Search

Context Data on the presence/quantification of the neurotrophic adipokines retinol-binding protein-4 (RBP4), clusterin, and pigment epithelium-derived factor (PEDF) in human cerebrospinal fluid (CSF) are scarce and migration of these adipokines across of the blood-brain barrier (BBB) is uncertain. Objective This work aimed to quantify RBP4, PEDF, and clusterin in paired serum and CSF samples of patients undergoing neurological evaluation. Methods A total of 268 patients (109 male, 159 female) were included. Adipokine serum and CSF concentrations were measured by enzyme-linked immunosorbent assay in duplicate. Results RBP4 was abundant in serum (mean, 31.9 ± 24.2 μg/mL). The serum concentrations were approximately 145 times higher than in CSF (CSF to serum RBP4 ratio, 8.2 ± 4.3 × 10–3). PEDF was detectable in serum (mean, 30.2 ± 11.7 μg/mL) and concentrations were approximately 25 times higher than in CSF (CSF to serum PEDF ratio, 42.3 ± 15.6 × 10–3). Clusterin serum concentrations were abundant with mean levels of 346.0 ± 114.6 μg/mL, which were approximately 40 times higher than CSF levels (CSF to serum clusterin ratio, 29.6 ± 23.4 × 10–3). RBP4 and PEDF serum levels correlated positively with CSF levels, which were increased in overweight/obese patients and in type 2 diabetic patients. The CSF concentrations of all 3 adipokines increased with BBB dysfunction. RBP4 in CSF correlated positively with inflammatory parameters. In detail, only RBP4 showed the kinetics and associations that are mandatory for a putative mediator of the fat-brain axis. Conclusion RBP4, PEDF, and clusterin are permeable to the BBB and increase with the measure of BBB dysfunction. RBP4 represents an inflammatory neurotrophic adipokine and is a promising mediator of the fat-brain axis.

We propose two online-learning algorithms for modeling the personal preferences of users of interactive systems. The proposed algorithms leverage user feedback to estimate user behavior and provide personalized adaptive recommendation for supporting context-dependent decision-making. We formulate preference modeling as online prediction algorithms over a set of learned policies, i.e., policies generated via supervised learning with interaction and context data collected from previous users. The algorithms then adapt to a target user by learning the policy that best predicts that user’s behavior and preferences. We also generalize the proposed algorithms for a more challenging learning case in which they are restricted to a limited number of trained policies at each timestep, i.e., for mobile settings with limited resources. While the proposed algorithms are kept general for use in a variety of domains, we developed an image-filter-selection application. We used this application to demonstrate how the proposed algorithms can quickly learn to match the current user’s selections. Based on these evaluations, we show that (1) the proposed algorithms exhibit better prediction accuracy compared to traditional supervised learning and bandit algorithms, (2) our algorithms are robust under challenging limited prediction settings in which a smaller number of expert policies is assumed. Finally, we conducted a user study to demonstrate how presenting users with the prediction results of our algorithms significantly improves the efficiency of the overall interaction experience.

Objective To develop a collection of concept-relationship-concept tuples to formally represent patients’ care context data to inform electronic health record (EHR) development. Materials and Methods We reviewed semantic relationships reported in the literature and developed a manual annotation schema. We used the initial schema to annotate sentences extracted from narrative note sections of cardiology, urology, and ear, nose, and throat (ENT) notes. We audio recorded ENT visits and annotated their parsed transcripts. We combined the results of each annotation into a consolidated set of concept-relationship-concept tuples. We then compared the tuples used within and across the multiple data sources. Results We annotated a total of 626 sentences. Starting with 8 relationships from the literature, we annotated 182 sentences from 8 inpatient consult notes (initial set of tuples = 43). Next, we annotated 232 sentences from 10 outpatient visit notes (enhanced set of tuples = 75). Then, we annotated 212 sentences from transcripts of 5 outpatient visits (final set of tuples = 82). The tuples from the visit transcripts covered 103 (74%) concepts documented in the notes of their respective visits. There were 20 (24%) tuples used across all data sources, 10 (12%) used only in inpatient notes, 15 (18%) used only in visit notes, and 7 (9%) used only in the visit transcripts. Conclusions We produced a robust set of 82 tuples useful to represent patients’ care context data. We propose several applications of our tuples to improve EHR navigation, data entry, learning health systems, and decision support.

This article sets in context Data Warehouses (DWs) and Online Analytical Processing (OLAP) against the backdrop of databases and Big Data and shows how data warehouses and OLAP were incorporated in...

