Single Data Source Research Articles

Mountain Vegetation Classification Method Based on Multi-Channel Semantic Segmentation Model

With the development of satellite remote sensing technology, a substantial quantity of remote sensing data can be obtained every day, but the ability to extract information from these data remains poor, especially regarding intelligent extraction models for vegetation information in mountainous areas. Because the features of remote sensing images (such as spectral, textural and geometric features) change with changes in illumination, viewing angle, scale and spectrum, it is difficult for a remote sensing intelligent interpretation model with a single data source as input to meet the requirements of engineering or large-scale vegetation information extraction and updating. The effective use multi-source, multi-resolution and multi-type data for remote sensing classification is still a challenge. The objective of this study is to develop a highly intelligent and generalizable classification model of mountain vegetation utilizing multi-source remote sensing data to achieve accurate vegetation extraction. Therefore, a multi-channel semantic segmentation model based on deep learning, FCN-ResNet, is proposed to integrate the features and textures of multi-source, multi-resolution and multi-temporal remote sensing data, thereby enhancing the differentiation of different mountain vegetation types by capturing their characteristics and dynamic changes. In addition, several sets of ablation experiments are designed to investigate the effectiveness of the model. The method is validated on Mt. Taibai (part of the Qinling-Daba Mountains), and the pixel accuracy (PA) of vegetation classification reaches 85.8%. The results show that the proposed multi-channel semantic segmentation model can effectively discriminate different vegetation types and has good intelligence and generalization ability in different mountainous areas with similar vegetation distributions. The multi-channel semantic segmentation model can be used for the rapid updating of vegetation type maps in mountainous areas.

Exploring the Potential of OpenStreetMap Data in Regional Economic Development Evaluation Modeling

In regional development studies, GDP serves as an important indicator for evaluating the developing levels of a region. However, due to statistical methods and possible human-induced interfering factors, GDP is also a commonly criticized indicator for less accurately assessing regional economic development in a dynamic environment, especially during a globalized era. Moreover, common data collection approaches are often challenging to obtain in real-time, and the assessments are prone to inaccuracies. This is especially true in economically underdeveloped regions where data are often less frequently or accurately collected. In recent years, Nighttime Light (NTL) data have emerged as a crucial supplementary data source for regional economic development evaluation and analysis. We adapt this approach and attempt to integrate multiple sources of spatial data to provide a new perspective and more effective tools for economic development evaluation. In our current study, we explore the integration of OpenStreetMap (OSM) data and NTL data in regional studies, and apply a Geographically and Temporally Weighted Regression model (GTWR) for modeling and evaluating regional economic development. Our results suggest that: (1) when using OSM data as a single data source for economic development evaluation, the adjusted R2 value is 0.889. When using NTL data as a single data source for economic development evaluation, the adjusted R2 value is 0.911. However, the fitting performance of OSM data with GDP shows a gradual improvement over time, while the fitting performance of NTL data exhibits a gradual decline starting from the year 2014; (2) Among the economic evaluation models, the GTWR model demonstrates the highest accuracy with an AICc value of 49,112.71, which is 2750.94 lower than the ordinary least squares (OLS) model; (3) The joint modeling of OSM data with NTL data yields an adjusted R2 value of 0.956, which is higher than using either one of them alone. Moreover, this joint modeling approach demonstrates excellent fitting performance, particularly in economically underdeveloped regions, providing a potential alternative for development evaluation in data-poor regions.

‘RISDM‘: species distribution modelling from multiple data sources in R

Species distribution models (SDMs) are usually based on a single data type, such as presence‐only (PO), presence‐absence (PA) or abundance (AA). Results from SDMs using single sources of data will suffer from inherent biases and limitations to that data type. For example, PO data contain sampling‐bias and PA/AA data are often less expansive and more sparse. Integrated SDMs (ISDMs) combine multiple data types and have recently emerged as a way to leverage strengths and minimise weaknesses of the different data types. They pose a common (distribution) model and separate observation models for each of the data types. The ‘RISDM' package for the R environment (www.r‐project.org) provides access to this modelling framework using functions for preparation, fitting, interpreting and diagnosing models. The functionality of the package is demonstrated here using synthetic data sets.

