Generalizing the use of geographical weights in biodiversity modelling

Aim Determining how ecological processes vary across space is a major focus in ecology. Current methods that investigate such effects remain constrained by important limiting assumptions. Here we provide an extension to geographically weighted regression in which local regression and spatial weighting are used in combination. This method can be used to investigate non-stationarity and spatial-scale effects using any regression technique that can accommodate uneven weighting of observations, including machine learning. Innovation We extend the use of spatial weights to generalized linear models and boosted regression trees by using simulated data for which the results are known, and compare these local approaches with existing alternatives such as geographically weighted regression (GWR). The spatial weighting procedure (1) explained up to 80% deviance in simulated species richness, (2) optimized the normal distribution of model residuals when applied to generalized linear models versus GWR, and (3) detected nonlinear relationships and interactions between response variables and their predictors when applied to boosted regression trees. Predictor ranking changed with spatial scale, highlighting the scales at which different species–environment relationships need to be considered. Main conclusions GWR is useful for investigating spatially varying species–environment relationships. However, the use of local weights implemented in alternative modelling techniques can help detect nonlinear relationships and high-order interactions that were previously unassessed. Therefore, this method not only informs us how location and scale influence our perception of patterns and processes, it also offers a way to deal with different ecological interpretations that can emerge as different areas of spatial influence are considered during model fitting.

A data mining approach for fault diagnosis: An application of anomaly detection algorithm

Rolling-element bearing failures are the most frequent problems in rotating machinery, which can be catastrophic and cause major downtime. Hence, providing advance failure warning and precise fault detection in such components are pivotal and cost-effective. The vast majority of past research has focused on signal processing and spectral analysis for fault diagnostics in rotating components. In this study, a data mining approach using a machine learning technique called anomaly detection (AD) is presented. This method employs classification techniques to discriminate between defect examples. Two features, kurtosis and Non-Gaussianity Score (NGS), are extracted to develop anomaly detection algorithms. The performance of the developed algorithms was examined through real data from a test to failure bearing. Finally, the application of anomaly detection is compared with one of the popular methods called Support Vector Machine (SVM) to investigate the sensitivity and accuracy of this approach and its ability to detect the anomalies in early stages.

Secondary structure element alignment kernel method for prediction of protein structural classes

In this paper, we aim at predicting protein structural classes for low-homology data sets based on predicted secondary structures. We propose a new and simple kernel method, named as SSEAKSVM, to predict protein structural classes. The secondary structures of all protein sequences are obtained by using the tool PSIPRED and then a linear kernel on the basis of secondary structure element alignment scores is constructed for training a support vector machine classifier without parameter adjusting. Our method SSEAKSVM was evaluated on two low-homology datasets 25PDB and 1189 with sequence homology being 25% and 40%, respectively. The jackknife test is used to test and compare our method with other existing methods. The overall accuracies on these two data sets are 86.3% and 84.5%, respectively, which are higher than those obtained by other existing methods. Especially, our method achieves higher accuracies (88.1% and 88.5%) for differentiating the α + β class and the α/β class compared to other methods. This suggests that our method is valuable to predict protein structural classes particularly for low-homology protein sequences. The source code of the method in this paper can be downloaded at http://math.xtu.edu.cn/myphp/math/research/source/SSEAK_source_code.rar.

Structure matters: Adoption of structured classification Approach in the context of cognitive presence classification

Within online learning communities, receiving timely and meaningful insights into the quality of learning activities is an important part of an effective educational experience. Commonly adopted methods – such as the Community of Inquiry framework – rely on manual coding of online discussion transcripts, which is a costly and time consuming process. There are several efforts underway to enable the automated classification of online discussion messages using supervised machine learning, which would enable the real-time analysis of interactions occurring within online learning communities. This paper investigates the importance of incorporating features that utilise the structure of on-line discussions for the classification of "cognitive presence" – the central dimension of the Community of Inquiry framework focusing on the quality of students' critical thinking within online learning communities. We implemented a Conditional Random Field classification solution, which incorporates structural features that may be useful in increasing classification performance over other implementations. Our approach leads to an improvement in classification accuracy of 5.8% over current existing techniques when tested on the same dataset, with a precision and recall of 0.630 and 0.504 respectively.

