The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework.

Over the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their environment. These types of LiDAR sensors are expensive and are not suitable for small-scale applications. In this paper, we address the performance effect of the LiDAR sensor configuration in DRL models. Our focus is on avoiding static obstacles ahead. We propose a novel approach that determines an initial FOV by calculating an angle of view using the sensor's width and the minimum safe distance required between the robot and the obstacle. The beams returned within the FOV, the robot's velocities, the robot's orientation to the goal point, and the distance to the goal point are used as the input state to generate new velocity values as the output action of the DRL. The cost function of collision avoidance and path planning is defined as the reward of the DRL model. To verify the performance of the proposed method, we adjusted the proposed FOV by ±10° giving a narrower and wider FOV. These new FOVs are trained to obtain collision avoidance and path planning DRL models to validate the proposed method. Our experimental setup shows that the LiDAR configuration with the computed angle of view as its FOV performs best with a success rate of 98% and a lower time complexity of 0.25 m/s. Additionally, using a Husky Robot, we demonstrate the model's good performance and applicability in the real world.

Robust Temporal Link Prediction in Dynamic Complex Networks via Stable Gated Models With Reinforcement Learning.

Temporal link prediction is one of the most important tasks for predicting time-varying links by capturing dynamics within complex networks. However, it suffers from difficulties such as vulnerability to adversarial attacks and inadaptation to distinct evolutionary patterns. In this article, we propose a robust temporal link prediction architecture via stable gated models with reinforcement learning (SAGE-RL) consisting of a state encoding network (SEN) and a self-adaptive policy network (SPN). The former is utilized to capture network dynamics, while the latter helps the former adapt to distinct evolutionary patterns across various time periods. Within the SEN, a novel stable gate is introduced to ensure multiple spatiotemporal dependency paths and defend against adversarial attacks. An SPN is proposed to select different SEN instances by approximating the optimal action function, thereby adapting to various evolutionary patterns to learn the robust temporal and structural features from dynamic complex networks. It is proven that SAGE-LR with integral Lipschitz graph convolution is stable to relative perturbations in dynamic complex networks. With the aid of extensive experiments on five real-world graph benchmarks, SAGE-LR is shown to substantially outperform current state-of-the-art approaches in terms of precision and stability of temporal link prediction and ability to successfully defend against various attacks. We also implement the temporal link prediction in shipping transaction networks, which forecast effectively its potential transaction risks.

Epidemiology and long-term outcomes of primary congenital glaucoma: a population-based study.

BACKGROUND/OBJECTIVES: to establish the incidence, prevalence and long-term outcomes of primary congenital glaucoma (PCG) in Northern Ireland's general and Irish Traveller (IT) populations over a 59-year period. SUBJECTS/METHODS: chart review of all PCG cases in Northern Ireland between 1962 and 2020. Incidence and prevalence were calculated with the aid of national population statistics. Long-term outcomes were analysed for eyes with at least 5 years follow up. Visual outcomes were stratified into groups: good-VA ≥ 6/12; moderate-VA 6/12 to 6/60, poor-VA < 6/60. Kaplan-Meier analysis was constructed to determine the probability of eyes retaining a good visual outcome over time. Outcomes of different surgeries were compared with regard to final vision, re-operations and complications. RESULTS: 57 PCG cases were identified between 1962 and 2020. Overall incidence was 3.4 per 100,000 live births. PCG prevalence in general and IT populations in 2019 was 4.3 per 100,000 and 238 per 100,000, respectively. Sixty eyes had sufficient data for long-term outcome analysis with a mean of 20.5 years follow up, 58% of which had good final visual outcome. Fifty-seven percent of eyes required multiple surgeries. Visual outcomes between trabeculectomies and tubes were comparable; however, there were more serious complications and reoperations associated with tubes. CONCLUSIONS: Incidence of PCG in NI is similar to Great-Britain and Ireland; however, PCG appears to be particularly prevalent within IT community. Although a good visual outcome can be achieved in the majority of patients, a subset of cases remain challenging to manage despite surgical advances.

