Pre-collected Data Research Articles

Robust data-driven predictive control for unknown linear time-invariant systems

This paper presents a new robust data-driven predictive control scheme for unknown linear time-invariant systems by using input-state-output or input–output data based on whether the state is measurable. To remove the need for the persistently exciting (PE) condition of a sufficiently high order on pre-collected data, a set containing all systems capable of generating such data is constructed. Then, at each time step, an upper bound on a given objective function is derived for all systems in the set, and a feedback controller is designed to minimize this bound. The optimal control gain at each time step is determined by solving a set of linear matrix inequalities. We prove that if the synthesis problem is feasible at the initial time step, it remains feasible for all future time steps. Unlike current data-driven predictive control schemes based on behavioral system theory, our approach requires less stringent conditions for the pre-collected data, facilitating easier implementation. The effectiveness of our proposed methods is demonstrated through application to an unknown and unstable batch reactor.

Pattern of health awareness by a health care provider in Maldives: A descriptive study

Abstract: Health awareness is considered to be one of the most essential ingredients of life. In Maldives, Mass media has been utilized to create health awareness among the people. Formally in Maldives, radio represents a popular form of communication and was the most extensively utilized form of mass media used to create health awareness among public. However, with advancement in technologies other forms of media social media platforms have been started using to create health awareness in the recent few years. The main objective of the study was to identify the pattern of health awareness created by selected health care provider (HCP), a single medical doctor who has been creating health awareness during the past 14 years period starting from 2010 till end of 2023.A retrospective descriptive cross-sectional study conducted using pre-collected data, by preparing a check list through note sheets of selected health care provider (HCP). The population for the current study is tasks or events performed by selected HCP with intention to create health awareness. Henceforth, total 359 events or tasks were included in this study as study subjects which were performed by the selected HCP in the past 14 years period starting from 2010 till end of 2023, which is also considered as sample size of the study. Majority of the awareness activity occurred in the year 2020, while majority occur specifically in the month of March. Radio was major source of awareness created, Voice Of Maldives (VOM) was main station where most of the awareness events took place and radio discussion was main method of awareness used by the selected HCP. Major topics covered in health awareness include tobacco, non-communicable disease, communicable disease, nutrition, Ramadan and health. Radio was major source of health awareness created by selected health care provider.

Digital twin-driven discriminative graph learning networks for cross-domain bearing fault recognition

Rolling bearing fault diagnosis holds paramount significance in industrial field, as it is pivotal for ensuring the reliability, safety, and economic viability of mechanical systems. Most of traditional data-driven fault diagnosis methods rely on the availability of pre-collected data sets (containing various failure modes) as training data. Regrettably, such datasets may not always be easy to collect, particularly in critical industrial settings. Consequently, the applicability of data-driven fault diagnostic methods across diverse applications is impeded. In response to this challenge, this research introduces a digital twin-empowered discriminative graph learning network (DT-DGLN) for bearing fault diagnostics with unlabeled industrial data. The primary improvements of this study are twofold: (1) The creation of an elaborate and meticulous digital twin model for bearings. This model encompasses multi-scale Kinetic simulations of the operational parameters of the bearing and relies exclusively on the architectural attributes of the bearing and magnitude of the failure to deduce the vibratory system’s reaction. (2) The establishment of a domain adaption-based framework based on discriminative graph learning strategy that facilitates the transfer of known intelligence from simulated signals to real signals. This framework enables efficient fault recognition in cases where knowledge is limited. Rigorous experiments have been conducted to validate the effectiveness of the proposed approach.

Equipment- and Time-Constrained Data Acquisition Protocol for Non-Intrusive Appliance Load Monitoring

