Intel (Ireland)

Applying new sensing technology to healthcare maybe part of a solution to the financial and demographic crisis facing global healthcare systems. Researchers applying new approaches to noninvasive patient monitoring and diagnostics are assisted by the features of Sensing Health with Intelligence, Modularity, Mobility and Experimental Reusability (SHIMMER™), a flexible sensing platform. Integrated peripherals, open software, modular expansion, specific power management hardware, and a library of applications supported with platform validation provide SHIMMER with advantages over many other medical research platforms.

Understanding black box models has become paramount as systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its application in real-world scenarios and addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. We aim to develop a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 28 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.

Tailoring of methods is commonplace in the vast majority of software development projects and organisations. However, there is not much known about the tailoring and engineering of agile methods, or about how these methods can be used to complement each other. This study investigated tailoring of the agile methods, eXtreme programming (XP) and Scrum, at Intel Shannon, and involved experienced software engineers who continuously monitored and reflected on these methods over a 3-year period. The study shows that agile methods may individually be incomplete in supporting the overall development process, but XP and Scrum complement each other well, with XP providing support for technical aspects and Scrum providing support for project planning and tracking. The principles of XP and Scrum were carefully selected (only six of the 12 XP key practices were implemented, for example) and tailored to suit the needs of the development environment at Intel Shannon. Thus, the study refutes the suggestion that agile methods are not divisible or individually selectable but achieve their benefits through the synergistic combination of individual agile practices; rather, this study shows that an a la carte selection and tailoring of practices can work very well. In the case of Scrum, some local tailoring has led to a very committed usage by developers, in contrast to many development methods whose usage is limited despite being decreed mandatory by management. The agile practices that were applied did lead to significant benefits, including reductions in code defect density by a factor of 7. Projects of 6-month and 1-year duration have been delivered ahead of schedule, which bodes well for future ability to accurately plan development projects.

A method to produce scalable, low-resistance, high-transparency, percolating networks of silver nanowires by spray coating is presented. By optimizing the spraying parameters, networks with a sheet resistance of R(s) ≈ 50 Ω □(-1) at a transparency of T = 90% can be produced. The critical processing parameter is shown to be the spraying pressure. Optimizing the pressure reduces the droplet size resulting in more uniform networks. High uniformity leads to a low percolation exponent, which is essential for low-resistance, high-transparency films.

We have prepared flexible, transparent, and very conducting thin composite films from poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate), filled with both arc discharge and HIPCO single-walled nanotubes, at high loading level. The films are of high optical uniformity. The arc discharge nanotube-filled composites were significantly more conductive, demonstrating DC conductivities of >10(5) S/m for mass fractions >50 wt %. The ratio of DC to optical conductivity was higher for composites with mass fractions of 55-60 wt % than for nanotube-only films. For an 80 nm thick composite, filled with 60 wt % arc discharge nanotubes, this conductivity ratio was maximized at sigma(DC)/sigma(Op) = 15. This translates into transmittance (550 nm) and sheet resistance of 75 and 80 Omega/square, respectively. These composites were electromechanically very stable, showing <1% resistance change over 130 bend cycles.

Falls are a major problem in older adults worldwide with an estimated 30% of elderly adults over 65 years of age falling each year. The direct and indirect societal costs associated with falls are enormous. A system that could provide an accurate automated assessment of falls risk prior to falling would allow timely intervention and ease the burden on overstretched healthcare systems worldwide. An objective method for assessing falls risk using body-worn kinematic sensors is reported. The gait and balance of 349 community-dwelling elderly adults was assessed using body-worn sensors while each patient performed the "timed up and go" (TUG) test. Patients were also evaluated using the Berg balance scale (BBS). Of the 44 reported parameters derived from body-worn kinematic sensors, 29 provided significant discrimination between patients with a history of falls and those without. Cross-validated estimates of retrospective falls prediction performance using logistic regression models yielded a mean sensitivity of 77.3% and a mean specificity of 75.9%. This compares favorably to the cross-validated performance of logistic regression models based on the time taken to complete the TUG test (manually timed TUG) and the Berg balance score. These models yielded mean sensitivities of 58.0% and 57.8%, respectively, and mean specificities of 64.8% and 64.2%, respectively. Results suggest that this method offers an improvement over two standard falls risk assessments (TUG and BBS) and may have potential for use in supervised assessment of falls risk as part of a longitudinal monitoring protocol.

