Search

Human Activity Recognition (HAR) is a crucial research focus in the body area networks and pervasive computing domains. The goal of HAR is to examine activities from raw sensor data, video sequences, or even images. It aims to classify input data correctly into its underlying category. In the current study, machine and deep learning approaches along with different traditional dimensionality reduction and TDA feature extraction techniques are suggested to solve the HAR problem. Two public datasets (i.e., WISDM and UCI-HAR) are used to conduct the experiments. Different data balancing techniques are utilized to deal with the problem of imbalanced data. Additionally, a sampling mechanism with two overlapping percentages (i.e., 0% and 50%) is applied to each dataset to retrieve four balanced datasets. Five traditional dimensionality reduction techniques in addition to the Topological Data Analysis (TDA) are utilized. Seven machine learning (ML) algorithms are used to perform HAR where six of them are ensemble classifiers. In addition to that, 1D-CNN, BiLSTM, and GRU deep learning approaches are utilized. Three categories of experiments (i.e., ML with traditional features, ML with TDA, and DL) are applied. For the first category experiments, the best-reported scores concerning the WISDM dataset are accuracy and WSM of 99.10% and 86.61%, respectively. When concerning the UCI-HAR dataset, the best-reported scores are accuracy and WSM of 100% and 100%, respectively. For the second category experiments, the best-reported scores concerning the WISDM dataset are accuracy and WSM of 95.34% and 89.62%, respectively. When concerning the UCI-HAR dataset, the best-reported scores are accuracy and WSM of 96.70% and 92.57%, respectively. For the third category experiments, the best-reported scores concerning the WISDM dataset are accuracy and WSM of 99.90% and 99.76%, respectively. When concerning the UCI-HAR dataset, the best-reported scores are accuracy and WSM of 100% and 100%, respectively. After concluding the final results, the suggested approach is compared with 6 related studies utilizing the same dataset(s). [ABSTRACT FROM AUTHOR]

Pervasive computing has become a key element to build applications that use fun as a motivating component because it allows exploring new interaction schemes by making the concept of space and time ambiguous and confusing. The present research describes a pervasive social gaming experience, using as a reference SocialPG, which is a model that describes social expansion as a strategy to improve gaming experiences supported by pervasive computing. In this article a description of the model is offered, software architecture is proposed to support it and a case study related to the process of error resolution and detection of improvement opportunities in software products is developed, finally, a general idea about the final software product that will support the game experience is offered together with an evaluation performed by a set of users, where some important findings are highlighted, such as the importance of the missions as a unit of cooperative work and the spectator's participation. [ABSTRACT FROM AUTHOR]

As the ageing population has become a global phenomenon in the past few decades, it has brought several issues to many countries (e.g., aged care). Thailand has one of the highest ageing populations in the region, which has challenged society to find a feasible solution for promoting the elderly's quality of life while considering the vital role of caregivers in the aged care context. Thanks to the advances in ubiquitous mobile computing, mobile-based applications have become promising for the aged care sector. However, a limited number of mobile-based applications can cater to the needs of the elderly and caregivers, particularly in Thailand. Using the design thinking approach, we developed an innovative elderly caretaking system called 'Aegis' to effectively manage aged care by caregivers. Using this system, the elderly can effectively communicate with their caregivers, while the latter can easily support what the elderly need. We conducted a usability evaluation of 'Aegis' with three elderly-caregiver pairs in Thailand. The findings show that the 'Aegis' is useful in promoting the quality of life for the elderly and caregivers while considering the importance of user-friendly interface design and experiences. The usability recommendations suggested by this study can help HCI researchers understand design guidelines for intergenerational digital technologies. [ABSTRACT FROM AUTHOR]

