Hasil untuk "Architecture"

Chin-Tong Ong, V. Corces

Y. Sun, Bing Xue, Mengjie Zhang et al.

Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.

J. Bosch

M. Coltheart, B. Curtis, Paul W. B. Atkins et al.

S. Kent

D. Tullsen, S. Eggers, H. Levy

J. Kleer

F. Iandola, Song Han, Matthew W. Moskewicz et al.

B. Givoni

C. Jencks

Agnieszka Gębczyńska-Janowicz, Elżbieta Marczak, Anna Zapiec et al.

The global phenomenon of an aging population calls for the modernization of public spaces to better accommodate the needs of older individuals. Beaches in coastal cities are popular destinations for seniors; therefore, this article will examine effective design practices for public spaces in coastal areas. The study focused on eleven pedestrian routes that connect public transport stops to the main beach entrances in the coastal zone of Gdańsk, Poland. Field observations assessed the pedestrian and cycling infrastructure, route lengths, surface quality, availability of small urban elements (such as benches, restrooms, and water fountains), and safety conditions (including lighting, signage, barriers, and general cleanliness). The analysis of these spaces led to the development of guidelines for the architectural and urban design of senior-friendly coastal urban zones.

Zhejian Zhang, Nan Li, Shude Mao et al.

IntroductionGalaxy cluster-scale strong gravitational lensing systems are rare yet valuable tools for investigating dark matter and dark energy, as well as providing the opportunity to study the distant universe at flux levels and spatial resolutions that would otherwise be unavailable. Large-scale imaging surveys present unprecedented opportunities to expand the sample of cluster lenses.MethodsIn this study, we adopt a deep learning-based approach to identify cluster lenses from the DESI Legacy Imaging Surveys, utilizing the catalog of galaxy cluster candidates identified by Zou et al. (2021). Our lens-finder employs a ResNet-18 architecture, trained with mock images of cluster lenses as positives and observational images of cluster scale non-lenses as negatives. We do an iterative operation to increase the completeness of our work, namely adding the found true positive samples back to the training set and training again for several times. Human inspection is conducted to further refine the candidates, categorizing them into grades (A, B, C) according to the significance of the strongly lensed arcs.ResultsReviewing all 540,432 objects in Zou’s catalog, we discover 485 high-confidence cluster lens candidates with a cluster M500 range of 1013.67∼14.97M⊙ and a Brightest Central Galaxy (BCG) redshift range of 0.04∼0.89. After excluding the lens candidates listed in previous studies, we identify 247 newly discovered cluster lens candidates, including 16 grade A, 90 grade B, and 141 grade C.DiscussionThis catalog of cluster lens candidates is publicly available online, and follow-up observations are encouraged to confirm and conduct thorough investigations of these systems.

Weixiong Lin, Nini Wang, Jianchuan Yin

Shipping is a major source of carbon emissions and faces an urgent need for decarbonization. Research on vessel carbon emissions not only characterizes regional emission patterns but also provides critical evidence for targeted mitigation policies and optimized maritime management. This study quantifies vessel carbon emissions in the Port of New York and New Jersey from February to November 2023 using Automatic Identification System (AIS) data combined with the STEAM model. An activity-weighted spatial allocation method was applied to distribute emissions across 100 m × 100 m grids. Emission characteristics were analyzed across four dimensions: vessel type, operational state, temporal variation, and spatial distribution. Results show that total emissions during the study period reached approximately 136,701.8 t, with container ships contributing 62.3% of the total. Berthing operations were identified as the dominant emission source, accounting for 73.4% of total emissions, followed by tugboats and cargo vessels. Temporally, emissions peaked in October (10.8%) and were lowest in February (8.8%), reflecting variations in trade intensity and seasonal weather conditions. Spatially, emissions exhibited strong clustering around terminal berths. A sensitivity analysis was performed to assess the robustness of the emission estimates. When the load factor (LF) varied by ±10%, total emissions changed by only ±1.85%, indicating that the results are highly stable and robust. This limited variation arises from the dominance of berthing operations with relatively steady auxiliary loads and the application of the constraint LF ≤ 1, which prevents unrealistic overloading. These findings offer indicative insights that can inform port-level emission management and serve as a reference for future low-carbon policy development.