SEEM: A Sequence Entropy Energy-Based Model for Pedestrian Trajectory All-Then-One Prediction.

Predicting the future trajectories of pedestrians is of increasing importance for many applications such as autonomous driving and social robots. Nevertheless, current trajectory prediction models suffer from limitations such as lack of diversity in candidate trajectories, poor accuracy, and instability. In this paper, we propose a novel Sequence Entropy Energy-based Model named SEEM, which consists of a generator network and an energy network. Within SEEM we optimize the sequence entropy by taking advantage of the local variational inference of f-divergence estimation to maximize the mutual information across the generator in order to cover all modes of the trajectory distribution, thereby ensuring SEEM achieves full diversity in candidate trajectory generation. Then, we introduce a probability distribution clipping mechanism to draw samples towards regions of high probability in the trajectory latent space, while our energy network determines which trajectory is most representative of the ground truth. This dual approach is our so-called all-then-one strategy. Finally, a zero-centered potential energy regularization is proposed to ensure stability and convergence of the training process. Through experiments on both synthetic and public benchmark datasets, SEEM is shown to substantially outperform the current state-of-the-art approaches in terms of diversity, accuracy and stability of pedestrian trajectory prediction.

Interpretable Machine Learning Methods for Monitoring Polymer Degradation in Extrusion of Polylactic Acid.

This work investigates real-time monitoring of extrusion-induced degradation in different grades of PLA across a range of process conditions and machine set-ups. Data on machine settings together with in-process sensor data, including temperature, pressure, and near-infrared (NIR) spectra, are used as inputs to predict the molecular weight and mechanical properties of the product. Many soft sensor approaches based on complex spectral data are essentially 'black-box' in nature, which can limit industrial acceptability. Hence, the focus here is on identifying an optimal approach to developing interpretable models while achieving high predictive accuracy and robustness across different process settings. The performance of a Recursive Feature Elimination (RFE) approach was compared to more common dimension reduction and regression approaches including Partial Least Squares (PLS), iterative PLS (i-PLS), Principal Component Regression (PCR), ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest (RF). It is shown that for medical-grade PLA processed under moisture-controlled conditions, accurate prediction of molecular weight is possible over a wide range of process conditions and different machine settings (different nozzle types for downstream fibre spinning) with an RFE-RF algorithm. Similarly, for the prediction of yield stress, RFE-RF achieved excellent predictive performance, outperforming the other approaches in terms of simplicity, interpretability, and accuracy. The features selected by the RFE model provide important insights to the process. It was found that change in molecular weight was not an important factor affecting the mechanical properties of the PLA, which is primarily related to the pressure and temperature at the latter stages of the extrusion process. The temperature at the extruder exit was also the most important predictor of degradation of the polymer molecular weight, highlighting the importance of accurate melt temperature control in the process. RFE not only outperforms more established methods as a soft sensor method, but also has significant advantages in terms of computational efficiency, simplicity, and interpretability. RFE-based soft sensors are promising for better quality control in processing thermally sensitive polymers such as PLA, in particular demonstrating for the first time the ability to monitor molecular weight degradation during processing across various machine settings.

Enabling affordable and efficiently deployed location based smart home systems.

With the obvious eldercare capabilities of smart environments it is a question of "when", rather than "if", these technologies will be routinely integrated into the design of future houses. In the meantime, health monitoring applications must be integrated into already complete home environments. However, there is significant effort involved in installing the hardware necessary to monitor the movements of an elder throughout an environment. Our work seeks to address the high infrastructure requirements of traditional location-based smart home systems by developing an extremely low infrastructure localisation technique. A study of the most efficient method of obtaining calibration data for an environment is conducted and different mobile devices are compared for localisation accuracy and cost trade-off. It is believed that these developments will contribute towards more efficiently deployed location-based smart home systems.

