Domain Knowledge Research Articles

Discovering urban block typologies in Seoul: Combining planning knowledge and unsupervised machine learning

Urban blocks are fundamental elements of urban form and play an important role in urban development. Identification of their typologies has been a long-standing challenge in urban planning and design. Traditionally, expert-based classification has been used, but recent studies have shifted towards data-driven clustering to achieve better results. However, most studies tend to use only one of these approaches and few integrate both. To address this gap, this study proposes a framework that combines planning knowledge and machine learning to identify urban block typologies in complex urban environments. The framework first classifies blocks based on their size types according to planning regulations and development types. Then, a combined hierarchical and Gaussian mixture model is used to discover clusters with complex feature data distributions. These clusters are translated into block typologies using a semantic naming system and illustrated with representative blocks. Finally, the validity of the results is tested by comparing them with other building features, such as building age. The proposed integrated framework was applied to Seoul, resulting in the discovery of 27 residential block typologies across the entire city. These typologies show significant correlations with the average building age in the blocks. The application of expert knowledge in the clustering method demonstrates higher accuracy compared to conventional clustering approaches. Overall, this framework holds significant potential for discovering urban block typologies that are consistent with planning domain knowledge and provide urban planners and designers with valuable insights into the characteristics of urban block typologies, thereby helping decision-making regarding zoning regulations, urban design, and urban development strategies.

Validating the knowledge represented by a self-organizing map with an expert-derived knowledge structure.

Professionals are reluctant to make use of machine learning results for tasks like curriculum development if they do not understand how the results were generated and what they mean. Visualizations of peer reviewed medical literature can summarize enormous amounts of information but are difficult to interpret. This article reports the validation of the meaning of a self-organizing map derived from the Medline/PubMed index of peer reviewed medical literature by its capacity to coherently summarize the references of a core psychiatric textbook. Reference lists from ten editions of Kaplan and Sadock's Comprehensive Textbook of Psychiatry were projected onto a self-organizing map trained on Medical Subject Headings annotating the complete set of peer reviewed medical research articles indexed in the Medline/PubMed database (MedSOM). K-means clustering was applied to references from every edition to examine the ability of the self-organizing map to coherently summarize the knowledge contained within the textbook. MedSOM coherently clustered references into six psychiatric knowledge domains across teneditions (1967-2017). Clustering occurred at the abstract level of broad psychiatric practice including General/adult psychiatry, Child psychiatry, and Administrative psychiatry. The uptake of visualizations of published medical literature by medical experts for purposes like curriculum development depends upon validation of the meaning of the visualizations. The current research demonstrates that a self-organizing map (MedSOM) can validate the stability and coherence of the references used to support the knowledge claims of a standard psychiatric textbook, linking the products of machine learning to a widely accepted standard of knowledge.

How generative AI will drive enterprise innovation

PurposeMost recent C-suite surveying suggests current applications of generative AI, although hyped, are fragmented and unlikely to yield major financial returns anticipated. Instead, business leaders expect major value from generative AI will be achieved through application of generative AI to innovation: operational innovation, product and service innovation, and most elusive of all, business model innovation.Design/methodology/approachFindings and analysis presented draws on data from several surveys of C-level executives conducted by IBM Institute for Business Value in collaboration with Oxford Economics during 2023. Each survey focused on the potential of generative AI in a particular business area. The n-count of each survey ranged from 100-3000.Findings1. Business leaders expect generative AI to build on returns achieved from investments in traditional AI, with 10 percent RoI expected on generative AI investments by 2025. 2. Executives anticipate that generative AI will have most impact when implemented to expand innovation. 3. Specific examples provided for operational innovation, product innovation, and business model innovationResearch limitations/implicationsWe are still very early in the generative AI development cycle. We have made best efforts to project, but only time will tell for sure.Practical implicationsBusiness application of generative AI are extremely fragmented. Despite the desire to throw investments at the wall to see what sticks, it is important that leaders take a structured approach to generative AI, focusing on RoI from innovation investments.Social implicationsTo alleviate negative impacts of generative AI, focusing on innovation potential and value maximization is crucial.Originality/valueThis research is based on completely new surveying and data. This papers adds to the sum total of new knowledge in the generative AI domain.

