Context-aware Applications Research Articles

Adaptive Middleware to Analyze and Confirm Data Centric Parameters for Data Aggregation in Federated Cloud Environment

In the last decade rapid data evolution has contributed to tremendous data movement. The efficient data movement from origin to cloud storage and vice versa leads to the significant performance of application. A software layer situated between user and cloud storage called middleware plays major role in handling data to full fill user goals and requirements. In this paper, proposed a development of middleware frameworks from generic to context aware framework. Explicit importance is given to the adaptation feature of the middleware. A preliminary background is presented to list out importance and details of adaptability of the middleware and curious differentiation in static and self-adaptive adaptation features of the middleware. The literature started with the description of many generic middleware which can be used for building applications in variety of domains and further the limitations imposed are exposed. The issues like multidisciplinary data, vendor lock-in, disparity of service and interoperability related to federated cloud services serving to the fast-developing technology are highlighted. Along with that the use of context aware data management techniques for efficient handling of federated cloud system are defined. An extensive and comprehensive analysis of context-aware middleware is presented. For skilful data management processes need of context aware application with self-adaptation capability is presented especially in response to dynamic situations in federated cloud environment. At the end three techniques to design and develop context-aware middleware are presented. Alongside, four different perspectives of realizing adaptive middleware are also detailed. The presented work concludes with the highlighted need of context aware middleware framework to enhance the performance of federated cloud system.

FlyDetect: An Android Application for Flight Detection.

Over the past years, transport mode recognition has become a large field of research. However, flight as a type of transportation has been mostly overlooked. A system for flight detection might be useful for context-aware applications, but more importantly, it can be used to automatically manage airplane mode on smartphones. Smartphones transmit radio frequency signals which could potentially interfere with aircraft systems, and it is therefore important that devices enable airplane mode to avoid this problem. This paper proposes flyDetect, a method for automatic flight mode detection and an embodiment in the form of an app that demonstrates the viability of the method. Thus, the system uses the accelerometer and barometer in an Android smartphone, can detect the start and end of a flight, and notify other apps or systems on the device when this happens. Our evaluation shows that flyDetect meets the requirements set for the solution, and the results are very promising.

Optimizing Mobile Reading Experience: Adaptive Font Size Adjustment in a Context-Aware Application

The reading experience on a mobile device can be influenced by many external elements that affect the viewing conditions. The user holding position, operating style, and the light conditions of the surroundings can all play a crucial factor in the legibility of the text. Furthermore, the user’s eye conditions may be an extra factor to consider when determining how to improve the reading experience. This study presents a context-aware application that adjusts the text font size based on the distance between the user and the device. The users select their preferred font size at certain distances in the calibration phase, accounting for individual preferences or their eye conditions, and the application uses the device’s front camera to calculate the distance in real time and adjust the font size accordingly. We present implementation details and challenges faced during development and how they were addressed. A two-part experiment ([Formula: see text] = 34) revealed that the application scored an excellent usability score while no differences were found between users with and without eye conditions, showing that both user groups find it equally usable. Additionally, initial results suggest that the visual landmarks used showed a promising start at addressing issues related to our approach.

The evaluation of the General Health Questionnaire (GHQ-12) reliability generalization: A meta-analysis.

The General Health Questionnaire (GHQ-12) is widely used for detecting psychiatric disorders, but its reliability across different populations remains to be determined. This meta-analysis aims to evaluate the reliability of GHQ-12 across varied cultural and demographic settings. This meta-analysis evaluates the reliability of General Health Questionnaire [GHQ-12]' across diverse populations, employing a systematic search strategy and rigorous inclusion criteria. This meta-analysis evaluates the General Health Questionnaire (GHQ-12) using a pre-registered protocol (CRD42023488436) to ensure unbiased results. Data from 20 studies published between 2016-2023 were analysed using a random-effects model, with quality assessment guided by COSMIN Risk of Bias and QUADAS-2. This study enhances our understanding of GHQ-12's psychometric properties. For the GHQ-12 subscales, Cronbach's alpha coefficients were 0.72 (90% CI [0.68, 0.75]) for anxiety and depression, 0.82 (90% CI [0.79, 0.86]) for social dysfunction, and 0.72 (90% CI [0.68, 0.76]) for loss of confidence. However, the analysis showed substantial heterogeneity (I2 = 90.04%), with significant variability in reliability estimates across different studies. The overall Cronbach's alpha was 0.84 (95% Cl [0.810, 0.873]) with SE = 0.016 (90% CI [0.68, 0.82], p < .05), indicating moderate to high internal consistency. Quantifying heterogeneity revealed a substantial level (se = 0.0016, I2 = 96.7%), signifying considerable variability in the reliability estimate among the studies. Results further show Cronbach's alpha coefficients range from 0.82 to 0.85 (95% Cl [0.77, 0.86 to 0.81, 0.90]) for the GHQ 12 items. While reaffirming the GHQ-12's utility in mental health assessment, our findings urge a more cautious and context-aware application of the questionnaire. The substantial heterogeneity and variability in reliability scores indicate a need for further research. Future studies should explore the reasons behind this variability, focusing on cultural, socio-economic, and methodological factors that might influence the GHQ-12's reliability. This critical analysis underscores the need for a deeper understanding of the GHQ-12's applicability and the importance of tailoring mental health assessment tools to specific population characteristics.

