The benefits of tree-based models for stock selection

The identification of the primary drivers of stock returns has been of great interest to both financial practitioners and academics alike for many decades. Influenced by classical financial theories such as the CAPM (Sharp, 1964; Lintner, 1965) and APT (Ross, 1976), a linear relationship is conventionally assumed between company characteristics as derived from their financial accounts and forward returns. Whilst this assumption may be a fair approximation to the underlying structural relationship, it is often adopted for the purpose of convenience. It is actually quite rare that the assumptions of distributional normality and a linear relationship are explicitly assessed in advance even though this information would help to inform the appropriate choice of modelling technique. Non-linear models have nevertheless been applied successfully to the task of stock selection in the past (Sorensen et al, 2000). However, their take-up by the investment community has been limited despite the fact that researchers in other fields have found them to be a useful way to express knowledge and aid decision-making...

Automatic Audio Segmentation Using the Generalized Likelihood Ratio

This paper presents a novel technique for segmenting an audio stream into homogeneous regions according to speaker identities, background noise, music, environmental and channel conditions. Audio segmentation is useful in audio diarization systems, which aim to annotate an input audio stream with information that attributes temporal regions of the audio into their specific sources. The segmentation method introduced in this paper is performed using the Generalized Likelihood Ratio (GLR), computed between two adjacent sliding windows over preprocessed speech. This approach is inspired by the popular segmentation method proposed by the pioneering work of Chen and Gopalakrishnan, using the Bayesian Information Criterion (BIC) with an expanding search window. This paper will aim to identify and address the shortcomings associated with such an approach. The result obtained by the proposed segmentation strategy is evaluated on the 2002 Rich Transcription (RT-02) Evaluation dataset, and a miss rate of 19.47% and a false alarm rate of 16.94% is achieved at the optimal threshold.

Adverse possession and Crown Leasehold in Queensland

The decision of Eckford v Stanbroke Pastoral Co Pty Ltd [2012] QSC 48 ,although a decision refusing summary judgement raises a very important question of the ability to claim adverse possession of a pastoral lease issued in 1956 under the Land Act 1962 (Queensland).Division 5 of Part 6 of the Land Title Act 1994 (Qld) which guarantees registered freehold title expressly deals with the right of adverse possession however, there is no such provision in the present Land Act 1994 unlike s 170 of the Crown Lands Act 1989(NSW) which expressly precludes claims for adverse possession of specified non freehold land. There is no mention of adverse possession in any version of the Queensland Land Acts and only s 6(4) of the Limitation of Actions Act 1974 makes it clear that “the right, title or interest of the Crown” in or to any land is not affected by any adverse possessor.It is against the background that the Court considered the right of an adverse possessor to a Crown lease.

Abundance of Natural Riparian Forests and Tree Plantations in the Amudarya Delta of Uzbekistan and their impact on emissions of soil-borne greenhouse gases

Through a forest inventory in parts of the Amudarya river delta, Central Asia, we assessed the impact of ongoing forest degradation on the emissions of greenhouse gases (GHG) from soils. Interpretation of aerial photographs from 2001, combined with data on forest inventory in 1990 and field survey in 2003 provided comprehensive information about the extent and changes of the natural tugai riparian forests and tree plantations in the delta. The findings show an average annual deforestation rate of almost 1.3% and an even higher rate of land use change from tugai forests to land with only sparse tree cover. These annual rates of deforestation and forest degradation are higher than the global annual forest loss. By 2003, the tugai forest area had drastically decreased to about 60% compared to an inventory in 1990. Significant differences in soil GHG emissions between forest and agricultural land use underscore the impact of the ongoing land use change on the emission of soil-borne GHGs. The conversion of tugai forests into irrigated croplands will release 2.5 t CO2 equivalents per hectare per year due to elevated emissions of N2O and CH4. This demonstrates that the ongoing transformation of tugai forests into agricultural land-use systems did not only lead to a loss of biodiversity and of a unique ecosystem, but substantially impacts the biosphere-atmosphere exchange of GHG and soil C and N turnover processes.

