Configurable Architecture Research Articles

Tomato Leaf Disease Detection using Flask Frame Work

In recent years, plant leaf diseases has become a widespread problem for which an accurate research and rapid application of deep learning in plant disease classification is required, tomato is also one of the most important plants and seeds which are used worldwide for cooking in either dried or fresh form, tomato are a great source of protein that offer many health benefits, but there are a lot of diseases associated with tomato leaf which hinder its production. Thus, an accurate classification of tomato leaf diseases is needed to solve the problem in the early stage. A deep learning approach is proposed to identify and classify leaf disease by using public dataset of leaf image and CNN model with the open source library TensorFlow. In this project, we proposed a method to classify tomato leaf disease and to find and describe the efficient network architecture (hyper parameters and optimization methods). Moreover, after applying each architecture separately, we compared their obtained results to find out the best architecture configuration for classifying tomato leaf diseases and their results. Furthermore, to satisfy the classification requirements, the model was trained using CNN architecture check if we could get faster training times, higher accuracy and easier retraining. Deep learning is a branch of artificial intelligence. In recent years, with the advantages of automatic learning and feature extraction, it has been widely concerned by academic and industrial circles. It has been widely used in image and video processing, voice processing, and natural language processing. At the same time, it has also become a research hotspot in the field of agricultural plant protection, such as plant disease recognition. The application of deep learning in plant disease recognition can avoid the disadvantages caused by artificial selection of disease spot features, make plant disease feature extraction more objective, and improve the research efficiency and technology transformation speed. This review provides the research progress of deep learning technology in the field of crop leaf disease identification in recent years. In this project, we present the current trends and challenges for the detection of plant leaf disease using deep learning and advanced imaging techniques. We hope that this project will be a valuable resource for researchers who study the detection of plant diseases. At the same time, we also discussed some of the current challenges and problems that need to be resolved.

Unveiling the genetic architecture and transmission dynamics of a novel multidrug-resistant plasmid harboring blaNDM-5 in E. Coli ST167: implications for antibiotic resistance management

BackgroundThe emergence of multidrug-resistant (MDR) Escherichia coli strains poses significant challenges in clinical settings, particularly when these strains harbor New Delhi metallo-ß-lactamase (NDM) gene, which confer resistance to carbapenems, a critical class of last-resort antibiotics. This study investigates the genetic characteristics and implications of a novel blaNDM-5-carrying plasmid pNDM-5-0083 isolated from an E. coli strain GZ04-0083 from clinical specimen in Zhongshan, China.ResultsPhenotypic and genotypic evaluations confirmed that the E. coli ST167 strain GZ04-0083 is a multidrug-resistant organism, showing resistance to diverse classes of antibiotics including ß-lactams, carbapenems, fluoroquinolones, aminoglycosides, and sulfonamides, while maintaining susceptibility to monobactams. Investigations involving S1 pulsed-field gel electrophoresis, Southern blot analysis, and conjugation experiments, alongside genomic sequencing, confirmed the presence of the blaNDM-5 gene within a 146-kb IncFIB plasmid pNDM-5-0083. This evidence underscores a significant risk for the horizontal transfer of resistance genes among bacterial populations. Detailed annotations of genetic elements—such as resistance genes, transposons, and insertion sequences—and comparative BLAST analyses with other blaNDM-5-carrying plasmids, revealed a unique architectural configuration in the pNDM-5-0083. The MDR region of this plasmid shares a conserved gene arrangement (repA-IS15DIV-blaNDM-5-bleMBL-IS91-suI2-aadA2-dfrA12) with three previously reported plasmids, indicating a potential for dynamic genetic recombination and evolution within the MDR region. Additionally, the integration of virulence factors, including the iro and sit gene clusters and enolase, into its genetic architecture poses further therapeutic challenges by enhancing the strain’s pathogenicity through improved host tissue colonization, immune evasion, and increased infection severity.ConclusionsThe detailed identification and characterization of pNDM-5-0083 enhance our understanding of the mechanisms facilitating the spread of carbapenem resistance. This study illuminates the intricate interplay among various genetic elements within the novel blaNDM-5-carrying plasmid, which are crucial for the stability and mobility of resistance genes across bacterial populations. These insights highlight the urgent need for ongoing surveillance and the development of effective strategies to curb the proliferation of antibiotic resistance.