HaLo‐NeRF: Learning Geometry‐Guided Semantics for Exploring Unconstrained Photo Collections

AbstractInternet image collections containing photos captured by crowds of photographers show promise for enabling digital exploration of large‐scale tourist landmarks. However, prior works focus primarily on geometric reconstruction and visualization, neglecting the key role of language in providing a semantic interface for navigation and fine‐grained understanding. In more constrained 3D domains, recent methods have leveraged modern vision‐and‐language models as a strong prior of 2D visual semantics. While these models display an excellent understanding of broad visual semantics, they struggle with unconstrained photo collections depicting such tourist landmarks, as they lack expert knowledge of the architectural domain and fail to exploit the geometric consistency of images capturing multiple views of such scenes. In this work, we present a localization system that connects neural representations of scenes depicting large‐scale landmarks with text describing a semantic region within the scene, by harnessing the power of SOTA vision‐and‐language models with adaptations for understanding landmark scene semantics. To bolster such models with fine‐grained knowledge, we leverage large‐scale Internet data containing images of similar landmarks along with weakly‐related textual information. Our approach is built upon the premise that images physically grounded in space can provide a powerful supervision signal for localizing new concepts, whose semantics may be unlocked from Internet textual metadata with large language models. We use correspondences between views of scenes to bootstrap spatial understanding of these semantics, providing guidance for 3D‐compatible segmentation that ultimately lifts to a volumetric scene representation. To evaluate our method, we present a new benchmark dataset containing large‐scale scenes with ground‐truth segmentations for multiple semantic concepts. Our results show that HaLo‐NeRF can accurately localize a variety of semantic concepts related to architectural landmarks, surpassing the results of other 3D models as well as strong 2D segmentation baselines. Our code and data are publicly available at https://tau‐vailab.github.io/HaLo‐NeRF/.

Geriatrics and artificial intelligence in Spain (Ger-IA project): talking to ChatGPT, a nationwide survey.

The purposes of the study was to describe the degree of agreement between geriatricians with the answers given by an AI tool (ChatGPT) in response to questions related to different areas in geriatrics, to study the differences between specialists and residents in geriatrics in terms of the degree of agreement with ChatGPT, and to analyse the mean scores obtained by areas of knowledge/domains. An observational study was conducted involving 126 doctors from 41 geriatric medicine departments in Spain. Ten questions about geriatric medicine were posed to ChatGPT, and doctors evaluated the AI's answers using a Likert scale. Sociodemographic variables were included. Questions were categorized into five knowledge domains, and means and standard deviations were calculated for each. 130 doctors answered the questionnaire. 126 doctors (69.8% women, mean age 41.4 [9.8]) were included in the final analysis. The mean score obtained by ChatGPT was 3.1/5 [0.67]. Specialists rated ChatGPT lower than residents (3.0/5 vs. 3.3/5 points, respectively, P < 0.05). By domains, ChatGPT ​​scored better (M: 3.96; SD: 0.71) in general/theoretical questions rather than in complex decisions/end-of-life situations (M: 2.50; SD: 0.76) and answers related to diagnosis/performing of complementary tests obtained the lowest ones (M: 2.48; SD: 0.77). Scores presented big variability depending on the area of knowledge. Questions related to theoretical aspects of challenges/future in geriatrics obtained better scores. When it comes to complex decision-making, appropriateness of the therapeutic efforts or decisions about diagnostic tests, professionals indicated a poorer performance. AI is likely to be incorporated into some areas of medicine, but it would still present important limitations, mainly in complex medical decision-making.

Reinforcement Learning Techniques in Optimizing Energy Systems

Reinforcement learning (RL) techniques have emerged as powerful tools for optimizing energy systems, offering the potential to enhance efficiency, reliability, and sustainability. This review paper provides a comprehensive examination of the applications of RL in the field of energy system optimization, spanning various domains such as energy management, grid control, and renewable energy integration. Beginning with an overview of RL fundamentals, the paper explores recent advancements in RL algorithms and their adaptation to address the unique challenges of energy system optimization. Case studies and real-world applications demonstrate the efficacy of RL-based approaches in improving energy efficiency, reducing costs, and mitigating environmental impacts. Furthermore, the paper discusses future directions and challenges, including scalability, interpretability, and integration with domain knowledge. By synthesizing the latest research findings and identifying key areas for further investigation, this paper aims to inform and inspire future research endeavors in the intersection of reinforcement learning and energy system optimization.

