Insight Research Collection
Permanent URI for this collection
At Insight we undertake high impact research in data analytics that has significant impact on industry and society by enabling better decision making.
Insight brings together leading Irish academics from 5 of Ireland's leading research centres (DERI, CLARITY, CLIQUE, 4C, TRIL), previously established by Science Foundation Ireland (SFI) and the Irish Industrial Development Authority (IDA), in key areas of priority research including:
- The Semantic Web
- Sensors and the Sensor Web
- Social network analysis
- Decision Support and Optimization
- Connected Health
For more information, please visit the official website.
Browse
Browsing Insight Research Collection by Title
Now showing 1 - 20 of 539
Results Per Page
Sort Options
- Publication2D Non-separable Linear Canonical Transform (2D-NS-LCT) based cryptography(2017-04-27)
; ; ; ; ; The 2D non-separable linear canonical transform (2D-NS-LCT) can describe a variety of paraxial optical systems. Digital algorithms to numerically evaluate the 2D-NS-LCTs are not only important in modeling the light field propagations but also of interest in various signal processing based applications, for instance optical encryption. Therefore, in this paper, for the first time, a 2D-NS-LCT based optical Double-random-Phase-Encryption (DRPE) system is proposed which offers encrypting information in multiple degrees of freedom. Compared with the traditional systems, i.e. (i) Fourier transform (FT); (ii) Fresnel transform (FST); (iii) Fractional Fourier transform (FRT); and (iv) Linear Canonical transform (LCT), based DRPE systems, the proposed system is more secure and robust as it encrypts the data with more degrees of freedom with an augmented key-space.417 - PublicationAbbreviation and Acronym Identification and Expansion Within Medical Health RecordsRecent years have seen the rapid increase in digitised medical information. In particular, the massive expansion of Electronic Health Records (EHRs), which are designed to document all information that is clinically relevant in a patient's use of a healthcare facility, has introduced unprecedented volumes of relatively unstructured data. This paper intends to determine the extent to which knowledge discovery in relation to both abbreviations and acronyms within heterogeneous data can be achieved. Heterogeneous data such as the narrative-based free-text notes found within patients' EHRs may use inconsistent ways to indicate contractions within the text and may use non-standard definitions for both abbreviations and acronyms. We approached this task through the retrieval and classification of contractions as well as using a novel method of combining multiple publically available repositories. In order to provide better coverage of abbreviations, and also to address the issue of neologisms in general, word embeddings were applied to find semantically similar lexemes.
99 - PublicationActive semi-supervised overlapping community finding with pairwise constraintsAlgorithms for finding communities in complex networks are generally unsupervised, relying solely on the structure of the network. However, these methods can often fail to uncover meaningful groupings that reflect the underlying communities in the data, particularly when they are highly overlapping. One way to improve these algorithms is by incorporating human expertise or background knowledge in the form of pairwise constraints to direct the community detection process. In this work, we explore the potential of semi-supervised strategies to improve algorithms for finding overlapping communities in networks. We propose a method, based on label propagation, for finding communities using pairwise constraints. Furthermore, we introduce a new strategy, inspired by active learning, for intelligent constraint selection, which is designed to minimize the level of human annotation required. Extensive evaluations on synthetic and real-world datasets demonstrate the potential of this strategy for effectively uncovering meaningful overlapping community structures, using a limited amount of supervision.