Yunfei Li, Jun Wei, Shaohua Cheng et al.

Spectral detection technology offers non-destructive, in situ, and high-speed capabilities, making it widely applicable for detecting biological and chemical samples and quantifying their concentrations. Water resources, essential to life on Earth, are widely distributed across the planet. The application of spectral technology to underwater environments is useful for wide-area water resource monitoring. Although spectral detection technology is well-established, its underwater application presents challenges, including waterproof housing design, power supply, and data transmission, which limit widespread application of underwater spectral detection. Furthermore, underwater spectral detection necessitates the development of compatible computational methods for sample classification or regression analysis. Focusing on underwater spectral detection, this work involved the construction of a suitable hardware system. A compact spectrometer and LEDs (400 nm–800 nm) were employed as the detection and light source modules, respectively, resulting in a compact system architecture. Extensive tests confirmed that the miniaturized design-maintained system performance. Further, this study addressed the estimation of total phosphorus (TP) concentration in water using spectral data. Samples with varying TP concentrations were prepared and calibrated against standard detection instruments. Subsequently, classification algorithms applied to the acquired spectral data enabled the in situ underwater determination of TP concentration in these samples. This work demonstrates the feasibility of underwater spectral detection for future in situ, high-speed monitoring of aquatic biochemical indicators. In the future, after adding UV LED light source, more water quality parameter information can be obtained.

Archana Thiruppathi, Shubham Rajaram Salunkhe, Shobica Priya Ramasamy et al.

Strategies to enhance rice productivity in response to global demand have been the paramount focus of breeders worldwide. Multiple factors, including agronomical traits such as plant architecture and grain formation and physiological traits such as photosynthetic efficiency and NUE (nitrogen use efficiency), as well as factors such as phytohormone perception and homeostasis and transcriptional regulation, indirectly influence rice grain yield. Advances in genetic analysis methodologies and functional genomics, numerous genes, QTLs (Quantitative Trait Loci), and SNPs (Single-Nucleotide Polymorphisms), linked to yield traits, have been identified and analyzed in rice. Genome editing allows for the targeted modification of identified genes to create novel mutations in rice, avoiding the unintended mutations often caused by random mutagenesis. Genome editing technologies, notably the CRISPR/Cas9 system, present a promising tool to generate precise and rapid modifications in the plant genome. Advancements in CRISPR have further enabled researchers to modify a larger number of genes with higher efficiency. This paper reviews recent research on genome editing of yield-related genes in rice, discusses available gene editing tools, and highlights their potential to expedite rice breeding programs.

Haijun Wang, Yuhang Yang, Yaohua Guo et al.

Based on the 10 MW OO-Star semi-submersible floating platform, this study proposes internal and external heave plates to enhance its stability and explores their influence on the platform’s hydrodynamic characteristics. The platform’s structural behavior is analyzed in both frequency and time domains using numerical simulation methods. The study investigates the effects of the porosity and number of holes (with an equal porosity) of the inner heave plate and the opening angle (with the equal area) of the external heave plate on the platform’s hydrodynamic characteristics, ultimately obtaining the optimal arrangement for the inner and external heave plates. Results indicate that the best scheme involves a 10% porosity with 16 holes, which reduces the heave amplitude by 5.7% compared to the original structure. Additionally, reducing the opening angle of the external heave plate increases the added mass and natural period in the heave and pitch directions of the platform. At an opening angle of 140°, the added mass in the heave direction can increase by 25.2% compared to the original structure. Overall, the internal and external heave plates effectively reduce the heave and pitch amplitude of the platform under severe sea conditions.

