный исход», валидность составила 1 и 0.86 соответственно, для прогноза инфекционных осложнений эффективность составила 0.86 для класса «Нет инфекционных осложнений» и 0.43 для «Инфекционные осложнения», валидность 0.71 и о.79 соответственно Conformal prediction and its special case Mondrian conformal classification is a new method that can improve the validity of results significantly. One of the interesting differences from the classical methods is that the conformal prediction algorithm allows using skewed samples without preliminary preprocessing. Possibility of applying this method to the problem of predicting the outcomes of acute pancreatitis on a small sample is studied in the paper (91 records). The implementation of the method in the KNIME Analytics Platform, made by Redfield AB, Sweden, is used, the order of the nodes usage is shown, the quality criteria for the conformal classification (efficiency and validity) are described. The results are allowed to say about good results of applying the method on the sample with skewed classes without preliminary adjusting the sample and the possibility of applying it to small samples. For the “Outcome” variable, the effectiveness was 0.67 for the class "Survived" and 0.14 for the class "Fatal outcome", the validity was 1 and 0.86, respectively, for the prognosis of infectious complications, the effectiveness was 0.86 for the class "No infectious complications" and 0.43 for the class "Infectious complications", validity 0.71 and o.79, respectively
21
Baldi, Niccolò, Alessandro Giorgetti, Alessandro Polidoro, et al. "A Supervised Machine Learning Model for Regression to Predict Melt Pool Formation and Morphology in Laser Powder Bed Fusion." Applied Sciences 14, no. 1 (2023): 328. http://dx.doi.org/10.3390/app14010328.
Full textAbstract:
In the additive manufacturing laser powder bed fusion (L-PBF) process, the optimization of the print process parameters and the development of conduction zones in the laser power (P) and scanning speed (V) parameter spaces are critical to meeting production quality, productivity, and volume goals. In this paper, we propose the use of a machine learning approach during the process parameter development to predict the melt pool dimensions as a function of the P/V combination. This approach turns out to be useful in speeding up the identification of the printability map of the material and defining the conduction zone during the development phase. Moreover, a machine learning method allows for an accurate investigation of the most promising configurations in the P-V space, facilitating the optimization and identification of the P-V set with the highest productivity. This approach is validated by an experimental campaign carried out on samples of Inconel 718, and the effects of some additional parameters, such as the layer thickness (in the range of 30 to 90 microns) and the preheating temperature of the building platform, are evaluated. More specifically, the experimental data have been used to train supervised machine learning models for regression using the KNIME Analytics Platform (version 4.7.7). An AutoML (node for regression) tool is used to identify the most appropriate model based on the evaluation of R2 and MAE scores. The gradient boosted tree model also performs best compared to Rosenthal’s analytical model.
22
Mesa-Varona, Octavio, Carolina Plaza-Rodríguez, Lars Valentin, and Matthias Filter. "WarenstromInfo: a tool for the easy extraction and visualisation of trade flow data." Research Ideas and Outcomes 10 (February 7, 2024): e112227. https://doi.org/10.3897/rio.10.e112227.
Full textAbstract:
Epidemiological outbreak investigations often prove to be lengthy and inconclusive due to the time-consuming nature of the currently-used approaches. An alternative approach to address these challenges could involve the application of algorithms to support authorities and food business operators by providing timely, relevant and reliable information. Algorithms, such as gravity models, could be applied as commodity trade models, but they require a large amount of reliable and consistent data on trade for generating projections at international, national or even regional level. Several trade databases, such as UN COMTRADE, EUROSTAT, BACI, CHELEM and GTAP, provide information on trace, albeit with variations in the provided information and in the structure. However, it is worth noting that not all of these databases are freely accessible and data management can pose challenges, hampering the access to the trade data. WarenstromInfo (WI) was created as a software solution that allows easy trade data extraction and visualisation for application in different areas, such as outbreak investigations.WarenstromInfo (WI) is an application tool that automatically extracts, decodes and visually displays trade flow data from EUROSTAT "EU trade since 2002 by statistical procedure, by HS2-4-6 and CN8 (DS-059322)" (hereinafter referred to EUROSTAT) and the BACI databases, based on user input.WI was developed by using the open-source desktop software KNIME Analytics Platform. WI offers the flexibility to be executed either as a web service on a KNIME Web Server infrastructure or as a local resource.To integrate the BACI database into WI, the database is annually downloaded as csv files, rebuilt as a SQLite database and hosted locally into the KNIME Web Server Infrastructure. In order to optimise storage space on the KNIME server, this SQLite database specifically includes only agrifood data, reflecting the tool´s focus. However, if new objectives are established, this database can be expanded. Further, data of the SQLite database can be customised by executing the WI workflow locally, enabling the user to expand the database at any time.In contrast to BACI, trade data extraction from the EUROSTAT database is performed via the EUROSTAT's API (Application Programming Interface) applying GET requests and XML data management.WI displays four User-friendly Interfaces (UIs) designed with interactive KNIME nodes that facilitate the input of variables. The extracted trade flow data are shown through interactive tables directly within the UIs. This feature enables users to easily explore the data in a structured and user-friendly manner. Additionally, WI incorporates the extracted trade flow data into maps. These maps provide a visual representation of the data, allowing users to gain insights and identify patterns and trends geographically. Both, the data table and the maps, can be downloaded as a single Excel file (containing multiple preformatted tables) and as png files, respectively.
23
Svecla, Monika, Giulia Garrone, Fiorenza Faré, Giacomo Aletti, Giuseppe Danilo Norata, and Giangiacomo Beretta. "DDASSQ: An open‐source, multiple peptide sequencing strategy for label free quantification based on an OpenMS pipeline in the KNIME analytics platform." PROTEOMICS 21, no. 16 (2021): 2000319. http://dx.doi.org/10.1002/pmic.202000319.
