The innovations founded on the artificial intelligence concept are promoting a scenario in which it is possible to shop interactively, to automate customer services and to personalize product descriptions, which, in turn, enhance the efficiency of the company and enrich the customer experience. Thus, taking into account the e-commerce domain, the current work provides a systematic literature review with regard to the advancements in fields, such as explainable artificial intelligence and generative artificial intelligence. In a nutshell, such a work reveals the evolution of the e-commerce landscape concerning topics as content automation, tailored marketing and system transparency, to mention a few. To be more precise, it is paramount to highlight that the aforementioned advances are intimately related to challenges of ethical nature and technical nature. Remarkably, the contributions inherent to the current work expatiate upon the provision of a taxonomical approach, as well as a description with respect to the temporal evolution regarding models, techniques and tools. Furthermore, through the e-commerce perspective, the contributions related to the current work also comprise the analysis of themes, such as applications, challenges and future directions, which means that the proposed survey identifies essential steps to advance the artificial intelligence solutions towards a scenario governed by ethics and trustworthiness.

Integrating wearable devices into smart city infrastructures offers a transformative potential for healthcare, promoting a shift from a reactive model to a proactive paradigm. Although not new, the literature today does not present surveys and studies that discuss the intersection of smart cities and healthcare, especially taking advantage of devices that are more and more incorporated into citizens’ daily lives. Thus, this article contributes to the state of the art by providing a holistic review that links the clinical requirements of wearables with the architectural challenges of large-scale implementations. The work presents a comprehensive analysis of the current landscape, including: (i) a review and comparison of leading commercial wearables and the vital signs they monitor; (ii) an analysis of existing innovative health projects, such as Brescia Smart Living, City4Age, and Minha História Digital; and; (iii) a detailed correlation table that maps changes in multiple vital signs to dozens of pathologies and their associated symptoms. The analysis confirms that data fusion can assist in detecting conditions such as sepsis early. Still, it also exposes a critical technological gap: the absence of continuous cuffless blood pressure measurement. In addition, systemic challenges such as the lack of interoperability and the need for robust privacy frameworks remain significant barriers. We conclude that progress in smart health depends on overcoming these interconnected gaps to leverage wearable data to improve individual and population health fully.

Edge computing and artificial intelligence gradually intersect to build a novel concept. Edge systems are now equipped with artificial intelligence solutions to deliver faster insights closer to where data is generated, reducing communication latency and avoiding fog or cloud interactions. Within the spectrum of applications demanding EdgeAI, anomaly detection is a pivotal research domain. Here, conventional statistical methods often prove inadequate for identifying anomalies across various scenarios. Therefore, more sophisticated techniques, such as machine learning methods, are required to handle the high dimensionality, nonlinearity, and nonstationarity of the data. Given the state of the art, the literature offers limited references in this field and lacks a clear, up-to-date overview of academic and market initiatives. In this way, the present survey aims to investigate the main concerns of anomaly detection, addressing the opportunity outlined above. We have analyzed 4,075 articles and 10 market players in the field of anomaly detection. Our study presents an updated overview of anomaly detection in EdgeAI, integrating academic and industry perspectives. It encompasses AI libraries, algorithms, hardware, communication technologies, and cost–benefit considerations. Furthermore, we introduce a novel taxonomy that categorizes these approaches by algorithmic features, communication methods, hardware capabilities, energy efficiency, and financial impact.

This work integrates NovaGenesis (NG), a clean-slate IoT architecture, with LoRa technology within low-power wide-area networks (LPWAN), extending previous efforts on NG connectivity with Wi-Fi. The research aims to update the embedded version of NG and develop devices for seamless LoRa and Wi-Fi IoT operation. It evaluates NG's performance on LoRa and Wi-Fi, focusing on throughput, delay, and packet loss. Despite LPWAN limitations, the results show that the NG deployment is feasible, validating its self-organizing IoT life cycle to maintain service continuity between an ESP-32 and a data client. Performance meets the needs of IoT applications in agribusiness, logistics, and smart monitoring. In addition, a 24-hour environmental monitoring experiment was conducted in Santa Rita do Sapuca & iacute;(SRS), Minas Gerais, Brazil, where a commercial weather station was modified to integrate NG, allowing accurate collection of temperature, humidity, atmospheric pressure, wind conditions, solar radiation and UV index. The results met expected diurnal patterns in SRS, proving the reliability and precision of the sensors and communication infrastructure. This solution overcomes common IETF IoT stack limitations in devices naming, information provenance, entities identification, programmability via digital twins, programmability, services and devices self-organization, and trust formation, offering a robust platform for varied IoT scenarios in LPWAN environments. These are the key benefits of applying NovaGenesis for LoRa and Wi-Fi-based environmental monitoring.

