Contextual Features Research Articles

A computationally efficient method for induction motor bearing fault detection based on parallel convolutions and semi-supervised GAN

ABSTRACT Accurate and timely bearing fault detection is imperative for optimal system functioning and the implementation of preventative maintenance measures. Deep learning models provide viable solutions to these malfunctions, however, the lack of labelled data makes the training both expensive and cumbersome. To remedy this, various semi-supervised approaches have surfaced in the last decade, significantly mitigating the need for extensive labelled data but with added computational cost. This study proposes one such approach by leveraging generative adversarial networks (GAN) trained on a time-frequency based representation. The proposed Parallel Convolutions Semi-Supervised GAN, namely PC-SSGAN, uses bottleneck parallel convolutions blocks to capture multi-scale features in both local and global contexts, lacing both the generator and discriminator with enhanced feature extraction capabilities and simultaneously reducing the parameters and training time. The Proposed framework is evaluated on two distinct open-source datasets. The classification accuracy for both models exceeded 99.50%. Moreover, the proposed parallel convolutions-based architecture spent approximately 33% less time on training than the normal convolutional layers. It has been foreseen that the proposed fault detection system can be integrated into the motor fault tolerant control system to produce a unified framework that can make informed decisions to handle the bearing faults effectively.

Contextual factors that influence adoption and sustainment of self-management support in cancer survivorship care: a practical application of theory with qualitative interviews

BackgroundSelf-management support (SMS) is a recommended component of cancer survivorship care that improves health-related quality of life and reduces healthcare utilisation. However, widespread implementation has been difficult to achieve, with a gap in the literature on system-wide implementation efforts. This study examines contextual factors perceived to influence SMS adoption and sustainment in cancer centres in the Republic of Ireland.MethodSemistructured interviews were conducted with 47 key informants from 20 cancer organisations across community and hospital settings. Participants were asked to report the level of adoption and sustainment of SMS at their organisation. This information was used to categorise organisations as low, medium or high implementers. We conducted cross-case analysis following the principles of Framework Analysis. Using the Consolidated Framework for Implementation Research as a menu of constructs, we examined factors influencing adoption and sustainment and variation in levels of implementation.ResultsNational policy, external accreditation, external financing opportunities and the presence of champions in organisations are influential early in the implementation process driving adoption. Healthcare provider-led programmes and evidence of SMS improving patient outcomes and aligning with an organisation’s priorities are necessary to secure buy-in, particularly among senior leadership. An organisational culture of entrepreneurship enables adoption and sustainment, with resources and a culture supporting staff well-being enabling sustainment.ConclusionWhile national policy is a driver, additional factors related to programme attributes and local contextual features such as the presence of champions, organisational readiness and culture influence implementation. The results may be used for future evaluations of SMS implementation in cancer survivorship care and to inform the development of tailored implementation strategies.

Personalised monitoring and feedback on risk-relevant features in forensic case formulation: a series of case-studies in men who have committed sexual offences

ABSTRACT The current study investigated to what extent personalised information on interrelated risk-relevant behavioural, psychological, and contextual features obtained using experience sampling method (ESM) can be deployed to inform forensic case formulations of adult men with a history of sexual offences. Five adult men in outpatient forensic treatment for committing sexual offences monitored personal risk-relevant features using ESM and discussed the resulting feedback report with their therapist. Data were collected using the Twente engagement with Ehealth technologies Scale, an online questionnaire, a semi-structured interview and log data. Participants reported increased awareness of personal patterns of risk-relevant features and their possible association with the risk of sexual reoffending. The participants did not perceive the ESM procedure as burdensome or intrusive. Obtaining personalised information on risk-relevant features by ESM was feasible and achievable for adult men with a history of sexual offences. Insights derived from ESM measurements could enhance traditional forensic case formulation. PRACTICE IMPACT STATEMENT Combining experience sampling method (ESM) and traditional forensic case formulation can help adult men with a history of sexual offences to better understand patterns in their risk-relevant characteristics. A more thorough understanding of such patterns may improve treatment plans focused on desistance of sexual reoffending.

