Integration Architecture Research Articles

A digital twin solution for fault detection in time-critical IIoT applications

ABSTRACT IIoT sensor data plays a pivotal role in monitoring the industrial system’s health and identifying potential faults. However, traditional fault detection approaches often face challenges such as network latency, limited accuracy, and resource-intensive processing. This paper introduces an end-to-end Digital Twin solution that enhances fault detection for IIoT systems. The solution is powered by two key innovations: the integration of a Digital Twin architecture that leverages a collaborative cloud-edge approach for real-time monitoring, and the use of a lightweight two-phased machine-learning ensemble model optimized for resource-constrained environments. The great performance achieved across various fault scenarios demonstrates the effectiveness of the proposed approach. The model provides an average accuracy of 99.71% with a mere 4.8 ms of average estimation delay. These advancements ensure both high accuracy and rapid response times, providing a robust solution for proactive fault detection in dynamic industrial environments.

Biomimetic 3D Prototyping of Hierarchically Porous Multilayered Membranes for Enhanced Oil-Water Filtration.

This study introduces a biomimetic approach to 3D printing multilayered hierarchical porous membranes (MHMs) using Direct Ink Writing (DIW) technology. Fabricated through a fast layer-by-layer printing process with varying concentrations of pore-forming agents, the produced MHMs mimic the hierarchical pore structure and filtration capabilities of natural soil systems. As a result, the 3D-printed MHMs achieved an impressive oil rejection rate of 99.02% and demonstrated exceptional reusability, maintaining a flux recovery ratio of 99.48% even after hours of continuous filtration. Moreover, the 3D-printed MHMs exhibit superior hierarchical porous architecture and mechanical integrity compared to traditional flat sheet single-layered membranes. This study presents a significant advancement for scalable 3D printing of customized multilayer membranes with tailored porosity and high-performance filtration properties. The simplicity, versatility, and cost-effectiveness of the presented manufacturing method offer a pathway for advanced design and on-demand membrane production.

Curcumin and Vitamin D Supplement Attenuates Knee Osteoarthritis Progression in ACLT + MMx Rat Model: Effect on Cartilage Protection and Pain Reduction.

Background: Knee osteoarthritis (OA) is a common and debilitating disorder marked by joint degradation, inflammation, and persistent pain. This study examined the possible therapeutic effects of curcumin and vitamin D on OA progression and pain in a rat knee OA model by anterior cruciate ligament transection and meniscectomy (ACLT + MMx). Methods: Male Wistar rats were categorized into five groups: control, curcumin-treated (100 mg/kg/day), vitamin D-treated (25 µg/kg/day), a combination of vitamin D and curcumin, and sham-operated. All supplements were administered orally on a daily basis for 12 weeks. Pain behaviors were assessed, serum biomarkers were measured, and knee histology was examined. Results: Both curcumin and vitamin D independently reduced pain, while the combined group exhibited better analgesic effects. Serum inflammatory cytokines demonstrated a decrease in pro-inflammatory cytokines and an elevation in anti-inflammatory cytokine interleukin-10 (IL-10) in the supplement groups. The antioxidative markers were partially recovered by curcumin and vitamin D supplement. However, the oxidative stress marker Cartilage Oligomeric Matrix Protein (COMP) was significantly reduced. Histology analysis revealed a preservation of joint architecture and cartilage integrity and decreased synovium inflammation in the groups treated with curcumin and vitamin D. Conclusions: Our findings indicate a dual mechanism that encompasses the role of anti-inflammation and antioxidation on knee OA progression and pain reduction, underscoring the potential of these natural chemicals as therapeutic agents for knee OA; curcumin and vitamin D supplement may be added in delaying knee OA progression and associated pain management in clinical patient care.

Forecasting Stock Market Indices Using Integration of Encoder, Decoder, and Attention Mechanism.

