Marker selection by Akaike information criterion and Bayesian information criterion

We carried out a discriminant analysis with identity by descent (IBD) at each marker as inputs, and the sib pair type (affected-affected versus affected-unaffected) as the output. Using simple logistic regression for this discriminant analysis, we illustrate the importance of comparing models with different number of parameters. Such model comparisons are best carried out using either the Akaike information criterion (AIC) or the Bayesian information criterion (BIC). When AIC (or BIC) stepwise variable selection was applied to the German Asthma data set, a group of markers were selected which provide the best fit to the data (assuming an additive effect). Interestingly, these 25-26 markers were not identical to those with the highest (in magnitude) single-locus lod scores.

Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

Detecting rare events using Kullback-Leibler divergence: A weakly supervised approach

Video surveillance infrastructure has been widely installed in public places for security purposes. However, live video feeds are typically monitored by human staff, making the detection of important events as they occur difficult. As such, an expert system that can automatically detect events of interest in surveillance footage is highly desirable. Although a number of approaches have been proposed, they have significant limitations: supervised approaches, which can detect a specific event, ideally require a large number of samples with the event spatially and temporally localised; while unsupervised approaches, which do not require this demanding annotation, can only detect whether an event is abnormal and not specific event types. To overcome these problems, we formulate a weakly-supervised approach using Kullback-Leibler (KL) divergence to detect rare events. The proposed approach leverages the sparse nature of the target events to its advantage, and we show that this data imbalance guarantees the existence of a decision boundary to separate samples that contain the target event from those that do not. This trait, combined with the coarse annotation used by weakly supervised learning (that only indicates approximately when an event occurs), greatly reduces the annotation burden while retaining the ability to detect specific events. Furthermore, the proposed classifier requires only a decision threshold, simplifying its use compared to other weakly supervised approaches. We show that the proposed approach outperforms state-of-the-art methods on a popular real-world traffic surveillance dataset, while preserving real time performance.

Computational methods for Bayesian model choice

In this note, we shortly survey some recent approaches on the approximation of the Bayes factor used in Bayesian hypothesis testing and in Bayesian model choice. In particular, we reassess importance sampling, harmonic mean sampling, and nested sampling from a unified perspective.

Adaptive frequency scaled wavelet packet decomposition for frog call classification

Environmental changes have put great pressure on biological systems leading to the rapid decline of biodiversity. To monitor this change and protect biodiversity, animal vocalizations have been widely explored by the aid of deploying acoustic sensors in the field. Consequently, large volumes of acoustic data are collected. However, traditional manual methods that require ecologists to physically visit sites to collect biodiversity data are both costly and time consuming. Therefore it is essential to develop new semi-automated and automated methods to identify species in automated audio recordings. In this study, a novel feature extraction method based on wavelet packet decomposition is proposed for frog call classification. After syllable segmentation, the advertisement call of each frog syllable is represented by a spectral peak track, from which track duration, dominant frequency and oscillation rate are calculated. Then, a k-means clustering algorithm is applied to the dominant frequency, and the centroids of clustering results are used to generate the frequency scale for wavelet packet decomposition (WPD). Next, a new feature set named adaptive frequency scaled wavelet packet decomposition sub-band cepstral coefficients is extracted by performing WPD on the windowed frog calls. Furthermore, the statistics of all feature vectors over each windowed signal are calculated for producing the final feature set. Finally, two well-known classifiers, a k-nearest neighbour classifier and a support vector machine classifier, are used for classification. In our experiments, we use two different datasets from Queensland, Australia (18 frog species from commercial recordings and field recordings of 8 frog species from James Cook University recordings). The weighted classification accuracy with our proposed method is 99.5% and 97.4% for 18 frog species and 8 frog species respectively, which outperforms all other comparable methods.

Activity recognition using binary tree SVM

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.

