Machine learning

Using machine and deep learning techniques the authors introduce pre-processing methods applied to satellite images to identify land cover features, detect object, classify crops, recognize targets, and monitor and support earth resources. Readers will need a basic understanding of computing, remote sensing and image interpretation.

The book (proceedings of the 4th International Conference on Deep Learning, Artificial Intelligence and Robotics (ICDLAIR) 2022) introduces key topics from artificial intelligence algorithms and programming organisations and explains how they contribute to health care, manufacturing, law, finance, retail, real estate, accountancy, digital marketing, and various other fields. Although artificial intelligence (AI) has generated a lot of hype over the past ten years, these consequences on how we live, work, and play are still in their infancy and will likely have a significant impact in the future. The supremacy of AI in areas like speech and picture recognition, navigational apps, personal assistants for smartphones, ride-sharing apps, and many other areas is already well established. The book is primarily meant for academics, researchers, and engineers who want to employ AI applications to address real-world issues. The authors hope that businesses and technology creators will also find it appealing to utilise in industry.

Knowledge Science beschäftigt sich mit Konzepten, Methoden und Prozessen zur systematischen Erzeugung, Extraktion, Speicherung und Bereitstellung von Wissen zur Lösung von Problemen und lässt sich somit dem Wissensmanagement zuordnen. Kognitive Assistenten sorgen dafür, das richtige Wissen zur richtigen Zeit in der richtigen Art und Weise seinen Anwendern und Anwenderinnen bereitzustellen. Damit dies gelingen kann, kommen inzwischen zahlreiche Methoden der Künstlichen Intelligenz (KI) zur Unterstützung unterschiedlicher Aufgaben des Wissensmanagements zum Einsatz.

In einer VUCA-Welt, die sich als immer unbeständiger, unsicherer und komplexer erweist, gilt es für Unternehmen, Organisation und Staaten zeitnah und adäquat auf die jeweiligen Situationen zu reagieren. Entscheidungen basierend auf in der Vergangenheit gemachten Erfahrungen zu treffen ist in diesen Zeiten weniger erfolgreich als ein akkurates Verständnis der gegenwärtigen Bedingungen. Die Bedeutung von empirischen Wissenschaften, das permanente Beobachten der Umwelt, die zeitnahe Analyse von Wirkungszusammenhängen und das daraus abgeleitete Gewinnen neuer Erkenntnissen, nimmt zu. Daraus lässt sich ableiten, welche Maßnahmen mit einer vorhersagbaren Wahrscheinlichkeit zur Erreichung der eigenen Ziele geeignet sind, z.B. welcher Preis für ein Angebot die gewünschte Nachfrage erzeugt oder welche Marketingmaßnahme eine gewünschte Zielgruppe erreicht.Wo früher klassische Statistik für Berechnungen und Vorhersagen herangezogen wurde, da erlaubenheute kostenlose (Open Source) Werkzeuge wie R Daten in unterschiedlichsten Formaten und aus beliebig vielen Quellen für die Analyse einzulesen, aufzubereiten und mit Hilfe von Methoden der Künstlichen Intelligenz und des Machine Learning zu analysieren. Die Ergebnisse können dann anschließend perfekt visuell dargestellt werden, so dass die Entscheider schnell und effektiv davon profitieren können.Das Zeitalter von Data Science ist erreicht. Digitalisierung ist mehr als ein Schlagwort oder ein Versprechen, es ist für jeden umsetzbar und nutzbar.Dieses Buch vermittelt Ihnen auf Basis der zum Zeitpunkt der Publikation aktuellsten Version von R, wie Sie Künstliche Intelligenz und Machine Learning in der Industrie 4.0 nutzen können.