Benchmark of Market Cloud Data Warehouse Technologies

Over the past two decades, the way computing resources are been developed, deployed, upgraded, and applied changed dramatically, with more and more software and hardware solutions being transferred to cloud technologies. Data Warehouses (DW), defined as a way of organizing corporate data in an integrated manner over (sequential) time periods, "structured & disposed" in order to generate a "single data source", were also affected by the evolution, thus giving rise to the concept of Cloud Data Warehouse (CDW). This technology allows users to be more technologically free, as they do not need to spend time investing in software and hardware, they only pay for the resources they used and the infrastructure itself has greater flexibility and scalability. However, selecting the most suitable platform or technology for a CDW can be a complex task due to the large number of factors that can influence the decision and due to the existing offer in the market.The objective of this paper is to describe the process of benchmarking a set of CDW platforms, with the goal of analyzing and exposing each one’s performance results. These platforms are Snowflake, Google BigQuery, Amazon Redshift, and Azure Synapse. The metrics to be measured are data loading and query running time, and alias running times. For this benchmark, the dataset used was Star Schema Benchmark (SSB), a dataset based on the well-known TPC Benchmark™ H (TPC-H).

Combining models to generate a consensus effective reproduction number R for the COVID-19 epidemic status in England

Abstract The effective reproduction number $ R $ was widely accepted as a key indicator during the early stages of the COVID-19 pandemic. In the UK, the $ R $ value published on the UK Government Dashboard has been generated as a combined value from an ensemble of epidemiological models via a collaborative initiative between academia and government. In this paper, we outline this collaborative modelling approach and illustrate how, by using an established combination method, a combined $ R $ estimate can be generated from an ensemble of epidemiological models. We analyse the $ R $ values calculated for the period between April 2021 and December 2021, to show that this $ R $ is robust to different model weighting methods and ensemble sizes and that using heterogeneous data sources for validation increases its robustness and reduces the biases and limitations associated with a single source of data. We discuss how $ R $ can be generated from different data sources and show that it is a good summary indicator of the current dynamics in an epidemic.

Determinants of Career Success: Teachers in Government Schools in Trincomalee District, Sri Lanka

The degree of career success that different people perceive varies substantially. Along with variations in objective achievements, this variety reflects various viewpoints on what constitutes a “successful” career. Teachers who continually develop themselves become better equipped to inspire and guide their students to achieve their full potential. Hence, the career success of teachers is important to not only teachers but also students. This has led to expanding research into the determinants of career success of teachers. This study aims to identify the determinants of career success of teachers in Trincomalee District, Sri Lanka. Using self-administered structured questionnaire surveys, determinants of career success were measured. The research used a single data source and cross-sectional design. The data from 365 valid surveys were collected using a simple random sampling technique. The hypotheses were tested using the Pearson correlation coefficient and linear regression analysis. Findings revealed that emotional intelligence, career adaptability, career commitment, work-life balance, and person-job fit impact the career success of teachers in Government Schools in Trincomalee District, Sri Lanka. Further, it was revealed that emotional intelligence, career adaptability, career commitment, work-life balance, and person-job fit have a positive relationship with career success, confirming the previous research findings. Thus, all hypotheses were accepted. According to the findings, person-job fit has the highest correlation with career success. Hence, the researcher recommended that uplifting person-job fit would have a greater impact on increasing the career success of teachers.

Performance of XGBoost Ensemble Learning Algorithm for Mangrove Species Classification with Multisource Spaceborne Remote Sensing Data

Accurately and timely monitoring the spatial distribution and composition of mangrove species is critical for assessing mangroves’ health, dynamics, and biodiversity, as well as mangroves’ degradation and restoration. Recent advances in machine learning algorithms, coupled with spaceborne remote sensing technique, offer an unprecedented opportunity to map mangroves at species level with high resolution over large extents. However, a single data source or data type is insufficient to capture the complex features of mangrove species and cannot satisfy the need for fine species classification. Moreover, identifying and selecting effective features derived from integrated multisource data are essential for integrating high-dimensional features for mangrove species discrimination. In this study, we developed a novel framework for mangrove species classification using spectral, texture, and polarization information derived from 3-source spaceborne imagery: WorldView-2 (WV-2), OrbitaHyperSpectral (OHS), and Advanced Land Observing Satellite-2 (ALOS-2). A total of 151 remote sensing features were first extracted, and 18 schemes were designed. Then, a wrapper method by combining extreme gradient boosting with recursive feature elimination (XGBoost-RFE) was conducted to select the sensitive variables and determine the optical subset size of all features. Finally, an ensemble learning algorithm of XGBoost was applied to classify 6 mangrove species in the Zhanjiang Mangrove National Nature Reserve, China. Our results showed that combining multispectral, hyperspectral, and L-band synthetic aperture radar features yielded the best mangrove species classification results, with an overall accuracy of 94.02%, a quantity disagreement of 4.44%, and an allocation disagreement of 1.54%. In addition, this study demonstrated important application potential of the XGBoost classifier. The proposed framework could provide fine-scale data and conduce to mangroves’ conservation and restoration.