With the constant increase in public transit coverage in Bangkok Metropolitan Area in Thailand, many people are still hesitant to switch from using private to public transit, with one potential cause being the unavailability and difficulty in accessing accurate and timely information about their itineraries, while they are commuting. To assess and tackle such issues, the researchers adopted the user-centric Design Thinking methodology to empathize with target users' pain points in this study. They proposed a solution in a user-centric manner by assessing the usability flaws of existing mobile navigation applications, such as Google Maps and ViaBus. By developing a holistic mobile application called 'Disgovery' that covers all modes of public transit in the Bangkok Metropolitan Area and provides relevant information about their trips, the researchers aim to help commuters in Bangkok easily access it in a timely fashion. Through the user-friendly interface, commuters can eliminate the difficulty of finding routes and prices suitable to their needs. By making public transit more accessible with the help of ubiquitous mobile computing, commuters are also encouraged to switch from using private vehicles to public transit, which also can reduce accidents and carbon emissions. The findings from the usability testing in this study suggest that 'Disgovery' is an effective and user-friendly application for daily commuters in Bangkok that can help them achieve their goals without difficulties. The findings also indicate the importance of user interface and user experience guidelines in designing such applications. [ABSTRACT FROM AUTHOR]

Smart city discourses often invoke the Panopticon, a disciplinary architecture designed by Jeremy Bentham and popularly theorized by Michel Foucault, as a model for understanding the social impact of AI technologies. This framing focuses attention almost exclusively on the negative ramifications of Urban AI, correlating ubiquitous surveillance, centralization, and data consolidation with AI development, and positioning technologies themselves as the driving factor shaping privacy, sociality, equity, access, and autonomy in the city. This paper describes an alternative diagram for Urban AI—the Polyopticon: a distributed, polyvalent, multi-modal network of synthetic intelligences. It posits that fourth industrial revolution technologies change the political, social, and psychodynamic relationships of sentience and witness in the city, shifting the effects of watching and watched beyond the exclusive domain of top-down surveillance and discipline. The Polyopticon poses a more expansive and ambivalent spectrum of possibilities for Urban AI scenarios, one that undermines the totalizing, singular, and cerebral notion of intelligence that so often characterizes Urban AI and smart city critiques. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) applications can be found in various industry areas, including critical infrastructure and healthcare, and IoT is one of several technological developments. As a result, tens of billions or possibly hundreds of billions of devices will be linked together. These smart devices will be able to gather data, process it, and even come to decisions on their own. Security is the most essential thing in these situations. In IoT infrastructure, authenticated key exchange systems are crucial for preserving client and data privacy and guaranteeing the security of data-in-transit (e.g., via client identification and provision of secure communication). It is still challenging to create secure, authenticated key exchange techniques. The majority of the early authenticated key agreement procedure depended on computationally expensive and resource-intensive pairing, hashing, or modular exponentiation processes. The focus of this paper is to propose an efficient three-party authenticated key exchange procedure (AKEP) using Chebyshev chaotic maps with client anonymity that solves all the problems mentioned above. The proposed three-party AKEP is protected from several attacks. The proposed three-party AKEP can be used in practice for mobile communications and pervasive computing applications, according to statistical experiments and low processing costs. To protect client identification when transferring data over an insecure public network, our three-party AKEP may also offer client anonymity. Finally, the presented procedure offers better security features than the procedures currently available in the literature. [ABSTRACT FROM AUTHOR]

Studies indicate the growth and relevance of systems that can recognize affective states in the most different areas. A tendency to more natural environments could be noticed that considering physical or physiological signs and the individual's relationship with the environment, other people, and daily activities. Therefore, what is the importance of combining ubiquitous computing, affective computing, and the contributions of context-aware information to provide more accurate and intelligent affective systems? This study presents a systematic literature mapping about the use of contextual information to identify affective states, which covered articles published between 2010 and October 2021, resulting in 1.638 studies. After applying filters, which we explain further in this article, we selected 49 works to answer a set of research questions. The results indicate that physiological data was the main parameter for recognizing affective signs (62.3%, 33/53), followed by visual data (32.1%, 17/53). The links between context and affective signs presented a more significant occurrence in the combination of contexts related to activities and physiological data (34%, 18/53). [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) plays a central role in ubiquitous computing applications such as health monitoring. In the real world, it is impractical to perform reliably and consistently over time across a population of individuals due to the cross-individual variation in human behavior. Existing transfer learning algorithms suffer the challenge of "negative transfer". Moreover, these strategies are entirely black-box. To tackle these issues, we propose X-WRAP (eXplain, Weight and Rank Activity Prediction), a simple but effective approach for cross-individual HAR, which improves the performance, transparency, and ease of control for stakeholders in HAR. X-WRAP works by wrapping transfer learning into a meta-learning loop that identifies the approximately optimal source individuals. The candidate source domains are ranked using a linear scoring function based on interpretable meta-features capturing the properties of the source domains. X-WRAP is optimized using Bayesian optimization. Experiments conducted on a publicly available dataset show that the model can effectively improve the performance of transfer learning models consistently. In addition, X-WRAP can provide interpretable analysis according to the meta-features, making it possible for stakeholders to get a high-level understanding of selective transfer. In addition, an extensive empirical analysis demonstrates the promise of the approach to outperform in data-sparse situations. [ABSTRACT FROM AUTHOR]

