Search

While the HCI community has developed many unique shape-changing artifacts for supporting novel interactions and experiences, little research has investigated long-term organic experiences of living with these objects. In parallel, Wiberg has proposed the notion of the materiality of interaction as a new ontology for tangible computing. However, cases of designing for materiality are still sparse. The overarching goal of this doctorial study is to fill in the gap between materiality and shape change. To do so, I plan to adopt design-oriented HCI approaches to frame my design implementations and field deployments. Fabricating shape-changing artifacts may extend practices of designing for materiality. Reflecting on design processes and accumulating empirical data of these devices may enrich the understanding of materiality in interaction design and HCI fields.

In this paper, a new speech driven 3-D geometric tongue model is constructed. The constructed 3-D tongue shape is controlled with control points on 2-D midsagittal tongue curve, and speech-driven inverse estimation based on the constructed model is evaluated by empirical data. X-Ray 2-D vocal tract motion videos are tagged for the midsagittal tongue motion, and static 3-D vocal tracts of 20 phonemes are collected with MRI for the realistic 3-D tongue shape. MFCC are calculated from the videos as acoustic features, and are then used in a LSTM-RNN to predict the control points movement of the tongue shape. Three geometrically intuitive control points are selected to represent and calculate the midsagittal line of the tongue through linear regression. Cross-sections on the central lines of the tongues, whose height, width and angle are then predicted from the midsagittal line, are reconstructed with geometric curves, and the shape of each cross-section are then placed on the midsagittal line to get the overall predicted moving grid of the 3-D tongue. In this 3-D tongue model, acoustic features and realistic tongue motion are mapped directly to preserve more realistic articulatory details, and the control points are intuitive for non-experts to control the model, and the geometric tongue shapes predicted are comparable with realistic tongue dynamics. Based on the proposed method, the speech-driven prediction is evaluated with the realistic data, which proved this proposed method feasible.

In order to improve the level of College Students' employment management, this paper puts forward an evaluation model of College Students' Employment Quality Based on AHP. First of all, this paper analyzes the evaluation index system of College Students' employment quality, and uses AHP to evaluate the employment quality of college students. The empirical data analysis results show that the accurate evaluation of the employment quality of college students can be achieved by using the analytic hierarchy process to evaluate the employment quality of College Students.

Software Product Lines (SPLs) are rarely developed from scratch. Commonly, they emerge from monolithic architectures when there is a need to create tailored variants, or from existing variants created in an ad-hoc way once their separated maintenance and evolution become challenging. Despite the vast literature about re-engineering systems into SPLs and related technical approaches, there is a lack of detailed analysis about the process itself and the effort that is involved. We provide and analyze empirical data of an existing SPL extraction process: the ArgoUML monolithic architecture transition to ArgoUML-SPL. The analysis relies on information mined from the version control history of the source-code repository and the discussion with developers that took part in the process. The contribution of this study is an in-depth characterization of the process compared to previous works that focused only on the structural results of the final SPL. We made publicly available the dataset and the analysis scripts to be used as baseline for extractive SPL adoption research and practice.

The design of while loops is among the hardest lessons for beginners in programming. Their design is difficult because students must do more than solve a problem. They must also, for example, correctly sequence mutations, define loop invariants, and avoid infinite loops. Another difficulty students face is making while loops iterative. This issue is commonly ignored in programming textbooks for beginners despite being relevant to future courses such as Computer Architecture, Programming Languages, and Algorithms. The difficulty with making while loops iterative revolves around the elimination of delayed operations. This requires introducing beginners to the concept of control. This article presents a novel transformation recipe for beginners to make while loops iterative. The transformation recipe guides students on how to accumulate control information on a stack to eliminate delayed operations in the body of loops. In addition, this article presents descriptive statistics obtained from students on the maiden voyage of the new design recipe. The empirical data suggests that students feel that writing iterative while loops is hard, but enlightening. In addition, the empirical data suggests that students have a very favorable opinion about designing while loops.

With the growing number of GPU-based supercomputing platforms and GPU-enabled applications, the ability to accurately model the performance of such applications is becoming increasingly important. Most current performance models for GPU-enabled applications are limited to single node performance. In this work, we propose a methodology for end-to-end performance modeling of distributed GPU applications. Our work strives to create performance models that are both accurate and easily applicable to any distributed GPU application. We combine trace-driven simulation of MPI communication using the TraceR-CODES framework with a profiling-based roofline model for GPU kernels. We make substantial modifications to these models to capture the complex effects of both on-node and off-node networks in today's multi-GPU supercomputers. We validate our model against empirical data from GPU platforms and also vary tunable parameters of our model to observe how they might affect application performance.

