More Like this

1. An infrastructure approach to improving effectiveness of Android UI testing tools

   https://doi.org/10.1145/3460319.3464828  

   Wang, Wenyu ; Lam, Wing ; Xie, Tao ( July 2021 , 30th ACM SIGSOFT International Symposium on Software Testing and Analysis)

   null (Ed.)

   Due to the importance of Android app quality assurance, many Android UI testing tools have been developed by researchers over the years. However, recent studies show that these tools typically achieve low code coverage on popular industrial apps. In fact, given a reasonable amount of run time, most state-of-the-art tools cannot even outperform a simple tool, Monkey, on popular industrial apps with large codebases and sophisticated functionalities. Our motivating study finds that these tools perform two types of operations, UI Hierarchy Capturing (capturing information about the contents on the screen) and UI Event Execution (executing UI events, such as clicks), often inefficiently using UIAutomator, a component of the Android framework. In total, these two types of operations use on average 70% of the given test time. Based on this finding, to improve the effectiveness of Android testing tools, we propose TOLLER, a tool consisting of infrastructure enhancements to the Android operating system. TOLLER injects itself into the same virtual machine as the app under test, giving TOLLER direct access to the app’s runtime memory. TOLLER is thus able to directly (1) access UI data structures, and thus capture contents on the screen without the overhead of invoking the Android framework services or remote procedure calls (RPCs), and (2) invoke UI event handlers without needing to execute the UI events. Compared with the often-used UIAutomator, TOLLER reduces average time usage of UI Hierarchy Capturing and UI Event Execution operations by up to 97% and 95%, respectively. We integrate TOLLER with existing state-of-the-art/practice Android UI testing tools and achieve the range of 11.8% to 70.1% relative code coverage improvement on average. We also find that TOLLER-enhanced tools are able to trigger 1.4x to 3.6x distinct crashes compared with their original versions without TOLLER enhancement. These improvements are so substantial that they also change the relative competitiveness of the tools under empirical comparison. Our findings highlight the practicality of TOLLER as well as raising the community awareness of infrastructure support’s significance beyond the community’s existing heavy focus on algorithms. 

   more » « less
2. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   null (Ed.)

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 

   more » « less
3. A Unified Prediction Framework for Signal Maps: Not All Measurements are Created Equal

   https://doi.org/10.1109/TMC.2022.3221773  

   Alimpertis, Emmanouil ; Markopoulou, Athina ; Butts, Carter T. ; Bakopoulou, Evita ; Psounis, Konstantinos ( January 2022 , IEEE Transactions on Mobile Computing)

   Signal maps are essential for the planning and operation of cellular networks. However, the measurements needed to create such maps are expensive, often biased, not always reflecting the performance metrics of interest, and posing privacy risks. In this paper, we develop a unified framework for predicting cellular performance maps from limited available measurements. Our framework builds on a state-of-the-art random-forest predictor, or any other base predictor. We propose and combine three mechanisms that deal with the fact that not all measurements are equally important for a particular prediction task. First, we design quality-of-service functions (Q), including signal strength (RSRP) but also other metrics of interest to operators, such as number of bars, coverage (improving recall by 76%-92%) and call drop probability (reducing error by as much as 32%). By implicitly altering the loss function employed in learning, quality functions can also improve prediction for RSRP itself where it matters (e.g., MSE reduction up to 27% in the low signal strength regime, where high accuracy is critical). Second, we introduce weight functions (W) to specify the relative importance of prediction at different locations and other parts of the feature space. We propose re-weighting based on importance sampling to obtain unbiased estimators when the sampling and target distributions are different. This yields improvements up to 20% for targets based on spatially uniform loss or losses based on user population density. Third, we apply the Data Shapley framework for the first time in this context: to assign values (ϕ) to individual measurement points, which capture the importance of their contribution to the prediction task. This can improve prediction (e.g., from 64% to 94% in recall for coverage loss) by removing points with negative values and storing only the remaining data points (i.e., as low as 30%), which also has the side-benefit of helping privacy. We evaluate our methods and demonstrate significant improvement in prediction performance, using several real-world datasets. 

   more » « less
4. Performance-Based Wind Engineering: Background and State of the Art

   https://doi.org/10.3389/fbuil.2022.830207  

   Spence, Seymour M. ; Arunachalam, Srinivasan ( March 2022 , Frontiers in Built Environment)

   This paper surveys the rapidly growing field of performance-based wind engineering (PBWE) of engineered systems, with focus on not only how PBWE has evolved since its early incarnations inspired by performance-based seismic engineering, but also the unique challenges of PBWE and the research that continues to emerge to tackle them. The limitations of traditional prescriptive wind design approaches are discussed with the aim of illustrating how such approaches are inadequate for providing acceptable building performance during extreme wind events, thus motivating why performance-based strategies for wind engineering are gaining traction and are poised to complement, if not replace, current approaches to wind design. In this respect, the current state of knowledge on the factors that affect building performance via extreme structural response, damage to the envelope system, and nonstructural components, is reviewed and challenges are identified. Lastly, the potential benefit of integrating optimization methods is identified while acknowledging the computational difficulty associated with such approaches. 

   more » « less
5. Fundamental Dynamics of 3-Dimensional Seismic Isolation

   Eltahawy, W. ( January 2017 , 16th World Conference on Earthquake Engineering)

   Seismic isolation systems for buildings are generally selected to achieve higher seismic performance objectives, such as continued operation or immediate occupancy following a design earthquake event. However, recent large scale tests have suggested that these objectives may be compromised if the shaking includes large vertical acceleration components that are damaging to the nonstructural components and contents. Some research has been conducted to develop three dimensional isolation systems that can isolate the structure from both the horizontal and vertical components of ground motion. In several cases, systems have been proposed without much justification of the target design parameters. Rocking has been noted as a potential concern for structures with 3D isolation systems, and complex systems have been proposed to control the rocking. In this study, the fundamental dynamic response of structures with 3D isolation systems is explored. Target horizontal and vertical spectra for a representative strong motion site were developed based on NEHRP recommendations, and horizontal and vertical ground motions were selected that best fit the target spectra when the same amplitude scale factor was applied to all three motion components. Using a simple model of a rigid block resting on linear isolation bearings, the following aspects are evaluated for a wide range of horizontal and vertical isolation periods: response modes and severity of rocking, horizontal and vertical displacement demands in the isolation bearings, and attenuation of both horizontal and vertical accelerations in the structure relative to the ground acceleration. Preliminary results point to a number of useful observations. For example, rocking appears to be an issue only if the horizontal and vertical isolation periods are closely spaced. Helical spring isolation systems that have been applied to a few structures have this characteristic. However, if the horizontal isolation period is large relative to the vertical isolation period, troublesome rocking can be avoided. In addition, other researchers have proposed systems with vertical isolation periods on the order of 2 seconds, which require large displacement and damping capacity. However, preliminary results suggest that vertical isolation periods as low as 0.5 seconds will be effective in attenuating the vertical acceleration. Limiting the vertical isolation period will make design of a 3D isolation system more feasible with respect to vertical displacement capacity and avoiding rocking. 

   more » « less