Combat sports analytics: Boxing punch classification using overhead depth imagery

In competitive combat sporting environments like boxing, the statistics on a boxer's performance, including the amount and type of punches thrown, provide a valuable source of data and feedback which is routinely used for coaching and performance improvement purposes. This paper presents a robust framework for the automatic classification of a boxer's punches. Overhead depth imagery is employed to alleviate challenges associated with occlusions, and robust body-part tracking is developed for the noisy time-of-flight sensors. Punch recognition is addressed through both a multi-class SVM and Random Forest classifiers. A coarse-to-fine hierarchical SVM classifier is presented based on prior knowledge of boxing punches. This framework has been applied to shadow boxing image sequences taken at the Australian Institute of Sport with 8 elite boxers. Results demonstrate the effectiveness of the proposed approach, with the hierarchical SVM classifier yielding a 96% accuracy, signifying its suitability for analysing athletes punches in boxing bouts.

Statistical analysis of spectral data: A methodology for designing an intelligent monitoring system for the diabetic foot

Early detection of (pre-)signs of ulceration on a diabetic foot is valuable for clinical practice. Hyperspectral imaging is a promising technique for detection and classification of such (pre-)signs. However, the number of the spectral bands should be limited to avoid overfitting, which is critical for pixel classification with hyperspectral image data. The goal was to design a detector/classifier based on spectral imaging (SI) with a small number of optical bandpass filters. The performance and stability of the design were also investigated. The selection of the bandpass filters boils down to a feature selection problem. A dataset was built, containing reflectance spectra of 227 skin spots from 64 patients, measured with a spectrometer. Each skin spot was annotated manually by clinicians as "healthy" or a specific (pre-)sign of ulceration. Statistical analysis on the data set showed the number of required filters is between 3 and 7, depending on additional constraints on the filter set. The stability analysis revealed that shot noise was the most critical factor affecting the classification performance. It indicated that this impact could be avoided in future SI systems with a camera sensor whose saturation level is higher than 106, or by postimage processing.

Blockade of PD-1/PD-L1 promotes adoptive T-Cell immunotherapy in a tolerogenic environment

Adoptive cellular immunotherapy using in vitro expanded CD8+ T cells shows promise for tumour immunotherapy but is limited by eventual loss of function of the transferred T cells through factors that likely include inactivation by tolerogenic dendritic cells (DC). The coinhibitory receptor programmed death-1 (PD-1), in addition to controlling T-cell responsiveness at effector sites in malignancies and chronic viral diseases is an important modulator of dendritic cell-induced tolerance in naive T cell populations. The most potent therapeutic capacity amongst CD8+ T cells appears to lie within Tcm or Tcm-like cells but memory T cells express elevated levels of PD-1. Based on established trafficking patterns for Tcm it is likely Tcm-like cells interact with lymphoid-tissue DC that present tumour-derived antigens and may be inherently tolerogenic to develop therapeutic effector function. As little is understood of the effect of PD-1/PD-L1 blockade on Tcm-like CD8+ T cells, particularly in relation to inactivation by DC, we explored the effects of PD-1/PD-L1 blockade in a mouse model where resting DC tolerise effector and memory CD8+ T cells. Blockade of PD-1/PDL1 promoted effector differentiation of adoptively-transferred Tcm-phenotype cells interacting with tolerising DC. In tumour-bearing mice with tolerising DC, effector activity was increased in both lymphoid tissues and the tumour-site and anti-tumour activity was promoted. Our findings suggest PD-1/PD-L1 blockade may be a useful adjunct for adoptive immunotherapy by promoting effector differentiation in the host of transferred Tcmlike cells. © 2015 Blake et al.

Antigen-specific CD4 cells assist CD8 T-effector cells in eliminating keratinocytes

Keratinocytes expressing tumor or viral antigens can be eliminated by antigen-primed CD8 cytotoxic T cells. CD4 T-helper cells help induction of CD8 cytotoxic T cells from naive precursors and generation of CD8 T-cell memory. In this study, we show, unexpectedly, that CD4 cells are also required to assist primed CD8 effector T cells in rejection of skin expressing human growth hormone, a neo-self-antigen, in keratinocytes. The requirement for CD4 cells can be substituted by CD40 costimulation. Rejection of skin expressing ovalbumin (OVA), a non-self-antigen, by primed CD8 cytotoxic T cells can in contrast occur without help from antigen-specific CD4 T cells. However, rejection of OVA expressing keratinocytes is helped by antigen-specific CD4 T cells if only low numbers of primed or naive OVA-specific CD8 T cells are available. Effective immunotherapy directed at antigens expressed in squamous cancer may therefore be facilitated by induction of tumor antigen-specific CD4 helper T cells, as well as cytotoxic CD8 T cells.