Application of image processing techniques for frog call classification

Frogs have received increasing attention due to their effectiveness for indicating the environment change. Therefore, it is important to monitor and assess frogs. With the development of sensor techniques, large volumes of audio data (including frog calls) have been collected and need to be analysed. After transforming the audio data into its spectrogram representation using short-time Fourier transform, the visual inspection of this representation motivates us to use image processing techniques for analysing audio data. Applying acoustic event detection (AED) method to spectrograms, acoustic events are firstly detected from which ridges are extracted. Three feature sets, Mel-frequency cepstral coefficients (MFCCs), AED feature set and ridge feature set, are then used for frog call classification with a support vector machine classifier. Fifteen frog species widely spread in Queensland, Australia, are selected to evaluate the proposed method. The experimental results show that ridge feature set can achieve an average classification accuracy of 74.73% which outperforms the MFCCs (38.99%) and AED feature set (67.78%).

Acoustic features for multi-level classification of Australian frogs

Over past few decades, frog species have been experiencing dramatic decline around the world. The reason for this decline includes habitat loss, invasive species, climate change and so on. To better know the status of frog species, classifying frogs has become increasingly important. In this study, acoustic features are investigated for multi-level classification of Australian frogs: family, genus and species, including three families, eleven genera and eighty five species which are collected from Queensland, Australia. For each frog species, six instances are selected from which ten acoustic features are calculated. Then, the multicollinearity between ten features are studied for selecting non-correlated features for subsequent analysis. A decision tree (DT) classifier is used to visually and explicitly determine which acoustic features are relatively important for classifying family, which for genus, and which for species. Finally, a weighted support vector machines (SVMs) classifier is used for the multi- level classification with three most important acoustic features respectively. Our experiment results indicate that using different acoustic feature sets can successfully classify frogs at different levels and the average classification accuracy can be up to 85.6%, 86.1% and 56.2% for family, genus and species respectively.

A multiscale study on the structural and mechanical properties of the luffa sponge from Luffa cylindrica plant

Cellular materials that are often observed in biological systems exhibit excellent mechanical properties at remarkably low densities. Luffa sponge is one of such materials with a complex interconnecting porous structure. In this paper, we studied the relationship between its structural and mechanical properties at different levels of its hierarchical organization from a single fiber to a segment of whole sponge. The tensile mechanical behaviors of three single fibers were examined by an Instron testing machine and the ultrastructure of a fractured single fiber was observed in a scanning electronic microscope. Moreover, the compressive mechanical behaviors of the foam-like blocks from different locations of the sponge were examined. The difference of the compressive stress-strain responses of four sets of segmental samples were also compared. The result shows that the single fiber is a porous composite material mainly consisting of cellulose fibrils and lignin/hemicellulose matrix, and its Young's modulus and strength are comparable to wood. The mechanical behavior of the block samples from the hoop wall is superior to that from the core part. Furthermore, it shows that the influence of the inner surface on the mechanical property of the segmental sample is stronger than that of the core part; in particular, the former's Young's modulus, strength and strain energy absorbed are about 1.6 times higher. The present work can improve our understanding of the structure-function relationship of the natural material, which may inspire fabrication of new biomimetic foams with desirable mechanical efficiency for further applications in anti-crushing devices and super-light sandwich panels.

