Fraunhofer Institute for Intelligent Analysis and Information Systems

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.

Focus on movement data has increased as a consequence of the larger availability of such data due to current GPS, GSM, RFID, and sensors techniques. In parallel, interest in movement has shifted from raw movement data analysis to more application-oriented ways of analyzing segments of movement suitable for the specific purposes of the application. This trend has promoted semantically rich trajectories, rather than raw movement, as the core object of interest in mobility studies. This survey provides the definitions of the basic concepts about mobility data, an analysis of the issues in mobility data management, and a survey of the approaches and techniques for: (i) constructing trajectories from movement tracks, (ii) enriching trajectories with semantic information to enable the desired interpretations of movements, and (iii) using data mining to analyze semantic trajectories and extract knowledge about their characteristics, in particular the behavioral patterns of the moving objects. Last but not least, the article surveys the new privacy issues that arise due to the semantic aspects of trajectories.

Part A: Data mining and knowledge discovery Part B: Fundamental Concepts Part C: The process of knowledge discovery in databases Part D: Discovery Systems Part E: Interdisciplinary links of KDD Part F: Business problems Part G: Industry sectors Part H: KDD in practice: case studies

Abstract 6D SLAM (simultaneous localization and mapping) or 6D concurrent localization and mapping of mobile robots considers six dimensions for the robot pose, namely, the x , y , and z coordinates and the roll, yaw, and pitch angles. Robot motion and localization on natural surfaces, e.g., driving outdoor with a mobile robot, must regard these degrees of freedom. This paper presents a robotic mapping method based on locally consistent 3D laser range scans. Iterative Closest Point scan matching, combined with a heuristic for closed loop detection and a global relaxation method, results in a highly precise mapping system. A new strategy for fast data association, cached k d‐tree search, leads to feasible computing times. With no ground‐truth data available for outdoor environments, point relations in maps are compared to numerical relations in uncalibrated aerial images in order to assess the metric validity of the resulting 3D maps. © 2007 Wiley Periodicals, Inc.

Visual analytics aims to combine the strengths of human and electronic data processing. Visualisation, whereby humans and computers cooperate through graphics, is the means through which this is achieved. Seamless and sophisticated synergies are required for analysing spatio-temporal data and solving spatio-temporal problems. In modern society, spatio-temporal analysis is not solely the business of professional analysts. Many citizens need or would be interested in undertaking analysis of information in time and space. Researchers should find approaches to deal with the complexities of the current data and problems and find ways to make analytical tools accessible and usable for the broad community of potential users to support spatio-temporal thinking and contribute to solving a large range of problems.

Support took place at the GIScience conference in Münster, Germany. The aim of the workshop was to bring together researchers from relevant fields to discuss the state of the art in visually-enabled spatial decision support, identify major problems, and

MOTIVATION: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). RESULTS: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26% over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.

Based on concepts of the human visual system, computational visual attention systems aim to detect regions of interest in images. Psychologists, neurobiologists, and computer scientists have investigated visual attention thoroughly during the last decades and profited considerably from each other. However, the interdisciplinarity of the topic holds not only benefits but also difficulties: Concepts of other fields are usually hard to access due to differences in vocabulary and lack of knowledge of the relevant literature. This article aims to bridge this gap and bring together concepts and ideas from the different research areas. It provides an extensive survey of the grounding psychological and biological research on visual attention as well as the current state of the art of computational systems. Furthermore, it presents a broad range of applications of computational attention systems in fields like computer vision, cognitive systems, and mobile robotics. We conclude with a discussion on the limitations and open questions in the field.

Movement data (trajectories of moving agents) are hard to visualize: numerous intersections and overlapping between trajectories make the display heavily cluttered and illegible. It is necessary to use appropriate data abstraction methods. We suggest a method for spatial generalization and aggregation of movement data, which transforms trajectories into aggregate flows between areas. It is assumed that no predefined areas are given. We have devised a special method for partitioning the underlying territory into appropriate areas. The method is based on extracting significant points from the trajectories. The resulting abstraction conveys essential characteristics of the movement. The degree of abstraction can be controlled through the parameters of the method. We introduce local and global numeric measures of the quality of the generalization, and suggest an approach to improve the quality in selected parts of the territory where this is deemed necessary. The suggested method can be used in interactive visual exploration of movement data and for creating legible flow maps for presentation purposes.