As the data or information gets increased in various applications, it is very much essential to make the retrieval and modeling easier and simple. Number of modeling aspects already exists for this crisis. Yet, context awareness modeling plays a significant role in this. However, there requires some advancement in modeling system with the incorporation of advanced technologies. Hence, this survey intends to formulate a review on the context-aware modeling in two aspects: context data retrieval and context data modeling. Here, the literature analyses on diverse techniques associated with context awareness modeling. It reviews 60 research papers and states the significant analysis. Initially, the analysis depicts various applications that are contributed in different papers. Subsequently, the analysis also focuses on various features such as web application, time series model, intelligence models and performance measure. Moreover, this survey gives the detailed study regarding the chronological review and performance achievements in each contribution. Finally, it extends the various research issues, mainly the adoption of Evolutionary algorithms, which can be useful for the researchers to accomplish further research on context-aware system.

Jednym z kluczowych elementów dla zdrowego starzenia się jest prawidłowe żywienie, w tym odpowiednia ilość i rodzaj spożywanych warzyw i owoców, jednakże seniorzy zazwyczaj nie jedzą wystarczającej ilości produktów z tych grup. W artykule przedstawiono dane na temat roli owoców i warzyw w zmniejszaniu ryzyka wystąpienia takich chorób, jak schorzenia układu krążenia, osteoporoza, przewlekła obturacyjna choroba płuc, depresja, zaburzenia funkcji poznawczych, niektóre rodzaje nowotworów, a także umieralności. W tym kontekście zaprezentowano dane dotyczące częstości spożywania warzyw i owoców przez osoby starsze, które wskazują na niezadawalającą realizację zaleceń żywieniowych. Częstsze spożywanie tych produktów zaobserwowano wśród kobiet, u osób z wyższym wykształceniem, u stosujących leki lub specjalną dietę. Posiadanie protezy zębowej istotnie zmniejszało spożycie owoców. Większa wiedza żywieniowa dotycząca owoców i warzyw związana była z częstszym spożyciem tych produktów. W związku z powyższym, prowadzenie żywieniowych programów edukacyjnych wydaje się szczególnie istotne wśród osób starszych. Słowa kluczowe: osoby starsze, owoce, warzywa, częstość spożycia, wiedza żywieniowa

The PhD project presented in this paper aims to design a trust management infrastructure that allows to assess the trustworthiness of context data in the scope of access control with the IoT. The main requirements for this design are independence from the underlying access control model and flexibility of trust calculation schemes based on application needs.

In the field of Human Activity Recognition (HAR) the majority of approaches exploit fully supervised methodologies to process inertial sensor data collected from the users’ wearable devices. Unfortunately, those solutions require users to collect a large number of annotated examples to train the recognition model, which is costly, unpractical, and time-consuming. In this paper, we propose diverse semi-supervised methodologies to tackle the data scarcity issue in the field of HAR. In particular, in Caviar and ProCaviar we introduce novel knowledge-based reasoning engines that exploiting the context data (e.g. semantic location, weather condition) allows a statistical classifier trained with a limited number of example to recognise a wide set of activities. Then, we propose FedHAR an hybrid semi-supervised and Federated-learning based system that enables distributing the training of an activity recognition model among a large number of subject, reducing the effort required from users to collect annotated data while preserving their privacy.

The Internet of Things (IoT) and Industrial 4.0 bring enormous potential benefits by enabling highly customised services and applications, which create huge volume and variety of data. However, preserving the privacy in IoT and Industrial 4.0 against re-identification attacks is very challenging. In this work, we considered three main data types generated in IoT: context data, continuous data, and media data. We first proposed a stream data anonymisation method based on k-anonymity for data collected by IoT devices; and then privacy enhancing techniques for both continuous data and media data were proposed for different IoT scenarios. The experiment results show that the proposed techniques can well preserve privacy without significantly affecting the utility of the data.

At present, user researchers have problems in UX (User experience) data analysis, such as low efficiency, inaccurate context data identification, and low satisfaction of analysis process. Therefore, in order to solve these problems, this paper proposes a design context UX data analysis system to compensate for the shortcomings in the data analysis process. This paper takes the analysis of UX data collected by the CAUX (Context-Aware User Experience) tool as an example, using the relevant methods in Cognitive Task Analysis (CTA), and on the basis of sensemaking loop model, explore the data analysis process of UX researchers through experiments. And carry out demand research for each stage of the analysis process, design a context UX data analysis system according to the requirements. This thesis summarizes the model of UX data analysis process, completes the design of context UX data analysis system, and evaluation experiment proves that the system can effectively solve the problems in the UX data analysis process, and provides a new idea for the UX research practice in the mobile Internet environment.

Literature exists granted electronic service quality delivery through Websites is a fundamental approach to success. Toward providing superior service quality, decision-makers of organizations with Web presences must first realize how customers develop online customer loyalty. In-formation about this topic limited from both academic and practitioner sources; however, this information should be examined in multi-context by using multiple e-SQ dimensions. This study employs the systematic review approach to review and synthesize the literature of electronic service quality and its effects on e-satisfaction, e-trust, e-shopping, and e-loyalty, illustrate what is known about the topic, and provide a set of recommendations and future research avenues. Moreover, discussion for how artificial intelligence Technology guided e-services among online shopping websites.