Pervasive computing, human–computer interaction, human behavior analysis, and human activity recognition (HAR) fields have grown significantly. Deep learning (DL)-based techniques have recently been effectively used to predict various human actions using time series data from wearable sensors and mobile devices. The management of time series data remains difficult for DL-based techniques, despite their excellent performance in activity detection. Time series data still has several problems, such as difficulties in heavily biased data and feature extraction. For HAR, an ensemble of Deep SqueezeNet (SE) and bidirectional long short-term memory (BiLSTM) with improved flower pollination optimization algorithm (IFPOA) is designed to construct a reliable classification model utilizing wearable sensor data in this research. The significant features are extracted automatically from the raw sensor data by multi-branch SE-BiLSTM. The model can learn both short-term dependencies and long-term features in sequential data due to SqueezeNet and BiLSTM. The different temporal local dependencies are captured effectively by the proposed model, enhancing the feature extraction process. The hyperparameters of the BiLSTM network are optimized by the IFPOA. The model performance is analyzed using three benchmark datasets: MHEALTH, KU-HAR, and PAMPA2. The proposed model has achieved 99.98%, 99.76%, and 99.54% accuracies on MHEALTH, KU-HAR, and PAMPA2 datasets, respectively. The proposed model performs better than other approaches from the obtained experimental results. The suggested model delivers competitive results compared to state-of-the-art techniques, according to experimental results on four publicly accessible datasets. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) has gained popularity in recent years and has engulfed nearly every industry. The widespread use of numerous ubiquitous computing devices in the low-resource domain has resulted in a new set of privacy and security concerns. To address the problem of security in resource-constrained devices, many lightweight algorithms have been developed. This paper proposes optimized hardware implementations of the lightweight PRINCE block cipher, with the aim of providing adequate security while maximizing resource efficiency. The proposed architecture uses fewer resources and provides a reasonable trade-off between area footprint and efficiency. In the proposed unrolled pipelined architecture, the encryption round is divided into three sub-stages, with registers inserted in between. Using this design approach, the operating frequency is greatly improved. As a result, this architecture adapts itself effectively to high-performance applications. This paper also proposes serial-based and round-based architectures for resource-constrained devices. The proposed unrolled sub pipeline PRINCE block cipher is implemented on the Virtex-6-FF784 and Virtex-4-FF668 FPGA device families and achieved substantial improvements in throughput of 13.057% and 113%, respectively, as well as efficiency of 8.109% and 113.734% respectively. The proposed architecture is evaluated on a variety of grayscale images, and the security analysis is performed using MATLAB software. Aside from that, the proposed architecture uses the CBC-mode of operation. The security analysis and encryption outputs show that the proposed architecture is an effective choice for image encryption and provides sufficient security to the cipher images. • Propose a serial architecture which reduces the number of utilized resources that suggests reduction in area for resource constrained devices. • Propose an unrolled pipeline architecture which achieves high throughput, and low latency implementation. • Propose a round-based architecture and provides a comparison of all proposed designs with existing implementations. • All the implementations are analyzed by using different security analyses for image encryption applications that secure their immunity against various statistical and differential attacks. [ABSTRACT FROM AUTHOR]