Artificial intelligence (AI) in the domain of healthcare is increasing in prominence. Acceptance is an indispensable prerequisite for the widespread implementation of AI. The aim of this integrative review is to explore barriers and facilitators influencing healthcare professionals' acceptance of AI in the hospital setting. Forty-two articles met the inclusion criteria for this review. Pertinent elements to the study such as the type of AI, factors influencing acceptance, and the participants' profession were extracted from the included studies, and the studies were appraised for their quality. The data extraction and results were presented according to the Unified Theory of Acceptance and Use of Technology (UTAUT) model. The included studies revealed a variety of facilitating and hindering factors for AI acceptance in the hospital setting. Clinical decision support systems (CDSS) were the AI form included in most studies (n = 21). Heterogeneous results with regard to the perceptions of the effects of AI on error occurrence, alert sensitivity and timely resources were reported. In contrast, fear of a loss of (professional) autonomy and difficulties in integrating AI into clinical workflows were unanimously reported to be hindering factors. On the other hand, training for the use of AI facilitated acceptance. Heterogeneous results may be explained by differences in the application and functioning of the different AI systems as well as inter-professional and interdisciplinary disparities. To conclude, in order to facilitate acceptance of AI among healthcare professionals it is advisable to integrate end-users in the early stages of AI development as well as to offer needs-adjusted training for the use of AI in healthcare and providing adequate infrastructure.

BACKGROUND: Identification of gene and protein names in biomedical text is a challenging task as the corresponding nomenclature has evolved over time. This has led to multiple synonyms for individual genes and proteins, as well as names that may be ambiguous with other gene names or with general English words. The Gene List Task of the BioCreAtIvE challenge evaluation enables comparison of systems addressing the problem of protein and gene name identification on common benchmark data. METHODS: The ProMiner system uses a pre-processed synonym dictionary to identify potential name occurrences in the biomedical text and associate protein and gene database identifiers with the detected matches. It follows a rule-based approach and its search algorithm is geared towards recognition of multi-word names. To account for the large number of ambiguous synonyms in the considered organisms, the system has been extended to use specific variants of the detection procedure for highly ambiguous and case-sensitive synonyms. Based on all detected synonyms for one abstract, the most plausible database identifiers are associated with the text. Organism specificity is addressed by a simple procedure based on additionally detected organism names in an abstract. RESULTS: The extended ProMiner system has been applied to the test cases of the BioCreAtIvE competition with highly encouraging results. In blind predictions, the system achieved an F-measure of approximately 0.8 for the organisms mouse and fly and about 0.9 for the organism yeast.

The Berlin Brain--Computer Interface (BBCI) project develops a noninvasive BCI system whose key features are: 1) the use of well-established motor competences as control paradigms; 2) high-dimensional features from multichannel EEG; and 3) advanced machine-learning techniques. Spatio-spectral changes of sensorimotor rhythms are used to discriminate imagined movements (left hand, right hand, and foot). A previous feedback study [M. Krauledat, K.-R. MUller, and G. Curio. (2007) The non-invasive Berlin brain--computer Interface: Fast acquisition of effective performance in untrained subjects. NeuroImage. [Online]. 37(2), pp. 539--550. Available: http://dx.doi.org/10.1016/j.neuroimage.2007.01.051] with ten subjects provided preliminary evidence that the BBCI system can be operated at high accuracy for subjects with less than five prior BCI exposures. Here, we demonstrate in a group of 14 fully BCI-naIve subjects that 8 out of 14 BCI novices can perform at >84% accuracy in their very first BCI session, and a further four subjects at >70%. Thus, 12 out of 14 BCI-novices had significant above-chance level performances without any subject training even in the first session, as based on an optimized EEG analysis by advanced machine-learning algorithms.

Analysis of movement is currently a hot research topic in visual analytics. A wide variety of methods and tools for analysis of movement data has been developed in recent years. They allow analysts to look at the data from different perspectives and fulfil diverse analytical tasks. Visual displays and interactive techniques are often combined with computational processing, which, in particular, enables analysis of a larger number of data than would be possible with purely visual methods. Visual analytics leverages methods and tools developed in other areas related to data analytics, particularly statistics, machine learning and geographic information science. We present an illustrated structured survey of the state of the art in visual analytics concerning the analysis of movement data. Besides reviewing the existing works, we demonstrate, using examples, how different visual analytics techniques can support our understanding of various aspects of movement.

We propose a simple yet effective detector for pedestrian detection. The basic idea is to incorporate common sense and everyday knowledge into the design of simple and computationally efficient features. As pedestrians usually appear up-right in image or video data, the problem of pedestrian detection is considerably simpler than general purpose people detection. We therefore employ a statistical model of the up-right human body where the head, the upper body, and the lower body are treated as three distinct components. Our main contribution is to systematically design a pool of rectangular templates that are tailored to this shape model. As we incorporate different kinds of low-level measurements, the resulting multi-modal & multi-channel Haar-like features represent characteristic differences between parts of the human body yet are robust against variations in clothing or environmental settings. Our approach avoids exhaustive searches over all possible configurations of rectangle features and neither relies on random sampling. It thus marks a middle ground among recently published techniques and yields efficient low-dimensional yet highly discriminative features. Experimental results on the INRIA and Caltech pedestrian datasets show that our detector reaches state-of-the-art performance at low computational costs and that our features are robust against occlusions.