Timely asset maintenance remains a critical challenge in Industry 4.0 environments. Predictive Maintenance aims to anticipate failures and estimate Remaining Useful Life (RUL), enabling cost reduction and minimizing production downtime. However, real-world industrial scenarios are often characterized by noisy telemetry data, incomplete information about operating conditions, and weak degradation signals, which limit the effectiveness of conventional data-driven approaches. This paper proposes a methodology for RUL prediction under such challenging conditions, leveraging raw sensor telemetry without requiring detailed knowledge of machine operating characteristics. The approach introduces a novel Degradation Index, combined with a Health Index, to better represent degradation patterns. Additionally, signal preprocessing techniques, including Savitzky-Golay and Kalman filters, are applied to mitigate noise and improve data quality. The methodology integrates statistical analysis, similarity-based pattern extraction, and machine learning techniques, including Convolutional Neural Networks and Long Short-Term Memory models, for feature selection and prediction. Experiments conducted on real-world industrial datasets demonstrate that the proposed approach significantly improves prediction performance, achieving high accuracy and enabling failure anticipation up to five days in advance. The results highlight the importance of feature engineering and signal processing in PdM applications, showing that combining degradation modeling with deep learning yields robust, generalizable RUL predictions, even in noisy, partially observed environments.

Blockchain technology in healthcare is gaining attention for addressing data privacy, interoperability, and health record integrity issues. Standards like HL7 FHIR and OpenEHR ensure data consistency, but privacy concerns persist under regulations like HIPAA, GDPR, and LGPD. Existing methods often store only data hashes, raising validation risks. The MEPCA model introduces a blockchain-based framework for secure health record management, focusing on on-chain EHR data processing. Key elements include Data Steward, Shared Data Vault, and Zero-Knowledge Proofs of HL7 FHIR fields. Experiments with Fully Homomorphic Encryption show enhanced security and reliability for health records, offering a robust alternative to traditional off-chain approaches.

The integration of blockchain technology in healthcare has gained significant attention due to its potential to address critical challenges such as data privacy, interoperability, and health record integrity. Although electronic health record (EHR) standards such as Fast Healthcare Interoperability Resources (HL7 FHIR) and OpenEHR provide frameworks for data consistency and interoperability, concerns persist regarding the privacy and security of sensitive patient information, particularly in compliance with regulations. Existing solutions often store only hashed representations of data on blockchain nodes, making direct on-chain validation impossible and increasing the risk of invalid or malicious data entering the system. This paper introduces MEPCA, a novel blockchain-based framework designed to enhance on-chain EHR data processing using cryptographic techniques. The model incorporates an innovative method to generate cryptographic proofs of data validity, enabling direct on-chain verification of hash digests. We present practical use case implementations and perform a technical evaluation of a fully on-chain MEPCA approach within the HL7 FHIR ecosystem. Our analysis examines the processing time of the hash proof algorithm, comparing it with existing methods based on Transactions per Second (TPS), latency, and computational efficiency in a multi-host network environment. The experimental results show that the MEPCA framework achieves an average of 83.2 TPS, with a latency below 1.5 seconds and the hash-proof computation taking 1.6 seconds. Our primary contribution is to demonstrate viable healthcare scenarios for a fully on-chain approach, providing strategic guidance for the adoption of decentralized solutions in healthcare through technical evaluation and real-world applications.

The demand for food is growing every year and demands more significant technology applications in the field Furthermore, due to food production, pests and climate change incidents are a real-time challenge for farmers. Due to the growing need to apply algorithms in the field, we investigate the algorithms most cited, used, and ongoing projects in the last three years, from 2019 to 2021 Therefore, we evaluated articles that focus was mainly on supervised learning algorithms This literature review presents an overview of algorithms usage in agriculture. A total of 81 articles were analysed. Our contributions as a) an analysis of the state-of-the-art on applying algorithms to various agricultural functions and b) a taxonomy to help researchers, governments, and farmers choose these algorithms. This article adds discoveries about the application of algorithms in crops, machinery, and processes and points out new lines of research.

The digital transformation process has significantly boosted the widespread adoption of telemedicine and the utilization of wearable devices for vital signs remote monitoring. However, implementing a system for continuous monitoring of the population's vital signs, with data being streamed from various locations within a smart city context, faces significant challenges. These challenges are related to bandwidth consumption, communication latency, and storage capacity due to the large volume of data. To overcome these challenges, a common practice consists in modeling an edge-fog-cloud layered architecture. The literature lacks software solutions capable of managing the simultaneous transmission of various vital signs data from geographically distributed individuals while maintaining the ability to generate health notifications promptly. In this context, we propose the VSAC (Vital Sign Adaptive Compressor) model, which combines lossy and lossless data compression algorithms in a layered architecture to support healthcare demands in a smart city. The main contribution is how we blend both strategies: we first use lossy compression to collect only valuable vital sign data for everyone, applying lossless algorithms afterwards to reduce the number of bytes before sending it to higher layers. We provide a real-time processing protocol that facilitates the collection of heterogeneous data distributed across different city regions. After executing a VSAC prototype, the results indicate that orchestrating the aforementioned two data compression algorithms is more efficient than conventional data reduction methods. In particular, we obtained gains of up to 42% when measuring the compression rate metric.

