Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa.

The growing urban population and traffic congestion underline the importance of building pedestrian-friendly environments to encourage walking as a preferred mode of transportation. However, a major challenge remains, which is the absence of such pedestrian-friendly walking environments. Identifying locations and routes with high pedestrian concentration is critical for improving pedestrian-friendly walking environments. This paper presents a quantitative method to map pedestrian walking behavior by utilizing real-time data from mobile phone sensors, focusing on the University of Moratuwa, Sri Lanka, as a case study. This holistic method integrates new urban data, such as location-based service (LBS) positioning data, and data clustering with unsupervised machine learning techniques. This study focused on the following three criteria for quantifying walking behavior: walking speed, walking time, and walking direction inside the experimental research context. A novel signal processing method has been used to evaluate speed signals, resulting in the identification of 622 speed clusters using K-means clustering techniques during specific morning and evening hours. This project uses mobile GPS signals and machine learning algorithms to track and classify pedestrian walking activity in crucial sites and routes, potentially improving urban walking through mapping.

Classification of Fashion Models' Walking Styles Using Publicly Available Data, Pose Detection Technology, and Multivariate Analysis: From Past to Current Trendy Walking Styles.

Understanding past and current trends is crucial in the fashion industry to forecast future market demands. This study quantifies and reports the characteristics of the trendy walking styles of fashion models during real-world runway performances using three cutting-edge technologies: (a) publicly available video resources, (b) human pose detection technology, and (c) multivariate human-movement analysis techniques. The skeletal coordinates of the whole body during one gait cycle, extracted from publicly available video resources of 69 fashion models, underwent principal component analysis to reduce the dimensionality of the data. Then, hierarchical cluster analysis was used to classify the data. The results revealed that (1) the gaits of the fashion models analyzed in this study could be classified into five clusters, (2) there were significant differences in the median years in which the shows were held between the clusters, and (3) reconstructed stick-figure animations representing the walking styles of each cluster indicate that an exaggerated leg-crossing gait has become less common over recent years. Accordingly, we concluded that the level of leg crossing while walking is one of the major changes in trendy walking styles, from the past to the present, directed by the world's leading brands.

Prospective Spatiotemporal Cluster Detection Using SaTScan: Tutorial for Designing and Fine-Tuning a System to Detect Reportable Communicable Disease Outbreaks.

Staff at public health departments have few training materials to learn how to design and fine-tune systems to quickly detect acute, localized, community-acquired outbreaks of infectious diseases. Since 2014, the Bureau of Communicable Disease at the New York City Department of Health and Mental Hygiene has analyzed reportable communicable diseases daily using SaTScan. SaTScan is a free software that analyzes data using scan statistics, which can detect increasing disease activity without a priori specification of temporal period, geographic location, or size. The Bureau of Communicable Disease's systems have quickly detected outbreaks of salmonellosis, legionellosis, shigellosis, and COVID-19. This tutorial details system design considerations, including geographic and temporal data aggregation, study period length, inclusion criteria, whether to account for population size, network location file setup to account for natural boundaries, probability model (eg, space-time permutation), day-of-week effects, minimum and maximum spatial and temporal cluster sizes, secondary cluster reporting criteria, signaling criteria, and distinguishing new clusters versus ongoing clusters with additional events. We illustrate how to support health equity by minimizing analytic exclusions of patients with reportable diseases (eg, persons experiencing homelessness who are unsheltered) and accounting for purely spatial patterns, such as adjusting nonparametrically for areas with lower access to care and testing for reportable diseases. We describe how to fine-tune the system when the detected clusters are too large to be of interest or when signals of clusters are delayed, missed, too numerous, or false. We demonstrate low-code techniques for automating analyses and interpreting results through built-in features on the user interface (eg, patient line lists, temporal graphs, and dynamic maps), which became newly available with the July 2022 release of SaTScan version 10.1. This tutorial is the first comprehensive resource for health department staff to design and maintain a reportable communicable disease outbreak detection system using SaTScan to catalyze field investigations as well as develop intuition for interpreting results and fine-tuning the system. While our practical experience is limited to monitoring certain reportable diseases in a dense, urban area, we believe that most recommendations are generalizable to other jurisdictions in the United States and internationally. Additional analytic technical support for detecting outbreaks would benefit state, tribal, local, and territorial public health departments and the populations they serve.

