Local Setting Research Articles

The activities, competencies, and conditions necessary for public-health policy advisers in a Dutch local government setting to contribute to a healthier living environment: a qualitative multiple-case study

The activities, competencies, and conditions necessary for public-health policy advisers in a Dutch local government setting to contribute to a healthier living environment: a qualitative multiple-case study

Transforming Urban Space: The Success of Sustainable Regeneration in Speirs Locks

This paper examines the Speirs Locks area regeneration project in Glasgow, focusing on the implementation of a sustainable and inclusive master plan aimed at revitalising the canal area. The study explores the strategic integration of urban planning principles, stakeholder engagement and environmental sustainability in the redevelopment process. Through qualitative analysis and case study methods, the research highlights the project's successes and challenges, particularly in improving the social, economic, and environmental conditions in the area. The findings show that despite facing physical and infrastructural constraints, the regeneration project has significantly improved the quality of life of the local community and set an example for future urban redevelopment initiatives.

Thai creative labour solidarity, (post)-pandemic precarity, and directions of production studies in the Global South

This paper offers an overview of the creative labour solidarity that took place in Thailand during the pandemic by young film graduates and political-conscious workers. A dialogic reflection with research on creative labour studies largely based in the Global North is discussed. In addition to tracing the development of this local ‘turn to labour,’ the paper offers a closer look at the lives of below-the-line film crews based on ‘solidarity dialogues’ during and post-pandemic. The paper explores precarity gaps based on the type of production, age, family, and social relation, as well as micro-practices adopted by workers to navigate different shades of precarity. Adopting ‘South-South citations’ and a feminist approach to production studies, aspects of local class systems, the paradoxical nature of workers’ solidarity, and the persistent structural inequality between large-scale international productions and local film sets are examined with reflections on other countries in the Global South.

Precise Image-level Localization of Intracranial Hemorrhage on Head CT Scans with Deep Learning Models Trained on Study-level Labels.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To develop a highly generalizable weakly supervised model to automatically detect and localize image- level intracranial hemorrhage (ICH) using study-level labels. Materials and Methods In this retrospective study, the proposed model was pretrained on the image-level RSNA dataset and fine-tuned on a local dataset using attention-based bidirectional long-short-term memory networks. This local training dataset included 10,699 noncontrast head CT scans from 7469 patients with ICH study-level labels extracted from radiology reports. Model performance was compared with that of two senior neuroradiologists on 100 random test scans using the McNemar test, and its generalizability was evaluated on an external independent dataset. Results The model achieved a positive predictive value (PPV) of 85.7% (95% CI: [84.0%, 87.4%]) and an AUC of 0.96 (95% CI: [0.96, 0.97]) on the held-out local test set (n = 7243, 3721 female) and 89.3% (95% CI: [87.8%, 90.7%]) and 0.96 (95% CI: [0.96, 0.97]), respectively, on the external test set (n = 491, 178 female). For 100 randomly selected samples, the model achieved performance on par with two neuroradiologists, but with a significantly faster (P < .05) diagnostic time of 5.04 seconds per scan (versus 86 seconds and 22.2 seconds for the two neuroradiologists, respectively). The model's attention weights and heatmaps visually aligned with neuroradiologists' interpretations. Conclusion The proposed model demonstrated high generalizability and high PPVs, offering a valuable tool for expedited ICH detection and prioritization while reducing false-positive interruptions in radiologists' workflows. ©RSNA, 2024.

Distributed event-triggered algorithm for convex optimization with coupled constraints

This paper develops a distributed primal–dual algorithm via an event-triggered mechanism to solve a class of convex optimization problems subject to local set constraints, coupled equality and inequality constraints. Different from some existing distributed algorithms with the diminishing step-sizes, our algorithm uses the constant step-sizes, and is shown to achieve an exact convergence to an optimal solution with an ergodic convergence rate of O(1/k) for general convex objective functions, where k>0 is the iteration number. Based on the event-triggered communication mechanism, the proposed algorithm can effectively reduce the communication cost without sacrificing the convergence rate. Finally, a numerical example is presented to verify the effectiveness of the proposed algorithm.

