Data Structure Research Articles

Learning curves for deep structured Gaussian feature models*

Abstract In recent years, significant attention in deep learning theory has been devoted to analyzing when models that interpolate their training data can still generalize well to unseen examples. Many insights have been gained from studying models with multiple layers of Gaussian random features, for which one can compute precise generalization asymptotics. However, few works have considered the effect of weight anisotropy; most assume that the random features are generated using independent and identically distributed Gaussian weights, and allow only for structure in the input data. Here, we use the replica trick from statistical physics to derive learning curves for models with many layers of structured Gaussian features. We show that allowing correlations between the rows of the first layer of features can aid generalization, while structure in later layers is generally detrimental. Our results shed light on how weight structure affects generalization in a simple class of solvable models.

Database Construction and Application of Large-scale Geospatial Data

Abstract. Geospatial data refers to data that related to spatial location. It is the abstract representation of objects, events, or other characteristic information located on or near the surface of the Earth. It characterizes attribute features, spatial features, and associated information of geospatial features. Geospatial data commonly include various data types such as point, polyline, polygon, and so on. Geospatial database is the basic method to store and manage geospatial data. It is also the important component of geographic information systems (GIS). Geospatial database generally stores data in a specific structure in a medium, which can achieve efficient management of geospatial data. Users can add, modify, and delete data efficiently. Furthermore, query retrieval and statistical analysis can be quickly performed based on geospatial database. In this paper, distributed geospatial database is constructed by using database partition tables storage technology. Meanwhile, database construction software is developed to achieve the construction, management, and application of large-scale geospatial data. It can improve data import, query and retrieval efficiency significantly. The database application service system can directly connect to the database for displaying statistical analysis results. At the same time, geospatial data are processed to vector tiles, which stored in the tile database. Furthermore, standard online service is then published, which can be used for database management and application service system. It can be used for natural resource management work such as basic surveying, survey and monitoring, and so on.

3D CNN for neuropsychiatry: Predicting Autism with interpretable Deep Learning applied to minimally preprocessed structural MRI data.

Predictive modeling approaches are enabling progress toward robust and reproducible brain-based markers of neuropsychiatric conditions by leveraging the power of multivariate analyses of large datasets. While deep learning (DL) offers another promising avenue to further advance progress, there are challenges related to implementation in 3D (best for MRI) and interpretability. Here, we address these challenges and describe an interpretable predictive pipeline for inferring Autism diagnosis using 3D DL applied to minimally processed structural MRI scans. We trained 3D DL models to predict Autism diagnosis using the openly available ABIDE I and II datasets (n = 1329, split into training, validation, and test sets). Importantly, we did not perform transformation to template space, to reduce bias and maximize sensitivity to structural alterations associated with Autism. Our models attained predictive accuracies equivalent to those of previous machine learning (ML) studies, while side-stepping the time- and resource-demanding requirement to first normalize data to a template. Our interpretation step, which identified brain regions that contributed most to accurate inference, revealed regional Autism-related alterations that were highly consistent with the literature, encompassing a left-lateralized network of regions supporting language processing. We have openly shared our code and models to enable further progress towards remaining challenges, such as the clinical heterogeneity of Autism and site effects, and to enable the extension of our method to other neuropsychiatric conditions.

Elevated peripheral inflammation is associated with choroid plexus enlargement in independent sporadic amyotrophic lateral sclerosis cohorts

BackgroundUsing neuroimaging techniques, growing evidence has suggested that the choroid plexus (CP) volume is enlarged in multiple neurodegenerative diseases, including amyotrophic lateral sclerosis (ALS). Notably, the CP has been suggested to play an important role in inflammation-induced CNS damage under disease conditions. However, to our knowledge, no study has investigated the relationships between peripheral inflammation and CP volume in sporadic ALS patients. Thus, in this study, we aimed to verify CP enlargement and explore its association with peripheral inflammation in vivo in independent ALS cohorts.MethodsBased on structural MRI data, CP volume was measured using Gaussian mixture models and further manually corrected in two independent cohorts of sporadic ALS patients and healthy controls (HCs). Serum inflammatory protein levels were measured using a novel high-sensitivity Olink proximity extension assay (PEA) technique. Xtreme gradient boosting (XGBoost) was used to explore the contribution of peripheral inflammatory factors to CP enlargement. Then, partial correlation analyses were performed.ResultsCP volumes were significantly higher in ALS patients than in HCs in the independent cohorts. Compared with HCs, serum levels of CRP, IL-6, CXCL10, and 35 other inflammatory factors were significantly increased in ALS patients. Using the XGBoost approach, we established a model-based importance of features, and the top three predictors of CP volume in ALS patients were CRP, IL-6, and CXCL10 (with gains of 0.24, 0.18, and 0.15, respectively). Correlation analyses revealed that CRP, IL-6, and CXCL10 were significantly associated with CP volume in ALS patients (r = 0.462 ∼ 0.636, p < 0.001).ConclusionOur study is the first to reveal a consistent and replicable contribution of peripheral inflammation to CP enlargement in vivo in sporadic ALS patients. Given that CP enlargement has been recently detected in other brain diseases, these findings should consider extending to other disease conditions with a peripheral inflammatory component.