Problem: developers are increasingly adopting security practices in software projects in response to cyber threats. Despite the additional effort required to perform those practices, current cost models either do not consider security as an input or were not properly validated with empirical data. Hypothesis: increasing degrees of application of security practices and security features, motivated by security risks, lead to growing levels of added software development effort. Such an effort increase can be quantified through a parametric model that takes as input the usage degrees of security practices and requirements and outputs the additional software development effort. Contributions: the accurate prediction of secure software development effort will support the provision of a proper amount of resources to projects. We also expect that the quantification of the security effort will contribute to advance research on the cost-effectiveness of software security.

Smartphones are becoming an integral part of the Internet of Things-(IoT) paradigm with their built-in sensor ecosystem providing a convenient platform to study human behavior. Examples include activity monitoring, transportation mode detection, travel behaviour and so on. All of these examples are connected in one way or the other to the IoT domain such as smart cities, smart health and so on. In this paper, we attempt to use smartphone sensors to understand college student behaviour within a campus for 30 days. The rising use of smartphones by the student population, motivated us to install a continuous sensing application on their smartphones to understand their daily routines, their physical activity levels, their sleep patterns, and their mobility patterns within the campus. Our empirical data was supported by qualitative responses from the students. The results of this experiment showed that smartphones indeed could be utilized to extract behavioral patterns of students.

Outsourcing effortful problems as microtasks has been successfully implemented by various human computation serious games or GWAP. Still, most of the academic ap-proaches validate their results by conducting laboratory studies. While these have the potential to assess proposed techniques thoroughly with respect to quantitative and qualitative measures, they are prone to the often under-estimated experimenter bias. In a large-scale field study(n= 713), we collect practically relevant empirical data about the quality of player behavior in a human computation serious game and classify the results as useful, insufficient or deliberately disruptive executions. Due to the drastic proportion of disruptive behavior (20.2%), we particularize explanations for this kind of behavior and discuss counteracting measurements.

The biodiversity literature is one of the longest-standing examples of recording heritage in the world. Today there are many efforts to standardise and integrate the literature to ensure access to the information, both for heritage and research purposes. Ontologies are increasingly being turned to as knowledge representation tools in these efforts. However, the validity of using ontological frameworks to represent biological taxonomies has been questioned. Biological taxonomies use the scientific nomenclature to assign names to described species. While the nomenclature is a useful classification tool, it can also be a source of confusion because of its synonymous, homonymous and fluid nature. Despite this, no empirical evaluation of scientific nomenclature use in the literature has ever been performed. Corpus-based analysis is already used in automatic ontology extraction, and this study explores the possibility of applying recently developed lexicography techniques to the problem to provide an evaluation of the empirical data in the literature, and serve as a comparison with existing ontologies. This paper focuses on the work flow, parameters and preliminary findings of the research investigating how to extract structures from the literature to perform these comparisons. It uses the manipulation of corpus analysis techniques, visualisation and filtering methods to do so and evaluates potential classification and disambiguation qualities of the resulting graphs for future work. Preliminary results look at the effects of frequency and salience when filtering the graphs, which indicate that these filter parameters could be used for different purposes in revealing relationships between organism mentions.

In this paper we unpack empirical data from two domains within the Blockchain information infrastructure: The cryptocurrency trading domain, and the energy domain. Through these accounts we introduce the relational concepts of Blockchain Assemblages and Whiteboxing. Blockchain assemblages comprise configurations of digital and analogue artefacts that are entangled with imaginaries about the current and future state of the Blockchain information infrastructure. Rather than being a black box, Blockchain assemblages alternate between being dynamic and stable entities. We propose Whiteboxing as the sociomaterial process which drives blockchain assemblages in their dynamic state to be (re)configured, while related artefacts and imaginaries are simultaneously transformed, creating dynamic representations. Whiteboxing is triggered during disconfirming events when representations are discovered as problematic. Complementing existing historical accounts demonstrating technologies in the making, the contribution of this paper, proposes whiteboxing as an analytical concept which allows us to unpack how contemporary technologies are created through entrepreneurial activities.

