Architectural Design Research Articles

Multi-objective Evolutionary Neural Architecture Search for Recurrent Neural Networks

Artificial neural network (NN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of NN architectures and has proven to be successful in automatically finding NN architectures that outperform those manually designed by human experts. NN architecture performance can be quantified based on multiple objectives, which include model accuracy and some NN architecture complexity objectives, among others. The majority of modern NAS methods that consider multiple objectives for NN architecture performance evaluation are concerned with automated feed forward NN architecture design, which leaves multi-objective automated recurrent neural network (RNN) architecture design unexplored. RNNs are important for modeling sequential datasets, and prominent within the natural language processing domain. It is often the case in real world implementations of machine learning and NNs that a reasonable trade-off is accepted for marginally reduced model accuracy in favour of lower computational resources demanded by the model. This paper proposes a multi-objective evolutionary algorithm-based RNN architecture search method. The proposed method relies on approximate network morphisms for RNN architecture complexity optimisation during evolution. The results show that the proposed method is capable of finding novel RNN architectures with comparable performance to state-of-the-art manually designed RNN architectures, but with reduced computational demand.

Trapping of isotropic droplets by disclinations in nematic liquid crystals controlled by surface anchoring and elastic constant disparity.

Linear defects such as dislocations and disclinations in ordered materials attract foreign particles since they replace strong elastic distortions at the defect cores. In this work, we explore the behavior of isotropic droplets nucleating at singular disclinations in a nematic liquid crystal, predesigned by surface photopatterning. Experiments show that in the biphasic nematic-isotropic region, although the droplets are attracted to the disclination cores, their centers of mass shift away from the core centers as the temperature increases. The shift is not random, being deterministically defined by the surrounding director field. The effect is explained by the balance of interfacial anchoring and bulk elasticity. An agreement with the experiment can be achieved only if the model accounts for the disparity of the nematic elastic constants; the so-called one-constant approximation, often used in the theoretical analysis of liquid crystals, produces qualitatively wrong predictions. In particular, the experimentally observed shift towards the bend region around a +1/2 disclination core can be explained only when the bend constant is larger than the splay constant. The described dependence of the precise location of a foreign inclusion at defect cores on the elastic and surface anchoring properties can be used in rational design of microscale architectures.

The green spaces of the city and their significance in rehabilitation of cognitive functions – The spatial method of stimulation

The article addresses the spatial aspect as a factor of significant importance for the success of rehabilitation functions. The location of cognitive rehabilitation activities in an open, urban space allows people with reduced fitness to take up stress-free rehabilitation activity without time limitations and without stigmatization. The architectural design of the positions for mental rehabilitation implemented in public space was addressed to people with dysfunctions of all ages and people suffering from covid fog as a result of a past disease. This article presents the results of preliminary observational studies conducted on a focus group of COVID19 convalescents, who were provided with an open rehabilitation space equipped with 12 rehabilitation tables. The results showed the decisive influence of the placement of rehabilitation elements in the open green space for rehabilitation results. The task of the mind training path is to raise and maintain intellectual fitness in a friendly recreational space. Prototype studies have shown that, de-pending on the arrangement of individual stops, the mind training path offers different efficiency of exercises, but it is always a better result than in closed spaces of medical facilities.

Programmable Interfacial Band Configuration in WS2/Bi2O2Se Heterojunctions.

van der Waals heterojunctions based on transition-metal dichalcogenides (TMDs) offer advanced strategies for manipulating light-emitting and light-harvesting behaviors. A crucial factor determining the light-material interaction is in the band alignment at the heterojunction interface, particularly the distinctions between type-I and type-II alignments. However, altering the band alignment from one type to another without changing the constituent materials is exceptionally difficult. Here, utilizing Bi2O2Se with a thickness-dependent band gap as a bottom layer, we present an innovative strategy for engineering interfacial band configurations in WS2/Bi2O2Se heterojunctions. In particular, we achieve tuning of the band alignment from type-I (Bi2O2Se straddling WS2) to type-II and finally to type-I (WS2 straddling Bi2O2Se) by increasing the thickness of the Bi2O2Se bottom layer from monolayer to multilayer. We verified this band architecture conversion using steady-state and transient spectroscopy as well as density functional theory calculations. Using this material combination, we further design a sophisticated band architecture incorporating both type-I (WS2 straddles Bi2O2Se, fluorescence-quenched) and type-I (Bi2SeO5 straddles WS2, fluorescence-recovered) alignments in one sample through focused laser beam (FLB). By programming the FLB trajectory, we achieve a predesigned localized fluorescence micropattern on WS2 without changing its intrinsic atomic structure. This effective band architecture design strategy represents a significant leap forward in harnessing the potential of TMD heterojunctions for multifunctional photonic applications.