Krupa Michał, Ivashko Yulia

This paper discusses landscape design inspired by Chinese tradition and symbolism. The authors briefly presented the basics of Chinese tradition in the establishment of gardens and parks, their elements, symbolism and the messages they convey, in the context of the interpretation of these traditions in the design of parks established in the Chinoiserie style outside China, mainly in Europe, both in the past and at present. This study also explores the problem of the poor state of the environment, especially in urban areas, which is largely related to the shortage of green space, including parks and gardens. The lack of these spaces and, at the same time, the need to create recreational yet visually appealing spaces for the urban bourgeoisie has led to a re-emergence of Chinese landscape design traditions. One example of a contemporary implementation of a Chinoiserie-style garden is the Monte Palace Tropical Garden in Funchal, the capital of Madeira.

Elanna Beatriz Americo Ferreira, Sandra De Albuquerque Siebra

Objective. Provide an overview of the scientific production on Information Architecture in the context of Information Science. Method. It is characterized as an exploratory and qualitative-quantitative study which used bibliometric techniques and content analysis. The scientific productions were retrieved from the Information Science Database (BRAPCI) and SCOPUS, as they bring together a significant quantity of productions on IA in the Brazilian and international contexts, respectively. Results. As a result, bibliometric indicators are presented (main authors and means publications, authors' countries of origin, recurring keywords and number of publications per year), and the thematic categories of the productions analysed are highlighted. We highlight the productions that mention IA, but focus on other discussions such as Usability, Accessibility and Findability, pointing out the relevance of IA as complementary to these other studies. Besides the productions with proposal, analysis, or evaluation of digital environments, where it is employed the systemic approach of IA and it was possible to observe that, in the Brazilian context, the applications focus on academic environments and, in the international context, on corporate environments. Conclusions. We conclude that the analysed productions collaborate with the social function of IC, demonstrating concern with the users of information, besides being relevant in the context of the post-custodial paradigm of Information Science, where the dissemination, access and use of information are valued, and, consequently, it is necessary that such information be organized and presented in a suitable way for its target audience.

Federica Bianchi, Rossella Moscarelli

The conquest of new public spaces is one of the main options in processes of urban regeneration. It seems essential in contemporary cities, since our life occurs more and more indoors and in private contexts, reducing the role of public and outdoor activities. Among cultural-based urban regeneration projects that operate within those spaces waiting for an improvement of the existing public functions, schools can play a particularly prominent role, as well spread and symbolic institutions with an educational mission for young people. From this perspective, the paper discusses how school squares, namely the urban areas close to the entrance of schools, can be designed and regenerated to produce a real public space where the city meets the school and vice versa. The paper presents a methodology to classify different typologies of school squares, based on an extensive analysis on over 600 school squares, located in the provinces of Milan, Turin and Varese. On the basis of such classification, some guidelines are discussed in order to propose a strategy to redesign these symbolic spaces and to conquer them as public areas.

Syed Rizvi, Akash Awasthi, Maria J. Peláez et al.

Abstract The COVID-19 pandemic affected countries across the globe, demanding drastic public health policies to mitigate the spread of infection, which led to economic crises as a collateral damage. In this work, we investigate the impact of human mobility, described via international commercial flights, on COVID-19 infection dynamics on a global scale. We developed a graph neural network (GNN)-based framework called Dynamic Weighted GraphSAGE (DWSAGE), which operates over spatiotemporal graphs and is well-suited for dynamically changing flight information updated daily. This architecture is designed to be structurally sensitive, capable of learning the relationships between edge features and node features. To gain insights into the influence of air traffic on infection spread, we conducted local sensitivity analysis on our model through perturbation experiments. Our analyses identified Western Europe, the Middle East, and North America as leading regions in fueling the pandemic due to the high volume of air traffic originating or transiting through these areas. We used these observations to propose air traffic reduction strategies that can significantly impact controlling the pandemic with minimal disruption to human mobility. Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policymakers for making informed decisions regarding air traffic restrictions during future outbreaks.