Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke. An example of application is given with monocular SLAM estimating the pose of the UGV while smoke is present in the environment. It is shown that the proposed novel quality metric can be used to anticipate situations where the quality of the pose estimate will be significantly degraded due to the input image data. This leads to decisions of advantageously switching between data sources (e.g. using infrared images instead of visual images).

Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke.

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.

The Marulan data sets: multi-sensor perception in a natural environment with challenging conditions

In this paper we present large, accurately calibrated and time-synchronized data sets, gathered outdoors in controlled and variable environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. These include four 2D laser scanners, a radar scanner, a color camera and an infrared camera. It provides a full description of the system used for data collection and the types of environments and conditions in which these data sets have been gathered, which include the presence of airborne dust, smoke and rain.

Laser-camera data discrepancies and reliable perception in outdoor robotics

This work aims to promote integrity in autonomous perceptual systems, with a focus on outdoor unmanned ground vehicles equipped with a camera and a 2D laser range finder. A method to check for inconsistencies between the data provided by these two heterogeneous sensors is proposed and discussed. First, uncertainties in the estimated transformation between the laser and camera frames are evaluated and propagated up to the projection of the laser points onto the image. Then, for each pair of laser scan-camera image acquired, the information at corners of the laser scan is compared with the content of the image, resulting in a likelihood of correspondence. The result of this process is then used to validate segments of the laser scan that are found to be consistent with the image, while inconsistent segments are rejected. Experimental results illustrate how this technique can improve the reliability of perception in challenging environmental conditions, such as in the presence of airborne dust.

Capturing complex, non-linear team behaviours during competitive football performance

This study investigated changes in the complexity (magnitude and structure of variability) of the collective behaviours of association football teams during competitive performance. Raw positional data from an entire competitive match between two professional teams were obtained with the ProZone® tracking system. Five compound positional variables were used to investigate the collective patterns of performance of each team including: surface area, stretch index, team length, team width, and geometrical centre. Analyses involve the coefficient of variation (%CV) and approximate entropy (ApEn), as well as the linear association between both parameters. Collective measures successfully captured the idiosyncratic behaviours of each team and their variations across the six time periods of the match. Key events such as goals scored and game breaks (such as half time and full time) seemed to influence the collective patterns of performance. While ApEn values significantly decreased during each half, the %CV increased. Teams seem to become more regular and predictable, but with increased magnitudes of variation in their organisational shape over the natural course of a match.

A hybrid genetic algorithm for the energy-efficient virtual machine placement problem in data centers

Server consolidation using virtualization technology has become an important technology to improve the energy efficiency of data centers. Virtual machine placement is the key in the server consolidation technology. In the past few years, many approaches to the virtual machine placement have been proposed. However, existing virtual machine placement approaches consider the energy consumption by physical machines only, but do not consider the energy consumption in communication network, in a data center. However, the energy consumption in the communication network in a data center is not trivial, and therefore should be considered in the virtual machine placement. In our preliminary research, we have proposed a genetic algorithm for a new virtual machine placement problem that considers the energy consumption in both physical machines and the communication network in a data center. Aiming at improving the performance and efficiency of the genetic algorithm, this paper presents a hybrid genetic algorithm for the energy-efficient virtual machine placement problem. Experimental results show that the hybrid genetic algorithm significantly outperforms the original genetic algorithm, and that the hybrid genetic algorithm is scalable.

Meta-analysis of individual patient data from randomized trials of chemotherapy plus cetuximab as first-line treatment for advanced non-small cell lung cancer

