检索结果-内蒙古大学图书馆

Plant Phenome Journal 2024年第1期7卷

作者： Ostermann, Ian Benes, Bedrich Gaillard, Mathieu Li, Bosheng Davis, Jensina Grove, Ryleigh Shrestha, Nikee Tross, Michael C. Schnable, James C. Department of Computer Science Purdue University West Lafayette IN United States Center for Plant Science Innovation and Department of Agronomy and Horticulture University of Nebraska–Lincoln Lincoln NE United States Complex Biosystems Graduate Program University of Nebraska–Lincoln Lincoln NE United States

This paper introduces a novel deep neural model for segmenting and tracking the number of leaves in sorghum plants in phenotyping facilities. Our algorithm inputs a sequence of images of a sorghum plant and outputs the segmented images and the number of leaves. The key novelty of our approach is in training the deep neural model. Manual annotations are tedious, and we have developed a procedural three-dimensional (3D) sorghum model that provides detailed geometry and texture to generate photorealistic 3D models. The overall shape of the sorghum leaf geometry is determined by its skeleton, and it is detailed by a procedural model that varies its curvature, width, length, and overall shape. The color is determined by using a Monte Carlo path tracer. We mimic the illumination of the phenotyping facility and use reflectance and transmittance on sorghum surfaces to determine the color of the leaves. The 3D procedural model allows us to generate photorealistic and segmented images that we use to train a deep neural model. Our segmentation provides a mean intersection over union score of 0.51, resulting in leaf counting accuracy within the 90% confidence interval for the human counts. © 2024 The Author(s). The Plant Phenome Journal published by Wiley Periodicals LLC on behalf of American Society of Agronomy and Crop science Society of America.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-driven multi-omics integration for multi-scale predictive modeling of causal genotype-environment-phenotype relationships

arXiv

引用

arXiv 2024年

作者： Wu, You Xie, Lei Ph.D. Program in Computer Science The Graduate Center The City University of New York New YorkNY United States Ph.D. Program in Biology and Biochemistry The Graduate Center The City University of New York New YorkNY United States Department of Computer Science Hunter College The City University of New York New YorkNY United States Helen & Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New YorkNY United States

Despite the wealth of single-cell multi-omics data, it remains challenging to predict the consequences of novel genetic and chemical perturbations in the human body. It requires knowledge of molecular interactions at all biological levels, encompassing disease models and humans. Current machine learning methods primarily establish statistical correlations between genotypes and phenotypes but struggle to identify physiologically significant causal factors, limiting their predictive power. Key challenges in predictive modeling include scarcity of labeled data, generalization across different domains, and disentangling causation from correlation. In light of recent advances in multi-omics data integration, we propose a new artificial intelligence (AI)-powered biology-inspired multiscale modeling framework to tackle these issues. This framework will integrate multi-omics data across biological levels, organism hierarchies, and species to predict causal genotype-environment-phenotype relationships under various conditions. AI models inspired by biology may identify novel molecular targets, biomarkers, pharmaceutical agents, and personalized medicines for presently unmet medical needs. © 2024, CC BY.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

DRYING OF REFRACTORY CASTABLES - HOW COMPLEX THE MODELLING NEEDS TO BE? A NUMERICAL AND EXPERIMENTAL STUDY 17

DRYING OF REFRACTORY CASTABLES - HOW COMPLEX THE MODELLING N...

引用

17th Unified International Technical Conference on Refractories, UNITECR 2022

作者： Moreira, M.H. Pont, S. Dal Ausas, R.F. Cunha, T.M. Luz, A.P. Pandolfelli, V.C. Federal University of Sao Carlos Graduate Program in Materials Science and Engineering SP Sao Carlos Brazil CNRS Grenoble INP 3SR Université Grenoble Alpes Grenoble38000 France Institute of Mathematical and Computer Sciences University of São Paulo SP São Carlos13566-590 Brazil

Calcium aluminate cement (CAC)bonded castables have numerous benefits when compared to monolithic refractories. Their main drawback is their long initial heating, when the physical and chemically-bonded water are released. If the mass flux of water to the ambient is lower than the vapor generation, the gas pressure can increase well above the material's strength resulting in cracks and spalling of the ceramic lining. In order to avoid this, optimized heat up curves are needed, and one promising methodology by using numerical models. Most of these calculations are based on tools used for simulating Portland cement concrete structures on fire and they vary both in complexity and their basic assumptions. Thus, the main question that remains is how complex such models need to be in order to capture the fundamental aspects of this phenomenon. The present work aimed to solve this issue by implementing multiple numerical tools reported in the literature with distinct complexity levels and fundamental assumptions and by also conducting neutron tomography tests on a CAC-bonded castable. It was possible to see that the pressure values predicted by such methodologies are equivalent and the water content predicted is qualitatively similar within the models and with the experimental values, indicating that the simplest approach might be used for predicting the castables' drying. © 2022 Unified International Technical Conference on Refractories, UNITECR 2022 - Proceedings. All rights reserved.