The market for remote sensing space-based applications is fundamentally limited by up- and downlink bandwidth and onboard compute capability for space data handling systems. This article details how the compute capability on these platforms can be vastly increased by leveraging emerging commercial off-the-shelf (COTS) system-on-chip (SoC) technologies. The orders of magnitude increase in processing power can then be applied to consuming data at source rather than on the ground allowing the deployment of value-added applications in space, which consume a tiny fraction of the downlink bandwidth that would be otherwise required. The proposed solution has the potential to revolutionize Earth observation (EO) and other remote sensing applications, reducing the time and cost to deploy new added value services to space by a great extent compared with the state of the art. This article also reports the first results in radiation tolerance and power/performance of these COTS SoCs for space-based applications and maps the trajectory toward low Earth orbit trials and the complete life-cycle for space-based artificial intelligence classifiers on orbital platforms and spacecraft.

We explore the state of the art in solutions for low power wide area (LPWA) networks and technologies serving the Internet of Things (IoT) and Connectivity for Everything markets. These networks are forecast to capture up to 55% market share using battery-powered devices operating up to 10 years and link distances measured in tens of kilometers. In this paper, we survey two LPWA technologies; ultra-narrow band solutions by SigFox and the LoRa technology by Semtech. Both technologies operate in the licence-exempt industrial, scientific, & medical (ISM) bands (EU 868 MHz / US 915 MHz). We survey both solutions in terms of physical layer (PHY) and associated medium access control (MAC) capabilities from an end-to-end system viewpoint. We then proceed to explore coverage ranges in eastern Ireland.We present results indicating a potential coverage area of 3,800 km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and from a real-world experimental test case involving the use of SigFox's technology operating over a 25 km test link between a 25 mW LPWA client test and a basestation. Finally, we provide example results demonstrating a received SNR consistently exceeding 20 dB over this test link distance.

As the rollout of 4G mobile communication networks takes place, representatives of industry and academia have started to look into the technological developments toward the next generation (5G). Several research projects involving key international mobile network operators, infrastructure manufacturers, and academic institutions, have been launched recently to set the technological foundations of 5G. However, the architecture of future 5G systems, their performance, and mobile services to be provided have not been clearly defined. In this paper, we put forth the vision for 5G as the convergence of evolved versions of current cellular networks with other complementary radio access technologies. Therefore, 5G may not be a single radio access interface but rather a "network of networks". Evidently, the seamless integration of a variety of air interfaces, protocols, and frequency bands, requires paradigm shifts in the way networks cooperate and complement each other to deliver data rates of several Gigabits per second with end-to-end latency of a few milliseconds. We provide an overview of the key radio technologies that will play a key role in the realization of this vision for the next generation of mobile communication networks. We also introduce some of the research challenges that need to be addressed.

Grazing and ruminating are the most important behaviours for ruminants, as they spend most of their daily time budget performing these. Continuous surveillance of eating behaviour is an important means for monitoring ruminant health, productivity and welfare. However, surveillance performed by human operators is prone to human variance, time-consuming and costly, especially on animals kept at pasture or free-ranging. The use of sensors to automatically acquire data, and software to classify and identify behaviours, offers significant potential in addressing such issues. In this work, data collected from sheep by means of an accelerometer/gyroscope sensor attached to the ear and collar, sampled at 16 Hz, were used to develop classifiers for grazing and ruminating behaviour using various machine learning algorithms: random forest (RF), support vector machine (SVM), k nearest neighbour (kNN) and adaptive boosting (Adaboost). Multiple features extracted from the signals were ranked on their importance for classification. Several performance indicators were considered when comparing classifiers as a function of algorithm used, sensor localisation and number of used features. Random forest yielded the highest overall accuracies: 92% for collar and 91% for ear. Gyroscope-based features were shown to have the greatest relative importance for eating behaviours. The optimum number of feature characteristics to be incorporated into the model was 39, from both ear and collar data. The findings suggest that one can successfully classify eating behaviours in sheep with very high accuracy; this could be used to develop a device for automatic monitoring of feed intake in the sheep sector to monitor health and welfare.

