Embedding Clustering Research Articles

Issue agenda-setting in the voice to parliament referendum: using big data to explain voice discourse on traditional and social media

ABSTRACT This article explores issue agenda-setting in Australia's 2023 Voice to Parliament referendum, analysing the dynamics of Yes and No campaigns in a diverse media ecosystem. We identify influential messages across this complex media environment using soft clustering of sentence embeddings from large language models (LLMs). Drawing on 3.3 million documents and over 10 million Voice specific sentences from mainstream and social media sources, we identify the narrative configurations of the campaigns, their audience size and engagement. Overall, the Yes campaign dominated with more diverse messaging and greater audience size and engagement than No. Yet, the No case prevailed. We find the narrower, mostly negative No campaign helped sustain the issue agenda both online and offline, forcing Yes to respond to it. The findings also challenge echo chamber theory, revealing most unique topics contained content from both #Yes and #No perspectives, indicating robust public engagement rather than isolated filter bubbles.

Parameterization before Meta-Analysis: Cross-Modal Embedding Clustering for Forest Ecology Question-Answering

In the field of forestry ecology, image data capture factual information, while literature is rich with expert knowledge. The corpus within the literature can provide expert-level annotations for images, and the visual information within images naturally serves as a clustering center for the textual corpus. However, both image data and literature represent large and rapidly growing, unstructured datasets of heterogeneous modalities. To address this challenge, we propose cross-modal embedding clustering, a method that parameterizes these datasets using a deep learning model with relatively few annotated samples. This approach offers a means to retrieve relevant factual information and expert knowledge from the database of images and literature through a question-answering mechanism. Specifically, we align images and literature across modalities using a pair of encoders, followed by cross-modal information fusion, and feed these data into an autoregressive generative language model for question-answering with user feedback. Experiments demonstrate that this cross-modal clustering method enhances the performance of image recognition, cross-modal retrieval, and cross-modal question-answering models. Our method achieves superior performance on standardized tasks in public datasets for image recognition, cross-modal retrieval, and cross-modal question-answering, notably achieving a 21.94% improvement in performance on the cross-modal question-answering task of the ScienceQA dataset, thereby validating the efficacy of our approach. Essentially, our method targets cross-modal information fusion, combining perspectives from multiple tasks and utilizing cross-modal representation clustering of images and text. This approach effectively addresses the interdisciplinary complexity of forestry ecology literature and the parameterization of unstructured heterogeneous data encapsulating species diversity in conservation images. Building on this foundation, intelligent methods are employed to leverage large-scale data, providing an intelligent research assistant tool for conducting forestry ecological studies on larger temporal and spatial scales.

Self‐supervised representation learning of metro interior noise based on variational autoencoder and deep embedding clustering

AbstractThe noise within train is a paradox; while harmful to passenger health, it is useful to operators as it provides insights into the working status of vehicles and tracks. Recently, methods for identifying defects based on interior noise signals are emerging, among which representation learning is the foundation for deep neural network models to understand the key information and structure of the data. To provide foundational data for track fault detection, a representation learning framework for interior noise, named the interior noise representation framework, is introduced. The method includes: (i) using wavelet transform to represent the original noise signal and designing a soft and hard denoising module for dataset denoising; (ii) deep residual convolutional denoising variational autoencoder (VAE) module performs representation learning with a VAE and deep residual convolutional neural networks, enabling richer data augmentation for sparsely labeled samples by manipulating the embedding space; (iii) deep embedding clustering submodule balances the representation of reconstruction and clustering features through the joint optimization of these aspects, categorizing metro noise into three distinct classes and effectively discriminating significantly different features. The experimental results show that, compared to traditional mechanism‐based models for characterizing interior noise, this approach offers a data‐driven general analysis framework, providing a foundational model for downstream tasks.