An analysis of TLS handshake proxying

Content delivery networks (CDNs) are an essential component of modern website infrastructures: edge servers located closer to users cache content, increasing robustness and capacity while decreasing latency. However, this situation becomes complicated for HTTPS content that is to be delivered using the Transport Layer Security (TLS) protocol: the edge server must be able to carry out TLS handshakes for the cached domain. Most commercial CDNs require that the domain owner give their certificate's private key to the CDN's edge server or abandon caching of HTTPS content entirely. We examine the security and performance of a recently commercialized delegation technique in which the domain owner retains possession of their private key and splits the TLS state machine geographically with the edge server using a private key proxy service. This allows the domain owner to limit the amount of trust given to the edge server while maintaining the benefits of CDN caching. On the performance front, we find that latency is slightly worse compared to the insecure approach, but still significantly better than the domain owner serving the content directly. On the security front, we enumerate the security goals for TLS handshake proxying and identify a subtle difference between the security of RSA key transport and signed-Diffie--Hellman in TLS handshake proxying; we also discuss timing side channel resistance of the key server and the effect of TLS session resumption.

Exercise and psychosocial interventions in breast cancer survivors: Preliminary results of a randomized controlled trial

Physical and psychological decline is common in the post-treatment breast cancer population, yet the efficacy of concurrent interventions to meet both physical- psychosocial needs in this population has not been extensively examined. PURPOSE: This study explores the effects of a combined exercise and psychosocial intervention model on selected physiological-psychological parameters in post-treated breast cancer. METHODS: Forty-one breast cancer survivors were randomly assigned to one of four groups for an 8-week intervention: exercise only [EX, n=13] (aerobic and resistance training), psychosocial therapy only [PS, n=11] (biofeedback), combined EX and PS [EX+PS, n=11], or to control conditions [CO, n=6]. Mean delta score (post-intervention - baseline) were calculated for each of the following: body weight, % body fat (skin folds), predicted VO2max (Modified Bruce Protocol), overall dynamic muscular endurance [OME] (RMCRI protocol), static balance (Single leg stance test), dynamic balance (360° turn and 4-square step test), fatigue (Revised Piper Scale), and quality of life (FACT-B). A one-way ANOVA was used to analyze the preliminary results of this on-going randomized trial. RESULTS: Overall, there were significant differences in the delta scores for predicted VO2max, OME, and dynamic balance among the 4 groups (p<0.05). The EX+PS group showed a significant improvement in VO2max compared with the PS group (4.2 ± 3.8 vs. -0.9 ± 4.2 mL/kg/min; p<0.05). Both the EX+PS and EX groups showed significant improvements in OME compared with the PS and CO groups (44.5 ± 23.5 and 43.4 ± 22.1 vs. -3.9 ± 15.2 and 2.7 ± 13.7 repetitions; p<0.05). All 3 intervention groups showed significant improvements in dynamic balance compared with the CO group (-0.8 ± 0.6, -0.6 ± 0.8, and -0.6 ±1.0 vs. 0.6 ± 0.6 seconds; p<0.05). Overall, changes in fatigue tended towards significance among the 4 groups (p = 0.08), with decreased fatigue in the intervention groups and increased fatigue in the CO group. CONCLUSIONS: Our preliminary findings suggest that EX and PS seem to produce greater positive changes in the outcome measures than CO. However, at this point no definite conclusions can be made on the additive effects of combining the EX and PS interventions.

Harnessing information from injury narrative in the 'big data' era: Understanding and applying machine learning for injury surveillance

Objective Vast amounts of injury narratives are collected daily and are available electronically in real time and have great potential for use in injury surveillance and evaluation. Machine learning algorithms have been developed to assist in identifying cases and classifying mechanisms leading to injury in a much timelier manner than is possible when relying on manual coding of narratives. The aim of this paper is to describe the background, growth, value, challenges and future directions of machine learning as applied to injury surveillance. Methods This paper reviews key aspects of machine learning using injury narratives, providing a case study to demonstrate an application to an established human-machine learning approach. Results The range of applications and utility of narrative text has increased greatly with advancements in computing techniques over time. Practical and feasible methods exist for semi-automatic classification of injury narratives which are accurate, efficient and meaningful. The human-machine learning approach described in the case study achieved high sensitivity and positive predictive value and reduced the need for human coding to less than one-third of cases in one large occupational injury database. Conclusion The last 20 years have seen a dramatic change in the potential for technological advancements in injury surveillance. Machine learning of ‘big injury narrative data’ opens up many possibilities for expanded sources of data which can provide more comprehensive, ongoing and timely surveillance to inform future injury prevention policy and practice.