251Scopus© Citations 4 - PublicationAcute ankle sprain injury alters kinematic and centre of pressure measures of postural control during single limb stance(BMJ Publishing, 2014-04-12)
; ; ; ; ; Background: Upright single-limb stance (SLS) is maintained via integration of visual, vestibular and somatosensory afferents. The presence of redundancies between these afferents allows the sensorimotor system to simplify a specific task within a number of strategies. Musculoskeletal injury challenges the somatosensory system to reweight distorted sensory afferents. No current investigation has supplemented kinetic analysis of eyes-open and eyes-closed SLS tasks with a kinematic profile of lower limb postural orientation in an acute lateral ankle sprain (LAS) group to assess the adaptive capacity of the sensorimotor system to injury. Objective: To compare centre of pressure (COP) and lower limb postural orientation characteristics of participants with acute LAS to non-injured participants during a SLS task. Design Cross-sectional: Setting University biomechanics laboratory. Participants: 66 participants with acute LAS completed a task of eyes-open SLS on their injured and non-injured limbs (task 1). 23 of these participants successfully completed the SLS task with their eyes closed (task 2). A non-injured control group of nineteen participants completed task 1, with 16 completing task 2. Main outcome measures: 3D kinematics of the hip, knee and ankle joints as well as associated fractal dimension (FD) of the COP path. Results: Between trial analyses of groups revealed significant differences in lower limb kinematics and FD of the COP path for task 2. Post-hoc testing revealed that non-injured control group bilaterally assumed a position of greater hip flexion compared to LAS participants (injured limb=7.41±6.1◦ vs 1.44±4.8◦; non-injured limb=9.59±8.5◦ vs 2.16±5.6◦), with a corollary of greater FD of the COP path (injured limb=1.39±0.16 vs 1.25±0.14; non-injured limb=1.37±0.21 vs 1.23±0.14). Conclusion: Acute LAS causes bilateral impairment in postural control strategies.364 - PublicationAdaptive Incremental Mixture Markov chain Monte CarloWe propose Adaptive Incremental Mixture Markov chain Monte Carlo (AIMM), a novel approach to sample from challenging probability distributions defined on a general state-space. While adaptive MCMC methods usually update a parametric proposal kernel with a global rule, AIMM locally adapts a semiparametric kernel. AIMM is based on an independent Metropolis-Hastings proposal distribution which takes the form of a finite mixture of Gaussian distributions. Central to this approach is the idea that the proposal distribution adapts to the target by locally adding a mixture component when the discrepancy between the proposal mixture and the target is deemed to be too large. As a result, the number of components in the mixture proposal is not fixed in advance. Theoretically, we prove that there exists a process that can be made arbitrarily close to AIMM and that converges to the correct target distribution. We also illustrate that it performs well in practice in a variety of challenging situations, including high-dimensional and multimodal target distributions.
218Scopus© Citations 4 - PublicationAdaptive MCMC for multiple changepoint analysis with applications to large datasetsWe consider the problem of Bayesian inference for changepoints where the number and position of the changepoints are both unknown. In particular, we consider product partition models where it is possible to integrate out model parameters for the regime between each changepoint, leaving a posterior distribution over a latent vector indicating the presence or not of a changepoint at each observation. The same problem setting has been considered by Fearnhead (2006) where one can use filtering recursions to make exact inference. However, the complexity of this filtering recursions algorithm is quadratic in the number of observations. Our approach relies on an adaptive Markov Chain Monte Carlo (MCMC) method for finite discrete state spaces. We develop an adaptive algorithm which can learn from the past states of the Markov chain in order to build proposal distributions which can quickly discover where changepoint are likely to be located. We prove that our algorithm leaves the posterior distribution ergodic. Crucially, we demonstrate that our adaptive MCMC algorithm is viable for large datasets for which the filtering recursions approach is not. Moreover, we show that inference is possible in a reasonable time thus making Bayesian change point detection computationally efficient.