Angstrom‐scale channels with versatile ion‐membrane interactions enabling precise ion separation via electrodialysis

AbstractIn nature, efficient and selective ion transport is facilitated by ion‐conductive channels in cell membranes; these channels reveal an architectural design with specialized functionality. Drawing inspiration from this, mechanistic insights into the angstrom‐scale‐channel membrane composed of ionic‐crosslinked polybenzimidazole and sulfonated poly(ether ether ketone), exhibiting functional differentiation and efficient ion‐sieving properties are presented. Nanochannels allow for strong hydrogen‐bonding interactions with hydrated ions of higher polarity, while rendering significant electrostatic charge effects that impede the transition of multivalent ions by compressing effective passageways. Both hydrogen bonding and electrostatic interactions synergistically result in high selectivity for monovalent ions over multivalent ions because the latter requires overcoming higher energy barriers for transport compared with the former, thereby causing varying extents of ion dehydration within the nanochannels. The resulting membrane achieves a high monovalent ion permeation rate of 1.35 mol m−2 h−1 with a high mono/multivalent ion selectivity of 56.5 for K+/Mg2+ and 286 for K+/Al3+.

Performance Assessment Analyzes of Research Nuclear Reactors Based on Steady-state and Kinetic Models

The mainstays of nuclear substance radiation and isotopic synthesis are nuclear-powered power plants, however effective safety evaluation is made tougher by the complicated construction topologies and physical connection effects. This work proposes a multiphysics-linked technique for evaluating both the kinetic and steady-state behaviors of the MPRR and LVR-15 laboratory reactors. To represent complicated member geometries, homogenized assembling sections are generated using two-dimensional whole-core computational simulations. It is discovered that the steady-state findings and the so-called Monte Carl solution comparisons correspond quite nicely. The greatest assemble power mistakes for LVR-15 and MPRR are 6.49%/10%, and the highest command rod value mistakes are 31 pcm/136 pcm, and the mistakes are 377 pcm/383 pcm, accordingly. Meanwhile, the study is done on transitory procedures, such as reactivity-initiated disasters and exposed loss-of-flow mishaps. Both units' modeling findings show plausible adverse feedback events. Furthermore, it is shown that the two reactors' accident-related behaviors are comparable though having different core architectures since they employ the exact same kinds of water as a fluid. The technique for studying nuclear power plant kinetics known as Multi-Physics Simulation (MPM) is explained. Drawing on many research and verification efforts conducted at Politecnico di Milan, Italy, MPM is shown to be a valuable instrument for managing reactors' security and oversight. It may be viewed as a holistic analytical tool that is implemented during the reactor architecture design phase. The capacity to concurrently answer the interrelated equations that control the many physical processes taking place in a nuclear plant inside the same simulated setting is a core characteristic of MPM.

Revelling pore microstructure impacts on the compressive strength of porous proppant based on finite and discrete element method

Ceramic spheres, typically with a particle diameter of less than 0.8 mm, are frequently utilized as a critical proppant material in hydraulic fracturing for petroleum and natural gas extraction. Porous ceramic spheres with artificial inherent pores are an important type of lightweight proppant, enabling their transport to distant fracture extremities and enhancing fracture conductivity. However, the focus frequently gravitates towards the low-density advantage, often overlooking the pore geometry impacts on compressive strength by traditional strength evaluation. This paper numerically bypasses such limitations by using a combined finite and discrete element method (FDEM) considering experimental results. The mesh size of the model undergoes validation, followed by the calibration of cohesive element parameters via the single particle compression test. The stimulation elucidates that proppants with a smaller pore size (40 µm) manifest crack propagation evolution at a more rapid pace in comparison to their larger-pore counterparts, though the influence of pore diameter on overall strength is subtle. The inception of pores not only alters the trajectory of crack progression but also, with an increase in porosity, leads to a discernible decline in proppant compressive strength. Intriguingly, upon crossing a porosity threshold of 10 %, the decrement in strength becomes more gradual. A denser congregation of pores accelerates crack propagation, undermining proppant robustness, suggesting that under analogous conditions, hollow proppants might not match the strength of their porous counterparts. This exploration elucidates the underlying mechanisms of proppant failure from a microstructural perspective, furnishing pivotal insights that may guide future refinements in the architectural design of porous proppant.