Evolving filter criteria for randomly initialized network pruning in image classification

Network pruning aims to enhance the performance of deep neural networks by eliminating redundant components from the model. However, existing pruning methods typically require a well-trained model and employ fixed, single pruning criteria throughout the pruning cycles. To address these limitations, we propose a novel method called Evolutionary Filter Criteria (EvoFC). This method enables the automated search for the network pruning ratio and criterion during a population-based heuristic search process. We introduce a unique encoding space that represents the chosen pruning criterion and ratio for each layer, facilitating the acquisition of optimal architecture configurations for candidate networks during iterations. Additionally, we devise a novel weight inheritance mechanism to mitigate the computational burden associated with the population-based nature of the method, resulting in a significant reduction in overall training time. We validate our method by applying it to randomly initialized networks and conducting empirical experiments on CIFAR-10/100, ILSVRC-2012 and Places365 datasets. The results demonstrate that our method effectively reduces the number of FLOPs while striking a fine balance between accuracy and computational efficiency. This underscores the practical value of our method in optimizing performance while efficiently utilizing computational resources, particularly when pruning networks starting from random initialization.

EquiCity game: a mathematical serious game for participatory design of spatial configurations

We propose a mathematical framework for developing social-choice games that are designed to mediate decision-making processes for city planning, urban area redevelopment, and architectural configuration of urban housing complexes. The proposed framework features a digital serious gaming approach for participatory design to support transparency and inclusion in the process of decision-making and ensure an equitable balance of sustainable development goals in spatial design outcomes. The mathematical process consists of a Markovian design machine for balancing the design decisions of actors, a massing configurator equipped with fuzzy logic and multi-criteria decision analysis, algebraic graph-theoretical accessibility evaluators, and automated solar-climatic evaluators using geospatial computational geometry. We demonstrate the effectiveness of the framework by implementing a multi-player online game that facilitates a participatory decision-making workshop for forming multi-functional building complexes by providing a generative configurator equipped with automated appraisal/scoring mechanisms for revealing the aggregate impact of alternatives. The EquiCity game empowers a group of decision-makers to reach a fair consensual spatial design by mathematically simulating many rounds of reasonable trade-offs between their decisions, with different levels of interest or control over various types of investments. The novelty of the framework is in its capability to encompass decision-making about the most idiosyncratic aspects of a site related to its heritage status and cultural significance to the most generic aspects such as balancing access to sunlight for the site while respecting ‘the right to sunlight’ of the neighbours of the site, ensuring coherence of the entire configuration with regards to a network of desired closeness ratings, the satisfaction of a programme of requirements, and intricately balancing individual development goals in conjunction with communal goals and environmental design codes.

Prediction of Noise Level in Ota Metropolis Using Artificial Neural Network

Capturing noise data is laborious, time-consuming, expensive and dangerous due to the exposure of the investigator to the menace. Also, appropriate software, computational skill and computational time are also required before the captured data could be of any use. In this work, an artificial neural network (ANN) was deployed to learn and train noise data in Ota Metropolis. Data were captured from forty-one (41) locations for the morning, afternoon and evening in Ota Metropolis. ANN with Levenberg Marquardt algorithm and architectural configuration of 2-21-9 (input-hidden neuron-output) was used to predict noise descriptors for Ota Metropolis with 73% accuracy. The two input variables were the latitude and longitude of the location measured in degrees while the nine output variables are the noise descriptors such traffic noise index (TNI), noise pollution level (LNP), and average equivalent noise levels (LAeq) computed for each selected location for morning, afternoon and evening periods. The results could be used in mobile applications, Google Earth and other platforms to guide residence dwellers, travellers, industrialists and technocrats in selecting travelling routes, choice of apartment location and use of appropriate personal protective equipment (PPE) in unavoidable noisy locations.