In this paper, we focus on realizing a zero-energy consumption scheme based on the hybrid memory with limited size of NVM. To achieve minimized NVM requirement, three techniques are proposed to solve the conflict between the context data size and NVM capacity during the suspend process. We build a system suspend/resume mode to evaluate data size and timing. The experiment results show that the amount of data which needs to be saved is reduced by 59% and the demand for NVM size is reduced by 51%, with little impact on system resuming time.

International audience; This paper considers generalizing context reasoning capabilities through a context mining facility offered to all Information System applications. This facility requires mining context data at the system scale, which raises several challenges for Machine Learning approaches used for such mining. Through a detailed literature review, we analyze these approaches with regard to the requirements of such a context mining facility at the Information System level, pointing to the potential and to the challenges raised by this perspective.

Biometric technology based on the human gait identifies people even if a person's face is covered, hidden or invisible to cameras in a dark environment. This paper presents a method of human motoric feature identification based on image recognition. One way of image recognition is described – the Haar Cascade method in conjunction with the classifier training process. Classifiers trained on MPII Human Pose and Microsoft Common Objects in Context data were used to recognize a human figure in an image. In the identification method described, joint movement parameters and characteristic body parts were analyzed. Five people were surveyed and recorded twice. The data obtained after the analysis of the first recordings, made with a camera placed at the front, served as benchmarks in the process of comparison with data from the second recordings (from behind the identified person). Data analysis was performed using a Microsoft Excel spreadsheet.

We present a sleep timing estimation approach that combines data-driven estimators with an expert model and uses smartphone context data. Our data-driven methodology comprises a classifier trained on features from smartphone sensors. Another classifier uses time as input. Expert knowledge is incorporated via the human circadian and homeostatic two process model. We investigate the two process model as output filter on classifier results and as fusion method to combine sensor and time classifiers. We analyse sleep timing estimation performance, in data from a two-week free-living study of 13 participants and sensor data simulations of arbitrary sleep schedules, amounting to 98280 nights. Five intuitive sleep parameters were derived to control the simulation. Moreover, we investigate model personalisation, by retraining classifiers based on participant feedback. The joint data and expert model yields an average relative estimation error of -2±62 min for sleep onset and -5±70 min for wake (absolute errors 40±48 min and 42±57 min, mean median absolute deviation 22 min and 15 min), which significantly outperforms data-driven methods. Moreover, the data and expert models combination remains robust under varying sleep schedules. Personalising data models with user feedback from the last two days showed the largest performance gain of 57% for sleep onset and 59% for wake up. Our power-efficient smartphone app makes convenient everyday sleep monitoring finally realistic.

Society’s increasing reliance on technology, fueled by a growing desire for increased connectivity (given the increased productivity, efficiency, and availability to name a few motivations) has helped give rise to the compounded growth of electronic data. The increasing adoption of various technologies has driven the need to protect said technologies as well as the massive amount of electronic data produced by them. Almost every type of new technology created today, from homes and cars to fridges, toys, and stoves, is designed as a smart device, generating data as an auxiliary function. These devices are all now part of the Internet of Things (IoT), which is comprised of devices that have embedded sensors, networking capabilities, and features that can generate significant amounts of data. Not only has society seen a dramatic rise in the use of IoT devices, but there has also been a marked evolution in the way that businesses use these technologies to deliver goods and services. These include banking, shopping, and procedure-driven processes. These enhanced approaches to delivering added value create avenues for misuse and increase the potential for criminal activities by utilizing the digital information generated for malicious purposes. This threat requires protecting this information from unauthorized access, as this data (ranging from sensitive personal data, demographic data, business data, to system data and context data) can be monetized by criminals.

Structural directives change the layout of the HTML document by adding and removing elements. They build on the core features available for attribute directives, described in Chapter 15, with additional support for micro-templates, which are small fragments of contents defined within the templates used by components. You can recognize when a structural directive is being used because its name will be prefixed with an asterisk, such as *ngIf and *ngFor. In this chapter, I explain how structural directives are defined and applied, how they work, and how they respond to changes in the data model. Table 16-1 puts structural directives in context.

Context Aware (CA) systems that adapt to user behaviors have many real-world uses. CA systems require accurately labeled training data to learn models of users’ context behavior. Unfortunately, it is difficult to gather sufficient realistic context data in controlled environments where reliable labels can be gathered. Therefore, recent works have used in-the-wild study designs, where data is gathered through passive sensing devices such as smartphones while users periodically supply corresponding context labels. However, labels gathered this way can be unreliable as users may provide incomplete or inaccurate labels which makes it difficult to build robust CA models. We propose DELFI (Detecting Erroneous Labels using Feature-linking Insights), a visual analytics approach to discover and clean unlabeled or mislabeled context data. Visualizations enable highlighting of similar data to find patterns and anomalies in behaviors. However, this is challenging when working with erroneous human-labelled data as linking similar context labels is flawed since the labels themselves are in question. DELFI identifies probably-mislabeled instances by color-coding them based on an anomaly score. Additionally, DELFI links similar instances based on a novel concept called Multi-Feature Similarity Linking, which facilitates the identification of probably true labels of mislabeled and unlabeled data. We demonstrate the utility of our approach with use cases and evaluation from domain experts.