The use of slime molds as a design guide in urban design, A case of Turkey/İzmir/Karabağlar

Urban design is a complex and challenging process that encompasses many disciplines, such as urban planning, architecture, and landscape. On the urban design scale, it’s important to consider short paths compatible with pedestrian behaviors, especially in public spaces, in terms of designing healthier and more accessible urban areas. But conventional design processes, which are mostly based on the designer’s observations or intuitions, fail to satisfy user behaviors in usage. Studies reveal that P. polycephalum slime molds have the potential to guide good urban planning. However, it is noteworthy that there are not enough studies yet in the disciplines of architecture and urban design on the design of pedestrian ways in small-scale areas, and there is a need for research. In this direction, this study is the first step of a method that is aimed at being developed for the disciplines of architecture and urban design in the long process. The main hypothesis is that a design template can be created as a result of graphical analysis of living slime mold experiments on the map, especially in undesigned empty urban areas, for architects and planners, and it can provide creative suggestions to the designer. In this direction, in this study, a graphic design template proposal was created based on live cell experiments at a site in Izmir, Turkey, which the local government aims to design as a pedestrianized zone and open for competition. Slime molds are used directly as a computer rather than as inspiration for a computer, and a pedestrian-oriented design template proposal develops with the behavioral models of slime molds. Compared to the award-winning designs developed for the same area, it has been shown that even within the framework of simple graphical measurements, it gives better results and creates more optimal routes on main and side roads. It is envisaged that this study can play a pioneering role for studies involving more detailed mathematical models that can begin in the field of architecture and urban design.

Visual analysis of fitness landscapes in architectural design optimization

In architectural design optimization, fitness landscapes are used to visualize design space parameters in relation to one or more objective functions for which they are being optimized. In our design study with domain experts, we developed a visual analytics framework for exploring and analyzing fitness landscapes spanning data, projection, and visualization layers. Within the data layer, we employ two surrogate models and three sampling strategies to efficiently generate a wide array of landscapes. On the projection layer, we use star coordinates and UMAP as two alternative methods for obtaining a 2D embedding of the design space. Our interactive user interface can visualize fitness landscapes as a continuous density map or a discrete glyph-based map. We investigate the influence of surrogate models and sampling strategies on the resulting fitness landscapes in a parameter study. Additionally, we present findings from a user study (N = 12), revealing how experts’ preferences regarding projection methods and visual representations may be influenced by their level of expertise, characteristics of the techniques, and the specific task at hand. Furthermore, we demonstrate the usability and usefulness of our framework by a case study from the architecture domain, involving one domain expert.

Enhancing BIM Integration: A Comparative Analysis of Novel Composite Structure Documentation Methods

The proper selection and planning of building materials are crucial tasks in architectural design, as they fundamentally impact the functioning of the structure. In traditional design processes, this information is recorded in text form, typically using word processing software. However, this approach hinders the integration with modern, data-driven design methods and is incompatible with the increasingly popular building information modeling (BIM) processes. To address this, two new methods have been developed: one database-like method in the form of an Excel spreadsheet and the other as a dedicated web application. This article introduces and compares these methods based on pilot projects conducted by university students and an expert. Based on the results of the study conducted among students and expert, the database-like method proves to be the fastest. For students, creating a composite structure took an average of 14–20 min, while for experts, it took an average of 1.2 min. According to the evaluation of participants, the traditional method does not facilitate automatic communication with BIM, while both the database and web solutions promote it. The web-based solution, with its dedicated layout and functionality, offers additional advantages in this regard. The research underscores the importance of structured data in BIM and proposes new methods to streamline composite documentation processes during the design phase.