Leveraging meditation research for the study of psychedelic-related adverse effects

Psychedelics have shown early evidence for a range of benefits and low harm profiles in extant research. However, adverse effects (AEs) research in psychedelics has been limited, leading to underspecified AE profiles, inconsistent measurement, and potential undercounting of AEs. The development of safe, effective psychedelic therapies and treatments for AEs when they occur requires a thorough assessment of psychedelic-related AEs, their phenomenology, risk factors, and longitudinal duration. This article proposes that research on meditation-related AEs, which overlap in important ways with the phenomenological and contextual characteristics of psychedelic-related AEs, has engaged many methodological challenges present in the study of psychedelic-related AEs. Thus, meditation-related AE research offers thematic and methodological insights that are valuable to psychedelic AE research. An integrative review of extant AE research in both psychedelics and meditation is provided, and an agenda for leveraging meditation research to advance the investigation of psychedelic AEs is recommended. This includes the utility of meditation-related AEs as a comparator condition for psychedelic-related AEs, as well as recommendations for the adoption of (1) detailed and comprehensive, (2) user-informed, (3) impact-based, (4) standardized, (5) unbiased, and (6) representative measures of AEs and (7) examining factors that influence their impacts and trajectories.

Signals in the Cells: Multimodal and Contextualized Machine Learning Foundations for Therapeutics.

Drug discovery AI datasets and benchmarks have not traditionally included single-cell analysis biomarkers. While benchmarking efforts in single-cell analysis have recently released collections of single-cell tasks, they have yet to comprehensively release datasets, models, and benchmarks that integrate a broad range of therapeutic discovery tasks with cell-type-specific biomarkers. Therapeutics Commons (TDC-2) presents datasets, tools, models, and benchmarks integrating cell-type-specific contextual features with ML tasks across therapeutics. We present four tasks for contextual learning at single-cell resolution: drug-target nomination, genetic perturbation response prediction, chemical perturbation response prediction, and protein-peptide interaction prediction. We introduce datasets, models, and benchmarks for these four tasks. Finally, we detail the advancements and challenges in machine learning and biology that drove the implementation of TDC-2 and how they are reflected in its architecture, datasets and benchmarks, and foundation model tooling.

In Search of Deliberate Practice: Simulating Teaching in Three Teacher Education Programs

Background: Mixed reality simulations (MRSs) offer a platform for novice teachers to practice teaching in the absence of real children. Though prior research suggests simulated practice can be beneficial for novice teachers, these studies describe widely varying designs and implementations across teacher education programs (TEPs). As such, we lack clarity about the relative benefits of different approaches to simulated practice for novices who are entering teaching via a growing array of pathways. Purpose: To better understand the influence of context on novice teachers’ experiences in simulations, we conducted a study of three teacher education programs that used simulations as a component of their teacher education curriculum. Specifically, we asked the following research questions: How do novices in three differently structured TEPs experience a series of parallel practice opportunities in MRSs? What contextual features into, through, and beyond the approximation contribute to variation, if any, in novices’ experiences of practice in MRSs? Research Design: This mixed methods study leverages postsimulation survey data from novices ( n = 160) in three TEPs to understand how they experienced a parallel series of simulation tasks paired with support in the form of coaching or self-reflection. We elaborate on survey findings with qualitative analysis of each teacher education program and interviews with a purposive sample of participants from each program ( n = 15). Conclusions: Findings highlight the influence of context and supports on novices’ simulation experiences. In particular, the sequencing of practice with other preparatory opportunities into and beyond the approximation, as well as the provision of feedback and level of challenge through the practice can promote more useful practice opportunities in teacher education.

ASSESSMENT OF THE QUALITY OF LEISURE PARKS USING THE IPA-KANO INTEGRATIVE APPROACH TO SATISFACTION, CASE TITO PARK, ALGERIA

