Architecture Model Research Articles

Fuzzy Neural Logic Reasoning for Robust Classification

The efficacy of neural networks is widely recognized across a multitude of machine learning tasks, yet their black-box nature impedes the understanding of their decision-making processes. Such lack of explainability limits their use in high-stake fields such as medicine and finance, where transparent decision-making is essential. In contrast, traditional rule-based models offer clear input-output mappings, but often lag in performance when compared to their neural network counterparts. To address this challenge, this study introduces Fuzzy Neural Logic Reasoning (FNLR), a novel architecture that combines the best of both rule-based and deep learning models to achieve performance, interpretability, and noise robustness simultaneously. At its core, FNLR employs a “Symbolic Pre-training + Neural Fine-tuning” paradigm. Initially, the model adapts a pre-fitted binary decision tree. It then performs a “neuralization” process, replacing each node of the tree with a corresponding neural network equivalent. This transformation is facilitated through three shallow MLP modules, which are trained to emulate the relational operators intrinsic to decision trees. The model architecture is also extensible, allowing it to further boost expressiveness. Furthermore, FNLR incorporates fuzzy logic by proposing novel fuzzy relational operators, accounting for satisfaction degrees of propositions and thus eliminating rigid decision boundaries. This approach enhances model flexibility, enabling all paths of the decision tree to contribute to the target prediction in a weighted manner. Empirical evaluations on tabular datasets from various domains demonstrate that FNLR performs comparably to, or better than, state-of-the-art deep learning models designed for tabular data, while also exhibiting strong robustness to noise.

Modelling and optimization for material removal rate while processing bio-compatible Ti-6Al-7Nb using wire electric discharge machining (WEDM)

Abstract This study utilizes machine learning methodologies, such as artificial neural networks (ANN) and TLBO (teaching Learning Based optimisation), to develop a model and Optimisation of the Material Removal Rate (MRR) in wire electrical discharge machining (WEDM) of Ti-6Al-7Nb. The material removal rate was determined by conducting WEDM experiments with different levels of control parameters, including spark on time, spark off time, peak current, servo voltage, and wire feed rate using a Full Factorial approach through 81 runs. The most effective architecture for the ANN model was 4–10–1, and the parameters were adjusted depending on R2. The Artificial Neural Network (ANN) predictions were compared to those produced by the Multiple Linear Regression (MLR) model. The performance of these models was assessed by calculating the correlation between the experimental values and predicted values by models (R2). MRR value is optimised using TLBO (Teaching Learning Based Optimisation), keeping the relation developed by MLR as the objective function and leading to an improved material removal rate. The proposed method ANN & TLBO would help accurately predict and optimise MRR while processing Ti-6Al-7Nb. These machine learning-based methods significantly enhance complex machining processes by providing predictive capabilities & optimizing parameters, hence playing a vital role in achieving higher efficiency, quality, and adaptability in manufacturing environments.

Features of the representation of architectural space in the painting works of Giorgio de Chirico

This article describes the features of the depiction of architectural space in the paintings of the surrealist artist Giorgio de Chirico. In general terms, surrealism is described as an artistic style of the early twentieth century, its emergence, distinctive features and semantic tasks; The questions in relation to Giorgio de Chirico are examined in more detail: from what architectural objects and constituent elements is the urban space of his paintings formed, what objects are the main semantic parts, the general universal architectural model of the formation of such a space in de Chirico’s compositions is described. The article describes the semiotic structure used by the master, reveals the concept and meaning of the term “metaphysical painting”, ways of reading a surreal work of art, and the playful nature of the interaction between the artist and the viewer. The article analyzes in detail the methods and features of constructing the internal space of the metaphysical works of this master, showing the constituent elements, methods, techniques, and techniques for organizing the composition of the painting. The significance of the image of architectural space in de Chirico’s works on modern man and the use of his artistic experience in our time is described.