Full text
24
Ricciardi, Carlo, Antonio Saverio Valente, Kyle Edmund, et al. "Linear discriminant analysis and principal component analysis to predict coronary artery disease." Health Informatics Journal 26, no. 3 (2020): 2181–92. http://dx.doi.org/10.1177/1460458219899210.
Full textAbstract:
Coronary artery disease is one of the most prevalent chronic pathologies in the modern world, leading to the deaths of thousands of people, both in the United States and in Europe. This article reports the use of data mining techniques to analyse a population of 10,265 people who were evaluated by the Department of Advanced Biomedical Sciences for myocardial ischaemia. Overall, 22 features are extracted, and linear discriminant analysis is implemented twice through both the Knime analytics platform and R statistical programming language to classify patients as either normal or pathological. The former of these analyses includes only classification, while the latter method includes principal component analysis before classification to create new features. The classification accuracies obtained for these methods were 84.5 and 86.0 per cent, respectively, with a specificity over 97 per cent and a sensitivity between 62 and 66 per cent. This article presents a practical implementation of traditional data mining techniques that can be used to help clinicians in decision-making; moreover, principal component analysis is used as an algorithm for feature reduction.
25
Adekitan, Aderibigbe Israel, Adeyinka Adewale, and Alashiri Olaitan. "Determining the operational status of a three phase induction motor using a predictive data mining model." International Journal of Power Electronics and Drive Systems (IJPEDS) 10, no. 1 (2019): 93. http://dx.doi.org/10.11591/ijpeds.v10.i1.pp93-103.
Full textAbstract:
<span lang="EN-GB">The operational performance of a three phase induction motor is impaired by unbalanced voltage supply due to the generation of negative sequence currents, and negative sequence torque which increase motor losses and also trigger torque pulsations. In this study, data mining approach was applied in developing a predictive model using the historical, simulated operational data of a motor for classifying sample motor data under the appropriate type of voltage supply i.e. balanced (BV) and unbalance voltage supply (UB = 1% to 5%). A dataset containing the values of a three phase induction motor’s performance parameter values was analysed using KNIME (Konstanz Information Miner) analytics platform. Three predictive models; the Naïve Bayes, Decision Tree and the Probabilistic Neural Network (PNN) Predictors were deployed for comparative analysis. The dataset was divided into two; 70% for model training and learning, and 30% for performance evaluation. The three predictors had accuracies of 98.649%, 100% and 98.649% respectively, and this confirms the suitability of data mining methods for predictive evaluation of a three phase induction motor’s performance using machine learning</span>
26
Aderibigbe, Israel Adekitan, Adewale Adeyinka, and Olaitan Alashiri. "Determining the operational status of a three phase induction motor using a predictive data mining model." International Journal of Power Electronics and Drive System (IJPEDS) 10, no. 1 (2019): 93–103. https://doi.org/10.11591/ijpeds.v10.i1.pp93-103.
Full textAbstract:
The operational performance of a three-phase induction motor is impaired by unbalanced voltage supply due to the generation of negative sequence currents, and negative sequence torque which increase motor losses and also trigger torque pulsations. In this study, data mining approach was applied in developing a predictive model using the historical, simulated operational data of a motor for classifying sample motor data under the appropriate type of voltage supply i.e. balanced (BV) and unbalance voltage supply (UB = 1% to 5%). A dataset containing the values of a three-phase induction motor’s performance parameter values was analysed using KNIME (Konstanz Information Miner) analytics platform. Three predictive models; the Naïve Bayes, Decision Tree and the Probabilistic Neural Network (PNN) Predictors were deployed for comparative analysis. The dataset was divided into two; 70% for model training and learning, and 30% for performance evaluation. The three predictors had accuracies of 98.649%, 100% and 98.649% respectively, and this confirms the suitability of data mining methods for predictive evaluation of a three-phase induction motor’s performance using machine learning.
27
Хливненко, Л. В., В. В. Елисеев, А. М. Гольцев, and Н. С. Переславцева. "DETERMINATION OF NEURAL NETWORK CONFIGURATION PARAMETERS FOR APPROXIMATION OF EXPERIMENTAL TENSILE CURVES." ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА, no. 5 (November 17, 2022): 17–24. http://dx.doi.org/10.36622/vstu.2022.18.5.002.
Full textAbstract:
Излагается способ решения задачи аппроксимации экспериментальных диаграмм растяжения искусственными нейронными сетями с архитектурой многослойного персептрона. Компьютерное моделирование обучения и функционирования обученной нейронной сети в режиме прогнозирования выполнено в Knime Analytics Platform. Для обучения сети использован метод RProp. Качество аппроксимации оценивалось по значениям показателей MSE и R 2 . Количество скрытых слоев и количество нейронов в них оказывает влияние на качество моделирования в прямой пропорциональной зависимости. При увеличении этих показателей наблюдается рост размерности матрицы весовых коэффициентов связей между нейронами. В этой связи актуальным является вопрос об оптимальном выборе внутренней структуры сети. Было изучено влияние конфигурации нейронной сети на качество аппроксимации на примере диаграммы растяжения образца, изготовленного из горячекатаного стального проката со степенью прессования 37%. Наилучшие результаты получены для модели с 4 скрытыми слоями по 40 нейронов в каждом слое. Найденная конфигурация нейронной сети апробирована на том же материале из горячекатаного стального проката со степенями прессования 16% и 6%, на высокопрочной борированной стали, на сером чугуне и полипропиленовом композитном материале с длинным стекловолокном. Проведенные исследования показали, что нейронная сеть с найденной конфигурацией успешно может быть использована для аппроксимации диаграмм растяжения образцов, изготовленных из разных материалов We described a method for solving the problem of approximating experimental tensile curves by artificial neural networks with architecture of multilayer perceptron. Computer modeling of the neural network was performed in Knime Analytics Platform. The RProp method was used to train the network. The quality of the approximation was assessed by the values of the MSE и R 2 indicators. The number of hidden layers and the number of neurons in them affects the quality of modeling in a direct proportional relationship. With an increase in these indicators, an increase in the dimension of the matrix of weight coefficients of connections between neurons is observed. In this regard, the question of the optimal choice of the internal structure of the network is relevant. The influence of the neural network configuration on the quality of the approximation was studied using tensile curve of specimen was made of hot-rolled steel with a pressing degree of 37%. The best results were obtained for the model with 4 hidden layers with 40 neurons in each layer. The found configuration of the neural network was tested on the same material from hot-rolled steel with pressing degrees of 16% and 6%, on high-strength boron steel, on gray cast iron, and on a polypropylene composite material with long glass fiber. The conducted studies have shown that a neural network with the found configuration can be successfully used to approximate the tensile curves of specimens made from different materials
28
Mucs, D., A. Borrel, T. Auman, T. Hirata, L. Neilson, and I. Baskerville-Abraham. "P05-04 Development of an open-source high throughput QSAR-parameterized PBTK prediction model workflow using httk, OPERA and the KNIME Analytics Platform." Toxicology Letters 399 (September 2024): S133. http://dx.doi.org/10.1016/j.toxlet.2024.07.340.
