Architecture Model Research Articles

Pioneering automation in agricultural subsidy processing through deep learning for computer vision

ABSTRACT Validating farmers’ eligibility for subsidies under the European Union’s Common Agricultural Policy (CAP) requires substantial resources. An automated solution can minimize human errors and save time. This study leverages deep learning to automate the validation process using ground-level landscape images (GLLP), an approach not previously explored. We conducted two rigorous experiments to identify the optimal model architecture and assess the impact of data cleaning, accurate labelling, reduced feature ambiguity, and stricter photo collection protocols on performance. Our results reveal that while the ResNet-18 architecture achieved a recall of 0.61 on the original dataset, distinguishing between eligible and ineligible grasslands was challenging. By addressing image quality and enforcing standardized data collection, accuracy improved to 0.89 and recall to 0.94. Crucially, our research emphasizes the development and validation of effective data collection strategies, ensuring uniformity and high-quality data essential for accurate model performance. Our findings affirm the potential of deep learning to automate subsidy eligibility classification, contingent on resolving challenges related to the quality and standardization of GLLP data.

Towards a more secure reconstruction-based anomaly detection model for power transformer differential protection

IntroductionCyberattacks against Power Transformer Differential Protection (PTDP) have the potential to cause significant disruption and widespread blackouts in power infrastructure. Recent literature has demonstrated how reconstruction-based anomaly detection models can play a critical role in enhancing the security of PTDP against such attacks. However, these models themselves are vulnerable to cyber threats. Adversarial sample generation is an example of a threat against reconstruction-based anomaly detection models.MethodsTo address this threat, we propose an approach for adversarial training of such models appropriate for PTDPs. We then review and compare the effect of adversarial training on the performance of four different model architectures. To demonstrate the efficacy of our proposed approach for improved security and performance in PTDP scenarios, the IEEE PSRC D6 benchmark test system is tested in an OPAL-RT environment.ResultsSimulation results show the effectiveness of the proposed method for improved detection of cyberattacks.

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning

Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. AI code models has demonstrated their value not only in code generating but also in defect detection, enhancing security measures, and improving overall software quality. They are emerging as crucial tools for both software development and maintaining software quality. Like traditional SE tools, open-source collaboration is key in realising the excellent products. However, with AI models, the essential need is in data. The collaboration of these AI-based SE models hinges on maximising the sources of high-quality data. However, data especially of high quality, often holds commercial or sensitive value, making it less accessible for open-source AI-based SE projects. This reality presents a significant barrier to the development and enhancement of AI-based SE tools within the software engineering community. Therefore, researchers need to find solutions for enabling open-source AI-based SE models to tap into resources by different organizations. Addressing this challenge, our position paper investigates one solution to facilitate access to diverse organizational resources for open-source AI models, ensuring privacy and commercial sensitivities are respected. We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security. Additionally, we present guidelines for developers on AI-based SE tool collaboration, covering data requirements, model architecture, updating strategies, and version control. Given the significant influence of data characteristics on federated learning, our research examines the effect of code data heterogeneity on federated learning performance. We consider 6 different scenarios of data distributions and include 4 code models. We also include 4 most common federated learning algorithms. Our experimental findings highlight the potential for employing federated learning in the collaborative development and maintenance of AI-based software engineering models. We also discuss the key issues to be addressed in the co-construction process and future research directions.

Application of Parametric Modeling Techniques for Automated Detailing of Exterior Finishes in Architectural BIM Models: A South Korean Case Study

The South Korean government has mandated the use of Building Information Modeling (BIM) as the main medium for design deliverables in public projects. Such stipulations require detailed BIM models to be submitted in the detailed design phases, which places a burden especially on small- to medium-sized design firms. The requirement means that both the interior and exterior finishes of a building need to be explicitly modeled, which when performed manually is labor intensive and error prone. The goal of this study was to apply parametric modeling techniques to automatically model such details, focusing on the exterior finishes. Through interviews with design experts, four elements were selected: parapets, external wall finishes, downspouts, and inspection ladders. Parametric processes and rules for each finish were developed and subsequently programmed as add-ins in Autodesk Revit. Validation through case studies conducted using three different BIM models resulted in the average scores of 92.28% and 92.44% in terms of accuracy and efficiency, respectively. In particular, downspouts achieved a perfect accuracy score, while external wall finishes achieved a 94.42% reduction in modeling time. Modeling errors, which occurred due to inconsistencies in the test models, also demonstrate the need for specifying uniform modeling conventions of BIM model submissions in the detailed design phases.