Accurate forecasting of stock market indices is crucial for investors, financial analysts, and policymakers. The integration of encoder and decoder architectures, coupled with an attention mechanism, has emerged as a powerful approach to enhance prediction accuracy. This paper presents a novel framework that leverages these components to capture complex temporal dependencies and patterns within stock price data. The encoder effectively transforms an input sequence into a dense representation, which the decoder then uses to reconstruct future values. The attention mechanism provides an additional layer of sophistication, allowing the model to selectively focus on relevant parts of the input sequence for making predictions. Furthermore, Bayesian optimization is employed to fine-tune hyperparameters, further improving forecast precision. Our results demonstrate a significant improvement in forecast precision over traditional recurrent neural networks. This indicates the potential of our integrated approach to effectively handle the complex patterns and dependencies in stock price data.

A Reference Architecture for Virtual Human Integration in the Metaverse: Enhancing the Galleries, Libraries, Archives, and Museums (GLAM) Sector with AI-Driven Experiences

The digital transformation of the GLAM (galleries, libraries, archives, and museums) sector is a multifaceted process that must address a range of requirements and critical challenges, such as traceability, long-term preservation, and sustainability. The potential of disruptive technologies to revolutionize this sector is significant, offering new ways to overcome these challenges and align with the broader objectives of smart cities. While substantial research has been conducted on the digital transformation of the GLAM sector, many opportunities remain unexplored by various stakeholders. This paper contributes to the field by proposing a reference architecture rooted in a design-oriented approach for developing and implementing processes related to the digital transformation within the context of smart cities. To illustrate the practical application of the proposed architecture, a proof of concept was developed in the form of an immersive digital gallery, which features an AI-powered virtual storyteller. The gallery, built using the open, cross-platform, Unreal, incorporates digitized physical art and a virtual metahuman tutor who guides users through the gallery. This interactive 3D environment enables users to explore the space, engage with artworks, and interact with a virtual guide. The environment’s performance was evaluated using a keystroke-level model analysis. Key findings from a pilot study involving 10 users showed that, when directed by the AI storyteller, the average time to locate an artwork was 16.5 s, while the average time to ask a question was 15.8 s. By integrating such technologies, the GLAM sector can contribute to the cultural fabric of smart cities, fostering more sustainable, accessible, and interactive public spaces.

FusionNet remote a hybrid deep learning ensemble model for remote image classification in multispectral images

Remote sensing plays a vital role in various industries, including smart cities, agriculture, and environmental monitoring, by capturing multispectral images of the Earth’s surface and analyzing its features. Accurate classification of these images is essential for extracting valuable information and making informed decisions. However, traditional image classification models, such as Convolutional Neural Networks (CNNs), often struggle to fully capture the complex spectral and spatial information inherent in multispectral images. Addressing this research gap, we propose FusionNet-Remote, a novel hybrid deep learning ensemble model that integrates CNNs with Random Forests (RF) to enhance the accuracy and robustness of remote image classification. The primary objective of this study is to develop a model that combines the strengths of CNNs for spatial feature extraction with the robust classification capabilities of RFs. Through comprehensive evaluations using LANDSAT data, FusionNet-Remote demonstrates superior performance compared to existing models, achieving an outstanding training accuracy of 99.8% and a testing accuracy of 98.7%. The model also exhibits the lowest training loss (0.0001) and testing loss (0.0043), significantly outperforming traditional models such as standalone CNNs, VGG16, and Inceptionv3. These results highlight the effectiveness of the hybrid ensemble approach in overcoming the limitations of conventional methods. This research contributes to the field by introducing an innovative ensemble technique that significantly improves remote image classification accuracy and reliability. The model’s high performance underscores its potential for critical applications such as land cover mapping, vegetation analysis, and disaster monitoring. Future work will explore the integration of more advanced CNN architectures and alternative fusion techniques to further enhance the model's performance and adaptability across different remote sensing scenarios.

Phase boundaries promote chemical reactions through localized fluxes.