Urban streets profiling with coupled spatio-temporal characteristics and topological information from the biking perspective

Urban street profiling is the spatio-temporal pattern discovery of street-level urban areas, which plays a vital role in understanding urban structures and dynamics. Due to the natural topology and various geographic characteristics on the streets, it is necessary to combine multi-dimensional spatio-temporal information to understand different profiles of streets. This research aims to develop a street profiling framework according to the coupled characteristics of streets. At the start, a bidirected dual graph and a spatial weighted graph embedding method were used to solve the street representation. Then, the street profiles can be extracted by clustering embedding vectors of streets and feature importance analysis. As the case study, we employed the bike trajectories and street view images in Xiamen, China to depict the geographic attributes of streets. The results can reveal nine spatio-temporal street profiles from the biking perspective, including three spatial distribution patterns and two spatial semantic patterns. Urban streets in the study area show a significant hierarchical pattern because of locations and the spatial lags of the biking behaviors. Meanwhile, the spatio-temporal characteristics of biking behaviors are the main factors of street profiles, though the street environment attributes participate in over half the number of profile types. We further evaluated the profiling ability of the proposed framework and the importance of urban street profiles using coupled characteristics. Overall, this study explored the profiling method for coupling static and dynamic characteristics of urban streets. The profiling results also help understand street usage and experiences by bikers, which have a practical value on the human-oriented classification of streets and further urban development from a geographic view.

IDS-DEC: A novel intrusion detection for CAN bus traffic based on deep embedded clustering

As the automotive industry advances towards greater automation, the proliferation of electronic control units (ECUs) has led to a substantial increase in the connectivity of in-vehicle networks with the external environment. However, the widely used Controller Area Network (CAN), which serves as the standard for in-vehicle networks, lacks robust security features, such as authentication or encrypted information transmission. This poses a significant challenge to the security of these networks. Despite the availability of powerful intrusion detection methods based on machine learning and deep learning, there are notable limitations in terms of stability and accuracy in the absence of a supervised learning process with labeled data. To address this issue, this paper introduces a novel in-vehicle intrusion detection system, termed IDS-DEC. This system combines a spatiotemporal self-coder employing LSTM and CNN (LCAE) with an entropy-based deep embedding clustering. Specifically, our approach involves encoding in-vehicle network traffic into windowed messages using a stream builder, designed to adapt to high-frequency traffic. These messages are then fed into the LCAE to extract a low-dimensional nonlinear spatiotemporal mapping from the initially high-dimensional data. The resulting low-dimensional mapping is subjected to a dual constraint in conjunction with our entropy-based pure deep embedding clustering module. This creates a bidirectional learning objective, addressing the optimization problem and facilitating an end-to-end training pattern for our model to adapt to diverse attack environments. The effectiveness of IDS-DEC is validated using both the benchmark Car Hacking dataset and the Car Hacking-Attack & Defense Challenge dataset. Experimental results demonstrate the model's high detection accuracy across various attacks, stabilizing at approximately 99% accuracy with a 0.5% false alarm rate. The F1 score also stabilizes at around 99%. In comparison with unsupervised methods based on deep stream clustering, LSTM-based self-encoder, and classification-based methods, IDS-DEC exhibits significant improvements across all performance metrics.

Hybrid deep learning and optimized clustering mechanism for load balancing and fault tolerance in cloud computing

ABSTRACT Cloud services are one of the most quickly developing technologies. Furthermore, load balancing is recognized as a fundamental challenge for achieving energy efficiency. The primary function of load balancing is to deliver optimal services by releasing the load over multiple resources. Fault tolerance is being used to improve the reliability and accessibility of the network. In this paper, a hybrid Deep Learning-based load balancing algorithm is developed. Initially, tasks are allocated to all VMs in a round-robin method. Furthermore, the Deep Embedding Cluster (DEC) utilizes the Central Processing Unit (CPU), bandwidth, memory, processing elements, and frequency scaling factors while determining if a VM is overloaded or underloaded. The task performed on the overloaded VM is valued and the tasks accomplished on the overloaded VM are assigned to the underloaded VM for cloud load balancing. In addition, the Deep Q Recurrent Neural Network (DQRNN) is proposed to balance the load based on numerous factors such as supply, demand, capacity, load, resource utilization, and fault tolerance. Furthermore, the effectiveness of this model is assessed by load, capacity, resource consumption, and success rate, with ideal values of 0.147, 0.726, 0.527, and 0.895 are achieved.

