Refine
Year of publication
Document Type
- Conference Proceeding (179)
- Article (64)
- Part of a Book (16)
- Bachelor Thesis (6)
- Book (5)
- Report (5)
- Contribution to a Periodical (3)
- Doctoral Thesis (2)
- Master's Thesis (2)
- Part of Periodical (2)
Language
- English (287) (remove)
Is part of the Bibliography
- no (287)
Keywords
The virtual classroom continues to grow, but it is becoming more and more the norm, and it is fundamentally different from the vocational students at the Indonesian university. With the promised benefits of the virtual classroom, many challenges and difficulties come in the implementation. Although there are already successful design principles for virtual classrooms that support organizations in overcoming the challenges, the approach to implementing the design principles of virtual classroom at the vocational higher education in Indonesia is still lacking. In this study, we aim to answer the research gap and used the design sciences research by interviewing the lecturers to design the solutions. The proposed design approaches were implemented in a course and evaluated with students from two different groups. Overall, the evaluation of the proposed approaches shows1 significant results as an indicator of the benefits of the implementation of a virtual classroom for vocational students in Indonesia.
Artificial Intelligence Driven Human-Machine Collaboration Scenarios in Virtual Reality (Poster)
(2018)
RELEVANCE & RESEARCH QUESTION: Currently the effectiveness of Virtual Reality (VR) and Augmented Reality (AR) systems as practice teaching methods are virtually uncharted. The proof that these systems can provide the same or better learning outcomes than a text instructed practical task could represent a significant benefit for educational activities. METHODS & DATA: To fathom the effectiveness, an experimental study with the three conditions (VR, AR and a real setup) were used to teach participant how to assemble a standard computer. Each condition was divided into two parts: part one in which participants were confronted with their specific scenario, part two in which participants had to go through a real practice after one week. The learning outcome was determined by the designation of hardware parts, a quiz that queried their function and the correct assembling of the components in addition to needed time. Apart from the mere performance, the acceptance of such application in academic context and difference in evaluation by men and women were of interest. RESULTS: Results concerning the Learning Outcome showed that participants from the VR condition outperformed those learned from the real setup ((M=10.0, SD=0.0) [virtual reality] vs. (M=8.95, SD=1.27) [control]). Furthermore, results from the assembling duration assessment demonstrated that VR Group Participants completed their tasks 6.62% faster than the control group. Regarding the identification of Hardware Parts, both groups scored a significant improvement during the post condition compared to the first test run, indicating a learning progress. However, due to the VR group achieving a better outcome in average answers and a more significant difference between the trials, the results indicate a better performance by participants assigned to the VR condition. ADDED VALUE: The results revealed that VR and AR systems could exceed text-based approach in terms of learning outcome performance. The effectiveness of the systems implicates a major benefit for the educational landscape, as learning content that is not realizable in terms of cost, distance or logistics could be designed as an immersive and engaging experience.
Today usually every student owns a reasonably powerful mobile device that allows to be integrated in scenarios. One of the drawbacks of the fast evolution of reasonably powerful devices, is the
heterogeneity of that these kind of devices us ually bring with them. This paper provides an overview how rich mobile learning scenarios can be implemented platform independent on the basis of HTML5 and JavaScript. The paper presents a mobile learning application based on the principles of Situated Lea
rning entirely developed in HTML5. The paper also presents the results of tests performed with the application which were aimed at finding out the difference in performance users perceived when compared with the native desktop version of the
application and the added value that mobility introduces in learning activities.
Blended learning offers learning solutions for higher educational institutions facing the industrial revolution 4.0. In this study, we investigated the influence factors student perceptions of blended learning based on gender-specific differences in Indonesia. We applied a research model to systematically assess the effect of design features on the effectiveness of blended learning indicators (intrinsic motivation and student satisfaction). Moreover, we evaluated the research model for both genders separately. Based on the quantitative survey of 223 Indonesian students, our study confirms that the design features significantly influence the effectiveness of blended learning for male and female students.
Efficient and reliable onsite inspection methods are gaining importance as the construc-tion of PV power plants is expanding. For large PV installations, time- and cost-efficient failure detection is essential for optimized operation and maintenance. For this purpose, various optical methods as Infrared thermography (IR), Electroluminescence (EL), Pho-toluminescence (PL) and Ultraviolet Fluorescence (UVF) are employed and under con-stant development. For each method, the camera, and eventually the light source, can be handheld, or mounted on a drone, also called unmanned aircraft vehicle (UAV), to achieve higher throughputs.