The EarSAVAS Dataset

Subject-aware vocal activity sensing on wearables, which specifically recognizes and monitors the wearer's distinct vocal activities, is essential in advancing personal health monitoring and enabling context-aware applications. While recent advancements in earables present new opportunities, the absence of relevant datasets and effective methods remains a significant challenge. In this paper, we introduce EarSAVAS, the first publicly available dataset constructed specifically for subject-aware human vocal activity sensing on earables. EarSAVAS encompasses eight distinct vocal activities from both the earphone wearer and bystanders, including synchronous two-channel audio and motion data collected from 42 participants totaling 44.5 hours. Further, we propose EarVAS, a lightweight multi-modal deep learning architecture that enables efficient subject-aware vocal activity recognition on earables. To validate the reliability of EarSAVAS and the efficiency of EarVAS, we implemented two advanced benchmark models. Evaluation results on EarSAVAS reveal EarVAS's effectiveness with an accuracy of 90.84% and a Macro-AUC of 89.03%. Comprehensive ablation experiments were conducted on benchmark models and demonstrated the effectiveness of feedback microphone audio and highlighted the potential value of sensor fusion in subject-aware vocal activity sensing on earables. We hope that the proposed EarSAVAS and benchmark models can inspire other researchers to further explore efficient subject-aware human vocal activity sensing on earables.

Context-Aware System for Information Flow Management in Factories of the Future

The trends of the 21st century are challenging the traditional production process due to the reduction in the life cycle of products and the demand for more complex products in greater quantities. Industry 4.0 (I4.0) was introduced in 2011 and it is recognized as the fourth industrial revolution, with the aim of improving manufacturing processes and increasing the competitiveness of industry. I4.0 uses technological concepts such as Cyber-Physical Systems, Internet of Things and Cloud Computing to create services, reduce costs and increase productivity. In addition, concepts such as Smart Factories are emerging, which use context awareness to assist people and optimize tasks based on data from the physical and virtual world. This article explores and applies the capabilities of context-aware applications in industry, with a focus on production lines. In specific, this paper proposes a context-aware application based on a microservices approach, intended for integration into a context-aware information system, with specific application in the area of manufacturing. The manuscript presents a detailed architecture for structuring the application, explaining components, functions and contributions. The discussion covers development technologies, integration and communication between the application and other services, as well as experimental findings, which demonstrate the applicability and advantages of the proposed solution.

A Systematic Literature Review on Human Activity Recognition

Human Activity Recognition (HAR) plays a significant role in several fields by automatically identifying and monitoring human activities using advanced techniques. It enhances safety, improves healthcare services, optimizes fitness routines, and enables context-aware applications in various fields. HAR contributes to a more efficient and intelligent interaction between humans and technology. It has emerged as an essential research domain with applications in healthcare, smart environments, and human-computer interaction. This study aims to provide a comprehensive survey of the evolving landscape of HAR, including key methodologies, techniques, and trends in existing research. The study discusses various applications of HAR and their significance in modern smart environments. The survey also highlights different types of HAR and data collection techniques. Additionally, it explores various methods for analyzing the collected data and provides a comprehensive analysis of existing human activity classification datasets. It offers valuable insights into understanding the strengths and limitations of various HAR techniques. The study also discusses various challenges and future directions for HAR.