Full text
29
Evans, Edward L., Ginger M. Pocock, Gabriel Einsdorf, et al. "HIV RGB: Automated Single-Cell Analysis of HIV-1 Rev-Dependent RNA Nuclear Export and Translation Using Image Processing in KNIME." Viruses 14, no. 5 (2022): 903. http://dx.doi.org/10.3390/v14050903.
Full textAbstract:
Single-cell imaging has emerged as a powerful means to study viral replication dynamics and identify sites of virus–host interactions. Multivariate aspects of viral replication cycles yield challenges inherent to handling large, complex imaging datasets. Herein, we describe the design and implementation of an automated, imaging-based strategy, “Human Immunodeficiency Virus Red-Green-Blue” (HIV RGB), for deriving comprehensive single-cell measurements of HIV-1 unspliced (US) RNA nuclear export, translation, and bulk changes to viral RNA and protein (HIV-1 Rev and Gag) subcellular distribution over time. Differentially tagged fluorescent viral RNA and protein species are recorded using multicolor long-term (>24 h) time-lapse video microscopy, followed by image processing using a new open-source computational imaging workflow dubbed “Nuclear Ring Segmentation Analysis and Tracking” (NR-SAT) based on ImageJ plugins that have been integrated into the Konstanz Information Miner (KNIME) analytics platform. We describe a typical HIV RGB experimental setup, detail the image acquisition and NR-SAT workflow accompanied by a step-by-step tutorial, and demonstrate a use case wherein we test the effects of perturbing subcellular localization of the Rev protein, which is essential for viral US RNA nuclear export, on the kinetics of HIV-1 late-stage gene regulation. Collectively, HIV RGB represents a powerful platform for single-cell studies of HIV-1 post-transcriptional RNA regulation. Moreover, we discuss how similar NR-SAT-based design principles and open-source tools might be readily adapted to study a broad range of dynamic viral or cellular processes.
30
Konnikov, Evgeny A., Olesya D. Starchenkova, and Ekaterina V. Burova. "THE INFLUENCE OF SOCIO-PSYCHOLOGICAL CONTEXT ON THE EDUCATIONAL ENVIRONMENT." EKONOMIKA I UPRAVLENIE: PROBLEMY, RESHENIYA 12/8, no. 141 (2023): 147–59. http://dx.doi.org/10.36871/ek.up.p.r.2023.12.08.012.
Full textAbstract:
The relevance of this topic is due to the subtle mental organization of adolescents and the influence of social and informational factors and factors of the educational environment on it. By external factors, the authors mean psychological triggers and other factors that indirectly or directly affect the psychological state of students. The purpose of the work is to identify the most significant factors of the socio-psychological environment, as well as determine their influence on the level of education in the region. The article provides the results of an analysis of the significance of these factors, carried out a procedure for assessing the quality of the constructed equations, and derived patterns in the dynamics of the indicator “number of universities” and “proportion of graduates who did not receive a certificate of secondary education. Mathematical and statistical data processing was carried out using the KNIME Analytics Platform. The source of the statistical database is the Federal State Statistics Service (EMISS). Data on the indicators were collected for 81 constituent entities of the Russian Federation in 2019 and can be conditionally divided into two groups: education and psychology.
31
Tan Wei Feng, Raihana Edros, Ngahzaifa Ab Ghani, Siti Umairah Mokhtar, and RuiHai Dong. "Prediction of Blood-Brain Barrier Permeability of Compounds by Machine Learning Algorithms." Journal of Advanced Research in Applied Sciences and Engineering Technology 33, no. 2 (2023): 269–76. http://dx.doi.org/10.37934/araset.33.2.269276.
Full textAbstract:
In the drug development for the Central Nervous System (CNS), the discovery of the compounds that can pass through the brain across the Blood-Brain Barrier (BBB) is the most challenging assessment. Almost 98% of small molecules are unable to permeate BBB, reducing the pharmacokinetics of the drugs in the CNS by affecting its absorption, distribution, metabolism, and excretion (ADME) mechanisms. Since the CNS is often inaccessible to many complex procedures and performing in-vitro permeability studies for thousands of compounds can be laborious, attempts were made to predict the permeation of compounds through BBB by implementing the Machine Learning (ML) approach. In this work, using the KNIME Analytics platform, 4 predictive models were developed with 4 ML algorithms followed by a ten-fold cross-validation approach to predict the external validation set. Among 4 ML algorithms, Extreme Gradient Boosting (XGBoost) overperformed in BBB permeability prediction and was chosen as the prediction model for deployment. Data pre-processing and feature selection enhanced the prediction of the model. Overall, the model achieved 86.7% and 88.5% of accuracy and 0.843 and 0.927 AUC, respectively in the training set and external validation set, proving that the model with high stability in prediction.