Present study on recommender systems mainly focuses on the logical nature of the existence or non-existence of a priority relationship between the user and data item, regardless of the ratio or implicative relationship based on statistics between users and data items in a particular context. Therefore, this report proposes a new approach to recommender systems based on data variation trends; such method will help form a new approach to recommender systems on basis of knowledge available in the form of implicity by computation of partial derivatives for interestingness measurements. In addition, experiments aim at evaluating the effectiveness of the proposed model with traditional models based on using MSWeb dataset as empirical data, comparing and discussing the results obtained from the proposed model.

Recent development in self-monitoring devices indicates that using quantified data in clinical practice supporting chronic diseases management holds a big potential. However, exploration of this design space also suggests that some unattended challenges still exist, such as a low adoption rate of self-monitoring tools in existing clinical practice. In this text, we therefore focus on the ways healthcare professionals use quantified data in their practice. We draw on empirical data from an ethnographic study of a cancer rehabilitation center. Our preliminary findings suggest that the self-monitoring tool supported the nurses' work because it became a functional complement to their work by allowing them to appropriate the device to their and the patients' needs.

In contrast to the extensive studies on static target pointing, much less formal understanding of moving target acquisition can be found in the HCI literature. We designed a set of experiments to identify regularities in 1D unidirectional moving target selection, and found a Ternary-Gaussian model to be descriptive of the endpoint distribution in such tasks. The shape of the distribution as characterized by μ and σ in the Gaussian model were primarily determined by the speed and size of the moving target. The model fits the empirical data well with 0.95 and 0.94 R2 values for μ and σ , respectively. We also demonstrated two extensions of the model, including 1) predicting error rates in moving target selection; and 2) a novel interaction technique to implicitly aid moving target selection. By applying them in a game interface design, we observed good performances in both predicting error rates (e.g., 2.7% mean absolute error) and assisting moving target selection (e.g., 33% or a greater increase in pointing accuracy).

Today's data visualization tools offer few capabilities and no representational standards for conveying uncertainty. Our aim is to remedy this by creating a visual vocabulary for uncertainty in data. However, we must first develop an extensible methodology for validating the effectiveness of uncertainty visualization techniques. In this paper we describe a test instrument we have developed to collect empirical data concerning four measures - accuracy, response time, reported confidence, and cognitive load - that can be used to evaluate techniques for visualizing data with uncertainty.

Voice User Interfaces (VUIs) are growing in popularity. However, even the most current VUIs regularly cause frustration for their users. Very few studies exist on what people do to overcome VUI problems they encounter, or how VUIs can be designed to aid people when these problems occur. In this paper, we analyze empirical data on how users (n=12) interact with our VUI calendar system, DiscoverCal, over three sessions. In particular, we identify the main obstacle categories and types of tactics our participants employ to overcome them. We analyzed the patterns of how different tactics are used in each obstacle category. We found that while NLP Error obstacles occurred the most, other obstacles are more likely to frustrate or confuse the user. We also found patterns that suggest participants were more likely to employ a "guessing" approach rather than rely on visual aids or knowledge recall.

In human-human interactions, individuals naturally achieve fluency by anticipating the partner»s actions. This predictive ability is largely lacking in robots, leading to stilted human-robot interactions. We aim to improve fluency in human-robot reaching motions using a unified predictive model of human reaching motions. Using this model, we allow the robot to infer human intent, while also applying the same model to generate the robot»s motion to make its intent more transparent to the human. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.

This paper studied the information diffusion process in Microblog network in China. By empirical data collection we proposed a new diffusion model of concept based on mean-field assumption. The model is developed on BA model and under the mean-field assumption, by which we divide the users into three groups: "non-enlightened" group, "enlightened and committed" group and "enlightened yet non-committed" group. Experiments show that the lager the "enlightened yet non-committed" group to an opinion, the slower the diffusing process, and the more rational the network would be. And the transmission ways is insignificant referring the result.

In literature, individuals, organizations, and technology can all been modelled as systems. This paper justifies the need for, and describes the development of a dual aspect model, which can be used to model and manage the interaction, alignment, and conflict between systems. Our initial dual aspect model consisted of overlapping semiotic onions [14], however model results did not match empirical data. When onion layer orders were adapted to reflect Hall's Major Triad definitions [6], system layer interaction was found to fit well with empirical data collected within modern organizations. Decomposition of the model allows academics and / or practitioners to consider systems alignment stages. Moreover, correction of layer definitions facilitates consideration of norms at the core belief / conceptual level, which supports analysis of human intention. In summary, this paper proposes a newly validated four layered onion structure and the dual alignment pathways, which can be used together to consistently represent and manage alignment between systems (i.e. individuals, technologies and/or organizational systems). The overlapping of these onions, can also be used to study the technical, formal, and informal interplay between individual, organizational and technology aspects.