Leisure parks provide innumerable benefits in terms of social well-being and economic advantages, hence the importance for managers to assess their condition and determine the beneficial actions to be taken. The physical and functional attributes of parks are key indicators of quality; especially, if they are inspected from the perspective of user satisfaction. Although previous studies have incorporated satisfaction, few have used management tools together in developing countries. This paper proposes the simultaneous use of importance-performance analysis (IPA) and the Kano model as an integrative approach to satisfaction to assess the quality of recreational parks. Tito Park in Algiers used as a case study, was the subject of two methods: first qualitative-exploratory by 116 interviews (2016-2017) on the sociocultural variables of visitors, and quantitative-empirical by IPA-Kano statistical analysis against 36 attributes hierarchized in 7 families of quality criteria. The results reveal a divergence of visitors' opinions against these attributes within the same family of criteria; this is reinforced by a disparity between the degrees of importance and satisfaction that users allocate to them. This research offers a pragmatic tool to help with targeted and optimized decision-making and design as a means of requalification of the landscape. Because it elucidates the state of the recreational offer and points out the contextual characteristics to be promoted in order of priority by integrating the dimensions: perceptual and time. In the future, two or more parks can be compared using these or other tools by aggregating more attributes.

Travel route recommendation with a trajectory learning model

This study addresses a critical issue in location-based services: travel route recommendation. It leverages historical trajectory data to predict the actual route on a road network from a starting point to a destination, given a specific departure time. However, capturing the latent patterns in complex trajectory data for accurate route planning presents a significant challenge. Existing route recommendation methods commonly face two major problems: first, inadequate integration of multi-source data, which fails to fully consider the potential factors affecting route choice; and second, limited capability to capture road network characteristics, which restricts the effective application of node features and negatively impacts recommendation accuracy. To address these issues, this research introduces a Trajectory Learning Model for Route Recommendation (TLMR) based on deep learning techniques. TLMR enhances the understanding of user route choice behavior in complex environments by integrating multi-source data. Moreover, by incorporating road network features, TLMR more effectively captures and utilizes the structural and dynamic information of the road network. Specifically, TLMR first employs a Position-aware Graph Neural Network to learn features of intersections from the road network, incorporating context features like weather and traffic conditions. Then, it integrates this information through neural networks to predict the next intersection. Finally, a beam search algorithm is applied to generate and recommend multiple candidate routes. Extensive experiments on four large real-world datasets demonstrate that TLMR outperforms existing methods in four key performance metrics. These results prove the effectiveness and superiority of TLMR in route recommendation.

A Novel Hybrid Model for Automatic Non-Small Cell Lung Cancer Classification Using Histopathological Images

Background/Objectives: Despite recent advances in research, cancer remains a significant public health concern and a leading cause of death. Among all cancer types, lung cancer is the most common cause of cancer-related deaths, with most cases linked to non-small cell lung cancer (NSCLC). Accurate classification of NSCLC subtypes is essential for developing treatment strategies. Medical professionals regard tissue biopsy as the gold standard for the identification of lung cancer subtypes. However, since biopsy images have very high resolutions, manual examination is time-consuming and depends on the pathologist’s expertise. Methods: In this study, we propose a hybrid model to assist pathologists in the classification of NSCLC subtypes from histopathological images. This model processes deep, textural and contextual features obtained by using EfficientNet-B0, local binary pattern (LBP) and vision transformer (ViT) encoder as feature extractors, respectively. In the proposed method, each feature matrix is flattened separately and then combined to form a comprehensive feature vector. The feature vector is given as input to machine learning classifiers to identify the NSCLC subtype. Results: We set up 13 different training scenarios to test 4 different classifiers: support vector machine (SVM), logistic regression (LR), light gradient boosting machine (LightGBM) and extreme gradient boosting (XGBoost). Among these scenarios, we obtained the highest classification accuracy (99.87%) with the combination of EfficientNet-B0 + LBP + ViT Encoder + SVM. The proposed hybrid model significantly enhanced the classification accuracy of NSCLC subtypes. Conclusions: The integration of deep, textural, and contextual features assisted the model in capturing subtle information from the images, thereby reducing the risk of misdiagnosis and facilitating more effective treatment planning.

