Different Levels Of Information Research Articles

A unified active learning framework for annotating graph data for regression tasks

In many domains, effectively applying machine learning models requires a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often requires significant time, effort, and computational resources, making it challenging. Active learning strategies are pivotal in addressing these challenges, particularly for diverse data types such as graphs. Although active learning has been extensively explored for node-level classification, its application to graph-level learning, especially for regression tasks, is not well-explored. We develop a unified active learning framework specializing in graph annotating and graph-level learning for regression tasks on both standard and expanded graphs, which are more detailed representations. We begin with graph collection and construction. Then, we construct various graph embeddings (unsupervised and supervised) into a latent space. Given such an embedding, the framework becomes task agnostic and active learning can be performed using any regression method and query strategy suited for regression. Within this framework, we investigate the impact of using different levels of information for active and passive learning, e.g., partially available labels and unlabelled test data. Despite our framework being domain agnostic, we validate it on a real-world application of software performance prediction, where the execution time of the source code is predicted. Thus, the graph is constructed as an intermediate source code representation. We support our methodology with a real-world dataset to underscore the applicability of our approach. Our real-world experiments reveal that satisfactory performance can be achieved by querying labels for only a small subset of all the data. A key finding is that Graph2Vec (an unsupervised embedding approach for graph data) performs the best, but only when all train and test features are used. However, Graph Neural Networks (GNNs) are the most flexible embedding techniques when used for different levels of information with and without label access. In addition, we find that the benefit of active learning increases for larger datasets (more graphs) and when the graphs are more complex, which is arguably when active learning is the most important.

A multi-scale dense residual correlation network for remote sensing scene classification

Most existing scene classification methods based on remote sensing images tend to ignore important interactive information at different levels in the image. We propose an effective remote sensing scene classification method named multi-scale dense residual correlation network. The method is divided into three parts. First, the multi-stream feature extraction module is introduced which effectively utilizes features at different scales to extract different levels of information. Secondly, the dense residual connected feature fusion technology is proposed, which allows for a wide range of feature fusion. The Correlation Attention Module learn feature representations at multiple levels. This improves classification performance. The method outperforms existing algorithms in terms of effectiveness and accuracy, achieving state-of-the-art results on widely used remote sensing scene classification benchmarks.

Dual-neighbourhood information aggregation and feature fusion for prediction of miRNA–disease association

Studying the intricate relationship between miRNAs and diseases is crucial to prevent and treat miRNA-related disorders. Existing computational methods often overlook the importance of features of different nodes and the propagation of features among heterogeneous nodes. Many prediction models focus only on the feature coding of miRNA and diseases and ignore the importance of feature aggregation. We propose a prediction method via dual-neighbourhood feature aggregation and feature fusion, which uses multiple sources of information, aggregates information on homogeneous and heterogeneous nodes and fuses learned features to predict multiple representations of disease nodes. We constructed similarity networks of multiple homogeneous nodes based on different similarity computation methods respectively, and fused the attention mechanism by using graph convolutional networks to obtain information of different levels of importance. To alleviate the problem of sparse connectivity in the dataset, we built a two-neighbourhood heterogeneous graph neural network model to integrate the homogeneous similarity network into a miRNA-disease heterogeneous network by using known miRNA–disease association information. We used the neighbourhood information associated with the nodes in the network to perform feature aggregation. In addition, we used a feature fusion module to learn the importance of different types of nodes to predict miRNA–disease associations. Our experimental results on the Human microRNA Disease Database (HMDD v3.2) show that the model demonstrates superior performance. This work demonstrates the capability of our model to identify potential miRNAs associated with diseases through a case study of two common cancers.

Native MS-guided lipidomics to define endogenous lipid microenvironments of eukaryotic receptors and transporters.