IR is the most widely used optical onsite PV inspection method, as many defects can be detected by the thermal radiation (heating) of the defect component. EL and PL reveal further information on the electrical behaviour of the Si-waver. They are also widely used and take the role of a complement to IR, showing electrically active/inactive areas of the semiconductor. On the other hand, UVF focuses on the degradation of the polymeric encapsulant of the Si-cell, most commonly consisting of EVA (ethylene-vinyl acetate). The degradation of the encapsulant can lead to its discoloration, also called yellow-ing/browning, which decreases the transmittance of visual light. UVF patterns can show this yellowing as well as humidity and oxygen entrances, which can lead to effects of corrosion. Both mechanisms (discoloration and corrosion) decrease the performance of the PV cell. The discoloration cannot be directly observed on IR or EL images, as the encapsulant is neither a heat source nor electroconductive. Using IR imagery, severe discoloration might be observed indirectly, as the reduced optical transmittance leads to changes in heat transfer mechanisms concerning the cell and the encapsulant.
Similarly, as long as corrosion does not lead to inactive cell areas or heating, it most likely will not be spotted using EL, PL or IR. So, UVF can fill the niche of inspecting the state of the encapsulant and detecting its defects due to climate impacts in early stages.
While a high number of studies on IR, EL, PL and some on UVF were performed in Europe and the USA, there are not yet many studies about the application of these tech-niques in South America (i.e., in Brazil). UVF mainly depends on climate factors (irradi-ation, temperature, humidity) and the operation time/”age” of the module. The UVF im-agery method has not yet been tested in climate and system conditions of Brazil. Fur-thermore, systems in Brazil are more recently installed. All this can affect differences in the results of UVF imagery applied in Europe, the USA and Brazil.
The present work focuses on the application of UVF imaging on PV power plants in Bra-zil, the creation of an experimental setup and the proposal of proceedings for the data analysis of the acquired images. The aim is to propose a method that is suitable for large-scale inspection.
Applications and research efforts in Mobile Learning constitute a growing field in the area of Technology Enhanced Learning. However, despite a permanent increase of mobile internet accessibility and availability of mobile devices over the past years, a mobile learning environment that is easy to use, widely accepted by teachers and learners, uses widespread off-the-shelf software, and that covers various application scenarios and mobile devices, is not yet available. In this paper, we address this issue by presenting an approach and technical framework called "Mobile Contributions" ("MoCo"). MoCo supports learners to create and send contributions through various channels (including third-party solutions like Twitter, SMS and Facebook), which are collected and stored in a central repository for processing, filtering and visualization on a shared display. A set of different learning and teaching scenarios that can be realized with MoCo are described along with first experiences and insights gained from qualitative and quantitative evaluation.
This paper presents an approach towards a mobile learning environment, which is flexible in terms of supported scenarios, supported devices and input channels. The approach makes use of existing and commonly used channels like SMS, Twitter or Face book to increase acceptance and ease-of-use of mobile devices in learning scenarios. Envisaged application scenarios are described along with technical details for their realization.
Developing an intelligent chatbot that can imitate human-to-human interaction has become important in recent years. For this reason, many studies have been conducted to evaluate the quality of chatbots. Furthermore, various approaches and tools, such as sentiment analysis, have been created to improve the performance of chatbots.
This study examines previous research to identify the quality dimensions used to measure chatbots performance in order to develop a general chatbot assessment model that evaluates and compares chatbots quality. The developed evaluation model measures ten chatbot quality dimensions. This model is based on user experience. It requires human testers to interact with the chatbot to test its functioning and then a quantitative approach is used to collect data from user testing by conducting a survey with these testers. In this survey, they are instructed to evaluate the quality of the chatbot using a questionnaire that contains the items needed to evaluate each dimension.
This study also investigates whether sentiment analysis can improve the quality of chatbots and, if so, to identify the dimensions improved with sentiment analysis. For this reason, two chatbot versions are implemented using the Rasa framework (one that cannot detect sentiment and the other that analyzes sentiment and responds accordingly).