OBJECTIVES: Four randomized phase II/III trials investigated the addition of cetuximab to platinum-based, first-line chemotherapy in patients with advanced non-small cell lung cancer (NSCLC). A meta-analysis was performed to examine the benefit/risk ratio for the addition of cetuximab to chemotherapy. MATERIALS AND METHODS: The meta-analysis included individual patient efficacy data from 2018 patients and individual patient safety data from 1970 patients comprising respectively the combined intention-to-treat and safety populations of the four trials. The effect of adding cetuximab to chemotherapy was measured by hazard ratios (HRs) obtained using a Cox proportional hazards model and odds ratios calculated by logistic regression. Survival rates at 1 year were calculated. All applied models were stratified by trial. Tests on heterogeneity of treatment effects across the trials and sensitivity analyses were performed for all endpoints. RESULTS: The meta-analysis demonstrated that the addition of cetuximab to chemotherapy significantly improved overall survival (HR 0.88, p=0.009, median 10.3 vs 9.4 months), progression-free survival (HR 0.90, p=0.045, median 4.7 vs 4.5 months) and response (odds ratio 1.46, p<0.001, overall response rate 32.2% vs 24.4%) compared with chemotherapy alone. The safety profile of chemotherapy plus cetuximab in the meta-analysis population was confirmed as manageable. Neither trials nor patient subgroups defined by key baseline characteristics showed significant heterogeneity for any endpoint. CONCLUSION: The addition of cetuximab to platinum-based, first-line chemotherapy for advanced NSCLC significantly improved outcome for all efficacy endpoints with an acceptable safety profile, indicating a favorable benefit/risk ratio.

Health big data analytics : current perspectives, challenges and potential solutions

Modern health information systems can generate several exabytes of patient data, the so called "Health Big Data", per year. Many health managers and experts believe that with the data, it is possible to easily discover useful knowledge to improve health policies, increase patient safety and eliminate redundancies and unnecessary costs. The objective of this paper is to discuss the characteristics of Health Big Data as well as the challenges and solutions for health Big Data Analytics (BDA) – the process of extracting knowledge from sets of Health Big Data – and to design and evaluate a pipelined framework for use as a guideline/reference in health BDA.

Oscar Pistorius and the death of Reeva Steenkamp : mapping public opinions on Twitter using frame analysis and data mining

This paper uses innovative content analysis techniques to map how the death of Oscar Pistorius' girlfriend, Reeva Steenkamp, was framed on Twitter conversations. Around 1.5 million posts from a two-week timeframe are analyzed with a combination of syntactic and semantic methods. This analysis is grounded in the frame analysis perspective and is different than sentiment analysis. Instead of looking for explicit evaluations, such as “he is guilty” or “he is innocent”, we showcase through the results how opinions can be identified by complex articulations of more implicit symbolic devices such as examples and metaphors repeatedly mentioned. Different frames are adopted by users as more information about the case is revealed: from a more episodic one, highly used in the very beginning, to more systemic approaches, highlighting the association of the event with urban violence, gun control issues, and violence against women. A detailed timeline of the discussions is provided.

Data innovation and open access [Blog]

After nearly fifteen years of the open access (OA) movement and its hard-fought struggle for a more open scholarly communication system, publishers are realizing that business models can be both open and profitable. Making journal articles available on an OA license is becoming an accepted strategy for maximizing the value of content to both research communities and the businesses that serve them. The first blog in this two-part series celebrating Data Innovation Day looks at the role that data-innovation is playing in the shift to open access for journal articles.

'Explain in plain English' questions revisited : data structures problems

Recent studies have linked the ability of novice (CS1) programmers to read and explain code with their ability to write code. This study extends earlier work by asking CS2 students to explain object-oriented data structures problems that involve recursion. Results show a strong correlation between ability to explain code at an abstract level and performance on code writing and code reading test problems for these object-oriented data structures problems. The authors postulate that there is a common set of skills concerned with reasoning about programs that explains the correlation between writing code and explaining code. The authors suggest that an overly exclusive emphasis on code writing may be detrimental to learning to program. Non-code writing learning activities (e.g., reading and explaining code) are likely to improve student ability to reason about code and, by extension, improve student ability to write code. A judicious mix of code-writing and code-reading activities is recommended.