With the help of pervasive computing, human living has changed into a smarter way using the developments in IoMT, telecommunication technologies, and wearable sensors for ensuring improved healthcare services. IoMT is comprised of certain potentiality for the revolution in the healthcare industry. IoMT is associated with caregivers, healthcare providers, patients, and wearable sensors with software and ICT. The healthcare industry is also a well-known expanding market that has huge demands. It ensures the potential services towards the patients and also provides its contributions to the profits of the health sector. According to the technical advancements, a healthcare system must be developed based on decision-making capacity. Numerous researchers have also focused on involving cognitive behavior in IoT technology. Thus, in this paper, a new smart healthcare system with the help of IoT devices is suggested. Initially, the data is collected from IoMT devices, which are fed to further processing. Secondly, the data pre-processing is carried out to remove the corrupted data and for removing the noise from the data. Thirdly, the features are collected from the pre-processed data through wavelet entropy computation, and deep features are gathered using CNN. Fourthly, both extracted wavelet entropy features and deep features have undergone an adaptive fusion process using an improved meta-heuristic algorithm, thus termed adaptive wavelet entropy deep feature fusion. Finally, the classification is performed through I-RNN to get the disease-related outcomes, where the weight of RNN is optimized using a new MVS-AVOA. Through the evaluation, the performance analysis of the proposed MVS-AVOA-RNN has 41.5% better than Naive Bayes, 26.8% better than SRU, 18.3% superior to LSTM, and 5.4% enriched than RNN. Thus, the obtained result reveals that the proposed optimized RNN with an advanced feature set supersedes the aforementioned techniques. [ABSTRACT FROM AUTHOR]

WSN has been widely used in many sensitive applications and it also has novel possibilities for laying the groundwork for using ubiquitous and pervasive computing, but it has also presented a number of issues and challenges, such as a dynamic network topology and a congestion problem that hinders not only network bandwidth utilisation but also performance. Proficient rate control and fair bandwidth allocation (PRC-FBA) was one of the schemes in the literature to solve issues of WSN by combining the ideas of traffic class priority and bandwidth fairness. However, because of the nature of WSN, the energy of nodes near the sink node is diminished when packets move from lowly congested nodes to highly congested nodes. This paper proposes a proficient rate control with data aggregation and fair bandwidth allocation (PRCDA-FBA) to address this problem by using an effective data aggregation approach for reducing the number of transmissions. In the proposed method, fair bandwidth allocation is simplified by an artificial intelligence-based bandwidth prediction method. Thus, PRCDA-FBA increases the network's durability. Despite having lower bandwidth utilizations, energy-critical sensor nodes require careful power management to avoid being eavesdropped upon. Along with data aggregation and fair bandwidth allocation, the effects of overhearing packets by energy-critical nodes are mitigated through network-wide route adjustments based on the energy level of nodes. Thus, in the proposed method, data aggregation is scheduled based on the availability of bandwidth, energy, queue size and packet priority. The proposed method is named as energy-aware proficient rate control with data aggregation and fair bandwidth allocation (EPRCDA-FBA). The proposed algorithms have been deployed on the Network Simulator 2.35 platform, and a comparative analysis has been performed using several metrics, including throughput, packet loss, End-to-End (E2E) delay and energy utilization. The EPRCDA-FBA method archives highest throughput which is 9.17%, 5.48%, 4.68% and 2.45% higher than congestion control strategies like discrete-time sliding mode congestion controller (DSMC), weighted priority based fair queue gradient rate control (WPFQGRC), PRC-FBA and rate adjustment-based congestion control (RACC). [ABSTRACT FROM AUTHOR]

The data explosion caused by the rapid and widespread use of IoT devices is placing tremendous pressure on current communication, computing and storage resources. In an ambient ubiquitous computing environment, taking advantage of the context of the application scenario can significantly improve the system performance of IoT networks. Therefore, in this paper, we propose CONTESS, a context-aware edge computing framework with selective sensing that leverages the context information of the sensed environment to improve its applicability to smart IoT systems. CONTESS is composed of two parts: context management, where context acquisition, modeling and reasoning happens; and selective sensing, where data selection happens. We demonstrate the capabilities of CONTESS in the scenario of a parking management system for a smart city environment. We implement CONTESS using linked data and semantic web technologies. We start by designing an OWL-based ontology and then simulating the proposed scenario using the OMNET++ network simulator along with the Veins framework and SUMO traffic simulator. The results show an improvement compared to traditional sensing methods in both communication overhead and the application results. [ABSTRACT FROM AUTHOR]

