Speaker attribution of Australian broadcast news data

Speaker attribution is the task of annotating a spoken audio archive based on speaker identities. This can be achieved using speaker diarization and speaker linking. In our previous work, we proposed an efficient attribution system, using complete-linkage clustering, for conducting attribution of large sets of two-speaker telephone data. In this paper, we build on our proposed approach to achieve a robust system, applicable to multiple recording domains. To do this, we first extend the diarization module of our system to accommodate multi-speaker (>2) recordings. We achieve this through using a robust cross-likelihood ratio (CLR) threshold stopping criterion for clustering, as opposed to the original stopping criterion of two speakers used for telephone data. We evaluate this baseline diarization module across a dataset of Australian broadcast news recordings, showing a significant lack of diarization accuracy without previous knowledge of the true number of speakers within a recording. We thus propose applying an additional pass of complete-linkage clustering to the diarization module, demonstrating an absolute improvement of 20% in diarization error rate (DER). We then evaluate our proposed multi-domain attribution system across the broadcast news data, demonstrating achievable attribution error rates (AER) as low as 17%.

Cyclin A/CDK2 regulates multiple G2 phase pathways

The cell cycle is a carefully choreographed series of phases that when executed successfully will allow the complete replication of the genome and the equal division of the genome and other cellular content into two independent daughter cells. The inability of the cell to execute cell division successfully can result in either checkpoint activation to allow repair and/or apoptosis and/or mutations/errors that may or may not lead to tumourgenesis. Cyclin A/CDK2 is the primary cyclin/CDK regulating G2 phase progression of the cell cycle. Cyclin A/CDK2 activity peaks in G2 phase and its inhibition causes a G2 phase delay that we have termed 'the cyclin A/CDK2 dependent G2 delay'. Understanding the key pathways that are involved in the cyclin A/CDK2 dependent G2 delay has been the primary focus of this study. Characterising the cyclin A/CDK2 dependent G2 delay revealed accumulated levels of the inactive form of the mitotic regulator, cyclin B/CDK1. Surprisingly, there was also increased microtubule nucleation at the centrosomes, and the centrosomes stained for markers of cyclin B/CDK1 activity. Both microtubule nucleation at the centrosomes and phosphoprotein markers were lost with short-term treatment of CDK1/2 inhibition. Cyclin A/CDK2 localised at the centrosomes in late G2 phase after separation of the centrosomes but before the start of prophase. Thus G2 phase cyclin A/CDK2 controls the timing of entry into mitosis by controlling the subsequent activation of cyclin B/CDK1, but also has an unexpected role in coordinating the activation of cyclin B/CDK1 at the centrosome and in the nucleus. In addition to regulating the timing of cyclin B/CDK1 activation and entry into mitosis in the unperturbed cell cycle, cyclin A/CDK2 also was shown to have a role in G2 phase checkpoint recovery. Known G2 phase regulators were investigated to determine whether they had a role in imposing the cyclin A/ CDK2 dependent G2 delay. Examination of the critical G2 checkpoint arrest protein, Chk1, which also has a role during unperturbed G2/M phases revealed the presence of activated Chk1 in G2 phase, in a range of cell lines. Activated Chk1 levels were shown to accumulate in cyclin A/CDK2 depleted/inhibited cells. Further investigations revealed that Chk1, but not Chk2, depletion could reverse the cyclin A/CDK2 dependent G2 delay. It was confirmed that the accumulative activation of Chk1 was not a consequence of DNA damage induced by cyclin A depletion. The potential of cyclin A/CDK2 to regulate Chk1 revealed that the inhibitory phosphorylations, Ser286 and Ser301, were not directly catalysed by cyclin A/CDK2 in G2 phase to regulate mitotic entry. It appeared that the ability of cyclin A/CDK2 to regulate cyclin B/CDK1 activation impacted cyclin B/CDK1s phosphorylation of Chk1 on Ser286 and Ser301, thereby contributing to the delay in G2/M phase progression. Chk1 inhibition/depletion partially abrogated the cyclin A/CDK2 dependent G2 delay, and was less effective in abrogating G2 phase checkpoint suggesting that other cyclin A/CDK2 dependent mechanisms contributed to these roles of cyclin A/CDK2. In an attempt to identify these other contributing factors another G2/M phase regulator known to be regulated by cyclin A/CDK2, Cdh1 and its substrates Plk1 and Claspin were examined. Cdh1 levels were reduced in cyclin A/CDK2 depleted/inhibited cells although this had little effect on Plk1, a known Cdh1 substrate. However, the level of another substrate, Claspin, was increased. Cdh1 depletion mimicked the effect of cyclin A depletion but to a weaker extent and was sufficient at increasing Claspin levels similar to the increase caused by cyclin A depletion. Co-depletion of cyclin A and Claspin blocked the accumulation of activated Chk1 normally seen with cyclin A depletion alone. However Claspin depletion alone did not reduce the cyclin A/CDK2 dependent G2 delay but this is likely to be a result of inhibition of S phase roles of Claspin. Together, these data suggest that cyclin A/CDK2 regulates a number of different mechanisms that contribute to G2/M phase progression. Here it has been demonstrated that in normal G2/M progression and possibly to a lesser extent in G2 phase checkpoint recovery, cyclin A/CDK2 regulates the level of Cdh1 which in turn affects at least one of its substrates, Claspin, and consequently results in the increased level of activated Chk1 observed. However, the involvement of Cdh1 and Claspin alone does not explain the G2 phase delay observed with cyclin A/CDK2 depletion/inhibition. It is likely that other mechanisms, possibly including cyclin A/CDK2 regulation of Wee1 and FoxM1, as reported by others, combine with the mechanism described here to regulate normal G2/M phase progression and G2 phase checkpoint recovery. These findings support the critical role for cyclin A/CDK2 in regulating progression into mitosis and suggest that upstream regulators of cyclin A/CDK2 activation will also be critical controllers of this cell cycle transition. The pathways that work to co-ordinate cell cycle progression are very intricate and deciphering these pathways, required for normal cell cycle progression, is key to understanding tumour development. By understanding cell cycle regulatory pathways it will allow the identification of the pathway/s and their mechanism/s that become affected in tumourgenesis. This will lead to the development of better targeted therapies, inferring better efficacy with fewer side effects than commonly seen with the use of traditional therapies, such as chemotherapy. Furthermore, this has the potential to positively impact the development of personalised medicines and the customisation of healthcare.