Fabrication framework for metal supported solid oxide cells via tape casting

Among the different solid oxide cells (SOCs) designs, metal supported SOCs (MSOCs) offer important advantages such as enhanced mechanical robustness, improved thermal resilience and lower material costs. The conventional tape casting method, which is used for the commercial multilayer ceramic technology, is also attractive for the fabrication of MSOCs due to its inherent scalability and cost-efficient fabrication methodology while offering a reliable product without compromising critical microstructural aspects and electrochemical performance during operation.This study is aimed at addressing the main challenges in the fabrication of MSOCs using tape casting, to provide a robust framework for the fabrication parameters, allowing the technology to advance to a more mature stage. It was shown that the dispersion of the powder particles and the physical and chemical characteristics of the binder are found to play a crucial role in obtaining defect free MSOCs and are discussed in detail. Different architectural designs of the cells (asymmetric and symmetric) and electrode configurations (ceramic and metal-ceramic composites) are studied, highlighting their strengths and challenges. The framework established within this work allowed to fabricate, reproduce and test MSOC that exhibited electrochemical performance comparable to state-of-the-art solid oxide cells (electrolysis current density of 0.6 A/cm2 at 1.3 V at 700oC, 50 % steam in H2 at fuel side and air at the oxygen side).

Improving Hadoop MapReduce performance on heterogeneous single board computer clusters

Over the past decade, Apache Hadoop has become a leading framework for big data processing. Single board computer (SBC) clusters, predominantly adopting Raspberry Pi (RPi), have been employed to explore the potential of MapReduce processing in terms of low power and cost because, capital costs aside, power consumption has also become a primary concern in many industries. After building SBC clusters, it is prevalent to consider adding more nodes, particularly newer generation SBCs, to the existing clusters or replacing old (or inactive) nodes with new ones to improve performance, inevitably causing heterogeneous SBC clusters. The Hadoop framework on these heterogeneous SBC clusters creates challenging new problems due to computing resource discrepancies in each node. Native Hadoop does not carefully consider the heterogeneity of the cluster nodes. Consequently, heterogeneous SBC Hadoop clusters result in significant performance variation or, more critically, persistent node failures. This paper proposes a new Hadoop Yet Another Resource Negotiator (YARN) architecture design to improve MapReduce performance on heterogeneous SBC Hadoop clusters with tight computing resources. We newly implement two main scheduling policies on Hadoop YARN based on the correct computing resource information that each SBC node provides: (1) two (master-driven vs. slave-driven) MapReduce task scheduling frameworks to determine more effective processing modes and (2) ApplicationMaster (AM) and reduce task distribution mechanisms to provide the best Hadoop performance by minimizing performance variation. Thus, the proposed Hadoop framework makes the best use of the performance-frugal SBC Hadoop cluster by intelligently distributing MapReduce tasks to each node. To our knowledge, the proposed framework is the first redesigned Hadoop YARN architecture to address various challenging problems particularly on heterogeneous SBC Hadoop clusters for big data processing. The extensive experiments with Hadoop benchmarks demonstrate that the redesigned framework performs better performance than the native Hadoop by an average of 2.55× and 1.55× under I/O intensive and CPU-intensive workloads, respectively.

Hardware Conceptual Design of Tsunhan-14 Multimodal Robot Observer in Support of TNI Tasks

The development of technology in the military field has changed from time to time. This dynamic must be taken seriously because they are a challenge, and pose a potential threat to the sovereignty of the Unitary State of the Republic of Indonesia (NKRI), As well as the trend of the technology-based warfare today. So it has become a necessity for the Indonesian National Army (TNI) to accept it. One of the popular technologies today, war robt technology(warbo), and including multimodal robots with a variety of basic missions. Furthermore, developing a multimodal robot concept design that can fulfil TNI surveillance needs. The methodology used is in the form of interview, observations, comparison, and literature studies by applying system engineering theory and life cycle models. This research has successfully formulated user requirement objectivies which are then elaborated into robot design concepts including characteristic design, and architecture design of multimodal monitoring robots. The hardware on the robot is design differently from others because it has the ability to fly and walk on the ground. The robot is also conceptualised to have advantages in terms of durability with agility, silence, and operate with various terrain conditions. Equipped with sensors to see, hear, measure ambient temperature, and read surrounding conditions using camera sensors, where the robot moves autonomously equipped with GPS and Lidar can send data in the form of audio visual directly to the Ground Control System (command centre). The concept design of the multimodal monitoring robot called Tsunhan-14 is expected to be the basis for determining technical requirement and further developed into a national innovation that is utilized as part of the TNI’s war strategy.