Blockchain-Enabled Pension System Innovations: A Hungarian Case Study on Business Process Management Integration

This paper explores the integration of Business Process Management (BPM) with blockchain technology to enhance pension systems, using Hungary as a case study. Specifically, it addresses scientific challenges related to data access management, regulatory compliance, and system scalability within blockchain-based pension frameworks. This study investigates how BPM can improve the transparency, efficiency, and security of blockchain applications in pension administration by optimizing workflows and automating compliance with regulations such as GDPR. By analyzing operational flow diagrams and implementing architectural models, this paper presents an innovative approach to pension management, demonstrating significant improvements in service quality and operational efficiency. Findings from this research provide empirical evidence of the benefits of BPM-enhanced blockchain systems, offering insights applicable to pension systems beyond the Hungarian context, including examples from other countries.

Unveiling anomalies: transformative insights from transformer-based autoencoder models

Nowadays, Intrusion Detection Systems (IDS) play a critical role in safeguarding networks by identifying and mitigating unauthorized access and malicious activities, yet face challenges in accurately detecting sophisticated threats while minimizing false positives. In this paper, we present a comprehensive analysis of a Transformer-based Autoencoder model for network intrusion detection using the NSL-KDD dataset. We evaluate the model's anomaly detection performance based on key metrics such as Mean Squared Error (MSE), Precision-Recall Area Under Curve (AUC), and Root Mean Squared Error (RMSE) on the test set. Our findings reveal promising results, with the model achieving low MSE, high AUC, and relatively low RMSE values, indicating its effectiveness in detecting anomalies. Additionally, we provide an in-depth examination of the model architecture, highlighting the role of encoder and decoder layers, dropout regularization, and optimization techniques such as Adam optimizer. Our analysis sheds light on the efficacy of Transformer-based Autoencoder models for network intrusion detection tasks, offering insights into their architectural design and performance evaluation. The novelty of this study lies in the implementation of a Transformer-based Autoencoder architecture for network intrusion detection, showcasing its superior performance in anomaly detection compared to traditional methods.

The Development of the Two-Dimensional Model of Emotion Based on Both Architectural Emotion Words and Design Elements in China

The purpose of this paper is to construct and validate a model centered on architectural emotion, to explore the role of emotion in architectural design, and to provide theoretical support for emotion-oriented design. This study collected 614 terms related to architectural emotion, screened 30 core terms, constructed a two-dimensional architectural emotion model, and verified the scientific and practicality of the model through three measurement methods. First, the one-dimensional scale analysis identified two dimensions of pleasure and charm, which portrayed the range of word variation; second, the Principal Component Analysis confirmed the periodic ordering pattern of words, which revealed its systematic relationship; and, lastly, the Multidimensional Scaling Analysis demonstrated the distribution of emotion words based on cognitive similarity in the multidimensional space. Based on this model, this paper proposes a three-layer circular model of “architectural emotion-architectural cognition-architectural elements”, which constructs the correspondence between architectural emotion and design elements, as well as how architectural cognition and architectural elements can synergize to create a spatial experience that triggers specific emotions. The model provides theoretical support for emotion-oriented architectural design and evaluation, and helps designers to better understand the relationship between emotion and space so as to create more valuable architectural works.

Fast Design Space Exploration for Always-On Neural Networks

An analytical model can quickly predict performance and energy efficiency based on information about the neural network model and neural accelerator architecture, making it ideal for rapid pre-synthesis design space exploration. This paper proposes a new analytical model specifically targeted for convolutional neural networks used in always-on applications. To validate the proposed model, the performance and energy efficiency estimated by the model were compared with actual hardware and post-synthesis gate-level simulations of hardware synthesized with a state-of-the-art electronic design automation (EDA) synthesis tool. Comparisons with hardware created for the Eyeriss neural accelerator showed average execution time and energy consumption error rates of 3.33% and 13.54%, respectively. Comparisons with hardware synthesis results showed an error of 3.18% to 9.44% for two example neural accelerator configurations used to execute MobileNet, EfficientNet, and DarkNet neural network models. Finally, the utility of the proposed model was demonstrated by using it to evaluate the effects of different channel sizes, pruning rates, and batch sizes in several neural network designs for always-on vision, text, and audio processing.