GPS-pPLM: A Language Model for Prediction of Prokaryotic Phosphorylation Sites

In the prokaryotic kingdom, protein phosphorylation serves as one of the most important posttranslational modifications (PTMs) and is involved in orchestrating a broad spectrum of biological processes. Here, we report an updated online server named the group-based prediction system for prokaryotic phosphorylation language model (GPS-pPLM), used for predicting phosphorylation sites (p-sites) in prokaryotes. For model training, two deep learning methods, a transformer and a deep neural network, were employed, and a total of 10 sequence features and contextual features were integrated. Using 44,839 nonredundant p-sites in 16,041 proteins from 95 prokaryotes, two general models for the prediction of O-phosphorylation and N-phosphorylation were first pretrained and then fine-tuned to construct 6 predictors specific for each phosphorylatable residue type as well as 134 species-specific predictors. Compared with other existing tools, the GPS-pPLM exhibits higher accuracy in predicting prokaryotic O-phosphorylation p-sites. Protein sequences in FASTA format or UniProt accession numbers can be submitted by users, and the predicted results are displayed in tabular form. In addition, we annotate the predicted p-sites with knowledge from 22 public resources, including experimental evidence, 3D structures, and disorder tendencies. The online service of the GPS-pPLM is freely accessible for academic research.

BreakNet: discontinuity-resilient multi-scale transformer segmentation of retinal layers

Visible light optical coherence tomography (vis-OCT) is gaining traction for retinal imaging due to its high resolution and functional capabilities. However, the significant absorption of hemoglobin in the visible light range leads to pronounced shadow artifacts from retinal blood vessels, posing challenges for accurate layer segmentation. In this study, we present BreakNet, a multi-scale Transformer-based segmentation model designed to address boundary discontinuities caused by these shadow artifacts. BreakNet utilizes hierarchical Transformer and convolutional blocks to extract multi-scale global and local feature maps, capturing essential contextual, textural, and edge characteristics. The model incorporates decoder blocks that expand pathways to enhance the extraction of fine details and semantic information, ensuring precise segmentation. Evaluated on rodent retinal images acquired with prototype vis-OCT, BreakNet demonstrated superior performance over state-of-the-art segmentation models, such as TCCT-BP and U-Net, even when faced with limited-quality ground truth data. Our findings indicate that BreakNet has the potential to significantly improve retinal quantification and analysis.

MFHARFNet: multi-branch feature hybrid and adaptive receptive field network for image segmentation

Abstract Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model’s adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.

Variational Type Graph Autoencoder For Denoising On Event Recommendation

Recommendations for events play a pivotal role in facilitating the discovery of upcoming intriguing events within Event-Based Social Networks (EBSNs). Previous research has established the crucial significance of mining contextual features and implicit relationships to enhance recommendation performance and alleviate data sparsity issues. However, the noise inherent in contextual features exacerbates data sparsity and hampers the ability of previous methods to explore implicit relationships for mitigating data sparsity. To address this challenge, we propose a variational type graph autoencoder model that attenuates the influence of noise in different types of context features by introducing type-specific latent variables. Firstly, we introduce a heterogeneous denoising convolution module composed of two components: 1) Denoising attention aggregation is proposed to mitigate the influence of noisy structures and uncover implicit relationships. 2) A heterogeneous normalization module leverages context features within the same type to alleviate the effects of noise in context features and data sparsity. Furthermore, we propose a learnable heterogeneous mixture prior that assists in assigning different priors to distinct types of latent variables, effectively modeling different types of contextual features. Through comprehensive experiments conducted on real-world datasets, we demonstrate the compelling performance of our model compared to state-of-the-art competitive approaches.

Uncovering Key Factors That Drive the Impressions of Online Emerging Technology Narratives

Social media platforms play a significant role in facilitating business decision making, especially in the context of emerging technologies. Such platforms offer a rich source of data from a global audience, which can provide organisations with insights into market trends, consumer behaviour, and attitudes towards specific technologies, as well as monitoring competitor activity. In the context of social media, such insights are conceptualised as immediate and real-time behavioural responses measured by likes, comments, and shares. To monitor such metrics, social media platforms have introduced tools that allow users to analyse and track the performance of their posts and understand their audience. However, the existing tools often overlook the impact of contextual features such as sentiment, URL inclusion, and specific word use. This paper presents a data-driven framework to identify and quantify the influence of such features on the visibility and impact of technology-related tweets. The quantitative analysis from statistical modelling reveals that certain content-based features, like the number of words and pronouns used, positively correlate with the impressions of tweets, with increases of up to 2.8%. Conversely, features such as the excessive use of hashtags, verbs, and complex sentences were found to decrease impressions significantly, with a notable reduction of 8.6% associated with tweets containing numerous trailing characters. Moreover, the study shows that tweets expressing negative sentiments tend to be more impressionable, likely due to a negativity bias that elicits stronger emotional responses and drives higher engagement and virality. Additionally, the sentiment associated with specific technologies also played a crucial role; positive sentiments linked to beneficial technologies like data science or machine learning significantly boosted impressions, while similar sentiments towards negatively viewed technologies like cyber threats reduced them. The inclusion of URLs in tweets also had a mixed impact on impressions—enhancing engagement for general technology topics, but reducing it for sensitive subjects due to potential concerns over link safety. These findings underscore the importance of a strategic approach to social media content creation, emphasising the need for businesses to align their communication strategies, such as responding to shifts in user behaviours, new demands, and emerging uncertainties, with dynamic user engagement patterns.