Closing the case of APOE in multiple sclerosis : no association with disease risk in over 29,000 subjects

Background Single nucleotide polymorphisms (SNPs) rs429358 (ε4) and rs7412 (ε2), both invoking changes in the amino-acid sequence of the apolipoprotein E (APOE) gene, have previously been tested for association with multiple sclerosis (MS) risk. However, none of these studies was sufficiently powered to detect modest effect sizes at acceptable type-I error rates. As both SNPs are only imperfectly captured on commonly used microarray genotyping platforms, their evaluation in the context of genome-wide association studies has been hindered until recently. Methods We genotyped 12 740 subjects hitherto not studied for their APOE status, imputed raw genotype data from 8739 subjects from five independent genome wide association studies datasets using the most recent high-resolution reference panels, and extracted genotype data for 8265 subjects from previous candidate gene assessments. Results Despite sufficient power to detect associations at genome-wide significance thresholds across a range of ORs, our analyses did not support a role of rs429358 or rs7412 on MS susceptibility. This included meta-analyses of the combined data across 13 913 MS cases and 15 831 controls (OR=0.95, p=0.259, and OR 1.07, p=0.0569, for rs429358 and rs7412, respectively). Conclusion Given the large sample size of our analyses, it is unlikely that the two APOE missense SNPs studied here exert any relevant effects on MS susceptibility.

HLA-DRB1 associations with disease susceptibility and clinical course in Australians with multiple sclerosis

Human leucocyte antigen (HLA)-DRB1*1501 and other class II alleles influence susceptibility to multiple sclerosis (MS), but their contribution if any to the clinical course of MS remains uncertain. Here, we have investigated DRB1 alleles in a large sample of 1230 Australian MS cases, with some enrichment for subjects with primary progressive (PPMS) disease (n = 246) and 1210 healthy controls. Using logistic regression, we found that DRB1*1501 was strongly associated with risk (P = 7 x 10-45), as expected, and after adjusting for DRB1*1501, a predisposing effect was also observed for DRB1*03 (P = 5 x 10-7). Individuals homozygous for either DRB1*15 or DRB1*03 were considerably more at risk of MS than heterozygotes and non-carriers. Both the DRB1*04 and the DRB1*01/DRB1*15 genotype combination, respectively, protected against PPMS in comparison to subjects with relapsing disease. Together, these data provide further evidence of heterogeneity at the DRB1 locus and confirm the importance of HLA variants in the phenotypic expression of MS.