Recently, scholars across disciplines raised ethical, legal and social concerns about the notion of human intervention, control, and oversight over Artificial Intelligence (AI) systems. This observation becomes particularly important in the age of ubiquitous computing and the increasing adoption of AI in everyday communication infrastructures. We apply Nicholas Garnham's conceptual perspective on mediation to users who are challenged both individually and societally when interacting with AI-enabled systems. One way to increase user agency are mechanisms to contest faulty or flawed AI systems and their decisions, as well as to request redress. Currently, however, users structurally lack such mechanisms, which increases risks for vulnerable communities, for instance patients interacting with AI healthcare chatbots. To empower users in AI-mediated communication processes, this article introduces the concept of active human agency. We link our concept to contestability and redress mechanism examples and explain why these are necessary to strengthen active human agency. We argue that AI policy should introduce rights for users to swiftly contest or rectify an AI-enabled decision. This right would empower individual autonomy and strengthen fundamental rights in the digital age. We conclude by identifying routes for future theoretical and empirical research on active human agency in times of ubiquitous AI. [ABSTRACT FROM AUTHOR]

When practitioners are in the midst of their busy day-to-day work--such as teachers facilitating learners in the classroom or nurses caring for patients in the hospital--they face complex social or material environments and intensive, intertwined activities. Yet unprecedentedly, these practitioners also need to incorporate technologies, as increasingly necessary supports, in their surroundings. A challenge thereby concerns practitioners' limited attention: current human-technology interfaces usually demand users' focus of attention, whereas interacting with digital devices is often neither the only nor the central task in practitioners' ongoing activities. This work explores the design of peripheral interaction to understand how surrounding technologies could leverage the periphery of human attention to tacitly augment practitioners' daily routines. Via a series of field explorations with teachers at school and nurses in neonatal intensive care units (NICU), we illustrate how peripheral interaction designs could seamlessly enrich the practitioners' action repertoire (readily available actions) or enhance their reflection-in-action (sensemaking of the unfolding situation) without interfering with their ongoing routines. From these cases, we extract two relevant design properties to inform future practice: i.e., the designed interaction being subsidiary to the main practice and open to practical knowing. Six considerations are provided to help designers to achieve these properties in practice. [ABSTRACT FROM AUTHOR]

Compressive sensing (CS) is a mathematically elegant tool for reducing the sensor sampling rate, potentially bringing context-awareness to a wider range of devices. Nevertheless, practical issues with the sampling and reconstruction algorithms prevent further proliferation of CS in real world domains, especially among heterogeneous ubiquitous devices. Deep learning (DL) naturally complements CS for adapting the sampling matrix, reconstructing the signal, and learning from the compressed samples. While the CS–DL integration has received substantial research interest recently, it has not yet been thoroughly surveyed, nor has any light been shed on practical issues towards bringing the CS–DL to real world implementations in the ubiquitous computing domain. In this paper we identify main possible ways in which CS and DL can interplay, extract key ideas for making CS–DL efficient, outline major trends in the CS–DL research space, and derive guidelines for the future evolution of CS–DL within the ubiquitous computing domain. [ABSTRACT FROM AUTHOR]

With the thriving development of sensor technology and pervasive computing, sensor-based human activity recognition (HAR) has become more and more widely used in healthcare, sports, health monitoring, and human interaction with smart devices. Inertial sensors were one of the most commonly used sensors in HAR. In recent years, the demand for comfort and flexibility in wearable devices has gradually increased, and with the continuous development and advancement of flexible electronics technology, attempts to incorporate stretch sensors into HAR have begun. In this paper, we propose a two-channel network model based on residual blocks, an efficient channel attention module (ECA), and a gated recurrent unit (GRU) that is capable of the long-term sequence modeling of data, efficiently extracting spatial–temporal features, and performing activity classification. A dataset named IS-Data was designed and collected from six subjects wearing stretch sensors and inertial sensors while performing six daily activities. We conducted experiments using IS-Data and a public dataset called w-HAR to validate the feasibility of using stretch sensors in human action recognition and to investigate the effectiveness of combining flexible and inertial data in human activity recognition, and our proposed method showed superior performance and good generalization performance when compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Smartphones have become ubiquitous, allowing people to perform various tasks anytime and anywhere. As technology continues to advance, smartphones can now sense and connect to networks, providing context-awareness for different applications. Many individuals store sensitive data on their devices like financial credentials and personal information due to the convenience and accessibility. However, losing control of this data poses risks if the phone gets lost or stolen. While passwords, PINs, and pattern locks are common security methods, they can still be compromised through exploits like smudging residue from touching the screen. This research explored leveraging smartphone sensors to authenticate users based on behavioral patterns when operating the device. The proposed technique uses a deep learning model called DeepResNeXt, a type of deep residual network, to accurately identify smartphone owners through sensor data efficiently. Publicly available smartphone datasets were used to train the suggested model and other state-of-the-art networks to conduct user recognition. Multiple experiments validated the effectiveness of this framework, surpassing previous benchmark models in this area with a top F1-score of 98.96%.