Data Generation and Training of Surrogate Models for Friction Factor and Nusselt Number in Low Reynolds Number Flows Through Pin Fin Geometries

Abstract The design of various biomedical, electronics cooling, and microfluidic devices relies on geometry-specific models and empirical correlations for flow and heat transfer through microscale pin fin geometries. Machine learning (ML) techniques are being used across many branches of science to develop more generalized surrogate models that can predict such transport processes. To collapse the simulation of flow and thermal properties across many different pin fin surfaces into a single predictive tool, the present study develops machine-learning-based surrogate models for the friction factor and Nusselt number (for constant wall temperature conditions) for fully developed low Reynolds number flow across pin fin geometries of differing cross section shape (circular, square, triangular) in aligned or staggered arrangements, oriented at any angle to the incoming flow, and for a range of transverse and longitudinal pitches, with water as the working fluid. The model training data are generated using an automated workflow that allows thousands of numerical simulations to be carried out on across different geometric and flow configurations. A total of ∼14,800 distinct simulation cases, for both friction factor and Nusselt number, are generated while varying the Reynolds number and aforementioned geometric parameters to train and test the machine learning models. The machine learning model architecture takes inputs of both image and vector data, and then outputs a scalar friction factor or Nusselt number. The trained models yield a goodness of fit (R2) value of 0.98 on unseen data.

Impact of data bias on machine learning for crystal compound synthesizability predictions

Abstract Machine learning models are susceptible to being misled by biases in training data that emphasize incidental correlations over
the intended learning task. In this study, we demonstrate the impact of data bias on the performance of a machine learning
model designed to predict the likelihood of synthesizability of crystal compounds. The model performs a binary classification on
labeled crystal samples. Despite using the same architecture for the machine learning model, we showcase how the model’s
learning and prediction behavior differs once trained on distinct data. We use two data sets for illustration: a mixed-source data
set that integrates experimental and computational crystal samples and a single-source data set consisting of data exclusively
from one computational database. We present simple procedures to detect data bias and to evaluate its effect on the model’s
performance and generalization. This study reveals how inconsistent, unbalanced data can propagate bias, undermining real world
applicability even for advanced machine learning techniques.

Integration of Fog Computing in a Distributed Manufacturing Execution System Under the RAMI 4.0 Framework

Technological progress has driven the integration of new technologies in the field of industrial automation, but a structured framework is often lacking to efficiently guide the transition from traditional industries. This article presents the implementation of advanced technologies on FESTO’s (MPS-500) modular production system, using the reference architectural model for Industry 4.0 (RAMI 4.0) as a guide for scaling. It highlights the importance of the synergy between information technologies (ITs), which enables the development of a multi-level processing system. This system performs concurrent tasks, thus managing execution and manufacturing through an MES based on requests from the cloud. On the other hand, at a lower level, a fog computing system was integrated, which relieves the processing load by distributing processes locally. In addition, matrix mapping was performed to map the integrated technologies within the context of a reference model, allowing a clear alignment between the different levels of the system. The results show a significant reduction in waiting times between batches and operations, which directly improves productivity and offers greater flexibility, that is crucial for SMEs during their growth and scaling process towards Industry 4.0.

Semantic Web-Driven Targeted Adversarial Attack on Black Box Automatic Speech Recognition Systems

The susceptibility of Deep Neural Networks (DNNs) to adversarial attacks in Automatic Speech Recognition (ASR) systems has drawn significant attention. Most work focuses on white-box methods, but the assumption of full transparency of model architecture and parameters is unrealistic in real-world scenarios. Although several targeted black-box attack methods have been proposed in recent years, due to the complexity of ASR systems, they primarily rely on query-based approaches with limited search capabilities, leading to low success rates and noticeable noise. To address this, we propose DE-gradient, a new black-box approach using differential evolution (DE), a population-based search algorithm. Inspired by Semantic Web ideas, we introduce modulation noise to preserve semantic coherence while enhancing imperceptibility. In experiments on two public datasets, DE-gradient improved attack success rates by 19% and increased the signal-to-noise ratio (SNR) of silent parts from 27 dB to 54 dB, establishing a strong baseline for evaluating black-box adversarial attacks in ASR systems.

Beyond Typologies: Early Modern Italian Town Halls in Comparative Perspective (14th-17th Centuries)

By challenging the traditional, typological, approach to the history of town halls, we aim to place Italian civic architecture at the center of a cross-disciplinary study focused, on one hand, on the uses and functions of these buildings, and on the other, on their cultural and identity meanings. The papers gathered in this special collection do not present a history of architectural models and persistencies, but rather one of continuous transformations, conversions, and adaptations, shaped by the material and symbolic functions that public buildings fulfilled, and often continue to fulfill, in the places where they were built.

