A Deep Learning Framework for Automatic Meal Detection and Estimation in Artificial Pancreas Systems

Current artificial pancreas (AP) systems are hybrid closed-loop systems that require manual meal announcements to manage postprandial glucose control effectively. This poses a cognitive burden and challenge to users with T1D since this relies on frequent user engagement to maintain tight glucose control. In order to move towards fully automated closed-loop glucose control, we propose an algorithm based on a deep learning framework that performs multitask quantile regression, for both meal detection and carbohydrate estimation. Our proposed method is evaluated in silico on 10 adult subjects from the UVa/Padova simulator with a Bio-inspired Artificial Pancreas (BiAP) control algorithm over a 2 month period. Three different configurations of the AP are evaluated -BiAP without meal announcement (BiAP-NMA), BiAP with meal announcement (BiAP-MA), and BiAP with meal detection (BiAP-MD). We present results showing an improvement of BiAP-MD over BiAP-NMA, demonstrating 144.5 ± 6.8 mg/dL mean blood glucose level (−4.4 mg/dL, p< 0.01) and 77.8 ± 6.3% mean time between 70 and 180 mg/dL (+3.9%, p< 0.001). This improvement in control is realised without a significant increase in mean in hypoglycaemia (+0.1%, p= 0.4). In terms of detection of meals and snacks, the proposed method on average achieves 93% precision and 76% recall with a detection delay time of 38 ± 15 min (92% precision, 92% recall, and 37 min detection time for meals only). Furthermore, BiAP-MD handles hypoglycaemia better than BiAP-MA based on CVGA assessment with fewer control errors (10% vs. 20%). This study suggests that multitask quantile regression can improve the capability of AP systems for postprandial glucose control without increasing hypoglycaemia.

Detecting Persistent User Behavior Using Probabilistic Counting in Network-Wide View

Persistent user behavior monitoring, which deals with finding users that occur persistently over a measurement period, is one hot topic in traffic measurement. It is significant for many applications, such as anomaly detection. Former works concentrate on monitoring frequent user behavior, such as users occurring frequently either over one measurement period or on one monitor. They have paid little attention to detect persistent user behavior over a long measurement period on multiple monitors. However, persistent users do not necessarily appear frequently in a short measurement period, but appear persistently in a long measurement period. Due to limited resource on monitors, it is not practical to collect a tremendous amount of network traffic in a long measurement period on one single monitor. Moreover, since network attackers deliberately send packets flowing through the entire managed network, it is difficult to detect abnormal behavior on one single monitor. To solve the above challenges, a novel method for detecting persistent user behavior called DPU is proposed, and it contains both online distributed traffic collection in a long measurement period on multiple monitors and offline centralized user behavior detection on the central server. The key idea of DPU is that we design the compact distributed synopsis data structure to collect the relevant information with users occurring in a long measurement period on each monitor, and we can reconstruct user IDs using simple calculations and bit settings to find users with persistent behavior on the basis of estimated occurrence frequency of users on the central server when user IDs are unknown in advance. The experiments are conducted on real traffic to evaluate the performance of detecting persistent user behavior, and the experimental results illustrate that our method can improve about 30% estimation accuracy, 40% detection precision, and accelerate about 3 times in comparison with the related method.

Relational cohesion between users and smart voice assistants

Purpose This study aims to examine users’ affective relationships with smart voice assistants (SVAs) and aims to analyze how these relationships explain user engagement behaviors toward the brands of SVAs. Drawing on relational cohesion theory, it proposes that cohesion between users and SVAs influences brand engagement behaviors, that is, continuing purchasing other products of the brand, providing knowledge to the brand and referring the brand. Design/methodology/approach Data from a survey of 717 US regular SVA users confirm the validity of the measurement scales and provide the input for the covariance-based structural equation modeling. Findings The results demonstrate that frequent user-SVA interactions evoke positive emotions, which encourage cohesive relationships. Pleasured-satisfaction and interest emerge as strong emotions. Moreover, relational cohesion between users and SVAs promotes engagement with the brand of the assistant. Originality/value This paper applies an interpersonal approach in a context that, to date, has been examined from a predominantly technological perspective. It shows that users develop positive emotions toward smart technologies through their interactions, and establishes the importance of building affective relationships. To the best of the authors’ knowledge, this is the first study to analyze cohesion between users and smart technologies and to examine the effect of this cohesion on user engagement with the brand.

Digital Bookstore

The project's main goal is to build an online book store where users can search for and buy books based on title, author, and subject. The chosen books are shown in a tabular style and the customer may buy them online using a credit card. Using this Website, the user may buy a book online rather than going to a bookshop and spending time. Many online bookstores, such as Powell's and Amazon, were created using HTML. We suggest creating a comparable website with .NET and SQL Server. An online book store is a web application that allows customers to purchase ebooks. Through a web browser the customers can search for a book by its title or author, later can add it to the shopping cart and finally purchase using a credit card transaction. The client may sign in using his login credentials, or new clients can simply open an account. Customers must submit their full name, contact details, and shipping address. The user may also provide a review of a book by rating it on a scale of one to five. The books are classified into different types depending on their subject matter, such as software, databases, English, and architecture. Customers can shop online at the Online Book Store Website using a web browser. A client may create an account, sign in, add things to his shopping basket, and buy the product using his credit card information. As opposed to a frequent user, the Administrator has more abilities. He has the ability to add, delete, and edit book details, book categories, and member information, as well as confirm a placed order. This application was created with PHP and web programming languages. The Online Book Store is built using the Master page, data sets, data grids, and user controls.