32
Irina, Ionită, and Ionită Liviu. "BRAIN Journal - Prediction of Thyroid Disease Using Data Mining Techniques." BRAIN - Broad Research in Artificial Intelligence and Neuroscience 7, no. 3 (2016): 115–24. https://doi.org/10.5281/zenodo.1044963.
Full textAbstract:
ABSTRACT Recently, thyroid diseases are more and more spread worldwide. In Romania, for example, one of eight women suffers from hypothyroidism, hyperthyroidism or thyroid cancer. Various research studies estimate that about 30% of Romanians are diagnosed with endemic goiter. Factors that affect the thyroid function are: stress, infection, trauma, toxins, low-calorie diet, certain medication etc. It is very important to prevent such diseases rather than cure them, because the majority of treatments consist in long term medication or in chirurgical intervention. The current study refers to thyroid disease classification in two of the most common thyroid dysfunctions (hyperthyroidism and hypothyroidism) among the population. The authors analyzed and compared four classification models: Naive Bayes, Decision Tree, Multilayer Perceptron and Radial Basis Function Network. The results indicate a significant accuracy for all the classification models mentioned above, the best classification rate being that of the Decision Tree model. The data set used to build and to validate the classifier was provided by UCI machine learning repository and by a website with Romanian data. The framework for building and testing the classification models was KNIME Analytics Platform and Weka, two data mining software.
33
Muhammad Fawwaz Narendra. "Forecasting Manpower Planning Using the CRISP-DM Method and Machine Learning Algorithm: A Case Study of Tiki Jalur Nugraha Ekakurir (JNE) Company." Journal of Information Systems Engineering and Management 10, no. 19s (2025): 371–78. https://doi.org/10.52783/jisem.v10i19s.3040.
Full textAbstract:
Introduction: The logistics industry faces significant fluctuations in demand, particularly during peak seasons, making effective manpower planning essential to maintaining service quality and controlling operational costs. Poor workforce planning can lead to inefficiencies such as overstaffing, which increases costs, or understaffing, which negatively impacts delivery performance. To address these challenges, this research focuses on developing a predictive analytics model for workforce planning at Tiki Jalur Nugraha Ekakurir (JNE) Company, a leading logistics company in Indonesia. By leveraging machine learning and dashboard modeling, the study aims to enhance decision-making and improve workforce efficiency during high-demand periods. Objectives: This research is driven by the need to develop a predictive analytics model capable of forecasting workforce requirements during peak seasons. The goal is to optimize manpower allocation based on shipment trends and provide real-time insights through an interactive dashboard. Methods: A quantitative approach is applied, following the CRISP-DM framework, which includes business understanding, data preparation, model development, and evaluation. The dataset consists of historical shipment records, workforce availability, and external factors like public holidays and promotional events. Machine learning models, including linear regression and Gradient Boosted Trees (GBT), are implemented using KNIME Analytics Platform to enhance forecasting accuracy. Results: The GBT model with six lag columns provided the most accurate predictions, achieving a Mean Absolute Percentage Error (MAPE) below 5%. To support real-time decision-making, a Manpower Planning Dashboard was developed, visualizing shipment trends, staffing requirements, and workforce distribution. By utilizing this system, JNE Company was able to improve task allocation by 15% and reduce overtime costs by 10%, demonstrating the benefits of predictive analytics in workforce management. Conclusions: In summary, this study successfully introduces a data-driven approach to manpower planning by integrating predictive analytics with an interactive dashboard. The model enhances workforce distribution, minimizes inefficiencies, and optimizes logistics operations. Moving forward, JNE Company can further refine this system by incorporating real-time data updates, considering external factors like weather conditions and customer demand fluctuations, and expanding predictive capabilities to other areas such as warehouse management and route optimization. By embracing these innovations, JNE Company can strengthen its market position, improve operational efficiency, and ensure optimal workforce allocation, particularly during peak seasons.
34
Ricciardi, Carlo, Halldór Jónsson, Deborah Jacob, et al. "Improving Prosthetic Selection and Predicting BMD from Biometric Measurements in Patients Receiving Total Hip Arthroplasty." Diagnostics 10, no. 10 (2020): 815. http://dx.doi.org/10.3390/diagnostics10100815.
Full textAbstract:
There are two surgical approaches to performing total hip arthroplasty (THA): a cemented or uncemented type of prosthesis. The choice is usually based on the experience of the orthopaedic surgeon and on parameters such as the age and gender of the patient. Using machine learning (ML) techniques on quantitative biomechanical and bone quality data extracted from computed tomography, electromyography and gait analysis, the aim of this paper was, firstly, to help clinicians use patient-specific biomarkers from diagnostic exams in the prosthetic decision-making process. The second aim was to evaluate patient long-term outcomes by predicting the bone mineral density (BMD) of the proximal and distal parts of the femur using advanced image processing analysis techniques and ML. The ML analyses were performed on diagnostic patient data extracted from a national database of 51 THA patients using the Knime analytics platform. The classification analysis achieved 93% accuracy in choosing the type of prosthesis; the regression analysis on the BMD data showed a coefficient of determination of about 0.6. The start and stop of the electromyographic signals were identified as the best predictors. This study shows a patient-specific approach could be helpful in the decision-making process and provide clinicians with information regarding the follow up of patients.
35
Somashekar, Harshitha, and Ramesh Boraiah. "Network intrusion detection and classification using machine learning predictions fusion." Indonesian Journal of Electrical Engineering and Computer Science 31, no. 2 (2023): 1147. http://dx.doi.org/10.11591/ijeecs.v31.i2.pp1147-1153.