Ragas: integration and enhanced visualization for single cell subcluster analysis.

SUMMARY: Subcluster analysis is a powerful means to improve clustering and characterization of single cell RNA-Seq data. However, there are no existing tools to systematically integrate results from multiple subclusters, which creates hurdles for accurate data quantification, visualization, and interpretation in downstream analysis. To address this issue, we developed Ragas, an R package that integrates multi-level subclustering objects for streamlined analysis and visualization. A new data structure was implemented to seamlessly connect and assemble miscellaneous single cell analyses from different levels of subclustering, along with several new or enhanced visualization functions. Moreover, a re-projection algorithm was developed to integrate nearest-neighbor graphs from multiple subclusters in order to maximize their separability on the combined cell embeddings, which significantly improved the presentation of rare and homogeneous subpopulations. AVAILABILITY AND IMPLEMENTATION: The Ragas package and its documentation can be accessed through https://github.com/jig4003/Ragas and its source code is also available at https://zenodo.org/records/11244921.

scCross: efficient search for rare subpopulations across multiple single-cell samples.

MOTIVATION: Identifying rare cell types is an important task to capture the heterogeneity of single-cell data, such as scRNA-seq. The widespread availability of such data enables to aggregate multiple samples, corresponding for example to different donors, into the same study. Yet, such aggregated data is often subject to batch effects between samples. Clustering it therefore generally requires the use of data integration methods, which can lead to overcorrection, making the identification of rare cells difficult. We present scCross, a biclustering method identifying rare subpopulations of cells present across multiple single-cell samples. It jointly identifies a group of cells with specific marker genes by relying on a global sum criterion, computed over entire subpopulation of cells, rather than pairwise comparisons between individual cells. This proves robust with respect to the high variability of scRNA-seq data, in particular batch effects. RESULTS: We show through several case studies that scCross is able to identify rare subpopulations across multiple samples without performing prior data integration. Namely, it identifies a cilium subpopulation with potential new ciliary genes from lung cancer cells, which is not detected by typical alternatives. It also highlights rare subpopulations in human pancreas samples sequenced with different protocols, despite visible shifts in expression levels between batches. We further show that scCross outperforms typical alternatives at identifying a target rare cell type in a controlled experiment with artificially created batch effects. This shows the ability of scCross to efficiently identify rare cell subpopulations characterized by specific genes despite the presence of batch effects. AVAILABILITY AND IMPLEMENTATION: The R and Scala implementation of scCross is freely available on GitHub, at https://github.com/agerniers/scCross/. A snapshot of the code and the data underlying this article are available on Zenodo, at https://zenodo.org/doi/10.5281/zenodo.10471063.

[An identification method of chromatin topological associated domains based on spatial density clustering].

The rapid development of high-throughput chromatin conformation capture (Hi-C) technology provides rich genomic interaction data between chromosomal loci for chromatin structure analysis. However, existing methods for identifying topologically associated domains (TADs) based on Hi-C data suffer from low accuracy and sensitivity to parameters. In this context, a TAD identification method based on spatial density clustering was designed and implemented in this paper. The method preprocessed the raw Hi-C data to obtain normalized Hi-C contact matrix data. Then, it computed the distance matrix between loci, generated a reachability graph based on the core distance and reachability distance of loci, and extracted clustering clusters. Finally, it extracted TAD boundaries based on clustering results. This method could identify TAD structures with higher coherence, and TAD boundaries were enriched with more ChIP-seq factors. Experimental results demonstrate that our method has advantages such as higher accuracy and practical significance in TAD identification.

Identifying obesogenic environment through spatial clustering of body mass index among adults.