The rise of ubiquitous computing has cemented ubiquitousreproduction (UR) as a defining feature of contemporaryhuman environments. UR is most obvious on our televisionsand smartphones but has homogenised most material aspectsof our lives. Emerging technologies such as 3D printing androbotics will ensure that this trend intensifies. UR is an issueof global scale that is relatively intractable to qualitativetreatment. This paper introduces a novel quantitativeapproach to cognitive science and to analysis of UR. Theapproach uses the finiteness of cognition to establish aminimal ontology with which to model cognitive diversityunder UR. It demonstrates that, despite widespreadvalorisation of diversity, cognitive diversity must be decliningat a global level. The implications of this for creativity arethat the arc for creative impact is growing shorter as the needto be immediately intelligible promotes the formulaic at theexpense of the interpretable.

The pandemic has highlighted the fast transmission of needs, goods and ideas that sustain the functionality of our globalised, networked world. At the same time, it has highlighted the resilience and unbreakability of this network when transporting undesirable events such as fake news or a virus. Henceforth, this situation has forced us to rethink how we plan our inhabited space. Since the inception of ubiquitous computing, the city has mutated under a new technologically mediated functionalism, overlaid by the platforms of a global and highly relational system that is submitting space to the logic of computing. Fruit of previous doctoral research, this article reviews the transformations leading to the constitution of this technologically mediated urban space and analyses them by applying Lefebvre’s Unitarian Theory of Space. The objective is to unveil the challenges of the postdigital urban space and present projects that point towards alternative possibilities for urban planning.

This document is an editorial from the journal "Personal & Ubiquitous Computing" discussing the advancements and challenges in the development of interactive media. The editorial highlights the importance of interdisciplinary collaboration in creating interactive media that are reactive, context-aware, ambient, and seamlessly integrated into everyday life. It emphasizes the role of artificial intelligence (AI) and machine learning in achieving responsiveness and personalization. The document also discusses the need for interdisciplinary approaches to achieve context-awareness and the integration of technology into the user's environment. It concludes by stating that the future of interactive media lies in its ability to combine human and technological insights and foster connections between diverse disciplines. [Extracted from the article]

To solve emerging problems, design uses new technologies to introduce “technofixes” (Hankey & Tuszynski, 2017) that are created to improve society in various capacities. The dissolution of technology, described as “ubiquitous computing”, brings with its pervasiveness a series of consequences to the constant production of personal data online (Greene, 2019; Manovich, 2012) that tech companies have now access to. Such data created new relationships between users, tech companies and their affiliates that are far from being settled, where scandals such as Cambridge Analytica provided visibility to the issue. The lack of awareness in this system, and the efforts in designing smooth and efficient experiences at the expense of clarity, raised questions in the public and legislators. The article explores, through literature review, if non-efficiency in design could be a viable way to make users reflect when using design products. As the antithesis to efficiency, we propose the term “friction”, a lens through which existing definitions of friction in design will be analyzed, introducing the concepts of “diegetic friction” and “extra-diegetic friction” as a possible taxonomy of design interventions.