As a society, we¿re in a constant struggle to control uncertainty and predict the unknown. Quite often, we think of scientific fields and theories as being separate from each other. But a more careful investigation can uncover the common thread that ties many of those together. From ChatGPT, to Amazon¿s Alexa, to Apple¿s Siri, data science, and computer science have become part of our lives. In the meantime, the demand for data scientists has grown, as the field has been increasingly called the ¿sexiest profession.¿ This book attempts to specifically cover this gap in literature between data science, machine learning and artificial intelligence (AI). How was uncertainty approached historically, and how has it evolved since? What schools of thought exist in philosophy, mathematics, and engineering, and what role did they play in the development of data science? It uses the history of data science as a stepping stone to explain what the future might hold. Predicting the Unknown provides the framework that will help you understand where AI is headed, and how to best prepare for the world that¿s coming in the next few years, both as a society and within a business. It is not technical and avoids equations or technical explanations, yet is written for the intellectually curious reader, and the technical expert interested in the historical details that can help contextualize how we got here. What Yoüll LearnExplore the bigger picture of data science and see how to best anticipate future changes in that fieldUnderstand machine learning, AI, and data scienceExamine data science and AI through engaging historical and human-centric narratives Who is This Book ForBusiness leaders and technology enthusiasts who are trying to understand how to think about data science and AI

Der Arbeitsplatz der Zukunft wird immer stärker durch die Wissensarbeit geprägt. Knowledge Science beschäftigt sich mit Konzepten, Methoden und Prozessen zur systematischen Erzeugung, Extraktion, Speicherung und Bereitstellung von Wissen zur Lösung von Problemen und lässt sich somit dem Wissensmanagement zuordnen. Kognitive Assistenten sorgen dafür, das richtige Wissen zur richtigen Zeit in der richtigen Art und Weise seinen Anwendern und Anwenderinnen bereitzustellen. Damit dies gelingen kann, kommen inzwischen zahlreiche Methoden der Künstlichen Intelligenz (KI) zur Unterstützung unterschiedlicher Aufgaben des Wissensmanagements zum Einsatz.Der InhaltWie lassen sich mit KI-Methoden die Wissenssicherung und Wissensnutzung in Unternehmen unterstützen? Dieses Buch charakterisiert den Arbeitsplatz der Zukunft und stellt die Bedeutung der Ressource Wissen und deren Management in den Vordergrund. Ziel ist es nicht, mittels KI den Menschen zu ersetzen, sondern ihn mittels kognitiver Assistenten bestmöglich bei seiner Arbeit zu unterstützen. Welche Bereiche des Unternehmens können mit Methoden der Künstlichen Intelligenz optimiert oder gänzlich transformiert werden? Welche Schritte sind sowohl organisatorisch als auch technisch notwendig und wie werden einzelne Methoden in den Bereichen tatsächlich durchgeführt? In diesem Buch werden die Methoden der KI anhand konkreter Fallstudien mit einer großen Bandbreite erläutert und entmystifiziert:Assistenzsysteme, die wie ein Mensch lernenWissenssicherung durch Smart Expert Debriefings Kognitive Assistenzsysteme für die Trendanalyse Kognitive Assistenzsysteme im ProjektmanagementMethoden der KI in industriellen AnwendungenDie ZielgruppenUnternehmer, Prozessverantwortliche und Fachanwender, die Methoden der KI in ihrem Unternehmen oder ihren Fachbereichen nutzen wollen.IT-Manager, IT-Experten und Data Scientists, die KI-basierte Lösungen im Wissensmanagement umsetzen Studierende im Bereich KI und Data Science

This book explores machine learning (ML) defenses against the many cyberattacks that make our workplaces, schools, private residences, and critical infrastructures vulnerable as a consequence of the dramatic increase in botnets, data ransom, system and network denials of service, sabotage, and data theft attacks. The use of ML techniques for security tasks has been steadily increasing in research and also in practice over the last 10 years. Covering efforts to devise more effective defenses, the book explores security solutions that leverage machine learning (ML) techniques that have recently grown in feasibility thanks to significant advances in ML combined with big data collection and analysis capabilities. Since the use of ML entails understanding which techniques can be best used for specific tasks to ensure comprehensive security, the book provides an overview of the current state of the art of ML techniques for security and a detailed taxonomy of security tasks and corresponding ML techniques that can be used for each task. It also covers challenges for the use of ML for security tasks and outlines research directions. While many recent papers have proposed approaches for specific tasks, such as software security analysis and anomaly detection, these approaches differ in many aspects, such as with respect to the types of features in the model and the dataset used for training the models. In a way that no other available work does, this book provides readers with a comprehensive view of the complex area of ML for security, explains its challenges, and highlights areas for future research. This book is relevant to graduate students in computer science and engineering as well as information systems studies, and will also be useful to researchers and practitioners who work in the area of ML techniques for security tasks.

