A Tobit model for analyzing speed limit compliance in work zones

Poor compliance with speed limits is a serious safety concern in work zones. Most studies of work zone speeds have focused on descriptive analyses and statistical testing without systematically capturing the effects of vehicle and traffic characteristics. Consequently, little is known about how the characteristics of surrounding traffic and platoons influence speeds. This paper develops a Tobit regression technique for innovatively modeling the probability and the magnitude of non-compliance with speed limits at various locations in work zones. Speed data is transformed into two groups—continuous for non-compliant and left-censored for compliant drivers—to model in a Tobit model framework. The modeling technique is illustrated using speed data from three long-term highway work zones in Queensland, Australia. Consistent and plausible model estimates across the three work zones support the appropriateness and validity of the technique. The results show that the probability and magnitude of speeding was higher for leaders of platoons with larger front gaps, during late afternoon and early morning, when traffic volumes were higher, and when higher proportions of surrounding vehicles were non-compliant. Light vehicles and their followers were also more likely to speed than others. Speeding was more common and greater in magnitude upstream than in the activity area, with higher compliance rates close to the end of the activity area and close to stop/slow traffic controllers. The modeling technique and results have great potential to assist in deployment of appropriate countermeasures by better identifying the traffic characteristics associated with speeding and the locations of lower compliance.

Student interactivity and teacher participation: An application of legitimate peripheral participation in higher education online learning environments

Lave and Wenger’s legitimate peripheral participation is an important aspect of online learning environments. It is common for teachers to scaffold varying levels of online participation in Web 2.0 contexts, such as online discussion forums and blogs. This study argues that legitimate peripheral participation needs to be redefined in response to students’ decentralised multiple interactions and non-linear engagement in hyperlinked learning environments. The study examines students’ levels of participation in online learning through theories of interactivity, distinguishing between five levels of student participation in the context of a first-year university course delivered via a learning management system. The data collection was implemented through two instruments: i) a questionnaire about students’ interactivity perception in the online reflective learning (n = 238) and then ii) an open discussion on the reason for the diverse perceptions of interactivity (n = 34). The study findings indicate that student participants, other than those who were active, need high levels of teacher or moderator intervention, which better enables legitimate peripheral participation to occur in online learning contexts.

Predicting structural disruption of proteins caused by crossover

We present a machine learning model that predicts a structural disruption score from a protein s primary structure. SCHEMA was introduced by Frances Arnold and colleagues as a method for determining putative recombination sites of a protein on the basis of the full (PDB) description of its structure. The present method provides an alternative to SCHEMA that is able to determine the same score from sequence data only. Circumventing the need for resolving the full structure enables the exploration of yet unresolved and even hypothetical sequences for protein design efforts. Deriving the SCHEMA score from a primary structure is achieved using a two step approach: first predicting a secondary structure from the sequence and then predicting the SCHEMA score from the predicted secondary structure. The correlation coefficient for the prediction is 0.88 and indicates the feasibility of replacing SCHEMA with little loss of precision.

A convolutional neural network for automatic analysis of aerial imagery

This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Recognising emotional expressions of complaining customers : A cross-cultural study

Purpose This study aims to test service providers’ ability to recognise non-verbal emotions in complaining customers of same and different cultures. Design/methodology/approach In a laboratory study, using a between-subjects experimental design (n = 153), we tested the accuracy of service providers’ perceptions of the emotional expressions of anger, fear, shame and happiness of customers from varying cultural backgrounds. After viewing video vignettes of customers complaining (with the audio removed), participants (in the role of service providers) assessed the emotional state of the customers portrayed in the video. Findings Service providers in culturally mismatched dyads were prone to misreading anger, happiness and shame expressed by dissatisfied customers. Happiness was misread in the displayed emotions of both dyads. Anger was recognisable in the Anglo customers but not Confucian Asian, while Anglo service providers misread both shame and happiness in Confucian Asian customers. Research limitations/implications The study was conducted in the laboratory and was based solely on participant’s perceptions of actors’ non-verbal facial expressions in a single encounter. Practical implications Given the level of ethnic differences in developed nations, a culturally sensitive workplace is needed to foster effective functioning of service employee teams. Ability to understand cultural display rules and to recognise and interpret emotions is an important skill for people working in direct contact with customers. Originality/value This research addresses the lack of empirical evidence for the recognition of customer emotions by service providers and the impact of cross-cultural differences.