The multi-platform user engagement and data visualisation tool

The ability to identify and assess user engagement with transmedia productions is vital to the success of individual projects and the sustainability of this mode of media production as a whole. It is essential that industry players have access to tools and methodologies that offer the most complete and accurate picture of how audiences/users engage with their productions and which assets generate the most valuable returns of investment. Drawing upon research conducted with Hoodlum Entertainment, a Brisbane-based transmedia producer, this project involved an initial assessment of the way engagement tends to be understood, why standard web analytics tools are ill-suited to measuring it, how a customised tool could offer solutions, and why this question of measuring engagement is so vital to the future of transmedia as a sustainable industry. Working with data provided by Hoodlum Entertainment and Foxtel Marketing, the outcome of the study was a prototype for a custom data visualisation tool that allowed access, manipulation and presentation of user engagement data, both historic and predictive. The prototyped interfaces demonstrate how the visualization tool would collect and organise data specific to multiplatform projects by aggregating data across a number of platform reporting tools. Such a tool is designed to encompass not only platforms developed by the transmedia producer but also sites developed by fans. This visualisation tool accounted for multiplatform experience projects whose top level is comprised of people, platforms and content. People include characters, actors, audience, distributors and creators. Platforms include television, Facebook and other relevant social networks, literature, cinema and other media that might be included in the multiplatform experience. Content refers to discreet media texts employed within the platform, such as tweet, a You Tube video, a Facebook post, an email, a television episode, etc. Core content is produced by the creators’ multiplatform experiences to advance the narrative, while complimentary content generated by audience members offers further contributions to the experience. Equally important is the timing with which the components of the experience are introduced and how they interact with and impact upon each other. Being able to combine, filter and sort these elements in multiple ways we can better understand the value of certain components of a project. It also offers insights into the relationship between the timing of the release of components and user activity associated with them, which further highlights the efficacy (or, indeed, failure) of assets as catalysts for engagement. In collaboration with Hoodlum we have developed a number of design scenarios experimenting with the ways in which data can be visualised and manipulated to tell a more refined story about the value of user engagement with certain project components and activities. This experimentation will serve as the basis for future research.

First-cycle rash and survival in patients with advanced non-small-cell lung cancer receiving cetuximab in combination with first-line chemotherapy : a subgroup analysis of data from the FLEX phase 3 study

Background: The randomised phase 3 First-Line Erbitux in Lung Cancer (FLEX) study showed that the addition of cetuximab to cisplatin and vinorelbine significantly improved overall survival compared with chemotherapy alone in the first-line treatment of advanced non-small-cell lung cancer (NSCLC). The main cetuximab-related side-effect was acne-like rash. Here, we assessed the association of this acne-like rash with clinical benefit. Methods: We did a subgroup analysis of patients in the FLEX study, which enrolled patients with advanced NSCLC whose tumours expressed epidermal growth factor receptor. Our landmark analysis assessed if the development of acne-like rash in the first 21 days of treatment (first-cycle rash) was associated with clinical outcome, on the basis of patients in the intention-to-treat population alive on day 21. The FLEX study is registered with ClinicalTrials.gov, number NCT00148798. Findings: 518 patients in the chemotherapy plus cetuximab group-290 of whom had first-cycle rash-and 540 patients in the chemotherapy alone group were alive on day 21. Patients in the chemotherapy plus cetuximab group with first-cycle rash had significantly prolonged overall survival compared with patients in the same treatment group without first-cycle rash (median 15·0 months [95% CI 12·8-16·4] vs 8·8 months [7·6-11·1]; hazard ratio [HR] 0·631 [0·515-0·774]; p<0·0001). Corresponding significant associations were also noted for progression-free survival (median 5·4 months [5·2-5·7] vs 4·3 months [4·1-5·3]; HR 0·741 [0·607-0·905]; p=0·0031) and response (rate 44·8% [39·0-50·8] vs 32·0% [26·0-38·5]; odds ratio 1·703 [1·186-2·448]; p=0·0039). Overall survival for patients without first-cycle rash was similar to that of patients that received chemotherapy alone (median 8·8 months [7·6-11·1] vs 10·3 months [9·6-11·3]; HR 1·085 [0·910-1·293]; p=0·36). The significant overall survival benefit for patients with first-cycle rash versus without was seen in all histology subgroups: adenocarcinoma (median 16·9 months, [14·1-20·6] vs 9·3 months [7·7-13·2]; HR 0·614 [0·453-0·832]; p=0·0015), squamous-cell carcinoma (median 13·2 months [10·6-16·0] vs 8·1 months [6·7-12·6]; HR 0·659 [0·472-0·921]; p=0·014), and carcinomas of other histology (median 12·6 months [9·2-16·4] vs 6·9 months [5·2-11·0]; HR 0·616 [0·392-0·966]; p=0·033). Interpretation: First-cycle rash was associated with a better outcome in patients with advanced NSCLC who received cisplatin and vinorelbine plus cetuximab as a first-line treatment. First-cycle rash might be a surrogate clinical marker that could be used to tailor cetuximab treatment for advanced NSCLC to those patients who would be most likely to derive a significant benefit. Funding: Merck KGaA. © 2011 Elsevier Ltd.