Osteostaticytes: A novel osteoclast subset couples bone resorption and bone formation

BackgroundOsteomyelitis (OM) is an inflammatory condition of bone characterized by cortical bone devascularization and necrosis. Dysregulation of bone remodelling is triggered by OM. Bone remodelling is precisely coordinated by bone resorption and formation via a reversal phase. However, the cellular and molecular mechanisms underlying bone remodelling failure after osteomyelitis remain elusive. MethodsTo elucidate the cellular and molecular mechanism underlying bone healing after osteomyelitis, we employed single-cell RNA sequencing (scRNA-seq) to depict the atlas of human cortical bone in normal, infected and reconstructed states. Dimensionality reduction by t-stochastic neighbourhood embedding (t-SNE) and graph-based clustering were applied to analyse the detailed clusters of osteoclast lineages. After trajectory analysis of osteoclast lineages over pseudotime, real-time PCR and immunofluorescence (IF) staining were applied to identify marker gene expression of various osteoclast lineages in the osteoclast induction model and human bone sections, respectively. The potential function and communication of osteoclasts were analysed via gene set enrichment analysis (GSEA) and CellChat. The chemotactic ability of mesenchymal stem cells (MSCs) and osteoclast lineage cells in various differentiation states was determined by transwell assays and coculture assays. The effects of various osteoclast lineages on the osteogenic differentiation potential of MSCs were also determined by using this coculture system. A normal mouse tibia fracture model and an osteomyelitis-related tibia fracture model were generated via injection of luciferase-labelled Staphylococcus aureus to verify the relationships between a novel osteoclast lineage and MSCs. Then, the infection was detected by a bioluminescence imaging system. Finally, immunofluorescence staining was used to detect the expression of markers of MSCs and novel osteoclast lineages in different remodelling phases in normal and infected bone remodelling models. ResultsIn this study, we constructed a cell atlas encompassing normal, infected, and reconstructed cortical bone. Then, we identified a novel subset at the earlier stage of the osteoclast lineage that exhibited increased expression of IDO1, CCL3, and CCL4. These IDO1highCCL3highCCL4high cells, termed osteostaticytes (OSCs), were further regarded as the reservoir of osteoclasts in the reversal phase. Notably, OSCs exhibited the highest chemotactic activity, surpassing other lineage subsets. We also discovered that cells at the earlier stage of the osteoclast lineage play a significant role in recruiting mesenchymal stem cells (MSCs). Finally, the data revealed that OSCs might be positively related to the occurrence of bone MSCs and the contribution of bone remodelling. ConclusionCollectively, our findings revealed a novel stage (OSC) within the osteoclast lineage, potentially representing elusive bone reversal cells due to its increased chemotactic ability towards MSCs and potential contribution to bone remodelling. This study provides valuable insights into the intricate mechanisms of the reversal phase during bone remodelling and unveils potential therapeutic strategies for diseases associated with bone uncoupling. Translational potential of this articleThis study identified a new subset, referred to as IDO1(plus symbol) CCL3(plus symbol) CCL4(plus symbol) osteostaticytes which displayed the highest chemotactic activity among all osteoclast lineages and may serve as reversal cells in bone remodelling. These findings offer new insights and insights for understanding bone reversal-related diseases and may serve as novel therapeutic targets for conditions such as osteomyelitis and delayed bone healing.