One of the hypothesized functions of biomolecular condensates is to act as chemical reactors, where chemical reactions can be modulated, i.e., accelerated or slowed down, while substrate molecules enter and products exit from the condensate. Similarly, the components themselves that take part in the architectural integrity of condensates might be modified by active (energy consuming, non-equilibrium) processes, e.g., by ATPase chaperones or by kinases and phosphatases. In this work, we study how the presence of spatial inhomogeneities, such as in the case of liquid-liquid phase separation, affects active chemical reactions and results in the presence of directional flows of matter, which are one of the hallmarks of non-equilibrium processes. We establish the minimal conditions for the existence of such spatial currents, and we furthermore find that these fluxes are maximal at the condensate interface. These results propose that some condensates might be most efficient as chemical factories due to their interfaces rather than their volumes and could suggest a possible biological reason for the observed abundance of small non-fusing condensates inside the cell, thus maximizing their surface and the associated fluxes.

Elastic robotic structures: a multidisciplinary framework for the design and control of shape-morphing elastic system for architectural and design applications

The design of adaptive structures and objects takes place at the intersection of design, architecture, robotics and engineering. Evolving from 1960s cybernetics to today’s interactive projects, technological advancements shape new visions for adaptive systems. A key challenge in this field is developing human-scale, shape-morphing structures. Elastic materials offer a promising solution for creating lightweight systems capable of large transformations with minimal components and energy, unlike conventional rigid systems. This approach requires methodologies for designing and controlling complex material deformations. While architectural and structural design methods focus on large-scale but static elastic structures, soft robotics explores dynamic behaviors. However these approaches are limited for complex shapes and large-scale, as their focus is on specialized applications. To address these issues, this research introduces a multidisciplinary framework for the design and control of shape-morphing elastic system for architectural and design applications. It also presents the concept of elastic robotic structures (ERS), which refers to a body of work developed with the framework. ERS are defined as large-scale elastic systems that are robotically actuated and can achieve multiple geometrical states, interacting with humans and adapting to diverse conditions. The multidisciplinary framework is presented for ERS design, characterization and control, showing how it leverages the integration of architecture, engineering and robotics to overcome the limitations of discipline-specific traditional approaches. The framework is applied in the realization of different types of ERS, which are presented and categorized. Combining the flexibility and interactivity of design methodologies with the reliability of robotic solutions will enable designers and engineers to develop innovative elastic shape-changing systems and program their behaviors.

Mastering Integration Architectures with Workday Studio: A Framework for Building Scalable and Efficient Integrations

Mastering Integration Architectures with Workday Studio: A Framework for Building Scalable and Efficient Integrations

National Heritage of Yakutsk and its Traditions in Modern Urban Architecture

This work studies the influence of the national heritage of Yakutsk on its architectural development and preservation of traditions in modern architecture. Considered are mogol urasa, winter log yurt (balagan), contiguous serge poles and traditional Yakut ornaments. The analysis of national sites identify traditional buildings and elements affecting modern architectural solutions. Buildings in Yakutsk are described, in which the influence and implementation of national symbols and forms in their architectural appearance is observed. It is shown that the modern architecture of Yakutsk continues to use traditional materials, symbols, shapes and colors of the Yakut culture, while integrating innovative and modern functionality. It is important to continue and preserve traditions of Yakutsk architecture, emphasizing their essential role in the formation of the modern architecture of the city. Material objects created in accordance with traditions give the houses a special atmosphere and uniqueness, retrospectively reflecting the spirit and cultural heritage of the Yakut people in the modern urban environment. The importance of preserving these architectural traditions lies in the preservation and transmission of unique cultural values.Purpose: The aim of the work is to identify continuity in the modern architecture of Yakutsk.Methodology: Interpretation of historical forms and Yakut culture in modern architecture. It focuses on Yakut national houses, the analysis of religious symbols, their sacred significance and applicability in the architectural landscape.Value: Systematization and conceptualization of formative methods typical for national buildings and symbols, while studying their integration in architecture of Yakutsk.

Refining breast cancer classification: Customized attention integration approaches with dense and residual networks for enhanced detection.