Energy behaviours will play a key role in decarbonising the building sector but require the provision of tailored insights to assist occupants to reduce their energy use. Energy disaggregation has been proposed to provide such information on the appliance level without needing a smart meter plugged in to each load. However, the use of public datasets with pre-collected data employed for energy disaggregation is associated with limitations regarding its compatibility with random households, while gathering data on the ground still requires extensive, and hitherto under-deployed, equipment and time commitments. Going beyond these two approaches, here, we propose a novel data acquisition protocol based on multiplexing appliances’ signals to create an artificial database for energy disaggregation implementations tailored to each household and dedicated to performing under conditions of time and equipment constraints, requiring that only one smart meter be used and for less than a day. In a case study of a Greek household, we train and compare four common algorithms based on the data gathered through this protocol and perform two tests: an out-of-sample test in the artificially multiplexed signal, and an external test to predict the household’s appliances’ operation based on the time series of a real total consumption signal. We find accurate monitoring of the operation and the power consumption level of high-power appliances, while in low-power appliances the operation is still found to be followed accurately but is also associated with some incorrect triggers. These insights attest to the efficacy of the protocol and its ability to produce meaningful tips for changing energy behaviours even under constraints, while in said conditions, we also find that long short-term memory neural networks consistently outperform all other algorithms, with decision trees closely following.

Characterizing the variability of footstep-induced structural vibrations for open-world person identification

Person identification is important in providing personalized services in smart buildings. Many existing studies focus on closed-world person identification, which only identifies a fixed group of people who have training data; however, they assume everyone has pre-collected data, which is not practical in real-world scenarios when newcomers are present. To overcome this drawback, open-world person identification recognizes both newcomers and registered people, which opens up new opportunities for smart building applications that involve newcomers, such as smart visitor management, customized retail, personalized health monitoring, and public emergency assistance. To achieve this, structural vibration sensing has various advantages when compared with the existing sensing modalities (e.g., cameras, wearables, and pressure sensors) because it only needs sparsely deployed sensors mounted on the floor, does not require people to carry devices, and is perceived as more privacy-friendly. However, one fundamental challenge in analyzing footstep-induced structural vibration data is its high variability due to the structural heterogeneity and the footstep variations. Therefore, it is difficult to distinguish different people given this high variability within each person, and it is more challenging to recognize a new person as that data is unobserved before.In this paper, we characterize the variability in footstep-induced structural vibration to develop an open-world person identification framework. Specifically, we address three variability challenges in developing our method. First, the high variability within each person comes from multiple sources that are entangled in the vibration signals, and thus is difficult to be decomposed and reduced. Secondly, the distribution of features extracted from the vibration signals is irregularly shaped, and therefore is difficult to model. Moreover, the identity of the next person is correlated with the previous observations, which makes the identification process more complicated. To overcome these challenges, we first characterize multiple variability sources and design a transformation function that results in signal features that are less variable within one person and more separable between different people. We then develop a modified Chinese Restaurant Process (mCRP) for nonparametric Bayesian modeling to capture the irregularly shaped feature patterns both from local and global perspectives. Finally, we design an adaptive hyperparameter α that represents the prior probability of newcomers at each observation, which keeps updating depending on the time, location, and previous predictions. We evaluate our approach through walking experiments with 20 people across 2 different structures. With only 1 pre-recorded person at each structure, our method achieves up to 92.3% average accuracy with randomly appearing newcomers.

Efficient experience replay architecture for offline reinforcement learning

PurposeOffline reinforcement learning (RL) acquires effective policies by using prior collected large-scale data, while, in some scenarios, collecting data may be hard because it is time-consuming, expensive and dangerous, i.e. health care, autonomous driving, seeking a more efficient offline RL method. The purpose of the study is to introduce an algorithm, which attempts to sample the high-value transitions in the prioritized buffer, and uniformly sample from the normal experience buffer, improving sample efficiency of offline reinforcement learning, as well as alleviating the “extrapolation error” commonly arising in offline RL.Design/methodology/approachThe authors propose a new structure of experience replay architecture, which consists of double experience replies, a prioritized experience replay and a normal experience replay, supplying samples for policy updates in different training phases. At the first training stage, the authors sample from prioritized experience replay according to the calculated priority of each transitions. At the second training stage, the authors sample from the normal experience replay uniformly. The combination of the two experience replies is initialized by the same offline data set.FindingsThe proposed method eliminates out-of-distribution problem in an offline RL regime, and promotes training by leveraging a new efficient experience replay. The authors evaluate their method on D4RL benchmark, and the results reveal that the algorithm can achieve superior performance over the state-of-the-art offline RL algorithm. The ablation study proves that the authors’ experience replay architecture plays an important role in terms of improving final performance, data-efficiency and training stability.Research limitations/implicationsBecause of the extra addition of prioritized experience replay, the proposed method increases the computational burden and has the risk of changing data distribution due to the combined sample strategy. Therefore, researchers are encouraged to use the experience replay block effectively and efficiently further.Practical implicationsOffline RL is susceptible to the quality and coverage of pre-collected data, which may be not easy to be collected from specific environment, demanding practitioners to handcraft behavior policy to interact with environment for gathering data.Originality/valueThe proposed approach focuses on the experience replay architecture for offline RL, and empirically demonstrates the superiority of the algorithm on data efficiency and final performance over conservative Q-learning across diverse D4RL tasks. In particular, the authors compare different variants of their experience replay block, and the experiments show that the stages, when to sample from the priority buffer, play an important role in the algorithm. The algorithm is easy to implement and can be combined with any Q-value approximation-based offline RL methods by minor adjustment.