Molecular biomarkers in non-small-cell lung cancer : a retrospective analysis of data from the phase 3 FLEX study

Background: Findings from the phase 3 FLEX study showed that the addition of cetuximab to cisplatin and vinorelbine significantly improved overall survival, compared with cisplatin and vinorelbine alone, in the first-line treatment of EGFR-expressing, advanced non-small-cell lung cancer (NSCLC). We investigated whether candidate biomarkers were predictive for the efficacy of chemotherapy plus cetuximab in this setting. Methods: Genomic DNA extracted from formalin-fixed paraffin-embedded (FFPE) tumour tissue of patients enrolled in the FLEX study was screened for KRAS codon 12 and 13 and EGFR kinase domain mutations with PCR-based assays. In FFPE tissue sections, EGFR copy number was assessed by dual-colour fluorescence in-situ hybridisation and PTEN expression by immunohistochemistry. Treatment outcome was investigated according to biomarker status in all available samples from patients in the intention-to-treat population. The primary endpoint in the FLEX study was overall survival. The FLEX study, which is ongoing but not recruiting participants, is registered with ClinicalTrials.gov, number NCT00148798. Findings: KRAS mutations were detected in 75 of 395 (19%) tumours and activating EGFR mutations in 64 of 436 (15%). EGFR copy number was scored as increased in 102 of 279 (37%) tumours and PTEN expression as negative in 107 of 303 (35%). Comparisons of treatment outcome between the two groups (chemotherapy plus cetuximab vs chemotherapy alone) according to biomarker status provided no indication that these biomarkers were of predictive value. Activating EGFR mutations were identified as indicators of good prognosis, with patients in both treatment groups whose tumours carried such mutations having improved survival compared with those whose tumours did not (chemotherapy plus cetuximab: median 17·5 months [95% CI 11·7-23·4] vs 8·5 months [7·1-10·8], hazard ratio [HR] 0·52 [0·32-0·84], p=0·0063; chemotherapy alone: 23·8 months [15·2-not reached] vs 10·0 months [8·7-11·0], HR 0·35 [0·21-0·59], p<0·0001). Expression of PTEN seemed to be a potential indicator of good prognosis, with patients whose tumours expressed PTEN having improved survival compared with those whose tumours did not, although this finding was not significant (chemotherapy plus cetuximab: median 11·4 months [8·6-13·6] vs 6·8 months [5·9-12·7], HR 0·80 [0·55-1·16], p=0·24; chemotherapy alone: 11·0 months [9·2-12·6] vs 9·3 months [7·6-11·9], HR 0·77 [0·54-1·10], p=0·16). Interpretation: The efficacy of chemotherapy plus cetuximab in the first-line treatment of advanced NSCLC seems to be independent of each of the biomarkers assessed. Funding: Merck KGaA. © 2011 Elsevier Ltd.