Full textAbstract:
The primary objective of an intrusion detection system (IDS) is to monitor the network performance and to look into any indications of malformation over the network. While providing high-security network IDS played a vital role for the past couple of years. IDS will fail to identify all types of attacks, when it comes to anomaly detection, it is often connected with a high false alarm rate with accuracy and the detection rate is very average. Recently, IDS utilize machine learning methods, because of the way that machine learning algorithms demonstrated to have the capacity of learning and adjusting as well as permitting a proper reaction for real-time data. This work proposes a prediction-level fusion model for intrusion detection and classification using machine learning techniques. This work also proposes retraining of model for unknown attacks to increase the effectiveness of classification in IDS. The experiments are carried out on the network security layer knowledge discovery in database (NSL-KDD) dataset using the Konstanz information miner (KNIME) analytics platform. The experimental results showed a classification accuracy of 90.03% for a simple model to 96.31% for fusion and re-trained models. This result inspires the researchers to use machine learning techniques with a fusion model to build IDS.
36
Harshitha, Somashekar, and Boraiah Ramesh. "Network intrusion detection and classification using machine learning predictions fusion." Indonesian Journal of Electrical Engineering and Computer Science 32, no. 2 (2023): 1147–53. https://doi.org/10.11591/ijeecs.v31.i2.pp1147-1153.
Full textAbstract:
The primary objective of an intrusion detection system (IDS) is to monitor the network performance and to look into any indications of malformation over the network. While providing high-security network IDS played a vital role for the past couple of years. IDS will fail to identify all types of attacks, when it comes to anomaly detection, it is often connected with a high false alarm rate with accuracy and the detection rate is very average. Recently, IDS utilize machine learning methods, because of the way that machine learning algorithms demonstrated to have the capacity of learning and adjusting as well as permitting a proper reaction for real-time data. This work proposes a prediction-level fusion model for intrusion detection and classification using machine learning techniques. This work also proposes retraining of model for unknown attacks to increase the effectiveness of classification in IDS. The experiments are carried out on the network security layer knowledge discovery in database (NSL-KDD) dataset using the Konstanz information miner (KNIME) analytics platform. The experimental results showed a classification accuracy of 90.03% for a simple model to 96.31% for fusion and re-trained models. This result inspires the researchers to use machine learning techniques with a fusion model to build IDS.
37
Lettieri, M., D. Mucs, L. Sartori, A. Ciacci, L. Broccardo, and I. Baskerville-Abraham. "P06-26: Using the KNIME Analytics Platform for the analysis of different combination of evidence approaches with toxicological predictions from VEGA and OECD (Q)SAR Toolbox." Toxicology Letters 384 (September 2023): S112. http://dx.doi.org/10.1016/s0378-4274(23)00530-1.
Full text
38
Scaccia, Nazareno, Taras Günther, de Abechuco Estibaliz Lopez, and Matthias Filter. "The Glossaryfication Web Service: an automated glossary creation tool to support the One Health community." Research Ideas and Outcomes 7 (August 6, 2021): e70183. https://doi.org/10.3897/rio.7.e70183.
Full textAbstract:
In many interdisciplinary research domains, the creation of a shared understanding of relevant terms is considered the foundation for efficient cross-sector communication and interpretation of data and information. This is also true for the domain of One Health (OH) where many One Health Surveillance (OHS) documents rarely contain glossaries with a list of terms for which their specific meaning in the context of the given document is defined (Cornelia et al. 2018, Buschhardt et al. 2021). The absence of glossaries within these documents may lead to misinterpretation of surveillance results due to the wrong interpretation of terminology specifically when term definitions differ across OH sectors. Under the One Health EJP project ORION, the OHEJP Glossary was recently created. The OHEJP Glossary is a tool to improve communication and collaboration amongst OH sectors by providing an easy-to-use online resource that lists relevant OH terms and sector-specific definitions. To improve the accessibility of content from the OHEJP Glossary and support the creation of integrative glossaries in future OHS-related documents, the OHEJP Glossaryfication Web Service was created. This service can support the practical use of the OHEJP Glossary and other relevant online glossaries by OH professionals.The Glossaryfication Web Service (GWS) is an application that automatically identifies terms in any uploaded text-based document and creates a document-specific list of matching definitions in selected online glossaries. This auto-generated document-specific glossary can easily be adjusted by the user, for example, by selecting the desired definition in case multiple definitions were found for a specific term. The document-specific glossary could then be downloaded, manually adjusted and finally included into the original document where it supports the correct interpretation of terminology used. Especially in sector-specific reports, such as from animal health or public health authorities, this can be beneficial to ensure the correct interpretation by other OH sectors in the future. The GWS was developed with the open-source desktop software KNIME Analytics Platform and runs as a web service on a KNIME Web Server infrastructure. The core data processing functionality in the GWS is based on KNIME's Text Processing extension. KNIME's JavaScript nodes provided the basis for an interactive user interface where users can easily upload their files and select between different reference glossaries, such as the OHEJP Glossary, the CDC Glossary, the WHO Glossary or the EFSA Glossary. After retrieval of the user input settings, the GWS tags words within the provided document and maps these tagged words with matching entries in the selected glossaries. As the main output, the user receives a downloadable list of matching terms with their corresponding definitions, sectorial assignments and references, which can then be added by the user to the original document. The GWS is freely accessible via this link as well as the underlying KNIME workflow.
39
Monteiro, Alex France Messias, Marcus Tullius Scotti, Alejandro Speck-Planche, Renata Priscila Costa Barros, and Luciana Scotti. "In Silico Studies for Bacterystic Evaluation against Staphylococcus aureus of 2-Naphthoic Acid Analogues." Current Topics in Medicinal Chemistry 20, no. 4 (2020): 293–304. http://dx.doi.org/10.2174/1568026619666191206111742.
