A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpus

We propose a hybrid generative/discriminative framework for semantic parsing which combines the hidden vector state (HVS) model and the hidden Markov support vector machines (HM-SVMs). The HVS model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. The HM-SVMs combine the advantages of the hidden Markov models and the support vector machines. By employing a modified K-means clustering method, a small set of most representative sentences can be automatically selected from an un-annotated corpus. These sentences together with their abstract annotations are used to train an HVS model which could be subsequently applied on the whole corpus to generate semantic parsing results. The most confident semantic parsing results are selected to generate a fully-annotated corpus which is used to train the HM-SVMs. The proposed framework has been tested on the DARPA Communicator Data. Experimental results show that an improvement over the baseline HVS parser has been observed using the hybrid framework. When compared with the HM-SVMs trained from the fully-annotated corpus, the hybrid framework gave a comparable performance with only a small set of lightly annotated sentences. © 2008. Licensed under the Creative Commons.

Photo-sketch synthesis and recognition based on subspace learning

This paper aims to reducing difference between sketches and photos by synthesizing sketches from photos, and vice versa, and then performing sketch-sketch/photo-photo recognition with subspace learning based methods. Pseudo-sketch/pseudo-photo patches are synthesized with embedded hidden Markov model. Because these patches are assembled by averaging their overlapping area in most of the local strategy based methods, which leads to blurring effect to the resulted pseudo-sketch/pseudo-photo, we integrate the patches with image quilting. Experiments are carried out to demonstrate that the proposed method is effective to produce pseudo-sketch/pseudo-photo with high quality and achieve promising recognition results. © 2009.

An intelligent broker agent for energy trading:an MDP approach

This paper details the development and evaluation of AstonTAC, an energy broker that successfully participated in the 2012 Power Trading Agent Competition (Power TAC). AstonTAC buys electrical energy from the wholesale market and sells it in the retail market. The main focus of the paper is on the broker’s bidding strategy in the wholesale market. In particular, it employs Markov Decision Processes (MDP) to purchase energy at low prices in a day-ahead power wholesale market, and keeps energy supply and demand balanced. Moreover, we explain how the agent uses Non-Homogeneous Hidden Markov Model (NHHMM) to forecast energy demand and price. An evaluation and analysis of the 2012 Power TAC finals show that AstonTAC is the only agent that can buy energy at low price in the wholesale market and keep energy imbalance low.

Weakly-constrained codes for suppression of patterning effects in digital communications

We propose weakly-constrained stream and block codes with tunable pattern-dependent statistics and demonstrate that the block code capacity at large block sizes is close to the the prediction obtained from a simple Markov model published earlier. We demonstrate the feasibility of the code by presenting original encoding and decoding algorithms with a complexity log-linear in the block size and with modest table memory requirements. We also show that when such codes are used for mitigation of patterning effects in optical fibre communications, a gain of about 0.5dB is possible under realistic conditions, at the expense of small redundancy 10%). © 2006 IEEE.

DIMUSE: An integrated framework for distributed multimedia system with database management and security support

With the recent explosion in the complexity and amount of digital multimedia data, there has been a huge impact on the operations of various organizations in distinct areas, such as government services, education, medical care, business, entertainment, etc. To satisfy the growing demand of multimedia data management systems, an integrated framework called DIMUSE is proposed and deployed for distributed multimedia applications to offer a full scope of multimedia related tools and provide appealing experiences for the users. This research mainly focuses on video database modeling and retrieval by addressing a set of core challenges. First, a comprehensive multimedia database modeling mechanism called Hierarchical Markov Model Mediator (HMMM) is proposed to model high dimensional media data including video objects, low-level visual/audio features, as well as historical access patterns and frequencies. The associated retrieval and ranking algorithms are designed to support not only the general queries, but also the complicated temporal event pattern queries. Second, system training and learning methodologies are incorporated such that user interests are mined efficiently to improve the retrieval performance. Third, video clustering techniques are proposed to continuously increase the searching speed and accuracy by architecting a more efficient multimedia database structure. A distributed video management and retrieval system is designed and implemented to demonstrate the overall performance. The proposed approach is further customized for a mobile-based video retrieval system to solve the perception subjectivity issue by considering individual user's profile. Moreover, to deal with security and privacy issues and concerns in distributed multimedia applications, DIMUSE also incorporates a practical framework called SMARXO, which supports multilevel multimedia security control. SMARXO efficiently combines role-based access control (RBAC), XML and object-relational database management system (ORDBMS) to achieve the target of proficient security control. A distributed multimedia management system named DMMManager (Distributed MultiMedia Manager) is developed with the proposed framework DEMUR; to support multimedia capturing, analysis, retrieval, authoring and presentation in one single framework.