A multi-layered approach for site detection in UAS emergency landing scenarios using geometry-based image segmentation

This paper presents an alternative approach to image segmentation by using the spatial distribution of edge pixels as opposed to pixel intensities. The segmentation is achieved by a multi-layered approach and is intended to find suitable landing areas for an aircraft emergency landing. We combine standard techniques (edge detectors) with novel developed algorithms (line expansion and geometry test) to design an original segmentation algorithm. Our approach removes the dependency on environmental factors that traditionally influence lighting conditions, which in turn have negative impact on pixel-based segmentation techniques. We present test outcomes on realistic visual data collected from an aircraft, reporting on preliminary feedback about the performance of the detection. We demonstrate consistent performances over 97% detection rate.

Automatic object segmentation of unstructured scenes using colour and depth maps

This study presents a segmentation pipeline that fuses colour and depth information to automatically separate objects of interest in video sequences captured from a quadcopter. Many approaches assume that cameras are static with known position, a condition which cannot be preserved in most outdoor robotic applications. In this study, the authors compute depth information and camera positions from a monocular video sequence using structure from motion and use this information as an additional cue to colour for accurate segmentation. The authors model the problem similarly to standard segmentation routines as a Markov random field and perform the segmentation using graph cuts optimisation. Manual intervention is minimised and is only required to determine pixel seeds in the first frame which are then automatically reprojected into the remaining frames of the sequence. The authors also describe an automated method to adjust the relative weights for colour and depth according to their discriminative properties in each frame. Experimental results are presented for two video sequences captured using a quadcopter. The quality of the segmentation is compared to a ground truth and other state-of-the-art methods with consistently accurate results.

GrabCutSFM : how 3D information improves unsupervised object segmentation

In this paper, we present an unsupervised graph cut based object segmentation method using 3D information provided by Structure from Motion (SFM), called Grab- CutSFM. Rather than focusing on the segmentation problem using a trained model or human intervention, our approach aims to achieve meaningful segmentation autonomously with direct application to vision based robotics. Generally, object (foreground) and background have certain discriminative geometric information in 3D space. By exploring the 3D information from multiple views, our proposed method can segment potential objects correctly and automatically compared to conventional unsupervised segmentation using only 2D visual cues. Experiments with real video data collected from indoor and outdoor environments verify the proposed approach.

Nonparametric semantic segmentation for 3D street scenes

In this paper we propose a method to generate a large scale and accurate dense 3D semantic map of street scenes. A dense 3D semantic model of the environment can significantly improve a number of robotic applications such as autonomous driving, navigation or localisation. Instead of using offline trained classifiers for semantic segmentation, our approach employs a data-driven, nonparametric method to parse scenes which easily scale to a large environment and generalise to different scenes. We use stereo image pairs collected from cameras mounted on a moving car to produce dense depth maps which are combined into a global 3D reconstruction using camera poses from stereo visual odometry. Simultaneously, 2D automatic semantic segmentation using a nonparametric scene parsing method is fused into the 3D model. Furthermore, the resultant 3D semantic model is improved with the consideration of moving objects in the scene. We demonstrate our method on the publicly available KITTI dataset and evaluate the performance against manually generated ground truth.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Purpose: Flat-detector, cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. Methods: The rich sources of prior information in IGRT are incorporated into a hidden Markov random field (MRF) model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk (OAR). The voxel labels are estimated using the iterated conditional modes (ICM) algorithm. Results: The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom (CIRS, Inc. model 062). The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. Conclusions: By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. The rich sources of prior information in IGRT are incorporated into a hidden Markov random field model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk. The voxel labels are estimated using iterated conditional modes. The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom. The mean voxel-wise misclassification rate was 6.2\%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Automatic segmentation of choroidal thickness in optical coherence tomography

The assessment of choroidal thickness from optical coherence tomography (OCT) images of the human choroid is an important clinical and research task, since it provides valuable information regarding the eye’s normal anatomy and physiology, and changes associated with various eye diseases and the development of refractive error. Due to the time consuming and subjective nature of manual image analysis, there is a need for the development of reliable objective automated methods of image segmentation to derive choroidal thickness measures. However, the detection of the two boundaries which delineate the choroid is a complicated and challenging task, in particular the detection of the outer choroidal boundary, due to a number of issues including: (i) the vascular ocular tissue is non-uniform and rich in non-homogeneous features, and (ii) the boundary can have a low contrast. In this paper, an automatic segmentation technique based on graph-search theory is presented to segment the inner choroidal boundary (ICB) and the outer choroidal boundary (OCB) to obtain the choroid thickness profile from OCT images. Before the segmentation, the B-scan is pre-processed to enhance the two boundaries of interest and to minimize the artifacts produced by surrounding features. The algorithm to detect the ICB is based on a simple edge filter and a directional weighted map penalty, while the algorithm to detect the OCB is based on OCT image enhancement and a dual brightness probability gradient. The method was tested on a large data set of images from a pediatric (1083 B-scans) and an adult (90 B-scans) population, which were previously manually segmented by an experienced observer. The results demonstrate the proposed method provides robust detection of the boundaries of interest and is a useful tool to extract clinical data.