Auditory-perceptual Parameters as Predictors of Voice Acoustic Measures

Much research has examined the relationship between perceptual and acoustic measures. However, little is known about the prediction values of perceptual measures on an acoustic parameter. This study utilized simulated and disordered voice samples to investigate the prediction values of breathiness, roughness, and strain ratings on the selection of some time-based and spectral-based measures of voice quality. This study retrospectively analysed two sets of precollected data. The experimental data had been collected from nine trained speakers manipulating false vocal fold activity, true vocal fold mass, and larynx height. The voice-disordered data had been extracted from a clinical database for 68 patients with muscle tension voice disorders (MTVD). Both data sets had been perceptually rated for breathiness, roughness, and strain. Voice samples (prolonged vowel /ɑ/ and Rainbow Passage readings) had undergone acoustic analysis using Praat for harmonics-to-noise ratio (HNR) and the program "Analysis of Dysphonia in Speech and Voice" (ADSV) for cepstral peak prominence (CPP), Cepstral/Spectral Index of Dysphonia (CSID), and Low/High spectral ratio (L/H ratio). Perceptual parameters were regressed against these acoustic measures to test their prediction values. Reliability data showed satisfactory intra- and inter-reliability of perceptual ratings for both data sets. Breathiness significantly predicted CPP (both vocal tasks) and CSID (Rainbow Passage) in experimental data and predicted all the acoustic measures in MTVD data. Roughness significantly predicted HNR, CPP, and CSID in experimental data, and CPP (Rainbow Passage) and CSID (both vocal tasks) in MTVD data. Strain (both vocal tasks) significantly predicted L/H ratio in both data sets. Breathiness ratings predicted selection of HNR, CPP and CSID; roughness ratings predicted selection of CPP and CSID, and strain ratings predicted L/H ratio.

Survival of Tunneled Double Lumen-Cuffed Catheters in Children on Maintenance Hemodialysis - A Retrospective Cohort Study.

Survival of tunneled cuffed catheters (TCC), used widely in children, is complicated by infections and catheter dysfunction. In resource limited settings, where risk of complications could be higher and waiting period for transplantation longer, catheter survival determines patient survival. This study was conducted to determine infection free catheter survival rates, incidence of catheter failure and associated risk factors. Children <18 years of age receiving maintenance hemodialysis through TCC at nephrology division of a pediatric hospital, over a period of 6 years. Data was collected with consecutive selection by a complete enumeration technique from pre-collected data sheets in the records. Exposure detected were catheter infections, thrombosis, and mechanical complications. Forty-five TCCs in 36 children studied for 12,590 catheter days showed catheter failure in 36%, due to catheter related infections in 75% and mechanical complications in 25%. The incidence of complications per 1000 catheter days was 1.19 infection, 1.03 thrombus, and 0.39 mechanical. Catheter-related blood stream infection (CRBSI) (15/36) was associated with thrombus in nine and led to mortality in three. The mean infection free catheter survival was 449 ± 42 days for cohort with 388 ± 38 days in Group A (premature catheter removal) and 593 ± 43 days in Group B (elective removal) (P = 0.03). Catheterization duration of 267 days predicted CRBSI (sensitivity 93%, specificity 66.7%) with area under the curve of 0.808. Median infection free catheter survival was 449 days with catheter failure in 36%. CRBSI was the main cause of failure. Duration of catheterization greater than 267 days was a predictor of CRBSI.