Knowledge engineering for wind energy

Abstract. With the rapid evolution of the wind energy sector, there is an ever-increasing need to create value from the vast amounts of data made available both from within the domain and from other sectors. This article addresses the challenges faced by wind energy domain experts in converting data into domain knowledge, connecting and integrating them with other sources of knowledge, and making them available for use in next-generation artificial intelligence systems. To this end, this article highlights the role that knowledge engineering can play in the digital transformation of the wind energy sector. It presents the main concepts underpinning knowledge-based systems and summarises previous work in the areas of knowledge engineering and knowledge representation in a manner that is relevant and accessible to wind energy domain experts. A systematic analysis of the current state of the art on knowledge engineering in the wind energy domain is performed with available tools put into perspective by establishing the main domain actors and their needs, as well as identifying key problematic areas. Finally, recommendations for further development and improvement are provided.

Trends, progress and future directions of nanomaterial based sensors: a bibliometric overview

PurposeNanosensors have a wide range of applications because of their high sensitivity, selectivity and specificity. In the past decade, extensive and pervasive research related to nanosensors has led to significant progress in diverse fields, such as biomedicine, environmental monitoring and industrial process control. This led to better and more efficient detection and monitoring of physical and chemical properties at better resolution, opening new horizons in the development of novel technologies and applications for improved human health, environment protection, enhanced industrial processes, etc.Design/methodology/approachIn this paper, the authors discuss the application of citation network analysis in the field of nanosensor research and development. Cluster analysis was carried out using papers published in the field of nanomaterial-based sensor research, and an in-depth analysis was carried out to identify significant clusters. The purpose of this study is to provide researchers to identify a pathway to the emerging areas in the field of nanosensor research. The authors have illustrated the knowledge base, knowledge domain and knowledge progression of nanosensor research using the citation analysis based on 3,636 Science Citation Index papers published during the period 2011 to 2021.FindingsAmong these papers, the bibliographic study identified 809 significant research publications, 11 clusters, 556 research sector keywords, 1,296 main authors, 139 referenced authors, 63 nations, 206 organizations and 42 journals. The authors have identified single quantum dot (QD)-based nanosensor for biological applications, carbon dot-based nanosensors, self-powered triboelectric nanogenerator-based nanosensor and genetically encoded nanosensor as the significant research hotspots that came to the fore in recent years. The future trend in nanosensor research might focus on the development of efficient and cost-effective designs for the detection of numerous environmental pollutants and biological molecules using mesostructured materials and QDs. It is also possible to optimize the detection methods using theoretical models, and generalized gradient approximation has great scope in sensor development.Research limitations/implicationsThe future trend in nanosensor research might focus on the development of efficient and cost-effective designs for the detection of numerous environmental pollutants and biological molecules using mesostructured materials and QDs. It is also possible to optimize the detection methods using theoretical models, and generalized gradient approximation has great scope in sensor development.Originality/valueThis is a novel bibliometric analysis in the area of “nanomaterial based sensor,” which is carried out in CiteSpace software.

Application of deep learning model incorporating domain knowledge in international migration forecasting

PurposeForecasting population movement trends is crucial for implementing effective policies to regulate labor force growth and understand demographic changes. Combining migration theory expertise and neural network technology can bring a fresh perspective to international migration forecasting research.Design/methodology/approachThis study proposes a conditional generative adversarial neural network model incorporating the migration knowledge – conditional generative adversarial network (MK-CGAN). By using the migration knowledge to design the parameters, MK-CGAN can effectively address the limited data problem, thereby enhancing the accuracy of migration forecasts.FindingsThe model was tested by forecasting migration flows between different countries and had good generalizability and validity. The results are robust as the proposed solutions can achieve lesser mean absolute error, mean squared error, root mean square error, mean absolute percentage error and R2 values, reaching 0.9855 compared to long short-term memory (LSTM), gated recurrent unit, generative adversarial network (GAN) and the traditional gravity model.Originality/valueThis study is significant because it demonstrates a highly effective technique for predicting international migration using conditional GANs. By incorporating migration knowledge into our models, we can achieve prediction accuracy, gaining valuable insights into the differences between various model characteristics. We used SHapley Additive exPlanations to enhance our understanding of these differences and provide clear and concise explanations for our model predictions. The results demonstrated the theoretical significance and practical value of the MK-CGAN model in predicting international migration.