Context is widely considered for NLP and knowledge discovery since it highly influences the exact meaning of natural language. The scientific challenge is not only to extract such context data, but also to store this data for further NLP approaches. Here, we propose a multiple step knowledge graphbased approach to utilize context data for NLP and knowledge expression and extraction. We introduce the graph-theoretic foundation for a general context concept within semantic networks and show a proof-of-concept-based on biomedical literature and text mining. We discuss the impact of this novel approach on text analysis, various forms of text recognition and knowledge extraction and retrieval.

Adding context-awareness capabilities to modern mobile and pervasive computing applications is becoming a mainstream activity in the software engineering community. In this respect, many context models and middleware architectures have been proposed with the aim to provide the developers with tools and abstractions that make it easier to produce context-aware applications. However, current solutions suffer from relatively low reusability and lack ease-of-use. In this paper, we propose a two-layer approach based on model-driven development: at the higher layer we introduce the design of reusable context plug-ins which can be used to monitor low-level context data and to infer higher-level information about the users, their computing infrastructure and their interaction. At the lower layer, the plug-ins themselves are synthesized using more elementary, reusable components. We argue that this development approach provides significant advantages to the developers, as it enables them to design, implement, re-use and maintain the code-base of context-aware apps more efficiently. To evaluate this approach, we demonstrate it in the context of a two-part case-study and assess it both qualitatively and quantitatively.

Smartphone has been a popular device utilized to support productivity in human life and has become an integral part of human activities such as for communication, entertainment and social interaction. Those activities can be related to the information which needs to be protected because of its high privacy. Therefore, the smartphone needs a procedure that demonstrates an ability to secure that user information. However, more protective the scheme, more difficult the usage. Based on that pattern behavior, a good security scheme which support the users for easy security feature is urgently needed. One of such kind security features is authentication feature. In that manner, the ease of use aspect for acquiring the system by using an easy authentication mechanism becomes critically important. The ease of use intended is the efficiency of interaction between the user and that security feature for doing authentication including the time needed for doing that. This study developed the app which utilizes the context data, namely Geofilock. The context data meant is the location data based on the GPS and MAC address of the Wi-Fi. The system detected both context data and determined whether the smartphone needs to show the pattern screen lock as authentication feature or not, based on the context data analysis. The functionality of Geofilock works properly as shown by less user interaction number and less time needed by the user for obtaining the access. In addition, the app is easy to operate, as suggested by the user feedback.

Background and aims Most studies reporting alcohol use among fatally injured victims are subject to bias, particularly that related to sample selection and to absence of injury context data. We developed a research method to estimate the prevalence of alcohol consumption and test correlates of alcohol use prior to fatal injuries. Design, Setting and Participants Cross-sectional study based on a probability sample of fatally injured adult victims (N = 365) autopsied in Sao Paulo, Brazil. Victims were sampled within systematically selected 8-hour sampling blocks, generating a representative sample of fatal injuries occurring during all hours of the day for each day of the week between June 2014 and December 2015. Measurements The presence of alcohol and blood alcohol concentration (BAC) were the primary outcomes evaluated according to victims’ socio-demographic, injury context data (type, day, time and injury place), and criminal history characteristics. Findings Alcohol was detected in 30.1% (CI 95%; 25.6-35.1) of the victims, with a mean BAC level of 0.11% w/v (CI 95%; 0.09-0.13) among alcohol-positive cases. Black and mixed race victims presented a higher mean BAC than white victims (p = 0.03). Fewer than one in every six suicides tested positive for alcohol, while almost half of traffic-related casualties were alcohol-positive. Having suffered traffic-related injuries, particularly those involving vehicle crashes, and injuries occurring during weekends and at night were significantly associated with alcohol use before injury (p

Building systems that acquire, process and reason with context data is a major challenge. Model updates and modifications are required for the mobile context-aware systems. Additionally, the nature of the sensor-based systems implies that the data required for the reasoning is not always available nor it is certain. Finally, the amount of context data can be significant and can grow fast, constantly being processed and interpreted under soft real-time constraints. Such characteristics make it a case for a challenging big data application. In this paper we argue, that mobile context-aware systems require specific methods to process big data related to context, at the same time being able to handle uncertainty and dynamics of this data. We identify and define main requirements and challenges for developing such systems. Then we discuss how these challenges were effectively addressed in the KnowMe project. In our solution, the acquisition of context data is made with the use of the AWARE platform. We extended it with techniques that can minimise the power consumption as well as conserve storage on a mobile device. The data can then be used to build rule models that can express user preferences and habits. We handle the missing or ambiguous data with number of uncertainty management techniques. Reasoning with rule models is provided by a rule engine developed for mobile platforms. Finally, we demonstrate how our tools can be used to visualise the stored data and simulate the operation of the system in a testing environment.