Over the past years, there has been an increase in the application of model driven engineering in industry. Similar to traditional software engineering, understanding how technologies are actually used in practice is essential for developing good tooling, and decision making processes. Unfortunately, obtaining and analyzing empirical data in a model-driven context is still tedious and time consuming, introducing large lead-times. In this paper we present a framework for the automated extraction, analysis, and visualization of data and metrics on model-driven artifacts. We subsequently present various examples of how the framework was successfully applied in a large industrial setting to answer a plethora of different questions with respect to decision making and tool development.

Although video sharing is common among youth, schools are only beginning to apply digital videos and digital storytelling to formal learning. This paper presents pedagogical models, examples, best practices, and outcomes that illustrate how teachers and students design and use digital stories in knowledge creation in cross-cultural settings. The results are based on the empirical data and findings from several international pilot studies. On the one hand, working with digital video stories drove engagement. However, on the other hand, technical issues significantly lowered engagement. In addition, the video inquiry pedagogy supported inquiry learning. Students began to pose scientifically oriented questions and seek answers together.

The switch from gasoline-powered vehicles to electric vehicles (EVs) is an important step to reduce greenhouse gas emissions. To this end, many European countries announced EV stock targets, e.g., Germany aims to have one million EVs on the roads by 2020. To achieve these goals and to handle the range limitation of EVs, a widespread publicly accessible charging infrastructure is needed. This paper provides a dynamic spatial and temporal simulation model for the building of charging infrastructure on a municipality scale. We evaluate empirical data about the timely utilization of different charging stations in the German federal state of Bavaria. This data is used to derive empirical models for the start time and duration of charging events as well as the popularity of charging stations. We develop a lightweight discrete event simulation model which can be used to investigate different expansion strategies, e.g., based on the load of charging stations or the number of successful and failed charging attempts. We show the applicability of our model using the German federal state of Bavaria as a use case.

This paper proposes an unsupervised framework for tracking real world events from their traces on Twitter and Instagram. Empirical data suggests that event detection from Instagram streams errs on the false-negative side due to the relative sparsity of Instagram data (compared to Twitter data), whereas event detection from Twitter can suffer from false-positives, at least if not paired with careful analysis of tweet content. To tackle both problems simultaneously, we design a unified unsupervised algorithm that fuses events detected originally on Instagram (called I-events) and events detected originally on Twitter (called T-events), that occur in adjacent periods, in an attempt to combine the benefits of both sources while eliminating their individual disadvantages. We evaluate the proposed framework with real data crawled from Twitter and Instagram. The results indicate that our algorithm significantly improves tracking accuracy compared to baselines.

Detecting calls to action in natural text conversations, such as emails, chats and instant messages, is a pre-processing step that enables assistive technologies, such as the ones used in virtual assistants and chatbots, to capture and handle human-to-human interactions. Different forms of question detection are often used as a proxy solution for detecting intended actions. In this position paper, we provide empirical evidence that, despite their accuracy in detecting questions, both state-of-the-art industrial and academic question detection technologies are not good proxy solutions for inferring intended actions. We provide empirical data to demonstrate that the problem should be approached differently and as a comparison we present results obtained with a solution derived from our patent pending intention inference technology.

In this work, we examine the technology acceptance of cloud computing by using the second iteration of the unified theory of acceptance and use of technology, from now on referred to as UTAUT2. UTAUT is a well established methodology widely used for the acceptance of technology. Empirical data was analyzed from 132 Cloud developers, Cloud users, IT professionals and managers using factor analysis. The results indicate that user acceptance of cloud computing can be explained and predicted by variables concerning performance expectancy, effort expectancy, social influence, habit, Price/Value, facilitating conditions, hedonic motivation and behavioral intention. These results further advance the theory and add to the bases for further research targeted at enhancing our knowledge of technology adoption for cloud computing. They also provide a first base for companies and governments on how to adopt and successfully integrate cloud technologies.

