Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Knowledge Management

Machine learning (ML) is the fastest growing field in computer science, and health informatics is among the greatest challenges. The goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions. Most ML researchers concentrate on automatic machine learning (aML), where great advances have been made, for example, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly benefit from big data with many training sets. However, in the health domain, sometimes we are confronted with a small number of data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive machine learning (iML) may be of help, having its roots in reinforcement learning, preference learning, and active learning. The term iML is not yet well used, so we define it as “algorithms that can interact with agents and can optimize their learning behavior through these interactions, where the agents can also be human.” This “human-in-the-loop” can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human agent involved in the learning phase.

/pdf/interactive-machine-learning-for-health-informatics-when-do-434i9eplg1.pdf

Interactive machine learning for health informatics: when do we need the human-in-the-loop?

Photoinhibition of Photosystem II (PSII) is the light-induced loss of PSII electron-transfer activity. Although photoinhibition has been studied for a long time, there is no consensus about its mechanism. On one hand, production of singlet oxygen ((1)O(2)) by PSII has promoted models in which this reactive oxygen species (ROS) is considered to act as the agent of photoinhibitory damage. These chemistry-based models have often not taken into account the photophysical features of photoinhibition-like light response and action spectrum. On the other hand, models that reproduce these basic photophysical features of the reaction have not considered the importance of data about ROS. In this chapter, it is shown that the evidence behind the chemistry-based models and the photophysically oriented models can be brought together to build a mechanism that confirms with all types of experimental data. A working hypothesis is proposed, starting with inhibition of the manganese complex by light. Inability of the manganese complex to reduce the primary donor promotes recombination between the oxidized primary donor and Q(A), the first stable quinone acceptor of PSII. (1)O(2) production due to this recombination may inhibit protein synthesis or spread the photoinhibitory damage to another PSII center. The production of (1)O(2) is transient because loss of activity of the oxygen-evolving complex induces an increase in the redox potential of Q(A), which lowers (1)O(2) production.

Photoinhibition of Photosystem II

In the domain of engineering large corpora of technical documents are commonly created and used. Applications such as semantic search offer advantages in accessing those documents, but require them to be semantically annotated. Annotating these corpora manually is in most cases not feasible. In recent years a lot of machine learning methods have proved their ability to annotate documents automatically. The downside of these methods is their need for training data. We present a holistic approach for the semantification of technical documents without training data. The approach tackles different challenges such as terminology extraction, semantic annotation, and reviewing. Our approach has been successfully applied to the technical documents corpora of two German machine builders

Towards the Semantification of Technical Documents.

To protect the health of human and environment, the European Union implemented the REACH regulation for chemical substances. REACH is an acronym for Registration, Evaluation, Authorization, and Restriction of Chemicals. Under REACH, the authorities have the task of assessing chemical substances, especially those that might pose a risk to human health or environment. The work under REACH is scientifically, technically and procedurally a complex and knowledge-intensive task that is jointly performed by the European Chemicals Agency and member state authorities in Europe. The assessment of substances under REACH conducted in the German Environment Agency is supported by the knowledge-based system KnowSEC, which is used for the screening, documentation, and decision support when working on chemical substances. The software KnowSEC integrates advanced semantic technologies and strong problem solving methods. It allows for the collaborative work on substances in the context of the European REACH regulation. We discuss the applied methods and process models and we report on experiences with the implementation and use of the system.

/pdf/collaborative-decision-support-and-documentation-in-chemical-2zav8nvwaa.pdf

Collaborative decision support and documentation in chemical safety with KnowSEC.

The aim of this research is a practical method to draw cable plans of complex machines. Such plans consist of electronic components and cables connecting specific ports of the components. Since the machines are configured for each client individually, cable plans need to be drawn automatically. The drawings must be well readable so that technicians can use them to debug the machines. In order to model plug sockets, we introduce port groups; within a group, ports can change their position (which we use to improve the aesthetics of the layout), but together the ports of a group must form a contiguous block. 
We approach the problem of drawing such cable plans by extending the well-known Sugiyama framework such that it incorporates ports and port groups. Since the framework assumes directed graphs, we propose several ways to orient the edges of the given undirected graph. We compare these methods experimentally, both on real-world data and synthetic data that carefully simulates real-world data. We measure the aesthetics of the resulting drawings by counting bends and crossings. Using these metrics, we compare our approach to Kieler [JVLC 2014], a library for drawing graphs in the presence of port constraints.

Layered Drawing of Undirected Graphs with Generalized Port Constraints

Evaluating and comparing machine learning methods concerning the effectiveness and the efficiency is a general research problem. For a careful evaluation the availability of data sets with known characteristics is a key issue. We propose a novel approach to intuitively generate data sets for the evaluation and the comparison of machine learning methods. Three case studies are provided to demonstrate the presented approach.

/pdf/a-datagenerator-for-evaluating-machine-learning-methods-3vasivqdu2.pdf

A Datagenerator for Evaluating Machine Learning Methods.

KnowWE is a semantic wiki that provides the possibility to define and maintain ontologies and strong problem-solving knowledge. Recently, the ontology engineering capabilities of KnowWE were significantly extended. As with other ontology engineering tools, the support of ontology debugging during the development of ontologies is the deficient. We present an Ontology Debugger for KnowWE that is based on the delta debugging approach known from Software Engineering. KnowWE already provides possibilities to define test cases to be used with various knowledge representations. While reusing the existing testing capabilities we implemented a debugger that is able to identify failure-inducing statements between two revisions of an ontology.

/pdf/an-ontology-debugger-for-the-semantic-wiki-knowwe-tool-1anlhuguab.pdf

Joachim Baumeister

Papers

Towards the Semantification of Technical Documents.

Collaborative decision support and documentation in chemical safety with KnowSEC.

Layered Drawing of Undirected Graphs with Generalized Port Constraints

A Datagenerator for Evaluating Machine Learning Methods.

An Ontology Debugger for the semantic wiki KnowWE: Tool Presentation