The normal development of "smart buildings," which calls for integrating sensors, rich data, and artificial intelligence (AI) simulation models, promises to usher in a new era of architectural concepts. AI simulation models can improve home functions and users' comfort and significantly cut energy consumption through better control, increased reliability, and automation. This article highlights the potential of using artificial intelligence (AI) models to improve the design and functionality of smart houses, especially in implementing living spaces. This case study provides examples of how artificial intelligence can be embedded in smart homes to improve user experience and optimize energy efficiency. Next, the article will explore and thoroughly analyze the thorough analysis of current research on the use of artificial intelligence (AI) technology in smart homes using a variety of innovative ideas, including smart interior design and a Smart Building System Framework based on digital twins (DT). Finally, the article explores the advantages of using AI models in smart homes, emphasizing living spaces. Through the case study, the theme seeks to provide ideas on how AI can be effectively embedded in smart homes to improve functionality, convenience, and energy efficiency. The overarching goal is to harness the potential of artificial intelligence by transforming how we live in our homes and improving our quality of life. The article concludes by discussing the unresolved issues and potential future research areas on the usage of AI in smart houses. Incorporating AI technology into smart homes benefits homeowners, providing excellent safety and convenience and increased energy efficiency. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Resource allocation in smart settings, more specifically in Internet of Things (IoT) transportation, is challenging due to the complexity and dynamic nature of fog computing. The demands of users may alter over time, necessitating more trustworthy resource allocation and administration. Effective resource allocation and management systems must be designed to accommodate changing user needs. Fog devices don't just run fog-specific software. Resource and link failures could be brought on by the absence of centralised administration, device autonomy, and wireless communication in the fog environment. Resources must be allocated and managed effectively because the majority of fog devices are battery-powered. Latency-aware IoT applications, such as intelligent transportation, healthcare, and emergency response, are now pervasive as a result of the enormous growth of ubiquitous computing. These services generate a large amount of data, which requires edge processing. The flexibility and services on-demand for the cloud can successfully manage these applications. It's not always advisable to manage IoT applications exclusively in the cloud, especially for latency-sensitive applications. Thus, fog computing has emerged as a bridge between the cloud and the devices it supports. This is typically how sensors and IoT devices are connected. These neighbouring Fog devices control storage and intermediary computation. In order to improve the Fog environment reliability in IoT-based systems, this paper suggests resource allocation and management strategy. When assigning resources, latency and energy efficiency are taken into account. Users may prioritise cost-effectiveness over speed in a fog. Simulation was performed in the iFogSim2 simulation tool, and performance was compared with one of the existing state-of-the-art strategy. A comparison of results shows that the proposed strategy reduced latency by 10.3% and energy consumption by 21.85% when compared with the existing strategy. [ABSTRACT FROM AUTHOR]

Ubiquitous computing has brought new challenges for the design of scenarios for people–technology interactions. Despite considerable research on formal accessibility standards, related work has hardly investigated them in ubiquitous computing contexts. In this work, we investigate means of analyzing accessibility aspects in ubiquitous environments based on two standard instruments: the Universal Design (UD) Principles and Guidelines and the W3C-WCAG (Web Content Accessibility Guidelines of the World Wide Web Consortium). Both instruments were applied to the context of socioenactive ubiquitous environments, providing insights into their applicability and shortcomings. As a result of this analysis we constructed UbiAccess, an instrument to evaluate access in ubiquitous scenarios, which combines and extends characteristics of both UD and W3C-WCAG, filling in some of the gaps we identified. The application of UbiAccess to a case study shows the advantages of its use in informing the evaluation of access in ubiquitous scenarios. [ABSTRACT FROM AUTHOR]

The recent era of pervasive computing has evolved with various applications and has ground-breaking realities in mobile crowdsourcing (MCS). Multiple attempts have been devoted to integrating MCS with IoT-based smart cities where crowdsensing has played a crucial role in the recent past. Despite having potential features, MCS devices lack efficiency when security aspects are concerned. The current security approaches exercised in MCS operations imply limited features and are not intelligent enough to deal with different types of attacks in IoT smart cities. On the other hand, as MCS communications involve radio environmental mapping functional blocks from communication, it is an obvious situation that leads to a vulnerable situation of which adversarial modules can take advantage of it. There are different types of active and passive modes of attacks that can degrade the Quality-of-Service (QoS) aspects in IoT-driven smart city operations. This study's prime aim and the appealing theme is to realize the need for resilient approaches to intelligent intrusion detection in MCS to mitigate different attacks. The study also introduces a theoretical approach of cluster-enabled multi-task (CeMT) based on bio-inspired learning modeling of the genetic approach to identify the maximum possible threats and misbehaving devices in the smart city-based MCS operations. The study also evaluated the model's performance based on the processing time of identifying malicious events and showed the accuracy of detecting misbehaving working associate (WA) modules. [ABSTRACT FROM AUTHOR]