Tourists’ Adoption of Context-Aware Applications: A Case Study, Using Personal Locator Beacons at the Mole National Park, Ghana

The use of technology to provide contextual information for decision-making has been a long-standing practice. The study aims to identify the antecedents influencing tourists’ use of context-aware applications. It employs the Unified Model of Electronic Government Adoption (UMEGA) and the Expectation Confirmation Model (ECM) to investigate tourists’ behaviors in the use of Personal Locator Beacons (PLBs) during the pre-adoption and post-adoption stages at the Mole National Park in Ghana. Data was analyzed using Smart PLS 3.0 software. The findings suggest that pre-adoption performance expectancy, motivational needs, and personal situation significantly affect tourists’ pre-adoption intentions to continue using context-aware applications. In addition, information recommendation, service quality, confirmation expectation, and satisfaction influenced continued use and recommendation. However, social influence and enjoyment experience did not significantly impact tourists’ behavioral intentions. The findings contribute to theory by integrating components of the two models (UMEGA &amp; ECM) and delving into the antecedents of users’ decision-making processes.

A Novel Self-Calibrated UWB-Based Indoor Localization Systems for Context-Aware Applications

A Novel Self-Calibrated UWB-Based Indoor Localization Systems for Context-Aware Applications

Smart Waiting Room: A Systematic Literature Review and a Proposal

In the past decade, Internet of Things (IoT) technologies have become more and more pervasive, allowing the development of Ambient Intelligence and Context Awareness applications. While the smart home is the chosen scenario for such technologies, a variety of environments could potentially benefit from the synergies between IoT and digital applications. Among them, the clinical waiting rooms is an environment facing several challenges, particularly after the COVID-19 pandemic. Clinical waiting rooms are crowded places associated with stress and anxiety, often linked to patients’ idling time. Nonetheless, the rise of IoT-enabled telehealth has focused attention on the possibility of changing the functions of clinical waiting rooms. In this work, we conducted a systematic literature review to identify the existing solutions for “smart waiting rooms”. The review process started with 278 works, and it identified 16 papers relevant to the topic of smart clinical waiting rooms. Moreover, the results of this review underlined that waiting rooms are a neglected research area that could take advantage of IoT and Artificial Intelligence (AI) technologies to enhance patients’ experience and support the diagnostic process. Leveraging the research directions identified in the review process, this work proposes a “Smart Waiting Room” that exploits virtual reality (VR), AI, and IoT technologies to support the diagnostic process (via a cognitive assessment) and the personalization of the patient’s context—taking into account the features of the physical environment. The prototypical smart waiting room constitutes an example of the potentialities of novel technologies applied to healthcare and can contribute to shaping the future of clinical waiting rooms.

Artificial Intelligence and Deep Learning-based Model for Indoor Environment: with Virtual Reference Tag Allocation

By the evolution of context-aware application, indoor location positioning gains much more attention worldwide. Radio Frequency Identification (RFID) is one such wireless positioning technology adopted widely. Moreover, enhancing the tracking accuracy and thus reducing the tracking error remains a challenging task in RFID based indoor environment. So as to overcome this aspect, a localization and tracking method depending on virtual reference tag (VRT) is employed in the indoor environment. This research work includes four modules like (i) data collection and Received Signal Strength Indication (RSSI) estimation;(ii) Optimal allocation of VRT using Spider Monkey Optimization (SMO) at which the allocation of VRT is made by considering number of tags, environmental factors (humidity and temperature), and SNR. Based on this data, the RFID reader allocates VRT for each grid so as to increase the tracking accuracy; (iii) Artificial Neural Network (ANN) module-based localization at which the localization of unknown tags is made; and (iv) tracking of moving target tag is carried based on Aquila Swarm Optimization-Long short-term memory (ASO-LSTM) approach. The optimization at this stage is employed to choose optimal position which enhances the accuracy of tracking. Thus, finally the location estimation is carried by this approach. The simulation is carried in NS3.26 network simulator and the performance are estimated in terms of SNR, tracking error, mean error, tracking accuracy, mean time, and standard deviation. The performance value is then compared with traditional models to show the enhancement of proposed mode over the other conventional techniques.

Information Fusion for 5G IoT: An Improved 3D Localisation Approach Using K-DNN and Multi-Layered Hybrid Radiomap

Indoor positioning is a core enabler for various 5G identity and context-aware applications requiring precise and real-time simultaneous localisation and mapping (SLAM). In this work, we propose a K-nearest neighbours and deep neural network (K-DNN) algorithm to improve 3D indoor positioning. Our implementation uses a novel data-augmentation concept for the received signal strength (RSS)-based fingerprint technique to produce a 3D fused hybrid. In the offline phase, a machine learning (ML) approach is used to train a model on a radiomap dataset that is collected during the offline phase. The proposed algorithm is implemented on the constructed hybrid multi-layered radiomap to improve the 3D localisation accuracy. In our implementation, the proposed approach is based on the fusion of the prominent 5G IoT signals of Bluetooth Low Energy (BLE) and the ubiquitous WLAN. As a result, we achieved a 91% classification accuracy in 1D and a submeter accuracy in 2D.