The Postmodernisms of Russell Hall: Exploring Australia’s Changing Architecture Culture Through a Biographical Approach

ABSTRACT This paper studies the work and practice of Brisbane-based architect Russell Hall to better understand how architects in Australia negotiated the professional and formal changes that emerged in architectural culture from the 1970s. Architectural historiographies tend to discuss postmodernism as plural and multiple, while also boxing it into various branches or strands, such as ecological, traditionalist/historicist, vernacular, or pop/fun. Many of these strands, however, co-exist within the work of architects. When you study their professional biographies up close, it becomes difficult (if not impossible) to sustain these categorisations, as architectural designs often blend different interests in specific, situated ways. If broad categorisations exist about postmodern architectural forms, so too do they exist about postmodern professional practice. In the latter decades of the 20th century, it is often said, the “hired-gun-architect” and the “conglomerate architecture-building-business corporation” replaced the “gentleman-artist-architect.” However, once again, on the ground, the situation is often more nuanced and multifaceted than that. This paper adopts a biographical approach to better understand how one architect, Hall, negotiated the professional and formal changes that emerged in architectural culture from the 1970s. In doing so, it seeks to improve our understanding of postmodern architectural culture in Australia—and Queensland specifically.

Sex classification of 3D skull images using deep neural networks

Determining the fundamental characteristics that define a face as "feminine" or "masculine" has long fascinated anatomists and plastic surgeons, particularly those involved in aesthetic and gender-affirming surgery. Previous studies in this area have relied on manual measurements, comparative anatomy, and heuristic landmark-based feature extraction. In this study, we collected retrospectively at Cedars Sinai Medical Center (CSMC) a dataset of 98 skull samples, which is the first dataset of this kind of 3D medical imaging. We then evaluated the accuracy of multiple deep learning neural network architectures on sex classification with this dataset. Specifically, we evaluated methods representing three different 3D data modeling approaches: Resnet3D, PointNet++, and MeshNet. Despite the limited number of imaging samples, our testing results show that all three approaches achieve AUC scores above 0.9 after convergence. PointNet++ exhibits the highest accuracy, while MeshNet has the lowest. Our findings suggest that accuracy is not solely dependent on the sparsity of data representation but also on the architecture design, with MeshNet's lower accuracy likely due to the lack of a hierarchical structure for progressive data abstraction. Furthermore, we studied a problem related to sex determination, which is the analysis of the various morphological features that affect sex classification. We proposed and developed a new method based on morphological gradients to visualize features that influence model decision making. The method based on morphological gradients is an alternative to the standard saliency map, and the new method provides better visualization of feature importance. Our study is the first to develop and evaluate deep learning models for analyzing 3D facial skull images to identify imaging feature differences between individuals assigned male or female at birth. These findings may be useful for planning and evaluating craniofacial surgery, particularly gender-affirming procedures, such as facial feminization surgery.

Towards Sustainable Education by Design: Evaluating Pro-Ecological Architectural Solutions in Centers for Environmental Education

The imperative shift towards ecological consciousness in architectural design, driven by the pressing need to mitigate energy consumption and carbon emissions while fostering user well-being, has propelled the discourse on sustainable architecture to the forefront of contemporary dialogue. Concepts such as ecological architecture, sustainable, green, and regenerative design have emerged as pivotal frameworks aimed at aligning architectural practices with environmental imperatives. In this evolving architectural landscape, the centers for ecological education (CEEs) play an important role, embodying the intersection of architecture and ecological education. These centers, with their diverse educational initiatives, provide dedicated spaces for comprehensive ecological education. However, a gap exists in the literature regarding studies focusing on CEEs and the evaluation criteria for such facilities. This article seeks to bridge this gap by evaluating buildings designated for ecological education, aiming to present ecological content while exemplifying sustainable architectural principles. The study employs a research by design approach, combining a literature review with site investigations and qualitative assessments to elucidate the unique challenges and opportunities inherent in designing CEEs. Criteria for assessing the ecological quality of buildings are formulated. Through a comparative analysis, the article identifies key parameters for evaluating CEEs, considering their dual function as educational spaces and architectural exemplars. The evaluation framework developed in this study provides a valuable tool for architects, designers, and policymakers seeking to promote ecological education and sustainable architectural practices.