This book is a timely book to summarize the latest developments in the optimization of tuned mass dampers covering all classical approaches and new trends including metaheuristic algorithms. Also, artificial intelligence and machine learning methods are included to predict optimum results by skipping long optimization processes. Another difference and advantage of the book are to provide chapters about several types of control types including passive tuned mass dampers, active tuned mass dampers, tuned liquid dampers, tuned liquid column dampers and inerter dampers. Tuned mass dampers (TMDs) are vibration absorber devices used in all types of mechanic systems. The key factor in the design is an effective tuning of TMDs for the desired performance. In practice, several high-rise structures and bridges were designed by including TMDs. Also, TMDs were installed after the construction of the structures after several negative experiences resulting from the disturbing sway of the structures. In optimum design, several closed-form expressions have been proposed for optimum frequency and damping ratio of TMDs, but the exact optimization requires iterative optimization approaches. The current trend is to use evolutionary algorithms and metaheuristic optimization methods to reach the goal.

The book is covering knowledge and results in theory, methodology, and applications of artificial intelligence and machine learning in academia and industry. Nowadays, artificial intelligence has been used in every company where intelligence elements are embedded inside sensors, devices, machines, computers and networks. The chapters in this book integrated approach toward global exchange of information on technological advances, scientific innovations, and the effectiveness of various regulatory programs toward AI application in medicine, biology, chemistry, financial, games, law, and engineering. Readers can find AI application in industrial workplace safety, manufacturing systems, medical imaging, biomedical engineering application, different computational paradigm, COVID-19, liver tracking, drug delivery system, and cost-effectiveness analysis. Real examples from academia and industry give beyond state of the art for application of AI and ML in different areas. These chapters are extended papers from the First Serbian International Conference on Applied Artificial Intelligence (SICAAI), which was held in Kragujevac, Serbia, on May 19¿20, 2022.

This book focuses on machine learning (ML) assisted evolutionary multi- and many-objective optimization (EMâO). EMâO algorithms, namely EMâOAs, iteratively evolve a set of solutions towards a good Pareto Front approximation. The availability of multiple solution sets over successive generations makes EMâOAs amenable to application of ML for different pursuits. Recognizing the immense potential for ML-based enhancements in the EMâO domain, this book intends to serve as an exclusive resource for both domain novices and the experienced researchers and practitioners. To achieve this goal, the book first covers the foundations of optimization, including problem and algorithm types. Then, well-structured chapters present some of the key studies on ML-based enhancements in the EMâO domain, systematically addressing important aspects. These include learning to understand the problem structure, converge better, diversify better, simultaneously converge and diversify better, and analyze the Pareto Front. In doing so, this book broadly summarizes the literature, beginning with foundational work on innovization (2003) and objective reduction (2006), and extending to the most recently proposed innovized progress operators (2021-23). It also highlights the utility of ML interventions in the search, post-optimality, and decision-making phases pertaining to the use of EMâOAs. Finally, this book shares insightful perspectives on the future potential for ML based enhancements in the EMâOA domain.To aid readers, the book includes working codes for the developed algorithms. This book will not only strengthen this emergent theme but also encourage ML researchers to develop more efficient and scalable methods that cater to the requirements of the EMâOA domain. It serves as an inspiration for further research and applications at the synergistic intersection of EMâOA and ML domains.

This book describes common applied problems that are solved with the use of digital technology. The digital technology has simplified most of our daily activities. Technology has been improving our quality of life where human capability alone is insufficient enough to be utilized. For any challenging tasks, digital technology helps to solve it in very efficient ways and thousands of them are solved on a daily basis without much notice in the public. Software and IT technology let us to complete tasks in just a moment that took days without this technical support. In that sense, this book presents several examples on how software- and IT-based solutions were successfully applied in solving actual engineering problems.