An efficient graph embedding clustering approach for heterogeneous network

An efficient graph embedding clustering approach for heterogeneous network

Clustering swap prediction for image-text pre-training

It is essential to delve into the strategy of multimodal model pre-training, which is an obvious impact on downstream tasks. Currently, clustering learning has achieved noteworthy benefits in multiple methods. However, due to the availability of open image-text pairs, it is challenging for multimodal with clustering learning. In this paper, we propose an approach that utilizes clustering swap prediction strategy to learn image-text clustering embedding space by interaction prediction between image and text features. Unlike existing models with clustering learning, our method (Clus) allows for an open number of clusters for web-scale alt-text data. Furthermore, in order to train the image and text encoders efficiently, we introduce distillation learning approach and evaluate the performance of the image-encoder in downstream visual tasks. In addition, Clus is pre-trained end-to-end by using large-scale image-text pairs. Specifically, both text and image serve as ground truth for swap prediction, enabling effective representation learning. Concurrently, extensive experiments demonstrate that Clus achieves state-of-the-art performance on multiple downstream fine-tuning and zero-shot tasks (i.e., Image-Text Retrieval, VQA, NLVR2, Image Captioning, Object Detection, and Semantic Segmentation).

Deep Batch Integration and Denoise of Single-Cell RNA-Seq Data.

Numerous single-cell transcriptomic datasets from identical tissues or cell lines are generated from different laboratories or single-cell RNA sequencing (scRNA-seq) protocols. The denoising of these datasets to eliminate batch effects is crucial for data integration, ensuring accurate interpretation and comprehensive analysis of biological questions. Although many scRNA-seq data integration methods exist, most are inefficient and/or not conducive to downstream analysis. Here, DeepBID, a novel deep learning-based method for batch effect correction, non-linear dimensionality reduction, embedding, and cell clustering concurrently, is introduced. DeepBID utilizes a negative binomial-based autoencoder with dual Kullback-Leibler divergence loss functions, aligning cell points from different batches within a consistent low-dimensional latent space and progressively mitigating batch effects through iterative clustering. Extensive validation on multiple-batch scRNA-seq datasets demonstrates that DeepBID surpasses existing tools in removing batch effects and achieving superior clustering accuracy. When integrating multiple scRNA-seq datasets from patients with Alzheimer's disease, DeepBID significantly improves cell clustering, effectively annotating unidentified cells, and detecting cell-specific differentially expressed genes.

Cluster Analysis of MSMES In Suleja, Nigeria: Insights From Fuzzy C-Means Clustering And T-SNE Visualizations

This study employs cluster analysis to segment Micro, Small, and Medium-sized Enterprises (MSMEs) in Suleja, Nigeria into distinct groups based on their financial and operational characteristics. We utilize Fuzzy C-Means Clustering and t-Distributed Stochastic Neighbor Embedding (t-SNE) visualizations to uncover hidden patterns and structures in the data. Our results reveal three distinct clusters, explaining 40.3% of the variance in the data (R² = 0.403). The clusters exhibit reasonable separation (Silhouette coefficient = 0.360) and distinct patterns in their variable means. Cluster 1 comprises high-performing MSMEs with high levels of engagement, participation, and satisfaction. Cluster 2 consists of low-performing MSMEs with low levels of engagement, participation, and satisfaction. Cluster 3 represents moderate-performing MSMEs with balanced levels of engagement, participation, and satisfaction. t-SNE visualizations confirm the clustering structure, revealing three distinct groups with varying densities and separation. The visualizations also highlight the relationships between the clusters, with Cluster 1 and Cluster 3 showing higher similarity than Cluster 2. Model performance metrics indicate a reasonable accuracy (Pearson's γ = 0.440) and a good balance between within-cluster sum of squares and between-cluster sum of squares (Calinski-Harabasz index = 13.087). The findings provide valuable insights for policymakers and practitioners seeking to support MSMEs in Nigeria. The results suggest that targeted interventions and support programs should focus on enhancing engagement, participation, and satisfaction among MSMEs, particularly for those in the low-performing cluster. The study contributes to the literature on MSMEs and cluster analysis, demonstrating the effectiveness of Fuzzy C-Means Clustering and t-SNE visualizations in uncovering meaningful patterns in MSMEs data.