Lucie: An Improved Python Package for Loading Datasets from the UCI Machine Learning Repository.

The University of California-Irvine (UCI) Machine Learning (ML) Repository (UCIMLR) is consistently cited as one of the most popular dataset repositories, hosting hundreds of high-impact datasets. However, a significant portion, including 28.4% of the top 250, cannot be imported via the ucimlrepo package that is provided and recommended by the UCIMLR website. Instead, they are hosted as .zip files, containing nonstandard formats that are difficult to import without additional ad hoc processing. To address this issue, here we present lucie-load University California Irvine examples-a utility that automatically determines the data format and imports many of these previously non-importable datasets, while preserving as much of a tabular data structure as possible. lucie was designed using the top 100 most popular datasets and benchmarked on the next 130, where it resulted in a success rate of 95.4% vs. 73.1% for ucimlrepo. lucie is available as a Python package on PyPI with 98% code coverage.

Ground-LIO: enhanced LiDAR-inertial odometry for ground robots based on ground optimization

Abstract In the field of LiDAR-based Simultaneous Localization and Mapping, the potential of ground point clouds to enhance pose estimation in mobile robots has yet to be fully realized. This paper focuses on leveraging ground point clouds to improve the performance of LiDAR-Inertial Odometry (LIO) systems for ground-based mobile robots. We begin by analyzing the characteristics of ground point clouds and the typical types of noise that affect their extraction and utilization. Ground point clouds are then extracted from denoised data. Given the generally local planar nature of ground point clouds, we propose a segmentation-and-refitting approach to process them. This method reduces the computational burden of residual calculation in pose estimation by avoiding redundant plane fitting. Additionally, we introduce a data structure designed for the efficient management and utilization of ground point clouds obtained through segmentation and refitting. This structure is particularly suited to the ground point cloud data produced by our method, enabling efficient access and registration through the continuous maintenance and consolidation of local plane parameters. Our method has been integrated into advanced LIO systems (Bai et al 2022 IEEE Robot. Autom. Lett. 7 4861–8), and experimental results on challenging datasets demonstrate its promising performance.

The Effect of Regularized Regression and Tree-Based Missing Data Imputation Methods on Classification Performance in High Dimensional Data

Missing data is an important problem in the analysis and classification of high dimensional data. The aim of this study is to compare the effects of four different missing data imputation methods on classification performance in high dimensional data. In this study, missing data imputation methods were evaluated using data sets, whose independent variables between mixed correlated with each other, for binary dependent variable, p=500 independent variables, n=150 units and 1000 times running simulation. Missing data structures were created according to different missing rates. Different datasets were obtained by imputing the missing values using different methods. Regularized regression methods such as lasso and elastic net regression were used for imputation, as well as tree-based methods such as support vector machine and classification and regression trees. At the end of simulation, the classification scores of the methods were obtained by gradient boosting machines and the missing data prediction performances were evaluated according to the distance of these scores from the reference. Our simulation demonstrates that regularized regression methods outperform tree-based methods in classifying high dimensional datasets. Additionally, it was found that the increase in the amount of missing values reduced the classification performance of the methods in high dimensional data.