We investigate the morphological, electrical, and optical properties of carbon nanotube thin films, focusing on films with transmittance, T&amp;gt;90%. For films with T≈90% we measure sheet resistance of Rs&amp;lt;400 Ω/◻. However, we show that optoelectrical properties, such as σdc and σdc/σOp, degrade with decreasing film thickness, t, for percolating nanotube networks, i.e., those with t&amp;lt;20 nm and T&amp;gt;90%. Thus, while reducing t can give T&amp;gt;99%, the corresponding Rs increases to &amp;gt;40 kΩ/◻. Acid treatment improves the conductivity by doping, giving properties such as T≈98% for Rs≈10 kΩ/◻.

A goal of cloud service management is to design self-adaptable auto-scaler to react to workload fluctuations and changing the resources assigned. The key problem is how and when to add/remove resources in order to meet agreed service-level agreements. Reducing application cost and guaranteeing service-level agreements (SLAs) are two critical factors of dynamic controller design. In this paper, we compare two dynamic learning strategies based on a fuzzy logic system, which learns and modifies fuzzy scaling rules at runtime. A self-adaptive fuzzy logic controller is combined with two reinforcement learning (RL) approaches: (i) Fuzzy SARSA learning FSL and (ii) Fuzzy Q-learning FQL. As an off-policy approach, Q-learning learns independent of the policy currently followed, whereas SARSA as an on-policy always incorporates the actual agent's behavior and leads to faster learning. Both approaches are implemented and compared in their advantages and disadvantages, here in the OpenStack cloud platform. We demonstrate that both auto-scaling approaches can handle various load traffic situations, sudden and periodic, and delivering resources on demand while reducing operating costs and preventing SLA violations. The experimental results demonstrate that FSL and FQL have acceptable performance in terms of adjusted number of virtual machine targeted to optimize SLA compliance and response time.

We present a silicon characterization vehicle implementing six different constructions of intrinsic Physically Unclonable Functions (PUFs). The design contains four different memory-based PUFs, one of which is a novel buskeeper PUF, and two different delay-based PUFs. Test chips are fabricated in 65 nm Low Power (LP) technology, using a standard cell ASIC design flow for the memory-based PUFs and a full custom flow for the delay-based ones. This test vehicle enables a comprehensive experimental evaluation of individual PUF implementations as well as a comparative analysis across different PUF types for the same silicon technology. PUF responses are obtained from 192 device samples and the uniqueness and reliability of the implemented PUFs are evaluated. In addition, the effects of varying temperature and silicon device ageing on the PUF characteristics are extensively studied.

OBJECTIVES: To develop biopsychosocial models of loneliness and social support thereby identifying their key risk factors in an Irish sample of community-dwelling older adults. Additionally, to investigate indirect effects of social support on loneliness through mediating risk factors. METHODS: A total of 579 participants (400 females; 179 males) were given a battery of biopsychosocial assessments with the primary measures being the De Jong Gierveld Loneliness Scale and the Lubben Social Network Scale along with a broad range of secondary measures. ANALYSIS: Bivariate correlation analyses identified items to be included in separate psychosocial, cognitive, biological and demographic multiple regression analyses. The resulting model items were then entered into further multiple regression analyses to obtain overall models. Following this, bootstrapping mediation analyses was conducted to examine indirect effects of social support on the subtypes (emotional and social) of loneliness. RESULTS: The overall model for (1) emotional loneliness included depression, neuroticism, perceived stress, living alone and accommodation type, (2) social loneliness included neuroticism, perceived stress, animal naming and number of grandchildren and (3) social support included extraversion, executive functioning (Trail Making Test B-time), history of falls, age and whether the participant drives or not. Social support influenced emotional loneliness predominantly through indirect means, while its effect on social loneliness was more direct. CONCLUSIONS: These results characterise the biopsychosocial risk factors of emotional loneliness, social loneliness and social support and identify key pathways by which social support influences emotional and social loneliness. These findings highlight issues with the potential for consideration in the development of targeted interventions.