One-step incremental multi-view spectral clustering based on graph linkage learning

Most traditional multi-view spectral clustering algorithms involve two separate steps: solving the spectral embedding matrix and clustering, which may introduce errors during the clustering process. Moreover, in practical applications, the number of available views may increase over time, and the approach of re-fusing all views in each computation would result in elevated computational costs. In this paper, we propose a novel model: One-step Incremental Multi-view Spectral Clustering based on Graph Linkage learning (OIMvSC). OIMvSC only needs to store the consensus spectral embedding matrix and the consensus label matrix of all previous views and combines them with the spectral embedding matrix of the newly available view to solve the fused consensus spectral embedding matrix and consensus label matrix. To further enhance clustering performance, OIMvSC introduces graph linkage learning, which reduces erroneous connections between clusters while preserving correct connections within clusters. A convergent iterative algorithm for solving OIMvSC is proposed. Experimental results demonstrate that OIMvSC exhibits excellent clustering performance.

Unsupervised structural damage identification based on covariance matrix and deep clustering

SummaryStructural damage identification is a major task in structural health monitoring. Machine learning and deep learning algorithms have been widely applied in the research of structural damage identification. Supervised algorithms require expert labeling, making it difficult to implement in engineering applications. Unsupervised structural damage identification algorithms are generally divided into two parts: damage‐sensitive factor extraction and damage determination. Existing algorithms all perform these two steps separately. This paper proposes a damage identification method combining covariance matrix and improved deep embedding clustering network (IDEC). IDEC can perform damage‐sensitive factor extraction and damage determination operations at the same time. The covariance matrix that introduces delay information contains rich damage features, and the combination of the two has been proven to effectively mine the damage‐sensitive feature space. After network hyperparameter optimization via Bayesian optimization, the proposed method is applied to the damage identification and quantification using real bridge acceleration response data under vehicle load. The results show that this method can identify structural damage with an accuracy of up to 97% with better performance than existing technologies, and it also has great performance in identifying small damages. The proposed method is expected to increase the damage identification accuracy if applied in engineering practice.

Attribute discrimination combined with selected sample dropout for unsupervised domain adaptive person re-identification

The popular clustering-based Unsupervised Domain Adaptive (UDA) person re-identification (re-ID) does not require additional annotation. However, owing to unsatisfactory feature embedding and imperfect clustering, most existing clustering-based methods suffer from the noise of pseudo labels in the target domain, which will lead to a serious performance degradation. To reduce the negative impact of noisy pseudo labels on training, we put forward an approach named selected sample dropout (SSD) in the training stage, which defines a criterion for evaluating the noise level of pseudo labels. SSD would mine and discard samples with noisy pseudo labels before training, and then all the remaining samples are fed into the network to train. On top of a strong baseline, SSD is proved to be effective. We call the baseline of adding SSD as the selected sample dropout-enhanced teacher-student network (SSD-TSNet). In addition, considering the robustness of pedestrian gender, we use it as auxiliary information in the SSD-TSNet test stage. Specifically, we propose a pedestrian gender attribute discriminator (GAD) to predict gender labels. Based on predictive gender labels, SSD-TSNet could retrieve one person among other persons with the same gender as the person, thus narrowing the search space of re-ID. The proposed SSD-TSNet and GAD are integrated into one framework, and extensive experiments on four widely used UDA benchmark protocols demonstrate its competitive performance. Specifically, our method outperforms the baseline by 11.6% mAP on the Duke-to-Market task, while surpassing the state-of-the-art method by 0.5% mAP on the Market-to-Duke task.

Deep Embedding Clustering Based onResidual Autoencoder

Clustering algorithm isone of the most widely used and influential analysis techniques.With the advent of deep learning, deep embedding clusteringalgorithms have rapidly evolved and yield promising results. Much ofthe success of these algorithms depends on the potential expressioncaptured by the autoencoder network. Therefore, the quality of thepotential expression directly determines the algorithm’sperformance. In view of this, researchers have proposed manyimprovements. Although the performance has been slightly improved,they all have one shortcoming, that is, too much emphasis is placedon the original data reconstruction ability during the process offeature expression, which greatly limits the further expression ofpotential features according to specific clustering tasks. Moreover,there is a large amount of noise in the original data, so blindlyemphasizing reconstruction will only backfire. Hence, weinnovatively propose a deep embedding clustering algorithm based onresidual autoencoder (DECRA) after in-depth research. Specifically,a novel autoencoder network with residual structure is proposed andintroduced into deep embedded clustering tasks. The networkintroduces an adaptive weight layer in feature representation z,which can make it have good robustness, generalization for specifictasks, and adaptive learning of better feature embeddings accordingto category classification. In this paper, the reasons for thevalidity of this structure are explained theoretically, andcomprehensive experiments on six benchmark datasets includingvarious types show that the clustering performance of the DECRA isvery competitive and significantly superior to the most advancedmethods.