Technical Note: Neural Network Architectures for Self-Supervised Body Part Regression Models with Automated Localized Segmentation Application.

The advancement of medical image deep learning necessitates tools that can accurately identify body regions from whole-body scans to serve as an essential pre-processing step for downstream tasks. Typically, these deep learning models rely on labeled data and supervised learning, which is labor-intensive. However, the emergence of self-supervised learning is revolutionizing the field by eliminating the need for labels. The purpose of this study was to compare neural network architectures of self-supervised models that produced a body part regression (BPR) slice score to aid in the development of anatomically localized segmentation models. VGG, ResNet, DenseNet, ConvNext, and EfficientNet BPR models were implemented in the MONAI/Pytorch framework. Landmark organs were correlated to slice scores and mean absolute error (MAE) was calculated from the predicted slice and the actual slice of various organ landmarks. Four localized DynUNet segmentation models (thorax, upper abdomen, lower abdomen, and pelvis) were developed using the BPR slice scores. Dice similarity coefficient (DSC) was compared between the localized and baseline segmentation models. The best performing BPR model was the EfficientNet architecture with an overall 3.18 MAE, compared to the VGG baseline model with a MAE of 6.29. The localized segmentation model significantly outperformed the baseline in 16 out of 20 organs with a DSC of 0.88. Enhanced neural networks like EfficientNet have a large performance increase in localizing anatomical structures in a CT compared in BPR task. Utilizing BPR slice score is shown to be effective in anatomically localized segmentation tasks with improved performance.

Survival models and longitudinal medical events for hospital readmission forecasting.

The rate of 30-day all-cause hospital readmissions can affect the funding a hospital receives. An accurate and reliable readmission prediction model could save money and increase quality-of-care. Few projects have explored formulating this task as a survival prediction problem, where models can exploit a real-valued time-to-readmission target. This paper demonstrates the effectiveness of a survival-inspired readmission model, especially when paired with a longitudinal patient representation that is agnostic to disease-cohort and predictive task. We forecast readmissions for a population-level cohort of 421,088 patients discharged in 2015 and 2016 from hospitals in Alberta, Canada. Clinical features and sequences of historical medical codes (calculated from at least four full years prior to discharge) from linked administrative sources serve as model inputs. We trained binary 30-day readmission models (XGBoost and a Deep Neural Network) and time-to-event readmission models (CoxPH and N-MTLR) with and without machine-learned medical knowledge at initialization, then compared against the popular LACE-based model using the AUROC score at 30 days (AUROC@30). Survival models are additionally evaluated using concordance, Integrated Brier, and L1-loss scores. All models that utilize sequence features markedly out-perform even the best models trained on only clinical features. Further, a time-to-event target improves predictive performance at 30 days, given the same model inputs and architecture. N-MTLR, using solely sequence inputs and initialized with pre-learned medical knowledge, achieves an average AUROC@30 of 0.8460 over five folds with a standard deviation of 0.003. All trained models match or out-perform the LACE baseline of 0.6587±0.003. Sequences of administrative medical codes contain rich predictive information for forecasting readmissions, and embedding medical knowledge a priori using machine learning provides readmission models an advantageous foundation for training. When combined with a model that can leverage a time-to-event target, excellent performance is possible on the 30-day all-cause readmission task using only administrative data.

Predicting Mutual Fund Stress Levels Utilizing SEBI’s Stress Test Parameters in MidCap and SmallCap Funds Using Deep Learning Models