Systematic application of traffic‐signal‐control system architecture design and selection using model‐based systems engineering and Pareto frontier analysis

AbstractThe global population rise has increased vehicles on roads, complicating traffic management. Inefficient traffic control systems cause significant economic losses owing to commuter time wastage, high energy consumption, and greenhouse gas emissions. Traffic signal control systems (TSCSs) are vital in traffic management, impacting traffic flow significantly; therefore, studies are exploring new optimization approaches that adapt to changing traffic conditions. However, they concentrate on either new technology infusion or on control algorithm optimization, and do not holistically address the architectural configuration of the system. In this study, we presented a unique case study by applying an existing systematic framework to the TSCS system architecture design and selection process. This application demonstrates that TSCS enhancement is a multifaceted process that requires a comprehensive assessment of not only technical aspects, such as the control algorithm, but also factors including system architecture, security, and data integrity. Because of the increasing reliance of TSCSs on data exchange between their various subsystems, this case study also adopted a cybersecurity perspective of the system and introduced cyber resiliency as a crucial metric for evaluating TSCS architecture performance. Furthermore, through the applied framework, an optimal TSCS architectural configuration with executable options was identified by generating multiple TSCS architectural configurations using decision option patterns and identifying those on the Pareto frontier to understand the architectural decision‐making process. Traffic engineers and transportation planners can use this case study application as a guide to optimize TSCSs employed in existing transportation networks and design more efficient transportation networks for future urban development.

Unraveling the influence of channel size and shape in 3D printed ceramic scaffolds on osteogenesis

Bone has the capacity to regenerate itself for relatively small defects; however, this regenerative capacity is diminished in critical-size bone defects. The development of synthetic materials has risen as a distinct strategy to address this challenge. Effective synthetic materials to have emerged in recent years are bioceramic implants, which are biocompatible and highly bioactive. Yet nothing suitable for the repair of large bone defects has made the transition from laboratory to clinic. The clinical success of bioceramics has been shown to depend not only on the scaffold's intrinsic material properties but also on its internal porous geometry. This study aimed to systematically explore the implications of varying channel size, shape, and curvature in tissue scaffolds on in vivo bone regeneration outcomes. 3D printed bioceramic scaffolds with varying channel sizes (0.3 mm to 1.5 mm), shapes (circular vs rectangular), and curvatures (concave vs convex) were implanted in rabbit femoral defects for 8 weeks, followed by histological evaluation. We demonstrated that circular channel sizes of around 0.9 mm diameter significantly enhanced bone formation, compared to channel with diameters of 0.3 mm and 1.5 mm. Interestingly, varying channel shapes (rectangular vs circular) had no significant effect on the volume of newly formed bone. Furthermore, the present study systematically demonstrated the beneficial effect of concave surfaces on bone tissue growth in vivo, reinforcing previous in silico and in vitro findings. This study demonstrates that optimizing architectural configurations within ceramic scaffolds is crucial in enhancing bone regeneration outcomes. Statement of significanceDespite the explosion of work on developing synthetic scaffolds to repair bone defects, the amount of new bone formed by scaffolds in vivo remains suboptimal. Recent studies have illuminated the pivotal role of scaffolds’ internal architecture in osteogenesis. However, these investigations have mostly remained confined to in silico and in vitro experiments. Among the in vivo studies conducted, there has been a lack of systematic analysis of individual architectural features. Herein, we utilized bioceramic 3D printing to conduct a systematic exploration of the effects of channel size, shape, and curvature on bone formation in vivo. Our results demonstrate the significant influence of channel size and curvature on in vivo outcomes. These findings provide invaluable insights into the design of more effective bone scaffolds.