Unveiling Water Allocation Dynamics: A Text Analysis of 25 Years of Stakeholder Meetings

Abstract Managing water resources in regions with high climate variability and frequent extreme weather events poses challenges for policymakers. To facilitate water allocation in these cases, participatory and collaborative decision-making approaches have become common. However, the evaluation of these approaches is hindered by the lack of structured methods and data to understand them. To address this knowledge gap, we propose a novel methodology that leverages text data to identify key topics, conflicts, and influential actors that shape water allocation dynamics. Our methodology is tested using records of 1020 water basin committee meetings held between 1997 and 2021 across twelve basin committees in Ceará, Brazil – a region known for its extensive history of droughts that have impacted water governance. To uncover key water management issues discussed during these meetings, we employed a three-step topic modeling framework: (1) sentence embedding, (2) dimensionality reduction, and (3) sentence clustering. Furthermore, we used entity recognition, dependency parsing, and network graphs to identify powerful actors influencing these meetings and, ultimately, the decisions taken. Our findings revealed stakeholders’ heightened concern for urban water supply over agricultural demand during droughts. We found that “reservoir operation” was the most recurring topic, especially in basins where the strategic reservoirs are located. Discussions related to “climate information” became significantly more important over time, which indicates that water allocation decisions are increasingly based on the seasonal forecast and data on oceanic indices provided by the meteorology agency. Despite the presence of local users in the committees, governmental representatives dominated the discussions and were central in all river basins. In conclusion, our proposed approach harnesses existing text data to uncover spatiotemporal patterns related to participatory water allocation. This study opens new avenues for investigating water governance using text-based analysis.

Graph embedding orthogonal decomposition: A synchronous feature selection technique based on collaborative particle swarm optimization

In unsupervised feature selection, the clustering label matrix has the ability to distinguish between projection clusters. However, the latent geometric structure of the clustering labels is often ignored. In addition, the optimal sub-feature selection performance of feature selection techniques relies greatly on the choice of balanced parameters, and the selection range of most technical parameters is limited and fixed. To solve the above-mentioned problems, this paper proposes a synchronous feature selection technique based on graph-embedded cluster label orthogonal decomposition and collaborative particle swarm optimization (GOD-cPSO). First, GOD-cPSO extends the feature selection framework of clustering label orthogonal decomposition by graph embedding to retain the latent geometric structure of clustering labels, thus maintaining the correlation between clustered sample labels. Then, the l2,1-2-norm with strong global convergence is extended to the graph embedding clustering label orthogonal decomposition framework. By imposing this non-convex constraint, GOD-cPSO can achieve low-dimensional sparse and low-redundant sub-features. In addition, the local structure preserving of low-dimensional manifolds is integrated into the graph-embedded clustering label orthogonal decomposition framework to obtain good cluster separation and effectively maintain the latent local structure of the data. Finally, to ensure the adaptive parameter selection over a large range, GOD-cPSO synchronously guides the graph-embedding clustering labeling orthogonal decomposition framework for feature selection through collaborative particle swarm optimization. GOD-cPSO has synchronous parameter optimization and feature selection and picks parameters in a larger range. Comprehensive numerical experiments are performed on nine datasets to test the validity of the GOD-cPSO. The experimental results demonstrate that the sub-features selected by the GOD-cPSO have stronger discriminative power and are superior to other techniques in the clustering assignments.

Application of clustering strategy for automatic segmentation of tissue regions in mass spectrometry imaging.