Speculative investment decisions in cryptocurrency: a structural equation modelling approach

ABSTRACT Cryptocurrency markets are inclined towards speculative usage due to the inherent high risk of financial loss and the potential for substantial gains during transaction completion. In response to this phenomenon, this study represents the inaugural effort to explore the influence of variables such as subjective norms, domain knowledge, impulsive investment tendencies, and self-control on decisions related to speculative investments. Utilising structural equation modelling with a dataset of 367 responses in India, the study is the first of its kind. The research reveals that subjective norms and domain knowledge play a significant role in influencing impulsive investment and self-control. Additionally, impulsive investment exhibits significant associations with decisions involving speculative investments. This insight underscores the complexity wherein individuals, despite exercising self-control, may still engage in speculative decisions that lead to adverse consequences. The findings have practical implications for investors and regulators, offering valuable insights into investment behaviours within the cryptocurrency realm.

Impact of training on knowledge, confidence and attitude amongst community health volunteers in the provision of community-based palliative care in rural Kenya

ObjectivesExisting literature suggests multiple potential roles for community health volunteers (CHVs) in the provision of palliative care (PC) in low- and middle-income countries. In Kenya the role of CHV in the provision of PC has not been reported. The objective of this study was to assess knowledge, confidence, attitude, and clinical practice of community health volunteers after attending a novel palliative care (PC) training program.MethodsA total of 105 CHVs participated in a 3-day in person training followed by a 1-month in person and telephone observation period of the palliative care activities in the community. Structured questionnaires were used pre- and post-training to assess knowledge acquisition, impact on practice, and content delivery. A mixed method study design was conducted 12-month post training to assess impact on clinical practice.ResultsImmediately after training, CHV provided positive ratings on relevance and content delivery. In the month following training, CHVs evaluated 1,443 patients, referred 154, and conducted 110 and 129 tele consults with the patients and PC providers respectively. The follow up survey at 12 months revealed improved knowledge and confidence in various domains of palliative care including symptom and spiritual assessment and provision of basic nursing and bereavement care. Focus group discussions revealed the CHVs ability to interpret symptoms, make referrals, improved communication/ interpersonal relationships, spiritual intervention, patient comfort measures and health care practices as newly learned and practiced skills.ConclusionsWe noted improved knowledge, new skills and change in practice after CHVs participation in a novel training curriculum. CHVs can make important contributions to the PC work force and be first line PC providers in the community as part of larger hub and spoke care model.

Promoting pre-service teachers’ knowledge integration from multiple text sources across domains with instructional prompts

AbstractMultiple document comprehension and knowledge integration across domains are particularly important for pre-service teachers, as integrated professional knowledge forms the basis for teaching expertise and competence. This study examines the effects of instructional prompts and relevance prompts embedded in pre-service teachers’ learning processes on the quality their knowledge integration in multiple document comprehension across domains. 109 pre-service teachers participated in an experimental study. They read four texts on “competencies” from different knowledge domains and wrote a text on a given scenario. Experimental group 1 was aided with instructional and relevance prompts, while experimental group 2 received only relevance prompts. The control group received no prompting. Perceived relevance of knowledge integration was assessed in a pre-post-test. Pre-service teachers’ separative and integrative learning, epistemological beliefs, metacognition, study-specific self-concept, and post-experimental motivation were assessed as control variables. Participants’ texts were analyzed concerning knowledge integration by raters and with computer linguistic measures. A key finding is that combined complex prompting enhances pre-service teachers perceived relevance of knowledge integration. This study found effects of prompting types on the pre-service teachers’ semantic knowledge structures. Implications for transfer are discussed.

Knowledge sharing behavior of service sector’s employees to attain sustainable development goals

Purpose The purpose of this study is to get an understanding regarding the clusters of middle management employees on the basis of their knowledge sharing behaviour. Designing knowledge sharing behaviors with a distinct focus for a specified group of employees can be an effective and productive one. As it is often argued that the cluster of employees labeled as “middle management” is the key player for knowledge sharing behaviors – a subject of this study that intends to contribute to management strategy to enhance organizational effectiveness and subsequently to its knowledge sharing phenomona. Design/methodology/approach Cluster analysis was adopted as key tool as a part of quantitative method to accumulate the data from 597 employees who are working within the middle management of service sector located in the union territory of India named Jammu and Kashmir. Findings Three distinct segments namely – “knowledge sharing adepts (KSA),” “knowledge sharing scrupulous (KSC)” and “knowledge sharing servitudes (KSE)” as the prime domains of knowledge sharing behavior are identified. Research limitations/implications To draw a narrow focus, the study was limited to the service sector of a union territory in India, hence the findings may not be generalized. Furthermore, as knowledge sharing behavior of individuals is always evolved out of social and historical practices, findings of this cross-sectional study should ideally be needed to be updated time to time through further research. Practical implications Cluster dynamicism of knowledge sharing behavior based on the differentiated and specified group of employee functions distinctly which in turn increases the organizational productivity with a particular focus on the mid-management of the service sector – a key managerial implication of this study. Originality/value To the best of the authors’ knowledge, this research paper is the first of its kind in Jammu and Kashmir adding value to the international literature in the area of knowledge sharing behaviors of service sector.