The mammalian membrane is composed of various eukaryotic lipids interacting with extensively post-translationally modified proteins. Probing interactions between these mammalian membrane proteins and their diverse and heterogeneous lipid cohort remains challenging. Recently, native mass spectrometry (MS) combined with bottom-up 'omics' approaches has provided valuable information to relate structural and functional lipids to membrane protein assemblies in eukaryotic membranes. Here we provide a step-by-step protocol to identify and provide relative quantification for endogenous lipids bound to mammalian membrane proteins and their complexes. Using native MS to guide our lipidomics strategies, we describe the necessary sample preparation steps, followed by native MS data acquisition, tailored lipidomics and data interpretation. We also highlight considerations for the integration of different levels of information from native MS and lipidomics and how to deal with the various challenges that arise during the experiments. This protocol begins with the preparation of membrane proteins from mammalian cells and tissues for native MS. The results enable not only direct assessment of copurified endogenous lipids but also determination of the apparent affinities of specific lipids. Detailed sample preparation for lipidomics analysis is also covered, along with comprehensive settings for liquid chromatography-MS analysis. This protocol is suitable for the identification and quantification of endogenous lipids, including fatty acids, sterols, glycerolipids, phospholipids and glycolipids and can be used to interrogate proteins from recombinant sources to native membranes.

Multi-query and multi-level enhanced network for semantic segmentation

Plain transformer-based methods have achieved promising performance on semantic segmentation recently. These methods adopt a single set of class queries to predict masks of different semantic categories based on multi-level feature maps. We argue that this single-query design cannot fully exploit diverse information of different levels for improved semantic segmentation. To address this issue, we propose a multi-query and multi-level enhanced network for semantic segmentation (named QLSeg). Our QLSeg first performs multi-level feature enhancement on plain transformer to improve feature discriminability. Afterwards, we introduce multi-query decoder to respectively extract feature embeddings and predict mask logits at different levels, where feature embeddings are adaptively merged for classification and mask logits are summed for output masks. In addition, we introduce masked attention-to-mask to focus on local regions with the same class. We perform the experiments on three widely-used semantic segmentation datasets: ADE20K, COCO-Stuff-10K, and PASCAL-Context. Our proposed QLSeg achieves competitive results on all these three datasets.

Are soil carbon credits empty promises? Shortcomings of current soil carbon quantification methodologies and improvement avenues

AbstractAs the consequences of climate change are looming large, agricultural soil carbon credits have emerged as an increasingly advocated lever to incentivize the reduction of greenhouse gas emissions and promote carbon storing farming practices. These credits are exchanged on self‐regulated voluntary carbon markets, each of them using distinct protocols to assess the changes in soil carbon stocks and convert them into carbon credits. Although serious discrepancies between protocols have already been noted regarding general carbon credit accounting principles, an in‐depth evaluation of how changes in soil organic carbon stocks are calculated is still lacking. In this context, the primary objective of our study was to investigate how changes in soil organic carbon stock are estimated by the major carbon credit protocols worldwide. We evaluated the requirements of each protocol regarding the estimation of the initial SOC stock as well as the modelling and/or measurement of changes in stock with time. We found that existing protocols vary greatly in their scientific rigour. We showed in particular that some protocols do not require in situ soil analyses to estimate initial soil carbon stocks but rely on regional values, leading them to potentially overestimate these stocks by up to 2.5 times. Our study also found that the protocols relying on models require different farming practices and different levels of information for each practice to estimate SOC stock changes. The protocols relying, at least partly, on soil sampling also displayed different requirements for the sampling design, sampling tools, SOC analysis methods and SOC stock calculation methods. On this basis, we suggest reforms designed to improve and standardize the quantification of carbon stock changes in soils and to improve the reliability of soil carbon credits.

Diffusion-Based Causal Representation Learning.

Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAEs). These methods only provide representations from a point estimate, and they are less effective at handling high dimensions. To overcome these problems, we propose a Diffusion-based Causal Representation Learning (DCRL) framework which uses diffusion-based representations for causal discovery in the latent space. DCRL provides access to both single-dimensional and infinite-dimensional latent codes, which encode different levels of information. In a first proof of principle, we investigate the use of DCRL for causal representation learning in a weakly supervised setting. We further demonstrate experimentally that this approach performs comparably well in identifying the latent causal structure and causal variables.