Aminolaevulinic acid diffusion characteristics in 'in vitro' normal human skin and actinic keratosis: implications for topical photodynamic therapy.

BACKGROUND: The response rate of aminolaevulinic acid (ALA)-based photodynamic therapy (PDT) in certain subtypes of actinic keratosis (AK), such as hypertrophic and hyperkeratotic lesions, is variable, an effect attributable to a supposed lack of ALA penetration. A detailed and depth-related profile of spatial ALA permeation in AK following drug administration would lead to a greater understanding of concentrations achievable before protoporphyrin IX biosynthesis and subsequent PDT. METHODS: ALA penetration through excised normal human skin (NS) and AK lesions was evaluated using a cryostatic sectioning technique and radio-isotope counting following drug delivery using a novel, bioadhesive patch, loaded with 19, 38 or 50 mg/cm(2) ALA. RESULTS: Distinct differences in ALA concentration with respect to depth between AK and NS samples were shown, particularly within the superficial layers of the tissue structure, down to a depth of 1.0 mm. Patch application times were shown to influence ALA concentrations in tissue, but there was no clear correlation between ALA penetration in AK lesions taken from different body locations and from patients of different age. Similarly, the thickness of stratum corneum was not related to the ALA distribution profiles. CONCLUSIONS: Sizable variation in ALA concentration was a prominent feature of profiles through AK lesions, which may explain the variation of observed protoporphyrin IX production seen in the clinical implementation of AK PDT. That said, the results of this study show sufficient ALA penetration to a depth of 1.0 mm, which should be satisfactory for successful treatment of the majority of non-hyperkeratotic, hypertrophic AK using patch-based delivery methods.

A Novel Variable Precision Reduction Approach to Comprehensive Knowledge Systems.

A comprehensive knowledge system reveals the intangible insights hidden in an information system by integrating information from multiple data sources in a synthetical manner. In this paper, we present a variable precision reduction theory, underpinned by two new concepts: 1) distribution tables and 2) genealogical binary trees. Sufficient and necessary conditions to extract comprehensive knowledge from a given information system are also presented and proven. A complete variable precision reduction algorithm is proposed, in which we introduce four important strategies, namely, distribution table abstracting, attribute rank dynamic updating, hierarchical binary classifying, and genealogical tree pruning. The completeness of our algorithm is proven theoretically and its superiority to existing methods for obtaining complete reducts is demonstrated experimentally. Finally, having obtaining the complete reduct set, we demonstrate how the relationships between the complete reduct set and the comprehensive knowledge system can be visualized in a double-layer lattice structure using Hasse diagrams.

Effect of diode laser retinal ablative therapy for threshold retinopathy of prematurity on the visual field: results of goldmann perimetry at a mean age of 11 years.

PURPOSE: To assess the peripheral visual field in premature children who received diode laser photocoagulation for threshold retinopathy of prematurity (ROP) and in a comparison group with subthreshold ROP that had regressed spontaneously without laser treatment. PATIENTS AND METHODS: Eleven patients (18 eyes) were treated with laser, and nine patients (16 eyes) with subthreshold untreated ROP were recalled for assessment at a mean follow-up of 11 years. All children underwent Goldmann visual field testing using the II4e and V4e stimuli. Distance visual acuity measurement, dilated fundal examination, and cycloplegic autorefraction were also performed. RESULTS: The visual field extent in treated eyes was 3% to 4% smaller for the V4e target and 7% to 10% smaller for the II4e target than in the comparison eyes. For the II4e stimulus, the right eye visual field extent of the laser-treated children did not differ significantly from that of the untreated comparison group (P = .11), but the left eyes showed a borderline significant reduction (P = .046). For the larger V4e stimulus, no significant differences were noted (right eye, P = .41; left eye, P = .30). CONCLUSIONS: This is the first study to assess the effect of diode laser therapy on the peripheral visual field in eyes with threshold ROP using Goldmann perimetry. Laser-treated eyes showed a slight constriction of peripheral visual fields compared with untreated subthreshold eyes. It is uncertain whether this was due to the laser treatment itself or to the more severe ROP in the laser group. However, the limited reduction in visual field extent is comparable to that reported for cryotherapy and is unlikely to be of functional significance.