Accurately predicting the accuracy of finger-touch target acquisition is crucial for designing touchscreen UI and for modeling complex and higher level touch interaction behaviors. Despite its importance, there has been little theoretical work on creating such models. Building on the Dual Gaussian Distribution Model[3], we derived an accuracy model that predicts the success rate of target acquisition based on the target size. We evaluated the model by comparing the predicted success rates with empirical measures for three types of targets including 1-dimensional vertical and horizontal, and 2-dimensional circular targets. The predictions matched the empirical data very well: the differences between predicted and observed success rates were under 5% for 4.8 mm and 7.2 mm targets, and under 10% for 2.4 mm targets. The evaluation results suggest that our simple model can reliably predict touch accuracy.

Empirical software engineering has produced a steady stream of evidence-based results concerning the factors that affect important outcomes such as cost, quality, and interval. However, programmers often also have strongly-held a priori opinions about these issues. These opinions are important, since developers are highly-trained professionals whose beliefs would doubtless affect their practice. As in evidence-based medicine, disseminating empirical findings to developers is a key step in ensuring that the findings impact practice. In this paper, we describe a case study, on the prior beliefs of developers at Microsoft, and the relationship of these beliefs to actual empirical data on the projects in which these developers work. Our findings are that a) programmers do indeed have very strong beliefs on certain topics b) their beliefs are primarily formed based on personal experience, rather than on findings in empirical research and c) beliefs can vary with each project, but do not necessarily correspond with actual evidence in that project. Our findings suggest that more effort should be taken to disseminate empirical findings to developers and that more in-depth study the interplay of belief and evidence in software practice is needed.

WiFi offloading has emerged as a key component of cellular operator strategy to meet the rich data needs of modern mobile devices. Hence, mobile devices tend to aggressively seek out WiFi in order to provide improved user Quality of Experience (QoE) and cellular capacity relief. For home and work environments, aggressive WiFi scans can significantly improve the speed at which mobile nodes join the WiFi network. Unfortunately, the same aggressive behavior that excels in the home environment incurs considerable side effects in crowded wireless environments. In this paper, we analyze empirical data collected from large (stadium) and medium (classroom) venues, and show through controlled experiments (laboratory) how aggressive WiFi scans can have significant implications for energy and throughput for mobile nodes. We close with several thoughts on the disjoint incentives for properly balancing WiFi discovery speed and crowded network interactions.

A number of recent studies of information diffusion in social media, both empirical and theoretical, have been inspired by viral propagation models derived from epidemiology. These studies model propagation of memes, i.e., pieces of information, between users in a social network similarly to the way diseases spread in human society. Naturally, many of these studies emphasize social exposure, i.e., the number of friends or acquaintances of a user that have exposed a meme to her, as the primary metric for understanding, predicting, and controlling information diffusion. Intuitively, one would expect a meme to spread in a social network selectively, i.e., amongst the people who are interested in the meme. However, the importance of the alignment between the topicality of a meme and the topical interests of the potential adopters and influencers in the network has been less explored in the literature. In this paper, we quantify the impact of the topical alignment between memes and users on their adoption. Our analysis, using empirical data about two different types of memes, i.e., hashtags and URLs spreading through the Twitter social media platform, finds that topical alignment between memes and users is as crucial as the social exposure in understanding and predicting meme adoptions. Our results emphasize the need to look beyond social network-based viral propagation models and develop microscopic models of information diffusion that account for interests of users and topicality of information.

In real world domains, from healthcare to power to finance, we deploy computer systems intended to streamline and improve the activities of human agents in the corresponding non-cyber worlds. However, talking to actual users (instead of just computer security experts) reveals endemic circumvention of the computer-embedded rules. Good-intentioned users, trying to get their jobs done, systematically work around security and other controls embedded in their IT systems.This poster reports on our work compiling a large corpus of such incidents and developing a model based on semiotic triads to examine security circumvention. This model suggests that mismorphisms---mappings that fail to preserve structure---lie at the heart of circumvention scenarios; differential perceptions and needs explain users' actions. We support this claim with empirical data from the corpus.

We conducted microscopic analysis on several frequently observed types of work-related reading to find ways to support each type of reading. We obtained empirical data from video recording, concurrent verbal reporting, and retrospective reporting by 18 participants in 10 target types of reading that use paper. Using these data, first, we categorized the ways people interact with paper documents when reading in detail. We analyzed which types of behaviors were frequently observed in each type of reading based on these categories. We will discuss what kind of support is required for each type of reading by specifying what types of behaviors were frequently observed for certain types of reading.