Context: modern software increasingly relies on contexts about computing environments to provide adaptive and smart services. Such contexts, captured and derived from environments of uncontrollable noises, can be inaccurate, incomplete or even in conflict with each other. This is known as the context inconsistency problem, and should be addressed by checking contexts in time to prevent abnormal behavior to applications. One popular way is to check application contexts against consistency constraints before their uses, but this can bring heavy computation due to tremendous amount of contexts in changing environments. Existing efforts improve the checking performance by incremental or concurrent computation, but they rely on CPU computing only and can consume valuable CPU capabilities that should otherwise be used by applications themselves.Objective: in this article, we propose GAIN, a GPU-supported technique to checking consistency constraints systematically and efficiently.Method: GAIN can automatically recognize a constraint's parallel units and associate these units and their runtime instances with matched contexts under checking. GAIN coordinates CPU and GPU and utilizes their capabilities for task preparation and context checking, respectively.Result: we evaluate GAIN experimentally with millions of real-life context data. The evaluation results show that GAIN can work at least 2-7 × faster and requires much less CPU usage than CPU-based techniques. Besides, GAIN can also work stably for different and varying workloads.Conclusion: our experience with GAIN suggests its high efficiency in constraint checking for context consistency as well as its wide applicability to different application workloads.

Monitoring human activities provides context data to be used by computational systems, aiming a better understanding of users and their surroundings. Uncertainty still is an obstacle to overcome when dealing with context-aware systems. The origin of it may be related to incomplete or outdated data. Attribute Grammars emerge as a consistent approach to deal with this problem due to their formal nature, allowing the definition of rules to validate context. In this paper, a model to validate human daily activities based on an Attribute Grammar is presented. Context data is analysed through the execution of rules that implement semantic statements. This processing, called semantic analysis, will highlight problems that can be raised up by uncertain situations. The main contribution of this paper is the proposal of a rigorous approach to deal with context-aware decisions (decisions that depend on the data collected from the sensors in the environment) in such a way that uncertainty can be detected and its harmful effects can be minimized., This work has been supported by national funds through FCT – Fundação para a Ciência e Tecnologia ˆ within the Project Scope: UID/CEC/00319/2019.

Novel smart devices are equipped with various sensors to capture context data. The Internet of Things (IoT) connects these devices with each other in order to bring together data from various domains. Due to the IoT, new application areas come up continuously. For instance, the quality of life and living can be significantly improved by installing connected and remote-controlled devices in Smart Homes. Or the treatment of chronic diseases can be made more convenient for both, patients and physicians, by using Smart Health technologies.

Urban traffic sensing has been investigated extensively by different real-time sensing approaches due to important applications such as navigation and emergency services. Basically, the existing traffic sensing approaches can be classified into two categories, i.e., explicit and implicit sensing. In this paper, we design a measurement framework called EXIMIUS for a large-scale data-driven study to investigate the strengths and weaknesses of these two sensing approaches by using two particular systems for traffic sensing as concrete examples, i.e., a vehicular system as a crowdsourcing-based explicit sensing and a cellular system as an infrastructure-based implicit sensing. In our investigation, we utilize TB-level data from two systems: (i) vehicle GPS data from 3 thousand private cars and 2 thousand commercial vehicles, (ii) cellular signaling data from 3 million cellphone users, from the Chinese city Hefei. Our study adopts a widely-used concept called crowdedness level to rigorously explore the impacts of various spatiotemporal contexts on real-time traffic conditions including population density, region functions, road categories, rush hours, etc. based on a wide range of context data. We quantify the strengths and weaknesses of these two sensing approaches in different scenarios then we explore the possibility of unifying these two sensing approaches for better performance. Our results provide a few valuable insights for urban sensing based on explicit and implicit data from transportation and telecommunication domains.

Recently, Clouds are wildly used for huge data repository and Internet services in various fields. And IoT networks collect a context data and support the monitoring and control services using thing virtualization. We will build the connection between IoT and cloud, it is very useful, and supports intelligent services based on huge context data. This paper presents the comparison analysis of IoT services based on Clouds for huge context acquisition in large scale IoT networks. And, we develop AWS, Azure, and Google cloud based on IoT, and compare the IoT service of AWS, Azure, and Google Cloud by sending sensing data messages from IoT devices. The comparison helps users to choose easily IoT service based on Cloud. Hence, it is necessary to collect the context data easily and extract useful part for information analysis and usage in Cloud based on IoT.

IoT platforms are the key solution to provide context data network using the sensor devices, and support backend applications that make sense of the mass of data generated by thousands of sensors. The global IoT platform market continues to rise significantly. To enable the interoperability among heterogeneity of IoT platforms becomes a big challenge for the development trend of the IoT nowadays. This paper presents an open framework based IoT interoperability architecture. This architecture offers the required functionalities for integrating with heterogeneous IoT platforms using open framework based on RESTful. Proposed open framework was designed to facilitate the integration of multiple IoT platforms in different standards. The result of our work indicates that the proposed architecture assists the development of interoperable IoT ecosystems.