Forward Selection Component Analysis: Algorithms and Applications.

Principal Component Analysis (PCA) is a powerful and widely used tool for dimensionality reduction. However, the principal components generated are linear combinations of all the original variables and this often makes interpreting results and root-cause analysis difficult. Forward Selection Component Analysis (FSCA) is a recent technique that overcomes this difficulty by performing variable selection and dimensionality reduction at the same time. This paper provides, for the first time, a detailed presentation of the FSCA algorithm, and introduces a number of new variants of FSCA that incorporate a refinement step to improve performance. We then show different applications of FSCA and compare the performance of the different variants with PCA and Sparse PCA. The results demonstrate the efficacy of FSCA as a low information loss dimensionality reduction and variable selection technique and the improved performance achievable through the inclusion of a refinement step.

Noncontact Pressure-Based Sleep/Wake Discrimination.

Poor sleep is increasingly being recognized as an important prognostic parameter of health. For those with suspected sleep disorders, patients are referred to sleep clinics, which guide treatment. However, sleep clinics are not always a viable option due to their high cost, a lack of experienced practitioners, lengthy waiting lists, and an unrepresentative sleeping environment. A home-based noncontact sleep/wake monitoring system may be used as a guide for treatment potentially stratifying patients by clinical need or highlighting longitudinal changes in sleep and nocturnal patterns. This paper presents the evaluation of an undermattress sleep monitoring system for noncontact sleep/wake discrimination. A large dataset of sensor data with concomitant sleep/wake state was collected from both younger and older adults participating in a circadian sleep study. A thorough training/testing/validation procedure was configured and optimized feature extraction and sleep/wake discrimination algorithms evaluated both within and across the two cohorts. An accuracy, sensitivity, and specificity of 74.3%, 95.5%, and 53.2% is reported over all subjects using an external validation dataset (71.9%, 87.9%, and 56% and 77.5%, 98%, and 57% is reported for younger and older subjects, respectively). These results compare favorably with similar research, however this system provides an ambient alternative suitable for long-term continuous sleep monitoring, particularly among vulnerable populations.

Long-term refractive and biometric outcomes following diode laser therapy for retinopathy of prematurity.

PURPOSE: To assess the long-term refractive and biometric outcomes of diode laser-treated eyes in threshold retinopathy of prematurity (ROP). METHODS: Cycloplegic autorefraction and biometry (Zeiss IOLMaster) were performed, at a mean follow-up of 11 years, on 16 laser-treated eyes with threshold ROP and 9 comparison eyes with subthreshold untreated ROP. RESULTS: The laser-treated eyes had a mean spherical equivalent of -2.33 D with a mean astigmatic error of 1.38 D. The comparison eyes had a mean spherical equivalent of +1.07 D with a mean astigmatic error of 0.42 D. This trend toward increased myopia in treated eyes did not achieve statistical significance (p=0.08). The myopia in the laser group appeared to be slowly progressive in nature when compared with earlier refractive data for these patients. The laser-treated eyes had reduced anterior chamber depth (ACD) compared with the subthreshold eyes (p=0.02). When physiologic accommodation was inhibited by cycloplegic drops, the anterior chamber deepened by 0.13 mm in the laser-treated eyes and by 0.06 mm in the comparison eyes. This effect of accommodation on ACD did not differ significantly between the two groups (p=0.23). The laser-treated eyes and the comparison eyes did not differ significantly in terms of axial length, corneal power, corneal diameter, or lens power. However, both groups had steeper corneas, shallower anterior chambers, and shorter axial lengths when compared with historical full-term controls. CONCLUSIONS: Myopia in premature infants requiring laser treatment for ROP is associated with a shallowing of the anterior chamber and a steepening of the cornea. Physiological accommodation is not impaired by laser therapy or by severe ROP.

