This paper describes our approach to create a neural machine translation system to translate between English and Swahili (both directions) in the news domain, as well as the process we followed to crawl the necessary parallel corpora from the Internet. We report the results of a pilot human evaluation performed by the news media organisations participating in the H2020 EU-funded project GoURMET.

Fact checking is an essential task in journalism; its importance has been highlighted due to recently increased concerns and efforts in combating misinformation. In this paper, we present an automated fact checking platform which given a claim, it retrieves relevant textual evidence from a document collection, predicts whether each piece of evidence supports or refutes the claim, and returns a final verdict. We describe the architecture of the system and the user interface, focusing on the choices made to improve its user friendliness and transparency. We conduct a user study of the fact-checking platform in a journalistic setting: we integrated it with a collection of news articles and provide an evaluation of the platform using feedback from journalists in their workflow. We found that the predictions of our platform were correct 58% of the time, and 59% of the returned evidence was relevant.

P2P sharing amongst consumers has been proposed as a way to decrease load on Content Delivery Networks. This paper develops an analytical model that shows an additional benefit of sharing content locally: Selecting close by peers to share content from leads to shorter paths compared to traditional CDNs, decreasing the overall carbon footprint of the system. Using data from a month-long trace of over 3 million monthly users in London accessing TV shows online, we show that local sharing can result in a decrease of 24-48% in the system-wide carbon footprint of online video streaming, despite various obstacle factors that can restrict swarm sizes. We confirm the robustness of the savings by using realistic energy parameters drawn from two widely used settings. We also show that if the energy savings of the CDN servers are transferred as carbon credits to the end users, over 70% of users can become carbon positive, i.e., are able to support their content consumption without incurring any carbon footprint, and are able to offset their other carbon consumption. We suggest carbon credit transfers from CDNs to end users as a novel way to incentivise participation in peer-assisted content delivery.

Mobile data offloading can greatly decrease the load on and usage of current and future cellular data networks by exploiting opportunistic and frequent access to Wi-Fi connectivity. Unfortunately, Wi-Fi access from mobile devices can be difficult during typical work commutes, e.g., via trains or cars on highways. In this paper, we propose a new approach: to preload the mobile device with content that a user might be interested in, thereby avoiding the need for cellular data access. We demonstrate the feasibility of this approach by developing a supervised machine learning model that learns from user preferences for different types of content, and propensity to be guided by the user interface of the player, and predictively preload entire TV shows. Testing on a data set of nearly 3.9 million sessions from all over the U.K. to BBC TV shows, we find that predictive preloading can save over 71% of the mobile data for an average user.

In search of scalable solutions, CDNs are exploring P2P support. However, the benefits of peer assistance can be limited by various obstacle factors such as ISP friendliness - requiring peers to be within the same ISP, bitrate stratification - the need to match peers with others needing similar bitrate, and partial participation - some peers choosing not to redistribute content. This work relates potential gains from peer assistance to the average number of users in a swarm, its capacity, and empirically studies the effects of these obstacle factors at scale, using a month-long trace of over 2 million users in London accessing BBC shows online. Results indicate that even when P2P swarms are localised within ISPs, up to 88% of traffic can be saved. Surprisingly, bitrate stratification results in 2 large sub-swarms and does not significantly affect savings. However, partial participation, and the need for a minimum swarm size do affect gains. We investigate improvements to gain from increasing content availability through two well-studied techniques: content bundling-combining multiple items to increase availability, and historical caching of previously watched items. Bundling proves ineffective as increased server traffic from larger bundles outweighs benefits of availability, but simple caching can considerably boost traffic gains from peer assistance.

Using nine months of access logs comprising 1.9 Billion sessions to BBC iPlayer, we survey the UK ISP ecosystem to understand the factors affecting adoption and usage of a high bandwidth TV streaming application across different providers. We find evidence that connection speeds are important and that external events can have a huge impact for live TV usage. Then, through a temporal analysis of the access logs, we demonstrate that data usage caps imposed by mobile ISPs significantly affect usage patterns, and look for solutions. We show that product bundle discounts with a related fixed-line ISP, a strategy already employed by some mobile providers, can better support user needs and capture a bigger share of accesses. We observe that users regularly split their sessions between mobile and fixed-line connections, suggesting a straightforward strategy for offloading by speculatively pre-fetching content from a fixed-line ISP before access on mobile devices.