Full textAbstract:
Background: Staphylococcus aureus is a gram-positive spherical bacterium commonly present in nasal fossae and in the skin of healthy people; however, in high quantities, it can lead to complications that compromise health. The pathologies involved include simple infections, such as folliculitis, acne, and delay in the process of wound healing, as well as serious infections in the CNS, meninges, lung, heart, and other areas. Aim: This research aims to propose a series of molecules derived from 2-naphthoic acid as a bioactive in the fight against S. aureus bacteria through in silico studies using molecular modeling tools. Methods: A virtual screening of analogues was done in consideration of the results that showed activity according to the prediction model performed in the KNIME Analytics Platform 3.6, violations of the Lipinski rule, absorption rate, cytotoxicity risks, energy of binder-receptor interaction through molecular docking, and the stability of the best profile ligands in the active site of the proteins used (PDB ID 4DXD and 4WVG). Results: Seven of the 48 analogues analyzed showed promising results for bactericidal action against S. aureus. Conclusion: It is possible to conclude that ten of the 48 compounds derived from 2-naphthoic acid presented activity based on the prediction model generated, of which seven presented no toxicity and up to one violation to the Lipinski rule.
40
Ricciardi, Carlo, Alfonso Maria Ponsiglione, Arianna Scala, et al. "Machine Learning and Regression Analysis to Model the Length of Hospital Stay in Patients with Femur Fracture." Bioengineering 9, no. 4 (2022): 172. http://dx.doi.org/10.3390/bioengineering9040172.
Full textAbstract:
Fractures of the femur are a frequent problem in elderly people, and it has been demonstrated that treating them with a diagnostic–therapeutic–assistance path within 48 h of admission to the hospital reduces complications and shortens the length of the hospital stay (LOS). In this paper, the preoperative data of 1082 patients were used to further extend the previous research and to generate several models that are capable of predicting the overall LOS: First, the LOS, measured in days, was predicted through a regression analysis; then, it was grouped by weeks and was predicted with a classification analysis. The KNIME analytics platform was applied to divide the dataset for a hold-out cross-validation, perform a multiple linear regression and implement machine learning algorithms. The best coefficient of determination (R2) was achieved by the support vector machine (R2 = 0.617), while the mean absolute error was similar for all the algorithms, ranging between 2.00 and 2.11 days. With regard to the classification analysis, all the algorithms surpassed 80% accuracy, and the most accurate algorithm was the radial basis function network, at 83.5%. The use of these techniques could be a valuable support tool for doctors to better manage orthopaedic departments and all their resources, which would reduce both waste and costs in the context of healthcare.
41
Lewandowski, Dirk, and Sebastian Sünkler. "What does Google recommend when you want to compare insurance offerings?" Aslib Journal of Information Management 71, no. 3 (2019): 310–24. http://dx.doi.org/10.1108/ajim-07-2018-0172.
Full textAbstract:
Purpose The purpose of this paper is to describe a new method to improve the analysis of search engine results by considering the provider level as well as the domain level. This approach is tested by conducting a study using queries on the topic of insurance comparisons. Design/methodology/approach The authors conducted an empirical study that analyses the results of search queries aimed at comparing insurance companies. The authors used a self-developed software system that automatically queries commercial search engines and automatically extracts the content of the returned result pages for further data analysis. The data analysis was carried out using the KNIME Analytics Platform. Findings Google’s top search results are served by only a few providers that frequently appear in these results. The authors show that some providers operate several domains on the same topic and that these domains appear for the same queries in the result lists. Research limitations/implications The authors demonstrate the feasibility of this approach and draw conclusions for further investigations from the empirical study. However, the study is a limited use case based on a limited number of search queries. Originality/value The proposed method allows large-scale analysis of the composition of the top results from commercial search engines. It allows using valid empirical data to determine what users actually see on the search engine result pages.
42
Minaev, Dmitry V. "The Study of the Educational Program Competence Model Based on the Intellectual Analysis of the Labor Market Professional Requirements." Administrative Consulting, no. 10 (166) (June 7, 2022): 65–83. https://doi.org/10.22394/1726-1139-2022-10-65-83.
Full textAbstract:
The educational standards of higher education — FGOS3++ require designing educational programs (EP) based on professional competencies in demand in the labor market. It is recommended to use professional standards. This way has certain disadvantages. For example, professional standards describe labor functions, but in the EP competencies are required. The use of professional standards in the development of the EP obviously determines a certain lag in the reaction in the labor market changes. An alternative to such EP design is a direct analysis of market requirements. Intelligent Analysis (IA) tools: data mining and machine learning can facilitate such analysis. An overview of developments in this direction is given. The results of the application of IA based on the KNIME analytical platform for determining the competence model of the EP in the field of project management are presented. Automation affected:the collection of requirements for more than 6000 vacancies of employers of the HeadHunter online resource; the analysis of texts presented in natural language (descriptions of EP of different universities, professional standards and guidance materials of professional associations — SOVNET-Agile, IPMA OCB&ICB). Based on these data sets was carried out: tokenization, collocation of terms and topics, clustering of topics, the cross-classification of professional standards and guidance materials based on a pre-trained competence model of the EP.The results confirmed the efficiency of the used technique. Such analytics allows us to dynamically systematize descriptions of professional activities and formulate considerations about the elements, structure, and mutual correspondence of the EP competence models and the competencies natural models on the labor market. In combination with the traditional expert assessment, it can contribute to the formation of a more complete isomorphism between the qualifications of EP and professional activity.
43
Gunawan, Gunawan, and Thi Lip Sam. "Exploring the Association between Mobility Fluctuations and Socioeconomic Indicators Using Data Mining Techniques in Indonesia and Malaysia." DIU Journal of Business and Entrepreneurship 16, no. 01 (2023): 79–105. http://dx.doi.org/10.36481/diujbe.v016i1.w8qv3970.