Abstract: The Association of Mutual Funds of India (AMFI), under the direction of the Securities and Exchange Board of India (SEBI), provided open access to various risk parameters with respect to MidCap and SmallCap funds for the first time from February 2024. Our study utilizes AMFI datasets from February 2024 to September 2024 which consisted of 14 variables. Among these, the primary variable identified in grading mutual funds is the stress test parameter, expressed as number of days required to liquidate between 50% and 25% of the portfolio, respectively, on a pro-rata basis under stress conditions as a response variable. The objective of our paper is to build and test various neural network models which can help in predicting stress levels with the highest accuracy and specificity in MidCap and SmallCap mutual funds based on AMFI’s 14 parameters as predictors. The results suggest that the simpler neural network model architectures show higher accuracy. We used Artificial Neural Networks (ANN) over other machine learning methods due to its ability to analyze the impact of dynamic interrelationships among 14 variables on the dependent variable, independent of the statistical distribution of parameters considered. Predicting stress levels with the highest accuracy in MidCap and SmallCap mutual funds will benefit investors by reducing information asymmetry while allocating investments based on their risk tolerance. It will help policy makers in designing controls to protect smaller investors and provide warnings for funds with unusually high risk.

Facial Image expression recognition and prediction system.

Facial expression recognition system is an advanced technology that allows machines to recognize human emotions based on their facial expressions. In order to develop a robust prediction model, this research work proposes three distinct architectural models to produce a facial expression prediction system that looks like this: The first model is on using a support vector machine to carry out a classification task. As a follow-up to the second model, an attempt was made to create a Convolution Neural Network (CNN) using the VGG-NET (Visual Geometry Group Network). Following analysis of the results, an attempt was made to enhance the outcome using the third model, which used convolutional sequential layers linked to seven distinct expressions, and an inference was drawn based on loss and accuracy metric behavior. We will use a dataset of human picture facial images in this research, which has more than 35500 facial photographs and represents seven different types of facial expressions. We will analyze our data and make every effort to remove as much noise as we can before feeding that information to our model. We use the confusion matrix to assess the model's performance after it has been implemented effectively. To demonstrate the effectiveness of our model architecture, we will generate bar graphs and scatter plots for each model to display model loss and accuracy. The output of this model is visualized with actual class and predictive class and the result has a graphical representation for each and every output facial Images which makes our recognition system user-friendly.

Power-consumption analysis for different IPoWDM network architectures with ZR/ZR+ and long-haul muxponders

Operators are constantly faced with the need to increase optical-network capacity to accommodate rapid traffic growth while minimizing the cost-per-bit and power-per-bit. The drastic reduction of the power consumption of IP routers and ZR/ZR+ pluggable transponders seen in the past several years has renewed the interest in “opaque” optical-network architectures, where no optical bypassing is allowed. In this work, we aim to quantify and compare the power consumption of four “IP over wavelength division multiplexing” (IPoWDM) transport network architectures employing ZR/ZR+ modules versus long-haul muxponders, considering different grooming, regeneration, and optical bypassing capabilities. We first propose a power consumption model for different IPoWDM node architectures with ZR/ZR+ modules and long-haul muxponders. Then, to obtain the power consumption of different architectures, we propose a compact auxiliary-graph-based network-design algorithm extensible to different network architectures. Moreover, we investigate how the continuous decrease in the power consumption of ZR/ZR+ and IP routers can impact the power consumption of different architectures through a sensitivity analysis. Illustrative numerical results on networks of different sizes show that, despite drastic reductions of power consumption at the IP layer, optical bypassing is still the most power-efficient solution, reducing consumption by up to 48%.

User-Centered Design of Architectural Models Adapted to Monolithic Structure Technology

Monolithic Structure Technology (MST) is a new construction process patented in Morocco, offering significant advantages in terms of durability, resilience, and energy efficiency. This technology enables the mass production of low-rise green buildings thanks to the design of a monolithic metal formwork with a high reuse rate for the bonding of the structure working mainly in compression. Unlike conventional approaches to construction, the architectural design and load-bearing structure are studied simultaneously from the formwork design phase, as the structure mobilizes its form to guarantee stability. The design of architectural models adapted to MST is therefore of paramount importance if we are to exploit the full potential of this innovative technology. In this context, we developed the most suitable designs for MST based on a user-centered approach by directly involving the presumed future operators through a structured questionnaire to identify their preferences.115 respondents were interviewed, and the results were analyzed and used to design 10 different models. We then complemented the design process with a neuro-architectural approach to optimize design factors (facades, levels and rooms, shape and openings, roof type, interior layout, green spaces, and materials). The 10 designed models were then used for a closed card sorting study, followed by another semi-structured interview. User preferences were synthesized and the optimum design for the Moroccan countryside was selected.