IT PROJECT RISK MANAGEMENT FOR CLOUD ENVIRONMENT LEVERAGING ARTIFICIAL INTELLIGENCE

Cloud security contributes to multiple risk parameters like multitenancy, Insecure interfaces/APIs, Malicious Insiders, Malware injections, the lack of information on location of storage of data, the unavailability of details on type of data saved in the same server, hacking. AI or Artificial Intelligence works on pre-collected data and scenarios fed into the computers thereby predicting in advance the possibilities of risk, warning if there is any unusual occurrence in the cloud and proposing the Risk Mitigation plans based on various scenarios. Proactive risk prediction will have a huge impact on risk mitigation, cost saving as well as customer satisfaction. A pilot study has been conducted to ascertain the impact of various risk factors identified by circulating the questionnaire among practitioners from the relevant domains. The questionnaire is circulated among the current industry practitioners and experts in this area and facilitates to conduct the pilot survey on the significance of various risk parameter. The impact of each risk factor is identified and is subjected to analysis. With the help of prediction algorithms, the possibility of occurrence of risk, the impact, and consequences of that particular event, as well as the mitigation strategies could be foretold. This objective of this paper is to propose management perspective of a framework of AI, that can contribute to proactive risk management in cloud. This paper deals only with the management overview of implementation of AI in risk mitigation strategies and not the technical aspects of AI. The futuristic scope of this paper would be a management overview on automation of risk mitigation strategies in cloud platform using AI.

TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis

TinyML has the potential to be a huge enabler of smart sensor nodes for fault diagnosis of machines by embedding powerful machine learning algorithms in low-cost edge devices. Static models trained with pre-collected data may not perform satisfactorily when deployed in use cases that present data with a significantly different distribution, due to changes in machine instances, installation, and environment and operating conditions. In this work, we present a transfer learning framework in conjunction with TinyML-powered convolutional neural network (CNN) architecture for vibration-based fault diagnosis of vastly different machines. We report that fine-tuning (retraining) of parameters (weights and biases) in convolutional layers and transfer of parameters in dense layers of CNNs results in higher accuracy for domain generalization than the conventional approach of transferring parameters for convolutional layers and fine-tuning dense layers. Using transfer learning also results in high accuracy when the total number of training samples used for fine-tuning on the target domain data sets are as low as 25 i.e. less than 5% of the size of the data set, which makes the proposed architecture viable for scenarios with a limited number of data points available for training the model. Furthermore, we have also demonstrated memory-efficient retraining at the edge by fine-tuning only the biases of hidden layers.

Ice reconnaissance data processing under low quality source images

A practically effective solution to the problem of automated processing of ice reconnaissance data in high latitudes is proposed. The intermediate result of ice reconnaissance is huge aerial survey data set consisting of images of low quality; this is a consequence of the difficult conditions of aerial survey in high latitudes. The goal of the study is to create a high-level method that can either efficiently process this pre-collected data set or perform real-time processing of similar images while ensuring high reliability in solving the problem of recognizing ice class distribution on the water surface with minimal computing resources. In particular, the problem of automatic classification of ice-floe size distribution (FSD) type for a three-class model based on aerial survey data is solved. The practically important case of low-quality images is considered, a common situation for the meteorological conditions of the Far North. The proposed approach is based on the use of machine learning methods, in particular on the well-known multi-class SVM (Support Vector Machine), which is extremely undemanding to computing resources and therefore can be implemented even by the onboard computer of an ice reconnaissance UAV. From the input images of low quality some numerical characteristics of the image are calculated which informatively characterize the image. These characteristics (features) are invariant to scaling, rotation and illumination as well as have a much smaller dimensionality than the original image. The main idea underlying the proposed method is to form an original set of features which are implemented in the original feature space. These features characterize large fragments of the analyzed image and are “stable”, in contrast to the features that characterize small details. A new method of FSD type classification based on the processing of aerial survey data by using machine learning methods, which is sufficiently effective for processing low-quality images, has been proposed. Also, the original feature space for classification was proposed which ensured high practical efficiency of this method. The method has shown high efficiency when it is tested on a data set composed of low-quality real images (high blurriness, vagueness, presence of meteorological noises). The developed algorithm can be used for express analysis of ice reconnaissance data, including an ice reconnaissance UAV on-board software component.

Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are developed in online settings where data are easy to collect or simulate. Their generalizations to mobile health applications with a pre-collected offline dataset remain are less explored. The aim of this article is to develop a novel advantage learning framework in order to efficiently use pre-collected data for policy optimization. The proposed method takes an optimal Q-estimator computed by any existing state-of-the-art RL algorithms as input, and outputs a new policy whose value is guaranteed to converge at a faster rate than the policy derived based on the initial Q-estimator. Extensive numerical experiments are conducted to back up our theoretical findings. A Python implementation of our proposed method is available at https://github.com/leyuanheart/SEAL. Supplementary materials for this article are available online.

New Ways of Working in Psychology: Evaluating a Pilot of the Clinical Associate Psychologist Apprenticeship on an Acute Mental Health Ward

Aim: Acute mental health wards have been criticised for being untherapeutic. NHS England aims to move towards therapeutic wards by increasing psychological practitioner staffing. The new clinical associate psychologist (CAP) role may provide a cost effective way of enhancing existing psychological therapies teams. The current study aimed to evaluate the introduction of a CAP apprentice on an acute mental health ward. Specifically, the study aimed to (1) examine whether the CAP role could improve patients access to direct psychological interventions; and (2) explore the ward team's experiences of the role. Method: Referrals for direct psychological interventions and sessions conducted were collected over a six-month period and compared to pre-collected data from the previous year. A focus group was held to explore the ward teams experiences of the role which was transcribed and thematically analysed. Results: Referrals for direct psychological interventions increased following the introduction of the CAP apprentice on the ward, including an increase in patient self-referrals. Direct psychological intervention sessions consequently increased as a result of referrals. Additionally, there were more follow-up sessions in the community. Analysis of the focus group derived three main themes Supporting the team, Patient experience and Ward based role, demonstrating that staff perceived numerous additional benefits of the CAP role. Conclusion: CAPs provide a cost effective way of improving access to psychological interventions on acute wards. CAPs may offer a way for psychology to become more present on acute wards and better integrated into staff teams.

0165 Prevalence of insomnia and/or obstructive sleep apnea in a sample of fit-for-duty U.S. Navy sailors

Abstract Introduction Obstructive sleep apnea (OSA) and insomnia are prevalent sleep disorders, known to negatively impact sleep and well-being in civilian populations. Studies of these sleep disorders in military populations have focused on individuals seeking treatment for a sleep disorder, rather than the general active-duty service member (ADSM). In this study, we investigated the prevalence of OSA and insomnia in U.S. Navy sailors serving on surface ships. Methods We analyzed pre-collected data from 548 fit-for-duty sailors (MD age=25 years, IQR=9; 79.4% males) serving on nine US Navy surface ships. Sailors reported their demographic information, health-related habits, and whether they had been diagnosed with OSA and/or insomnia. Sleep was assessed with wrist-worn actigraphy (371 sailors). Results Approximately 66.8% of sailors reported having an exercise routine, 83.6% reported drinking caffeinated beverages, and 29.1% used nicotine products. In terms of disorders, 15 (2.7%) male sailors reported having been diagnosed with OSA, 12 (2.2%) with insomnia (8 males, 4 females), and one (0.2%) male sailor with comorbid insomnia and OSA. Compared to sailors without a sleep disorder, sailors with OSA were older (MD=34 years, IQR=7; p&amp;lt;0.001) and had a higher proportion of nicotine users (53.3%) (p=0.041). Sailors with insomnia did not differ from sailors with no sleep disorder in terms of demographics and habits. The average daily sleep duration was 6.4±1.0 hours, which did not differ between disorder groups. However, sailors with insomnia had more sleep episodes per day (MD=1.7; IQR=0.9) than sailors without a sleep disorder (MD=1.3, IQR=0.5; p=0.042). Conclusion Only ~5% of the sailors in our study reported a diagnosis of OSA and/or insomnia, whereas one in three people in the general population has a sleep disorder. Notably, all sailors, regardless of sleep disorder diagnosis, exhibited short sleep durations. Previous studies of ADSMs found that ~48% reported poor enough sleep quality to meet the diagnostic criteria for a sleep disorder. Thus, our results suggest that, despite evidence that many Sailors exhibited sleep problems, sleep disorders are significantly underdiagnosed in ADSMs. Support (If Any) This work was supported in part by the Naval Medical Research Center's Naval Advanced Medical Development Program (MIPR N3239820WXHN007).