Full textAbstract:
Human mobility has become a global issue during the Covid-19 pandemic and is believed to be a critical factor in the transmission of Covid -19. The timetable for the government's movement control has stimulated the fluctuation of national mobility. However, the characteristics of variations between regions of the country are not yet understood. The purpose of this study was to characterise community mobility fluctuations in Indonesia and Malaysia and identify the association between socioeconomic indicators and mobility fluctuations in regions. This secondary and exploratory research investigated 34 Indonesian provinces and 14 Malaysian states. Data mining approaches using the CRISP-DM framework and the Knime Analytics platform was used. As a result, Indonesia and Malaysia show the strength of mobility fluctuations in decreasing order: transit stations, workplaces, and residential areas. Malaysia shows higher mobility fluctuations than Indonesia, which may indicate the community's response to the Covid-19 pandemic. As socioeconomic indicators, Human Development Index (HDI), poverty rate, and labor force participation are associated with the fluctuation of mobility. Therefore, regions with high fluctuation in mobility will likely have high HDI, high labour force participation rates, and low poverty rates. High-mobility areas include capitals and other cities with high-density populations. This study provides evidence that socioeconomic indicators are determinants of mobility fluctuation during the pandemic. Regional governments may use the findings to anticipate community mobility and planning policies when similar pandemic conditions occur.
44
Minaev, D. V. "The Study of the Educational Program Competence Model Based on the Intellectual Analysis of the Labor Market Professional Requirements." Administrative Consulting, no. 10 (December 6, 2022): 65–83. http://dx.doi.org/10.22394/1726-1139-2022-10-65-83.
Full textAbstract:
The educational standards of higher education — FGOS3++ require designing educational programs (EP) based on professional competencies in demand in the labor market. It is rec ommended to use professional standards. This way has certain disadvantages. For example, professional standards describe labor functions, but in the EP competencies are required. The use of professional standards in the development of the EP obviously determines a certain lag in the reaction in the labor market changes. An alternative to such EP design is a direct analysis of market requirements. Intelligent Analysis (IA) tools: data mining and machine learning can facilitate such analysis. An overview of developments in this direction is given. The results of the application of IA based on the KNIME analytical platform for determining the competence model of the EP in the feld of project management are presented. Automation affected:the collection of requirements for more than 6000 vacancies of employers of the Head Hunter online resource; the analysis of texts presented in natural language (descriptions of EP of different universities, professional standards and guidance materials of professional associations — SOVNET-Agile, IPMA OCB&ICB). Based on these data sets was carried out: tokenization, collocation of terms and topics, clustering of topics, the cross-classifcation of professional standards and guidance materials based on a pre-trained competence model of the EP. The results confrmed the efciency of the used technique. Such analytics allows us to dynamically systematize descriptions of professional activities and formulate considerations about the elements, structure, and mutual correspondence of the EP competence models and the competencies natural models on the labor market. In combination with the traditional expert assessment, it can contribute to the formation of a more complete isomorphism between the qualifcations of EP and professional activity.
45
Khlivnenko, L. V., V. V. Eliseev, and A. M. Goltsev. "Neural network approximation of deformation curves under uniaxial tension of steel and silumin specimens." Industrial laboratory. Diagnostics of materials 89, no. 4 (2023): 71–76. http://dx.doi.org/10.26896/1028-6861-2023-89-4-71-76.
Full textAbstract:
The purpose of the study is developing and testing of the new computational technique for approximation of deformation curves of steel and silumin specimens under uniaxial tension. A scheme of testing steel and silumin specimens for uniaxial tensile is presented. The experiment was carried out in the mechanical testing laboratory of the Department of Applied Mathematics and Mechanics of the Voronezh State Technical University. The experimental deformation curve of a steel specimen was approximated by P. Ludwig’s equation. Prediction of the true stress from the logarithmic strain using a pretrained artificial neural network with a multilayer perceptron architecture is discussed. The neural network model was trained using the RProp (resilient backpropagation) method. The software implementation of the neural network approximation was carried out in a framework of the open source for data analysis — Knime Analytics Platform. A scheme for the implementation of a multilayer perceptron that solves the approximation problem is considered. The simulation results are compared by the values of the mean squared error (MSE) of the approximation. The neural network approximation is turned out to be an order of magnitude more accurate for the steel specimen than the approximation by the P. Ludwig equation. The neural network approximation provided even a smaller MSE value for a silumin specimen than that or a steel specimen. It is revealed that changing the architecture of an artificial neural network affects the quality of modeling. With an increase in the number of hidden layers, the accuracy of the approximation increases. Neural network approximation is an effective approach to solving the problem of the analytical description of experimental deformation curves and leaves the possibility of using a universal technique for a variety of materials and different types of tests.
46
S., Surendar, and Elangovan M. "Comparison of Surface Roughness Prediction with Regression and Tree Based Regressions during Boring Operation." Indonesian Journal of Electrical Engineering and Computer Science 5, no. 1 (2017): 887–92. https://doi.org/10.11591/ijeecs.v7.i3.pp887-892.
Full textAbstract:
Modern manufacturing methods permit the study and prediction of surface roughness since the acquisition of signals and its processing is made instantaneously. With the availability of better computing facilities and newer algorithms in the machine learning domain, online surface roughness prediction will lead to the manufacture of intelligent machines that alert the operator when the process crosses the specified range of roughness. Prediction of surface roughness by multiple linear regression, regression tree and M5P tree methods using multivariable predictors and a single response dependent variable Ra (surface roughness) is attempted. Vibration signal from the boring operation has been acquired for the study that predicts the surface roughness on the inner face of the workpiece. A machine learning approach was used to extract the statistical features and analyzed by four different cases to achieve higher predictability, higher accuracy, low computing effort and reduction of the root mean square error. One case among them was carried out upon feature reduction using Principle Component Analysis (PCA) to examine the effect of feature reduction.