Automated behavioural classification and identification through sensors has the potential to improve health and welfare of the animals. Position of a sensor, sampling frequency and window size of segmented signal data has a major impact on classification accuracy in activity recognition and energy needs for the sensor, yet, there are no studies in precision livestock farming that have evaluated the effect of all these factors simultaneously. The aim of this study was to evaluate the effects of position (ear and collar), sampling frequency (8, 16 and 32 Hz) of a triaxial accelerometer and gyroscope sensor and window size (3, 5 and 7 s) on the classification of important behaviours in sheep such as lying, standing and walking. Behaviours were classified using a random forest approach with 44 feature characteristics. The best performance for walking, standing and lying classification in sheep (accuracy 95%, F -score 91%–97%) was obtained using combination of 32 Hz, 7 s and 32 Hz, 5 s for both ear and collar sensors, although, results obtained with 16 Hz and 7 s window were comparable with accuracy of 91%–93% and F -score 88%–95%. Energy efficiency was best at a 7 s window. This suggests that sampling at 16 Hz with 7 s window will offer benefits in a real-time behavioural monitoring system for sheep due to reduced energy needs.

Many research works indicate that EEG bands, specifically the alpha and theta bands, have been potentially helpful cognitive load indicators. However, minimal research exists to validate this claim. This study aims to assess and analyze the impact of the alpha-to-theta and the theta-to-alpha band ratios on supporting the creation of models capable of discriminating self-reported perceptions of mental workload. A dataset of raw EEG data was utilized in which 48 subjects performed a resting activity and an induced task demanding exercise in the form of a multitasking SIMKAP test. Band ratios were devised from frontal and parietal electrode clusters. Building and model testing was done with high-level independent features from the frequency and temporal domains extracted from the computed ratios over time. Target features for model training were extracted from the subjective ratings collected after resting and task demand activities. Models were built by employing Logistic Regression, Support Vector Machines and Decision Trees and were evaluated with performance measures including accuracy, recall, precision and f1-score. The results indicate high classification accuracy of those models trained with the high-level features extracted from the alpha-to-theta ratios and theta-to-alpha ratios. Preliminary results also show that models trained with logistic regression and support vector machines can accurately classify self-reported perceptions of mental workload. This research contributes to the body of knowledge by demonstrating the richness of the information in the temporal, spectral and statistical domains extracted from the alpha-to-theta and theta-to-alpha EEG band ratios for the discrimination of self-reported perceptions of mental workload.

AIMS: To describe trends in the incidence of non-traumatic amputations among people with and without diabetes and estimate the relative risk of an individual with diabetes undergoing a lower extremity amputation compared to an individual without diabetes in the Republic of Ireland. METHODS: All adults who underwent a nontraumatic amputation during 2005 to 2009 were identified using HIPE (Hospital In-patient Enquiry) data. Participants were classified as having diabetes or not having diabetes. Incidence rates were calculated using the number of discharges for diabetes and non-diabetes related lower extremity amputations as the numerator and estimates of the resident population with and without diabetes as the denominator. Age-adjusted incidence rates were used for trend analysis. RESULTS: Total diabetes-related amputation rates increased non-significantly during the study period; 144.2 in 2005 to 175.7 in 2009 per 100,000 people with diabetes (p = 0.11). Total non-diabetes related amputation rates dropped non-significantly from 12.0 in 2005 to 9.2 in 2009 per 100,000 people without diabetes (p = 0.16). An individual with diabetes was 22.3 (95% CI 19.1-26.1) times more likely to undergo a nontraumatic amputation than an individual without diabetes in 2005 and this did not change significantly by 2009. DISCUSSION: This study provides the first national estimate of lower extremity amputation rates in the Republic of Ireland. Diabetes-related amputation rates have remained steady despite an increase in people with diabetes. These estimates provide a base-line and will allow follow-up over time.