Automatic feature extraction with Vectorial Genetic Programming for Alzheimer’s Disease prediction through handwriting analysis

Alzheimer’s Disease (AD) is an incurable neurodegenerative disease that strongly impacts the lives of the people affected. Even if, to date, there is no cure for this disease, its early diagnosis helps to manage the course of the disease better with the treatments currently available. Even more importantly, an early diagnosis will also be necessary for the new treatments available in the future. Recently, machine learning (ML) based tools have demonstrated their effectiveness in recognizing people’s handwriting in the early stages of AD. In most cases, they use features defined by using the domain knowledge provided by clinicians. In this paper, we present a novel approach based on vectorial genetic programming (VE_GP) to recognize the handwriting of AD patients. VE_GP is an enhanced version of GP that can manage time series directly. We applied VE_GP to data collected using an experimental protocol, which was defined to collect handwriting data to support the development of ML tools for the early diagnosis of AD based on handwriting analysis. The experimental results confirmed the effectiveness of the proposed approach in terms of classification performance, size, and simplicity.

Ontologies and knowledge representation in terminology: Present and future perspectives

This contribution reflects on the current role of ontologies in terminology research and practice and their future role, especially with a view to the creation of fully digital terminographic resources. The very notion of (domain) ontology, its concept and term, is discussed, highlighting metaterminological differences and substantial ambiguities arising from the interdisciplinary contact between Ontology Engineering and Terminology. Major challenges in ontology building, e.g. subjectivity, are mentioned, also with respect to the distinction between realist and non-realist ontologies and their relevance in Terminology. In addition, this contribution presents some examples of terminology resources with a distinct ontological component, showing a diversity of approaches depending on the purpose of the resource and its scope. In this context, more specific topics are addressed, such as the acquisition of ontological data and suitable formats and models for representing domain knowledge. The contribution ends with a vision of the integration of complex concept systems such as ontologies in future terminology work: here, the development of models based on terminology-specific requirements and typical users will be fundamental.

UCDCN: a nested architecture based on central difference convolution for face anti-spoofing

AbstractThe significance of facial anti-spoofing algorithms in enhancing the security of facial recognition systems cannot be overstated. Current approaches aim to compensate for the model’s shortcomings in capturing spatial information by leveraging spatio-temporal information from multiple frames. However, the additional branches to extract inter-frame details increases the model’s parameter count and computational workload, leading to a decrease in inference efficiency. To address this, we have developed a robust and easily deployable facial anti-spoofing algorithm. In this paper, we propose Central Difference Convolution UNet++ (UCDCN), which takes advantage of central difference convolution and improves the characterization ability of invariant details in diverse environments. Particularly, we leverage domain knowledge from image segmentation and propose a multi-level feature fusion network structure to enhance the model’s ability to capture semantic information which is beneficial for face anti-spoofing tasks. In this manner, UCDCN greatly reduces the number of model parameters as well as achieves satisfactory metrics on three popular benchmarks, i.e., Replay-Attack, Oulu-NPU and SiW.

MR-Scout : Automated Synthesis of Metamorphic Relations from Existing Test Cases

Metamorphic Testing (MT) alleviates the oracle problem by defining oracles based on metamorphic relations (MRs), that govern multiple related inputs and their outputs. However, designing MRs is challenging, as it requires domain-specific knowledge. This hinders the widespread adoption of MT. We observe that developer-written test cases can embed domain knowledge that encodes MRs. Such encoded MRs could be synthesized for testing not only their original programs but also other programs that share similar functionalities. In this paper, we propose MR-Scout to automatically synthesize MRs from test cases in open-source software (OSS) projects. MR-Scout first discovers MR-encoded test cases (MTCs), and then synthesizes the encoded MRs into parameterized methods (called codified MRs ), and filters out MRs that demonstrate poor quality for new test case generation. MR-Scout discovered over 11,000 MTCs from 701 OSS projects. Experimental results show that over 97% of codified MRs are of high quality for automated test case generation, demonstrating the practical applicability of MR-Scout . Furthermore, codified-MRs-based tests effectively enhance the test adequacy of programs with developer-written tests, leading to 13.52% and 9.42% increases in line coverage and mutation score, respectively. Our qualitative study shows that 55.76% to 76.92% of codified MRs are easily comprehensible for developers.