BACKGROUND: The escalating trend of obesity in Malaysia is surmounting, and the lack of evidence on the environmental influence on obesity is untenable. Obesogenic environmental factors often emerge as a result of shared environmental, demographic, or cultural effects among neighbouring regions that impact lifestyle. Employing spatial clustering can effectively elucidate the geographical distribution of obesity and pinpoint regions with potential obesogenic environments, thereby informing public health interventions and further exploration on the local environments. This study aimed to determine the spatial clustering of body mass index (BMI) among adults in Malaysia. METHOD: This study utilized information of respondents aged 18 to 59 years old from the National Health and Morbidity Survey (NHMS) 2014 and 2015 at Peninsular Malaysia and East Malaysia. Fast food restaurant proximity, district population density, and district median household income were determined from other sources. The analysis was conducted for total respondents and stratified by sex. Multilevel regression was used to produce the BMI estimates on a set of variables, adjusted for data clustering at enumeration blocks. Global Moran's I and Local Indicator of Spatial Association statistics were applied to assess the general clustering and location of spatial clusters of BMI, respectively using point locations of respondents and spatial weights of 8 km Euclidean radius or 5 nearest neighbours. RESULTS: Spatial clustering of BMI independent of individual sociodemographic was significant (p < 0.001) in Peninsular and East Malaysia with Global Moran's index of 0.12 and 0.15, respectively. High-BMI clusters (hotspots) were in suburban districts, whilst the urban districts were low-BMI clusters (cold spots). Spatial clustering was greater among males with hotspots located closer to urban areas, whereas hotspots for females were in less urbanized areas. CONCLUSION: Obesogenic environment was identified in suburban districts, where spatial clusters differ between males and females in certain districts. Future studies and interventions on creating a healthier environment should be geographically targeted and consider gender differences.

Clustering of Social Determinants of Health as an Indicator of Meaningful Subgroups within an African American Population: Application of Latent Class Analysis.

BACKGROUND: Health disparities between people who are African American (AA) versus their White counterparts have been well established, but disparities among AA people have not. The current study introduces a systematic method to determine subgroups within a sample of AA people based on their social determinants of health. METHODS: Health screening data collected in the West Side of Chicago, an underserved predominantly AA area, in 2018 were used. Exploratory latent class analysis was used to determine subgroups of participants based on their responses to 16 variables, each pertaining to a specific social determinant of health. RESULTS: Four unique clusters of participants were found, corresponding to those with "many unmet needs", "basic unmet needs", "unmet healthcare needs", and "few unmet needs". CONCLUSION: The findings support the utility of analytically determining meaningful subgroups among a sample of AA people and their social determinants of health. Understanding the differences within an underserved population may contribute to future interventions to eliminate health disparities.

Recognizing Patterns of Nature Contact Associated with Well-Being: An Exploratory Cluster Analysis.

Statement of Problem: Progressive urbanization has reduced human interactions with nature, raising concerns about its impact on mental well-being. Previous research has often focused on specific aspects of nature contact, neglecting its multifaceted dimensions and their effects on mental health, particularly in developing countries. Research Gap: There is a scarcity of studies exploring the comprehensive dimensions of nature contact, such as frequency, duration, intensity, and space naturalness, and their correlation with mental well-being in developing countries' urban settings. Purpose: This study aims to identify patterns of nature contact related to mental well-being in metropolitan areas of Brazil using exploratory cluster analysis, bridging the existing knowledge gap and informing targeted interventions to enhance mental health through nature contact. Method: An online survey collected data from 2136 participants in Brazil's metropolitan areas, focusing on their nature interaction patterns and mental health status using the Depression Anxiety and Stress Scale (DASS-21), hierarchical clustering with p-values via multiscale bootstrap resampling, and analysis of variance. Results and Conclusions: Three distinct groups were identified, showing varied patterns of nature contact and demographic profiles. Greater and more frequent nature contact was associated with lower levels of depression, anxiety, and stress. These findings suggest a beneficial relationship between nature contact and mental well-being. Practical Implications: The results underline the importance of urban planning and public health policies that facilitate access to natural spaces, highlighting socioeconomic factors as significant barriers to this access. Future Directions: Further research should explore causal relationships and consider the specific realities and challenges faced by residents of developing nations.