Congenital Nasolacrimal Duct Obstruction: Comparison of Two Different Treatment Algorithms.

PURPOSE: To clarify the most appropriate treatment regimen for congenital nasolacrimal duct obstruction (CNLDO). METHODS: A retrospective observational analysis was performed of patients undergoing probing with or without intubation to treat CNLDO in a single institution (Royal Victoria Hospital, Belfast) from 2006 to 2011. RESULTS: Based on exclusion criteria, 246 eyes of 177 patients (aged 0 to 9.8 years with a mean age of 2.1 years) were included in this study: 187 (76%) eyes had successful outcome at first intervention with primary probing, whereas 56 (23%) eyes underwent secondary intervention. There were no significant differences by gender, age, or obstruction complexity between the successful and unsuccessful patients with first intervention. For those patients requiring secondary intervention, 16 of 24 (67%) eyes had successful probing, whereas 22 of 24 (92%) had successful intubation. Patients with intubation as a secondary procedure were significantly more likely to have a successful outcome (P = .037). Statistical analysis was performed using the Fisher's exact test and Barnard's exact test. CONCLUSIONS: Primary probing for CNLDO has a high success rate that is not adversely affected by increasing age. This study also indicates that if initial probing is unsuccessful, nasolacrimal intubation rather than repeat probing yields a significantly higher success rate. [J Pediatr Ophthalmol Strabismus. 2016;53(5):285-291.].

The use of ensemble empirical mode decomposition with canonical correlation analysis as a novel artifact removal technique.

Biosignal measurement and processing is increasingly being deployed in ambulatory situations particularly in connected health applications. Such an environment dramatically increases the likelihood of artifacts which can occlude features of interest and reduce the quality of information available in the signal. If multichannel recordings are available for a given signal source, then there are currently a considerable range of methods which can suppress or in some cases remove the distorting effect of such artifacts. There are, however, considerably fewer techniques available if only a single-channel measurement is available and yet single-channel measurements are important where minimal instrumentation complexity is required. This paper describes a novel artifact removal technique for use in such a context. The technique known as ensemble empirical mode decomposition with canonical correlation analysis (EEMD-CCA) is capable of operating on single-channel measurements. The EEMD technique is first used to decompose the single-channel signal into a multidimensional signal. The CCA technique is then employed to isolate the artifact components from the underlying signal using second-order statistics. The new technique is tested against the currently available wavelet denoising and EEMD-ICA techniques using both electroencephalography and functional near-infrared spectroscopy data and is shown to produce significantly improved results.

Artifact removal in physiological signals--practices and possibilities.

The combination of reducing birth rate and increasing life expectancy continues to drive the demographic shift toward an aging population. This, in turn, places an ever-increasing burden on healthcare due to the increasing prevalence of patients with chronic illnesses and the reducing income-generating population base needed to sustain them. The need to urgently address this healthcare "time bomb" has accelerated the growth in ubiquitous, pervasive, distributed healthcare technologies. The current move from hospital-centric healthcare toward in-home health assessment is aimed at alleviating the burden on healthcare professionals, the health care system and caregivers. This shift will also further increase the comfort for the patient. Advances in signal acquisition, data storage and communication provide for the collection of reliable and useful in-home physiological data. Artifacts, arising from environmental, experimental and physiological factors, degrade signal quality and render the affected part of the signal useless. The magnitude and frequency of these artifacts significantly increases when data collection is moved from the clinic into the home. Signal processing advances have brought about significant improvement in artifact removal over the past few years. This paper reviews the physiological signals most likely to be recorded in the home, documenting the artifacts which occur most frequently and which have the largest degrading effect. A detailed analysis of current artifact removal techniques will then be presented. An evaluation of the advantages and disadvantages of each of the proposed artifact detection and removal techniques, with particular application to the personal healthcare domain, is provided.