An Analysis of Contextual Factors Influencing women's Candidacy in Local Elections: Insights From Italy

ABSTRACTExtensive research showed that the gender gap in electoral participation, both active and passive, is linked to cultural and socio‐economic aspects that can combine in diverse ways across different territories, leading to regional disparities. The present study analyzes how such heterogeneity in cultural and socio‐economic conditions interacts with the level of female participation in political competition in Italy, as measured by the proportion of female candidates in municipal elections from 2009 to 2016. Focusing on the gender dimension of candidacy in local elections, the study investigates its territorial determinants, particularly the role of the social and economic context. The research is innovative in two ways. First, it utilizes a large original panel dataset covering gender aspects of electoral candidatures at the municipal level as well as many socio‐economic contextual characteristics. Second, it employs a specification of the Correlated Random Effects Within‐Between model, which allows to disentangle the effect of both time‐variant and time‐invariant information within a panel data framework. Finally, the time period examined is of interest as it encompasses the Italian electoral reform known as Law 215/2012, which introduced a gender list quota at the municipal level. The results of the study suggest that policies to reduce the gender gap must aim not only at introducing quotas for women's representation but also at acting on all those economic and social factors that limit the presence of women in electoral candidacy.

GroupMorph: Medical Image Registration via Grouping Network With Contextual Fusion.

Pyramid-based deformation decomposition is a promising registration framework, which gradually decomposes the deformation field into multi-resolution subfields for precise registration. However, most pyramid-based methods directly produce one subfield per resolution level, which does not fully depict the spatial deformation. In this paper, we propose a novel registration model, called GroupMorph. Different from typical pyramid-based methods, we adopt the grouping-combination strategy to predict deformation field at each resolution. Specifically, we perform group-wise correlation calculation to measure the similarities of grouped features. After that, n groups of deformation subfields with different receptive fields are predicted in parallel. By composing these subfields, a deformation field with multi-receptive field ranges is formed, which can effectively identify both large and small deformations. Meanwhile, a contextual fusion module is designed to fuse the contextual features and provide the inter-group information for the field estimator of the next level. By leveraging the inter-group correspondence, the synergy among deformation subfields is enhanced. Extensive experiments on four public datasets demonstrate the effectiveness of GroupMorph. Code is available at https://github.com/TVayne/GroupMorph.

Goal Shifts Structure Memories and Prioritize Event-defining Information in Memory.

Every day, we encounter far more information than we could possibly remember. Thus, our memory systems must organize and prioritize the details from an experience that can adaptively guide the storage and retrieval of specific episodic events. Prior work has shown that shifts in internal goal states can function as event boundaries, chunking experiences into distinct and memorable episodes. In addition, at short delays, memory for contextual information at boundaries has been shown to be enhanced compared with items within each event. However, it remains unclear if these memory enhancements are limited to features that signal a meaningful transition between events. To determine how changes in dynamic goal states influence the organization and content of long-term memory, we designed a 2-day experiment in which participants viewed a series of black-and-white objects surrounded by a color border on a two-by-two grid. The location of the object on the grid determined which of two tasks participants performed on a given trial. To examine if distinct types of goal shifts modulate the effects of event segmentation, we changed the border color, the task, or both after every four items in a sequence. We found that goal shifts influenced temporal memory in a manner consistent with the formation of distinct events. However, for subjective memory representations in particular, these effects differed by the type of event boundary. Furthermore, to examine if goal shifts lead to the prioritization of goal-relevant features in longer lasting memories, we tested source memory for each object's color and grid location both immediately and after a 24-hr delay. On the immediate test, boundaries enhanced the memory for all concurrent source features compared with nonboundary items, but only if those boundaries involved a goal shift. In contrast, after a delay, the source memory was selectively enhanced for the feature relevant to the goal shift. These findings suggest that goals can adaptively structure memories by prioritizing contextual features that define a unique episode in memory.