Parallel multi-criteria decision analysis for sub-national prioritization of zoonoses and animal diseases in Africa: The case of Cameroon.

The use of multi-criteria decision analysis (MCDA) for disease prioritization at the sub-national level in sub-Sahara Africa (SSA) is rare. In this research, we contextualized MCDA for parallel prioritization of endemic zoonoses and animal diseases in The Adamawa and North regions of Cameroon. MCDA was associated to categorical principal component analysis (CATPCA), and two-step cluster analysis. Six and seven domains made of 17 and 19 criteria (out of 70) respectively were selected by CATPCA for the prioritization of zoonoses and animal diseases, respectively. The most influencing domains were "public health" for zoonoses and "control and prevention" for animal diseases. Twenty-seven zoonoses and 40 animal diseases were ranked and grouped in three clusters. Sensitivity analysis resulted in high correlation between complete models and reduced models showing the robustness of the simplification processes. The tool used in this study can be applied to prioritize endemic zoonoses and transboundary animal diseases in SSA at the sub-national level and upscaled at the national and regional levels. The relevance of MCDA is high because of its contextualization process and participatory nature enabling better operationalization of disease prioritization outcomes in the context of African countries or other low and middle-income countries.

Analysis of genetic diversity and population structure of some Ethiopian barley (Hordeum vulgare L.) accessions using SSR markers.

Understanding the genetic diversity of existing genetic resources at the DNA level is an effective approach for germplasm conservation and utilization in breeding programs. However, the patterns of genetic diversity and population structure remain poorly characterized, making germplasm conservation and breeding efforts difficult to succeed. Thus, this study is aimed to evaluate the genetic diversity and population structure of 49 barley accessions collected from different geographic origins in Ethiopia. Twelve SSR markers were used to analyze all accessions and a total of 61 alleles were found, with a mean of 5.08 alleles per locus. The analysis pointed out the existence of moderate to high values of polymorphic information content ranging from 0.39 to 0.91 and the mean Shannon diversity index(I) was 1.25, indicating that they were highly informative markers. The highest Euclidean distance (1.32) was computed between accession 9950 and two accessions (247011 and 9949), while the lowest Euclidean distance (0.00) was estimated between accessions 243191 and 243192. The result of molecular variance analysis revealed that the highest variation was found among accessions (47) relative to within accessions (44) and among geographic origins (9). Cluster analysis grouped the 49 barley accessions into three major clusters regardless of their geographic origin which could be due to the presence of considerable gene flow (2.72). The result of the STRUCTURE analysis was consistent with neighbor-joining clustering and principal coordinate analysis. Generally, this study concluded that the variation among accessions was more important than the difference in geographical regions to develop an appropriate conservation strategy and for parental selection to use in breeding programs. This information will be helpful for barley conservation and breeding, and it may speed up the development of new competing barley varieties.

Protein family annotation for the Unified Human Gastrointestinal Proteome by DPCfam clustering.

Technological advances in massively parallel sequencing have led to an exponential growth in the number of known protein sequences. Much of this growth originates from metagenomic projects producing new sequences from environmental and clinical samples. The Unified Human Gastrointestinal Proteome (UHGP) catalogue is one of the most relevant metagenomic datasets with applications ranging from medicine to biology. However, the low levels of sequence annotation may impair its usability. This work aims to produce a family classification of UHGP sequences to facilitate downstream structural and functional annotation. This is achieved through the release of the DPCfam-UHGP50 dataset containing 10,778 putative protein families generated using DPCfam clustering, an unsupervised pipeline grouping sequences into single or multi-domain architectures. DPCfam-UHGP50 considerably improves family coverage at protein and residue levels compared to the manually curated repository Pfam. In the hope that DPCfam-UHGP50 will foster future discoveries in the field of metagenomics of the human gut, we release a FAIR-compliant database of our results that is easily accessible via a searchable web server and Zenodo repository.