关键词： Portland cement

来源：评论

学校读者我要写书评

暂无评论

New connections between brand and environmentally sustainable businesses in the Amazon forest and local business owner’s perception

引用

Sustainable Earth Reviews 2023年第1期6卷 1-17页

作者： Luiz Diego Vidal Santos Francisco Sandro Rodrigues Holanda Pedro Vinícius Bertulino de Menezes Ana Paula Schervinski Villwock Alceu Pedrotti Catuxe Varjão de Santana Oliveira Graduate Program in Intellectual Property Science Universidade Federal de Sergipe-UFS São Cristóvão Sergipe Brasil Agronomy Engineering Department Universidade Federal de Sergipe-UFS São Cristóvão Sergipe Brasil Computer Science Department Instituto Federal de Sergipe-UFS Lagarto Sergipe Brasil

The debate surrounding entrepreneurship in the Amazon rainforest region highlights the importance of sustainable actions developed by local brands. However, limited attention has been given to entrepreneur's perspectives regarding the outcome of their applied practices. The objective of this study was to understand the entrepreneurs’ perception based on their business models concerning the connection to the Amazon brand and the aspects of sustainable use of its natural resources. The study was performed through semi-structured interviews with seven Amazonian product brands entrepreneurs utilizing Grounded Theory. The results demonstrate that entrepreneurs understand that reaching the social dimension relies on the articulation of three main factors: entrepreneurs, the native people, and the shared traditional knowledge and culture. It is observed that the political dimension is still underdeveloped in the region with limited application of its effects on products. Additionally, the economic dimension is not significantly favored by the utilization of environmentally sustainable brands. Lastly, the territorial dimension depends on the establishment of permanent protection areas, as well as agroforestry systems.

关键词： Brand Environmental sustainability Marketing Entrepreneur behavior Traditional communities

来源：评论

学校读者我要写书评

暂无评论

DIRECT OBSERVATION OF DRYING BY NEUTRON AND X-RAY TOMOGRAPHY ANALYSIS 17

DIRECT OBSERVATION OF DRYING BY NEUTRON AND X-RAY TOMOGRAPHY...

引用

17th Unified International Technical Conference on Refractories, UNITECR 2022

作者： Moreira, M.H. Dal Pont, S. Tengattini, A. Luz, A.P. Cunha, T.M. Ausas, R.F. Pandolfelli, V.C. Federal University of Sao Carlos Graduate Program in Materials Science and Engineering SP Sao Carlos Brazil 3SR Université Grenoble Alpes Grenoble France Large Scale Structures Institut Laue-Langevin Grenoble France Institute of Mathematical and Computer Sciences University of São Paulo São Carlos Brazil

The drying of refractory monolithics is one of the main drawbacks of this class of materials due to its implication on the production halt of many industrial equipment. This is especially true for calcium aluminate cement (CAC)-bonded castables, where the vapor derived from the unreacted water and dehydration reactions can pressurize yielding cracks and explosions of the ceramic lining. Numerous advances on additives have been made to increase these materials' resistance to explosive spalling, however, the fundamentals of the physical phenomena that yields such a problem remain an open issue. For years, the techniques used to study this process were limited to indirect tests, such as the thermogravimetric analysis or the pressure and temperature measurements of samples being unidirectionally heated. Recently, direct techniques such as nuclear magnetic resonance and X-ray tomography were applied in the context of regular concrete on fire scenarios. The current work presents preliminary results of neutron tomography applied to monitoring the drying of refractory castables. The overall behavior of the castable was qualitatively similar to those observed for regular concrete, and the results provide information that can be successfully applied on numerical simulations of larger pieces with dimensions closer to the industrial ones, overcoming the main drawback of such techniques, their small sample dimensions. © 2022 Unified International Technical Conference on Refractories, UNITECR 2022 - Proceedings. All rights reserved.

关键词： Drying

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Identification of Suitable Congregations for Preachers Using a GMM-PCA-BIC Hybrid Clustering Approach

Optimizing the Identification of Suitable Congregations for ...