MOTIVATION: There is much interest in reducing the complexity inherent in the representation of the 20 standard amino acids within bioinformatics algorithms by developing a so-called reduced alphabet. Although there is no universally applicable residue grouping, there are numerous physiochemical criteria upon which one can base groupings. Local descriptors are a form of alignment-free analysis, the efficiency of which is dependent upon the correct selection of amino acid groupings. RESULTS: Within the context of G-protein coupled receptor (GPCR) classification, an optimization algorithm was developed, which was able to identify the most efficient grouping when used to generate local descriptors. The algorithm was inspired by the relatively new computational intelligence paradigm of artificial immune systems. A number of amino acid groupings produced by this algorithm were evaluated with respect to their ability to generate local descriptors capable of providing an accurate classification algorithm for GPCRs.

AIRS (Artificial Immune Recognition System) has shown itself to be a competitive classifier. It has also proved to be the most popular immune inspired classifier. However, rather than AIRS being a classifier in its own right as previously described, we see AIRS more as a pre-processor to a KNN classifier. It is our view that by not explicitly classing it as such development of this algorithm has been rather held back. Seeing it as a pre-processor allows inspiration to be taken from the machine learning literature where such pre-processors are not uncommon. With this in mind, this paper takes a core feature of many such pre-processors, that of attribute weighting, and applies it to AIRS. The resultant algorithm called WAIRS (Weighted AIRS) uses a weighted distance function during all affinity evaluations. WAIRS is tested on 9 benchmark datasets and is found to outperform AIRS in the majority of cases.

MOTIVATION: G protein-coupled receptors (GPCRs) play an important role in many physiological systems by transducing an extracellular signal into an intracellular response. Over 50% of all marketed drugs are targeted towards a GPCR. There is considerable interest in developing an algorithm that could effectively predict the function of a GPCR from its primary sequence. Such an algorithm is useful not only in identifying novel GPCR sequences but in characterizing the interrelationships between known GPCRs. RESULTS: An alignment-free approach to GPCR classification has been developed using techniques drawn from data mining and proteochemometrics. A dataset of over 8000 sequences was constructed to train the algorithm. This represents one of the largest GPCR datasets currently available. A predictive algorithm was developed based upon the simplest reasonable numerical representation of the protein's physicochemical properties. A selective top-down approach was developed, which used a hierarchical classifier to assign sequences to subdivisions within the GPCR hierarchy. The predictive performance of the algorithm was assessed against several standard data mining classifiers and further validated against Support Vector Machine-based GPCR prediction servers. The selective top-down approach achieves significantly higher accuracy than standard data mining methods in almost all cases.

With the increase in information on the Internet, the strive to find more effective tools for distinguishing between interesting and non-interesting material is increasing. Drawing analogies from the biological immune system, this paper presents an immune-inspired algorithm called AISEC that is capable of continuously classifying electronic mail as interesting and non-interesting without the need for re-training. Comparisons are drawn with a naive Bayesian classifier and it is shown that the proposed system performs as well as the naive Bayesian system and has a great potential for augmentation.

For a scalable video coder to remain efficient over a wide range of bit-rates, some form of scalability must exist in the motion information. We propose a wavelet-based highly scalable video coder with scalable motion coding. Our proposed method involves the construction of quality layers for the coded wavelet sample data and a separate set of quality layers for scalably coded motion parameters. When the motion layers are truncated, the decoder receives a quantized version of the motion parameters used to generate the wavelet sample data. A linear model is used to infer the impact of motion quantization on reconstructed video distortion. An optimal tradeoff between the motion and subband bit-rates may then be found. Experimental results indicate that the cost of scalability is small. At low bit-rates, significant improvements are observed relative to lossless coding of the motion information.

An important problem in medical imaging is that of efficient volumetric image compression. In addition to compression efficiency, scalable representations which allow access to the data at various qualities up to and including lossless reproduction are particularly important. Also important is the ability to access local regions of the volumetric data set or to alter the fidelity or resolution with which a selected region is accessed. In this paper, we first consider bounds to the efficacy of three dimensional transform techniques. We then propose a particular technique, based on motion adaptive wavelet lifting, which is able to realize the goals of high compression efficiency, lossy to lossless scalability, and efficient random access, all within a single compressed data stream.