Simplified Vulnerability Assessment of Historical Churches in Banat Seismic Region, Romania

ABSTRACT Romania, a mid-eastern European country, has a moderate seismicity and a large stock of historical buildings and churches. One of the most important seismic areas of the country is the Banat area, which ranks as the second most seismic area in Romania, with shallow earthquakes of crustal type. Many Orthodox and Catholic churches can be found in the area, the majority of them having a central nave. The churches are built in masonry, with vaults and wooden frameworks, and they present valuable architectural-artistic details, including paintings made by recognized painters. Various forms of structural damage appeared to the historical churches after past earthquakes, depending on the architectural configuration. This paper illustrates a study made on six historic churches in the Banat region, to investigate seismic vulnerability with simplified methods. The study highlights the most vulnerable points of the historic religious structures and the importance of investigating in a quick and simplified way the seismic behavior of such important buildings for the local community. Moreover, the main novelty of the paper is the highlighting of the importance of the sustainability aspect in the process of heritage preservation, as simplified assessment procedures are essential for more resilient risk reduction policies.

More-Than-Human Footprints

This issue of Footprint explores techn-natural spatialities and materialities found across operational landscapes of primary production. To the extent that these landscapes are increasingly automated and digitised, production and circulation practices are becoming more capital intensive and even less labour-intensive. While amplifying the precarity of human labour, this process relies on appropriating the work of more-than-human assemblages of machines, plants, animals and microorganisms. Central to the focus of this issue is understanding the way these processes are grounded in specific architectural and landscape configurations. In this way, we also aim to complement the debates on past issues of Footprint, offering an investigation of the impact of technological transformations beyond the concentrated landscapes of human inhabitation.

Influence of sedimentary architecture on static connectivity and geothermal doublet performance (Mezőberény, SE Hungary)

Although the Pannonian Basin in Hungary boasts significant geothermal potential, most geothermal wells in the region suffer from reinjection issues. The aim of this study is to examine the impact of the sedimentary architecture of a paralic lacustrine succession on the static connectivity of a geothermal aquifer. This problem was examined for a case-study geothermal doublet drilled in Mezőberény, southeast Hungary, which experienced injectivity problems shortly after commencing operations in 2012, ultimately leading to shut-in of the wells. A characterization of the architecture of the deltaic aquifer has been undertaken through a novel workflow that combines sedimentological and sequence stratigraphic analysis of the well-doublet and stochastic 3D modelling techniques to assess the likely static connectivity between the production and injection wells. Planform dimension of aquifer-forming mouth-bar elements and fluvial channel bodies were estimated from geological analogues, selected based on the thickness values of such sedimentary bodies interpreted on the gamma-ray logs of the well doublet and nearby hydrocarbon wells. In total five mouth-bar and two fluvial channel input geometry groups were selected, and fifty object-based realizations were constructed to analyse the static connectivity of different geological scenarios. The internal lithology of mouth-bar and fluvial-channel elements were modelled by sequential indicator simulations (ten realizations). Results of connected volume analysis indicate that the sandstone content of the aquifer is located within vertically segmented fluvial-channel and mouth-bar elements separated by mud-prone prodelta and lower delta-front deposits. This architectural configuration, in combination with low net-sandstone content suggests limited connectivity between the wells. Across the set of stochastic realizations, the volume of sandstone connecting the injection and production wells is ∼4% of the total aquifer volume, on average. Results of this study shows that simplified reservoir models can lead to over-estimation of connectivity of geothermal doublets. The proposed workflow combines sedimentological analysis and 3D modelling supported by geological analogues to predict sandstone reservoir connectivity of deltaic geothermal reservoirs. The described workflow can be carried out in target areas using existing boreholes to assist borehole planning.