Cluster analysis of cancer knowledge, attitudes and behaviors in the Moroccan population.

BACKGROUND: Cancer has become a major health concern due to the increasing morbidity and mortality rates, and its negative social, economic consequences and the heavy financial burden incurred by cancer patients. About 40% of cancers are preventable. The aim of this study was to assess the knowledge, attitudes, and practices regarding cancer prevention, and associated characteristics to inform the development of targeted cancer prevention campaigns and policies. METHODS: We conducted a cross-sectional survey of adult patients at Mohamed Sekkat and Sidi Othmane Hospitals in Casablanca, Morocco. Data collection was conducted by two trained interviewers who administered the questionnaire in-person in the local language. An unsupervised clustering approach included 17 candidate variables for the cluster analysis. The variables covered a wide range of characteristics, including demographics, health perceptions and attitudes. Survey answers were calculated to compose qualitative ordinal categories, including a cancer attitude score and knowledge score. RESULTS: The cluster-based analysis showed that participants in cluster 1 had the highest mean attitude score (13.9 ± 2.15) and percentage of individuals with a high level of knowledge (50.8%) whereas the lowest mean attitude score (9.48 ± 2.02) and knowledge level (7.5%.) were found in cluster 3. The participants with the lowest cancer attitude scores and knowledge levels were aged 34 to 47 years old (middle age group), predominantly females, living in rural settings, and were least likely to report health professionals as a source of health information. CONCLUSIONS: The findings showed that female individuals living in rural settings, belonging to an older age group, who were least likely to use health professionals as an information source had the lowest levels of knowledge and attitudes. These groups are amenable to targeted and tailored interventions aiming to modify their understanding of cancer in order to enhance the outcomes of Morocco's on-going efforts in cancer prevention and control strategies.

The intervention of local public authorities and the impact of the COVID-19 pandemic in Romania: a subnational analysis.

The COVID-19 pandemic had a strong territorial dimension, with a highly asymmetric impact among Romanian counties, depending on pre-existing vulnerabilities, regions' economic structure, exposure to global value chains, specialization, and overall ability to shift a large share of employees to remote working. The aim of this paper is to assess the role of Romanian local authorities during this unprecedented global medical emergency by capturing the changes of public spending at the local level between 2010 and 2021 and amid the COVID-19 pandemic, and to identify clusters of Romanian counties that shared similar characteristics in this period, using a panel data quantitative model and hierarchical cluster analysis. Our empirical analysis shows that between 2010-2021, the impact of social assistance expenditures was higher than public investment (capital spending and EU funds) on the GDP per capita at county level. Additionally, based on various macroeconomic and structural indicators (health, labour market performance, economic development, entrepreneurship, and both local public revenues and several types of expenditures), we determined seven clusters of counties. The research contributes to the discussion regarding the increase of economic resilience but also to the evidence-based public policies implementation at local level.

Investigating the temporal dynamics of motor vehicle collision density patterns in urban road networks - A case study of New York.

INTRODUCTION: Motor vehicle collisions are a leading source of mortality and injury on urban highways. From a temporal perspective, the determination of a road segment as being collision-prone over time can fluctuate dramatically, making it difficult for transportation agencies to propose traffic interventions. However, there has been limited research to identify and characterize collision-prone road segments with varying collision density patterns over time. METHOD: This study proposes an identification and characterization framework that profiles collision-prone roads with various collision density variations. We first employ the spatio-temporal network kernel density estimation (STNKDE) method and time-series clustering to identify road segments with different collision density patterns. Next, we characterize collision-prone road segments based on spatio-temporal information, consequences, vehicle types, and contributing factors to collisions. The proposed method is applied to two-year motor vehicle collision records for New York City. RESULTS: Seven clusters of road segments with different collision density patterns were identified. Road segments frequently determined as collision-prone were primarily found in Lower Manhattan and the center of the Bronx borough. Furthermore, collisions near road segments that exhibit greater collision densities over time result in more fatalities and injuries, many of which are caused by both human and vehicle factors. CONCLUSIONS: Collision-prone road segments with various collision density patterns over time have distinct differences in the spatio-temporal domain and the collisions that occur on them. PRACTICAL APPLICATIONS: The proposed method can help policymakers understand how collision-prone road segments change over time, and can serve as a reference for more targeted traffic treatment.

iIMPACT: integrating image and molecular profiles for spatial transcriptomics analysis.