Deep Learning Applications in Natural Language Processing and Optimization Strategies

In recent years, deep learning has made significant advancements in the field of natural language processing (NLP), driving the development of language understanding and generation tasks. Deep learning utilizes multi-layer neural networks to automatically extract and represent complex data features. This paper first introduces the basic principles of deep learning and mainstream frameworks (such as TensorFlow and PyTorch) and discusses core NLP tasks, including word embedding, language modeling, and text generation. Subsequently, it analyzes specific practices of deep learning applications in text classification, machine translation, automatic summarization, dialogue systems, and speech recognition. Further discussion covers model optimization methods, including structural optimization (such as RNN, LSTM, GRU, and Transformer), data preprocessing and feature engineering, hyperparameter tuning, and accelerated computation. Finally, it explores cutting-edge optimization strategies like federated learning, model compression, self-supervised learning, and transfer learning, proposing future research directions and challenges. This paper aims to systematically analyze the applications and optimization strategies of deep learning in NLP.

Towards Sustainable Development of Mineral Resources in Sub-Saharan Africa: A Structural Equation Modeling Approach

This study focuses on economic, governmental, social, and environmental factors and their impact on the sustainable development of mineral resources in sub-Saharan Africa. Using structural equation modeling (SEM) and data from 40 countries from 2010 to 2022, the research examines the hypothesized links between these factors and sustainable development. The results reveal a positive and statistically significant relationship between economic factors and sustainable development, underlining the crucial role of economic growth in achieving sustainable development goals. Furthermore, effective governance and policy implementation are strongly associated with better sustainable development, underscoring the importance of robust government action. This study also highlights the importance of social factors, demonstrating that increased community involvement and participation contribute positively to sustainable development. Contrary to the initial hypothesis, the research reveals a positive relationship between environmental factors and sustainable development, challenging existing ideas and suggesting the need for a more nuanced understanding of the interaction between environmental practices and sustainability. This study concludes with concrete recommendations, including prioritizing economic growth, improving governance and policy effectiveness, promoting social inclusion, and reassessing environmental conservation strategies. These findings provide valuable information for policymakers, corporations, and communities in sub-Saharan Africa, thus contributing to a more comprehensive understanding of the dynamics of sustainable development in the region.

Implementation of concurrency control mechanisms to enhance the performance of multi-threaded applications

Concurrency control is a crucial aspect of multi-threaded application development, directly impacting performance and resource utilization.This research project investigates the impact of various concurrency control mechanisms on the performance of multi-threaded applications, specifically focusing on mutexes, semaphores, and lock-free data structures implemented using queues. Conducted in a Python environment within Google Colab, the study aims to assess performance metrics such as execution time, cpu usage, and memory usage. Each mechanism’s performance was evaluated through repeated trials, and the results were aggregated and averaged to ensure reliability. By systematically evaluating these concurrency control mechanisms, the project seeks to understand how each approach affects the efficiency of applications in a multi-threaded context. The findings reveal that the queue mechanism provides the fastest execution time, the semaphore mechanism, on the other hand, exhibited the lowest CPU usage, and the mutex mechanism offered a balanced performance in both speed and CPU efficiency. Memory usage was similar in mutex and semaphore, but queue differed significantly from the other two. These results show that the choice of concurrency control mechanism should be guided by the specific requirements of the application, considering factors such as workload nature and system architecture.

Semantic Alignment in Disciplinary Tutoring System: Leveraging Sentence Transformer Technology

In this work, we present a disciplinary e-tutoring system that integrates ONTO-TDM, an ontology designed for teaching domain modeling, with advanced transformer technology. Our primary objective is to enhance semantic similarity tasks within the system by fine-tuning a Sentence Transformer model. By carefully adjusting training parameters with a curated dataset of question-answer pairs focused on algorithms and data structures, we achieved a notable improvement in system performance. The Sentence Transformer model, combined with domain ontology, achieved an accuracy of 91%, a precision of 93%, a recall of 89%, and an F1-score of 90%, significantly surpassing the results of existing works. This methodology highlights the potential to deliver personalized support and guidance in tutoring scenarios. It effectively addresses the evolving needs of modern education by offering tailored answers and reducing the necessity for constant learner-tutor interaction, thereby improving the efficiency of educational support systems.

Orphan GPCRs in Neurodegenerative Disorders: Integrating Structural Biology and Drug Discovery Approaches.