Due to market deregulation and globalisation, competitive environments in various sectors continuously evolve, leading to increased customer churn. Effectively anticipating and mitigating customer churn is vital for businesses to retain their customer base and sustain business growth. This research scrutinizes 212 published articles from 2015 to 2023, delving into customer churn prediction using machine learning methods. Distinctive in its scope, this work covers key stages of churn prediction models comprehensively, contrary to published reviews, which focus on some aspects of churn prediction, such as model development, feature engineering and model evaluation using traditional machine learning-based evaluation metrics. The review emphasises the incorporation of features such as demographic, usage-related, and behavioural characteristics and features capturing customer social interaction and communications graphs and customer feedback while focusing on popular sectors such as telecommunication, finance, and online gaming when producing newer datasets or developing a predictive model. Findings suggest that research on the profitability aspect of churn prediction models is under-researched and advocates using profit-based evaluation metrics to support decision-making, improve customer retention, and increase profitability. Finally, this research concludes with recommendations that advocate the use of ensembles and deep learning techniques, and as well as the adoption of explainable methods to drive further advancements.

The thermodynamics of self-assembling systems are discussed in terms of the chemical interactions and the intermolecular forces between species. It is clear that there are both theoretical and practical limitations on the dimensions and the structural regularity of these systems. These considerations are made with reference to the microphase separation that occurs in block copolymer (BCP) systems. BCP systems self-assemble via a thermodynamic driven process where chemical dis-affinity between the blocks driving them part is balanced by a restorative force deriving from the chemical bond between the blocks. These systems are attracting much interest because of their possible role in nanoelectronic fabrication. This form of self-assembly can obtain highly regular nanopatterns in certain circumstances where the orientation and alignment of chemically distinct blocks can be guided through molecular interactions between the polymer and the surrounding interfaces. However, for this to be possible, great care must be taken to properly engineer the interactions between the surfaces and the polymer blocks. The optimum methods of structure directing are chemical pre-patterning (defining regions on the substrate of different chemistry) and graphoepitaxy (topographical alignment) but both centre on generating alignment through favourable chemical interactions. As in all self-assembling systems, the problems of defect formation must be considered and the origin of defects in these systems is explored. It is argued that in these nanostructures equilibrium defects are relatively few and largely originate from kinetic effects arising during film growth. Many defects also arise from the confinement of the systems when they are 'directed' by topography. The potential applications of these materials in electronics are discussed.

BACKGROUND: Falls are the most common cause of injury and hospitalization and one of the principal causes of death and disability in older adults worldwide. This study aimed to determine if a method based on body-worn sensor data can prospectively predict falls in community-dwelling older adults, and to compare its falls prediction performance to two standard methods on the same data set. METHODS: Data were acquired using body-worn sensors, mounted on the left and right shanks, from 226 community-dwelling older adults (mean age 71.5 ± 6.7 years, 164 female) to quantify gait and lower limb movement while performing the 'Timed Up and Go' (TUG) test in a geriatric research clinic. Participants were contacted by telephone 2 years following their initial assessment to determine if they had fallen. These outcome data were used to create statistical models to predict falls. RESULTS: Results obtained through cross-validation yielded a mean classification accuracy of 79.69% (mean 95% CI: 77.09-82.34) in prospectively identifying participants that fell during the follow-up period. Results were significantly (p < 0.0001) more accurate than those obtained for falls risk estimation using two standard measures of falls risk (manually timed TUG and the Berg balance score, which yielded mean classification accuracies of 59.43% (95% CI: 58.07-60.84) and 64.30% (95% CI: 62.56-66.09), respectively). CONCLUSION: Results suggest that the quantification of movement during the TUG test using body-worn sensors could lead to a robust method for assessing future falls risk.