Air quality prediction using stacked bi- long short-term memory and convolutional neural network in India

Air quality is a critical aspect of environmental health, and its assessment and prediction serve as pivotal components in mitigating the adverse effects of air pollution. This study focuses on advancing air quality prediction in India through the application of cutting-edge deep learning techniques, specifically the Stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN) architecture. Through meticulous preprocessing - encompassing missing value handling, normalization, and temporal sequencing - the dataset is prepared for the Stacked Bi-LSTM and CNN hybrid model. The model architecture leverages the temporal sequence-capturing capabilities of Stacked Bi-LSTM layers, enhancing it with the spatial feature extraction prowess of CNN layers. This integrated approach aims to address the intricate and nonlinear dependencies present in air quality time series data. During the training phase, the Adam optimizer is used to fine-tune the model’s hyperparameters, with Mean Squared Error (MSE) serving as the loss function. Important assessment metrics, including as Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and MSE, are used to evaluate the performance of the model. Furthermore, this study conducts a detailed temporal analysis, unraveling diurnal, seasonal, and long-term trends in air quality fluctuations. The study aims to offer valuable insights into the temporal and spatial patterns of air quality in India, thereby aiding environmental policymakers, urban planners, and researchers in formulating effective strategies for air quality management. The application of Stacked Bi-LSTM and CNN architectures in this research holds promise for enhancing real-time forecasting accuracy and facilitating informed decision-making towards sustainable environmental practices.

A federated anti-forgetting representation method based on hybrid model architecture and gradient truncation

A federated anti-forgetting representation method based on hybrid model architecture and gradient truncation

Automated segmentation of dental restorations using deep learning: exploring data augmentation techniques.

Deep learning has revolutionized image analysis for dentistry. Automated segmentation of dental radiographs is of great importance towards digital dentistry. The performance of deep learning models heavily relies on the quality and diversity of the training data. Data augmentation is a widely used technique implemented in machine learning and deep learning to artificially increase the size and diversity of a training dataset by applying various transformations to the original data. This work aims to automatically segment implants, prostheses, and fillings in panoramic images using 9 different deep learning segmentation models. Later, it explores the effect of data augmentation methods on segmentation performance of the models. Eight different data augmentation techniques are examined. Performance is evaluated by well-accepted metrics such as intersection over union (IoU) and Dice coefficient. While averaging the segmentation results for the three classes, IoU varies between 0.62 and 0.82 while Dice score is between 0.75 and 0.9 among deep learning models used. Augmentation techniques provided performance improvements of up to 3.37%, 5.75% and 8.75% for implant, prosthesis and filling classes, respectively. Findings reveal that choosing optimal augmentation strategies depends on both model architecture and dental structure type.

Spot the bot: the inverse problems of NLP

This article concerns the problem of distinguishing human-written and bot-generated texts. In contrast to the classical problem formulation, in which the focus falls on one type of bot only, we consider the problem of distinguishing texts written by any person from those generated by any bot; this involves analysing the large-scale, coarse-grained structure of the language semantic space. To construct the training and test datasets, we propose to separate not the texts of bots, but bots themselves, so the test sample contains the texts of those bots (and people) that were not in the training sample. We aim to find efficient and versatile features, rather than a complex classification model architecture that only deals with a particular type of bots. In the study we derive features for human-written and bot generated texts, using clustering (Wishart and K-Means, as well as fuzzy variations) and nonlinear dynamic techniques (entropy-complexity measures). We then deliberately use the simplest of classifiers (support vector machine, decision tree, random forest) and the derived characteristics to identify whether the text is human-written or not. The large-scale simulation shows good classification results (a classification quality of over 96%), although varying for languages of different language families.

