First International Workshop on Negative Results in Pervasive Computing
Co-located with IEEE PerCom 2022
Not all research leads to fruitful results, trying new ways or methods may surpass the state of the art, but sometimes the hypothesis is not proven or the improvement is insignificant. But failure to succeed is not failure to progress and this workshop aims to create a platform for sharing insights, experiences, and lessons learned when conducting research in the area of pervasive computing.
While the direct outcome of negative results might not contribute much to the field, the wisdom of hindsight could be a contribution itself, such that other researchers could avoid falling into similar pitfalls. We consider negative results to be studies that are run correctly (in the light of the current state of the art) and in good practice, but fail in terms of proving of the hypothesis or come up with no significance. The “badness” of the work can also come out as a properly but unfittingly designed data collection, or (non-trivial) lapses of hindsight especially in measurement studies.
The papers of this workshop should highlight lessons learned from the negative results. The main outcome of the workshop is to share experiences so that others avoid the pitfalls that the community generally overlooks in the final accepted publications. All areas of pervasive computing, networking and systems research are considered. While we take a very broad view of “negative results”, submissions based on opinions and non-fundamental circumstances (e.g. coding errors and “bugs”) are not in scope of the workshop as they do not indicate if the approach (or hypothesis) was bad.
The main topics of interests include (but are not limited to):
We also welcome submissions from experienced researchers that recounts post-mortem of experiments or research directions they have failed in the past (e.g. in a story-based format). With this workshop, our aim is to normalize the negative outcomes and inherent failures while conducting research in pervasive computing, systems and networking, and provide a complementary view to all the success stories in these fields.
Paper submission: November 14, 2021 November 28, 2021
Author notification: January 5, 2022
Camera-ready due: February 5, 2022
Workshop date: March 25, 2022
Regular papers should present novel perspectives within the scope of the workshop: negative results, lessons learned, and other fruitful “failure” stories. Papers must be in PDF format and contain 6 pages maximum (including references), but also shorter submissions are welcome. Papers should contain names and affiliations of the authors (not blinded). All papers must be typeset in double-column IEEE format using 10pt fonts on US letter paper, with all fonts embedded. Submissions must be made via EDAS. The IEEE LaTeX and Microsoft Word templates, as well as related information, can be found at the IEEE Computer Society website.
PerFail will be held in conjunction with IEEE Percom 2022. All accepted papers will be included in the Percom workshops proceedings and included and indexed in the IEEE digital library Xplore. At least one author will be required to have a full registration in the Percom 2022 conference and present the paper during the workshop (either remotely or in location). There will be no workshop-only registration.
Submission link: here
Each accepted workshop paper requires a full PerCom registration (no registration is available for workshops only). Otherwise, the paper will be withdrawn from publication. The authors of all accepted papers must guarantee that their paper will be presented at the workshop. Papers not presented at the workshop will be considered as a "no-show" and it will not be included in the proceedings.
Registration link: here
Jussi Kangasharju received his MSc from Helsinki University of Technology in 1998. He received his Diplome d’Etudes Approfondies (DEA) from the Ecole Superieure des Sciences Informatiques (ESSI) in Sophia Antipolis in 1998. In 2002 he received his PhD from University of Nice Sophia Antipolis/Institut Eurecom. In 2002 he joined Darmstadt University of Technology (TUD), first as post-doctoral researcher, and from 2004 onwards as assistant professor. Since June 2007 Jussi is a professor at the department of computer science at University of Helsinki and is currently the head of the department. Between 2009 and 2012 he was the director of the Future Internet research program at Helsinki Institute for Information Technology (HIIT). Jussi’s research interests are information-centric networks, edge and cloud computing, content distribution, opportunistic networks, and green ICT. He is a member of IEEE and ACM.
|
Insights on Mini-Batch Alignment for WiFi-CSI Data Domain Factor Independent
Feature Extraction
Authors: Bram van Berlo, Tanir Ozcelebi, Nirvana Meratnia
Read Abstract
Unobtrusive sensing has the ambition to embed sensing into our daily
lives. A way to achieve it is through repurposing technology that we
are already used to having in our environments. Wireless Fidelity
(WiFi) sensing which makes use of Channel State Information (CSI)
measurement data seems to be a perfect fit for this, since WiFi
networks are already omnipresent. A big challenge is that CSI data
is very sensitive to 'domain factors' such as position and
orientation, making its interpretation in different domains very
difficult. We present a domain factor independent feature extraction
pipeline called 'mini-batch alignment'. Its goal is to develop
models with domain factor independent latent representations.