Steady-state dendritic cells expressing cognate antigen terminate memory CD8+ T-cell responses

Antigen stimulation of naive T cells in conjunction with strong costimulatory signals elicits the generation of effector and memory populations. Such terminal differentiation transforms naive T cells capable of differentiating along several terminal pathways in response to pertinent environmental cues into cells that have lost developmental plasticity and exhibit heightened responsiveness. Because these cells exhibit little or no need for the strong costimulatory signals required for full activation of naive T cells, it is generally considered memory and effector T cells are released from the capacity to be inactivated. Here, we show that steadystate dendritic cells constitutively presenting an endogenously expressed antigen inactivate fully differentiated memory and effector CD8+ T cells in vivo through deletion and inactivation. These findings indicate that fully differentiated effector and memory T cells exhibit a previously unappreciated level of plasticity and provide insight into how memory and effector T-cell populations may be regulated. © 2008 by The American Society of Hematology.

Pheo-type: A diagnostic gene-expression assay for the classification of pheochromocytoma and paraganglioma

Context: Pheochromocytomas and paragangliomas (PPGLs) are heritable neoplasms that can be classified into gene-expression subtypes corresponding to their underlying specific genetic drivers. Objective: This study aimed to develop a diagnostic and research tool (Pheo-type) capable of classifying PPGL tumors into gene-expression subtypes that could be used to guide and interpret genetic testing, determine surveillance programs, and aid in elucidation of PPGL biology. Design: A compendium of published microarray data representing 205 PPGL tumors was used for the selection of subtype-specific genes that were then translated to the Nanostring gene-expression platform. A support vector machine was trained on the microarray dataset and then tested on an independent Nanostring dataset representing 38 familial and sporadic cases of PPGL of known genotype (RET, NF1, TMEM127, MAX, HRAS, VHL, and SDHx). Different classifier models involving between three and six subtypes were compared for their discrimination potential. Results: A gene set of 46 genes and six endogenous controls was selected representing six known PPGL subtypes; RTK1–3 (RET, NF1, TMEM127, and HRAS), MAX-like, VHL, and SDHx. Of 38 test cases, 34 (90%) were correctly predicted to six subtypes based on the known genotype to gene-expression subtype association. Removal of the RTK2 subtype from training, characterized by an admixture of tumor and normal adrenal cortex, improved the classification accuracy (35/38). Consolidation of RTK and pseudohypoxic PPGL subtypes to four- and then three-class architectures improved the classification accuracy for clinical application. Conclusions: The Pheo-type gene-expression assay is a reliable method for predicting PPGL genotype using routine diagnostic tumor samples.

Automated feature engineering for HTTP tunnel detection

Generating discriminative input features is a key requirement for achieving highly accurate classifiers. The process of generating features from raw data is known as feature engineering and it can take significant manual effort. In this paper we propose automated feature engineering to derive a suite of additional features from a given set of basic features with the aim of both improving classifier accuracy through discriminative features, and to assist data scientists through automation. Our implementation is specific to HTTP computer network traffic. To measure the effectiveness of our proposal, we compare the performance of a supervised machine learning classifier built with automated feature engineering versus one using human-guided features. The classifier addresses a problem in computer network security, namely the detection of HTTP tunnels. We use Bro to process network traffic into base features and then apply automated feature engineering to calculate a larger set of derived features. The derived features are calculated without favour to any base feature and include entropy, length and N-grams for all string features, and counts and averages over time for all numeric features. Feature selection is then used to find the most relevant subset of these features. Testing showed that both classifiers achieved a detection rate above 99.93% at a false positive rate below 0.01%. For our datasets, we conclude that automated feature engineering can provide the advantages of increasing classifier development speed and reducing development technical difficulties through the removal of manual feature engineering. These are achieved while also maintaining classification accuracy.