231Scopus© Citations 5 - PublicationAdaptive Representations for Tracking Breaking News on Twitter(2014-08-27)
; ; Twitter is often the most up-to-date source for finding and tracking breaking news stories. Therefore, there is considerable interest in developing filters for tweet streams in order to track and summarize stories. This is a non-trivial text analytics task as tweets are short,and standard text similarity metrics often fail as stories evolve over time. In this paper we examine the effectiveness of adaptive text similarity mechanisms for tracking and summarizing breaking news stories. We evaluate the effectiveness of these mechanisms on a number of recent news events for which manually curated timelines are available. Assessments based on the ROUGE metric indicate that an adaptive similarity mechanism is best suited for tracking evolving stories on Twitter.100 - PublicationAlpha Band Cortico-Muscular Coherence Occurs in Healthy Individuals during Mechanically-Induced Tremor(Public Library of Science, 2014-12-16)
; ; ; ; ; The present work aimed at investigating the effects of mechanically amplified tremor on cortico-muscular coherence (CMC) in the alpha band. The study of CMC in this specific band is of particular interest because this coherence is usually absent in healthy individuals and it is an aberrant feature in patients affected by pathological tremors; understanding its mechanisms is therefore important. Thirteen healthy volunteers (23±4 years) performed elbow flexor sustained contractions both against a spring load and in isometric conditions at 20% of maximal voluntary isometric contraction (MVC). Spring stiffness was selected to induce instability in the stretch reflex servo loop. 64 EEG channels, surface EMG from the biceps brachii muscle and force were simultaneously recorded. Contractions against the spring resulted in greater fluctuations of the force signal and EMG amplitude compared to isometric conditions (p<.05). During isometric contractions CMC was systematically found in the beta band and sporadically observed in the alpha band. However, during the contractions against the spring load, CMC in the alpha band was observed in 12 out of 13 volunteers. Partial directed coherence (PDC) revealed an increased information flow in the EMG to EEG direction in the alpha band (p<.05). Therefore, coherence in the alpha band between the sensory-motor cortex and the biceps brachii muscle can be systematically induced in healthy individuals by mechanically amplifying tremor. The increased information flow in the EMG to EEG direction may reflect enhanced afferent activity from the muscle spindles. These results may contribute to the understanding of the presence of alpha band CMC in tremor related pathologies by suggesting that the origin of this phenomenon may not only be at cortical level but may also be affected by spinal circuit loops.244Scopus© Citations 18 - PublicationAlterations in Motor Unit Firing Rate and Action Potential Properties during Isometric Fatigue in Stroke Survivors(2016-07-08)
; ; ; ; The limited number of studies that have investigated fatigue in chronic stroke survivors during voluntary contr actions to the endurance limit have reported relatively higher central fatigue and lower peripher al fatigue on the affected side when compared to the less-affected side and healthy controls (Riley and Bilodeau, 2002; Knorr et al., 2011). Although these changes have been investigated using global indices of motor unit (MU) activation, alterations at th e level of the single motor unit have not yet been examined.97 - PublicationAMBIQUAL - a full reference objective quality metric for ambisonic spatial audio(IEEE, 2018-09-13)
; ; ; ; Streaming spatial audio over networks requires efficient encoding techniques that compress the raw audio content without compromising quality of experience. Streaming service providers such as YouTube need a perceptually relevant objective audio quality metric to monitor users' perceived quality and spatial localization accuracy. In this paper we introduce a full reference objective spatial audio quality metric, AMBIQUAL, which assesses both Listening Quality and Localization Accuracy. In our solution both metrics are derived directly from the B-format Ambisonic audio. The metric extends and adapts the algorithm used in ViSQOLAudio, a full reference objective metric designed for assessing speech and audio quality. In particular, Listening Quality is derived from the omnidirectional channel and Localization Accuracy is derived from a weighted sum of similarity from B-format directional channels. This paper evaluates whether the proposed AMBIQUAL objective spatial audio quality metric can predict two factors: Listening Quality and Localization Accuracy by comparing its predictions with results from MUSHRA subjective listening tests. In particular, we evaluated the Listening Quality and Localization Accuracy of First and Third-Order Ambisonic audio compressed with the OPUS 1.2 codec at various bitrates (i.e. 32, 128 and 256, 512kbps respectively). The sample set for the tests comprised both recorded and synthetic audio clips with a wide range of time-frequency characteristics. To evaluate Localization Accuracy of compressed audio a number of fixed and dynamic (moving vertically and horizontally) source positions were selected for the test samples. Results showed a strong correlation (PCC=0.919; Spearman=0.882 regarding Listening Quality and PCC=0.854; Spearman=0.842 regarding Localization Accuracy) between objective quality scores derived from the B-format Ambisonic audio using AMBIQUAL and subjective scores obtained during listening MUSHRA tests. AMBIQUAL displays very promising quality assessment predictions for spatial audio. Future work will optimise the algorithm to generalise and validate it for any Higher Order Ambisonic formats.667Scopus© Citations 19 - PublicationAMBIQUAL: Towards a Quality Metric for Headphone Rendered Compressed Ambisonic Spatial Audio(MDPI, 2020-05-03)