Website fingerprinting attacks enable an adversary to infer which website a victim is visiting, even if the victim uses an encrypting proxy, such as Tor. Previous work has shown that all proposed defenses against website fingerprinting attacks are ineffective. This paper advances the study of website fingerprinting defenses by first laying out the complete specifications of the CS-BuFlo scheme outlined by Cai, et al. CS-BuFlo, which is based on the BuFlo defense proposed by Dyer, et al., was not fully-specified by Cai, et al, but has nonetheless attracted the attention of the Tor developers. Next, a full working implementation of CS-BuFlo is provided. Finally, a thorough evaluation of CS-BuFlo is performed using empirical data (rather than data from simulations). Our experiments find that CS-BuFlo has high overhead (around 2.3-2.8x) but can get 6times closer to the bandwidth/security trade-off lower bound than Tor or SSH.

Sharing data with client-side encryption requires key management. Selecting an appropriate key management protocol for a given scenario is hard, since the interdependency between scenario parameters and the resource consumption of a protocol is often only known for artificial, simplified scenarios. In this paper, we explore the resource consumption of systems that offer sharing of encrypted data within real-world scenarios, which are typically complex and determined by many parameters. For this purpose, we first collect empirical data that represents real-world scenarios by monitoring large-scale services within our organization. We then use this data to parameterize a resource consumption model that is based on the key graph generated by each key management protocol. The preliminary simulation runs we did so far indicate that this key-graph based model can be used to estimate the resource consumption of real-world systems for sharing encrypted data.

PCK (Pedagogical Content Knowledge) is that special mixture of deep content knowledge and deep pedagogical knowledge which results in specialized knowledge around a subject that grows with the years of teaching experience. We present our approach to foster development of PCK during university based teacher education; namely by including our teacher students in cyclic processes of researching and developing teaching models. In this paper, we describe our approach for fostering PCK through reflection on the activities of planning and teaching, and how we included this in our cyclic model. We also present first results from an evaluation of students' PCK. Based on the empirical data we present a preliminary model of development steps of PCK, describing three competence levels divided in the dimensions 'teaching', 'learning', and 'other'.

Here we develop an alternate method to evaluate the evolutionary mechanics of theoretical network models which is free of the bias introduced by seed graph selection. We run a model in reverse directly on empirical data, and then run the model forward to generate a network topology to compare against the empirical data. We implement this method on a well-regarded gene duplication and divergence model, and find that it is unable to generate the high clustering found in the empirical data.

Engaging students in science, technology, engineering, and math (STEM) fields is critical to ensure the success of the next generation of scientists and engineers. Given that 97% of American teens play video games, there is a tremendous opportunity to facilitate interest in STEM topics through the design of engaging learning games. While a growing number of serious games have been developed for biological science and computer science learning, few address the communication and technical challenges that arise in cyberinfrastructure intensive projects, where multiple domain scientists and computer scientists collaborate. This paper describes empirical data collected during a year-long human centered game design process, in which design ideas generated by high school students were bridged with cyberinfrastructure and bioinformatics learning concepts. Our research shows that "fun" and engaging game elements are well suited for addressing the sociotechnical aspects of cyberinfrastructure projects. In this research we provide a human centered game design methodology for science educators and science game designers, as well as design implications for integrating game-based experiences into the use of large-scale shared computing resources and services.

Auditeur is a general-purpose, energy-efficient, and context-aware acoustic event detection platform for smartphones. It enables app developers to have their app register for and get notified on a wide variety of acoustic events. Auditeur is backed by a cloud service to store user contributed sound clips and to generate an energy-efficient and context-aware classification plan for the phone. When an acoustic event type has been registered, the smartphone instantiates the necessary acoustic processing modules and wires them together to execute the plan. The phone then captures, processes, and classifies acoustic events locally and efficiently. Our analysis on user-contributed empirical data shows that Auditeur's energy-aware acoustic feature selection algorithm is capable of increasing the device lifetime by 33.4%, sacrificing less than 2% of the maximum achievable accuracy. We implement seven apps with Auditeur, and deploy them in real-world scenarios to demonstrate that Auditeur is versatile, 11.04% - 441.42% less power hungry, and 10.71% - 13.86% more accurate in detecting acoustic events, compared to state-of-the-art techniques. We present a user study to demonstrate that novice programmers can implement the core logic of interesting apps with Auditeur in less than 30 minutes, using only 15 - 20 lines of Java code.