Following that, we used our evaluation model to evaluate and compare the two chatbot versions with two groups of participants by conducting a survey. In this survey, each group tested the functioning of one version. Then, both groups were instructed to use the items of the evaluation model to evaluate the version they tested. The goal of this survey was to evaluate the validity and reliability of the items used in the evaluation model to evaluate chatbots, and also to determine if sentiment analysis improved the chatbot quality by comparing survey results between the two groups. The results show that items used in the assessment model to evaluate chatbots are valid and reliable. The findings also indicate that sentiment analysis improves the chatbot’s quality. However, it improves the quality of some dimensions but not the majority of them.
In this document a reliable data streaming mechanism for a TDMA LPWAN application is developed by adapting a link layer solution for power line communication, published at the International Symposium on Power Line Communications and its Applications (ISPLC) 2015. A C++ implementation of the services link layer is provided and demonstrated
working at a packet error rate of 50%.
Starting with the automatic gear change, the operation of a vehicle becomes more and more abstract. In the future, we could control vehicles with single, simple commands. For such a maneuver-based vehicle control system, we investigate a head-up display design in a workshop. The aims are to identify common and distinct features of various display designs through mock-ups. First results show that different sizes of GUI elements are preferred by different states. The preferred position of GUI elements in the head-up display (HUD) is the central bottom area. We found two major interface design styles: static interfaces (all elements visible) with fixed layout and dynamic interfaces (only relevant elements visible) with fixed or adaptive layout.
For highly automated vehicles (AVs), new interaction concepts need to be developed. Even in AVs, the driver might want to intervene and override the automation from time to time. To create the possibility of control, we explore vehicle control through maneuver-based interventions (MBI). Thereby, we focus on explicit, contact-less interaction, which could be beneficial in future AV designs, where the driver is not necessarily bound to classical controls. We propose a set of freehand gestures and keywords for voice control derived in a user-centered design process. Further, we discuss properties, applicability and user impressions of both interaction modalities. Voice control seems to be an efficient way to select a maneuver and free-hand gestures could be used, if voice channel is blocked, e.g., through conversation with passengers.
How to Increase Automated Vehicles’ Acceptance through In-Vehicle Interaction Design: A Review
(2020)
Automated vehicles (AVs) are on the edge of being available on the mass market. Research often focuses on technical aspects of automation, such as computer vision, sensing, or artificial intelligence. Nevertheless, researchers also identified several challenges from a human perspective that need to be considered for a successful introduction of these technologies. In this paper, we first analyze human needs and system acceptance in the context of AVs. Then, based on a literature review, we provide a summary of current research on in-car driver-vehicle interaction and related human factor issues. This work helps researchers, designers, and practitioners to get an overview of the current state of the art.
Human emotion detection in automated vehicles helps to improve comfort and safety. Research in the automotive domain focuses a lot on sensing drivers' drowsiness and aggression. We present a new form of implicit driver-vehicle cooperation, where emotion detection is integrated into an automated vehicle's decision-making process. Constant evaluation of the driver's reaction to vehicle behavior allows us to revise decisions and helps to increase the safety of future automated vehicles.
Self-driving cars will relief the human from the driving task. Nevertheless, the human might want to intervene in the driving process and thus needs the possibility to control the car. Switching back to fully manual controls is uncomfortable once being passive and engaging in non-driving-related activities. A more comfortable way is controlling the car with elemental maneuvers (e.g., "turn left" or "stop"). Whereas touch interaction concepts exist, contactless interaction through voice and mid-air gestures has not yet been explored for maneuver-based car control. In this paper, we, therefore, compare the general eligibility of voice and mid-air gesture with touch interaction as the primary maneuver selection mechanism in a driving simulator study. Our results show high usability for all modalities. Contactless interaction leads to a more positive emotional perception of the interaction, yet mid-air gestures lead to higher task load. Overall, voice and touch control are preferred over mid-air gestures by most users.
Currently, car assistant systems mainly try to prevent accidents. Increasing built-in car technology also extends the potential applications in vehicles. Future cars might have virtual windshields that augment the traffic or individual virtual assistants interacting with the user. In this paper, we explore the potential of an assistant system that helps the car’s occupants to calm down and reduce stress when they experience an accident in front of them. We present requirements from a discussion (N= 11) and derive a system design from them. Further, we test the system design in a video-based simulator study (N= 43). Our results indicate that an accident support system increases perceived control and trust and helps to calm down the user.