Current clustering analysis of spatial transcriptomics data primarily relies on molecular information and fails to fully exploit the morphological features present in histology images, leading to compromised accuracy and interpretability. To overcome these limitations, we have developed a multi-stage statistical method called iIMPACT. It identifies and defines histology-based spatial domains based on AI-reconstructed histology images and spatial context of gene expression measurements, and detects domain-specific differentially expressed genes. Through multiple case studies, we demonstrate iIMPACT outperforms existing methods in accuracy and interpretability and provides insights into the cellular spatial organization and landscape of functional genes within spatial transcriptomics data.

DCRELM: dual correlation reduction network-based extreme learning machine for single-cell RNA-seq data clustering.

Single-cell ribonucleic acid sequencing (scRNA-seq) is a high-throughput genomic technique that is utilized to investigate single-cell transcriptomes. Cluster analysis can effectively reveal the heterogeneity and diversity of cells in scRNA-seq data, but existing clustering algorithms struggle with the inherent high dimensionality, noise, and sparsity of scRNA-seq data. To overcome these limitations, we propose a clustering algorithm: the Dual Correlation Reduction network-based Extreme Learning Machine (DCRELM). First, DCRELM obtains the low-dimensional and dense result features of scRNA-seq data in an extreme learning machine (ELM) random mapping space. Second, the ELM graph distortion module is employed to obtain a dual view of the resulting features, effectively enhancing their robustness. Third, the autoencoder fusion module is employed to learn the attributes and structural information of the resulting features, and merge these two types of information to generate consistent latent representations of these features. Fourth, the dual information reduction network is used to filter the redundant information and noise in the dual consistent latent representations. Last, a triplet self-supervised learning mechanism is utilized to further improve the clustering performance. Extensive experiments show that the DCRELM performs well in terms of clustering performance and robustness. The code is available at https://github.com/gaoqingyun-lucky/awesome-DCRELM .

Estimating dengue burden among family contacts through cluster investigation around probable cases in 2022 and 2023 in the Central Region, Burkina Faso.

BACKGROUND: In 2023, Burkina Faso experienced the largest dengue epidemic ever in Africa. This study aimed to estimate the prevalence of symptomatic, subclinical, and asymptomatic dengue and determine the associated factors among adult contacts of dengue in the Central Region, Burkina Faso. METHODS: This cross-sectional study included contacts of dengue probable cases through cluster sampling in 2022-2023. These suspected cases that tested positive were identified from the five health facilities (Pissy CMA, Saaba CM, Kossodo CMA, Samandin CM, and Marcoussis CSPS) that reported the highest number of cases in 2021 per district. All participants underwent dengue and malaria rapid diagnostic tests (RDT). Samples positive for non-structural 1 protein antigen (AgNS1) and/or immunoglobulin M (IgM) were tested for serotype detection by reverse transcription polymerase chain reaction (RT-PCR). Binary logistic regression was done to identify the determinants of asymptomatic, subclinical, and symptomatic dengue among contacts of probable dengue cases. RESULTS: A total of 484 contacts were included, mostly in 2023 (75.2%). Most participants were females (58.6%), residing (24.3%) and passing their daytime (23.1%) in Saaba. The overall prevalence of dengue was estimated at 15.1% [95% confidence interval (CI): 12.0-18.6%], representing cases not seeking care in hospitals. Asymptomatic cases represented 2.9% (95% CI: 1.6-4.8%). Subclinical and symptomatic cases accounted for 6.0% (95% CI: 4.1-8.5%) and 6.2% (95% CI: 4.2-8.7%), respectively. Of the 58 samples tested by RT-PCR, 10 were confirmed for serotype 3 in 2023. Malaria cases were estimated at 5.6% (95% CI: 3.7-8.0%). After adjustment, participants claiming that a virus transmits dengue were likelier to have asymptomatic dengue [adjusted odds ratio (aOR) = 7.1, 95% CI: 2.4-21.0]. From the multivariable analysis, subclinical dengue was statistically associated with being included in the study in 2023 (aOR = 30.2, 95% CI: 2.0-455.5) and spending the daytime at Arrondissement 4 (aOR = 11.5, 95% CI: 1.0-131.0). After adjustment, symptomatic dengue was associated with living less than 50 m away from cultivated land (aOR = 2.8, 95% CI: 1.1-6.9) and living less than 50 m from a stretch of water (aOR = 0.1, 95% CI: 0.0-0.6). CONCLUSIONS: The overall burden of dengue among populations not seeking care in hospitals was quite high, with few asymptomatic cases. Efforts to manage dengue cases should also target non-hospital cases and raise population awareness. The 2023 epidemic could be due to dengue virus (DENV)-3.