Neurodegenerative disorders, particularly Alzheimer's and Parkinson's diseases, continue to challenge modern medicine despite therapeutic advances. Orphan G-protein-coupled receptors (GPCRs) have emerged as promising targets in the central nervous system, offering new avenues for drug development. This review focuses on the structural biology of orphan GPCRs implicated in these disorders, providing a comprehensive analysis of their molecular architecture and functional mechanisms. We examine recent breakthroughs in structural determination techniques, such as cryo-electron microscopy and X-ray crystallography, which have elucidated the intricate conformations of these receptors. The review highlights how structural insights inform our understanding of orphan GPCR activation, ligand binding and signaling pathways. By integrating structural data with molecular pharmacology, we explore the potential of structure-guided approaches in developing targeted therapeutics toward orphan GPCRs. This structural-biology-centered perspective aims to deepen our comprehension of orphan GPCRs and guide future drug discovery efforts in neurodegenerative disorders.

NeRF-based Localization and Meshing with Wearable Laser Scanning System: A Case Study in Underground Environment

Abstract. Due to the subterranean scene’s poor lighting conditions and variability of the environment, real-time localizing and meshing in complex underground scenes present a challenging task, with high-potential applications in mining and tunnel protection. In this work, we propose a method that combines SLAM and NeRF for mesh reconstruction in the underground environment with a wearable device. First, a LiDAR-Inertial odometry is used for pose estimation. The resulting poses and sequential laser frames are synchronized to generate a novel data structure, scan-block, which is crucial for improving efficiency and ensuring local precision. This structure is designed to enhance efficiency and ensure local precision. Finally, the generated scan-blocks are passed to the backend NeRF for real-time mesh reconstruction. The experiments are carried out in a complex underground space. The experimental results proved that this method achieved good results. The demo video can be found at https://youtu.be/_y1vbaW06EM?si= hFnAl12u-ffU933h.

Performance Evaluation of HTTP, DHCP and DNS Protocols of Data Packets for Vulnerabilities Using the Isolation Forest Algorithm

In the contemporary digital landscape, network security is paramount to safeguard data integrity and prevent unauthorized access as data have been structured in the network through protocols. In term of data structure IPv6 protocol has extended data size due to the robust addresses of 128 bits as compare to 32 bits of IPv4. Due to the improved security data structure of IPv6, the study focuses on identifying vulnerabilities in HTTP, DHCP, and DNS packets using the Isolation Forest algorithm approach, a machine-learning technique designed for anomaly detection. By analyzing packet lengths, size, payload and addressing, the study visualizes normal and anomalous behavior, providing insights into potential security threats in IPv4 network structure. The results highlight the effectiveness of Goodput, Quality of service and risk as essential factors in the network, using Little's theorem analysis and the Isolation Forest in detecting anomalies across these different network protocols, offering valuable implications for network security structures, due to IoT in recent networks. The time response determination in this paper explained details information on the time the treats entered the network, the duration of the vulnerabilities within the network, leading to a certain threshold, and traffic delay factors due to deviation of packet length and other social engineering activities. Sensitive multipurpose security devices are involved; MikroTik routers were configured and installed in the network under evaluation. Which the normal DPI technique was unable to effectively and efficiently addressed. ADPI principles and operations where the needed security measures adopted to detect those vulnerabilities which were eventually addressed and have contributed to recent measures of network security.

Sustainable Waste Management in Urban Area - A Case Study of the Waste Management of the Cities in China

As urbanisation continues to accelerate, the integration of regional waste treatment capacity is becoming increasingly important and challenging nowadays, as economic development imbalances and environmental problems are becoming more prominent. An important component of urban development is the generation and management of municipal solid waste , and due to differences in socio-economic status, China's world-class metropolises such as Shanghai and medium-sized cities such as Xiamen are facing the same problem. This study attempts to explore the possibilities and prospects for sustainable waste management in China's future by comparing Xiamen with Shanghai, using relevant structural models and relevant research data within the city and the region. The introduction of the concept of waste-free cities also provides a greater diversity of options for future programmes. Finding effective strategies based on China's socio-economic and cultural conditions has implications for developing countries such as China in promoting the shift from waste management to a circular economy.

How Late Nights Influence Brain Cortical Structures: Distinct Neuroanatomical Measures Associated With Late Chronotype in Young Adults.