Quantitative assessment of neurodevelopmental maturation: a comprehensive systematic literature review of artificial intelligence-based brain age prediction in pediatric populations

IntroductionOver the past few decades, numerous researchers have explored the application of machine learning for assessing children’s neurological development. Developmental changes in the brain could be utilized to gauge the alignment of its maturation status with the child’s chronological age. AI is trained to analyze changes in different modalities and estimate the brain age of subjects. Disparities between the predicted and chronological age can be viewed as a biomarker for a pathological condition. This literature review aims to illuminate research studies that have employed AI to predict children’s brain age.MethodsThe inclusion criteria for this study were predicting brain age via AI in healthy children up to 12 years. The search term was centered around the keywords “pediatric,” “artificial intelligence,” and “brain age” and was utilized in PubMed and IEEEXplore. The selected literature was then examined for information on data acquisition methods, the age range of the study population, pre-processing, methods and AI techniques utilized, the quality of the respective techniques, model explanation, and clinical applications.ResultsFifty one publications from 2012 to 2024 were included in the analysis. The primary modality of data acquisition was MRI, followed by EEG. Structural and functional MRI-based studies commonly used publicly available datasets, while EEG-based studies typically relied on self-recruitment. Many studies utilized pre-processing pipelines provided by toolkit suites, particularly in MRI-based research. The most frequently used model type was kernel-based learning algorithms, followed by convolutional neural networks. Overall, prediction accuracy may improve when multiple acquisition modalities are used, but comparing studies is challenging. In EEG, the prediction error decreases as the number of electrodes increases. Approximately one-third of the studies used explainable artificial intelligence methods to explain the model and chosen parameters. However, there is a significant clinical translation gap as no study has tested their model in a clinical routine setting.DiscussionFurther research should test on external datasets and include low-quality routine images for MRI. T2-weighted MRI was underrepresented. Furthermore, different kernel types should be compared on the same dataset. Implementing modern model architectures, such as convolutional neural networks, should be the next step in EEG-based research studies.

Modeling of Heat Transfer and Airflow Inside Evacuated Tube Collector With Heat Storage Media: Experimental Validation Powered by Artificial Neural Network

ABSTRACTSolar air heater (SAH) is a widely employed technology for harnessing solar thermal energy in numerous applications. Contemporary research optimizes designs within identical spatial constraints to maximize energy output. However, there is a recognized need to conduct analytical validation to stimulate the experimental setup and formulate an artificial neural network (ANN) model to govern and predict the operation system. This investigation involved developing and assessing an evacuated tube solar air heater (ETSAH) integrated with annulus‐filled heat storage media. Furthermore, this study introduced an ANN model and analytical solution to predict performance parameters, representing a noteworthy contribution. The proposed ANN model achieved its optimal validation performance with a mean square error of 5.4018 × 10−6 after 11 epochs within 31 of training. Also, correlation findings show that the optimal architecture of a feed‐forward backpropagation is achieved when the 5‐40‐40‐40‐2 model architecture is used. In this case, there are five neural nodes in the input layer that represent timing, temperature, radiation, and airflow rate. The power output of the ETSAH device shows a strong correlation with the flow rate, reaching its peak at 0.05 kg/s with a value of 2261 W and dropping to 368 W at 0.006 kg/s. Correspondingly, the greatest energy efficiency was measured at airflow rates of 0.05, 0.01, and 0.006 kg/s, accounting for 48.38%, 27.32%, and 19.65%, respectively.

CTNI-67. AI BASED PREDICTION OF CLINICAL TTFIELDS RESPONSE IN GLIOBLASTOMA PATIENTS (RETROSPECTIVE ANALYSIS)