A methodology for validating artifact removal techniques for physiological signals.

Artifact removal from physiological signals is an essential component of the biosignal processing pipeline. The need for powerful and robust methods for this process has become particularly acute as healthcare technology deployment undergoes transition from the current hospital-centric setting toward a wearable and ubiquitous monitoring environment. Currently, determining the relative efficacy and performance of the multiple artifact removal techniques available on real world data can be problematic, due to incomplete information on the uncorrupted desired signal. The majority of techniques are presently evaluated using simulated data, and therefore, the quality of the conclusions is contingent on the fidelity of the model used. Consequently, in the biomedical signal processing community, there is considerable focus on the generation and validation of appropriate signal models for use in artifact suppression. Most approaches rely on mathematical models which capture suitable approximations to the signal dynamics or underlying physiology and, therefore, introduce some uncertainty to subsequent predictions of algorithm performance. This paper describes a more empirical approach to the modeling of the desired signal that we demonstrate for functional brain monitoring tasks which allows for the procurement of a "ground truth" signal which is highly correlated to a true desired signal that has been contaminated with artifacts. The availability of this "ground truth," together with the corrupted signal, can then aid in determining the efficacy of selected artifact removal techniques. A number of commonly implemented artifact removal techniques were evaluated using the described methodology to validate the proposed novel test platform.

Identification of nocturnal movements during sleep using the non-contact under mattress bed sensor.

This paper describes the calculation of statistical, spatial and spatiotemporal features from a novel non-contact technology for sleep monitoring, the Under Mattress Bed Sensor (UMBS). Data was collected from two relatively healthy adults with a possible sleep disorder in a clinical setting. Methods for the extraction of statistical data describing overall bed restlessness, a spatial description of movement (centre and spread of pressure) and a spatiotemporal description of each in-bed body movement over the entire sleeping episode are discussed using the pressure sensing grid. These provide a quantitative description of sleep and restlessness throughout the night.

A methodology for validating artifact removal techniques for fNIRS.

fNIRS recordings are increasingly utilized to monitor brain activity in both clinical and connected health settings. These optical recordings provide a convenient measurement of cerebral hemodynamic changes which can be linked to motor and cognitive performance. Such measurements are of clinical utility in a broad range of conditions ranging from dementia to movement rehabilitation therapy. For such applications fNIRS is increasingly deployed outside the clinic for patient monitoring in the home. However, such a measurement environment is poorly controlled and motion, in particular, is a major source of artifacts in the signal, leading to poor signal quality for subsequent clinical interpretation. Artifact removal techniques are increasingly being employed with an aim of reducing the effect of the noise in the desired signal. Currently no methodology is available to accurately determine the efficacy of a given artifact removal technique due to the lack of a true reference for the uncontaminated signal. In this paper we propose a novel methodology for fNIRS data collection allowing for effective validation of artifact removal techniques. This methodology describes the use of two fNIRS channels in close proximity allowing them to sample the same measurement location; allowing for the introducing of motion artifact to only one channel while having the other free of contamination. Through use of this methodology, for each motion artifact epoch, a true reference for the uncontaminated signal becomes available for use in the development and performance evaluation of signal processing strategies. The advantage of the described methodology is demonstrated using a simple artifact removal technique with an accelerometer based reference.

Minimal hardware Bluetooth tracking for long-term at-home elder supervision.

The ability to automatically detect the location of an elder within their own home is a significant enabler of remote elder supervision and interaction applications. This location information is typically generated via a myriad of sensors throughout the home environment. Even with high sensor redundancy, there are still situations where traditional elder monitoring systems are unable to resolve the location of the elder. This work develops a minimal infrastructure radio-frequency localisation system for long-term elder location tracking. An RFID room-labelling technique is employed and with it, the localisation system developed in this work is shown to exhibit superior performance to more traditional localisation systems in realistic long-term deployments.