Learning the Kernel Matrix with Semi-Definite Programming

Kernel-based learning algorithms work by embedding the data into a Euclidean space, and then searching for linear relations among the embedded data points. The embedding is performed implicitly, by specifying the inner products between each pair of points in the embedding space. This information is contained in the so-called kernel matrix, a symmetric and positive definite matrix that encodes the relative positions of all points. Specifying this matrix amounts to specifying the geometry of the embedding space and inducing a notion of similarity in the input space -- classical model selection problems in machine learning. In this paper we show how the kernel matrix can be learned from data via semi-definite programming (SDP) techniques. When applied to a kernel matrix associated with both training and test data this gives a powerful transductive algorithm -- using the labelled part of the data one can learn an embedding also for the unlabelled part. The similarity between test points is inferred from training points and their labels. Importantly, these learning problems are convex, so we obtain a method for learning both the model class and the function without local minima. Furthermore, this approach leads directly to a convex method to learn the 2-norm soft margin parameter in support vector machines, solving another important open problem. Finally, the novel approach presented in the paper is supported by positive empirical results.

SwarmPS: Rapid, semi-automated single particle selection software

Single particle analysis (SPA) coupled with high-resolution electron cryo-microscopy is emerging as a powerful technique for the structure determination of membrane protein complexes and soluble macromolecular assemblies. Current estimates suggest that ∼104–105 particle projections are required to attain a 3 Å resolution 3D reconstruction (symmetry dependent). Selecting this number of molecular projections differing in size, shape and symmetry is a rate-limiting step for the automation of 3D image reconstruction. Here, we present SwarmPS, a feature rich GUI based software package to manage large scale, semi-automated particle picking projects. The software provides cross-correlation and edge-detection algorithms. Algorithm-specific parameters are transparently and automatically determined through user interaction with the image, rather than by trial and error. Other features include multiple image handling (∼102), local and global particle selection options, interactive image freezing, automatic particle centering, and full manual override to correct false positives and negatives. SwarmPS is user friendly, flexible, extensible, fast, and capable of exporting boxed out projection images, or particle coordinates, compatible with downstream image processing suites.

Leveraging Web 2.0 data for scalable semi-supervised learning of domain-specific sentiment lexicons

Since manually constructing domain-specific sentiment lexicons is extremely time consuming and it may not even be feasible for domains where linguistic expertise is not available. Research on the automatic construction of domain-specific sentiment lexicons has become a hot topic in recent years. The main contribution of this paper is the illustration of a novel semi-supervised learning method which exploits both term-to-term and document-to-term relations hidden in a corpus for the construction of domain specific sentiment lexicons. More specifically, the proposed two-pass pseudo labeling method combines shallow linguistic parsing and corpusbase statistical learning to make domain-specific sentiment extraction scalable with respect to the sheer volume of opinionated documents archived on the Internet these days. Another novelty of the proposed method is that it can utilize the readily available user-contributed labels of opinionated documents (e.g., the user ratings of product reviews) to bootstrap the performance of sentiment lexicon construction. Our experiments show that the proposed method can generate high quality domain-specific sentiment lexicons as directly assessed by human experts. Moreover, the system generated domain-specific sentiment lexicons can improve polarity prediction tasks at the document level by 2:18% when compared to other well-known baseline methods. Our research opens the door to the development of practical and scalable methods for domain-specific sentiment analysis.

A semi-local method for iterative depth-map refinement

We present an iterative hierarchical algorithm for multi-view stereo. The algorithm attempts to utilise as much contextual information as is available to compute highly accurate and robust depth maps. There are three novel aspects to the approach: 1) firstly we incrementally improve the depth fidelity as the algorithm progresses through the image pyramid; 2) secondly we show how to incorporate visual hull information (when available) to constrain depth searches; and 3) we show how to simultaneously enforce the consistency of the depth-map by continual comparison with neighbouring depth-maps. We show that this approach produces highly accurate depth-maps and, since it is essentially a local method, is both extremely fast and simple to implement.

Molecular structure of the phosphate mineral brazilianite NaAl3(PO4)2(OH)4 : a semi precious jewel

The phosphate mineral brazilianite NaAl3(PO4)2(OH)4 is a semi precious jewel. There are almost no minerals apart from brazilianite which are used in jewellery. Vibrational spectroscopy was used to characterize the mol. structure of brazilianite. Brazilianite is composed of chains of edge-sharing Al-O octahedra linked by P-O tetrahedra, with Na located in cavities of the framework. An intense sharp Raman band at 1019 cm-1 is attributed to the PO43- sym. stretching mode. Raman bands at 973 and 988 cm-1 are assigned to the stretching vibrations of the HOPO33- units. The IR spectra compliment the Raman spectra but show greater complexity. Multiple Raman bands are obsd. in the PO43- and HOPO33- bending region. This observation implies that both phosphate and hydrogen phosphate units are involved in the structure. Raman OH stretching vibrations are found at 3249, 3417 and 3472 cm-1. These peaks show that the OH units are not equiv. in the brazilianite structure. Vibrational spectroscopy is useful for increasing the knowledge of the mol. structure of brazilianite.

