Physical activity recognition from accelerometer data using a multi-scale ensemble method

Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. However, interpreting accelerometer data once it has been collected can be challenging. In this work, we applied machine learning algorithms to the task of physical activity recognition from triaxial accelerometer data. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.

Semantic context and visual feature effects in object naming : an fMRI study using arterial spin labeling

Previous behavioral studies reported a robust effect of increased naming latencies when objects to be named were blocked within semantic category, compared to items blocked between category. This semantic context effect has been attributed to various mechanisms including inhibition or excitation of lexico-semantic representations and incremental learning of associations between semantic features and names, and is hypothesized to increase demands on verbal self-monitoring during speech production. Objects within categories also share many visual structural features, introducing a potential confound when interpreting the level at which the context effect might occur. Consistent with previous findings, we report a significant increase in response latencies when naming categorically related objects within blocks, an effect associated with increased perfusion fMRI signal bilaterally in the hippocampus and in the left middle to posterior superior temporal cortex. No perfusion changes were observed in the middle section of the left middle temporal cortex, a region associated with retrieval of lexical-semantic information in previous object naming studies. Although a manipulation of visual feature similarity did not influence naming latencies, we observed perfusion increases in the perirhinal cortex for naming objects with similar visual features that interacted with the semantic context in which objects were named. These results provide support for the view that the semantic context effect in object naming occurs due to an incremental learning mechanism, and involves increased demands on verbal self-monitoring.

Using collaborative and activity-based learning for engaging IT students

Active and collaborative learning are becoming essential strategies to attract, engage and retain students. These methods have been adopted within the Science and Engineering Faculty of Queensland University of Technology for use in its Science, Information Technology and Engineering degrees. This paper describes the adoption and application of these techniques in a specific first year unit in a new Bachelor of Information Technology degree which has majors in Computer Science and Information Systems. The paper reports on the design, development and implementation of this foundation subject and discusses how it uses active and collaborative learning to teach design thinking through a series of design challenges, and how it uses critiquing and reflection to ensure that students become more aware of design and team processes.

Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

Activity Recognition in Egocentric Life-Logging Videos

With the increasing availability of wearable cameras, research on first-person view videos (egocentric videos) has received much attention recently. While some effort has been devoted to collecting various egocentric video datasets, there has not been a focused effort in assembling one that could capture the diversity and complexity of activities related to life-logging, which is expected to be an important application for egocentric videos. In this work, we first conduct a comprehensive survey of existing egocentric video datasets. We observe that existing datasets do not emphasize activities relevant to the life-logging scenario. We build an egocentric video dataset dubbed LENA (Life-logging EgoceNtric Activities) (http://people.sutd.edu.sg/similar to 1000892/dataset) which includes egocentric videos of 13 fine-grained activity categories, recorded under diverse situations and environments using the Google Glass. Activities in LENA can also be grouped into 5 top-level categories to meet various needs and multiple demands for activities analysis research. We evaluate state-of-the-art activity recognition using LENA in detail and also analyze the performance of popular descriptors in egocentric activity recognition.

Expression and activity profiles of DPP IV/CD26 and NEP/CD10 glycoproteins in the human renal cancer are tumor-type dependent

Background: Cell-surface glycoproteins play critical roles in cell-to-cell recognition, signal transduction and regulation, thus being crucial in cell proliferation and cancer etiogenesis and development. DPP IV and NEP are ubiquitous glycopeptidases closely linked to tumor pathogenesis and development, and they are used as markers in some cancers. In the present study, the activity and protein and mRNA expression of these glycoproteins were analysed in a subset of clear-cell (CCRCC) and chromophobe (ChRCC) renal cell carcinomas, and in renal oncocytomas (RO). Methods: Peptidase activities were measured by conventional enzymatic assays with fluorogen-derived substrates. Gene expression was quantitatively determined by qRT-PCR and membrane-bound protein expression and distribution analysis was performed by specific immunostaining. Results: The activity of both glycoproteins was sharply decreased in the three histological types of renal tumors. Protein and mRNA expression was strongly downregulated in tumors from distal nephron (ChRCC and RO). Moreover, soluble DPP IV activity positively correlated with the aggressiveness of CCRCCs (higher activities in high grade tumors). Conclusions: These results support the pivotal role for DPP IV and NEP in the malignant transformation pathways and point to these peptidases as potential diagnostic markers.

Frame-level features conveying phonetic information for language and speaker recognition

150 p.

Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition

Most wearable activity recognition systems assume a predefined sensor deployment that remains unchanged during runtime. However, this assumption does not reflect real-life conditions. During the normal use of such systems, users may place the sensors in a position different from the predefined sensor placement. Also, sensors may move from their original location to a different one, due to a loose attachment. Activity recognition systems trained on activity patterns characteristic of a given sensor deployment may likely fail due to sensor displacements. In this work, we innovatively explore the effects of sensor displacement induced by both the intentional misplacement of sensors and self-placement by the user. The effects of sensor displacement are analyzed for standard activity recognition techniques, as well as for an alternate robust sensor fusion method proposed in a previous work. While classical recognition models show little tolerance to sensor displacement, the proposed method is proven to have notable capabilities to assimilate the changes introduced in the sensor position due to self-placement and provides considerable improvements for large misplacements.

Heterospecific mating and species recognition in the planktonic marine copepods Temora stylifera and T. longicornis

Many planktonic copepods use diffusible pheromone or hydromechanical signals to remotely detect the presence of potential mates. To determine whether these mating signals also play a role in species recognition and mate choice, we observed and video recorded (3D) mate-finding and pursuit behaviors in heterospecific and conspecific mating crosses in a pair of congeneric, partially sympatric species (Temora stylifera and T. longicornis) in the laboratory. The species appear to have asymmetrical pre-mating isolation, with T. longicornis males readily pursuing T. stylifera females to mate contact and capture, but with little mate-finding activity observed in the reverse cross. Males of T. longicornis pursuing heterospecific females executed a number of behaviors known to facilitate successful pheromone trail following and mate capture in conspecific mating, including accelerated swimming in a ‘signal-scanning’ mode to recover a lost pheromone trail, reversal of the tracking direction in cases when the male initiated tracking in the incorrect direction, and accelerated swimming speeds when in the presence of a pheromone signal but prior to locating the trail. Detailed analyses of mate-tracking behavior in T. longicornis male × T. stylifera female crosses gave no indication that males were aware they were pursuing heterospecific females prior to mate contact, indicating that diffusible pheromone and hydromechanical signals are not used, either singly or in combination, for species recognition in this mating pair. Heterospecific mating attempts among sympatric, congeneric copepods may commonly proceed to mate capture, and incur fitness costs to either or both mating partners.

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.

Indications for an influence of hot Jupiters on the rotation and activity of their host stars

Context. The magnetic activity of planet-hosting stars is an importantfactor for estimating the atmospheric stability of close-in exoplanetsand the age of their host stars. It has long been speculated thatclose-in exoplanets can influence the stellar activity level. However,testing for tidal or magnetic interaction effects in samples ofplanet-hosting stars is difficult because stellar activity hindersexoplanet detection, so that stellar samples with detected exoplanetsshow a bias toward low activity for small exoplanets.

Aims: Weaim to test whether exoplanets in close orbits influence the stellarrotation and magnetic activity of their host stars.

Methods: Wedeveloped a novel approach to test for systematic activity-enhancementsin planet-hosting stars. We use wide (several 100 AU) binary systems inwhich one of the stellar components is known to have an exoplanet, whilethe second stellar component does not have a detected planet andtherefore acts as a negative control. We use the stellar coronal X-rayemission as an observational proxy for magnetic activity and analyzeobservations performed with Chandra and XMM-Newton.

Results: Wefind that in two systems for which strong tidal interaction can beexpected the planet-hosting primary displays a much higher magneticactivity level than the planet-free secondary. In three systems forwhich weaker tidal interaction can be expected the activity levels ofthe two stellar components agree with each other.

Conclusions:Our observations indicate that the presence of Hot Jupiters may inhibitthe spin-down of host stars with thick outer convective layers. Possiblecauses for this effect include a transfer of angular momentum from theplanetary orbit to the stellar rotation through tidal interaction, ordifferences during the early evolution of the system, where the hoststar may decouple from the protoplanetary disk early because of a gapopened by the forming Hot Jupiter.

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.

Design of Cyclophanes: Synthesis and Study of Photophysical and Biomolecular Recognition Properties

Development of organic molecules that exhibit selective interactions with different biomolecules has immense significance in biochemical and medicinal applications. In this context, our main objective has been to design a few novel functionaIized molecules that can selectively bind and recognize nucleotides and DNA in the aqueous medium through non-covalent interactions. Our strategy was to design novel cycIophane receptor systems based on the anthracene chromophore linked through different bridging moieties and spacer groups. It was proposed that such systems would have a rigid structure with well defined cavity, wherein the aromatic chromophore can undergo pi-stacking interactions with the guest molecules. The viologen and imidazolium moieties have been chosen as bridging units, since such groups, can in principle, could enhance the solubility of these derivatives in the aqueous medium as well as stabilize the inclusion complexes through electrostatic interactions.We synthesized a series of water soluble novel functionalized cyclophanes and have investigated their interactions with nucleotides, DNA and oligonucIeotides through photophysical. chiroptical, electrochemical and NMR techniques. Results indicate that these systems have favorable photophysical properties and exhibit selective interactions with ATP, GTP and DNA involving electrostatic. hydrophobic and pi-stacking interactions inside the cavity and hence can have potential use as probes in biology.