Breast cancer detection is critical for timely and effective treatment, and automatic detection systems can significantly reduce human error and improve diagnosis speed. This study aims to develop an accurate and robust framework for classifying breast cancer into benign and malignant categories using a novel machine learning architecture. We propose a dense-ResNet attention integration (DRAI) architecture that combines DenseNet and ResNet models with three attention mechanisms to enhance feature extraction from the BreakHis dataset. The attention mechanisms focus on regionally important features, improving classification accuracy. A triple-level ensemble (TLE) method combines the performance of multiple models, further enhancing prediction accuracy. The proposed DRAI architecture with TLE achieves an accuracy of 99.58% in classifying breast cancer into benign and malignant categories, surpassing existing methodologies. This high accuracy demonstrates the effectiveness of the fusion architecture and its ability to reduce manual errors in breast cancer diagnosis. The DRAI architecture with TLE provides a robust, automated framework for breast cancer classification. Its exceptional accuracy lays a solid foundation for future advancements in automated diagnostics and offers a reliable method for aiding early breast cancer detection.

Empowering drones in vehicular network through fog computing and blockchain technology.

The performance of drones, especially for time-sensitive tasks, is critical in various applications. Fog nodes strategically placed near IoT devices serve as computational resources for drones, ensuring quick service responses for deadline-driven tasks. However, the limited battery capacity of drones poses a challenge, necessitating energy-efficient Internet of Drones (IoD) systems. Despite the increasing demand for drone flying automation, there is a significant absence of a comprehensive drone network service architecture tailored for secure and efficient operations of drones. This research paper addresses this gap by proposing a safe, reliable, and real-time drone network service architecture, emphasizing collaboration with fog computing. The contribution includes a systematic architecture design and integration of blockchain technology for secure data storage. Fog computing was introduced for the Drone with Blockchain Technology (FCDBT) model, where drones collaborate to process IoT data efficiently. The proposed algorithm dynamically plans drone trajectories and optimizes computation offloading. Results from simulations demonstrate the effectiveness of the proposed architecture, showcasing reduced average response latency and improved throughput, particularly when accessing resources from fog nodes. Furthermore, the model evaluates blockchain consensus algorithms (PoW, PoS, DAG) and recommends DAG for superior performance in handling IoT data. Fog; Drones; Blockchain; PSO; IoT; Vehicular.

Bulk thermally conductive polyethylene as a thermal interface material.

As the demand for high-power-density microelectronics rises, overheating becomes the bottleneck that limits device performance. In particular, the heterogeneous integration architecture can magnify the importance of heat dissipation and necessitate electrical insulation between critical junctions to prevent dielectric breakdown. Consequently, there is an urgent need for thermal interface materials (TIMs) with high thermal conductivity and electrical insulation to address this challenge. In this work, we synthesized thermally conductive polyethylene (PE) bars with vertically aligned polymer chains via a solid-state drawing technique to achieve a thermal conductivity of 13.5 W m-1 K-1 with a coverage area of 2.16 mm2. We utilized wide-angle X-ray scattering to elucidate the molecular structural changes that led to this thermal conductivity enhancement. Furthermore, we conducted a device-cooling experiment and showed a 39% hot spot temperature reduction compared to a commercial ceramic-filled silicone thermal pad under a heating power of 3.6 W. Thus, this bulk-scale thermally conductive PE bar with nanoscale structural refinement demonstrated superior cooling performance, offering potential as an advanced thermal interface material for thermal management in microelectronics.