Comparative research on multi-source heterogeneous data fusion technologies

Both structured market data and unstructured financial news data can significantly affect stock price fluctuations. Therefore, relying only on a single data source for stock price trend prediction may produce information bias. This article combines these two types of heterogeneous data and systematically compares the effectiveness of different data fusion technologies to establish the optimal data integration strategy, thereby improving the accuracy of stock price prediction. Specifically, this paper innovatively proposes a stock price trend prediction model named MVL-SVM. The model successfully combines multi-perspective learning with support vector machine, and realizes the effective fusion of stock market data and financial news data. It is worth mentioning that the prediction accuracy of MVL-SVM model using direct fusion method is more than 30% higher than that of index modeling method, which indicates that direct fusion method can fully learn effective information from multiple information sources, thus significantly improving the prediction effect.

Workshop synthesis: Data Fusion - Generating More Than a Sum of Parts

This report summarizes the insights from a workshop conducted during the 12th International Conference on Transport Survey Methods focusing on data fusion. The workshop discussion and the presentations illustrated that data fusion comes in many ways utilizing various data and methodologies. While much of the academic literature and practical applications of data fusion in transport apply to travel demand modelling, fusion in the context of travel survey data production is still in its infancy. Despite data fusion's acknowledged potential, a reason for this hesitancy is a lack of quality standards. The report recommends future research to improve knowledge about the suitability of data and methodologies for fusion and the development of respective standards. This will be necessary to convince stakeholders that the quality of fused data is not inferior to any single data source, be it travel survey data or, e.g. mobile phone data.

Applying multimodal data fusion to track autistic adolescents’ representational flexibility development during virtual reality-based training

In our study, we harnessed multimodal data to develop a predictive model aimed at assessing the development of representational flexibility (RF) in autistic adolescents engaged in virtual reality (VR)-based cognitive skills training. Recognizing VR's potential to enhance RF through immersive 3D simulation tasks, we addressed the research gap in analyzing learners' digital interactions within this environment. This data mining study integrated diverse data sources—including behavioral cues, physiological responses, and direct interaction logs—collected from 178 training sessions with eight autistic adolescents. This comprehensive dataset, encompassing both audio and screen recordings, was analyzed using advanced machine learning techniques. Through decision-level data fusion, particularly employing the random forest algorithm, our model demonstrated enhanced accuracy in predicting RF development, surpassing single-source data approaches. This research not only contributes to the effective use of VR in educational interventions for autistic adolescents but also showcases the potential of multimodal data fusion in understanding complex cognitive skills development.

An integrated framework for importance-performance analysis of product attributes and validation from online reviews and maintenance records

Abstract Importance-performance analysis (IPA) is widely used for needs analysis, product positioning, and strategic planning in product design. Previous research on IPA often employs single-source data such as customer surveys or online reviews with unavoidable subjective bias. In contrast, product maintenance records provide objective information on product quality and failure patterns, which can be cross-validated with customers’ personal experiences from surveys or online reviews. In this paper, we propose an integrated framework for conducting IPA from online reviews and product maintenance records jointly. An attribute-keyword dictionary is first established using keyword extraction and clustering methods. Then, semantic groups, including product attributes and associated descriptions, are extracted using dependency parsing analysis. The sentiment scores of identified product attributes are determined by a voting mechanism using two pre-trained sentiment analysis models. The importance of product attributes in IPA is estimated from the impact of sentiments of each product attribute on product ratings with the extreme gradient boosting (XGBoost) model, while the performance is estimated from the sentiment scores of online reviews or the quality statistics from product maintenance records. In addition, we propose two methods to validate the IPA results, in which the IPA results are compared with the actual product improvements on the market or compared with the analysis of customer reviews from different time periods, respectively. The validated IPA results from online reviews and maintenance records are then integrated to obtain a more comprehensive understanding of customer needs. A case study of passenger vehicles is used to demonstrate the framework. The proposed framework enables automatic data processing and can support companies in making efficient design decisions with more comprehensive perspectives from multisource data.