; ; ; ; ; Spatial audio is essential for creating a sense of immersion in virtual environments. Efficient encoding methods are required to deliver spatial audio over networks without compromising Quality of Service (QoS). Streaming service providers such as YouTube typically transcode content into various bit rates and need a perceptually relevant audio quality metric to monitor users’ perceived quality and spatial localization accuracy. The aim of the paper is two-fold. First, it is to investigate the effect of Opus codec compression on the quality of spatial audio as perceived by listeners using subjective listening tests. Secondly, it is to introduce AMBIQUAL, a full reference objective metric for spatial audio quality, which derives both listening quality and localization accuracy metrics directly from the B-format Ambisonic audio. We compare AMBIQUAL quality predictions with subjective quality assessments across a variety of audio samples which have been compressed using the Opus 1.2 codec at various bit rates. Listening quality and localization accuracy of first and third-order Ambisonics were evaluated. Several fixed and dynamic audio sources (single and multiple) were used to evaluate localization accuracy. Results show good correlation regarding listening quality and localization accuracy between objective quality scores using AMBIQUAL and subjective scores obtained during listening tests.154Scopus© Citations 10 - PublicationAn Ambulatory Method of Identifying Anterior Cruciate Ligament Reconstructed Gait PatternsThe use of inertial sensors to characterize pathological gait has traditionally been based on the calculation of temporal and spatial gait variables from inertial sensor data. This approach has proved successful in the identification of gait deviations in populations where substantial differences from normal gait patterns exist; such as in Parkinsonian gait. However, it is not currently clear if this approach could identify more subtle gait deviations, such as those associated with musculoskeletal injury. This study investigates whether additional analysis of inertial sensor data, based on quantification of gyroscope features of interest, would provide further discriminant capability in this regard. The tested cohort consisted of a group of anterior cruciate ligament reconstructed (ACL-R) females and a group of non-injured female controls, each performed ten walking trials. Gait performance was measured simultaneously using inertial sensors and an optoelectronic marker based system. The ACL-R group displayed kinematic and kinetic deviations from the control group, but no temporal or spatial deviations. This study demonstrates that quantification of gyroscope features can successfully identify changes associated with ACL-R gait, which was not possible using spatial or temporal variables. This finding may also have a role in other clinical applications where small gait deviations exist.
319Scopus© Citations 38 - PublicationAnalysing Fatigue in Chronic Ankle Instability [Poster Presentation](2015-04-30)
; ; ; Lateral ankle sprains are one of the most common injuries suffered by athletes in sports. It is estimated that an upwards of 70% of athletes will develop chronic ankle instability following an initial sprain. Despite the high prevalence of CAI, knowledge of the mechanism or prevention of repeated ankle sprains is limited . Since most sprains occur in the latter halves of matches, the purpose of this study was to determine the effects of fatigue on lower limb movement variability in individuals with and without CAI during running gait using 3D inertial sensors72 - PublicationAn Analysis Framework for Content-based Job Recommendation(2014-09-29)
; ; In this paper, we focus on the task of job recommendation. In particular, we consider several personalised content-based and case-based approaches to recommendation. We investigate a number of feature-based item representations, along with a variety of feature weighting schemes. A comparative evaluation of the various approaches is performed using a realworld, open source dataset.756 - PublicationAnalysis of EHR Free-text Data with Supervised Deep Neural Networks(2018-07-29)
; In this paper we present an efficient supervised deep neural network architecture to classify patients based solely on free-text notes extracted from their Electronic Health Records (EHRs). In particular, a three-layer Recurrent Neural Network was used in conjunction with the aggregated EHRs of about 127,149 patients from a medical data warehouse. The result forms a key component of an application we name PANNACEA. We evaluated this neural network in the context of competing neural network architectures, comparing the performance of multilayer perceptrons, convolutional neural networks, and recurrent neural networks in relation to the dataset under investigation. We performed evaluation our program to successfully classify the suitability of these patients to the medical service offered based upon a single medical episode.209 - PublicationAnalysis of Oscillatory Neural Activity in Series Network Models of Parkinson’s Disease During Deep Brain StimulationParkinson’s disease is a progressive, neurodegenerative disorder, characterized by hallmark motor symptoms. It is associated with pathological, oscillatory neural activity in the basal ganglia. Deep brain stimulation (DBS) is often successfully used to treat medically refractive Parkinson’s disease. However, the selection of stimulation parameters is based on qualitative assessment of the patient, which can result in a lengthy tuning period and a suboptimal choice of parameters. This study explores fourth order, control theory-based models of oscillatory activity in the basal ganglia. Describing function analysis is applied to examine possible mechanisms for the generation of oscillations in interacting nuclei and to investigate the suppression of oscillations with high-frequency stimulation. The theoretical results for the suppression of the oscillatory activity obtained using both the fourth-order model, and a previously described second-order model, are optimized to t clinically recorded local field potential data obtained from Parkinsonian patients with implanted DBS. Close agreement between the power of oscillations recorded for a range of stimulation amplitudes is observed (R2 =0 .690.99). The results suggest that the behavior of the system and the suppression of pathological neural oscillations with DBS is well described by the macroscopic models presented. The results also demonstrate that in this instance, a second-order model is sufficient to model the clinical data, without the need for added complexity. Describing the system behaviour with computationally efficient models could aid in the identification of optimal stimulation parameters for patients in a clinical environment.