引用

International Conference of computer and Informatics Engineering (IC2IE)

作者： Rahmad Kurniawan Ibnu Daqiqil I D Fatayat Sukamto Aidil Fitriansyah Fitra Lestari Ilyas Husti Department of Computer Science Faculty of Mathematics and Natural Sciences Universitas Riau Pekanbaru Indonesia Department of Industrial Engineering Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia Graduate Program Universitas Islam Negeri Sultan Syarif Kasim Riau Pekanbaru Indonesia

ISBN: (数字)9798331505530

ISBN: (纸本)9798331505547

The assignment of preachers to mosques in Riau Province faces significant challenges due to the geographic dispersion of mosques and inconsistent scheduling practices. Preachers often travel long distances, and mismatched assignments lead to inefficiencies and reduced effectiveness in delivering sermons. This study addresses these issues by leveraging advanced clustering techniques to optimize preacher assignments. Specifically, we applied Gaussian Mixture Models (GMM) to cluster mosque and preacher data based on geolocation, activity, and profiles. We integrated Principal Component Analysis (PCA) for dimensionality reduction to enhance the clustering performance, forming a GMM-PCA hybrid approach. Data was obtained from the Indonesian Ulema Council Riau Province Chapter, which consists of 185 mosques and 250 preachers, totaling 435 data points. The results indicate that using GMM alone, the optimal clustering was achieved with 10 clusters, yielding a Silhouette Score of 0.31. The GMM-PCABIC hybrid approach improved clustering quality. It achieved optimal results with 9 clusters, a significantly higher Silhouette Score of 0.48, and a lower BIC Score of 2696.18. These findings demonstrate the novelty of the GMM-PCA-BIC hybrid method in effectively capturing the complex characteristics of mosque and preacher data, ensuring efficient and relevant preacher assignments. Implementing this optimized clustering approach allows mosque administrators to make data-driven decisions, enhancing the effectiveness of religious activities.

关键词： Measurement Instruments Geology Education Real-time systems Geospatial analysis Informatics Gaussian mixture model Faces Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Reproducing ATT&CK Techniques and Lifecycles to Train Machine Learning Classifier

引用

IEEE Network 2025年

作者： Yudha, Fietyata Lin, Ying-Dar Lai, Yuan-Cheng Sudyana, Didik Hwang, Ren-Hung EECS International Graduate Program National Yang Ming Chiao Tung University Hsinchu City300 Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu City300 Taiwan The Department of Information Management National Taiwan University of Science and Technology Tapei106 Taiwan The Computer and Network Center National Cheng Kung University Tainan701 Taiwan The College of Artificial Intelligence National Yang Ming Chiao Tung University Tainan711 Taiwan

he MITRE ATT&CK framework categorizes threat actor behaviors into a sequence of techniques called the attack lifecycle. Based on this, Our work introduces a dual-labeled dataset that is accurately labeled with distinct techniques and lifecycles defined by ATT&CK. The dataset offered a more thorough perspective than previous datasets that employed binary or attack classification. It encompassed 17 distinct techniques throughout five lifecycles and was generated through an automated method that guarantees reproducibility and learnability. Reproducibility guarantees the dataset’s consistency, whereas learnability signifies its use in training machine learning models. Our analysis produced a positive result. The dataset achieved a Pearson correlation coefficient of 0.7 for reproducibility. Regarding distinguishing classes, it exhibits an average AUC-ROC score of 0.92 for techniques and 0.82 for lifecycles. The model training yielded an average F1 score of 0.95 for technique classification and 0.9 for lifecycle classification, but only for the traffic dataset. © 1986-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT for Water Quality Categorization

IoT for Water Quality Categorization

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Hermantoro Sastrohartono Andreas Wahyu Krisdiarto Arief Ika Uktoro Reza Rahutomo Teddy Suparyanto Bens Pardamean Agricultural Engineering Department Faculty of Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia Information System Department School of Information Systems Bina Nusantara University Jakarta Indonesia Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