Robust multi-stage progressive autoencoder for hyperspectral anomaly detection

Recently, Autoencoders (AEs) have demonstrated remarkable performance in the field of hyperspectral anomaly detection, owing to their powerful capability in handling high-dimensional data. However, they often overlook the inherent global distribution characteristics and long-range dependencies in hyperspectral images (HSI). This oversight makes it challenging to accurately characterize and describe boundaries between different backgrounds and anomalies in complex HSI, thereby affecting detection accuracy. To address this issue, a robust multi-stage progressive autoencoder for hyperspectral anomaly detection (RMSAD) is proposed. Initially, a progressive multi-stage learning framework based on convolutional autoencoders is employed. This framework incrementally reveals and integrates deep contextual features along with their long-range dependencies in HSI, aiming to accurately characterize the background and anomalies. Subsequently, an innovative multi-scale fusion strategy is introduced at the intersections of each stage, reinforcing the learning and representation of background and global spatial details across multiple stages. Finally, by collectively extracting abnormal spatial information across stages, effectively reducing the tendency of autoencoders to reconstruct anomalies. This ensures the efficient restoration and replication of global textural details in HSI. The experimental results on the six HSI datasets demonstrate that the proposed RMSAD is superior to other state-of-the-art methods.

Investigating students’ arguments with real-life functional situations throughout a sequence of collaborative activities

Recent years have seen increasing interest in providing students with opportunities for developing important argumentation skills in the mathematics classroom. Social interactions with peers to critique alternative ideas, justify arguments, and build consensus, have been found to promote deep thinking and meaningful development of concepts. In this study we explored 9<sup>th</sup>-grade students’ interactions during a sequence of specifically designed argumentation tasks on real-life functional situations to investigate the appropriateness of their arguments. Data were collected from the students’ written task responses, student reflections, small-group observations, individual interviews with the group members, and teacher interviews. Analysis of the level of appropriateness of the students’ individual and group written responses in each activity focused on three aspects: identifying variables, forming relations between them, and noticing contextual features of the real-life situation. We found evidence of students grappling with selecting two suitable variables and with conceptualizing the nature of their relation. It also appeared that aspects of the students’ social interactions played a role in students ignoring correct arguments and accepting incorrect arguments. We discuss implications for small-group argumentation and suggest avenues for future research.

UNet-like transformer for 1D soil stratification using cone penetration test and borehole data

Subsurface stratification is crucial for the construction safety of underground projects. The one-dimensional (1D) soil stratification aims at identifying segmentation points that separate soil strata. Current engineering practice mainly requires human judgement, which is time-consuming, labour-intensive, and heavily relies on domain expertise. Other probabilistic methods, such as Bayesian approaches, usually involve complex expressions. With the advent of artificial intelligence, deep learning has emerged as a powerful tool in various domains. The UNet, as a typical convolutional neural network, has been extensively utilized for its superior performance in segmentation tasks, but struggles to capture global and long-range semantic information due to the locality of convolution operations. To realize intelligent and automatic 1D soil stratification, this paper introduces a UNet-like Transformer (ULTra) that integrates multiple data sources, including cone penetration test and borehole data, to incorporate prior knowledge. The architecture features a multi-level Transformer with shifted windows in both the encoder and decoder to extract context features and restore spatial resolution, respectively. Experimental results demonstrate that the ULTra outperforms other UNet variants, particularly in detecting minor textures and local details, underscoring the benefits of integrating Transformers into a standard UNet. Case studies indicate that compared with probabilistic methods, the ULTra enables automatic 1D soil stratification using original exploration data with less human intervention, which is fast, effective, and could be continuously improved through interaction with human knowledge, thus streamlining the intelligent data analysis.