Organosolv pretreatment of plant biomass for enhanced enzymatic saccharification

The combination of dwindling petroleum reserves and population growth make the development of renewable energy and chemical resources more pressing than ever before. Plant biomass is the most abundant renewable source for energy and chemicals. Enzymes can selectively convert the polysaccharides in plant biomass into simple sugars which can then be upgraded to liquid fuels and platform chemicals using biological and/or chemical processes. Pretreatment is essential for efficient enzymatic saccharification of plant biomass and this article provides an overview of how organic solvent (organosolv) pretreatments affect the structure and chemistry of plant biomass, and how these changes enhance enzymatic saccharification. A comparison between organosolv pretreatments utilizing broadly different classes of solvents (i.e., low boiling point, high boiling point, and biphasic) is presented, with a focus on solvent recovery and formation of by-products. The reaction mechanisms that give rise to these by-products are investigated and strategies to minimize by-product formation are suggested. Finally, process simulations of organosolv pretreatments are compared and contrasted, and discussed in the context of an industrial-scale plant biomass to fermentable sugar process.

Automatic ICD-10 classification of cancers from free-text death certificates

Objective Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates – an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. Methods Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. Results The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. Conclusion The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Ion irradiation as a tool for modifying the surface and optical properties of plasma polymerised thin films

Radio frequency (R.F.) glow discharge polyterpenol thin films were prepared on silicon wafers and irradiated with I10+ ions to fluences of 1 × 1010 and 1 × 1012 ions/cm2. Post-irradiation characterisation of these films indicated the development of well-defined nano-scale ion entry tracks, highlighting prospective applications for ion irradiated polyterpenol thin films in a variety of membrane and nanotube-fabrication functions. Optical characterisation showed the films to be optically transparent within the visible spectrum and revealed an ability to selectively control the thin film refractive index as a function of fluence. This indicates that ion irradiation processing may be employed to produce plasma-polymer waveguides to accommodate a variety of wavelengths. XRR probing of the substrate-thin film interface revealed interfacial roughness values comparable to those obtained for the uncoated substrate's surface (i.e., both on the order of 5 Å), indicating minimal substrate etching during the plasma deposition process.

A bottom-up integration of vision and actions to create cognitive humanoids

In recent years more and more complex humanoid robots have been developed. On the other hand programming these systems has become more difficult. There is a clear need for such robots to be able to adapt and perform certain tasks autonomously, or even learn by themselves how to act. An important issue to tackle is the closing of the sensorimotor loop. Especially when talking about humanoids the tight integration of perception with actions will allow for improved behaviours, embedding adaptation on the lower-level of the system.

Analysing the Impact of Learning Inputs - Application to Terrain Traversability Estimation

Data-driven approaches such as Gaussian Process (GP) regression have been used extensively in recent robotics literature to achieve estimation by learning from experience. To ensure satisfactory performance, in most cases, multiple learning inputs are required. Intuitively, adding new inputs can often contribute to better estimation accuracy, however, it may come at the cost of a new sensor, larger training dataset and/or more complex learning, some- times for limited benefits. Therefore, it is crucial to have a systematic procedure to determine the actual impact each input has on the estimation performance. To address this issue, in this paper we propose to analyse the impact of each input on the estimate using a variance-based sensitivity analysis method. We propose an approach built on Analysis of Variance (ANOVA) decomposition, which can characterise how the prediction changes as one or more of the input changes, and also quantify the prediction uncertainty as attributed from each of the inputs in the framework of dependent inputs. We apply the proposed approach to a terrain-traversability estimation method we proposed in prior work, which is based on multi-task GP regression, and we validate this implementation experimentally using a rover on a Mars-analogue terrain.