Navigating the complexities of online opinion formation: An insight into consumer cognitive heuristics

Few studies have considered changes in consumer perceptions when faced with multiple levels of review ratings. Drawing on availability heuristic theory, we aim to explore the synergistic effects of different levels of review ratings on consumers' cognitive processes. Using a longitudinal dataset of reviews from 4637 restaurants on Yelp, we conducted an empirical study using individual and time-dual fixed-effects models. Our findings indicate that easy-to-retrieve (review) rating is better than aggregate ratings in predicting consumer purchase decisions. The inconsistency between easy-to-retrieve and aggregate ratings influences consumers' cognitive heuristic when interpreting online reviews. Additionally, inconsistencies and proportional changes in expert and amateur reviews influence consumer perceptions of different levels of information. Furthermore, we conducted two online experiments to validate the distinguishing impact of aggregate versus easy-to-retrieve ratings on consumers. These findings provide insightful implications for understanding consumers’ cognitive heuristics in online consumption contexts.

Multitask Learning for Concurrent Grading Diagnosis and Semi-Supervised Segmentation of Honeycomb Lung in CT Images

Honeycomb lung is a radiological manifestation of various lung diseases, seriously threatening patients’ lives worldwide. In clinical practice, the precise localization of lesions and assessment of their severity are crucial. However, accurate segmentation and grading are challenging for physicians due to the heavy annotation burden and diversity of honeycomb lungs. In this paper, we propose a multitask learning architecture for semi-supervised segmentation and grading diagnosis to achieve automatic localization and assessment of lesions. To the best of our knowledge, this is the first method that integrates a grading diagnosis task into honeycomb lung semi-supervised segmentation. Firstly, we adapt cross-learning to capture local features and long-range dependencies from the CNN and transformer. Secondly, considering the diversity of honeycomb lung lesions, the shape-edge aware constraint is designed to assist the model in locating lesions. Then, in order to better understand the different levels of information in the images, we develop global contrast and local contrast learning to enhance the model’s learning of semantic-level and pixel-level features. Lastly, aiming to improve the diagnostic accuracy, we propose a gradient thresholding algorithm to integrate the segmentation predictions into the grading diagnosis network. The experiment’s results based on the in-house honeycomb lung dataset demonstrate the superiority of our method. Compared to other methods, our approach achieves a state-of-the-art performance. In particular, in external data testing, our predictions are consistent with physicians in the majority of cases. In addition, the segmentation results based on the public Kvasir-SEG dataset also indicate that our method has good generalization ability.

Temporally Consistent Enhancement of Low-Light Videos via Spatial-Temporal Compatible Learning

Temporal inconsistency is the annoying artifact that has been commonly introduced in low-light video enhancement, but current methods tend to overlook the significance of utilizing both data-centric clues and model-centric design to tackle this problem. In this context, our work makes a comprehensive exploration from the following three aspects. First, to enrich the scene diversity and motion flexibility, we construct a synthetic diverse low/normal-light paired video dataset with a carefully designed low-light simulation strategy, which can effectively complement existing real captured datasets. Second, for better temporal dependency utilization, we develop a Temporally Consistent Enhancer Network (TCE-Net) that consists of stacked 3D convolutions and 2D convolutions to exploit spatial-temporal clues in videos. Last, the temporal dynamic feature dependencies are exploited to obtain consistency constraints for different frame indexes. All these efforts are powered by a Spatial-Temporal Compatible Learning (STCL) optimization technique, which dynamically constructs specific training loss functions adaptively on different datasets. As such, multiple-frame information can be effectively utilized and different levels of information from the network can be feasibly integrated, thus expanding the synergies on different kinds of data and offering visually better results in terms of illumination distribution, color consistency, texture details, and temporal coherence. Extensive experimental results on various real-world low-light video datasets clearly demonstrate the proposed method achieves superior performance to state-of-the-art methods. Our code and synthesized low-light video database will be publicly available at https://github.com/lingyzhu0101/low-light-video-enhancement.git.

Hierarchical spatial attention-based cross-scale detection network for Digital Works Supervision System (DWSS)

Vision-based on-site detection is a crucial component of the Digital Works Supervision System (DWSS). However, accurate detecting cross-scale objects in complicated construction sites remains a challenge. In this research, a hierarchical spatial attention-based cross-scale detection network is designed to address these challenges and provide accurate on-site information for the DWSS. Firstly, a convolutional neural network is constructed to extract multi-scale feature maps with different levels of information. Furthermore, a hierarchical spatial attention mechanism is proposed to facilitate information propagation and complement between multi-scale feature maps. Secondly, the cascade detection mechanism is designed to improve the detection performance of cross-scale objects. Large-scale feature maps with more detailed information are used for the detection of small-scale objects such as workers. Small-scale feature maps with semantic features are used for the detection of large-scale objects such as construction machines. Finally, the on-site information is automatically extracted from detection results and converted into suitable data formats to generate on-site reports for the DWSS. Experiments demonstrate that the proposed method can achieve SOTA detection performance on both MOCS and SODA dataset, especially for the small-scale objects and complicated construction scenarios.