Unfortunately, based on extensive evaluations on a benchmark
dataset, the proposed mini-batch alignment pipeline did not lead to
better inference performance. We discuss the pitfalls that may have
led to this result, as well as future research directions.
|
|
Enabling On-Device Smartphone GPU based Training: Lessons Learned
Authors:
Anish Das, Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
Read Abstract
Deep Learning (DL) has shown impressive performance in many mobile
applications. Most existing works have focused on reducing the
computational and resource overheads of running Deep Neural Networks
(DNN) inference on resource-constrained mobile devices. However, the
other aspect of DNN operations, i.e. training (forward and backward
passes) on smartphone GPUs, has received little attention thus far.
To this end, we conduct an initial analysis to examine the
feasibility of on-device training on smartphones using mobile GPUs.
We first employ the open-source mobile DL framework (MNN) and its
OpenCL backend for running compute kernels on GPUs. Next, we
observed that training on CPUs is much faster than on GPUs and
identified two possible bottlenecks related to this observation: (i)
computation and (ii) memory bottlenecks. To solve the computation
bottleneck, we optimize the OpenCL backend's kernels, showing 2x
improvements (40-70 GFLOPs) over CPUs (15-30 GFLOPs) on the
Snapdragon 8 series processors. However, we find that the full DNN
training is still much slower on GPUs than on CPUs, indicating that
memory bottleneck plays a significant role in the lower performance
of GPU over CPU. The data movement takes almost 91% of training time
due to the low bandwidth. Lastly, based on the findings and failures
during our investigation, we present limitations and practical
guidelines for future directions.
|
Jon Crowcroft has been the Marconi Professor of Communications Systems in the Computer Laboratory since October 2001. He has worked in the area of Internet support for multimedia communications for over 30 years. Three main topics of interest have been scalable multicast routing, practical approaches to traffic management, and the design of deployable end-to-end protocols. Current active research areas are Opportunistic Communications, Social Networks, Privacy Preserving Analytics, and techniques and algorithms to scale infrastructure-free mobile systems. He leans towards a "build and learn" paradigm for research. From 2016-2018, he was Programm Chair at the Turing, the UK's national Data Science and AI Institute, and is now researcher-at-large there. He graduated in Physics from Trinity College, University of Cambridge in 1979, gained an MSc in Computing in 1981 and PhD in 1993, both from UCL. He is a Fellow the Royal Society, a Fellow of the ACM, a Fellow of the British Computer Society, a Fellow of the IET and the Royal Academy of Engineering and a Fellow of the IEEE.
Victor Bahl is a Technical Fellow and Chief Technology Officer of Azure for Operators at Microsoft Research. He is known for his research contributions to edge computing, white space radio data networks, wireless network virtualization, and for bringing wireless links into the datacenter. He is also known for his leadership of the mobile computing community as the co-founder of the ACM Special Interest Group on Mobility of Systems, Users, Data, and Computing (SIGMOBILE). He is the founder of international conference on Mobile Systems, Applications, and Services Conference (MobiSys), and the founder of ACM Mobile Computing and Communications Review. Bahl has received important awards; delivered dozens of keynotes and plenary talks at conferences and workshops; delivered over six dozen distinguished seminars at universities; written over hundred papers with more than 25,000 citations and awarded over 100 US and international patents. He is a Fellow of the Association for Computing Machinery, IEEE, and American Association for the Advancement of Science.
