The ORCHID Project Developing the science of Human-Agent Collectives Fri, 16 Mar 2018 11:20:49 +0000 en-US hourly 1 Office 365 Migration question for you Fri, 16 Mar 2018 11:17:47 +0000 Folks, As you know, this migration is about to happen. You will almost certainly already have an iSolutions Exchange account, which is being moved to Office 365. *Do you already have some email stored in your iSolutions mailbox???* You can check this at *This is the problem:* For example, say there are already messages in your iSolutions Inbox, and we copy your IMAP Inbox messages straight into your iSolutions Inbox, you may wind up in a real mess as you won’t know which came from where. Likewise for any other mail folders you currently have in your iSolutions mailbox. (This is a particular issue for those of you who keep copies of your incoming mail in both accounts!) There are *2 options* at this point: 1. This is what will happen by default. It is the safe option. *We will create a folder* in your iSolutions mailbox called “*ECS IMAP mail*” and *copy your tree of IMAP mail folders into there***(maintaining the complete tree structure of your folders, don’t worry!). For example, an IMAP folder called “projects/important” would end up in the iSolutions/Office365 folder “ECS IMAP mail/projects/important”. 2. You empty out your iSolutions mailbox *now*, and *you tell us* that you want your *IMAP mail moved straight across*. In this case, an IMAP folder called “projects/important” would end up in the iSolutions/Office365 folder “projects/important”. ** If you want option 2, sort out any mail in your iSolutions mailbox right now, which can be easily done at and tell us you want to be moved *straight across*. Warning: If you tell us to do opton 2, but do *not* sort out your iSolutions mailbox first, you will end up in a total mess of merged/duplicate email that we will not be able to undo for you. At which point it’s your problem. :) If we don’t hear from you, we will do option 1 for you. This is the safe option. You will then need to move folders around to organise them how you want them. Thanks! Jules

]]> 0
Office 365 Email Migration Update Thu, 15 Mar 2018 09:32:20 +0000 You are receiving this email as you were identified as an ECS staff member currently using an IMAP email account. *What’s happening and why?* The current ECS IMAP email service has limited storage capacity and is reaching end of life.  The Faculty is working with iSolutions to migrate your email to Office 365 to address these issues. Some IMAP email users have both an Exchange email account and an IMAP email account.  To simplify, the faculty has decided to merge the two accounts together into one mailbox.  This unified mailbox is capable of hosting multiple aliases (for example both & allowing users to use their preferred email address. *What is the timeline for the Office 365 email migration for IMAP accounts?* *Monday, March 19th* iSolutions Soton Exchange accounts are migrated to Office 365 first.  This will require you to restart Outlook so it automatically configures itself with the new settings. This move will take up to 5 days. ECS IMAP accounts will work as normal while this occurs. *Monday, March 26th* From this date all new incoming email will be delivered to Office 365, and you will need to configure both the new and old accounts on your email client and/or devices.  Instructions on how to do this will be provided in a following email. We will start copying emails across to your new account. Based on test migrations we estimate this process will be finished by Wednesday 28th March. Once you can verify that all your mail is present on Office365, you can then remove your original ECS IMAP account from your email client. *** Important note*** During the migration from Exchange to Office 365, your mailbox will be available for most of the time. There will be a short period (usually a few minutes) towards the end of the move where it does the final sync where neither the Exchange mailbox nor Office 365 mailbox will be available. Any new mail arriving in that period will be queued and delivered as soon as your mailbox is available again. *What’s next?* While we are planning and carrying out the move, you will receive updates with information about the new service and how you will be supported during the move. If you have any questions or concerns please email Thanks! Jules

]]> 0
ECS IMAP email migration Mon, 05 Mar 2018 16:54:26 +0000 You are receiving this email as you were identified as an ECS member currently using an IMAP email account. *What’s happening and why?* The current ECS IMAP email service has limited storage capacity and is reaching end of life.  In consultation with the Faculty, we will be migrating your email to Office 365, which is used by our students. *What else do I need to know?* Your new email service will also come with an increase in mail storage to 50 GB and the ability to use your existing mail client or devices. *When is the mailbox migration happening?* The planned window for this move is the week commencing 19th March. *What’s next?* While we are planning and testing the move, you will receive weekly updates with information about the new service and how you will be supported during the move. If you have any questions or concerns please email or simply reply to this email. Jules