A cost-effective over-temperature alarm system for cold chain delivery

Managing over-temperature alarms in cold chain logistics (CCL) is crucial for temperature monitoring systems. However, existing research in this area primarily focuses on improving identification accuracy while overlooking the associated cost implications. This study addresses this gap by proposing a cost-effective over-temperature alarm system using an artificial neural network (ANN) model that integrates multi-source data (MSD). This article demonstrates that utilizing ANN and MSD leads to significantly improved recognition accuracy compared to using single-source data while keeping the cost increase to a minimum. The paper found recognition accuracy to be 97.4% with three feature values and 98.6% with six feature values. Sensitivity analyses reveal that factors such as the initial food temperature, cumulative open time, data acquisition interval, and algorithm significantly impact the recognition accuracy of the over-temperature alarm system. The location of sensors, however, has a slight effect. Furthermore, the choice of the number of feature values and the granularity of the data influences the cost of temperature management and recognition accuracy. This study provides valuable insights into the factors influencing recognition accuracy, aiding in designing cost-effective over-temperature alarm systems for food supply chain management.

HARMONIZATION OF SELF-REPORTED RACE/ETHNICITY TO ENHANCE HEALTH EQUITY RESEARCH USING MEDICARE DATA

Abstract Collection of valid race and ethnicity data is critical to understanding and promoting health equity. However, current administrative data often misclassifies members of the racial/ethnic minority groups. To address this issue, the Research Triangle Institute (RTI) developed an imputed race variable, which improves on administrative race data for Hispanic and Asian beneficiaries, but still has limitations. This study compares the RTI race with our new, harmonized, self-reported race/ethnicity data collected during Medicaid enrollment and post-acute and long-term care assessments. Out of 2,322,071 Medicare beneficiaries aged 18 and older who died in 2019 in the U.S., self-reported race/ethnicity was available for 75.1% (1,745,327) who formed the study population. Compared to the RTI race variable, our new race variable categorized more Medicare beneficiaries as non-Hispanic white (79.5% vs. 77.9%) and Asian American/Pacific Islander (2.5% vs. 2.3%), a similar percentage as American Indians/Alaska Native (0.5% vs. 0.5%), and slightly fewer as Black (11.1% vs. 10.9%) and Hispanic (7.2% vs. 6.5%). Using our new race variable as the gold-standard, RTI race had good validity (k=0.81), however sensitivity was highest for non-Hispanic white (96.5) and Black (95.8) beneficiaries, and lower for Hispanic (87.2), Asian American/Pacific Islander (76.2), and American Indian/Alaska Native (58.7) beneficiaries. These findings are consistent with prior work, comparing RTI race with self-reported race from a single data source. Our study provides empirical evidence to support the U.S. Office of the Inspector General’s recommendations to the Centers for Medicare and Medicaid Services to incorporate self-reported race/ethnicity data available to reduce error and bias.

Predicting coastal harmful algal blooms using integrated data-driven analysis of environmental factors

Coastal harmful algal blooms (HABs) have become one of the challenging environmental problems in the world's thriving coastal cities due to the interference of multiple stressors from human activities and climate change. Past HAB predictions primarily relied on single-source data, overlooked upstream land use, and typically used a single prediction algorithm. To address these limitations, this study aims to develop predictive models to establish the relationship between the HAB indicator – chlorophyll-a (Chl-a) and various environmental stressors, under appropriate lagging predictive scenarios. To achieve this, we first applied the partial autocorrelation function (PACF) to Chl-a to precisely identify two prediction scenarios. We then combined multi-source data and several machine learning algorithms to predict harmful algae, using SHapley Additive exPlanations (SHAP) to extract key features influencing output from the prediction models. Our findings reveal an apparent 1-month autoregressive characteristic in Chl-a, leading us to create two scenarios: 1-month lead prediction and current-month prediction. The Extra Tree Regressor (ETR), with an R2 of 0.92, excelled in 1-month lead predictions, while the Random Forest Regressor (RFR) was most effective for current-month predictions with an R2 of 0.69. Additionally, we identified current month Chl-a, developed land use, total phosphorus, and nitrogen oxides (NOx) as critical features for accurate predictions. Our predictive framework, which can be applied to coastal regions worldwide, provides decision-makers with crucial tools for effectively predicting and mitigating HAB threats in major coastal cities.