The way we communicate with autonomous cars will fundamentally change as soon as manual input is no longer required as back-up for the autonomous system. Maneuver-based driving is a potential way to allow still the user to intervene with the autonomous car to communicate requests such as stopping at the next parking lot. In this work, we highlight different research questions that still need to be explored to gain insights into how such control can be realized in the future.
Anonymity-preserving Methods for Client-side Filtering in Position-based Collaboration Approaches
(2017)
Recently, rescue worker resources have not been sufficient to meet the regular response time during large-scale catastrophic events in every case. However, many volunteers supported official forces in different disaster situations, often self-organized through social media. In this paper, a system will be introduced which allows the coordination of trained volunteers by a professional control center with the objective of a more efficient distribution of human resources and technical equipment. Volunteers are contacted via app on their private smartphone. The design of this app is based on user requirements gathered in focus group discussions. The feedback of the potential users includes privacy aspects, low energy consumption, and mechanisms for long-term motivation and training. The authors present the results of the focus group analyses as well as the transfer to their app design concept.
Public transportation will become highly automated in the future, and at some point, human drivers are no longer necessary. Today many people are skeptical about such scenarios of autonomous public transport (abbr.: APT). In this paper, we assess users’ subjective priority of different factors that lead to personal acceptance or rejection of APT using an adapted online version of the Q-Methodology with 44 participants. We found four prototypical attitudes to which subgroups of participants relate: 1) technical enthusiasts, 2) social skeptics, 3) service-oriented non-enthusiasts, and 4) technology-oriented non-enthusiasts. We provide an unconventional perspective on APT acceptance that helps practitioners prioritize design requirements and communicate, targeting users’ specific attitudes.
Understanding user needs and behavior in automated vehicles (AVs) while traveling is essential for future in-vehicle interface and service design. Since AVs are not yet market-ready, current knowledge about AV use and perception is based on observations in other transportation modes, interviews, or surveys about the hypothetical situation. In this paper, we close this gap by presenting real-world insights into the attitude towards highly automated driving and non-driving-related activities (NDRAs). Using a Wizard of Oz AV, we conducted a real-world driving study (N= 12) with six rides per participant during multiple days. We provide insights into the users’ perceptions and behavior. We found that (1) the users’ trust a human driver more than a system,(2) safety is the main acceptance factor, and (3) the most popular NDRAs were being idle and the use of the smartphone.
In catastrophic events, the potential of help has grown through new technologies. Voluntary help has many forms. Within this paper different categories of voluntary help are suggested. Those categories are based on properties like organizational structures, helping process, kind of prosocial behavior and many more. A focus is clearly on the organizational structure and motivational aspects of helper groups. Examples are given for each category. The categorization’s aim is to give a brief overview of possible properties a group of system users could have.
The presented work formulates an framework in which early prediction of drivers lane change behavior is realized. We aim to build a representation of drivers lane change behavior in order to recognize and to predict driver's intentions as a first step towards a realistic driver model. In the test bed of the Institute of Neuroinformatik, based on the traffic simulator NISYS TRS 1, 10 individuals have driven in the experiments and they performed more then 150 lane change maneuvers. Lane-offset, distance to the front car and time to contact, were recorded. The acquired data was used to train - in parallel- a recurrent neural network, a feed forward neural network and a set of support vector machines. In the followed test drives the system was able of performing a lane change prediction time of 1.5 sec beforehand. The proposed approach describes a framework for lane-change detection and prediction, which will serve as a prerequisite for a successful driver model.
In the presented work we compare machine learning techniques in the context of lane change behavior performed by humans in a semi-naturalistic simulated environment. We evaluate different learning approaches using differing feature combinations in order to identify appropriate feature, best feature combination, and the most appropriate machine learning technique for the described task. Based on the data acquired from human drivers in the traffic simulator NISYS TRS 1 , we trained a recurrent neural network, a feed forward neural network and a set of support vector machines. In the followed test drives the system was able to predict lane changes up to 1.5 sec in beforehand.
Women are still underrepresented at the highest management levels. The think-manager-think-male phenomenon suggests that leadership is associated with male rather than female attributes. Although styling has been shown to influence the evaluation of women's leadership abilities, the relevant specific features have been left remarkably unaddressed. In a 2 × 2 × 2 × 2 (skirt/pants, with/without jewelry, loose hair/braid, with/without makeup) between-subjects design, 354 participants evaluated a woman in a photograph. Women with makeup, pants, or with jewelry were rated as more competent than women without makeup, with skirts, or without jewelry. A combination of loose hair and no makeup was perceived as warmest, and women with loose hair were more likely to be hired than those with braids. In sum, even subtle changes in styling have a strong impact on how women's leadership abilities are evaluated.