Three carrier ambiguity resolution : distance-independent performance demonstrated using semi-generated triple frequency GPS signals

In spite of significant research in the development of efficient algorithms for three carrier ambiguity resolution, full performance potential of the additional frequency signals cannot be demonstrated effectively without actual triple frequency data. In addition, all the proposed algorithms showed their difficulties in reliable resolution of the medium-lane and narrow-lane ambiguities in different long-range scenarios. In this contribution, we will investigate the effects of various distance-dependent biases, identifying the tropospheric delay to be the key limitation for long-range three carrier ambiguity resolution. In order to achieve reliable ambiguity resolution in regional networks with the inter-station distances of hundreds of kilometers, a new geometry-free and ionosphere-free model is proposed to fix the integer ambiguities of the medium-lane or narrow-lane observables over just several minutes without distance constraint. Finally, the semi-simulation method is introduced to generate the third frequency signals from dual-frequency GPS data and experimentally demonstrate the research findings of this paper.

Prediction of the wash-off of traffic related semi- and non-volatile organic compounds from urban roads under climate change influenced rainfall characteristics

Traffic generated semi and non volatile organic compounds (SVOCs and NVOCs) pose a serious threat to human and ecosystem health when washed off into receiving water bodies by stormwater. Climate change influenced rainfall characteristics makes the estimation of these pollutants in stormwater quite complex. The research study discussed in the paper developed a prediction framework for such pollutants under the dynamic influence of climate change on rainfall characteristics. It was established through principal component analysis (PCA) that the intensity and durations of low to moderate rain events induced by climate change mainly affect the wash-off of SVOCs and NVOCs from urban roads. The study outcomes were able to overcome the limitations of stringent laboratory preparation of calibration matrices by extracting uncorrelated underlying factors in the data matrices through systematic application of PCA and factor analysis (FA). Based on the initial findings from PCA and FA, the framework incorporated orthogonal rotatable central composite experimental design to set up calibration matrices and partial least square regression to identify significant variables in predicting the target SVOCs and NVOCs in four particulate fractions ranging from >300-1 μm and one dissolved fraction of <1 μm. For the particulate fractions range >300-1 μm, similar distributions of predicted and observed concentrations of the target compounds from minimum to 75th percentile were achieved. The inter-event coefficient of variations for particulate fractions of >300-1 μm were 5% to 25%. The limited solubility of the target compounds in stormwater restricted the predictive capacity of the proposed method for the dissolved fraction of <1 μm.

Semantic service discovery in the service ecosystem

Electronic services are a leitmotif in ‘hot’ topics like Software as a Service, Service Oriented Architecture (SOA), Service oriented Computing, Cloud Computing, application markets and smart devices. We propose to consider these in what has been termed the Service Ecosystem (SES). The SES encompasses all levels of electronic services and their interaction, with human consumption and initiation on its periphery in much the same way the ‘Web’ describes a plethora of technologies that eventuate to connect information and expose it to humans. Presently, the SES is heterogeneous, fragmented and confined to semi-closed systems. A key issue hampering the emergence of an integrated SES is Service Discovery (SD). A SES will be dynamic with areas of structured and unstructured information within which service providers and ‘lay’ human consumers interact; until now the two are disjointed, e.g., SOA-enabled organisations, industries and domains are choreographed by domain experts or ‘hard-wired’ to smart device application markets and web applications. In a SES, services are accessible, comparable and exchangeable to human consumers closing the gap to the providers. This requires a new SD with which humans can discover services transparently and effectively without special knowledge or training. We propose two modes of discovery, directed search following an agenda and explorative search, which speculatively expands knowledge of an area of interest by means of categories. Inspired by conceptual space theory from cognitive science, we propose to implement the modes of discovery using concepts to map a lay consumer’s service need to terminologically sophisticated descriptions of services. To this end, we reframe SD as an information retrieval task on the information attached to services, such as, descriptions, reviews, documentation and web sites - the Service Information Shadow. The Semantic Space model transforms the shadow's unstructured semantic information into a geometric, concept-like representation. We introduce an improved and extended Semantic Space including categorization calling it the Semantic Service Discovery model. We evaluate our model with a highly relevant, service related corpus simulating a Service Information Shadow including manually constructed complex service agendas, as well as manual groupings of services. We compare our model against state-of-the-art information retrieval systems and clustering algorithms. By means of an extensive series of empirical evaluations, we establish optimal parameter settings for the semantic space model. The evaluations demonstrate the model’s effectiveness for SD in terms of retrieval precision over state-of-the-art information retrieval models (directed search) and the meaningful, automatic categorization of service related information, which shows potential to form the basis of a useful, cognitively motivated map of the SES for exploratory search.