Prognostic factors in patients with advanced non-small cell lung cancer : data from the phase III FLEX study

The FLEX study demonstrated that the addition of cetuximab to chemotherapy significantly improved overall survival in the first-line treatment of patients with advanced non-small cell lung cancer (NSCLC). In the FLEX intention to treat (ITT) population, we investigated the prognostic significance of particular baseline characteristics. Individual patient data from the treatment arms of the ITT population of the FLEX study were combined. Univariable and multivariable Cox regression models were used to investigate variables with potential prognostic value. The ITT population comprised 1125 patients. In the univariable analysis, longer median survival times were apparent for females compared with males (12.7 vs 9.3 months); patients with an Eastern Cooperative Oncology Group performance status (ECOG PS) of 0 compared with 1 compared with 2 (13.5 vs 10.6 vs 5.9 months); never smokers compared with former smokers compared with current smokers (14.6 vs 11.1 vs 9.0); Asians compared with Caucasians (19.5 vs 9.6 months); patients with adenocarcinoma compared with squamous cell carcinoma (12.4 vs 9.3 months) and those with metastases to one site compared with two sites compared with three or more sites (12.4 months vs 9.8 months vs 6.4 months). Age (<65 vs ≥65 years), tumor stage (IIIB with pleural effusion vs IV) and percentage of tumor cells expressing EGFR (<40% vs ≥40%) were not identified as possible prognostic factors in relation to survival time. In multivariable analysis, a stepwise selection procedure identified age (<65 vs ≥65 years), gender, ECOG PS, smoking status, region, tumor histology, and number of organs involved as independent factors of prognostic value. In summary, in patients with advanced NSCLC enrolled in the FLEX study, and consistent with previous analyses, particular patient and disease characteristics at baseline were shown to be independent factors of prognostic value. The FLEX study is registered with ClinicalTrials.gov, number NCT00148798. © 2012 Elsevier Ireland Ltd.

EGFR expression as a predictor of survival for first-line chemotherapy plus cetuximab in patients with advanced non-small-cell lung cancer : analysis of data from the phase 3 FLEX study

Background: Findings from the phase 3 First-Line ErbituX in lung cancer (FLEX) study showed that the addition of cetuximab to first-line chemotherapy significantly improved overall survival compared with chemotherapy alone (hazard ratio [HR] 0·871, 95% CI 0·762-0·996; p=0·044) in patients with advanced non-small-cell lung cancer (NSCLC). To define patients benefiting most from cetuximab, we studied the association of tumour EGFR expression level with clinical outcome in FLEX study patients. Methods: We used prospectively collected tumour EGFR expression data to generate an immunohistochemistry score for FLEX study patients on a continuous scale of 0-300. We used response data to select an outcome-based discriminatory threshold immunohistochemistry score for EGFR expression of 200. Treatment outcome was analysed in patients with low (immunohistochemistry score <200) and high (≥200) tumour EGFR expression. The primary endpoint in the FLEX study was overall survival. We analysed patients from the FLEX intention-to-treat (ITT) population. The FLEX study is registered with ClinicalTrials.gov, number NCT00148798. Findings: Tumour EGFR immunohistochemistry data were available for 1121 of 1125 (99·6%) patients from the FLEX study ITT population. High EGFR expression was scored for 345 (31%) evaluable patients and low for 776 (69%) patients. For patients in the high EGFR expression group, overall survival was longer in the chemotherapy plus cetuximab group than in the chemotherapy alone group (median 12·0 months [95% CI 10·2-15·2] vs 9·6 months [7·6-10·6]; HR 0·73, 0·58-0·93; p=0·011), with no meaningful increase in side-effects. We recorded no corresponding survival benefit for patients in the low EGFR expression group (median 9·8 months [8·9-12·2] vs 10·3 months [9·2-11·5]; HR 0·99, 0·84-1·16; p=0·88). A treatment interaction test assessing the difference in the HRs for overall survival between the EGFR expression groups suggested a predictive value for EGFR expression (p=0·044). Interpretation: High EGFR expression is a tumour biomarker that can predict survival benefit from the addition of cetuximab to first-line chemotherapy in patients with advanced NSCLC. Assessment of EGFR expression could offer a personalised treatment approach in this setting. Funding: Merck KGaA. © 2012 Elsevier Ltd.