This chapter highlights the approach of interlinking diverse context sources to the semantically enriched network topology data of the OpenMobileNetwork in order to enable sophisticated context-aware services as shown in Chap. 7. For this purpose, Sect. 5.1 describes the interlinking process with already available context data in the LOD Cloud. Taking the limitations of the available geo-related linked datasets as a reference, Sect. 5.2 presents Linked Crowdsourced Data as a new dataset incorporating not only static, but also diverse and dynamic context information associated with locations. In addition, the OpenMobileNetwork Geocoding Dataset is introduced in Sect. 5.3 as another context source that interconnects address data to the OpenMobileNetwork for enabling address-related services such as geocoding.

Los sistemas de salud en todo el mundo afrontan el desafío de combatir el gran incremento de enfermedades crónicas no transmisibles (ECNT), especialmente enfermedades cardiovasculares. Estas enfermedades pueden ser prevenidas si se logra la adopción de hábitos y estilos de vida saludables por parte de las personas, fundamentalmente el incremento de la actividad física y la nutrición sana. El objetivo de este artículo es describir el proceso de modelado de un sistema consciente del contexto, con el fin de soportar intervenciones que promuevan la actividad física y dieta saludable y se adapten a las características del contexto del usuario. Los principales resultados de este trabajo son a) un modelo de clasificación del contexto en salud y un modelo del proceso de adaptabilidad y personalización del contexto, b) una propuesta de un modelo de contexto para un sistema consciente en el contexto que apoye la promoción de actividad física y nutrición saludable, c) una arquitectura de referencia y un prototipo del sistema desarrollado sobre esta arquitectura, el cual consiste en una aplicación móvil soportada en tecnologías NFC y GPS y d) la evaluación de la usabilidad de la solución. Health systems around the world are currently facing a challenge to fight the tremendous growth of non-transmissible chronic diseases (NTCD), especially cardiovascular diseases. These diseases can be prevented if adoption of healthy habits and lifestyles are adopted by people, specifically by increasing their physical activity and having a healthy nutrition. The objective of this article is to describe the modeling process of a contextaware system with the purpose of supporting interventions to promote physical activity and healthy nutrition, duly adjusted to the characteristics of the user’s context. The main results of this article are: a) a classification model of health context and a context adaptability and personalization process model; b) a proposal of a context model for a context-aware system, which supports the promotion of physical activity and healthy nutrition; c) a reference architecture and a prototype of the system developed on such architecture, which consists of a mobile application supported by NFC and GPS technologies; and d) an evaluation of the solution usability.

Over the last decade, researchers are investigating the potential of the educational paradigm shift from the traditional “one-size-fits all” teaching approach to an adaptive and more personalized study process. Availability of fast mobile connections along with the portative handheld device evolution, like phones and tablets, enable teachers and learners to communicate and interact with each other in a completely different way and speed. The mentioned devices not only deliver tutoring material to the learner, but might also serve as sensors to provide data about the learning process itself, e.g., learning conditions, location, detailed information on learning of tutoring material and other information. This sensor data put into the context of the study process can be widely used to improve student experience in the classroom and e-learning by providing more precise and detailed information to the teacher and/or an intelligent tutoring system for the selection of an appropriate tutoring strategy. This paper analyses and discusses acquisition, processing, and application scenarios of contextual information.

Intelligent home network has to notify the context data instantly to the profiler when home device user's main context such as user and access right are changed and renew the profiling with the updated context [1]. To make it sense, we propose the profile based intelligent home network device access control. It includes; (1) Intelligence profiling generation study (2) an intelligent home network configuration and management study, and (3) an intelligent profiling multiple signature study. So, in this study, it suggests a secure profile structure.

Smart homes identify the implicit intentions and needs of occupants through the detection of the activities of residents and their internal environment, and they provide a convenient service to them. In smart home research, context-awareness technology is essential. Context-awareness research requires a large amount of data of residents’ activities in living spaces. Data collection using a simulator is a recently developed method to overcome the difficulties of data collection in the real world, and to get consistent data. In this paper we present the usage of a simulator consisting of a virtual space similar to an actual living space, with virtual sensors and virtual character. Through this simulation we collected user context data which has a high probability in the real world. Collected data is analyzed via a classifier, and resultantly a user activity reasoning model in a virtual living space is generated.

Human mobility prediction is of great advantage in route planning and schedule management. However, mobility data is a high-dimensional dataset in which multi-context prediction is difficult in a single model. Mobility data can usually be expressed as a home event, a work event, a shopping event and a traveling event. Previous works have only been able to learn and predict one type of mobility event and then integrate them. As the tensor model has a strong ability to describe high-dimensional information, we propose an algorithm to predict human mobility in tensors of location context data. Using the tensor decomposition method, we extract human mobility patterns with multiple expressions and then synthesize the future mobility event based on mobility patterns. The experiment is based on real-world location data and the results show that the tensor decomposition method has the highest accuracy in terms of prediction error among the three methods. The results also prove the feasibility of our multi-context prediction model.