Forecasting future prevalence of type 2 diabetes mellitus in Syria

Background Type 2 diabetes mellitus (T2DM) is increasingly becoming a major public health problem worldwide. Estimating the future burden of diabetes is instrumental to guide the public health response to the epidemic. This study aims to project the prevalence of T2DM among adults in Syria over the period 2003–2022 by applying a modelling approach to the country’s own data. Methods Future prevalence of T2DM in Syria was estimated among adults aged 25 years and older for the period 2003–2022 using the IMPACT Diabetes Model (a discrete-state Markov model). Results According to our model, the prevalence of T2DM in Syria is projected to double in the period between 2003 and 2022 (from 10% to 21%). The projected increase in T2DM prevalence is higher in men (148%) than in women (93%). The increase in prevalence of T2DM is expected to be most marked in people younger than 55 years especially the 25–34 years age group. Conclusions The future projections of T2DM in Syria put it amongst countries with the highest levels of T2DM worldwide. It is estimated that by 2022 approximately a fifth of the Syrian population aged 25 years and older will have T2DM.

Gaussian Process Kernels for Cross-Spectrum Analysis in Electrophysiological Time Series

Multi-output Gaussian processes provide a convenient framework for multi-task problems. An illustrative and motivating example of a multi-task problem is multi-region electrophysiological time-series data, where experimentalists are interested in both power and phase coherence between channels. Recently, the spectral mixture (SM) kernel was proposed to model the spectral density of a single task in a Gaussian process framework. This work develops a novel covariance kernel for multiple outputs, called the cross-spectral mixture (CSM) kernel. This new, flexible kernel represents both the power and phase relationship between multiple observation channels. The expressive capabilities of the CSM kernel are demonstrated through implementation of 1) a Bayesian hidden Markov model, where the emission distribution is a multi-output Gaussian process with a CSM covariance kernel, and 2) a Gaussian process factor analysis model, where factor scores represent the utilization of cross-spectral neural circuits. Results are presented for measured multi-region electrophysiological data.

Human behaviour recognition in data-scarce domains

This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an unordered bag. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao–Blackwellised Particle Filter. Simulated annealing is used to identify pairs of agents involved in multi-agent activity. We validate our framework using the benchmarked PETS 2006 video surveillance dataset and our own sequences, and achieve a mean recognition F-Score of 0.82. Our approach achieves a mean improvement of 17% over a Hidden Markov Model baseline.

The Coxian Phase-type distribution with a Hidden Node

Healthcare providers are under increased pressure to ensure that the quality
of care delivered to patients are off the highest standard. Modelling quality of
care is difficult due to the many ways of defining it. This paper introduces a potential
model which could be used to take quality of care into account when modelling
length of stay. The Coxian phase-type distribution is used to model length of stay
and quality of care incorporated into this using a Hidden Markov model. This model
is then applied to

Legionella pneumophila secretes a mitochondrial carrier protein during infection

The Mitochondrial Carrier Family (MCF) is a signature group of integral membrane proteins that transport metabolites across the mitochondrial inner membrane in eukaryotes. MCF proteins are characterized by six transmembrane segments that assemble to form a highly-selective channel for metabolite transport. We discovered a novel MCF member, termed Legionellanucleotide carrier Protein (LncP), encoded in the genome of Legionella pneumophila, the causative agent of Legionnaire's disease. LncP was secreted via the bacterial Dot/Icm type IV secretion system into macrophages and assembled in the mitochondrial inner membrane. In a yeast cellular system, LncP induced a dominant-negative phenotype that was rescued by deleting an endogenous ATP carrier. Substrate transport studies on purified LncP reconstituted in liposomes revealed that it catalyzes unidirectional transport and exchange of ATP transport across membranes, thereby supporting a role for LncP as an ATP transporter. A hidden Markov model revealed further MCF proteins in the intracellular pathogens, Legionella longbeachae and Neorickettsia sennetsu, thereby challenging the notion that MCF proteins exist exclusively in eukaryotic organisms.

IntelliChair: a non-intrusive sitting posture and sitting activity recognition system