]]> 0
ACM e-Energy 2015 Thu, 03 Sep 2015 16:11:10 +0000 During July of this year, the sixth ACM International Conference on Future Energy Systems (ACM e-Energy) took place in Bangalore, India. The conference aims to be the premier venue for research taking place in the area of computing and communication for smart energy systems. The conference played host to a number of keynote speakers alongside a single track of full and challenge papers and was co-located with three smart grid themed workshops. The keynotes included Professor Iven Mareels from the University of Melbourne, discussing his work on coordinating supply and demand on the low-voltage distribution network; Professor Ashok Junjhunwala from IIT Madras presenting his solution to India’s blackout problems by including a low-voltage DC line that becomes active during grid outages; and Professor Bruce Nordman from the Lawrence Berkeley National Laboratory making the case against ever increasing reliability power quality and reliability (PQR) in favour of localised reliability. The Best Paper Award was awarded jointly to Paul Scott and Sylvie Thiébaux from Australia National University for their work on the coordination of independent agents within microgrids and a team from Tata Consultancy Services and Pennsylvania State University for their work on fault detection in supermarket refrigeration systems. The best poster award was awarded to Rabbani and Keshav from the University of Waterloo for their work on ‘The SPOT* System’, which is a personal thermal comfort system for use in offices. Full proceedings (including keynote and poster abstracts and papers from the three co-located workshops are available at Next year, ACM e-Energy will be hosted by the University of Waterloo in Canada, and will be chaired by Professor Srinivasan Keshav

]]> 0
NILM 2015 Workshop Summary Tue, 28 Jul 2015 10:44:41 +0000 During July 2015, Imperial College London played host to nearly 70 attendees from all over the world for the European Non-Intrusive Load Monitoring (NILM) workshop, bringing together energy disaggregation researchers and professionals for this 2-day event.


The purpose of the workshop was to provide a forum for energy disaggregation enthusiasts to learn about recent developments in the field, as well as network and discuss projects for future collaboration. The workshop was attended by academics, employees of energy disaggregation companies, multinational utility companies and a few hobbyists.


Prof Mario Bergés, Assistant Professor at Carnegie Mellon University gave the keynote speech which focussed on the relevance of NILM within the emerging domain of the Internet of Things (IoT). Mario covered recent trends in energy disaggregation, as well as his projection of the field’s relevance into the future. His talk also proposed four ‘million dollar’ ideas which he believes will have significant impact on the domain of energy disaggregation. You can watch Mario’s full talk on YouTube.


Workshop attendees also enjoyed talks from both academic and industry aspects, with speakers including Mingjun Zhong from the University of Edinburgh and Stephen Makonin from Simon Fraser University representing academic findings, and focussed on models for energy disaggregation, socioeconomic concerns and accuracy evaluation. From an industry perspective the workshop welcomed Bruno Charbonnier from EDF R&D, and Hjalmar Nilsonne from Watty who cemented the importance and benefits of disaggregating electricity and announced the release of a new dataset.


Delegates were invited to bring a poster to present at a dedicated ‘lightning talk’ session, giving each presenter a chance to disseminate and discuss a NILM related topic of their choice for 1 minute. During the lunch and break sessions, posters were displayed on the walls, giving the presenter an opportunity to engage in one-to-one discussions with other attendees. The posters are available via a dropbox folder, while the lightning talk session is also available on YouTube.
An MSc group from Imperial College London presented a tool for evaluating NILM algorithms without requiring the NILM algorithm’s code to be released. There was a real buzz of excitement around such an initiative, and a number of improvements were suggested around the need for a real-world private data set.


As the NILM Workshop came to a close, an agenda was decided for topics to discuss the following morning at an informal user group designed to encourage collaboration and potential projects among attendees, which included funding applications and data sharing. The afternoon session explored NILMTK; an open source toolkit for non-intrusive load monitoring and included an overview of the toolkit as well as discussions on how to encourage contributions from the community. The need for a collaborative knowledge base, where items such as public data sets can be described in an easily comparable and searchable format was also discussed, with the result being a web based wiki which will be available on the website soon.


The most obvious learning from the workshop was the increasing momentum in this domain. The 2014 European Workshop was attended by around 20 people while this year saw nearly 70 attendees from around the globe. In addition, the diversity of the problems being studied by each of the attendees was also clear from the poster session, as each start up or academic project has a subtle but significantly different take on the problem of energy disaggregation. Lastly, the problem of evaluation accuracy cropped up regularly throughout the workshop. The need for standard data sets, metrics and methodologies is now more important than ever.


The workshop was streamed live on YouTube, and videos of all talks can be seen via our YouTube playlist, while each presenter’s slides can be downloaded from our dropbox folder.


The two day workshop finished with a discussion of plans for the 2016 European workshop. While the location of the workshop is yet to be decided, it was clear that there was sufficient demand for a future meeting.

]]> 0
Crowdsourcing Smartphone GPS Could Improve Earthquake Warnings Thu, 16 Apr 2015 07:09:12 +0000 Interesting article on the IEEE Spectrum about earthquake warnings with smartphones:

]]> 0
Language Understanding in the Wild: Combining Crowdsourcing and Machine Learning – WWW 2015 Mon, 30 Mar 2015 10:07:13 +0000 How do we build an automated tool for tweet sentiment analysis that learns from crowdsourced human annotations? This is the challenge addressed by the Bayesian Classifier Combination with Words (BCCWords) model presented in the paper to appear in WWW 2015:


Simpson, Edwin, Venanzi, Matteo, Reece, Steven, Kohli, Pushmeet, Guiver, John, Roberts, Stephen and Jennings, Nicholas R. (2015) Language Understanding in the Wild: Combining Crowdsourcing and Machine Learning. In, 24th International World Wide Web Conference (WWW 2015)


This problem involves classifying the sentiment of a large corpus, i.e., hundreds of thousands, of tweets using only a small set of crowdsourced sentiment labels provided by human annotators. In particular, this problem is relevant to various text mining tasks such as weather sentiment classification from twitter [1] and disaster response applications, e.g., the Ushahidi-Haiti project where 40,000 emergency reports were received in the first week from victims of the 2010 Haiti earthquake [2].