Prediction of CO concentrations based on a hybrid Partial Least Square and Support Vector Machine model

Due to the health impacts caused by exposures to air pollutants in urban areas, monitoring and forecasting of air quality parameters have become popular as an important topic in atmospheric and environmental research today. The knowledge on the dynamics and complexity of air pollutants behavior has made artificial intelligence models as a useful tool for a more accurate pollutant concentration prediction. This paper focuses on an innovative method of daily air pollution prediction using combination of Support Vector Machine (SVM) as predictor and Partial Least Square (PLS) as a data selection tool based on the measured values of CO concentrations. The CO concentrations of Rey monitoring station in the south of Tehran, from Jan. 2007 to Feb. 2011, have been used to test the effectiveness of this method. The hourly CO concentrations have been predicted using the SVM and the hybrid PLS–SVM models. Similarly, daily CO concentrations have been predicted based on the aforementioned four years measured data. Results demonstrated that both models have good prediction ability; however the hybrid PLS–SVM has better accuracy. In the analysis presented in this paper, statistic estimators including relative mean errors, root mean squared errors and the mean absolute relative error have been employed to compare performances of the models. It has been concluded that the errors decrease after size reduction and coefficients of determination increase from 56 to 81% for SVM model to 65–85% for hybrid PLS–SVM model respectively. Also it was found that the hybrid PLS–SVM model required lower computational time than SVM model as expected, hence supporting the more accurate and faster prediction ability of hybrid PLS–SVM model.

A Bayesian regression approach to assess uncertainty in pollutant wash-off modelling

Due to knowledge gaps in relation to urban stormwater quality processes, an in-depth understanding of model uncertainty can enhance decision making. Uncertainty in stormwater quality models can originate from a range of sources such as the complexity of urban rainfall-runoff-stormwater pollutant processes and the paucity of observed data. Unfortunately, studies relating to epistemic uncertainty, which arises from the simplification of reality are limited and often deemed mostly unquantifiable. This paper presents a statistical modelling framework for ascertaining epistemic uncertainty associated with pollutant wash-off under a regression modelling paradigm using Ordinary Least Squares Regression (OLSR) and Weighted Least Squares Regression (WLSR) methods with a Bayesian/Gibbs sampling statistical approach. The study results confirmed that WLSR assuming probability distributed data provides more realistic uncertainty estimates of the observed and predicted wash-off values compared to OLSR modelling. It was also noted that the Bayesian/Gibbs sampling approach is superior compared to the most commonly adopted classical statistical and deterministic approaches commonly used in water quality modelling. The study outcomes confirmed that the predication error associated with wash-off replication is relatively higher due to limited data availability. The uncertainty analysis also highlighted the variability of the wash-off modelling coefficient k as a function of complex physical processes, which is primarily influenced by surface characteristics and rainfall intensity.

Multilocus sequence analysis provides insights into molecular epidemiology of Chlamydia pecorum infections in Australian sheep, cattle and koalas

Chlamydia pecorum is a significant pathogen of domestic livestock and wildlife. We have developed a C. pecorum-specific multilocus sequence analysis (MLSA) scheme to examine the genetic diversity of and relationships between Australian sheep, cattle, and koala isolates. An MLSA of seven concatenated housekeeping gene fragments was performed using 35 isolates, including 18 livestock isolates (11 Australian sheep, one Australian cow, and six U.S. livestock isolates) and 17 Australian koala isolates. Phylogenetic analyses showed that the koala isolates formed a distinct clade, with limited clustering with C. pecorum isolates from Australian sheep. We identified 11 MLSA sequence types (STs) among Australian C. pecorum isolates, 10 of them novel, with koala and sheep sharing at least one identical ST (designated ST2013Aa). ST23, previously identified in global C. pecorum livestock isolates, was observed here in a subset of Australian bovine and sheep isolates. Most notably, ST23 was found in association with multiple disease states and hosts, providing insights into the transmission of this pathogen between livestock hosts. The complexity of the epidemiology of this disease was further highlighted by the observation that at least two examples of sheep were infected with different C. pecorum STs in the eyes and gastrointestinal tract. We have demonstrated the feasibility of our MLSA scheme for understanding the host relationship that exists between Australian C. pecorum strains and provide the first molecular epidemiological data on infections in Australian livestock hosts.