"Explores the history of Android attacks and covers static and dynamic approaches to analyzing real malware specimens, machine-learning techniques to detect malicious apps, and how to identify banking trojans, ransomware, and SMS fraud"--

This book presents the process and framework you need to transform aspects of our world into data that can be collected, analyzed, and used to make decisions. You will understand the technologies used to gather and process data from many sources, and you will learn how to analyze data with AI and ML models.Datafication is becoming increasingly prevalent in many areas of our lives, from business to education and healthcare. It has the potential to improve decision-making by providing insights into patterns, trends, and correlation between seemingly unconnected pieces of data. This book explains the evolution, principles, and patterns of datafication used in our day-to-day activities. It covers how to collect data from a variety of sources, using technologies such as edge, streaming techniques, REST, and frameworks, as well as data cleansing and data lineage. A data analysis framework is provided to guide you in designing and developing AI and ML projects, including the details of sentiment and behavioral analytics.Introduction to Datafication teaches you how to engineer AI and ML projects by using various methodologies, covers the security mechanisms to be applied for datafication, and shows you how to govern the datafication process with a well-defined governance framework.What You Will LearnUnderstand the principles and patterns to be adopted for dataficationGain techniques for sourcing and mining data, and for sharing data with a data pipelineLeverage the AI and ML algorithms most suitable for dataficationUnderstand the data analysis framework used in every AI and ML projectMaster the details of sentiment and behavioral analytics through practical examplesUtilize development methodologies for datafication engineering and the related security and governance framework Who This Book Is ForStudents, data scientists, data analysts, and AI and ML engineers

This practical guide provides nearly 200 self-contained recipes to help you solve machine learning challenges you may encounter in your daily work. If youre comfortable with Python and its libraries, including pandas and scikit-learn, youll be able to address specific problems such as loading data, handling text or numerical data, model selection, and dimensionality reduction and many other topics.Each recipe includes code that you can copy and paste into a toy dataset to ensure that it actually works. From there, you can insert, combine, or adapt the code to help construct your application. Recipes also include a discussion that explains the solution and provides meaningful context. This cookbook takes you beyond theory and concepts by providing the nuts and bolts you need to construct working machine learning applications.Youll find recipes for:Vectors, matrices, and arraysHandling numerical and categorical data, text, images, and dates and timesDimensionality reduction using feature extraction or feature selectionModel evaluation and selectionLinear and logical regression, trees and forests, and k-nearest neighborsSupport vector machines (SVM), nave Bayes, clustering, and neural networksSaving and loading trained models

This book introduces some fundamentals of information and communication technology (ICT) and other current and future technologies that are relevant to the field of cybersecurity. In a digitally connected world, cybersecurity is one of the most important issues today. We have witnessed tremendous advancements over the last two decades in various fields of networking, connectivity, electronics, and the technologies that make use of those platforms and devices. Many emerging technologies are also showing promise for future use in the cybersecurity area. Hence, it is important to understand some basics of the technologies and concepts that are making their impacts today and those which may show stronger influence in the near future. The book begins with an introduction to ICT and its advancements, then talks about Artificial Intelligence (AI), Machine Learning (ML), and Blockchain Technologies. It then goes on to cover wireless technology, Internet of Things (IoT), Distributed Cloud Computing, Quantum Computing, Virtual Reality, and other futuristic technologies that would be directly related to Cyberspace and Cybersecurity.This textbook is written in a step-by-step manner, with easily accessible information for both general readers and experts in the field. It is suitable to be used as a textbook for undergraduate and graduate courses like Computer Networks and Security, Information Security, etc.

This book constitutes the refereed proceedings of the 29th International Working Conference on Requirements Engineering: Foundation for Software Quality, REFSQ 2023, which took place in Barcelona, Spain, during April 17-20, 2023.The 12 full technical design and scientific evaluation papers, 8 short research previews and vision papers, and 5 experience reports presented in this volume were carefully reviewed and selected from 78 submissions.They were organized in topical sections as follows: Requirements communication and conceptualization; NLP and machine learning for AI; RE for artificial intelligence; crowd RE; and RE in practice.

Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty quantification to avoid consequential model failures. Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models. One can use conformal prediction with any pre-trained model, such as a neural network, to produce sets that are guaranteed to contain the ground truth with a user-specified probability, such as 90%. It is easy-to-understand, easy-to-use, and in general, applies naturally to problems arising in the fields of computer vision, natural language processing, deep reinforcement learning, amongst others. In this hands-on introduction the authors provide the reader with a working understanding of conformal prediction and related distribution-free uncertainty quantification techniques. They lead the reader through practical theory and examples of conformal prediction and describe its extensions to complex machine learning tasks involving structured outputs, distribution shift, time-series, outliers, models that abstain, and more. Throughout, there are many explanatory illustrations, examples, and code samples in Python. With each code sample comes a Jupyter notebook implementing the method on a real-data example. This hands-on tutorial, full of practical and accessible examples, is essential reading for all students, practitioners and researchers working on all types of systems deploying machine learning techniques.