Chronotype is an inherent physiological trait reflecting an individual's subjective preference for their sleep awakening time, exerting a substantial influence on both physical and mental well-being. While existing research has established a close relationship between chronotype and individual brain structure, prior studies have predominantly focused on individual measurements of brain structural scales, thereby limiting the exploration of the underlying mechanisms of structural changes. This study seeks to validate previous research findings and enhance our understanding of the correlation between circadian rhythm preference and diverse cortical indicators in healthy young individuals. Magnetic resonance imaging (MRI) scans and chronotype assessments were conducted once for all participants, comprising 49 late chronotype (LC) young adults and 49 matched early chronotype young adults. The Chronotype Questionnaire was utilized to assess morningness and eveningness preferences. Surface-based analysis of structural MRI data revealed that LC young adults exhibited thinner cortical thickness of left pars orbitalis and lower cortical mean curve of right paracentral gyrus. Overall, this study represents a significant advancement in elucidating the connection between brain structure and function within the context of chronotypes.

Evolutionary Sequences and Structural Information-driven Reconstruction of New Insulin-like Growth Factor-I Peptide Variants.

Insulin-like growth factor-I (IGF-I) is crucial in controlling cell growth, proliferation, and apoptosis. Its strong link to the development of cancers such as breast, prostate, lung, thyroid, and colorectal has positioned the IGF-1 signalling pathway as a promising target for novel cancer therapies. When activated, the IGF-1 receptor (IGF-1R) binds to IGF-I, playing a central role in promoting tumour cell growth and survival. In this study, we combined evolutionary sequences with structural and functional data of IGF-1 to reconstruct ancestral sequences and design novel IGF-1 peptide variants. The insulin-like growth factor system exhibits a vast sequence diversity, yet it shares a similar structural topology with conserved three pairs of disulfide linkages. Our study reveals that IGF-1 is associated with the IGF system of cell surface receptors through protein-protein interactions. Reconstructed IGF-1 variants show similar structure fold to reported viral IGF-1 competitive antagonists. This new insight guides the design of novel natural IGF-1 mimic peptides. It enhances our understanding of IGF-1's functionality and opens new avenues for the development of therapeutic peptides and small molecules as anticancer agents.

A Practice of City-scale 3D Geographic Entity Representation and Application in China: The Smart Chongqing City Centre

Abstract. The Chinese photogrammetry industry is currently experiencing a significant revolution driven by digital intelligence technologies. Traditional city-scale 3D modelling, typically reconstructed from oblique photogrammetry or laser points, is facing increasing limitations in refined expression, real-time rendering, machine recognition, data sharing, and interoperability due to its large data volume and mesh structure. These limitations make it difficult to meet the substantial demands of spatial analysis, simulation, and prediction. The concept of geographic entities, which are machine-recognizable spatial data structures, is anticipated to provide a competitive solution for these challenges. This work employs 3D scene modelling and geographic knowledge graphs to construct geographic entities with semantic relationships at city-scale, addressing the limitations encountered in the application of traditional mesh/point-based 3D models. A case study in Chongqing city centre demonstrates the feasibility and effectiveness of the proposed approach and its potential applications in simulation, prediction, early warning, and feedback for urban planning and smart city management.

3D Data Integration in the Voxel Domain

Abstract. The interest in 3D data integration is growing as the concept of Spatial Digital Twins gains traction among local governments and stakeholders. Spatial data is typically organized into standardised themes such as buildings, transport, and vegetation, or as ad hoc data products in either 2D or 3D dimensions. However, integrating these data sets into a cohesive 3D model presents several challenges. The foundational data sets may vary in terms of accuracy, resolution, representation, and actuality due to differences in creation standards and procedures. Consequently, inconsistencies often arise within the 3D models, making them difficult to identify and rectify. Many of these data integration issues can be traced back to the 3D vector representation. Vector 3D models exhibit significant geometric diversity, which complicates the computational operations required for examining and validating the models. In this paper, we propose a novel voxel-based approach for integrating 3D data. Voxels, analogous to pixels in 2D raster images, inherit several key properties. We employ a dedicated voxel data structure and a set of operations tailored for this purpose. First, we voxelise vector datasets, converting continuous geometric information into discrete voxel representations. Next, we merge voxel layers using a specialized voxel overlay operation. The resulting 3D model adheres to most validity and integrity requirements. To highlight the flexibility of our voxel data structure, we transformed it into point clouds for visualisation in ArcGIS Pro, enabling the addition of 3D base maps and GIS layers. We then published these datasets to Scene Services, granting public access. This allows users to easily explore the 3D scenes through a web browser, making complex geographic data more accessible. By leveraging voxels, our approach facilitates efficient and accurate 3D data integration, making it a valuable contribution to the field.

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Abstract Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. In this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.