Context: At the same time as our dependence on IT systems increases, the number of reports of problems caused by failures of critical IT systems has also increased. This means that there is a need for risk analysis in the development of this kind of systems. Risk analysis of technical systems has a long history in mechanical and electrical engineering. Objective: Even if a number of methods for risk analysis of technical systems exist, the failure behaviour of information systems is typically very dierent from mechanical systems. Therefore, risk analysis of IT systems requires dierent risk analysis techniques, or at least adaptations of traditional approaches. This means that there is a need to understand what types of methods are available for IT systems and what research that has been conducted on these methods. Method: In this paper we present a systematic mapping study on risk analysis for information systems. 1086 unique papers were identied in a database search and 57 papers were identied as relevant for this study. These papers were classied based on 5 dierent criteria. Results: This classication, for example, shows that most of the discussed risk analysis methods are qualitative and not quantitative and that most of the risk analysis methods that are presented in these papers are developed for IT systems in general and not for specic types of IT system, like medical systems. Conclusions: The results show that many new risk analysis methods have been proposed in the last decade but even more that there is a need for more empirical evaluations of the dierent risk analysis methods. Many papers were identified that propose new risk analysis methods, but few papers discuss a systematic evaluation of these methods or a comparison of dierent methods based on empirical data.

In this paper, we present a method of real-time graphical presentation from empirical data for welding tasks under virtual reality (VR) environments. To express virtual situations with datasets produced from real operations, we expressed virtual objects considering both the welding shape and datasets related to real world. Additionally, we also carried out a comparison study between empirical data and virtually generated data under the same conditions, the predicted results of graphical presentation had more than 90% accuracy.

We employ user activity data from three highly popular gifting applications on Facebook to study the evolution of user activity on applications through the most commonly-used growth mechanism, namely Application Requests. We find user activity graphs differ from friendship graphs in large part due to the inherent directionality of user activity, and node transience. Our results show that, unlike degree distributions in friendship graphs, activity graphs exhibit strong asymmetry in in- and out-degree distributions, and that out-degrees are not accurately described by currently known parametric distributions. As such, user activity graphs cannot be simulated through existing intent- and feature-driven algorithms that can model friendship graphs. We present a novel probabilistic growth model for user activity on the gifting genre of social applications. Our model decouples in- and out-degrees based on their distinct nature exhibited by our empirical data. We use the insight that regardless of increasing, declining or stable user activity, gifting application user activity exhibits the same graph structure. Our model produces synthetic graphs that consist of disconnected components with low clustering of nodes, and exhibit degree structures very similar to our real activity data. We discuss the benefits and shortfalls of our model and its applicability to other types of OSN-based applications, such as social games. To the best of our knowledge this study is the first to explore and model user activity growth processes on OSN-based applications.

In wireless mobile networks, energy can be saved by using dynamic transmission scheduling with pre-knowledge about channel conditions. Such pre-knowledge can be obtained via profiling as proposed by several existing systems which assumed that the existence of spatial link correlation makes the measured channel status at one location reusable over a long period of time. Our empirical data, however, tells a different story: spatial link correlation only maintains well within a short duration (from seconds to tens of seconds) while decreases significantly afterwards, a phenomena we call ephemeral link correlation. By leveraging this observation, we design and implement a real-time transmission scheduling system, named PreSeer, on the railway platform for cargo transportation, where the transmission of a sink (to cellular towers) can be scheduled intelligently by utilizing future channel status measured by sinks located in front of it on the same train. We have implemented and evaluated the PreSeer system on the collected data extensively over 7,000-kilometer railway routes during a period of one and half years. Results reveal that PreSeer can help save as much as 40% energy, comparing with three base-line algorithms. More importantly, lessons learned from this major effort provide useful guidelines for transmission scheduling in highly-dynamic mobile environments, where (i) channel measurements cannot be perfectly aligned due to varying vehicle velocities, and (ii) the accuracy of channel measurements is subject to hardware discrepancy as well as environment irregularity.

This work aims to provide a better understanding of the process, content and outcome of different programs' models of doctoral education in Computer Science. Our approach compares them on the basis of the analysis of empirical data gathered about the experiences and career paths of doctoral students, as well as the impacts of the initiatives themselves.

The use of open standards to promote responsible and available design in Internet-based healthcare systems is examined by using theoretical notations and recent research results from the literature. Moreover, empirical data will be gathered from a case study on an e-healthcare system for depression treatment. Our contribution is to initiate a discussion aiming at increasing the awareness on appropriate conceptual models for Internet-based depression treatment. Moreover, an up-to-date e-healthcare system, based on open standards and implemented with requirements of an Internet-based system treating patients suffering from depressions, is proposed.