Design, implementation and multisite evaluation of a system suitability protocol for the quantitative assessment of instrument performance in liquid chromatography-multiple reaction monitoring-MS (LC-MRM-MS)

Multiple reaction monitoring (MRM) mass spectrometry coupled with stable isotope dilution (SID) and liquid chromatography (LC) is increasingly used in biological and clinical studies for precise and reproducible quantification of peptides and proteins in complex sample matrices. Robust LC-SID-MRM-MS-based assays that can be replicated across laboratories and ultimately in clinical laboratory settings require standardized protocols to demonstrate that the analysis platforms are performing adequately. We developed a system suitability protocol (SSP), which employs a predigested mixture of six proteins, to facilitate performance evaluation of LC-SID-MRM-MS instrument platforms, configured with nanoflow-LC systems interfaced to triple quadrupole mass spectrometers. The SSP was designed for use with low multiplex analyses as well as high multiplex approaches when software-driven scheduling of data acquisition is required. Performance was assessed by monitoring of a range of chromatographic and mass spectrometric metrics including peak width, chromatographic resolution, peak capacity, and the variability in peak area and analyte retention time (RT) stability. The SSP, which was evaluated in 11 laboratories on a total of 15 different instruments, enabled early diagnoses of LC and MS anomalies that indicated suboptimal LC-MRM-MS performance. The observed range in variation of each of the metrics scrutinized serves to define the criteria for optimized LC-SID-MRM-MS platforms for routine use, with pass/fail criteria for system suitability performance measures defined as peak area coefficient of variation <0.15, peak width coefficient of variation <0.15, standard deviation of RT <0.15 min (9 s), and the RT drift <0.5min (30 s). The deleterious effect of a marginally performing LC-SID-MRM-MS system on the limit of quantification (LOQ) in targeted quantitative assays illustrates the use and need for a SSP to establish robust and reliable system performance. Use of a SSP helps to ensure that analyte quantification measurements can be replicated with good precision within and across multiple laboratories and should facilitate more widespread use of MRM-MS technology by the basic biomedical and clinical laboratory research communities.

Odometry-driven inference to link multiple exemplars of a location

A major challenge for robot localization and mapping systems is maintaining reliable operation in a changing environment. Vision-based systems in particular are susceptible to changes in illumination and weather, and the same location at another time of day may appear radically different to a system using a feature-based visual localization system. One approach for mapping changing environments is to create and maintain maps that contain multiple representations of each physical location in a topological framework or manifold. However, this requires the system to be able to correctly link two or more appearance representations to the same spatial location, even though the representations may appear quite dissimilar. This paper proposes a method of linking visual representations from the same location without requiring a visual match, thereby allowing vision-based localization systems to create multiple appearance representations of physical locations. The most likely position on the robot path is determined using particle filter methods based on dead reckoning data and recent visual loop closures. In order to avoid erroneous loop closures, the odometry-based inferences are only accepted when the inferred path's end point is confirmed as correct by the visual matching system. Algorithm performance is demonstrated using an indoor robot dataset and a large outdoor camera dataset.

Slicing big data - Twitter, gambling and time sensitive information

Big Data presents many challenges related to volume, whether one is interested in studying past datasets or, even more problematically, attempting to work with live streams of data. The most obvious challenge, in a ‘noisy’ environment such as contemporary social media, is to collect the pertinent information; be that information for a specific study, tweets which can inform emergency services or other responders to an ongoing crisis, or give an advantage to those involved in prediction markets. Often, such a process is iterative, with keywords and hashtags changing with the passage of time, and both collection and analytic methodologies need to be continually adapted to respond to this changing information. While many of the data sets collected and analyzed are preformed, that is they are built around a particular keyword, hashtag, or set of authors, they still contain a large volume of information, much of which is unnecessary for the current purpose and/or potentially useful for future projects. Accordingly, this panel considers methods for separating and combining data to optimize big data research and report findings to stakeholders. The first paper considers possible coding mechanisms for incoming tweets during a crisis, taking a large stream of incoming tweets and selecting which of those need to be immediately placed in front of responders, for manual filtering and possible action. The paper suggests two solutions for this, content analysis and user profiling. In the former case, aspects of the tweet are assigned a score to assess its likely relationship to the topic at hand, and the urgency of the information, whilst the latter attempts to identify those users who are either serving as amplifiers of information or are known as an authoritative source. Through these techniques, the information contained in a large dataset could be filtered down to match the expected capacity of emergency responders, and knowledge as to the core keywords or hashtags relating to the current event is constantly refined for future data collection. The second paper is also concerned with identifying significant tweets, but in this case tweets relevant to particular prediction market; tennis betting. As increasing numbers of professional sports men and women create Twitter accounts to communicate with their fans, information is being shared regarding injuries, form and emotions which have the potential to impact on future results. As has already been demonstrated with leading US sports, such information is extremely valuable. Tennis, as with American Football (NFL) and Baseball (MLB) has paid subscription services which manually filter incoming news sources, including tweets, for information valuable to gamblers, gambling operators, and fantasy sports players. However, whilst such services are still niche operations, much of the value of information is lost by the time it reaches one of these services. The paper thus considers how information could be filtered from twitter user lists and hash tag or keyword monitoring, assessing the value of the source, information, and the prediction markets to which it may relate. The third paper examines methods for collecting Twitter data and following changes in an ongoing, dynamic social movement, such as the Occupy Wall Street movement. It involves the development of technical infrastructure to collect and make the tweets available for exploration and analysis. A strategy to respond to changes in the social movement is also required or the resulting tweets will only reflect the discussions and strategies the movement used at the time the keyword list is created — in a way, keyword creation is part strategy and part art. In this paper we describe strategies for the creation of a social media archive, specifically tweets related to the Occupy Wall Street movement, and methods for continuing to adapt data collection strategies as the movement’s presence in Twitter changes over time. We also discuss the opportunities and methods to extract data smaller slices of data from an archive of social media data to support a multitude of research projects in multiple fields of study. The common theme amongst these papers is that of constructing a data set, filtering it for a specific purpose, and then using the resulting information to aid in future data collection. The intention is that through the papers presented, and subsequent discussion, the panel will inform the wider research community not only on the objectives and limitations of data collection, live analytics, and filtering, but also on current and in-development methodologies that could be adopted by those working with such datasets, and how such approaches could be customized depending on the project stakeholders.