This book constitutes the refereed proceedings of the 12th European Conference on Artificial Intelligence in Music, Sound, Art and Design, EvoMUSART 2023, held as part of Evo* 2023, in April 2023, co-located with the Evo* 2023 events, EvoCOP, EvoApplications, and EuroGP.The 20 full papers and 7 short papers presented in this book were carefully reviewed and selected from 55 submissions. They cover a wide range of topics and application areas of artificial intelligence, including generative approaches to music and visual art, deep learning, and architecture.

This book constitutes the proceedings of the 21st International Symposium on Intelligent Data Analysis, IDA 2022, which was held in Louvain-la-Neuve, Belgium, during April 12-14, 2023.The 38 papers included in this book were carefully reviewed and selected from 91 submissions. IDA is an international symposium presenting advances in the intelligent analysis of data. Distinguishing characteristics of IDA are its focus on novel, inspiring ideas, its focus on research, and its relatively small scale.

This book constitutes the proceedings of the 7th International Conference on Smart Computing and Communication, SmartCom 2022, held in New York City, NY, USA, during November 18¿20, 2022.The 64 papers included in this book were carefully reviewed and selected from 312 submissions. SmartCom 2023 focus on recent booming developments in Web-based technologies and mobile applications which have facilitated a dramatic growth in the implementation of new techniques, such as cloud computing, edge computing, big data, pervasive computing, Internet of Things, security and privacy, blockchain, Web 3.0, and social cyber-physical systems.The conference gathered all high-quality research/industrial papers related to smart computing and communications and aimed at proposing a reference guideline for further research.

This book constitutes the refereed proceedings of the 26th European Conference on Genetic Programming, EuroGP 2023, held as part of EvoStar 2023, in Brno, Czech Republic, during April 12¿14, 2023, and co-located with the EvoStar events, EvoCOP, EvoMUSART, and EvoApplications. The 14 revised full papers and 8 short papers presented in this book were carefully reviewed and selected from 38 submissions. The wide range of topics in this volume reflects the current state of research in the field. The collection of papers cover topics including developing new variants of GP algorithms for both optimization and machine learning problems as well as exploring GP to address complex real-world problems.

This open access book constitutes revised selected papers from the International Workshops held at the 4th International Conference on Process Mining, ICPM 2022, which took place in Bozen-Bolzano, Italy, during October 23¿28, 2022.The conference focuses on the area of process mining research and practice, including theory, algorithmic challenges, and applications. The co-located workshops provided a forum for novel research ideas. The 42 papers included in this volume were carefully reviewed and selected from 89 submissions. They stem from the following workshops:¿ 3rd International Workshop on Event Data and Behavioral Analytics (EDBA)¿ 3rd International Workshop on Leveraging Machine Learning in Process Mining (ML4PM)¿ 3rd International Workshop on Responsible Process Mining (RPM) (previously known as Trust, Privacy and Security Aspects in Process Analytics)¿ 5th International Workshop on Process-Oriented Data Science for Healthcare (PODS4H)¿3rd International Workshop on Streaming Analytics for Process Mining (SA4PM)¿ 7th International Workshop on Process Querying, Manipulation, and Intelligence (PQMI)¿ 1st International Workshop on Education meets Process Mining (EduPM)¿ 1st International Workshop on Data Quality and Transformation in Process Mining (DQT-PM)