A Housing First Approach to Limiting Frequent Emergency Room Use

This article explores the use of a Housing First policy to decrease emergency room use by Canadians suffering from homelessness, an emergency department frequent user population. We explore the research evidence behind the cost-effectiveness, efficacy, and feasibility of Housing First strategies, and an overview of how a Housing First approach was successfully implemented in Canada as a national policy. While Canadian Housing First policies have demonstrated success in addressing homelessness and decreasing costly healthcare utilization, we consider policy improvements that can be made to overcome future challenges.

Exploring the Factors that Affect the Frequency of Use of Ridehailing and the Adoption of Shared Ridehailing in California

This study explores the factors that affect the use of ridehailing services (Uber, Lyft) as well as the adoption of shared (pooled) ridehailing (UberPool, Lyft Share) using data collected in California in fall 2018 using a cross-sectional travel survey. A semi-ordered bivariate probit model is estimated using this dataset. Among other findings, the model results show that better-educated, younger individuals who currently work or work and study are more likely to use shared ridehailing services than other individuals, and in particular members of older cohorts. Being white and living in a higher-income household is associated with a higher likelihood of being a frequent user of regular ridehailing but does not have statistically significant effects on the likelihood of adopting shared ridehailing. With respect to the factors limiting the use of shared ridehailing services, it was found that the increased travel time and lack of privacy discourage the adoption of shared ridehailing. Evidence is also found that some land-use features affect the likelihood of using both types of services. While the likelihood of using both ridehailing and shared ridehailing is higher in urban areas, residents of neighborhoods with higher intersection density are found to be more likely to adopt shared ridehailing only. However, some of the land-use variables become insignificant after introducing individuals’ attitudes related to land use into the model. This is an indication of residential self-selection, and the potential risk of attributing impacts to land-use features if individual attitudes are not explicitly controlled for.

A dynamic service migration strategy based on mobility prediction in edge computing

Mobile edge computing is a new computing paradigm, which pushes cloud computing capabilities away from the centralized cloud to the network edge to satisfy the increasing amounts of low-latency tasks. However, challenges such as service interruption caused by user mobility occur. In order to address this problem, in this article, we first propose a multiple service placement algorithm, which initializes the placement of each service according to the user’s initial location and their service requests. Furthermore, we build a network model and propose a based on Lyapunov optimization method with long-term cost constraints. Considering the importance of user mobility, we use the Kalman filter to correct the user’s location to improve the success rate of communication between the device and the server. Compared with the traditional scheme, extensive simulation results show that the dynamic service migration strategy can effectively improve the service efficiency of mobile edge computing in the user’s mobile scene, reduce the delay of requesting terminal nodes, and reduce the service interruption caused by frequent user movement.

Characteristics of frequent paediatric users of emergency departments in England: an observational study using routine national data

BackgroundFrequent attendances of the same users in emergency departments (ED) can intensify workload pressures and are common among children, yet little is known about the characteristics of paediatric frequent users in EDs.AimTo describe the volume of frequent paediatric attendance in England and the demographics of frequent paediatric ED users in English hospitals.MethodWe analysed the Hospital Episode Statistics dataset for April 2014–March 2017. The study included 2 308 816 children under 16 years old who attended an ED at least once. Children who attended four times or more in 2015/2016 were classified as frequent users. The preceding and subsequent years were used to capture attendances bordering with the current year. We used a mixed effects logistic regression with a random intercept to predict the odds of being a frequent user in children from different sociodemographic groups.ResultsOne in 11 children (9.1%) who attended an ED attended four times or more in a year. Infants had a greater likelihood of being a frequent attender (OR 3.24, 95% CI 3.19 to 3.30 vs 5 to 9 years old). Children from more deprived areas had a greater likelihood of being a frequent attender (OR 1.57, 95% CI 1.54 to 1.59 vs least deprived). Boys had a slightly greater likelihood than girls (OR 1.05, 95% CI 1.04 to 1.06). Children of Asian and mixed ethnic groups were more likely to be frequent users than those from white ethnic groups, while children from black and 'other' had a lower likelihood (OR 1.03, 95% CI 1.01 to 1.05; OR 1.04, 95% CI 1.01 to 1.06; OR 0.88, 95% CI 0.86 to 0.90; OR 0.90, 95% CI 0.87 to 0.92, respectively).ConclusionOne in 11 children was a frequent attender. Interventions for reducing paediatric frequent attendance need to target infants and families living in deprived areas.