TECHNOLOGICAL AND TACTICAL SUBSYSTEMS OF THE INTELLIGENT MANAGEMENT INFORMATION SYSTEM (ON THE EXAMPLE OF AN OIL AND GAS CORPORATION)

Providing Ukraine with its own oil and natural gas is one of the main tasks of the national economy. The possibility of development of the oil and gas industry is primarily determined by the volume of explored and mined resources. Since the existing explored reserves will not ensure the growth of oil and gas production, it is necessary to increase the amount of investments in the exploration and development of new deposits and hydrocarbon deposits with the aim of increasing their reserves and further growth of production, which requires the adoption of management decisions, which are characterized by increased technological and economic risk, uncertainty.
 Taking into account the main reasons for the decline in oil and gas production in Ukraine, the specifics of the industry and the requirements for information systems in the oil and gas industry, it can be argued that the use of intelligent technologies not only at the strategic, but also at the tactical and technological levels of management - is one of the keys to success in creating/reengineering, implementation and effective use of management decision support systems.
 The scientific and practical results presented in the article regarding the innovative configurations of architecture and design, proposed intellectual methodology for tactical and technological subsystems of the corporation management information systems. The above-proposed solutions - should be taken into account when reengineering corporate information systems not only in the oil and gas industry in Ukraine [1-3]. 
 Moreover, the obtained results are relevant and applicable not only for local companies, but also for international corporations on emerging markets in the context of global and regional macroeconomic and military crisis phenomena.

A Versatile Board for Event-Driven Data Acquisition.

Event-driven data acquisition is used to capture information from fast transient phenomena typically requiring a high sampling speed. This is an important requirement in the ITER Neutral Beam Test Facility for the development of one of the heating systems of the ITER nuclear fusion experiment. The Red Pitaya board has been chosen for this project because of its versatility and low cost. Versatility is provided by the hosted Zynq System on Chip (SoC), which allows full configuration of the module architecture and the OpenSource architecture of Red Pitaya. Price is an important factor, because the boards are installed in a hostile environment where devices can be damaged by EMI and radiation. A flexible solution for event-driven data acquisition has been developed in the Zynq SoC and interfaced to the Linux-based embedded ARM processor. It has been successfully adopted in a variety of data acquisition applications in the test facility.

Predicting Melting Temperatures of Freeze Valve in Molten Salt Reactors using LSTM-Based Deep Learning Models

The realm of molten salt reactors (MSR) presents unique challenges and opportunities in the pursuit of advancing nuclear energy technology. One pivotal aspect is the development of safety mechanisms, including freeze valves, aimed at enhancing the security and operational integrity of these reactors. Freeze valves, designed to halt the flow of molten salt in emergency scenarios, play a critical role in averting potential hazardous situations. This research paper investigates the application of deep learning models for predicting melting temperatures, leveraging time-series temperature data, specifically targeting the freeze valve technology within the context of molten salt reactors. The research methodology encompasses the creation of a synthetic dataset representative of freeze valve conditions in MSR. Each dataset entry comprises a time-series temperature profile associated with the freeze valve and its corresponding melting temperature. To capture the intricate temporal relationships inherent in these profiles, a specialized Recurrent Neural Network (RNN) architecture, incorporating Long Short-Term Memory (LSTM) cells, is developed and trained. The model’s training is augmented by preprocessing techniques, including the normalization of time-series temperature data. Evaluation of the model’s predictive capabilities focuses on its performance in forecasting the melting temperatures of the freeze valve. Metrics such as mean squared error (MSE) and mean absolute error (MAE) are utilized to quantify the model’s accuracy and robustness. The study delves into the influence of architectural configurations, hyperparameter tuning, and dataset characteristics on the model’s predictions, shedding light on the factors that contribute to optimal predictive performance. The outcomes of this research highlight the potential of deep learning models in predicting the melting temperatures of freeze valves in the context of MSR. The developed model not only showcases an ability to anticipate impending safety-critical events but also underscores the significance of leveraging time-series temperature data to enhance the integrity of safety mechanisms in nuclear reactor systems. Ultimately, this research contributes to the pursuit of safer and more efficient nuclear energy solutions, offering valuable insights into predictive modeling techniques within the complex landscape of molten salt reactor technologies.