To build such a system that classifies tweets based on crowdsourced judgments, we must deal with three key challenges. Firstly, each annotator may have different reliabilities of labelling tweets correctly depending on the content of the tweet. In fact, interpreting sentiment or relevance of a piece of text is highly subjective and, along with variations in annotators’ skill levels, it can result in disagreement amongst the annotators. Secondly, typically there are so many tweets that a small number of dedicated expert labellers will be overwhelmed as was the case during the Haiti earthquake. As a result, the human labels may or may not cover the whole set of tweets, so we may have tweets with only one label or multiple, perhaps conflicting, labels, or none. Thirdly, each distinct term of the dictionary has different probabilities to appear in tweets of different sentiment classes. For example, the terms “Good” and “Nice” are more likely to be used for tweets with a positive sentiment. Thus, we must be able to provide reliable classifications of each tweet by leveraging the language model inferred from the aggregated crowdsourced labels to classify the entire corpus (i.e., tweet set).


To solve this problem, BCCWords builds upon the core structure the Bayesian Classifier Combination model (BCC) to add a new feature relating to modelling human language in addition to aggregating crowdsourced labels. In detail, BCC can learn the reliability of each annotator through a confusion matrix expressing the labelling probabilities for each possible sentiment class. Here are examples of confusion matrices for two annotators rating tweets in five sentiment classes [neutral, positive, not related, unknown] from the CrowdFlower (CF) dataset described in the paper:




Thus, by combining the aggregation mechanism of BCC with language model, we are able to simultaneously inferring the confusion matrix of each worker, the true label of each tweet and the word probabilities of each sentiment class.


We have applied BCCWords to the CF dataset containing up to five weather sentiment annotations for tens of thousands of tweets annotated by thousands of workers. The model correctly found the correlation between positive, negative, neutral words in the related sentiment class. We can see this in the word clouds below. These show the most probable words in each class with word size proportional to the estimated probability of the word conditioned on the true label:


*The black boxes hide some swear words that were inferred by BCCWords within the feature set for the tweets with negative sentiment.

We can also identify the most discriminative words in each class by applying a standard normalisation of the estimated word probabilities (details in the paper):


These word clouds clearly show that the words such are “beautiful” and “perfect” are more discriminative for positive tweets, while the words “stayinghometweet” and “dammit” are more likely to occur in negative tweets. We also found that some words like “complain”, “snowstorm” and “warm” do not necessarily imply a particular positive or negative sentiment as their interpretation is highly context dependent and therefore most of the annotators classified the relative tweets as “unknown”. You can find out more about the classification accuracy of BCCWords and its ability to exploit the language model to predict labels for the entire set of tweets in the paper.


More trials of this technology is in progress. We are currently working with RescueGlobal (A UK-NGO specialised in professional disaster response) and the ORCHID project to use the developed model to analyse live streams of emergency tweets received during recent environmental disasters in the Philippines.


[1] See


[2] See


]]> 0
The limits of human performance and artificial intelligence Thu, 26 Mar 2015 10:42:31 +0000 Last month in Oxford, Garry Kasparov spoke on ‘The limits of human performance and artificial intelligence’. A few Orchid researchers attended the talk and found it thought-provoking. The video is available to view here or on YouTube.

At one point Garry mentioned humans and computers playing together, rather than in opposition. One human plus one computer interact to devise the next move, and on the other side of the chessboard sits another human/computer pair. This setup, which made some of us think of HACs, enhances rather then detracts from player creativity and has led to innovations in game strategy.

]]> 0
Gamification online course Wed, 18 Feb 2015 18:38:31 +0000

The second edition of the Gamification course taught by Prof. Kevin Werback (University of Pennsylvania) is live on Coursera. The course was very successful in his first edition (2012). It is currently half way through its programme but all the videos and assignments are available online and the lectures organise regular hangout meetings with the students. I find it quite engaging and fun to attend and presents a lot of interesting material.


]]> 0
CHI video preview: Building a Birds Eye View Tue, 10 Feb 2015 13:19:48 +0000
Here is the CHI ‘video preview’ that will be published alongside the paper in the ACM Digital Library.

      This message and any attachment are intended solely for the addressee  and may contain confidential information. If you have received this  message in error, please send it back to me, and immediately delete it.     Please do not use, copy or disclose the information contained in this  message or in any attachment.  Any views or opinions expressed by the  author of this email do not necessarily reflect the views of the  University of Nottingham.    This message has been checked for viruses but the contents of an  attachment may still contain software viruses which could damage your  computer system, you are advised to perform your own checks. Email  communications with the University of Nottingham may be monitored as  permitted by UK legislation.  
]]> 0