Massive open online courses (MOOCs) become more and more popular. These course formats are typically highly flexible and attract large groups of learners from heterogeneous backgrounds. So far research in this area concentrating on success factors for low dropout rates and high satisfaction on the side of the learners in MOOCs is scarce. In this chapter, we describe experiences of a large online course offered to students of two large German universities. Based on theory drawn from a social psychological perspective on the relevance of social interaction for learning, we describe the background, structure, and specific elements of the MOOC-like course. We outline evaluation results of both small group collaboration (in workshops) and mass interaction (via forum and wiki usage) as well as results of the general evaluation of the overall course concept. We argue that the specific mixture of small and large group interaction as well as teacher- and learner-generated content is especially promising with regard to satisfaction, learning outcomes, and course completion rates.
With the spread of mobile devices among both, men and women, app-based games also become more popular. While traditionally, digital games are more famous among men, women seem to spend more time and money on mobile gaming. There are a lot of open questions with regard to women and gaming in general; research on gender differences in app-based mobile gaming is almost nonexistent. Taking an exploratory perspective, our study investigates gender differences in general usage patterns, attachment towards the game and motivational differences for choosing to play the famous QuizClash app. Also, we identify differences in reported and actual performance in specific categories and capture anticipation of success as well as likeliness of choosing specific knowledge categories depending on the opponents’ performance profile.
This work aims to generate synthetic electromyographic (EMG) signals using Generative Adversarial Network (GAN). GANs are considered as one of the most exciting and promising approaches in deep learning [6], offering the possibility to generate artificial data based on real data. GAN consists of two main parts, a discriminator that attempts to differentiate between the generated data and the original data, and a generator that tries to fool the discriminator by generating data which looks like real data, the GAN works by staging a two-player
minimax game between generator and discriminator networks. To achieve the objective of generating realistic artificial electromyographic signals, two different architectures are considered for the generator and the discriminator networks of the GAN model: Long short-term memory (LSTM), which can avoid the long-term dependency problem and remembers information over a long period of time, and convolutional neural network (CNN), which is a powerful tool at automatic feature extraction. Different combinations of CNN and LSTM including hybrid model are experimented within the GAN using the same training data-set. The results and performances of each combination are compared and reviewed. The generated artificial EMG signals can be used to
simulate real muscle activity situations to for example improve muscle signal controlled prostheses using artificial data that may include conditions that does not exist in real data. This method of artificial data generation is not limited to EMG signals, the network can also be used to generate other synthetic biomedical signals such as electroencephalogram (EEG) or electrocardiogram (ECG) that can be practically used for testing algorithms and classifiers.
The uprising levels of autonomous vehicles allow the drivers to shift their attention to non-driving tasks while driving (ie, texting, reading, or watching movies). However, these systems are prone to failure and, thus, depending on human intervention becomes crucial in critical situations. In this work, we propose using human actuation as a new mean of communicating take-over requests (TOR) through proprioception. We conducted a user study via a driving simulation in the presence of a complex working memory span task. We communicated TORs through four different modalities, namely, vibrotactile, audio, visual, and proprioception. Our results show that the vibrotactile condition yielded the fastest reaction time followed by proprioception. Additionally, proprioceptive cues resulted in the second best performance of the non-driving task following auditory cues.
Checking wind turbines for damage is a common problem for operators of wind parks, as regular inspections are legally required in many countries and prevention is economically viable. While some of the common forms of damage are easily visible on the surface, structural problems can remain invisible for years before they eventually result in catastrophic failure of a rotor blade. Common forms of testing fibre composite parts like ultrasonic testing or X-ray tests are impractical due to the large dimensions of wind turbine components and their limited accessibility for any short-range methods. Active thermographic inspection of wind turbines is a promising approach to testing for structural flaws beneath the surface of rotor blades. As part of an ongoing research project, a setup for testing the general viability of this method was built and used to compare different thermographic cameras. A sample cut from a discarded rotor blade was modified to emulate structural damage. The results are promising for the development of a cost effective on-site testing system.