FACULTY OF PSYCOLOGY OF MÁLAGA, SPAIN. COMPOSITE STEEL‐CONCRETE STRUCTURE IN A SINGULAR BUILDING

AbstractThe paper presents the design and construction of the new Faculty of Psychology in Málaga, Spain, by LLPS Architects. The project offers an interesting example of the relation between structure and architecture, based on a singular configuration of a composite steel‐concrete structure, which responds in a coherent and attractive way to the architectural configuration. The building is formed by a massive and compact three‐heights volume of 90x100 m. Two main architectural features determine the structural configuration: the interior courtyards, that measure 18x3 m., and are disposed in staggered arrangement to allow the entrance of natural light; and the cantilever of the above‐ground volume, that creates a large column‐free covered space.

Biological parameters for quality evaluation of allografts from the Brazilian National Institute of Traumatology and Orthopedics tissue bank.

Bone allografts are clinically used in a variety of surgical procedures, and tissue banks are responsible for harvesting, processing, quality testing, storing, and delivering these materials for transplantation. In tissue banks, the bone is processed for the removal of all organic content, remaining only the tissue structure (scaffold). However, several studies have shown that even after using different processing methods, viable cells, functional proteins, and DNA may still persist in the tissue, which constitute the main causes of graft rejection. Therefore, the objective of this study was to establish techniques and biological parameters for quality validation of allografts. To this end, we propose the use of 3 combined methods such as microscopy, histology, and molecular biology techniques to evaluate the quality of allografts harvested and processed by the Brazilian National Institute of Traumatology and Orthopedics (INTO) tissue bank according to the donation criteria of the Brazilian National Health Surveillance Agency and the Brazilian National Transplant System. Bone fragments from different processing stages showed no viable cells on histology, an intact extracellular matrix on scanning electron microscopy, and gradual reduction in DNA amount. Different techniques were used to demonstrate the quality of allografts produced by the INTO tissue bank and to establish biological parameters for ensuring the safety and quality of these products. Future studies need to be undertaken to assess and validate the efficacy of the decellularization process in larger bone grafts with diverse architectural configurations.

Aerodynamic analysis of building with zigzag-patterned façade: Insights from large eddy simulation

High-rise buildings have diverse shapes and configurations to harmonize with the architectural, engineering, environmental, economic, and functional considerations, and aspirations. However, the architectural shape and configuration plays a vital role in determining the aerodynamic characteristics of the surrounding flow field and wind forces acting on the building. This paper numerically investigates the aerodynamic characteristics of the zigzag-patterned building by adopting the three-dimensional large eddy simulation (LES). The flow around a square cylinder in high Reynolds number is used to valid the numerical method. The results show that the zigzag pattern has a little effect on the mean streamwise velocity but significantly influences the fluctuation of streamwise and vertical velocities in the wake region. It is observed that the zigzag pattern on the leeward wall results in a narrower wake region, while on the windward wall, leads to a thinner and longer shear layers and shorter recirculation region. As for the pedestrian level wind, the flow velocity within the separation area is noticeably reduced when incorporating a zigzag pattern on the windward wall. Moreover, the fluctuating pressure coefficient values at the sidewalls of a building with a zigzag windward wall is significantly smaller than that of a smooth configuration building due to the façade pattern's impact in diminishing the curvature of the nearby separation at the leading edge.

Landscape and Architecture: Yawanawá Design Lessons from the Brazilian Amazon Forest

The purpose of this article is to observe the spatial design practices of the Yawanawá indigenous population that inhabits the Rio Gregorio Indigenous Land, located in the Brazilian Amazon Forest. In collaboration with this community, the intention is to reflect on approaches that can enrich the research of their spatial knowledge, thereby contributing to the consolidation of Amerindian knowledge in the academic field of architecture and design. The participant observation methodology allowed an immersion into Yawanawá narratives that rescue their ancestral role in the architectural and landscape configuration of the territory. Through elaborating a photographic visual investigation, it is sought to expand voices and meanings in strata of coexisting times, articulating the images to the Amerindian architectural conceptions that survived colonial abuse. In the conclusions, the lessons that the Yawanawá express and manifest are highlighted when building spaces of resistance in a poetic, symbolic, and daily way where the urban power structures constructed and/or that cross their territory were and are re-signified to test other ways of living in the forest.