Interactive effects of organizational resources on sustainable product design practices: a resource orchestration perspective

PurposeThe purpose of this study is to investigate the interactive effects of a firm’s strategic sustainability orientation (SSO) and customer relationship capital (CRC) on sustainable product design practices (SPDP).Design/methodology/approachThe authors examine the interactive effects of two firm resources, namely, SSO and CRC, as they relate to SPDP, using survey data from 132 manufacturers in Malaysia.FindingsThe findings show that the effect of SSO on SPDP is stronger when CRC is low, than otherwise. The authors also find that the interactive effects of the firm-level resources stated above are stronger when customer pressures (CPs) are higher than when they are low.Research limitations/implicationsThe authors contribute to the literature by studying the effects of firm-level strategic resources and their interactions as they relate to SPDP. An important limitation of this research is the usage of single-source data and single-period data.Practical implicationsManagerially, this research provides new insights into how organizations should respond to CPs while understanding the counterintuitive but disabling effects of customer relationship assets.Social implicationsThe findings are important to society because most of the environmental impact arising from the production, consumption and disposal of products is a direct consequence of decisions made at the product design stage and an unintended consequence of the marketing decision-making processes that underlie marketing strategy formulation that fails to recognize ecosystems impact as a standard decision influence.Originality/valueTo the best of the authors’ knowledge, this research is the first to study the effects of firm-level strategic resources and their interactions as they relate to SPDP.

A Comprehensive Model for Recommending Personalized Learning Resources for the Development of Linguistic Competence

With the continuous advancement of globalization and informatization, the linguistic competence of college students has become a key index for evaluating their comprehensive quality. Faced with diverse needs of students and educational environments, it is increasingly important and complex to accurately locate the linguistic competence goals of college students. Although existing research methods, such as standardized testing and teacher assessment, provide certain convenience, they rely on single data sources and have a certain degree of subjectivity, which limits their universality and accuracy. This study aimed to solve this problem by doing comprehensive research on two aspects: first, curriculum analysis based on relation extraction. A relation extraction model, such as Casrel, was used for advanced text analysis, which provided educators with more in-depth insights; second, personalized learning material recommendation based on text recommendation. Personalized learning paths were provided for students of different levels using the abstractness-based text recommendation algorithm. This study not only filled the gaps in existing research methods, but also provided a new, scientific and efficient solution, helping improve the quality of education and promote the formulation of scientific education policies.

Stock market prediction-COVID-19 scenario with lexicon-based approach

Stock market forecasting remains a difficult problem in the economics industry due to its incredible stochastic nature. The creation of such an expert system aids investors in making investment decisions about a certain company. Due to the complexity of the stock market, using a single data source is insufficient to accurately reflect all of the variables that influence stock fluctuations. However, predicting stock market movement is a challenging undertaking that requires extensive data analysis, particularly from a big data perspective. In order to address these problems and produce a feasible solution, appropriate statistical models and artificially intelligent algorithms are needed. This paper aims to propose a novel stock market prediction by the following four stages; they are, preprocessing, feature extraction, improved feature level fusion and prediction. The input data is first put through a preparation step in which stock, news, and Twitter data (related to the COVID-19 epidemic) are processed. Under the big data perspective, the input data is taken into account. These pre-processed data are then put through the feature extraction, The improved aspect-based lexicon generation, PMI, and n-gram-based features in this case are derived from the news and Twitter data, while technical indicator-based features are derived from the stock data. The improved feature-level fusion phase is then applied to the extracted features. The ensemble classifiers, which include DBN, CNN, and DRN, were proposed during the prediction phase. Additionally, a SI-MRFO model is suggested to enhance the efficiency of the prediction model by adjusting the best classifier weights. Finally, SI-MRFO model’s effectiveness compared to the existing models with regard to MAE, MAPE, MSE and MSLE. The SI-MRFO accomplished the minimal MAE rate for the 90th learning percentage is approximately 0.015 while other models acquire maximum ratings.

MMCL-CDR: enhancing cancer drug response prediction with multi-omics and morphology images contrastive representation learning.