Visible and near infrared spectroscopy of Hayabusa re-entry using semi-autonomous tracking

A ground-based tracking camera and co-aligned slit-less spectrograph were used to measure the spectral signature of visible radiation emitted from the Hayabusa capsule as it entered into the Earth's atmosphere in June 2010. Good quality spectra were obtained that showed the presence of radiation from the heat shield of the vehicle and the shock-heated air in front of the vehicle. An analysis of the black body nature of the radiation concluded that the peak average temperature of the surface was about (3100±100) K.

Semi-parametric forecasting of realized volatility

Forecasts generated by time series models traditionally place greater weight on more recent observations. This paper develops an alternative semi-parametric method for forecasting that does not rely on this convention and applies it to the problem of forecasting asset return volatility. In this approach, a forecast is a weighted average of historical volatility, with the greatest weight given to periods that exhibit similar market conditions to the time at which the forecast is being formed. Weighting is determined by comparing short-term trends in volatility across time (as a measure of market conditions) by means of a multivariate kernel scheme. It is found that the semi-parametric method produces forecasts that are significantly more accurate than a number of competing approaches at both short and long forecast horizons.

Semi-parametric modelling of ultrafine particle number concentration

Quantifying spatial and/or temporal trends in environmental modelling data requires that measurements be taken at multiple sites. The number of sites and duration of measurement at each site must be balanced against costs of equipment and availability of trained staff. The split panel design comprises short measurement campaigns at multiple locations and continuous monitoring at reference sites [2]. Here we present a modelling approach for a spatio-temporal model of ultrafine particle number concentration (PNC) recorded according to a split panel design. The model describes the temporal trends and background levels at each site. The data were measured as part of the “Ultrafine Particles from Transport Emissions and Child Health” (UPTECH) project which aims to link air quality measurements, child health outcomes and a questionnaire on the child’s history and demographics. The UPTECH project involves measuring aerosol and particle counts and local meteorology at each of 25 primary schools for two weeks and at three long term monitoring stations, and health outcomes for a cohort of students at each school [3].

Anomalous event detection using a semi-two dimensional hidden Markov model

The rapid increase in the deployment of CCTV systems has led to a greater demand for algorithms that are able to process incoming video feeds. These algorithms are designed to extract information of interest for human operators. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned `normal' model. Many researchers have tried various sets of features to train different learning models to detect abnormal behaviour in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM) to model the normal activities of people. The outliers of the model with insufficient likelihood are identified as abnormal activities. Our Semi-2D HMM is designed to model both the temporal and spatial causalities of the crowd behaviour by assuming the current state of the Hidden Markov Model depends not only on the previous state in the temporal direction, but also on the previous states of the adjacent spatial locations. Two different HMMs are trained to model both the vertical and horizontal spatial causal information. Location features, flow features and optical flow textures are used as the features for the model. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

Shear thinning and shear thickening non-Newtonian confined fluid flow over rotating cylinder

In present work, numerical solution is performed to study the confined flow of power-law non Newtonian fluids over a rotating cylinder. The main purpose is to evaluate drag and thermal coefficients as functions of the related governing dimensionless parameters, namely, power-law index (0.5 ≤ n ≤ 1.4), dimensionless rotational velocity (0 ≤ α ≤ 6) and the Reynolds number (100 ≤ Re ≤ 500). Over the range of Reynolds number, the flow is known to be steady. Results denoted that the increment of power law index and rotational velocity increases the drag coefficient due to momentum diffusivity improvement which is responsible for low rate of heat transfer, because the thicker the boundary layer, the lower the heat transfer is implemented.

Growth of confined cancer spheroids : a combined experimental marker, critical modelling approach

A critical step in the dissemination of ovarian cancer is the formation of multicellular spheroids from cells shed from the primary tumour. The objectives of this study were to apply bioengineered three-dimensional (3D) microenvironments for culturing ovarian cancer spheroids in vitro and simultaneously to build on a mathematical model describing the growth of multicellular spheroids in these biomimetic matrices. Cancer cells derived from human epithelial ovarian carcinoma were embedded within biomimetic hydrogels of varying stiffness and grown for up to 4 weeks. Immunohistochemistry, imaging and growth analyses were used to quantify the dependence of cell proliferation and apoptosis on matrix stiffness, long-term culture and treatment with the anti-cancer drug paclitaxel. The mathematical model was formulated as a free boundary problem in which each spheroid was treated as an incompressible porous medium. The functional forms used to describe the rates of cell proliferation and apoptosis were motivated by the experimental work and predictions of the mathematical model compared with the experimental output. This work aimed to establish whether it is possible to simulate solid tumour growth on the basis of data on spheroid size, cell proliferation and cell death within these spheroids. The mathematical model predictions were in agreement with the experimental data set and simulated how the growth of cancer spheroids was influenced by mechanical and biochemical stimuli including matrix stiffness, culture duration and administration of a chemotherapeutic drug. Our computational model provides new perspectives on experimental results and has informed the design of new 3D studies of chemoresistance of multicellular cancer spheroids.