Reactivating and Preserving Interactive Multimedia Artworks: An Analog Performance from the Seventies

Interactive multimedia art shows a complex nature as it is time- and process-based, interconnected with technology, derived by the participation of several authors (artists, technicians, performers, to name a few) and an audience, and it is strongly tied to the moment and space of the original exhibition. These characteristics make the preservation of these artworks a multifaceted process. Building on the foundations developed since the 2000s by international projects focused on preserving and restoring these new art forms, the paper proposes an original model for achieving dynamic preservation, called “the multilevel preservation model”. Since it is no longer possible to guarantee physical integrity for interactive multimedia artworks, dynamic preservation involves recording all the changes that occur to display the artworks in the future. In other words, it makes it possible to record the dynamic authenticity of artworks. The model proposes two fundamental properties: multiple layering, which allows to handle different levels of information about the artwork; multiple belongingness , which allows to represent the dynamic authenticity of the artwork at the archival level and achieving dynamic preservation. The paper demonstrates the high-level implementation of the model by presenting a case study: the reactivation and preservation of an analog video art performance from the 1970s. This case study proposes an interesting real scenario for testing the model, as the reactivation process involved the migration of the entire analog technological apparatus of the artwork into the digital domain.

A graph neural network with topic relation heterogeneous multi-level cross-item information for session-based recommendation

The aim of session-based recommendation (SBR) mainly analyzes the anonymous user’s historical behavior records to predict the next possible interaction item and recommend the result to the user. However, due to the anonymity of users and the sparsity of behavior records, recommendation results are often inaccurate. The existing SBR models mainly consider the order of items within a session and rarely analyze the complex transition relationship between items, and additionally, they are inadequate at mining higher-order hidden relationship between different sessions. To address these issues, we propose a topic relation heterogeneous multi-level cross-item information graph neural network (TRHMCI-GNN) to improve the performance of recommendation. The model attempts to capture hidden relationship between items through topic classification and build a topic relation heterogeneous cross-item global graph. The graph contains inter-session cross-item information as well as hidden topic relation among sessions. In addition, a self-loop star graph is established to learn the intra-session cross-item information, and the self-connection attributes are added to fuse the information of each item itself. By using channel-hybrid attention mechanism, the item information of different levels is pooled by two channels: max-pooling and mean-pooling, which effectively fuse the item information of cross-item global graph and self-loop star graph. In this way, the model captures the global information of the target item and its individual features, and the label smoothing operation is added for recommendation. Extensive experimental results demonstrate that the recommendation performance of TRHMCI-GNN model is superior to the comparable baseline models on the three real datasets Diginetica, Yoochoose1/64 and Tmall. The code is available now.11https://github.com/usstyangfan/TRHMCI-GNN.

Evaluating different levels of information on the calibration of building energy simulation models

Evaluating different levels of information on the calibration of building energy simulation models

Comparison of soft-computing techniques: Data-driven models for flood forecasting

<p>Accurate flood forecasting is a crucial process for predicting the timing, occurrence, duration, and magnitude of floods in specific zones. This prediction often involves analyzing various hydrological, meteorological, and environmental parameters. In recent years, several soft computing techniques have been widely used for flood forecasting. In this study, flood forecasting for the Narmada River at the Hoshangabad gauging site in Madhya Pradesh, India, was conducted using an Artificial Neural Network (ANN) model, a Fuzzy Logic (FL) model, and an Adaptive Neuro-Fuzzy Inference System (ANFIS) model. To assess their capacity to handle different levels of information, three separate input data sets were used. Our objective was to compare the performance and evaluate the suitability of soft computing data-driven models for flood forecasting. For the development of these models, monthly discharge data spanning 33 years from six gauging sites were selected. Various performance measures, such as regression, root mean square error (RMSE), and percentage deviation, were used to compare and evaluate the performances of the different models. The results indicated that the ANN and ANFIS models performed similarly in some cases. However, the ANFIS model generally predicted much better than the ANN model in most cases. The ANFIS model, developed using the hybrid method, delivered the best performance with an RMSE of 211.97 and a coefficient of regression of 0.96, demonstrating the potential of using these models for flood forecasting. This research highlighted the effectiveness of soft computing techniques in flood forecasting and established useful suitability criteria that can be employed by flood control departments in various countries, regions, and states for accurate flood prognosis.</p>