Information searching in cultural heritage archives: a user study

PurposeThe PICCH research project contributes to opening a dialogue between cultural heritage archives and users. Hence, the users are identified and their information needs, the search strategies they apply and the search challenges they experience are uncovered.Design/methodology/approachA combination of questionnaires and interviews is used for collection of data. Questionnaire data were collected from users of three different audiovisual archives. Semi-structured interviews were conducted with two user groups: (1) scholars searching information for research projects and (2) archivists who perform their own scholarly work and search information on behalf of others.FindingsThe questionnaire results show that the archive users mainly have an academic background. Hence, scholars and archivists constitute the target group for in-depth interviews. The interviews reveal that their information needs are multi-faceted and match the information need typology by Ingwersen. The scholars mainly apply collection-specific search strategies but have in common primarily doing keyword searching, which they typically plan in advance. The archivists do less planning owing to their knowledge of the collections. All interviewees demonstrate domain knowledge, archival intelligence and artefactual literacy in their use and mastering of the archives. The search challenges they experience can be characterised as search system complexity challenges, material challenges and metadata challenges.Originality/valueThe paper provides a rare insight into the complexity of the search situation of cultural heritage archives, and the users’ multi-facetted information needs and hence contributes to the dialogue between the archives and the users.

Domain Knowledge-Driven Relation Extraction Methods

Relation classification is one of the important tasks in natural language processing, which aims to determine the relationship between entities given a sentence and their respective positions. Most of the existing methods for relation classification are based on neural networks using pre-trained models such as BERT. In recent years, models based on pre-trained models like BERT have achieved excellent results in relation classification tasks in general domains. However, these methods often struggle when applied to specialized domains due to the limitations of the corpora used for BERT pre-training. Most pre-trained models are trained on text corpora from general sources like Wikipedia, which cover a wide range of domains. As a result, the content of these corpora in specific domains is limited and lacks the necessary expertise, leading to subpar performance of relation classification models in specific domains. While providing a large number of domain-specific corpora to pre-trained models could potentially address this issue, it comes with limitations such as increased computational requirements and insufficient training of specialized vocabulary. This paper proposes a method inspired by the K-BERT pre-training model to incorporate triplet knowledge from domain knowledge graphs into sentence sequences. The triplets are transformed into sentence trees and then fed into the BERT pre-trained model using absolute and relative indices. Our model has achieved an accuracy of 93.06%, which is markedly higher than that of any other baseline approach. This approach allows the incorporation of domain knowledge without significantly increasing the computational complexity. Additionally, the paper introduces a partial input method that enables the computer to understand input sentences from multiple dimensions and hierarchical levels. Experimental results on a medical domain dataset for relation classification, which includes type labels, demonstrate significant advantages over other relation classification models in terms of Accuracy.

USES-Net: An Infrared Dim and Small Target Detection Network with Embedded Knowledge Priors

Detecting and identifying small infrared targets has always been a crucial technology for many applications. To address the low accuracy, high false-alarm rate, and poor environmental adaptability that commonly exist in infrared target detection methods, this paper proposes a composite infrared dim and small target detection model called USES-Net, which combines the target prior knowledge and conventional data-driven deep learning networks to make use of both labeled data and the domain knowledge. Based on the typical encoder–decoder structure, USES-Net firstly introduces the self-attention mechanism of Swin Transformer to replace the universal convolution kernel at the encoder end. This helps to extract potential features related to dim, small targets in a larger receptive field. In addition, USES-Net includes an embedded patch-based contrast learning module (EPCLM) to integrate the spatial distribution of the target as a knowledge prior in the training network model. This guides the training process of the constrained network model with clear physical interpretability. Finally, USES-Net also designs a bottom-up cross-layer feature fusion module (AFM) as the decoder of the network, and a data-slicing-aided enhancement and inference method based on Slicing Aided Hyper Inference (SAHI) is utilized to further improve the model’s detection accuracy. An experimental comparative analysis shows that USES-Net achieves the best results on three typical infrared weak-target datasets: NUAA-SIRST, NUDT-SIRST, and IRSTD-1K. The results of the target segmentation are complete and sufficient, which demonstrates the validity and practicality of the proposed method in comparison to others.