DocLite: A Docker-Based Lightweight Cloud Benchmarking Tool

Existing benchmarking methods are time consuming processes as they typically benchmark the entire Virtual Machine (VM) in order to generate accurate performance data, making them less suitable for real-time analytics. The research in this paper is aimed to surmount the above challenge by presenting DocLite - Docker Container-based Lightweight benchmarking tool. DocLite explores lightweight cloud benchmarking methods for rapidly executing benchmarks in near real-time. DocLite is built on the Docker container technology, which allows a user-defined memory size and number of CPU cores of the VM to be benchmarked. The tool incorporates two benchmarking methods - the first referred to as the native method employs containers to benchmark a small portion of the VM and generate performance ranks, and the second uses historic benchmark data along with the native method as a hybrid to generate VM ranks. The proposed methods are evaluated on three use-cases and are observed to be up to 91 times faster than benchmarking the entire VM. In both methods, small containers provide the same quality of rankings as a large container. The native method generates ranks with over 90% and 86% accuracy for sequential and parallel execution of an application compared against benchmarking the whole VM. The hybrid method did not improve the quality of the rankings significantly.

Minimising the Execution of Unknown Bag-of-Task Jobs with Deadlines on the Cloud

Scheduling jobs with deadlines, each of which defines the latest time that a job must be completed, can be challenging on the cloud due to incurred costs and unpredictable performance. This problem is further complicated when there is not enough information to effectively schedule a job such that its deadline is satisfied, and the cost is minimised. In this paper, we present an approach to schedule jobs, whose performance are unknown before execution, with deadlines on the cloud. By performing a sampling phase to collect the necessary information about those jobs, our approach delivers the scheduling decision within 10% cost and 16% violation rate when compared to the ideal setting, which has complete knowledge about each of the jobs from the beginning. It is noted that our proposed algorithm outperforms existing approaches, which use a fixed amount of resources by reducing the violation cost by at least two times.

Neural adaptations associated with interlimb transfer in a ballistic wrist flexion task.

Cross education is the process whereby training of one limb gives rise to increases in the subsequent performance of its opposite counterpart. The execution of many unilateral tasks is associated with increased excitability of corticospinal projections from primary motor cortex (M1) to the opposite limb. It has been proposed that these effects are causally related. Our aim was to establish whether changes in corticospinal excitability arising from prior training of the opposite limb determine levels of interlimb transfer.

We used three vision conditions shown previously to modulate the excitability of corticospinal projections to the inactive (right) limb during wrist flexion movements performed by the training (left) limb. These were: mirrored visual feedback of the training limb; no visual feedback of either limb; and visual feedback of the inactive limb. Training comprised 300 discrete, ballistic wrist flexion movements executed as rapidly as possible. Performance of the right limb on the same task was assessed prior to, at the mid point of, and following left limb training.

There was no evidence that variations in the excitability of corticospinal projections (assessed by transcranial magnetic stimulation (TMS)) to the inactive limb were associated with, or predictive of, the extent of interlimb transfer that was expressed. There were however associations between alterations in muscle activation dynamics observed for the untrained limb, and the degree of positive transfer that arose from training of the opposite limb.

The results suggest that the acute adaptations that mediate the bilateral performance gains realised through unilateral practice of this ballistic wrist flexion task are mediated by neural elements other than those within M1 that are recruited at rest by single-pulse TMS.

Transposing Musical Skill: Sonification of movement as concurrent augmented feedback enhances learning in a bimanual task

Concurrent feedback provided during acquisition can enhance performance of novel tasks. The ‘guidance hypothesis’ predicts that feedback provision leads to dependence and poor performance in its absence. However, appropriately-structured feedback information provided through sound (‘sonification’) may not be subject to this effect. We test this directly using a rhythmic bimanual shape-tracing task in which participants learned to move at a 4:3 timing ratio. Sonification of movement and demonstration was compared to two other learning conditions: (1) sonification of task demonstration alone and (2) completely silent practice (control). Sonification of movement emerged as the most effective form of practice, reaching significantly lower error scores than control. Sonification of solely the demonstration, which was expected to benefit participants by perceptually unifying task requirements, did not lead to better performance than control. Good performance was maintained by participants in the sonification condition in an immediate retention test without feedback, indicating that the use of this feedback can overcome the guidance effect. On a 24-hour retention test, performance had declined and was equal between groups. We argue that this and similar findings in the feedback literature are best explained by an ecological approach to motor skill learning which places available perceptual information at the highest level of importance.

Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

Number comparison and number ordering as predictors of arithmetic performance in adults: Exploring the link between the two skills, and investigating the question of domain-specificity.

Recent evidence has highlighted the important role that number ordering skills play in arithmetic abilities (e.g., Lyons & Beilock, 2011). In fact, Lyons et al. (2014) demonstrated that although at the start of formal mathematics education number comparison skills are the best predictors of arithmetic performance, from around the age of 10, number ordering skills become the strongest numerical predictors of arithmetic abilities. In the current study we demonstrated that number comparison and ordering skills were both significantly related to arithmetic performance in adults, and the effect size was greater in the case of ordering skills. Additionally, we found that the effect of number comparison skills on arithmetic performance was partially mediated by number ordering skills. Moreover, performance on comparison and ordering tasks involving the months of the year was also strongly correlated with arithmetic skills, and participants displayed similar (canonical or reverse) distance effects on the comparison and ordering tasks involving months as when the tasks included numbers. This suggests that the processes responsible for the link between comparison and ordering skills and arithmetic performance are not specific to the domain of numbers. Finally, a factor analysis indicated that performance on comparison and ordering tasks loaded on a factor which included performance on a number line task and self-reported spatial thinking styles. These results substantially extend previous research on the role of order processing abilities in mental arithmetic.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.