Towards Automated Model Design on Recommender Systems

The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further optimization demands extensive co-design efforts on jointly optimizing model architecture and hardware. Design automation, such as Automated Machine Learning (AutoML), is necessary to fully exploit the potential of recommender model design, including model choices and model-hardware co-design strategies. We introduce a novel paradigm that utilizes weight sharing to explore abundant solution spaces. Our paradigm creates a large supernet to search for optimal architectures and co-design strategies to address the challenges of data multi-modality and heterogeneity in the recommendation domain. From a model perspective, the supernet includes a variety of operators, dense connectivity, and dimension search options. From a co-design perspective, it encompasses versatile Processing-In-Memory (PIM) configurations to produce hardware-efficient models. Our solution space’s scale, heterogeneity, and complexity pose several challenges, which we address by proposing various techniques for training and evaluating the supernet. Our crafted models show promising results on three Click-Through Rates (CTR) prediction benchmarks, outperforming both manually designed and AutoML-crafted models with state-of-the-art performance when focusing solely on architecture search. From a co-design perspective, we achieve 2 × FLOPs efficiency, 1.8 × energy efficiency, and 1.5 × performance improvements in recommender models.

Recognition of Conus species using a combined approach of supervised learning and deep learning-based feature extraction.

Cone snails are venomous marine gastropods comprising more than 950 species widely distributed across different habitats. Their conical shells are remarkably similar to those of other invertebrates in terms of color, pattern, and size. For these reasons, assigning taxonomic signatures to cone snail shells is a challenging task. In this report, we propose an ensemble learning strategy based on the combination of Random Forest (RF) and XGBoost (XGB) methods. We used 47,600 cone shell images of uniform size (224 x 224 pixels), which were split into an 80:20 train-test ratio. Prior to performing subsequent operations, these images were subjected to pre-processing and transformation. After applying a deep learning approach (Visual Geometry Group with a 16-layer deep model architecture) for feature extraction, model specificity was further assessed by including multiple related and unrelated seashell images. Both classifiers demonstrated comparable recognition ability on random test samples. The evaluation results suggested that RF outperformed XGB due to its high accuracy in recognizing Conus species, with an average precision of 95.78%. The area under the receiver operating characteristic curve was 0.99, indicating the model's optimal performance. The learning and validation curves also demonstrated a robust fit, with the training score reaching 1 and the validation score gradually increasing to 95 as more data was provided. These values indicate a well-trained model that generalizes effectively to validation data without significant overfitting. The gradual improvement in the validation score curve is crucial for ensuring model reliability and minimizing the risk of overfitting. Our findings revealed an interactive visualization. The performance of our proposed model suggests its potential for use with datasets of other mollusks, and optimal results may be achieved for their categorization and taxonomical characterization.

An explainable deep learning platform for molecular discovery.

Deep learning approaches have been increasingly applied to the discovery of novel chemical compounds. These predictive approaches can accurately model compounds and increase true discovery rates, but they are typically black box in nature and do not generate specific chemical insights. Explainable deep learning aims to 'open up' the black box by providing generalizable and human-understandable reasoning for model predictions. These explanations can augment molecular discovery by identifying structural classes of compounds with desired activity in lieu of lone compounds. Additionally, these explanations can guide hypothesis generation and make searching large chemical spaces more efficient. Here we present an explainable deep learning platform that enables vast chemical spaces to be mined and the chemical substructures underlying predicted activity to be identified. The platform relies on Chemprop, a software package implementing graph neural networks as a deep learning model architecture. In contrast to similar approaches, graph neural networks have been shown to be state of the art for molecular property prediction. Focusing on discovering structural classes of antibiotics, this protocol provides guidelines for experimental data generation, model implementation and model explainability and evaluation. This protocol does not require coding proficiency or specialized hardware, and it can be executed in as little as 1-2 weeks, starting from data generation and ending in the testing of model predictions. The platform can be broadly applied to discover structural classes of other small molecules, including anticancer, antiviral and senolytic drugs, as well as to discover structural classes of inorganic molecules with desired physical and chemical properties.

Improving Transferability of Physical Adversarial Attacks on Object Detectors Through Multi-Model Optimization

Physical adversarial attacks face significant challenges in achieving transferability across different object detection models, especially in real-world conditions. This is primarily due to variations in model architectures, training data, and detection strategies, which can make adversarial examples highly model-specific. This study introduces a multi-model adversarial training approach to improve the transferability of adversarial textures across diverse detection models, including one-stage, two-stage, and transformer-based architectures. Using the Truck Adversarial Camouflage Optimization (TACO) framework and a novel combination of YOLOv8n, YOLOv5m, and YOLOv3 models for optimization, our approach achieves an AP@0.5 detection score of 0.0972—over 50% lower than textures trained on single models alone. This result highlights the importance of multi-model training in enhancing attack effectiveness across object detectors, contributing to improved adversarial effectiveness.