47
Sulaiman, Badie H., Amer M. Ibrahim, and Hadeel J. Imran. "Deep Learning-Based Keras Network Formulation for Predicting the Shear Capacity of Squat RC Walls and Sensitivity Analysis." Tikrit Journal of Engineering Sciences 32, no. 2 (2025): 1–16. https://doi.org/10.25130/tjes.32.2.11.
Full textAbstract:
Squat-reinforced concrete (RC) shear walls with an aspect ratio of less than two are commonly used as lateral load-resisting buildings. It is frequently utilized in nuclear power plants and building structures due to its lateral strength and high stiffness. It is distinguished by its optimal cost and excellent performance. Nonetheless, precise assessment of the shear strength of squat shear walls is crucial for design specifications, and its computation can be exceedingly variable and intricate due to several efficient, expensive, and time-consuming constraining elements. The present study utilizes Keras deep learning techniques to develop a model for predicting the shear strength of squat RC walls to find a way to overcome these issues. The most comprehensive dataset of 1424 RC squat wall test specimens collected from the published literature to date has been used to develop the proposed deep learning model as well as three well-known machine learning models: RF, ANN, and LR. The results demonstrated that the Keras network exhibited a lower error rate and higher accuracy when predicting the shear strength of squat walls compared to earlier machine learning models, achieving 97.3% accuracy compared with the highest value in the RF algorithm, reaching 93.4%. Furthermore, parametric and sensitivity analyses were performed to verify that the algorithms can identify the most significant variables significantly influencing shear strength. The results showed that the (hw) was the most influencing factor on the peak shear strength of the squat shear wall as a ratio (6.36%), according to the results of the sensitivity analysis, followed by (lw) as a (5.10%), (tf) (4.96%), ( f´c ) (4.69%), (tw) (4.06%), (fy) of the web as a ratio (3.94%), and (ρh) (3.89%). These results and analyses were obtained using the (KNIME) analytics platform software, characterized by its vital role in precise computing operations and simple handling without the need for codes to reduce costs and time, and it was supported for Python and R languages.
48
Shaladonova, M. I., Ya V. Dzichenka, and S. A. Usanov. "Predictive model for identifying new CYP19A1 ligands on the KNIME analytical platform." Doklady of the National Academy of Sciences of Belarus 67, no. 5 (2023): 388–98. http://dx.doi.org/10.29235/1561-8323-2023-67-5-388-398.
Full textAbstract:
The purpose of this study was to create a database of the chemical compounds – ligands of human steroid-hydroxylating cytochrome CYP19A1 (aromatase) in order to build a predictive model. The idea was to create a model on the basis of the machinery learning method such as random forest for two types of ligands – with steroidal (I type) and non-steroidal structure (II type). Two predictive models were built with the help of the KNIME analytical platform. Topological descriptors of the chemical structure were used as training data when building a model that takes into account their correlation between the structure of the molecule and the biological effect. The selection of the feature importance of the descriptors, optimal parameters of random forest and the definition of applicability domain of the models were carried out. The assessment of the ability to predict the results of a test sample was performed for each model. The quality marks of the obtained models indicated a rather high predictive ability of the models and the prospects of their use for identification of new human CYP19A1 ligands as potential drugs for treatment of hormone-dependent tumors.
49
Bilgin, Turgay Tugay, Süleyman Burak Altınışık, and Nihat Aydın Adıgüzel. "A Comparative Study of Classification and Clustering Methods for Data Analysis in Digital Transformation and IoT Systems." Orclever Proceedings of Research and Development 3, no. 1 (2023): 1–18. http://dx.doi.org/10.56038/oprd.v3i1.280.
Full textAbstract:
This study employs classification and clustering methodologies on datasets derived from digital transformation and Internet of Things (IoT) initiatives within the cable and automotive sectors. The analytical procedures are conducted utilizing the KNIME platform, employing Support Vector Machines (SVM) and K-Means algorithms. The results indicate that SVM exhibits superior accuracy rates compared to K-Means within both industries. The data collection methodology facilitated by the Mert Software IoT platform is identified as reliable and efficacious. The primary objective of this article is to augment decision-making precision in digital transformation software and contribute to the scholarly discourse within this domain.
50
Falcón-Cano, Gabriela, Christophe Molina, and Miguel Ángel Cabrera-Pérez. "Reliable Prediction of Caco-2 Permeability by Supervised Recursive Machine Learning Approaches." Pharmaceutics 14, no. 10 (2022): 1998. http://dx.doi.org/10.3390/pharmaceutics14101998.
Full textAbstract:
The heterogeneity of the Caco-2 cell line and differences in experimental protocols for permeability assessment using this cell-based method have resulted in the high variability of Caco-2 permeability measurements. These problems have limited the generation of large datasets to develop accurate and applicable regression models. This study presents a QSPR approach developed on the KNIME analytical platform and based on a structurally diverse dataset of over 4900 molecules. Interpretable models were obtained using random forest supervised recursive algorithms for data cleaning and feature selection. The development of a conditional consensus model based on regional and global regression random forest produced models with RMSE values between 0.43–0.51 for all validation sets. The potential applicability of the model as a surrogate for the in vitro Caco-2 assay was demonstrated through blind prediction of 32 drugs recommended by the International Council for the Harmonization of Technical Requirements for Pharmaceuticals (ICH) for validation of in vitro permeability methods. The model was validated for the preliminary estimation of the BCS/BDDCS class. The KNIME workflow developed to automate new drug prediction is freely available. The results suggest that this automated prediction platform is a reliable tool for identifying the most promising compounds with high intestinal permeability during the early stages of drug discovery.