Daniela Nicklas is full professor at the University of Bamberg, Germany since 2014 and holds the Chair of Computer Science, in particular Mobile Software Systems / Mobility. Before that, she was a junior professor for database and internet technologies at the Universität Oldenburg and member of the Member of Executive Board in the Transportation division at the OFFIS institute for computer science. Her research interests are computer systems that bridge the gap between the physical world and the digital world. She focuses on the continuous management of data from sensors and other active data sources and their incorporation in so-called context-aware applications. In 2009, she received the IBM Exploratory Stream Analytics Innovation Award for „Data Stream Technology for Future Energy Grid Control“. Together with Prof. Dr. Marc Redepenning, she manages the Smart City Research Lab. She is a member of many programme committees and organizing committees of pervasive computing and database conferences and workshops and a member of the editorial board of the Datenbankspektrum (German Journal on Databases).
Keith Winstein is an assistant professor of computer science and, by courtesy, of electrical engineering at Stanford University. His research group creates new kinds of networked systems by rethinking abstractions around communication, compression, and computing. Some of his group’s research has found broader use, including the Mosh tool, the Puffer video-streaming site, the Lepton compression tool, the Mahimahi network emulators, and the gg lambda-computing framework. He has received the SIGCOMM Rising Star Award, the Sloan Research Fellowship, the NSF CAREER Award, the Usenix NSDI Community Award (2020, 2017), the Usenix ATC Best Paper Award, a Google Faculty Research Award (2017, 2015), a Facebook Faculty Award, the Applied Networking Research Prize, the SIGCOMM Doctoral Dissertation Award, and a Sprowls award for best doctoral thesis in computer science at MIT. Winstein previously served as a staff reporter at The Wall Street Journal and worked at Ksplice, a startup company (now part of Oracle) where he was the vice president of product management and business development and also cleaned the bathroom. He did his undergraduate and graduate work at MIT.
Suzan Bayhan is an assistant professor at the University of Twente (UT) in the Netherlands. Before joining the UT, she worked as a researcher at TU Berlin, University of Helsinki, and Bogazici University. She co-received the best paper award at ACM ICN 2015 and IEEE WoWMoM 2020 as well as the best demo award at IEEE INFOCOM 2020. She acted as a mentoring co-chair in N2Women board. Her current research interests include coexistence in unlicensed spectrum, edge computing, and energy efficient communications.
|
Lessons Learned from an Eye Tracking Study for Targeted Advertising in the
Wild Extraction
Authors: Melanie Heck, Janick Edinger, Christian Becker
Read Abstract
With the ambitious objective in mind to assess the validity of
gaze-based interest prediction and test its application for targeted
advertising on a self-order terminal, we set out to conduct a user
study at a fast food restaurant. We recorded the customers' eye
movements while they were placing their order, and used the
collected data to infer which information about the meals they were
interested in. We then wanted to test whether the predictions can be
used to display targeted advertisements, and influence the
customers' purchase intention for a complementary product. The
results did not corroborate the hypothesized relationship between
visual attention and interest. However, due to the multiplicity of
underlying assumptions, we were unable to identify whether a link
does indeed not exist, or whether the result was caused by the
experimental setup. In this paper, we describe the design and
results of our user study, and discuss our lessons learned. Our
observations shall guide other researchers to avoid these common
pitfalls.
|
|
Hindsight is 20/20: Retrospective Lessons for Conducting Longitudinal
Wearable Sensing Studies
Authors: Salaar Liaqat, Daniyal Liaqat, Tatiana Son, Andrea Gershon, Moshe Gabel, Robert Wu, Eyal de Lara
Read Abstract
Pervasive sensing using wearables for health monitoring presents a
promising and unique opportunity to widely manage illnesses and
conditions. To better understand the capabilities and limitations of
using wearable devices for health monitoring, systems need to be
developed and studies conducted. We conducted one such study for
monitoring patients with Chronic Obstructive Pulmonary Disease
(COPD), in which we aim to understand the disease and predict
patient outcomes. However, despite a carefully well-planned and
well-conducted study that resulted in a very large dataset, some
non-obvious design oversights meant the data was much less useful.
We analyze the shortcomings of our study to construct lessons and
concrete actions to avoid these pitfalls. We ratify these lessons by
briefly discussing a second iteration of our study, in which we
apply these lessons and obtain much better outcomes. Real-world
sensing studies are time consuming and expensive investments, for a
promising research area. By sharing our failure and proposing
actionable lessons, we hope to minimize the risk for others aiming
to run such studies.
|