The Catlin Seaview Survey – kilometre-scale seascape assessment, and monitoring of coral reef ecosystems

1.Marine ecosystems provide critically important goods and services to society, and hence their accelerated degradation underpins an urgent need to take rapid, ambitious and informed decisions regarding their conservation and management. 2.The capacity, however, to generate the detailed field data required to inform conservation planning at appropriate scales is limited by time and resource consuming methods for collecting and analysing field data at the large scales required. 3.The ‘Catlin Seaview Survey’, described here, introduces a novel framework for large-scale monitoring of coral reefs using high-definition underwater imagery collected using customized underwater vehicles in combination with computer vision and machine learning. This enables quantitative and geo-referenced outputs of coral reef features such as habitat types, benthic composition, and structural complexity (rugosity) to be generated across multiple kilometre-scale transects with a spatial resolution ranging from 2 to 6 m2. 4.The novel application of technology described here has enormous potential to contribute to our understanding of coral reefs and associated impacts by underpinning management decisions with kilometre-scale measurements of reef health. 5.Imagery datasets from an initial survey of 500 km of seascape are freely available through an online tool called the Catlin Global Reef Record. Outputs from the image analysis using the technologies described here will be updated on the online repository as work progresses on each dataset. 6.Case studies illustrate the utility of outputs as well as their potential to link to information from remote sensing. The potential implications of the innovative technologies on marine resource management and conservation are also discussed, along with the accuracy and efficiency of the methodologies deployed.

Situating learning : (re)examining the notion of apprenticeship in coach education

The last two decades has seen a proliferation in the provision of, and importance attached to, coach education in many Western countries [1]. Pivotal to many coach education programmes is the notion of apprenticeship [2,3,4]. Increasingly, mentoring is being positioned as a possible tool for enhancing coach education and consequently professional expertise [5]. However, there is a paucity of empirical data on interventions in, and evaluations of, coach education programmes. In their recent evaluation of a coach education programme Cassidy, Potrac & McKenzie [6] conclude that the situated learning literature could provide coach educators with a generative platform for the (re)examinationof apprenticeships and mentoring in a coach education context. This paper consequently discusses the merits of using situated learning theory [7] and the associated concept of Communities of Practice (CoP) [8] to stimulate discussion on developing new understandings of the practices of apprenticeship and mentoring in coach education.

Application of anomaly technique in wind turbine bearing fault detection

Bearing faults are the most common cause of wind turbine failures. Unavailability and maintenance cost of wind turbines are becoming critically important, with their fast growing in electric networks. Early fault detection can reduce outage time and costs. This paper proposes Anomaly Detection (AD) machine learning algorithms for fault diagnosis of wind turbine bearings. The application of this method on a real data set was conducted and is presented in this paper. For validation and comparison purposes, a set of baseline results are produced using the popular one-class SVM methods to examine the ability of the proposed technique in detecting incipient faults.

Multi-action recognition via stochastic modelling of optical flow and gradients

In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.

Modelling busway operation with mixed stopping and non-stopping buses

This thesis investigated the complexity of busway operation with stopping and non-stopping buses using field data and microscopic simulation modelling. The proposed approach made significant recommendations to transit authorities to achieve the most practicable system capacity for existing and new busways. The empirical equations developed in this research and newly introduced analysis methods will be ideal tools for transit planners to achieve optimal reliability of busways.

The potential for utilising the collaborative learning spaces approach in the delivery of résumé development education

This study investigated the potential for using collaborative learning spaces for the development of résumé writing knowledge and skills in higher education students. Utilising a collaborative learning environment, 227 students from a mix of programmes and year levels participated in one of 24 workshops centering on a technology supported, shared review and reflection approach to résumé construction. It was concluded that use of technology supported collaborative learning spaces has the potential to be a valuable, innovative approach for the delivery of career management related skills in higher education.

Safety envelope for security

We present an approach for detecting sensor spoofing attacks on a cyber-physical system. Our approach consists of two steps. In the first step, we construct a safety envelope of the system. Under nominal conditions (that is, when there are no attacks), the system always stays inside its safety envelope. In the second step, we build an attack detector: a monitor that executes synchronously with the system and raises an alarm whenever the system state falls outside the safety envelope. We synthesize safety envelopes using a modified machine learning procedure applied on data collected from the system when it is not under attack. We present experimental results that show effectiveness of our approach, and also validate the several novel features that we introduced in our learning procedure.

Centroid training to achieve effective text classification

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F1 and Accuracy have been chosen as the key evaluation measures. We stress the F1 measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F1 and Accuracy compared with three other influential baseline models.

Towards robust automatic affective classification of images using facial expressions for practical applications

Affect is an important feature of multimedia content and conveys valuable information for multimedia indexing and retrieval. Most existing studies for affective content analysis are limited to low-level features or mid-level representations, and are generally criticized for their incapacity to address the gap between low-level features and high-level human affective perception. The facial expressions of subjects in images carry important semantic information that can substantially influence human affective perception, but have been seldom investigated for affective classification of facial images towards practical applications. This paper presents an automatic image emotion detector (IED) for affective classification of practical (or non-laboratory) data using facial expressions, where a lot of “real-world” challenges are present, including pose, illumination, and size variations etc. The proposed method is novel, with its framework designed specifically to overcome these challenges using multi-view versions of face and fiducial point detectors, and a combination of point-based texture and geometry. Performance comparisons of several key parameters of relevant algorithms are conducted to explore the optimum parameters for high accuracy and fast computation speed. A comprehensive set of experiments with existing and new datasets, shows that the method is effective despite pose variations, fast, and appropriate for large-scale data, and as accurate as the method with state-of-the-art performance on laboratory-based data. The proposed method was also applied to affective classification of images from the British Broadcast Corporation (BBC) in a task typical for a practical application providing some valuable insights.