Intelligent Identification of Cryptographic Ciphers using Machine Learning Techniques

This research work demonstrates cipher-type identification methods using machine learning algorithms. Cipher-type identification is a recent research interest to do better cryptanalysis of an encryption algorithm in a minimal time. Along with the increased security issues, obfuscation is being used with encryption algorithms to keep them hidden. This is when the ciphertext identification challenge came into play. The ciphertext classification challenge was performed using both image processing and natural language processing methods. For image processing purposes, CNN was utilized; whereas text-CNN, transformers and BERT models were used as natural language processing tools. In order to train the proposed machine learning based classification models, two types of datasets were generated: image data and text data. This study compares the experimental outcomes derived from various architectural CNN, Transformer, and BERT models. We also present a comparative study of our research work with another research works which are done in the recent past. The proposed BERT model is found to be the most efficient model for the correct classification of ciphertext over other transformer and CNN-based classification models. This work will surely help the cryptanalyst to perform cryptanalysis of an encryption algorithm in a minimal time.

ADDITIVE TECHNOLOGIES IN CONSTRUCTION: TECHNICAL, ECONOMIC AND MANAGEMENT ANALYSIS

The study is devoted to a comprehensive analysis of the introduction of additive technologies into modern construction production, revealing the technical, economic, and managerial aspects of concrete 3D-printing of architectural structures. The work systematically analyzes the evolution of additive manufacturing technologies and identifies the main structural types of 3D-printers (an additive machine for layer-by-layer construction of objects), including portal, robotic, mobile, and hybrid systems. A detailed study of the technological parameters of concrete 3D-printing with concrete mixtures is presented, in particular, optimal printing speed modes, layer parameters, criteria for shaping and quality of building structures. A comparative analysis of the technological capabilities of leading world equipment manufacturers, such as ICON, COBOD International, Apis Cor, and WinSun, is conducted. The economic analysis demonstrates significant advantages of additive technologies: reduction of construction time by 2-6 times, reduction of construction cost by 20-35%, and increase in the load-bearing capacity of structures. The study comprehensively explores the structure of capital and operational expenses associated with technology implementation. Special emphasis is placed on the management aspects of introducing additive technologies, highlighting the critical need for an interdisciplinary approach and knowledge integration across architecture, engineering, management, and computer modeling. The study determines the prospects for the development of concrete 3D-printing technology in the construction industry and outlines the main directions of further scientific research and practical implementation of innovative solutions. This study was developed between the Department of "Integrated Technologies of Mechanical Engineering" named after M. Semko of NTU "KhPI" and "Geopolimer" LTD to implement innovative technologies in the construction industry.

Intelligent Information System for Monitoring the Quality of Drinking Water

The article explores the global issue of water scarcity. Methods are being applied to eliminate water pollution, which can lead to water shortages. Azerbaijan is also one of the countries suffering from this problem. A global approach to the issue is required. Considering the complexity of the problem, a prototype is being developed, and potential solutions are demonstrated on it. The JWR is taken as the prototype object. The conceptual model, functional model, and system architecture have been presented.

ANALISIS EFEKTIFITAS VISUALISASI PERMODELAN DESAIN ARSITEKTUR BERBASIS KECERDASAN BUATAN (AI)

This research focuses on the iteration of architectural modeling using artificial intelligence (AI) as a solution to generate visualization concepts in the architectural iteration process. It examines the development of AI in architecture and highlights AI's position in current architectural practice. AI has revolutionized the way architectural designs are developed, presented, and interpreted. With its ability to process complex data, AI accelerates the design process, enables the exploration of innovative solutions, and enhances understanding of projects before construction begins. AI is used in various applications, from automating visualizations to generating floor plans, opening new potentials in designing and visualizing architectural projects. However, the use of AI in architecture is still in its early stages, and challenges remain in applying AI to conceptual design stages. This research will analyze the effectiveness of AI in architectural modeling and design visualization, evaluating its impact on efficiency, creativity, and design output quality, and exploring limitations and future recommendations for AI use in architectural practice. Based on platform evaluations, MidJourney and DALL·E show superiority in visual quality and design accuracy, each with the highest scores. MidJourney and DALL·E are the top choices for creative and technical architectural visualization, while Leonardo AI and Bing AI show limitations in creativity and flexibility.