Siamese Hybrid Network Approach for Sentence Similarity

This paper presents a novel Siamese Hybrid Network approach, namely Siamese Bidirectional Long Short Memory with Convolutional Neural Network (SiBiLConv), for evaluating the similarity in natural language. The model integrates a Siamese neural network architecture with similarity metrics, including Manhattan Distance and Cosine Similarity, to improve the accuracy of semantic relationships measurement between sentences. Evaluations were performed on Sinhala, a complex and under-resourced language spoken in Sri Lanka, which poses unique challenges due to its morphological richness and syntactic variability. The SiBiLConv model achieved an accuracy of 89.80%, an F1 score of 0.9041, and a mean squared error (MSE) of 0.0281 with the Cosine Distance metric outperforming baseline models such as MaLSTM, which achieved an accuracy of 78.99% and an F1 score of 0.7797. While existing methods for sentence similarity primarily focus on resource-rich languages, this work addresses the pressing need for tailored approaches in low-resource language contexts, where pre-trained models and annotated datasets are often limited. The novelty lies in SiBiLConv's hybrid architecture and metric integration, specifically designed to overcome the syntactic and semantic complexities of Sinhala. This research not only bridges a critical gap in the application of sentence similarity models for low-resource languages but also establishes a framework adaptable to other morphologically rich languages, advancing the broader scope of natural language processing. Keywords: Siamese Hybrid Network, Sentences similarity, Sinhala sentence similarity, Morphologically Rich Language Processing

Application of a Multicriteria Genetic Algorithm for Structural Parametric Synthesis of Convolutional Neural Networks

The paper identifies and describes promising architectural solutions for convolutional neural networks, along with key parameters for further structural and parametric synthesis. The advantages and disadvantages of different blocks are outlined, and their relevance in structural synthesis is substantiated. The use of a genetic evolutionary algorithm for structural-parametric synthesis is proposed, along with a review of contemporary approaches. The configuration process of the evolutionary algorithm is shown and described. Based on optimization criteria, the fitness function, selection, mutation, and crossover methods are defined. The results of the experimental evolutionary process are presented and analyzed. An example model created by evolutionary algorithms is considered, which is based on functional blocks aggregated from various architectural approaches in convolutional neural networks. For each model, performance criteria, including average reduction in training time, benefits, and architectural integration details, were calculated during the synthesis process. Experimental results demonstrate that using complex structural blocks instead of traditional layers with a flexible fitness function configuration according to quality and performance criteria yields significant improvements for the final model

Differentiation of design solutions according to architectural and artistic criteria

The paper proposes a classification of buildings and structures into levels by the criterion of whether their design solutions contain such architectural and artistic qualities as architectural idea, artistic image and integrity of architectural composition. In total, four levels of construction have been identified. At the lower first level, the utilitarian-functional approach prevails, where the shell of the building body strictly follows the function and carries no artistic meaning. The second level is decoration or embellishment, when patterns, mantles and decor are superimposed on the object. At the next level, work concerns the form: the exterior express the units or program, cantilevered spaces, offset volumes (left-right, up-down, forward-inwards), various surface finishes. The highest level is when the volume conveys an architectural idea, an artistic idea, and all the composition techniques and means work to reveal it.

Integrity and life in emerging architecture - positioning the architect in continual digital design

Guided by questions of contemporaries, leading to the question of integrity and durability of architecture, and by conclusions from recent conferences which advance architecture through digital approaches to designing and guiding architecture towards Artificial Intelligence (AI), we need to get back to the question on how to design in the future under multi-layered complex conditions and sustainability requirements of emerging architecture. Based on this, we conclude that the topic - Integrity of Architectural Objects is yet highly relevant, and this paper represents a continuation of research/ consideration of architectural spatiality as an activity of creativity and structural durability. The sense of careful and complex structural design as an example of a continual digital approach, e.g. a multi-layered network - joint effect of design and realisation of architecture is highlighted. As digital design in architecture has proven to be elusive and occasionally uncontrollable without the meaningful participation of the architect, this paper highlights positioning of the architect as an important factor in solving integrity and durability challenges of emerging architecture. Digital approaches in architecture are constantly developed and improved, and structural integrity and durability issues are becoming increasingly complex and serious, especially in relation to geometry/space design and sustainability, so architect’s knowledge involvement is inevitable and necessary in future data-driven design processes. Positioning of the architect is based on expertise - activities and features, crucial in the process with identical characteristics, as the continuous development and improvement of knowledge, linking and anticipating all needs of the architectural process, the integrity and durability of architecture. Additionally, knowledge will be meaningfully placed and integrated by positioning of the architect in society, in a critical attitude towards new technological achievements and re-examination of integrity and life of the structure in terms of sustainability and resilience of functional and spatial features of architecture. The aim of the work is to show that knowledge as the main characteristic of the architect’s positioning in future design and realisation, is also the foundation for integrity and life in emerging architecture.