Sensor Data Integrity : Multi-Sensor Perception for Unmanned Ground Vehicles

This document describes large, accurately calibrated and time-synchronised datasets, gathered in controlled environmental conditions, using an unmanned ground vehicle equipped with a wide variety of sensors. These sensors include: multiple laser scanners, a millimetre wave radar scanner, a colour camera and an infra-red camera. Full details of the sensors are given, as well as the calibration parameters needed to locate them with respect to each other and to the platform. This report also specifies the format and content of the data, and the conditions in which the data have been gathered. The data collection was made in two different situations of the vehicle: static and dynamic. The static tests consisted of sensing a fixed ’reference’ terrain, containing simple known objects, from a motionless vehicle. For the dynamic tests, data were acquired from a moving vehicle in various environments, mainly rural, including an open area, a semi-urban zone and a natural area with different types of vegetation. For both categories, data have been gathered in controlled environmental conditions, which included the presence of dust, smoke and rain. Most of the environments involved were static, except for a few specific datasets which involve the presence of a walking pedestrian. Finally, this document presents illustrations of the effects of adverse environmental conditions on sensor data, as a first step towards reliability and integrity in autonomous perceptual systems.

Combining multiple sensor modalities for a localisation robust to smoke

This paper proposes an approach to obtain a localisation that is robust to smoke by exploiting multiple sensing modalities: visual and infrared (IR) cameras. This localisation is based on a state-of-the-art visual SLAM algorithm. First, we show that a reasonably accurate localisation can be obtained in the presence of smoke by using only an IR camera, a sensor that is hardly affected by smoke, contrary to a visual camera (operating in the visible spectrum). Second, we demonstrate that improved results can be obtained by combining the information from the two sensor modalities (visual and IR cameras). Third, we show that by detecting the impact of smoke on the visual images using a data quality metric, we can anticipate and mitigate the degradation in performance of the localisation by discarding the most affected data. The experimental validation presents multiple trajectories estimated by the various methods considered, all thoroughly compared to an accurate dGPS/INS reference.

A data analytics case study assessing factors affecting pavement deflection values

Road networks are a national critical infrastructure. The road assets need to be monitored and maintained efficiently as their conditions deteriorate over time. The condition of one of such assets, road pavement, plays a major role in the road network maintenance programmes. Pavement conditions depend upon many factors such as pavement types, traffic and environmental conditions. This paper presents a data analytics case study for assessing the factors affecting the pavement deflection values measured by the traffic speed deflectometer (TSD) device. The analytics process includes acquisition and integration of data from multiple sources, data pre-processing, mining useful information from them and utilising data mining outputs for knowledge deployment. Data mining techniques are able to show how TSD outputs vary in different roads, traffic and environmental conditions. The generated data mining models map the TSD outputs to some classes and define correction factors for each class.