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.

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.

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.

Quantitative data collection and study validity

The quality of data collection methods selected and the integrity of the data collected are integral tot eh success of a study. This chapter focuses on data collection and study validity. After reading the chapter, readers should be able to define types of data collection methods in quantitative research; list advantages and disadvantages of each method; discuss factors related to internal and external validity; critically evaluate data collection methods and discuss the need to operationalise variables of interest for data collection.

A stochastic neighborhood conditional autoregressive model for spatial data

A spatial process observed over a lattice or a set of irregular regions is usually modeled using a conditionally autoregressive (CAR) model. The neighborhoods within a CAR model are generally formed deterministically using the inter-distances or boundaries between the regions. An extension of CAR model is proposed in this article where the selection of the neighborhood depends on unknown parameter(s). This extension is called a Stochastic Neighborhood CAR (SNCAR) model. The resulting model shows flexibility in accurately estimating covariance structures for data generated from a variety of spatial covariance models. Specific examples are illustrated using data generated from some common spatial covariance functions as well as real data concerning radioactive contamination of the soil in Switzerland after the Chernobyl accident.

Noise levels in a General Surgical Ward : a descriptive study

Aims and objectives.  This study was undertaken to measure and analyse levels of acoustic noise in a General Surgical Ward. Method.  Measurements were undertaken using the Norsonic 116 sound level meter (SLM) recording noise levels in the internationally agreed ‘A’ weighted scale. Noise level data and observational data as to the number of staff present were obtained and recorded at 5-min intervals over three consecutive days. Results.  Results of noise level analysis indicated that mean noise level within this clinical area was 42.28 dB with acute spikes reaching 70 dB(A). The lowest noise level attained was that of 36 dB(A) during the period midnight to 7 a.m. Non-parametric testing, using Spearman's Rho (two-tailed), found a positive relationship between the number of staff present and the level of noise recorded, indicating that the presence of hospital personnel strongly influences the level of noise within this area. Relevance to clinical practice.  Whilst the results of this may seem self-evident in many respects the problems of excessive noise production and the exposure to it for patients, hospital personnel and relatives alike continues unabated. What must be of concern is the psychophysiological effects excessive noise exposure has on individuals, for example, decreased wound healing, sleep deprivation and cardiovascular stimulation.