As the basic paradigm of health management has changed from diagnosis and treatment to preventative management, health improvement and management has received growing attention in societies around the world. Recently the number of obese youth has risen globally and obesity has caused serious problems regarding almost all of the diseases of these days. This study presents dietary nutrition recommendations based on knowledge for obese youth. The knowledge-based dietary nutrition recommendations herein include not only static dietary nutritional data but also individualized diet menus for them by utilizing knowledge-based context data through a collaborative filtering method. The suggested method utilizes the basic information on obese youth, forms a similarity clustering with a high correlation, applies the similarity weight on {user-menu} matrix within the similarity clustering and utilizes the knowledge based collaborative filtering to recommend the dietary nutritional menu. Also by using the knowledge-based context-aware modeling, the study constitutes a {user-menu} merge matrix and solves the sparse problem of previous recommendation system. The suggested method herein, unlike the conventional uniformed dietary nutrition recommendations for obesity management, is capable of providing the personalized recommendations. Also through mobile devices, users can receive personalized recipes and menus anytime and anywhere. By using the proposed method, the researcher develops a mobile application of dietary nutrition recommendation service for obese management. A mobile interface will be built herein and applied in an experiment to test its logical validity and effectiveness.

Applications for the Internet of Things are becoming increasingly popular. Due to the large amount of available context data, such applications can be used effectively in many domains. By interlinking these data and analyzing them, it is possible to gather a lot of knowledge about a user. Therefore, these applications pose a threat to privacy. In this paper, we illustrate this threat by looking at a real-world application scenario. Current state of the art focuses on privacy mechanisms either for Smart Things or for big data processing systems. However, our studies show that for a comprehensive privacy protection a holistic view on these applications is required. Therefore, we describe how to combine two promising privacy approaches from both categories, namely AVARE and PATRON. Evaluation results confirm the thereby achieved synergy effects.

Among many semantic segmentation works using deep learning methods, fusing multiple layer features usually could boost performance. Multi-layer feature fusion could obtain more comprehensive context information. However, fusing different layers leads to different experiment results. There is no unified method to select effective layers to fuse in previous works, which mostly relied on intuition or experience. In this paper, we propose a fusion coefficient learning method that can guide us to select effective layers. What’s more, our approaches can be added to other works that require multi-scale fusion to further boost their performance. We proposed three principles for preliminary screening of layers and presented the fusion coefficient learning algorithm. Then, We could select the most effective layer through three steps. Our approaches are verified by massive experiments and proved to be effective on the PASCAL VOC2012, PASCAL Context data set.

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning models. Recently, Hate and Abusive Speech on Twitter, a dataset much greater in size and reliability, has been released. However, this dataset has not been comprehensively studied to its potential. In this paper, we conduct the first comparative study of various learning models on Hate and Abusive Speech on Twitter, and discuss the possibility of using additional features and context data for improvements. Experimental results show that bidirectional GRU networks trained on word-level features, with Latent Topic Clustering modules, is the most accurate model scoring 0.805 F1., Comment: ALW2: 2nd Workshop on Abusive Language Online to be held at EMNLP 2018 (Brussels, Belgium), October 31st, 2018

Nowadays travellers can benefit from the computing capabilities, collection of on board sensors and ubiquitous Internet access provided by mobile devices. These are the three pillars of any tourist support system since they provide the power, means and data to establish the local user context, to access remote services and to provide value-added user-centred context-aware applications. However, making sense of the user context data is not straightforward, as it requires dedicated knowledge acquisition and knowledge representation solutions. Besides, the range and diversity of available data sources is huge, requiring appropriate knowledge processing techniques to provide addequated tourism services. This article presents an updated review, and a comparison of recent context-aware tourism applications (CATA), including supporting technologies; and considering four possible dimensions: knowledge acquisition, knowledge representation, knowledge processing and knowledge-based services. We propose and apply a CATA analysis framework, contemplating these four dimensions to the applications found in the literature. This survey constitutes, not only, a state of the art review on tourism mobile applications, but, also, anticipates the latest development trends in tourism-related applications.

Pervasive computing allows users to benefit from information and services provided by advanced applications using smart and interconnected devices. Given the inherent complexity of this software environment, platforms become a typical means of easing the development and execution of pervasive applications. These platforms are usually in charge of managing the application context, ensuring that data are reliable and available to applications. Most platforms provide this feature, making real-time information available, even when applications do not need such information in real-time. This occurs, for example, when sensors continuously provide measurements to in-house temperature controllers and these measurements have limited time variance. Therefore, controllers can be updated only occasionally, reducing application overload without compromising effectiveness. To address this issue, in this paper, we present a pervasive platform, iCasa, extended with an autonomic manager of service-oriented context module. Our solution consists of tracking application needs and context information to achieve the best caching configuration, regarding a multi-application pervasive environment. This caching configuration can decrease the power consumption of devices due to the reduced unnecessary network communications between platform and devices.