In recent years, the number of mobile devices that are available for learning scenarios has increased a lot. Different learning settings are usually supported by mobile devices. On the one hand we find mobile devices in informal learning settings, and on the other hand in formal learning settings like a usual lecture. This paper motivates the question whether the usage of mobile devices in a usual lecture is something that is wanted by the students. A first case study is provided with an platform independent prototype that gives an initial indication for preferred usage.
NewsGrid
(2005)
Film archives—particularly those storing video material on all kinds of news items—are important information sources for TV stations. Each TV station creates and maintains its own archive by storing video material received via satellite and/or internet on tapes in analogue and/or digital form. It cannot be predicted in advance which of this archived material will actually be used. Thus all material received must be catalogued and stored. On average only a small percentage of the material stored is actually used. Due to the increase in data volumes the cost of maintaining such repositories and retrieving particular stored items has become prohibitive. To-day digital videos are increasingly replacing analogue material. Digital videos offer the advantage that the can be stored in distributed databases and then be transferred without loss of quality to the transmitting station. Such digital archives can be made accessible to many TV stations, thus spreading the maintenance cost. Individual stations can retrieve only the material they actually need for particular news casts. In this paper a grid architecture for distributed video archives for news broadcasts is proposed. A crucial aspect of such a grid approach is that advanced methods for retrieving data must be available.
Sensing and processing of multimedia information is one of the basic traits of human beings. The development of digital technologies and applications allows the production of huge amounts of multimedia data. The rapidly decreasing prices for hardware such as digital cameras/camcorders, sound cards and the corresponding displays led to wide distribution of multimedia-capable input and output devices in all fields of the everyday life, from home entertainment to companies and educational organisations. Thus, multimedia information in terms of digital pictures, videos, and music can be created intuitively and is affordable for a broad spectrum of users.
Knowledge of fundamentals of human-computer interaction resp. usability engineering is getting more and more important in technical domains. However this interdisciplinary field of work and corresponding degree programs are not broadly known. Therefore at the Hochschule Ruhr West, University of Applied Sciences, a program was developed to give teen-aged pupils insights into this area in a project-based learning environment with professional tools. Within the last 18 month this project was successfully conducted several times with participants of different age.
In recent years the diversity and the ownership of mobile devices steadily increased while the prices for this kind of devices decreased to a level that allows many students to own reasonably powerful devices. As mobile devices are also being used in learning scenarios, the challenge of today is the integration of multiple heterogeneous devices into existing and upcoming learning scenarios. This paper describes an architecture that allows easy integration of various kinds of mobile and non-mobile devices. The presented architecture will be exemplified by a group discussion scenario in a heterogeneous learning environment. The paper concludes with the description of a pilot study using the described system.
In this scientific research, an innovative sensor system is developed to prevent child heatstrokes in vehicles. The system incorporates a 24 GHz Continuous-Wave (CW) radar system, which identifies vital signs of an infant through a 4-by-1 patch antenna array embedded in a specifically designed circuit board. Intelligent signal processing algorithms analyze data generated by the radar chip and execute processing tasks on a robust microcontroller. The child’s respiration
rate can be extracted qualitatively from the data in nearly real-time, enabling the system to differentiate between a child and a mere shopping bag on the seat. In the event of identifying a critical condition, the system transmits this information via a data bus to a central ECU within the vehicle. This ECU is integrated with GSM and GPS connections, allowing communication with the driver or emergency services. The development of the sensor system adheres to existing
automotive industry standards, featuring a cost-effective design intended as a prototype for large-scale production. Through rigorous evaluation across various scenarios, including realworld
situations with children, the sensor system is refined. The continuously reliable function of the developed radar-based sensor system holds the potential to save children’s lives, making
a major contribution to automotive safety.
In this demo paper we present a new visualization technique for dynamic networks. It displays the time slices of the dynamic network using two dimensional graph layouting algorithms and stacks these in the third dimension to show the development over time. The visualization ensures that the same node always has the same position in each time slice so that it is easy to follow its development. It also allows filtering data and influencing node appearance based on properties. Additionally we offer a two dimensional comparison view for two time slices which highlights changes in graph structure and (if available) in measures of nodes. The presented visualization technique is implemented using Web technology and is available in a Web-based analytics workbench. We demonstrate the benefits of these techniques by an analysis of a data set from a learning community.