Human-AI Enabled Edge Computing for Data Processing: A Comprehensive Analysis

The exponential growth in data generation and processing requirements has driven the need for more efficient and intelligent computational approaches at the edge of networks. This comprehensive article investigates the integration of human expertise with AI-enabled edge computing systems, focusing on optimization strategies, implementation frameworks, and real-world applications. Through extensive analysis of implementation cases and performance metrics, the research demonstrates significant improvements in processing efficiency, with systems achieving a reduction in latency and improvement in decision accuracy through human-AI collaboration. The article presents a detailed framework for implementing these hybrid systems, addressing critical aspects including technical architecture requirements, integration guidelines, and risk mitigation strategies. Results indicate substantial benefits in operational efficiency, resource utilization, and decision-making capabilities across various industrial applications. While identifying implementation challenges and limitations, the article provides strategic recommendations for successful deployment and highlights opportunities for future advancement in the field. The article contributes significantly to understanding how organizations can effectively leverage human-AI collaboration in edge computing environments to address the growing demands of data processing in modern digital infrastructure.

Integrated quantum communication network and vibration sensing in optical fibers

Communication and sensing technologies play crucial roles in various aspects of modern society. The seamless combination of communication and sensing systems has attracted significant interest in recent years. Without adding core devices, vibration-sensing functions can be integrated to build a quantum network with high efficiency and versatility. In this study, we propose and demonstrate a network architecture that integrates a downstream quantum access network (DQAN) and vibration sensing in optical fibers. By encoding the key information of eight users simultaneously on the sidemode quantum states of a single laser source and successively separating them using a specially designed narrow-bandwidth filter network, we achieved a secure and efficient DQAN with an average key rate of 1.94×104 bits per second over an 80 km single-mode fiber. Meanwhile, vibration locations with spatial resolutions of 131, 25, and 4 m at vibration frequencies of 100 Hz, 1 kHz, and 10 kHz, respectively, were implemented using the existing DQAN system infrastructure. The results indicate that the backward probe beam has a negligible effect on the DQAN system. Our integrated architecture provides a viable and cost-effective solution for building a quantum communication sensor network and paves the way for the functionality expansion of quantum communication networks.

A Framework for Multi-Objective Optimization in Energy Retrofit of Heritage Museums: Enhancing Preservation, Comfort, and Conservation Conditions

Energy rehabilitation of heritage buildings used as museums presents unique challenges, as it must balance the preservation of cultural heritage with achieving comfortable indoor conditions for visitors and staff. These objectives often conflict, requiring innovative approaches. We propose a methodology that uses dynamical simulation with EnergyPlus and multi-objective optimization with jEPlus + EA software to reduce energy consumption and maximize comfort while maintaining architectural integrity and conservation conditions evaluated by a quantitative analysis based on the European Standards. The framework also includes monitoring microclimate conditions and assessing the risk levels of the exposed collections. A case study in Salta City, Argentina—a historical building repurposed as a museum—illustrates this approach. Results show improved energy performance and comfort conditions for visitors, with an annual energy requirement of about 36% of the original requirement (16.4 kWh/m2 versus 45 kWh/m2) and a decrease of about 32% in the discomfort hours (from 5362 h to 3643 h). Additionally, conservation conditions improved, achieving a more stable microclimate for air temperature and relative humidity. The framework proved useful for evaluating retrofit solutions that enhance the building’s energy performance and comfort without compromising the conservation conditions of the exhibited collections.