Building systems that acquire, process and reason with context data is a major challenge, especially on mobile platforms. Constant updates of knowledge models are one of the primary requirements for the mobile context-aware systems. In this chapter we discuss selected practical results of the KnowMe project. We demonstrate the use of the formal model for uncertainty handling. We distinguish three phases that every context-aware system should pass during the development and later while operating on the mobile device. We discuss the knowledge modeling aspects and the use of the KnowMe toolset.

International audience; This paper discusses the requirements of situation identification in the Internet of Things and the necessity to consider the quality of the input context data during the inference process for deriving a situation and evaluating its resulting quality. We propose to extend previous works by integrating the QoCIM meta-model within the muSIC framework dedicated to situation identification. Situation identification is derived using an ontological approach and Quality criteria are aggregated using the fuzzy Choquet operator for computing the quality of a situation. This paper shows that QoCIM allows to model quality of context (QoC) as well as quality of situation in a unified approach

Infectious diseases are a major cause of human morbidity, but most are avoidable. An accurate and personalized risk prediction is expected to alert people to the risk of getting exposed to infectious diseases. However, as data and knowledge in the epidemiology and infectious diseases field becomes available, an updateable risk prediction model is needed. The objectives of this article are (1) to describe the mechanisms for generating a Bayesian Network (BN), as risk prediction model, from a knowledge-base, and (2) to examine the accuracy of the prediction result. The research in this paper started by encoding declarative knowledge from the Atlas of Human Infectious Diseases into an Infectious Disease Risk Ontology. Automatic generation of a BN from this knowledge uses two tools (1) a Rule Converter generates a BN structure from the ontology (2) a Joint & Marginal Probability Supplier tool populates the BN with probabilities. These tools allow the BN to be recreated automatically whenever knowledge and data changes. In a runtime phase, a third tool, the Context Collector, captures facts given by the client and consequent environmental context. This paper introduces these tools and evaluates the effectiveness of the resulting BN for a single infectious disease, Anthrax. We have compared conditional probabilities predicted by our BN against incidence estimated from real patient visit records. Experiments explored the role of different context data in prediction accuracy. The results suggest that building a BN from an ontology is feasible. The experiments also show that more context results in better risk prediction.

International audience; This paper discusses the design and development efforts made to collect data using an opportunistic crowdsensing mobile application. Relevant issues are underlined, and solutions proposed within the CHIST-ERA Macaco project for the specifics of collecting fine-grained content and context data are highlighted. Global statistics on the data gathered for over a year of collection show its quality: Macaco data provides a longterm and fine-grained sampling of the user behavior and network usage that is relevant to model and analyse for future content and context-aware networking developments.

The amount of data within the Linking Open Data (LOD) Cloud is steadily increasing and resembles a rich source of information. Since Context-aware Services (CAS) are based on the correlation of heterogeneous data sources for deriving the contextual situation of a target, it makes sense to leverage that enormous amount of data already present in the LOD Cloud to enhance the quality of these services. Within this work, the applicability of the LOD Cloud as a context provider for enriching CAS is investigated. For this purpose, a deep analysis according to the discoverability and availability of datasets is performed. Furthermore, in order to ease the process of finding a dataset that matches the information needs of a CAS developer, techniques for retrieving contents of LOD datasets are discussed and different approaches to condense the dataset to its most important concepts are shown. Finally, a Context Data Lookup Service is introduced that enables context data discovery within the LOD Cloud and its applicability is highlighted based on an example.

Vigilance decrement of traffic controllers would greatly threaten public safety. Hence, extensive studies have been conducted to establish the physiological data-based vigilance model for objectively monitoring or detecting vigilance decrement. Nevertheless, most of them using intrusive devices to collect physiological data and failed to consider context information. Consequently, these models can be used in a laboratory environment while cannot adapt to dynamic working conditions of traffic controllers. The goal of this research is to develop an adaptive vigilance model for monitoring vigilance objectively and non-intrusively. In recent years, with advanced information and communication technology, a massive amount of data can be collected from connected daily use items. Hence, we proposed a hybrid data-driven approach based on connected objects for establishing vigilance model in the traffic control center and provide an elaborated case study to illustrate the method. Specifically, eye movements are selected as the primary inputs of the proposed vigilance model; Bagged trees technique is adapted to generate the vigilance model. The results of case study indicated that (1) eye metrics would be correlated with the vigilance performance subjected to the mental fatigue levels, (2) the bagged trees with the fusion features as inputs achieved a relatively stable performance under the condition of data loss, (3) the proposed method could achieve better performance than the other classic machine learning methods.