An efficient feature selection method for mobile devices with application to activity recognition

This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modelled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited. An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.

Practical automated activity recognition using standard smartphones

This paper describes a simple application for mobile devices which automatically recognizes different physical activity. This application could be used to log exercise sessions for the purpose of aiding weight management or improving sporting performance. © 2012 IEEE.

Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.

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.

A sequential algorithm for sparse support vector classifiers

Support vector machines (SVMs), though accurate, are not preferred in applications requiring high classification speed or when deployed in systems of limited computational resources, due to the large number of support vectors involved in the model. To overcome this problem we have devised a primal SVM method with the following properties: (1) it solves for the SVM representation without the need to invoke the representer theorem, (2) forward and backward selections are combined to approach the final globally optimal solution, and (3) a criterion is introduced for identification of support vectors leading to a much reduced support vector set. In addition to introducing this method the paper analyzes the complexity of the algorithm and presents test results on three public benchmark problems and a human activity recognition application. These applications demonstrate the effectiveness and efficiency of the proposed algorithm.


--------------------------------------------------------------------------------

Magnetoencephalography study of brain dynamics in young children born extremely preterm

Magnetoencephalography (MEG) was recorded while 5-7 year-old children were performing a visual-spatial memory recognition task. Full-term children showed greater gamma-band (30-50 Hz) amplitude in the right temporal region during the task, than children who were born extremely preterm. These results may represent altered brain processing in extremely preterm children who escape major impairment.

A Fast Algorithm for Sparse Support Vector Machines for Mobile Computing Applications

This research presents a fast algorithm for projected support vector machines (PSVM) by selecting a basis vector set (BVS) for the kernel-induced feature space, the training points are projected onto the subspace spanned by the selected BVS. A standard linear support vector machine (SVM) is then produced in the subspace with the projected training points. As the dimension of the subspace is determined by the size of the selected basis vector set, the size of the produced SVM expansion can be specified. A two-stage algorithm is derived which selects and refines the basis vector set achieving a locally optimal model. The model expansion coefficients and bias are updated recursively for increase and decrease in the basis set and support vector set. The condition for a point to be classed as outside the current basis vector and selected as a new basis vector is derived and embedded in the recursive procedure. This guarantees the linear independence of the produced basis set. The proposed algorithm is tested and compared with an existing sparse primal SVM (SpSVM) and a standard SVM (LibSVM) on seven public benchmark classification problems. Our new algorithm is designed for use in the application area of human activity recognition using smart devices and embedded sensors where their sometimes limited memory and processing resources must be exploited to the full and the more robust and accurate the classification the more satisfied the user. Experimental results demonstrate the effectiveness and efficiency of the proposed algorithm. This work builds upon a previously published algorithm specifically created for activity recognition within mobile applications for the EU Haptimap project [1]. The algorithms detailed in this paper are more memory and resource efficient making them suitable for use with bigger data sets and more easily trained SVMs.

Comparative study of the spatial relationship between nicotinamide adenine dinucleotide phosphate-diaphorase activity, serotonin immunoreactivity, and GYIRFamide immunoreactivity and the musculature of the adult liver fluke, Fasciola hepatica (Digenea, Fasciolidae)

This is the first detailed description of the nitrergic nervous system in a fluke. In this study, the authors analysed the distribution of the nicotinamide adenine dinucleotide phosphate-diaphorase (NADPH-d) reactivity in neuronal and nonneuronal tissues of the adult fluke Fasciola hepatica and compared this with the distribution of the musculature using tetramethylrhodamine isothiocyanate-phalloidin. To assess the correlation between the number of muscle cells in different parts of the fluke and the NADPH-d-stained cells, the nuclei were stained with Hoechst 333 42, which is specific for chromatin. The spatial relation between the NADPH-d-positive nerves and the 5-hydroxytryptamine (serotonin; 5-HT)-immunoreactive (-IR) and GYIRFamide-IR nervous elements was also examined. The methods complement each other. NADPH-d-positive staining occurs in both in neuronal tissue and nonneuronal tissue. Large, NADPH-d-stained neurones were localised in the nervous system. The oral and ventral suckers are innervated with many large NADPH-d-stained neurones. Ln addition, the NADPH-d staining reaction follows closely the muscle fibres in both the suckers, in the body, and in the ducts of the reproductive organs. The presence of NADPH-d activity along muscle fibres in F. hepatica and in other flatworms supports a possible myoinhibitory role for nitric oxide. Neuronal nitric oxide synthase in flatworms may form a novel drug target, which would facilitate the development of a novel anthelminthic. (C) 2001 Wiley-Liss, Inc.

Activation of the cGMP/PKG pathway inhibits electrical activity in rabbit urethral interstitial cells of Cajal by reducing the spatial spread of Ca2+ waves.

In the present study we used a combination of patch clamping and fast confocal Ca2+ imaging to examine the effects of activators of the nitric oxide (NO)/cGMP pathway on pacemaker activity in freshly dispersed ICC from the rabbit urethra, using the amphotericin B perforated patch configuration of the patch-clamp technique. The nitric oxide donor, DEA-NO, the soluble guanylyl cyclase activator YC-1 and the membrane-permeant analogue of cGMP, 8-Br-cGMP inhibited spontaneous transient depolarizations (STDs) and spontaneous transient inward currents (STICs) recorded under current-clamp and voltage-clamp conditions, respectively. Caffeine-evoked Cl- currents were unaltered in the presence of SP-8-Br-PET-cGMPs, suggesting that activation of the cGMP/PKG pathway does not block Cl- channels directly or interfere with Ca2+ release via ryanodine receptors (RyR). However, noradrenaline-evoked Cl- currents were attenuated by SP-8-Br-PET-cGMPs, suggesting that activation of cGMP-dependent protein kinase (PKG) may modulate release of Ca2+ via IP3 receptors (IP3R). When urethral interstitial cells (ICC) were loaded with Fluo4-AM (2 microm), and viewed with a confocal microscope, they fired regular propagating Ca2+ waves, which originated in one or more regions of the cell. Application of DEA-NO or other activators of the cGMP/PKG pathway did not significantly affect the oscillation frequency of these cells, but did significantly reduce their spatial spread. These effects were mimicked by the IP3R blocker, 2-APB (100 microm). These data suggest that NO donors and activators of the cGMP pathway inhibit electrical activity of urethral ICC by reducing the spatial spread of Ca2+ waves, rather than decreasing wave frequency.

Effect of chronic angiotensin converting enzyme inhibition on spatial memory and anxiety-like behavours in rats

Angiotensin converting enzyme inhibitors (ACEis) are widely used anti-hypertensive agents that are also reported to have positive effects on mood and cognition. The present study examined the influence of the ACEi, perindopril, on cognitive performance and anxiety measures in rats. Two groups of rats were treated orally for one week with the ACEi, perindopril, at doses of 0.1 and 1.0mg/kg/day. Learning was assessed by the reference memory task in the water maze, comparing treated to control rats. Over five training days both perindopril-treated groups learnt the location of the submerged platform in the water maze task significantly faster than control rats. A 60s probe trial on day 6 showed that the 1.0mg/kg/day group spent significantly longer time in the training quadrant than control rats. This improved performance in the swim maze task was not due to the effect of perindopril on motor activity or the anxiety levels of the rats as perindopril-treated and control animals behaved similarly in activity boxes and on the elevated+maze. These results confirm the anecdotal human studies that ACEis have a positive influence on cognition and provide possibilities for ACEis to be developed into therapies for memory loss.