Multi-user conflict resolution mechanisms for smart home environments.

Context-awareness is a pervasive computing enabling technology that allows context-aware applications to respond to multiple contexts such as activity, location, temperature, and so on. When many users attempt to access the same context-aware application, user conflicts may emerge. This issue is emphasized, and a conflict resolution approach is presented to address it. Although there are other conflict resolution approaches in the literature, the one presented here is unique in that it considers the users' special cases such as their sickness, examinations, and so on when resolving conflicts. The proposed approach is helpful when several users with different special cases try to access the same context-aware application. To demonstrate the usefulness of the proposed approach, a conflict manager is integrated with the UbiREAL simulated context-aware home environment. The integrated conflict manager resolves conflicts by taking users special cases into account and employing either automated, mediated, or hybrid conflict resolution approaches. The evaluation of the proposed approach demonstrates that users are satisfied with it and that it is critical and essential to employ users' special cases in detecting and resolving users conflicts.

Context Elements Taxonomy for Intelligent Transportation Systems

Design and development of context-aware Intelligent Transportation Systems (ITS) are not trivial due to the large number of possible context elements that may be relevant to the application and the lack of structured information to guide system designers in this task. This paper proposes that context elements with common characteristics can be grouped into categories, and these categories can be organized in a taxonomy. This taxonomy could help system designers with the task of modeling and developing new context-aware ITS. We performed a literature review of 68 articles describing 70 ITS applications with context-aware features to identify context elements used in this type of application. Furthermore, we also analyzed three commercial ITS applications. We used data collected from the analysis of these 73 projects to define the categories and identify their relationships. We propose a taxonomy with 79 categories, with 57 leaf categories (a category without children subcategories). We also performed two experiments to validate whether the exposure to this taxonomy could improve the quality of an ITS application during its design, with favorable results showing a 2.7 times increase in the average amount of relevant context elements used in the application. Finally, we compiled a knowledge base of which context element categories are used in the 73 analyzed projects. It is another companion information that can be used to help system designers. The proposed taxonomy of context element categories organizes the information of the context-aware ITS domain in a way that can ease the task of designing such systems and improve the usage of context-aware features. The overall methodology used in this work to create the taxonomy for the ITS domain could be applied to other popular domains of context-aware applications.

Domain Adaptation Methods for Lab-to-Field Human Context Recognition

Human context recognition (HCR) using sensor data is a crucial task in Context-Aware (CA) applications in domains such as healthcare and security. Supervised machine learning HCR models are trained using smartphone HCR datasets that are scripted or gathered in-the-wild. Scripted datasets are most accurate because of their consistent visit patterns. Supervised machine learning HCR models perform well on scripted datasets but poorly on realistic data. In-the-wild datasets are more realistic, but cause HCR models to perform worse due to data imbalance, missing or incorrect labels, and a wide variety of phone placements and device types. Lab-to-field approaches learn a robust data representation from a scripted, high-fidelity dataset, which is then used for enhancing performance on a noisy, in-the-wild dataset with similar labels. This research introduces Triplet-based Domain Adaptation for Context REcognition (Triple-DARE), a lab-to-field neural network method that combines three unique loss functions to enhance intra-class compactness and inter-class separation within the embedding space of multi-labeled datasets: (1) domain alignment loss in order to learn domain-invariant embeddings; (2) classification loss to preserve task-discriminative features; and (3) joint fusion triplet loss. Rigorous evaluations showed that Triple-DARE achieved 6.3% and 4.5% higher F1-score and classification, respectively, than state-of-the-art HCR baselines and outperformed non-adaptive HCR models by 44.6% and 10.7%, respectively.

Toward explainable AI-empowered cognitive health assessment.

Explainable artificial intelligence (XAI) is of paramount importance to various domains, including healthcare, fitness, skill assessment, and personal assistants, to understand and explain the decision-making process of the artificial intelligence (AI) model. Smart homes embedded with smart devices and sensors enabled many context-aware applications to recognize physical activities. This study presents XAI-HAR, a novel XAI-empowered human activity recognition (HAR) approach based on key features identified from the data collected from sensors located at different places in a smart home. XAI-HAR identifies a set of new features (i.e., the total number of sensors used in a specific activity), as physical key features selection (PKFS) based on weighting criteria. Next, it presents statistical key features selection (SKFS) (i.e., mean, standard deviation) to handle the outliers and higher class variance. The proposed XAI-HAR is evaluated using machine learning models, namely, random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), naive Bayes (NB) and deep learning models such as deep neural network (DNN), convolution neural network (CNN), and CNN-based long short-term memory (CNN-LSTM). Experiments demonstrate the superior performance of XAI-HAR using RF classifier over all other machine learning and deep learning models. For explainability, XAI-HAR uses Local Interpretable Model Agnostic (LIME) with an RF classifier. XAI-HAR achieves 0.96% of F-score for health and dementia classification and 0.95 and 0.97% for activity recognition of dementia and healthy individuals, respectively.