End-to-end Prediction of EGFR Mutation Status with Denseformer.

Accurate genotyping of the epidermal growth factor receptor (EGFR) is critical for the treatment planning of lung adenocarcinoma. Currently, clinical identification of EGFR genotyping highly relies on biopsy and sequence testing which is invasive and complicated. Recent advancements in the integration of computed tomography (CT) imagery with deep learning techniques have yielded a non-invasive and straightforward way for identifying EGFR profiles. However, there are still many limitations for further exploration: 1) most of these methods still require physicians to annotate tumor boundaries, which are time-consuming and prone to subjective errors; 2) most of the existing methods are simply borrowed from computer vision field which does not sufficiently exploit the multi-level features for final prediction. To solve these problems, we propose a Denseformer framework to identify EGFR mutation status in a real end-to-end fashion directly from 3D lung CT images. Specifically, we take the 3D whole-lung CT images as the input of the neural network model without manually labeling the lung nodules. This is inspired by the medical report that the mutational status of EGFR is associated not only with the local tumor nodules but also with the microenvironment surrounded by the whole lung. Besides, we design a novel Denseformer network to fully explore the distinctive information across the different level features. The Denseformer is a novel network architecture that combines the advantages of both convolutional neural network (CNN) and Transformer. Denseformer directly learns from the 3D whole-lung CT images, which preserves the spatial location information in the CT images. To further improve the model performance, we designed a combined Transformer module. This module employs the Transformer Encoder to globally integrate the information of different levels and layers and use them as the basis for the final prediction. The proposed model has been tested on a lung adenocarcinoma dataset collected at the Affiliated Hospital of Zunyi Medical University. Extensive experiments demonstrated the proposed method can effectively extract meaningful features from 3D CT images to make accurate predictions. Compared with other state-of-the-art methods, Denseformer achieves the best performance among current methods using deep learning to predict EGFR mutation status based on a single modality of CT images.

Sliding scales for assessing and communicating human and ecological risks and complexities for restoration, remediation crises, and decisions

Many lands were degraded or destroyed by human activities, including contamination from industry and military facilities. The United States and other industrialized counties have legacy wastes remaining from the Second World War, the Cold War, and industrialization. There is increasing need to return degraded land to suitable future land uses, including ecological parks and preserves. This paper proposes a conceptual model of the different levels of information needed to understand the risk to human health, the environment, and ecological resources. I propose a four-part approach: (1) general model for assessing ecological resources, (2) model for assessment needed for remediation or restoration projects, (3) a sliding scale, conceptual model for causes, events, and sources that lead to exposure and risk, and (4) an additional step that includes environmental justice (equity, diversity, and inclusion) as a necessary consideration of traditional exposure assessment. While the factors involved in ecological risk assessment are well established, the combination of human health, ecological health, and environmental justice determining risk for remediation or restoration projects is not. Major factors useful for human health, environmental, and ecological evaluation include causes, events (earthquakes, accidents, chemical releases), sources, exposure, and informational challenges, as well as barriers to exposure. I propose that exposure through an environmental justice (diversity, equity, and inclusion) lens should be a key component of risk assessment. Each of these factors involves a sliding scale or continuum that must be considered in evaluating risk and communicating with the regulators, resource trustees, land managers and the public. The conceptual model also serves as a template for obtaining information about the environment that will be useful for communicating the importance of different risk factors. The model was developed for consideration of remediation on Department of Energy lands, it can be applied more broadly to other projects.

Blend U-Net: Redesigning Skip Connections to Obtain Multiscale Features for Lung CT Images Segmentation.