Mass spectrometry imaging (MSI) has been widely used in biomedical research fields. Each pixel in MSI consists of a mass spectrum that reflects the molecule feature of the tissue spot. Because MSI contains high-dimensional datasets, it is highly desired to develop computational methods for data mining and constructing tissue segmentation maps. To visualize different tissue regions based on mass spectrum features and improve the efficiency in processing enormous data, we proposed a computational strategy that consists of four procedures including preprocessing, data reduction, clustering, and quantitative validation. In this study, we examined the combination of t-distributed stochastic neighbor embedding (t-SNE) and hierarchical clustering (HC) for MSI data analysis. Using publicly available MSI datasets, one dataset of mouse urinary bladder, and one dataset of human colorectal cancer, we demonstrated that the generated tissue segmentation maps from this combination were superior to other data reduction and clustering algorithms. Using the staining image as a reference, we assessed the performance of clustering algorithms with external and internal clustering validation measures, including purity, adjusted Rand index (ARI), Davies-Bouldin index (DBI), and spatial aggregation index (SAI). The result indicated that SAI delivered excellent performance for automatic segmentation of tissue regions in MSI. We used a clustering algorithm to construct tissue automatic segmentation in MSI datasets. The performance was evaluated by comparing it with the stained image and calculating clustering validation indexes. The results indicated that SAI is important for automatic tissue segmentation in MSI, different from traditional clustering validation measures. Compared to the reports that used internal clustering validation measures such as DBI, our method offers more effective evaluation of clustering results for MSI segmentation. We envision that the proposed automatic image segmentation strategy can facilitate deep learning in molecular feature extraction and biomarker discovery for the biomedical applications of MSI.

Predicting the Fishery Ground of Jumbo Flying Squid (Dosidicus gigas) off Peru by Extracting Features of the Ocean Environment

We introduce a novel method that combines satellite data, advanced clustering techniques, machine learning feature extraction, and statistical models to enhance fishery forecasting accuracy. Focusing on jumbo flying squid in the southeast Pacific Ocean near Peru, we utilize MODIS-Aqua and MODIS-Terra satellite data on sea surface temperature (SST) to construct a deep convolutional embedded clustering (DCEC) model and extract the monthly SST features (FM) based on an optimized number of clusters determined by the Davies–Bouldi index (DBI). We use the extracted FM to construct a series of Generalized Additive Models (GAM) to forecast the catch per unit effort (CPUE) of jumbo flying squid within a spatial resolution of 0.5° × 0.5°. Our results demonstrate the following findings: (1) The SST feature clusters obtained through the DCEC model could capture the SST monthly variations; (2) The GAM models with FM outperform the models with the traditional monthly average SST in terms of predictive accuracy; (3) Using both FM and average SST together can further improve model performance. This study demonstrates the effectiveness of the DCEC combined with DBI in extracting marine environmental features and highlights the ocean environment feature extraction method to enhance the precision and reliability of fishery forecasting models.

An MIU-based deep embedded clustering model for urban functional zoning from remote sensing images and VGI data

Urban functional zoning offers valuable insights into urban morphology and sustainable development. However, the conventional fixed spatial units, such as blocks and grids, cannot easily capture the morphological characteristics inherent in functional union and separation during urban evolution. In this paper, by taking advantage of remote sensing images and geospatial big data, we propose a minimum identification unit (MIU)-based urban functional zoning model. This approach integrates the deep embedded clustering of buildings to generate the spatial unit segmentation, and then identifies the urban function by generating semantic vectors with the Word2Vec model. The effectiveness of the proposed method was tested in the city of Wuhan in China. The results highlight that MIUs provide a more flexible and suitable unit for segmenting urban functional zones compared to traditional street blocks. The proposed method is a feasible way to deal with the semantic redundancy of volunteered geographic information (VGI) data when identifying urban function, and the quality issue only has a significant impact on the minor functional types. Moreover, the building clustering results can effectively reveal the fine-scale urban structure, especially for the administration, manufacturing, and residential types. This demonstrates the potential of our approach in enhancing the understanding of urban morphology and supporting sustainable urban development.