We live in a disruptive moment where technology plays a crucial role in capturing and analyzing citizens’ vital signs in real time. Although having a vast literature on providing health-based intelligent cities, the current articles are disappointing since explanations about scale, module interactions, and processing capabilities need to be detailed. Here, we present an in-depth vision of a new vital sign-driven smart city, highlighting each hierarchical level, its modules, and interactions. This article addresses Internet of Things data capturing, buffering schemes, hierarchical messaging engines, health services, task offloading among layers, person and service priority computation, different dashboards, and notification centers. Although edge, fog, and cloud are not new topics, their scalable blending in favor of delivering digital health is. The presented architecture helps fight against the COVID-19 and other pandemics sequels since data regarding temperature, respiratory rate, heart rate variability, and oxygen saturation of the whole population could be analyzed efficiently.

Multi-agent reinforcement learning (MARL), ontology-based medical knowledge representation, and generative AI–particularly large language models (LLMs) are increasingly applied in clinical decision support systems (CDSSs). Despite rapid advances, no systematic review has comprehensively examined these issues from a combined perspective, leaving gaps in the understanding of hierarchical architectures, bidirectional knowledge flow, and explainable AI mechanisms. To address this, we reviewed 42 studies published between 2016 and 2025, identifying key challenges and proposing a structured taxonomy that organizes the field across learning paradigms, knowledge representation, and generative AI, while also addressing cross-cutting concerns such as explainability and adaptability. Our findings suggest that the convergence of hierarchical MARL, ontology-grounded knowledge representation, and LLM-enhanced explainability may provide a foundation for next-generation CDSSs that are adaptive, semantically robust, and clinically actionable.

A transformação digital impulsionou a telemedicina e o uso de dispositivos vestíveis para o monitoramento remoto de sinais vitais. Contudo, a transmissão desses dados em cidades inteligentes enfrenta desafios relacionados à largura de banda, latência e armazenamento. Para isso, em uma arquitetura em camadas (edge-fog-cloud) o modelo VSAC gere a transmissão simultânea e envia alertas de saúde de forma ágil. O modelo combina algoritmos de compressão com e sem perdas para otimizar a coleta e o envio de dados. Os testes demonstraram que o modelo é mais eficiente que métodos convencionais com ganhos de até 42% na taxa de compressão.

This paper proposes the Decentralized Adaptive Priority-based Hierarchical Offloading (DAPHO) model for offloading strategies in fog computing applied to healthcare in smart cities. The model handles large volumes of IoT data by prioritizing critical signals in the fog while less critical ones are processed in the cloud. Unlike centralized or single-path approaches, DAPHO enables autonomous offloading decisions among fog nodes hierarchically organized (e.g., neighborhoods, cities). The flexibility of multiple destinations and dynamic thresholds improved response time and prioritized signal processing, although fixed thresholds showed better performance in some scenarios

Health institutions and hospitals are essential in ensuring the appropriate treatment of human health. One of the major concerns is the increasingly overcrowded patients care queues. The global COVID-19 pandemic heightened this problem. In an increasingly connected environment, such as smart cities, people's health can be monitored, so scenarios requiring medical support can be identified beforehand. Looking at the literature, we did not find surveys that address smart cities' approaches to handling the pandemic landscape. Based on this background, we propose a systematic literature review discussing the following issues: involved players and their interactions, processing techniques to generate value for the population, smart city architectures to cover pandemic situations, and data standards and technologies applied in this context. We have studied 58 articles, answering research questions regarding the above-mentioned topics. As contributions, we add to the literature a state-of-the-art vision regarding challenges, open issues, and trends in the combination of smart cities and their support for pandemic situations.

A otimização da utilização de recursos em cidades inteligentes tem o potencial de melhorar o bem-estar dos cidadãos. Através do monitoramento contínuo da saúde das pessoas, é possível a identificação precoce de problemas médicos. No entanto, o problema dos hospitais superlotados persiste, conduzindo a longos períodos de espera para os pacientes que necessitam de tratamento. Trabalhos anteriores tentaram resolver esse problema, porém ainda existe a necessidade de uma solução que possa adequar de forma eficiente recursos humanos em múltiplos ambientes de saúde. Este trabalho apresenta o ElCareCity, um modelo focado em cidades inteligentes para monitorar o uso de ambientes de saúde pelos pacientes e adaptar a alocação de profissionais de saúde para atender às suas necessidades. ElCareCity introduz na literatura um algoritmo que combina abordagens de elasticidade reativa e proativa para alocar profissionais de saúde. O modelo foi avaliado por meio de emulações de uma cidade inteligente com quatro ambientes hospitalares e obteve resultados promissores que reduziram o tempo de espera por atendimento em até 86,8%.