Using multi-label classification for acoustic pattern detection and assisting bird species surveys

Acoustics is a rich source of environmental information that can reflect the ecological dynamics. To deal with the escalating acoustic data, a variety of automated classification techniques have been used for acoustic patterns or scene recognition, including urban soundscapes such as streets and restaurants; and natural soundscapes such as raining and thundering. It is common to classify acoustic patterns under the assumption that a single type of soundscapes present in an audio clip. This assumption is reasonable for some carefully selected audios. However, only few experiments have been focused on classifying simultaneous acoustic patterns in long-duration recordings. This paper proposes a binary relevance based multi-label classification approach to recognise simultaneous acoustic patterns in one-minute audio clips. By utilising acoustic indices as global features and multilayer perceptron as a base classifier, we achieve good classification performance on in-the-field data. Compared with single-label classification, multi-label classification approach provides more detailed information about the distributions of various acoustic patterns in long-duration recordings. These results will merit further biodiversity investigations, such as bird species surveys.

Afatinib versus gefitinib as first-line treatment of patients with EGFR mutation-positive non-small-cell lung cancer (LUX-Lung 7): a phase 2B, open-label, randomised controlled trial

Background The irreversible ErbB family blocker afatinib and the reversible EGFR tyrosine kinase inhibitor gefitinib are approved for first-line treatment of EGFR mutation-positive non-small-cell lung cancer (NSCLC). We aimed to compare the efficacy and safety of afatinib and gefitinib in this setting. Methods This multicentre, international, open-label, exploratory, randomised controlled phase 2B trial (LUX-Lung 7) was done at 64 centres in 13 countries. Treatment-naive patients with stage IIIB or IV NSCLC and a common EGFR mutation (exon 19 deletion or Leu858Arg) were randomly assigned (1:1) to receive afatinib (40 mg per day) or gefitinib (250 mg per day) until disease progression, or beyond if deemed beneficial by the investigator. Randomisation, stratified by EGFR mutation type and status of brain metastases, was done centrally using a validated number generating system implemented via an interactive voice or web-based response system with a block size of four. Clinicians and patients were not masked to treatment allocation; independent review of tumour response was done in a blinded manner. Coprimary endpoints were progression-free survival by independent central review, time-to-treatment failure, and overall survival. Efficacy analyses were done in the intention-to-treat population and safety analyses were done in patients who received at least one dose of study drug. This ongoing study is registered with ClinicalTrials.gov, number NCT01466660. Findings Between Dec 13, 2011, and Aug 8, 2013, 319 patients were randomly assigned (160 to afatinib and 159 to gefitinib). Median follow-up was 27·3 months (IQR 15·3–33·9). Progression-free survival (median 11·0 months [95% CI 10·6–12·9] with afatinib vs 10·9 months [9·1–11·5] with gefitinib; hazard ratio [HR] 0·73 [95% CI 0·57–0·95], p=0·017) and time-to-treatment failure (median 13·7 months [95% CI 11·9–15·0] with afatinib vs 11·5 months [10·1–13·1] with gefitinib; HR 0·73 [95% CI 0·58–0·92], p=0·0073) were significantly longer with afatinib than with gefitinib. Overall survival data are not mature. The most common treatment-related grade 3 or 4 adverse events were diarrhoea (20 [13%] of 160 patients given afatinib vs two [1%] of 159 given gefitinib) and rash or acne (15 [9%] patients given afatinib vs five [3%] of those given gefitinib) and liver enzyme elevations (no patients given afatinib vs 14 [9%] of those given gefitinib). Serious treatment-related adverse events occurred in 17 (11%) patients in the afatinib group and seven (4%) in the gefitinib group. Ten (6%) patients in each group discontinued treatment due to drug-related adverse events. 15 (9%) fatal adverse events occurred in the afatinib group and ten (6%) in the gefitinib group. All but one of these deaths were considered unrelated to treatment; one patient in the gefitinib group died from drug-related hepatic and renal failure. Interpretation Afatinib significantly improved outcomes in treatment-naive patients with EGFR-mutated NSCLC compared with gefitinib, with a manageable tolerability profile. These data are potentially important for clinical decision making in this patient population.