A remote field course implementing high-resolution topography acquisition with geomorphic applications

Abstract. Here we describe the curriculum and outcomes from a data-intensive geomorphic analysis course, “Geoscience Field Issues Using High-Resolution Topography to Understand Earth Surface Processes”, which pivoted to virtual in 2020 due to the COVID-19 pandemic. The curriculum covers technologies for manual and remotely sensed topographic data methods, including (1) Global Positioning Systems and Global Navigation Satellite System (GPS/GNSS) surveys, (2) Structure from Motion (SfM) photogrammetry, and (3) ground-based (terrestrial laser scanning, TLS) and airborne lidar. Course content focuses on Earth-surface process applications but could be adapted for other geoscience disciplines. Many other field courses were canceled in summer 2020, so this course served a broad range of undergraduate and graduate students in need of a field course as part of degree or research requirements. Resulting curricular materials are available freely within the National Association of Geoscience Teachers' (NAGT's) “Teaching with Online Field Experiences” collection. The authors pre-collected GNSS data, uncrewed-aerial-system-derived (UAS-derived) photographs, and ground-based lidar, which students then used in course assignments. The course was run over a 2-week period and had synchronous and asynchronous components. Students created SfM models that incorporated post-processed GNSS ground control points and created derivative SfM and TLS products, including classified point clouds and digital elevation models (DEMs). Students were successfully able to (1) evaluate the appropriateness of a given survey/data approach given site conditions, (2) assess pros and cons of different data collection and post-processing methods in light of field and time constraints and limitations of each, (3) conduct error and geomorphic change analysis, and (4) propose or implement a protocol to answer a geomorphic question. Overall, our analysis indicates the course had a successful implementation that met student needs as well as course-specific and NAGT learning outcomes, with 91 % of students receiving an A, B, or C grade. Unexpected outcomes of the course included student self-reflection and redirection and classmate support through a daily reflection and discussion post. Challenges included long hours in front of a computer, computing limitations, and burnout because of the condensed nature of the course. Recommended implementation improvements include spreading the course out over a longer period of time or adopting only part of the course and providing appropriate computers and technical assistance. This paper and published curricular materials should serve as an implementation and assessment guide for the geoscience community to use in virtual or in-person high-resolution topographic data courses that can be adapted for individual labs or for an entire field or data course.

Adaptive Sparse Domain Selection for Weather Radar Superresolution

Accurate and high-resolution weather radar data reflecting detailed structure information of radar echo plays an important role in analysis and forecast of extreme weather. Typically, this is done using interpolation schemes, which only use several neighboring data values for computational approximation to get the estimated, resulting the loss of intense echo information. Focus on this limitation, a superresolution reconstruction algorithm of weather radar data based on adaptive sparse domain selection (ASDS) is proposed in this article. First, the ASDS algorithm gets a compact dictionary by learning the precollected data of model weather radar echo patches. Second, the most relevant subdictionaries are adaptively select for each low-resolution echo patches during the spare coding. Third, two adaptive regularization terms are introduced to further improve the reconstruction effect of the edge and intense echo information of the radar echo. Experimental results show that the ASDS algorithm substantially outperforms interpolation methods for ×2 and ×4 reconstruction in terms of both visual quality and quantitative evaluation metrics.

SP1.1.4The Walking Thread – What happens to fistula-in-ano patients who are lost to follow up? A Service Improvement Study

Abstract Aims Management of perianal abscess and resultant fistula-in-ano remains controversial. Studies suggest that 1/3 of idiopathic cryptoglandular abscesses can result in fistula-in-ano. Our current practice is to incise and drain primary abscesses and for patients to return as necessary. Known fistula patients will be appointed for Examination Under Anaesthetic (EUA) at 6-12 weeks. Does this result in best management or do they become “elective emergencies”? Methods A retrospective audit of management of fistula-in-ano over 4 years was conducted, utilising precollected data of Cryptoglandular abscesses, excluding inflammatory, radiation or malignant causes. Patients lost to follow up were analysed including presentation, fistula diagnosed at first or subsequent attendance, number of operations, number of attendances and seton placement. Results 512 patients underwent operations for cryptoglandular abscess causing fistula-in-ano between 2013 and 2017. 10% (N = 50) were lost to follow up despite documented follow up plans for 32. Of these, 18 were elective attendances, 14 emergency. 24 of the 32 had a Seton sited prior to being lost to follow up. Conclusions The various presentations (emergency, elective, clinic) and waiting lists mean these patients are presenting as emergencies whilst awaiting follow-up. Many are simply lost to follow up, with Setons in-situ. We propose a fortnightly hot-clinic system, run by second on-call registrars to assess and manage these patients. This would provide an elective clinic to allow single point of access to fistula-in-ano patients ensuring prompt follow-up and reduction in unnecessary EUA, as well as improving senior colorectal trainees exposure to perianal disease and its management.