ANALYSIS OF ENVIRONMENTALLY SUSTAINABLE PROJECTS IN THE FIELD OF GREEN ARCHITECTURE: USE OF NATURAL MATERIALS AND RENEWABLE ENERGY SOURCES

The article explores contemporary architectural trends focused on the establishment of sustainable and ecologically responsible environments. It scrutinizes projects incorporating natural building materials and renewable energy sources, evaluating their environmental impact and discerning their role in fostering sustainable development. Additionally, the article delves into alternative approaches for the utilization of materials during both the construction and operational phases of green buildings. A comprehensive analysis is presented, elucidating the intricacies of the "green building" concept, notable for its pronounced benefits in curtailing energy consumption for heating purposes. The salient characteristic of such structures lies in the integration of green design strategies and cutting-edge building materials. The article meticulously examines the efficacy of energy utilization within the context of a "green" architectural paradigm. Emphasis is placed on technologies and solutions conducive to diminishing energy expenditure, particularly in the domain of heating. This encompasses the deployment of renewable energy sources, optimal architectural configurations, and innovative engineering systems. The investigation reveals that the integration of green methodologies in construction is contingent not solely upon the reduction of energy consumption but also on the adoption of environmentally friendly and sustainable materials. Such materials not only serve to ameliorate the structural quality but also enhance the comfort of indoor spaces. The findings proffered by the analysis hold the potential to unveil novel avenues for the progressive refinement of green architecture and its application in construction.

Programmable Analog System Benchmarks Leading to Efficient Analog Computation Synthesis

This effort develops the first rich suite of analog and mixed-signal benchmark of various sizes and domains, intended for use with contemporary analog and mixed-signal designs and synthesis tools. Benchmarking enables analog-digital co-design exploration as well as extensive evaluation of analog synthesis tools and the generated analog/mixed-signal circuit or device. The goals of this effort are defining analog computation system benchmarks, developing the required concepts for higher-level analog and mixed-signal tools to utilize these benchmarks, and enabling future automated architectural design space exploration (DSE) to determine the best configurable architecture (e.g., a new FPAA) for a certain family of applications. The benchmarks comprise multiple levels of an acoustic , a vision , a communications , and an analog filter system that must be simultaneously satisfied for a complete system.

Intra- and Inter-expert Validation of an Automatic Segmentation Method for Fluid Regions Associated with Central Serous Chorioretinopathy in OCT Images

Central Serous Chorioretinopathy (CSC) is a retinal disorder caused by the accumulation of fluid, resulting in vision distortion. The diagnosis of this disease is typically performed through Optical Coherence Tomography (OCT) imaging, which displays any fluid buildup between the retinal layers. Currently, these fluid regions are manually detected by visual inspection a time-consuming and subjective process that can be prone to errors. A series of six deep learning-based automatic segmentation architectural configurations of different levels of complexity were trained and compared in order to determine the best model intended for the automatic segmentation of CSC-related lesions in OCT images. The best performing models were then evaluated in an external validation study. Furthermore, an intra- and inter-expert analysis was conducted in order to compare the manual segmentation performed by expert ophthalmologists with the automatic segmentation provided by the models. Test results of the best performing configuration achieved a mean Dice of 0.868±0.056\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.868 \\mathop {\\pm } 0.056$$\\end{document} in the internal dataset. In the external validation set, these models achieved a level of agreement with human experts of up to 0.960 in terms of Kappa coefficient, contrasting with a value of 0.951 for agreement between human experts. Overall, the models reached a better agreement with either of the human experts than these experts with each other, suggesting that automatic segmentation models for the detection of CSC-related lesions in OCT imaging can be useful tools for assessing this disease, reducing the workload of manual inspection and leading to a more robust and objective diagnosis method.