Design of a low-area hardware architecture to predict early signs of sudden cardiac arrests

Sudden cardiac arrest (SCA) results in an unexpected and untimely death within minutes, and its early prediction can alert cardiac patients to a timely medical diagnosis. To detect early symptoms of an SCA, the detection and classification of ventricular tachycardias (VT) are of utmost importance. In this work, a low-area yet highly accurate hardware architecture for VT classification is proposed based on the detection of premature ventricular contraction (PVC) beats. After pre-processing of the ECG signals using a wavelet-based pre-processing unit, a characteristics-matching algorithm is used to detect the PVC beats, and a low-complexity adaptive decision-based logic classifier is used to classify them into four types of VTs, namely monomorphic, polymorphic, non-sustained VT (NSVT), and sustained VT (SVT). FPGA verification of the hardware architecture for the VT classifier using the Nexys 4 DDR Artix-7 board utilizes 10.4 % of the total available resources and displays the type of VT and the number of PVCs detected to help in determining the severity of SCA and the need for medical attention. The ASIC implementation of the proposed PVC-based VT classification using the SCL 180 nm CMOS technology results in an area overhead of 0.02 mm2 and a power consumption of 3.47 μW for a high accuracy rate of 98.2 %. When compared to the existing CA detection systems for wearable devices, the proposed one consumes the least area while achieving high detection rates.

Optimizing wall structure for enhanced thermal performance: A layer-specific dimensionless parameter analysis in multi-layer walls

Enhancing building energy efficiency and thermal comfort crucially involves optimizing the phase shift (PS) and decrement factor (DF) of exterior walls. Using the auxiliary function method, this paper presents analytical solutions for the DF and PS in double-layer walls, subsequently extending these to multi-layer walls. Insulation and structural material properties (density, thermal conductivity, specific heat capacity), thickness, internal and external convective heat transfer coefficients, outdoor temperature fluctuations, and insulation layering in multi-layered walls were taken into consideration in acquiring analytical solutions. Our findings in double-layer walls and analogous structures show that the DF and PS are largely governed by two dimensionless parameters per layer: thermal diffusivity index and Biot number. Regardless of Biot numbers (ε1 and ε2), an increase in thermal diffusivity indexes (δ1 and δ2) consistently reduces the DF and enhances the PS. Moreover, a larger ε1 with a smaller ε2 generally associates with a lower DF, but their impact on PS is less significant compared to thermal diffusivity index. In multi-layer walls, especially with mirror symmetry, we observe a dual extremum phenomenon, marked by prolonged PS and reduced DF. This underlines the importance of structural configuration in wall thermal performance. Thus, in double-layer structures, while the DF decreases and PS increases with increasing thermal diffusivity index, the influence of Biot numbers is comparatively minimal, highlighting the paramount role of thermal diffusivity index in optimizing thermal behavior. This discovery provides valuable guidance for identifying wall structures with minimal DF and maximal PS during the architectural design phase.

From Reading to Design of the “[entra]mar”: The Role of Urban Morphology in Architectural Pedagogy and Design

From Reading to Design of the “[entra]mar”: The Role of Urban Morphology in Architectural Pedagogy and Design

ON THE MIGRATION OF DOMAIN DRIVEN DESIGN TO CQRS WITH EVENT SOURCING SOFTWARE ARCHITECTURE

The article addresses the issue of migrating applications, particularly those following the Domain-Driven Design (DDD) architecture, to the Command Query Responsibility Segregation (CQRS) paradigm with Event Sourcing. Long-standing systems often need help with problems related to inflexible, outdated architecture, and dependencies, leading to increased maintenance costs. The paper examines the advantages of DDD and proposes CQRS as a viable alternative, focusing on improving productivity and scalability. The main objective of the work is to assess a secure path for migrating a project from DDD architecture to the CQRS and Event Sourcing architecture and to determine the migration roadmap. The article conducts an experiment in which migration of a test project is performed, evaluating the time, effort, and results of the migration. The research methodology includes evaluating complexity using McCabe's Cyclomatic Complexity metric and assessing performance through the execution time of system methods. The experiment is conducted on a typical project – a task-tracking system. The results of implementing CQRS show a fourfold increase in the number of classes and a 50% increase in the number of lines of code. However, this increase is justified as it improves modularity, transparency, and manageability during development, ultimately facilitating system maintenance and significantly enhancing overall system productivity. It is worth noting that the overall cyclomatic complexity of the system remains almost unchanged. In summary, the article examines the assessment of migrating a project from DDD architecture to CQRS and Event Sourcing, combining theoretical findings with practical experimentation. It provides valuable insights into the advantages, disadvantages, and challenges of implementing CQRS architecture in complex information systems.