Research on load clustering algorithm based on variational autoencoder and hierarchical clustering.

Time series data complexity presents new challenges in clustering analysis across fields such as electricity, energy, industry, and finance. Despite advances in representation learning and clustering with Variational Autoencoders (VAE) based deep learning techniques, issues like the absence of discriminative power in feature representation, the disconnect between instance reconstruction and clustering objectives, and scalability challenges with large datasets persist. This paper introduces a novel deep time series clustering approach integrating VAE with metric learning. It leverages a VAE based on Gated Recurrent Units for temporal feature extraction, incorporates metric learning for joint optimization of latent space representation, and employs the sum of log likelihoods as the clustering merging criterion, markedly improving clustering accuracy and interpretability. Experimental findings demonstrate a 27.16% improvement in average clustering accuracy and a 47.15% increase in speed on industrial load data. This study offers novel insights and tools for the thorough analysis and application of time series data, with further exploration of VAE's potential in time series clustering anticipated in future research.

YOLO-ISTD: An infrared small target detection method based on YOLOv5-S.

Infrared target detection is widely used in industrial fields, such as environmental monitoring, automatic driving, etc., and the detection of weak targets is one of the most challenging research topics in this field. Due to the small size of these targets, limited information and less surrounding contextual information, it increases the difficulty of target detection and recognition. To address these issues, this paper proposes YOLO-ISTD, an improved method for infrared small target detection based on the YOLOv5-S framework. Firstly, we propose a feature extraction module called SACSP, which incorporates the Shuffle Attention mechanism and makes certain adjustments to the CSP structure, enhancing the feature extraction capability and improving the performance of the detector. Secondly, we introduce a feature fusion module called NL-SPPF. By introducing an NL-Block, the network is able to capture richer long-range features, better capturing the correlation between background information and targets, thereby enhancing the detection capability for small targets. Lastly, we propose a modified K-means clustering algorithm based on Distance-IoU (DIoU), called K-means_DIOU, to improve the accuracy of clustering and generate anchors suitable for the task. Additionally, modifications are made to the detection heads in YOLOv5-S. The original 8, 16, and 32 times downsampling detection heads are replaced with 4, 8, and 16 times downsampling detection heads, capturing more informative coarse-grained features. This enables better understanding of the overall characteristics and structure of the targets, resulting in improved representation and localization of small targets. Experimental results demonstrate significant achievements of YOLO-ISTD on the NUST-SIRST dataset, with an improvement of 8.568% in mAP@0.5 and 8.618% in mAP@0.95. Compared to the comparative models, the proposed approach effectively addresses issues of missed detections and false alarms in the detection results, leading to substantial improvements in precision, recall, and model convergence speed.