In diesem Buch wird erklärt, wie Sie die in Power BI Desktop geladenen Daten durch den Zugriff auf eine Reihe von Funktionen der künstlichen Intelligenz (KI) anreichern können. Diese KI-Funktionen sind in Power BI Desktop integriert und helfen Ihnen, neue Erkenntnisse aus vorhandenen Daten zu gewinnen. Einige der Funktionen sind automatisiert und stehen Ihnen auf Knopfdruck oder durch das Schreiben von Datenanalyseausdrücken (DAX) zur Verfügung. Andere Funktionen sind durch das Schreiben von Code in den Sprachen R, Python oder M verfügbar. Dieses Buch eröffnet Ihnen die gesamte Palette der KI-Funktionen mit klaren Beispielen, die zeigen, wann sie am besten angewendet werden und wie Sie sie auf Ihre eigenen Datensätze anwenden können. Ganz gleich, ob Sie Geschäftsanwender, Analyst oder Datenwissenschaftler sind - Power BI verfügt über KI-Funktionen, die auf Sie zugeschnitten sind. In diesem Buch erfahren Sie, welche Arten von Erkenntnissen Power BI automatisch liefern kann. Sieerfahren, wie Sie die Sprachen R und Python für Statistiken integrieren und nutzen können, wie Sie beim Laden von Daten mit Cognitive Services und Azure Machine Learning Services zusammenarbeiten, wie Sie Ihre Daten durch Fragen in einfachem Englisch erkunden können ... und vieles mehr! Es gibt KI-Funktionen für die Entdeckung Ihrer Daten, die Charakterisierung unerforschter Datensätze und die Erstellung von Was-wäre-wenn-Szenarien. Es gibt viel zu mögen und von diesem Buch zu lernen, ob Sie ein Neuling in Power BI oder ein erfahrener Benutzer sind. Power BI Desktop ist ein frei verfügbares Tool zur Visualisierung und Analyse. Dieses Buch hilft Ihnen, das Beste aus diesem Tool herauszuholen, indem Sie einige seiner neuesten und fortschrittlichsten Funktionen nutzen.Was Sie lernen werden:- Stellen Sie Fragen in natürlicher Sprache und erhalten Sie Antworten aus Ihren Daten - Lassen Sie sich von Power BI erklären, warum sich ein bestimmter Datenpunkt von den anderen unterscheidet - Lassen Sie Power BI die wichtigsten Einflussfaktoren über Datenkategorien anzeigen - Zugriff auf die in der Azure-Cloud verfügbaren Funktionen für künstliche Intelligenz - Gehen Sie denselben Drilldown-Pfad in verschiedenen Teilen Ihrer Hierarchie - Laden Sie Visualisierungen, um Ihre Berichte intelligenter zu gestalten - Simulieren Sie Änderungen an Daten und sehen Sie sofort die Folgen - Kennen Sie Ihre Daten, noch bevor Sie Ihren ersten Bericht erstellen - Erstellen Sie neue Spalten, indem Sie Beispiele für die benötigten Daten angeben - Transformieren und visualisieren Sie Ihre Daten mit Hilfe von R- und Python-SkriptenFür wen dieses Buch gedacht ist:Für den begeisterten Power BI-Anwender, der modernste Funktionen der künstlichen Intelligenz (KI) einsetzen möchte, um neue Erkenntnisse aus vorhandenen Daten zu gewinnen. Für Endanwender und IT-Fachleute, die sich nicht scheuen, in die neue Welt des maschinellen Lernens einzutauchen, und bereit sind, diesen Schritt zu tun und einen tieferen Blick in ihre Daten zu werfen. Für diejenigen, die von einfachen Berichten und Visualisierungen zu diagnostischen und prädiktiven Analysen übergehen wollen.

This book constitutes the proceedings of the 25th RoboCup International Symposium which was held online during July 2022 in Bangkok, Thailand.The 28 full papers included in these proceedings were carefully reviewed and selected from 40 submissions; the volume includes 12 papers from the winners of the RoboCup 2022 competitions under the Champions Track. The RoboCup International Symposium focuses on the science behind the advances in robotics, including the key innovations that led the winning teams to their success, and the outcomes of research inspired by challenges across the different leagues at RoboCup.

This book focuses on research and development aspects of building data analytics workflows that address various challenges of e-learning applications.This book represents a guideline for building a data analysis workflow from scratch. Each chapter presents a step of the entire workflow, starting from an available dataset and continuing with building interpretable models, enhancing models, and tackling aspects of evaluating engagement and usability. The related work shows that many papers have focused on machine learning usage and advancement within e-learning systems. However, limited discussions have been found on presenting a detailed complete roadmap from the raw dataset up to the engagement and usability issues. Practical examples and guidelines are provided for designing and implementing new algorithms that address specific problems or functionalities. This roadmap represents a potential resource for various advances of researchers and practitioners in educational data mining and learning analytics.