In agricultural water research, the adoption of Internet of Things (IoT) technology has emerged as a pivotal approach for large-scale data collection. Water availability in the context of water quality is very important, both for domestic and industrial purposes. For domestic purposes, drinking water and bathing water are separated. Meanwhile, for the palm oil industry, boiler filler is differentiated from additional process water (dilution water). Water quality parameters can be assessed from turbidity and Total Dissolve Solid (TDS). Measurements using measuring instruments separately and repeatedly require significant energy, time, and costs. This research was conducted with the primary objective of presenting a novel method for categorizing water quality with the approach of IoT sensor technology. The research methodology entailed the utilization of an integrated IoT water sensors system in conjunction with manual water categorization. The methods consist of (1) system design, (2) design and installation of sensor and IoT-based microcontrollers, and (3) accuracy and precision testing compared with laboratory measurements. The precision of the integrated IoT water sensors was assessed through a dedicated sensor precision test, resulting in an accuracy rate of 94.4% for the turbidity sensor and 97.5% for the TDS sensor. Notably, this approach successfully discriminated drinking water with valid categorization, while other water types, including groundwater, water with tea, and water with coffee, yielded null categorization results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discover and align taxonomic context priors for open-world semi-supervised learning 23

Discover and align taxonomic context priors for open-world s...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yu Wang Zhun Zhong Pengchong Qiao Xuxin Cheng Xiawu Zheng Chang Liu Nicu Sebe Rongrong Ji Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China School of Computer Sceince University of Nottingham United Kingdom School of Electronic and Computer Engineering Peking University Shenzhen China and Department of Information Engineering and Computer Science University of Trento Italy School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China and Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Department of Automation Tsinghua University Beijing China Department of Information Engineering and Computer Science University of Trento Italy School of Electronic and Computer Engineering Peking University Shenzhen China and Peng Cheng Laboratory Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China

Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task, aiming to classify unlabeled samples from both seen and novel classes using partially labeled samples from the seen classes. Previous works typically explore the relationship of samples as priors on the pre-defined single-granularity labels to help novel class recognition. In fact, classes follow a taxonomy and samples can be classified at multiple levels of granularity, which contains more underlying relationships for supervision. We thus argue that learning with single-granularity labels results in sub-optimal representation learning and inaccurate pseudo labels, especially with unknown classes. In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context prIors Discovering and Aligning (TIDA), which exploits the relationship of samples under various granularity. It allows us to discover multi-granularity semantic concepts as taxonomic context priors (i.e., sub-class, target-class, and super-class), and then collaboratively leverage them to enhance representation learning and improve the quality of pseudo labels. Specifically, TIDA comprises two components: i) A taxonomic context discovery module that constructs a set of hierarchical prototypes in the latent space to discover the underlying taxonomic context priors; ii) A taxonomic context-based prediction alignment module that enforces consistency across hierarchical predictions to build the reliable relationship between classes among various granularity and provide additions supervision. We demonstrate that these two components are mutually beneficial for an effective OSSL framework, which is theoretically explained from the perspective of the EM algorithm. Extensive experiments on seven commonly used datasets show that TIDA can significantly improve the performance and achieve a new state of the art. The source codes are publicly available at https://***/rain305f/TIDA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulated prosthetic vision identifies checkerboard as an effective raster pattern for retinal implants

arXiv

引用

arXiv 2025年

作者： Kasowski, Justin M. Beyeler, Michael Interdepartmental Graduate Program in Dynamical Neuroscience University of California Santa BarbaraCA93106 United States Department of Computer Science University of California Santa BarbaraCA93106 United States Department of Psychological & Brain Sciences University of California Santa BarbaraCA93106 United States

Objective: This study systematically evaluates the impact of raster patterns-specific spatial arrangements of sequential electrode activation-on performance and perceived difficulty in simulated prosthetic vision (SPV). By addressing a critical gap in the literature, we aimed to identify patterns that optimize functional vision in retinal implants. Approach: Sighted participants completed letter recognition and motion discrimination tasks under four raster patterns (horizontal, vertical, checkerboard, and random) using an immersive SPV system. The simulations employed psychophysically validated models of electrode activation, phosphene appearance, and temporal dynamics, ensuring realistic representation of prosthetic vision. Performance accuracy and self-reported difficulty were analyzed to assess the effects of raster patterning. Main Results: The checkerboard pattern consistently outperformed other raster patterns, yielding significantly higher accuracy and lower difficulty ratings across both tasks. The horizontal and vertical patterns introduced biases aligned with apparent motion artifacts, while the checkerboard minimized such effects. Random patterns resulted in the lowest performance, underscoring the importance of structured activation. Significance: These findings provide the first systematic evaluation of raster patterns, suggesting that the checkerboard configuration may enhance usability and perceptual clarity in retinal implants. While based on simulated environments, this study establishes a foundation for optimizing spatial and temporal electrode activation strategies in next-generation devices. © 2025, CC BY.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：