Predator Crown-of-Thorns Starfish (Acanthaster planci) Outbreak, Mass Mortality of Corals, and Cascading Effects on Reef Fish and Benthic Communities

Outbreaks of the coral-killing seastar Acanthaster planci are intense disturbances that can decimate coral reefs. These events consist of the emergence of large swarms of the predatory seastar that feed on reef-building corals, often leading to widespread devastation of coral populations. While cyclic occurrences of such outbreaks are reported from many tropical reefs throughout the Indo-Pacific, their causes are hotly debated, and the spatio-temporal dynamics of the outbreaks and impacts to reef communities remain unclear. Based on observations of a recent event around the island of Moorea, French Polynesia, we show that Acanthaster outbreaks are methodic, slow-paced, and diffusive biological disturbances. Acanthaster outbreaks on insular reef systems like Moorea's appear to originate from restricted areas confined to the ocean-exposed base of reefs. Elevated Acanthaster densities then progressively spread to adjacent and shallower locations by migrations of seastars in aggregative waves that eventually affect the entire reef system. The directional migration across reefs appears to be a search for prey as reef portions affected by dense seastar aggregations are rapidly depleted of living corals and subsequently left behind. Coral decline on impacted reefs occurs by the sequential consumption of species in the order of Acanthaster feeding preferences. Acanthaster outbreaks thus result in predictable alteration of the coral community structure. The outbreak we report here is among the most intense and devastating ever reported. Using a hierarchical, multi-scale approach, we also show how sessile benthic communities and resident coral-feeding fish assemblages were subsequently affected by the decline of corals. By elucidating the processes involved in an Acanthaster outbreak, our study contributes to comprehending this widespread disturbance and should thus benefit targeted management actions for coral reef ecosystems.

Image segmentation and pose estimation of humans in video

This thesis introduces improved techniques towards automatically estimating the pose of humans from video. It examines a complete workflow to estimating pose, from the segmentation of the raw video stream to extract silhouettes, to using the silhouettes in order to determine the relative orientation of parts of the human body. The proposed segmentation algorithms have improved performance and reduced complexity, while the pose estimation shows superior accuracy during difficult cases of self occlusion.

Transit passenger segmentation using travel regularity mined from Smart Card transactions data

Transit passenger market segmentation enables transit operators to target different classes of transit users to provide customized information and services. The Smart Card (SC) data, from Automated Fare Collection system, facilitates the understanding of multiday travel regularity of transit passengers, and can be used to segment them into identifiable classes of similar behaviors and needs. However, the use of SC data for market segmentation has attracted very limited attention in the literature. This paper proposes a novel methodology for mining spatial and temporal travel regularity from each individual passenger’s historical SC transactions and segments them into four segments of transit users. After reconstructing the travel itineraries from historical SC transactions, the paper adopts the Density-Based Spatial Clustering of Application with Noise (DBSCAN) algorithm to mine travel regularity of each SC user. The travel regularity is then used to segment SC users by an a priori market segmentation approach. The methodology proposed in this paper assists transit operators to understand their passengers and provide them oriented information and services.

The efficacy of Aloe vera, tea tree oil and saliva as first aid treatment for partial thickness burn injuries

Many alternative therapies are used as first aid treatment for burns, despite limited evidence supporting their use. In this study, Aloe vera, saliva and a tea tree oil impregnated dressing (Burnaid) were applied as first aid to a porcine deep dermal contact burn, compared to a control of nothing. After burn creation, the treatments were applied for 20 min and the wounds observed at weekly dressing changes for 6 weeks. Results showed that the alternative treatments did significantly decrease subdermal temperature within the skin during the treatment period. However, they did not decrease the microflora or improve re-epithelialisation, scar strength, scar depth or cosmetic appearance of the scar and cannot be recommended for the first aid treatment of partial thickness burns.