In this paper we discuss the temporal aspects of indexing and classification in information systems. Basing this discussion off of the three sources of research of scheme change: of indexing: (1) analytical research on the types of scheme change and (2) empirical data on scheme change in systems and (3) evidence of cataloguer decision-making in the context of scheme change. From this general discussion we propose two constructs along which we might craft metrics to measure scheme change: collocative integrity and semantic gravity. The paper closes with a discussion of these constructs.

Until recently archival storage tiers have consisted of tape-based devices with a large storage capacity, but limited I/O performance for data retrieval. However, the growing capacity and shrinking cost of disk-based devices means that disk-based systems are now a realistic option for enterprise archival storage tiers. Given the increasingly diverse options for archival storage, robust benchmarking of possible technologies for archival storage tiers is vital for reducing risk before deployment.This paper investigates benchmarks that utilize archival workloads developed from an analysis of historical file size distributions. These benchmarks not only provide more appropriate measurements of system performance as an archive than traditional approaches, but we also incorporate the variation observed in the historical data to provide "best" and "worst" case workloads for benchmarking. By considering not only the usual workload, but also workloads at either end of the archival workload spectrum, our benchmarking is robust. It provides measures of performance for the envelope of typical archival workload observed from empirical data.

Mobile text entry methods are typically evaluated by having study participants copy phrases. However, currently there is no available phrase set that has been composed by mobile users. Instead researchers have resorted to using invented phrases that probably suffer from low external validity. Further, there is no available phrase set whose phrases have been verified to be memorable. In this paper we present a collection of mobile email sentences written by actual users on actual mobile devices. We obtained our sentences from emails written by Enron employees on their BlackBerry mobile devices. We provide empirical data on how easy the sentences were to remember and how quickly and accurately users could type these sentences on a full-sized keyboard. Using this empirical data, we construct a series of phrase sets we suggest for use in text entry evaluations.

Software fault localization is an expensive component of program debugging, and thus, many different types of fault localization techniques have been proposed over the recent years. Such techniques aim to rank program components (such as statements, blocks, functions, etc.) in decreasing order of their likelihood of being faulty, such that programmers may then examine the ranking starting from the top, until a fault is found. However, comparisons between fault localization techniques (to see which one is more effective) have generally been based on case studies and empirical data. In this paper we propose an equivalence relation by virtue of which two or more fault localization techniques may be considered equivalent if they produce identical rankings of program components, and are therefore, equally as effective. We then make use of the proposed equivalence relation to prove that several similarity coefficient-based fault localization techniques are in fact equivalent to one another. Furthermore, no case studies and/or data were required for any of the proofs of equivalency provided in this paper.

Efficiently entering text on interactive surfaces, such as touch-based tabletops, is an important concern. One novel solution is shape writing - the user strokes through all the letters in the word on a virtual keyboard without lifting his or her finger. While this technique can be used with any keyboard layout, the layout does impact the expected performance. In this paper, I investigate the influence of keyboard layout on expert text-entry performance for stroke-based text entry. Based on empirical data, I create a model of stroking through a series of points based on Fitts's law. I then use that model to evaluate various keyboard layouts for both tapping and stroking input. While the stroke-based technique seems promising by itself (i.e., there is a predicted gain of 17.3% for a Qwerty layout), significant additional gains can be made by using a more-suitable keyboard layout (e.g., the OPTI II layout is predicted to be 29.5% faster than Qwerty).

A study to compare two different empirical research methods for evaluating visualization tools is described: the traditional benchmark-task method and the insight method. The methods were compared using different criteria such as: the conclusions about the visualization tools provided by each method, the time participants spent during the study, the time and effort required to analyze the resulting empirical data, and the effect of individual differences between participants on the results. The studies used three graph visualization alternatives to associate bioinformatics microarray timeseries data to pathway graph vertices, based on popular approaches used in existing bioinformatics software.

Social network contents are not limited to text but also multimedia. Dailymotion, YouTube, and MySpace are examples of successful sites which allow users to share videos among themselves. Due to the huge amount of videos, grouping videos with similar contents together can help users to search videos more efficiently. Unlike the traditional approach to group videos into some predefined categories, we propose a novel comment-based matrix factorization technique to categorize videos and generate concept words to facilitate searching and indexing. Since the categorization is learnt from users feedback, it can accurately represent the user sentiment on the videos. Experiments conducted by using empirical data collected from YouTube shows the effectiveness of our proposed methodologies.