A Bidirectional Relay-Assisted Underlay Device-to-Device Communication in Cellular Networks: An IoT Application for FinTech

The device-to-device (D2D) networks bear a close resemblance to future Internet-of-Things (IoT) networks. IoT plays a significant role in the FinTech industry, especially in data security and context-aware applications. D2D communication in cellular networks has emerged as a competent technology for the upcoming future cellular networks. To improve spectral efficiency and data secrecy, we propose a two-phase network coding-based two-way decode-and-forward (DF) relaying policy for D2D communication. First, a suitable relay node is selected considering the end-to-end signal-to-interference-plus-noise ratio (SINR). Then, an XOR-based DF operation is performed when the signal transmitted by both the D2D users (DUEs) is successfully decoded at the relay node. In order to analyze the performance of the proposed two-way communication system, we derive the outage probability expression as a function of various system parameters, such as the SINR, position of both the relays and DUEs, power splitting factor, number of relays, and data rate. Furthermore, we also derive an expression for the error probability and average throughput of the D2D link to evaluate a fair comparison of the proposed approach with the traditional methods. The analytical results are also validated with the simulation results to justify the efficacy of the proposed method.

Intelligent and Efficient IoT Through the Cooperation of TinyML and Edge Computing

The coordinated integration of heterogeneous TinyML-enabled elements in highly distributed Internet of Things (IoT) environments paves the way for the development of truly intelligent and context-aware applications. In this work, we propose a hierarchical ensemble TinyML scheme that permits system-wide decisions by considering the individual decisions made by the IoT elements deployed in a certain scenario. A two-layered TinyML-based edge computing solution has been implemented and evaluated in a real smart-agriculture use case, permitting to save wireless transmissions, reduce energy consumption and response times, at the same time strengthening data privacy and security.

Environmental Sound Classification using Hybrid Ensemble Model

Environmental sound classification (ESC) is the most trending research areas. The sounds in the surroundings such as screaming, air conditioners, and rain droplets can help in the development of context-aware applications. It is complex to process the envi- ronmental sounds as compared to speech and music due to the unstructured essence of environmental sounds. In the past, certain preprocessing techniques, feature extraction, and classification algorithms are used for ESC. Several researchers have applied ma- chine learning classifiers for ESC and certain ensemble classifiers are also used but the accuracy can be increased if instead of combining homogeneous classifiers, heterogeneous classifiers can be ensembled. In this paper, a hybrid ensemble classifier is used for ESC on the UrbanSound8k dataset and cepstral features Mel Frequency Cepstral Coefficients are used. Five different machine learning classifiers- Decision Tree, Support Vector Machine, Logistic Regression, K- Nearest Neighbour, and Naive Bayes are used to develop a hybrid ensemble model. The highest accuracy is obtained when all the five classifiers are combined. The proposed approach gives an accuracy of 79.4% and is compared with the benchmark results using individual classifiers and the former out- performs the latter. The results of the hybrid ensemble model on the UrbanSound8K dataset are also compared with the dataset ESC-10.

Building a COVID-Safe Navigation App Using a Meta-Model Based Context Server

Building context-aware applications is an already widely researched topic. It is our belief that context awareness has the potential to supplement the Internet of Things, when a suitable methodology including supporting tools will ease the development of context-aware applications. We believe that a meta-model based approach can be key to achieving this goal. In this paper, we present our meta-model based methodology, which allows us to define and build application-specific context models and the integration of sensor data without any programming. We describe how that methodology is applied with the implementation of a relatively simple context-aware COVID-safe navigation app. The outcome showed that programmers with no experience in context-awareness were able to understand the concepts easily and were able to effectively use it after receiving a short training. Therefore, context-awareness is able to be implemented within a short amount of time. We conclude that this can also be the case for the development of other context-aware applications, which have the same context-awareness characteristics. We have also identified further optimization potential, which we will discuss at the conclusion of this article.