Abstract RESEARCH QUESTION Accurate and individualized prediction of response to therapies is central to precision medicine and a major goal in neuro-oncology. An extension of overall survival (OS) and progression-free survival (PFS) was observed in patients treated with tumor treating fields (TTFields) plus maintenance temozolomide compared to those treated with maintenance temozolomide alone and TTFields have become an integral part of the treatment of glioblastoma. To identify patients who benefit most from TTFields, we aim to implement a state-of-the-art machine learning approach to create a model capable of identifying responding patients early in treatment. METHODOLOGY In this retrospective analysis, patients with IDH-wildtype glioblastoma treated with TTFields, in addition to RT and temozolomide, as first-line therapy are included. Clinical data and MRI raw data (in DICOM format) are collected. The preprocessing of the MRI data includes reorientation, bias field correction, registration, segmentation, and intensity normalization. This is followed by the extraction of a Radiomics signature. The latter, along with the clinical data, is trained using various machine learning models. The model validation occurs on an independent test cohort. Data collection from various neuro-oncological centers across Europe is ongoing. RESULTS So far, data from 134 TTFields patients and 131 control patients have been collected. Initial results, providing detailed insights into the model architecture and performance, will be presented at the time of the SNO meeting. CONCLUSION This study has the potential to optimize the treatment of glioblastoma patients by using machine learning to allow the early identification of patients that respond to first line therapy.

Development of a model-based modular building kit for sensor-integrating machine elements—Theory and application

AbstractIn the Priority Program 2305 of the German Research Foundation, so-called Sensor-integrating Machine Elements (SiME) are to be developed. These are essentially highly standardized components with integrated microelectronics. The present article presents the development of a model-based construction kit to support the design of integrated sensor systems for these new machine elements. A methodical procedure for collecting the development data required for modeling the modular building kit for SiME is presented and applied to four different cases within the project. Use cases, product structure and module diagrams were recorded and modeled for the machine elements screw, gear, coupling and feather key. These are then linked in SysML models to enable sensor systems for SiME to be configured in line with requirements. The modeling of the system architectures deepens the understanding of the underlying mechatronic system architecture and supports the identification of differentiation features as well as synergy potentials.

Breast Cancer Classification Using Fine-Tuned SWIN Transformer Model on Mammographic Images

Breast cancer is the most prevalent type of disease among women. It has become one of the foremost causes of death among women globally. Early detection plays a significant role in administering personalized treatment and improving patient outcomes. Mammography procedures are often used to detect early-stage cancer cells. This traditional method of mammography while valuable has limitations in its potential for false positives and negatives, patient discomfort, and radiation exposure. Therefore, there is a probe for more accurate techniques required in detecting breast cancer, leading to exploring the potential of machine learning in the classification of diagnostic images due to its efficiency and accuracy. This study conducted a comparative analysis of pre-trained CNNs (ResNet50 and VGG16) and vision transformers (ViT-base and SWIN transformer) with the inclusion of ViT-base trained from scratch model architectures to effectively classify mammographic breast cancer images into benign and malignant cases. The SWIN transformer exhibits superior performance with 99.9% accuracy and a precision of 99.8%. These findings demonstrate the efficiency of deep learning to accurately classify mammographic breast cancer images for the diagnosis of breast cancer, leading to improvements in patient outcomes.

A novel framework for debris flow susceptibility assessment considering the uncertainty of sample selection

The uncertainty arising from random sampling of non-debris flow samples significantly impacts the accuracy of debris flow susceptibility assessments (DFSA). This study introduces a novel uncertainty elimination method, Kernel Density Estimation (KDE), and compares it with Mean and Maximum Probability Analysis (MPA) methods. Furthermore, we investigate the responses of four commonly used machine learning models to sampling uncertainty, comparing two structurally similar models (Random Forest (RF) and Extremely Randomized Trees (ERT)) with two structurally different models (Support Vector Machine (SVM) and Multilayer Perceptron (MLP)). The results indicate that the application of these uncertainty elimination methods can significantly enhance AUC values and zoning accuracy, with the KDE method outperforming the others. Specifically, the AUC values based on KDE for RF, ERT, SVM, and MLP are 0.995, 0.999, 0.999, and 0.853, respectively. The corresponding zoning accuracy for these models is 1.00, 1.00, 1.00, and 0.78, respectively. The study further reveals that the responses to sampling uncertainty vary by model architecture: RF, ERT, and SVM typically exhibit bimodal normal distributions, while the MLP model shows a unimodal distribution. Additionally, MLP is more sensitive to variations in negative samples, whereas RF and ERT are less affected due to the ensemble structure.