Cancer is a complex disease that results in a significant number of global fatalities. Treatment strategies can vary among patients, even if they have the same type of cancer. The application of precision medicine in cancer shows promise for treating different types of cancer, reducing healthcare expenses, and improving recovery rates. To achieve personalized cancer treatment, machine learning models have been developed to predict drug responses based on tumor and drug characteristics. However, current studies either focus on constructing homogeneous networks from single data source or heterogeneous networks from multiomics data. While multiomics data have shown potential in predicting drug responses in cancer cell lines, there is still a lack of research that effectively utilizes insights from different modalities. Furthermore, effectively utilizing the multimodal knowledge of cancer cell lines poses a challenge due to the heterogeneity inherent in these modalities. To address these challenges, we introduce MMCL-CDR (Multimodal Contrastive Learning for Cancer Drug Responses), a multimodal approach for cancer drug response prediction that integrates copy number variation, gene expression, morphology images of cell lines, and chemical structure of drugs. The objective of MMCL-CDR is to align cancer cell lines across different data modalities by learning cell line representations from omic and image data, and combined with structural drug representations to enhance the prediction of cancer drug responses (CDR). We have carried out comprehensive experiments and show that our model significantly outperforms other state-of-the-art methods in CDR prediction. The experimental results also prove that the model can learn more accurate cell line representation by integrating multiomics and morphological data from cell lines, thereby improving the accuracy of CDR prediction. In addition, the ablation study and qualitative analysis also confirm the effectiveness of each part of our proposed model. Last but not least, MMCL-CDR opens up a new dimension for cancer drug response prediction through multimodal contrastive learning, pioneering a novel approach that integrates multiomics and multimodal drug and cell line modeling. MMCL-CDR is available at https://github.com/catly/MMCL-CDR.

Prediction of Dementia Using Machine Learning Methods within a Large Pooled Consortia: The Dementia Risk Prediction Pooling (DRPP) Consortium

AbstractBackgroundMachine learning models have been used to create accurate prediction models for dementia. However, many suffer from overfitting and external validation often results in decreased performance. Pooling data from various sources for model training can improve the generalizability of prediction models. We show here a prediction model for dementia developed on pooled data from the Dementia Risk Prediction Pooling (DRPP) Consortium.MethodData from 11 longitudinal disease cohorts within the DRPP and relevant risk factors (25 in total) were collected and harmonized at baseline and follow‐up exams. An ensemble tree‐based algorithm, LightGBM, was used to create two prediction models for dementia at or before 10 years. The first model contains all variables in the dataset, and the second clinical model excludes the Mini‐Mental State Examination (MMSE) score and APOE genotype. 5‐fold cross‐validation was repeated 1000 times to tune the model hyperparameters (number of leaves, tree depth, learning rate) to yield the greatest area under the curve (AUC). Feature importance of the model was analyzed via individual feature information gain. Analysis was performed in R 4.1.2.ResultsAmong the 55,614 participants from 11 cohorts included in this analysis (Table 1), the first model with all the variables had a cross‐validation AUC of 0.762 (CI: 0.757‐0.767). Counterintuitively, the second model of the without the MMSE and APOE variables yielded an AUC of 0.804 (CI: 0.799‐0.809), which may indicate overfitting in the first model. Feature importance analysis show that age is the most important variable in both models. APOE, MMSE, fasting glucose, and any physical activity are the next most important predictors in the full model (Figure 1). In the second model, fasting glucose, any physical activity, gender, and A1c levels were the next most important predictors (Figure 2).ConclusionBy pooling various data sources, we can train machine learning models for dementia risk prediction on more diverse data. Further work is needed to compare the performance of these models with models trained on single data sources via external validation. A pooled dataset also offers an opportunity to understand how model performance will change given shifts in the underlying population.

Hyperspectral and SAR Image Classification via Multiscale Interactive Fusion Network.

Due to the limitations of single-source data, joint classification using multisource remote sensing data has received increasing attention. However, existing methods still have certain shortcomings when faced with feature extraction from single-source data and feature fusion between multisource data. In this article, a method based on multiscale interactive information extraction (MIFNet) for hyperspectral and synthetic aperture radar (SAR) image classification is proposed. First, a multiscale interactive information extraction (MIIE) block is designed to extract meaningful multiscale information. Compared with traditional multiscale models, it can not only obtain richer scale information but also reduce the model parameters and lower the network complexity. Furthermore, a global dependence fusion module (GDFM) is developed to fuse features from multisource data, which implements cross attention between multisource data from a global perspective and captures long-range dependence. Extensive experiments on the three datasets demonstrate the superiority of the proposed method and the necessity of each module for accuracy improvement.