265Scopus© Citations 17 - PublicationAnalysis of Parkinsonian Surface Electomyography Through Advanced Signal Processing and Nonlinear Methods(2016-01-23)
; Parkinson’s disease (PD) is a neurodegenerative disease that affects approx. 4% of people over 80 years of age [4]. The result of depleted dopaminergic neurons in the substantia nigra, PD is characterised with symptoms such as muscle rigidity, bradykinetic gait, and severe tremor. To distinguish Parkinsonian electromyographic (EMG) signals from those of healthy controls, recent studies have employed nonlinear methods which can capture the underlying activity of the neuromuscular system. Recurrence quantification analysis (RQA) has been shown to effectively characterise the degree of repeated synchronous structure in non-linear dynamical systems including parkinsonian EMG, through parameters such as determinism (%DET) and recurrence rate (%REC) [1]. Additional parameters such as intermuscular coherence and kurtosis have also been used to observe changes in EMG signals under various conditions [2,3]. To date, limited research has examined the potential to discern EMG of individuals with PD from healthy controls using RQA and intermuscular coherence. The work presented here aims to examine differences in Parkinsonian EMG from that of healthy controls using these measures.254 - PublicationAn Analysis of Recommender Algorithms for Online News(2014-09-18)
; ; ; This paper presents the recommendation algorithms used by the Insight UCD team participating in the CLEF-NewsREEL 2014 online news recommendation challenge.430 - PublicationAnalysis of Surface Electromyography in Parkinson's Disease Using Time Frequency and Recurrence Quantification Methods(2015-01-17)
; The work presented here aims to establish the optimal RQA variables for the calculation of RQA parameters (REC, DET, JRP, etc.), and to apply these parameters to EMG data of Parkinson’s disease patients. Additionally, the cross-correlation of these parameters with time frequency features will be assessed with the intention of classifying Parkinson’s patients from healthy controls.94 - PublicationAn Analysis of the Coherence of Descriptors in Topic ModelingIn recent years, topic modeling has become an established method in the analysis of text corpora, with probabilistic techniques such as latent Dirichlet allocation (LDA) commonly employed for this purpose. However, it might be argued that adequate attention is often not paid to the issue of topic coherence, the semantic interpretability of the top terms usually used to describe discovered topics. Nevertheless, a number of studies have proposed measures for analyzing such coherence, where these have been largely focused on topics found by LDA, with matrix decomposition techniques such as Non-negative Matrix Factorization (NMF) being somewhat overlooked in comparison. This motivates the current work, where we compare and analyze topics found by popular variants of both NMF and LDA in multiple corpora in terms of both their coherence and associated generality, using a combination of existing and new measures, including one based on distributional semantics. Two out of three coherence measures find NMF to regularly produce more coherent topics, with higher levels of generality and redundancy observed with the LDA topic descriptors. In all cases, we observe that the associated term weighting strategy plays a major role. The results observed with NMF suggest that this may be a more suitable topic modeling method when analyzing certain corpora, such as those associated with niche or non-mainstream domains.
2428Scopus© Citations 165