Current Ambient Intelligence and Intelligent Environment research focuses on the interpretation of a subject’s behaviour at the activity level by logging the Activity of Daily Living (ADL) such as eating, cooking, etc. In general, the sensors employed (e.g. PIR sensors, contact sensors) provide low resolution information. Meanwhile, the expansion of ubiquitous computing allows researchers to gather additional information from different types of sensor which is possible to improve activity analysis. Based on the previous research about sitting posture detection, this research attempts to further analyses human sitting activity. The aim of this research is to use non-intrusive low cost pressure sensor embedded chair system to recognize a subject’s activity by using their detected postures. There are three steps for this research, the first step is to find a hardware solution for low cost sitting posture detection, second step is to find a suitable strategy of sitting posture detection and the last step is to correlate the time-ordered sitting posture sequences with sitting activity. The author initiated a prototype type of sensing system called IntelliChair for sitting posture detection. Two experiments are proceeded in order to determine the hardware architecture of IntelliChair system. The prototype looks at the sensor selection and integration of various sensor and indicates the best for a low cost, non-intrusive system. Subsequently, this research implements signal process theory to explore the frequency feature of sitting posture, for the purpose of determining a suitable sampling rate for IntelliChair system. For second and third step, ten subjects are recruited for the sitting posture data and sitting activity data collection. The former dataset is collected byasking subjects to perform certain pre-defined sitting postures on IntelliChair and it is used for posture recognition experiment. The latter dataset is collected by asking the subjects to perform their normal sitting activity routine on IntelliChair for four hours, and the dataset is used for activity modelling and recognition experiment. For the posture recognition experiment, two Support Vector Machine (SVM) based classifiers are trained (one for spine postures and the other one for leg postures), and their performance evaluated. Hidden Markov Model is utilized for sitting activity modelling and recognition in order to establish the selected sitting activities from sitting posture sequences.2. After experimenting with possible sensors, Force Sensing Resistor (FSR) is selected as the pressure sensing unit for IntelliChair. Eight FSRs are mounted on the seat and back of a chair to gather haptic (i.e., touch-based) posture information. Furthermore, the research explores the possibility of using alternative non-intrusive sensing technology (i.e. vision based Kinect Sensor from Microsoft) and find out the Kinect sensor is not reliable for sitting posture detection due to the joint drifting problem. A suitable sampling rate for IntelliChair is determined according to the experiment result which is 6 Hz. The posture classification performance shows that the SVM based classifier is robust to “familiar” subject data (accuracy is 99.8% with spine postures and 99.9% with leg postures). When dealing with “unfamiliar” subject data, the accuracy is 80.7% for spine posture classification and 42.3% for leg posture classification. The result of activity recognition achieves 41.27% accuracy among four selected activities (i.e. relax, play game, working with PC and watching video). The result of this thesis shows that different individual body characteristics and sitting habits influence both sitting posture and sitting activity recognition. In this case, it suggests that IntelliChair is suitable for individual usage but a training stage is required.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Impact of radiofrequency ablation for patients with varicose veins on the budget of the German statutory health insurance system

Objectives: In contrast to other countries, surgery still represents the common invasive treatment for varicose veins in Germany. However, radiofrequency ablation, e.g. ClosureFast, becomes more and more popular in other countries due to potential better results and reduced side effects. This treatment option may cause less follow-up costs and is a more convenient procedure for patients, which could justify an introduction in the statutory benefits catalogue. Therefore, we aim at calculating the budget impact of a general reimbursement of ClosureFast in Germany. Methods: To assess the budget impact of including ClosureFast in the German statutory benefits catalogue, we developed a multi-cohort Markov model and compared the costs of a “World with ClosureFast” with a “World without ClosureFast” over a time horizon of five years. To address the uncertainty of input parameters, we conducted three different types of sensitivity analysis (one-way, scenario, probabilistic). Results: In the Base Case scenario, the introduction of the ClosureFast system for the treatment of varicose veins saves costs of about 19.1 Mio. € over a time horizon of five years in Germany. However, the results scatter in the sensitivity analyses due to limited evidence of some key input parameters. Conclusions: Results of the budget impact analysis indicate that a general reimbursement of ClosureFast has the potential to be cost-saving in the German Statutory Health Insurance.

Cost-effectiveness analysis of apixaban compared to low-molecular-weight heparins and vitamin k antagonists for treatment and secondary prevention of venous thromboembolism

Objective: Cost-effectiveness analysis of a 6-month treatment of apixaban (10 mg/12h, first 7 days; 5 mg/12h afterwards) for the treatment of the first event of venous thromboembolism (VTE) and prevention of recurrences, versus low-molecular-weight heparins/vitamin K antagonists treatment (LMWH/VKA). Material and methods: A lifetime Markov model with 13 health states was used for describing the course of the disease. Efficacy and safety data were obtained from AMPLIFY and AMPLIFY-EXT clinical trials; health outcomes were measured as life years gained (LYG) and quality-adjusted life years (QALY). The chosen perspective of this analysis has been the Spanish National Health System (NHS). Drugs, management of VTE and complications costs were obtained from several Spanish data sources (€, 2014). A 3% discount rate was applied to health outcomes and costs. Univariate and probabilistic sensitivity analyses (SA) were performed in order to assess the robustness of the results. Results: Apixaban was the most effective therapy with 7.182 LYG and 5.865 QALY, versus 7.160 LYG and 5.838 QALYs with LMWH/VKA. Furthermore, apixaban had a lower total cost (€13,374.70 vs €13,738.30). Probabilistic SA confirmed dominance of apixaban (led to better health outcomes with less associated costs) in 89% of the simulations. Conclusions: Apixaban 5 mg/12h versus LMWH/VKA was an efficient therapeutic strategy for the treatment and prevention of recurrences of VTE from the NHS perspective.

SARASOM: a supervised architecture based on the recurrent associative SOM

We present and evaluate a novel supervised recurrent neural network architecture, the SARASOM, based on the associative self-organizing map. The performance of the SARASOM is evaluated and compared with the Elman network as well as with a hidden Markov model (HMM) in a number of prediction tasks using sequences of letters, including some experiments with a reduced lexicon of 15 words. The results were very encouraging with the SARASOM learning better and performing with better accuracy than both the Elman network and the HMM.