Visualizing trajectory attribute data is challenging because it involves showing the trajectories in their spatio-temporal context as well as the attribute values associated with the individual points of trajectories. Previous work on trajectory visualization addresses selected aspects of this problem, but not all of them. We present a novel approach to visualizing trajectory attribute data. Our solution covers space, time, and attribute values. Based on an analysis of relevant visualization tasks, we designed the visualization solution around the principle of stacking trajectory bands. The core of our approach is a hybrid 2D/3D display. A 2D map serves as a reference for the spatial context, and the trajectories are visualized as stacked 3D trajectory bands along which attribute values are encoded by color. Time is integrated through appropriate ordering of bands and through a dynamic query mechanism that feeds temporally aggregated information to a circular time display. An additional 2D time graph shows temporal information in full detail by stacking 2D trajectory bands. Our solution is equipped with analytical and interactive mechanisms for selecting and ordering of trajectories, and adjusting the color mapping, as well as coordinated highlighting and dedicated 3D navigation. We demonstrate the usefulness of our novel visualization by three examples related to radiation surveillance, traffic analysis, and maritime navigation. User feedback obtained in a small experiment indicates that our hybrid 2D/3D solution can be operated quite well.

With widespread availability of low cost GPS devices, it is becoming possible to record data about the movement of people and objects at a large scale. While these data hide important knowledge for the optimization of location and mobility oriented infrastructures and services, by themselves they lack the necessary semantic embedding which would make fully automatic algorithmic analysis possible. At the same time, making the semantic link is easy for humans who however cannot deal well with massive amounts of data. In this paper, we argue that by using the right visual analytics tools for the analysis of massive collections of movement data, it is possible to effectively support human analysts in understanding movement behaviors and mobility patterns. We suggest a framework for analysis combining interactive visual displays, which are essential for supporting human perception, cognition, and reasoning, with database operations and computational methods, which are necessary for handling large amounts of data. We demonstrate the synergistic use of these techniques in case studies of two real datasets.

To create with an autonomous mobile robot a 3D volumetric map of a scene it is necessary to gage several 3D scans and to merge them into one consistent 3D model. This paper provides a new solution to the simultaneous localization and mapping (SLAM) problem with six degrees of freedom. Robot motion on natural surfaces has to cope with yaw, pitch and roll angles, turning pose estimation into a problem in six mathematical dimensions. A fast variant of the Iterative Closest Points algorithm registers the 3D scans in a common coordinate system and relocalizes the robot. Finally, consistent 3D maps are generated using a global relaxation. The algorithms have been tested with 3D scans taken in the Mathies mine, Pittsburgh, PA. Abandoned mines pose significant problems to society, yet a large fraction of them lack accurate 3D maps.

Data about movements of various objects are collected in growing amounts by means of current tracking technologies. Traditional approaches to visualization and interactive exploration of movement data cannot cope with data of such sizes. In this research paper we investigate the ways of using aggregation for visual analysis of movement data. We define aggregation methods suitable for movement data and find visualization and interaction techniques to represent results of aggregations and enable comprehensive exploration of the data. We consider two possible views of movement, traffic-oriented and trajectory-oriented. Each view requires different methods of analysis and of data aggregation. We illustrate our argument with example data resulting from tracking multiple cars in Milan and example analysis tasks from the domain of city traffic management.

One of the most common operations in exploration and analysis of various kinds of data is clustering, i.e. discovery and interpretation of groups of objects having similar properties and/or behaviors. In clustering, objects are often treated as points in multi-dimensional space of properties. However, structurally complex objects, such as trajectories of moving entities and other kinds of spatio-temporal data, cannot be adequately represented in this manner. Such data require sophisticated and computationally intensive clustering algorithms, which are very hard to scale effectively to large datasets not fitting in the computer main memory. We propose an approach to extracting meaningful clusters from large databases by combining clustering and classification, which are driven by a human analyst through an interactive visual interface.

Eye movement analysis is gaining popularity as a tool for evaluation of visual displays and interfaces. However, the existing methods and tools for analyzing eye movements and scanpaths are limited in terms of the tasks they can support and effectiveness for large data and data with high variation. We have performed an extensive empirical evaluation of a broad range of visual analytics methods used in analysis of geographic movement data. The methods have been tested for the applicability to eye tracking data and the capability to extract useful knowledge about users' viewing behaviors. This allowed us to select the suitable methods and match them to possible analysis tasks they can support. The paper describes how the methods work in application to eye tracking data and provides guidelines for method selection depending on the analysis tasks.