Lung cancer is a pervasive and persistent issue worldwide, with the highest morbidity and mortality among all cancers for many years. In the medical field, computer tomography (CT) images of the lungs are currently recognized as the best way to help doctors detect lung nodules and thus diagnose lung cancer. U-Net is a deep learning network with an encoder-decoder structure, which is extensively employed for medical image segmentation and has derived many improved versions. However, these advancements do not utilize various feature information from all scales, and there is still room for future enhancement. In this study, we proposed a new model called Blend U-Net, which incorporates nested structures, redesigned long and short skip connections, and deep supervisions. The nested structures and the long and short skip connections combined characteristic information of different levels from feature maps in all scales, while the deep supervision learning hierarchical representations from all-scale concatenated feature maps. Additionally, we employed a mixed loss function to obtain more accurate results. We evaluated the performance of the Blend U-Net against other architectures on the publicly available Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. Moreover, the accuracy of the segmentation was verified by using the dice coefficient. Blend U-Net with a boost of 0.83 points produced the best outcome in a number of baselines. Based on the results, our method achieves superior performance in terms of dice coefficient compared to other methods and demonstrates greater proficiency in segmenting lung nodules of varying sizes.

Extraction of target structures in learners' corpora

Foreign language (FL) or second language (L2) corpora are sets of productions by non-native speakers, learners of a given language, which contemplate the errors and well-formed structures produced. These serve different research objectives, such as studies on language acquisition (LE and L2), phenomena of linguistic interference or analysis and diagnosis of LE/L2 proficiency levels. In the context of this research, the definition of the learner's proficiency level is often relevant, and this is done, typically, through the analysis of the presence or absence of errors in the learners' productions, based on mappings of typical or expected errors and well-formed structures for a given level of proficiency. However, contrary to the learner's error – which is explicitly marked in the corpus and whose typology and methodology of analysis constitutes a subtopic of investigation on its own –, the well-formed structures, and in particular the target structures (well-formed structures expected in the learners' productions of a given level of proficiency), are not easily identifiable in the corpora. The work presented here aims to fill this gap in COPLE2 – Corpus of Portuguese Foreign/Second Language through the use of expressions in CQL – Corpus Query Language. Based on pre-identified target structures and on the information made available in COPLE2, such as morphosyntactic tagging and different levels of information and annotation (learner production, teacher correction, normalized form, lemma, etc.), we propose query expressions in CQL that easily allow any user to immediately extract examples of target structures by proficiency level. The construction of the query expressions implies the definition and testing of the best strategies for each case and requires the systematization of linguistic rules and patterns of occurrence of the phenomena in question, but also the definition of ways to circumvent the limitations inherent to the corpus annotation, on the one hand, and the query language, on the other.

A hybrid reinsurance-investment game with delay and asymmetric information

In this paper, we investigate the optimal reinsurance and investment problem in the framework of the hybrid stochastic differential game, which includes a stochastic Stackelberg differential subgame and a non-zero-sum stochastic differential subgame. The stochastic Stackelberg differential subgame considers the leader–follower relationship between a reinsurer and two insurers. The reinsurer, as the leader, prices reinsurance premium and invests its wealth in a financial market that contains a risk-free asset and a risky asset whose price process is described by the constant elasticity of variance (CEV) model. On the other side, the two insurers, as the followers, purchase proportional reinsurance from the reinsurer and invest in the same financial market. Also, the competitive relationship between the two insurers is characterized by the non-zero-sum stochastic differential subgame in which each insurer considers the relative performance. By introducing the delay feature into the hybrid game, we are able to obtain the wealth processes depicted by the stochastic delay differential equations. Considering the effect of asymmetric information, we assume the reinsurer and insurers have different levels of information about the financial market. The objective of the reinsurer is to maximize the mean–variance functional of its terminal surplus with delay, while each insurer is to maximize the mean–variance functional of its terminal surplus with delay relative to that of its competitor. By applying techniques in stochastic control theory, we obtain the extended Hamilton–Jacobi–Bellman equations, and then by using the idea of backward induction, we establish the equilibrium strategies and the corresponding value functions. Finally, we include some numerical examples and sensitivity analysis to illustrate the effects of model parameters on the equilibrium strategies.