Hourly Origin-Destination Matrix Estimation Using Intelligent Transportation Systems Data and Deep Learning.

Predicting the travel demand plays an indispensable role in urban transportation planning. Data collection methods for estimating the origin–destination (OD) demand matrix are being extensively shifted from traditional survey techniques to the pre-collected data from intelligent transportation systems (ITSs). This shift is partly due to the high cost of conducting traditional surveys and partly due to the diversity of scattered data produced by ITSs and the opportunity to derive extra benefits out of this big data. This study attempts to predict the OD matrix of Tehran metropolis using a set of ITS data, including the data extracted from automatic number plate recognition (ANPR) cameras, smart fare cards, loop detectors at intersections, global positioning systems (GPS) of navigation software, socio-economic and demographic characteristics as well as land-use features of zones. For this purpose, five models based on machine learning (ML) techniques are developed for training and test. In evaluating the performance of the models, the statistical methods show that the convolutional neural network (CNN) leads to the best performance in terms of accuracy in predicting the OD matrix and has the lowest error in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE). Moreover, the predicted OD matrix was structurally compared with the ground truth matrix, and the CNN model also shows the highest structural similarity with the ground truth OD matrix in the presented case.

A multi-objective supplier selection framework based on user-preferences

This paper introduces an interactive framework to guide decision-makers in a multi-criteria supplier selection process. State-of-the-art multi-criteria methods for supplier selection elicit the decision-maker’s preferences among the criteria by processing pre-collected data from different stakeholders. We propose a different approach where the preferences are elicited through an active learning loop. At each step, the framework optimally solves a combinatorial problem multiple times with different weights assigned to the objectives. Afterwards, a pair of solutions among those computed is selected using a particular query selection strategy, and the decision-maker expresses a preference between them. These two steps are repeated until a specific stopping criterion is satisfied. We also introduce two novel fast query selection strategies, and we compare them with a myopically optimal query selection strategy. Computational experiments on a large set of randomly generated instances are used to examine the performance of our query selection strategies, showing a better computation time and similar performance in terms of the number of queries taken to achieve convergence. Our experimental results also show the usability of the framework for real-world problems with respect to the execution time and the number of loops needed to achieve convergence.

1703 The Walking Thread – What Happens to Fistula-In-Ano Patients Who Are Lost to Follow Up? A Service Improvement Study

Abstract Aim 1/3 of idiopathic cryptoglandular abscesses can result in fistula-in-ano. Current practice is to incise and drain primary abscesses and safety net for patients to return as necessary. Known fistula patients will be appointed for Examination Under Anaesthetic at 6-12 weeks.Is this best management or do they become “elective emergencies”? Method We performed a retrospective audit of management of fistula-in-ano over 4 years. We used a precollected data set of Cryptoglandular abscesses, excluding inflammatory, radiation or malignant causes and collected data for patients lost to follow up, including presentation, fistula diagnosed at first or subsequent attendance, number of operations, number of attendances and seton placement. Results 512 patients were operated on for cryptoglandular abscess causing fistula-in-ano between 2013 and 2017. 10% (N = 50) were lost to follow up. 32 had documented follow up plans, that were not fulfilled (eg elective theatre not booked). Of these, 18 were elective attendances, 14 emergency. 24 of the 32 had a Seton sited prior to being lost to follow up Conclusions The various presentations (emergency, elective, clinic or day surgery) and long waiting lists mean many of these patients are presenting as emergencies still awaiting follow up. Many are lost to follow-up, with Setons in situ. We propose a fortnightly hot-clinic system, registrar led to assess and manage these patients. This would provide an elective clinic to allow single point of access to fistula-in-ano patients ensuring prompt follow up and reduction in unnecessary EUA, as well as improving senior colorectal trainees exposure to perianal disease and its management.