Intelligent modeling of combined heat and power unit under full operating conditions via improved crossformer and precise sparrow search algorithm

The flexible operation capability of combined heat and power (CHP) unit under full operating conditions must be promoted to suppress the power grid fluctuation in large-scale integration of renewable energy. However, obtaining CHP unit model under large-scale variable loads and deep peak shaving is extremely challenging. To this end, an intelligent modeling method incorporating improved crossformer and precise sparrow search algorithm is designed to provide reference for flexible controller design. Firstly, to address the strong time dependence of CHP unit boiler-turbine coupling process, a bidirectional gated recurrent unit is employed as the position encoding to extract the hidden temporal feature. Secondly, a novel encoder structure with multi-receptive field convolution module is designed to enhance the local feature extraction capability of the network, which is conducive to the analysis of multivariable coupling characteristics of CHP unit. On this basis, a precise sparrow search algorithm with stronger search ability is formed by combining Tent chaotic mapping, osprey optimization algorithm, Cauchy mutation and quantum behavior, which provides support for the dynamic characteristics analysis of CHP unit. The time dependence, local feature information and optimal parameter settings are fully considered in the comprehensive modeling scheme, which results in an accurate identification model for CHP unit under full operating conditions. Finally, the effectiveness of the proposed method is verified based on the actual operating data of a 350 MW CHP unit. The accuracy of established model is greater than 99.4 %, which can well reflect the nonlinear characteristics of the unit. Therefore, the built model can be used for controller design and simulation analysis.

Ichino periods for CM forms

In both local and global settings, we establish explicit relations between Ichino triple product period and Waldspurger toric periods for CM forms via the theta lifting and the see-saw principle.

Efekty spillover chińskich inwestycji zagranicznych w Angoli i Zambii

SPILLOVER EFFECT OF THE CHINESE FDI IN ANGOLA AND ZAMBIAIn recent years, Chinese foreign direct investment (FDI) in Africa has attracted interest from both academia and the wider political world. Some postulate that Chinese companies – unlike Western corporations – have greater potential to initiate and carry out the structural transformation of the continent. Some researchers even indicate that thanks to the inflow of Chinese FDI, Africa may become “the next factory of the world”. The aim of this article is to analyse external effects (also called spillover effects) related to Chinese FDI in Africa using the examples of Angola and Zambia. According to the current state of knowledge, spillover effects are the most desirable effects of FDI in the host country, because the related increase in the productivity of local enterprises is key to the occurrence of structural transformation in local economies. The subject of the analysis presented in this article are three aspects (determinants) of spillover effects: (i) the potential of Chinese FDI to generate spillover effects, (ii) the absorptive capacity of local companies and (iii) local institutional settings favouring the occurrence of spillover effects. The findings indicate that due to the existence of weak and few linkages between foreign investors and local firms, spillover effects occur rarely and are relatively small. They are also not sufficient to initiate the transfer of valuable knowledge and technology. The presented research results were based on over 150 in-depth interviews and two rounds of surveys conducted among Chinese investors, Angolan and Zambian companies and representatives of local authorities.

Local nature-based recreation as a pathway to environmental citizenship

Local parks and protected areas (PPAs) offer important settings for nature exposure proximate to home that may encourage local environmental citizenship (LEC); however, there has been limited investigation of this relationship and how it may be impacted by individual characteristics. This national panel study of U.S. adults examined relationships between frequency of visitation to local nature-based recreation settings and LEC, with assessment of differences by race/ethnicity and associations with age and political orientation (N = 556). Results indicate that more frequent visitation to local nature-based recreation settings is associated with significantly greater environmental advocacy and activism, volunteering, literacy, and political ecological citizenship. Age was negatively related to environmental advocacy and activism, volunteering, and literacy, and liberalism was associated with greater participation in all types of LEC, especially political ecological citizenship. Most LEC types did not vary by race/ethnicity, although there were small differences in environmental advocacy and activism, which was higher among Black/African American and Hispanic/Latino populations compared to Asian respondents. Findings indicate that frequency of visitation to local nature-based recreation settings is associated with LEC regardless of one's age, political orientation, or race/ethnicity, and thus increasing equitable access to local nature-based recreation, especially among those who have been historically underserved, has the potential to encourage PPA stewardship through LEC, while also contributing to the advancement of procedural environmental justice. Management implications•Environmental stewardship and volunteer organizations should focus on supporting land managers in advancing equity in local parks and protected areas (PPAs) as well as engaging users in these spaces through programs which leverage people's connection with nature at the local scale and provide opportunities for accessible involvement in environmental citizenship activities.•Interpretation and education can be used to increase individual's environmental knowledge, while contextualizing such information to places they care about.•Enhanced promotion of local opportunities for stewardship among local PPA visitors may be warranted, especially events or programs with few barriers to entry that might encourage greater future participation.

Micro- and Nanoplastics Produced from Textile Finishes: A Review.

The problem of increasing plastic pollution has emerged as a significant societal issue. Plastics can originate from various sources, and there is growing concern among researchers to study and investigate this new category of pollution. The plastic waste is found at the macro, micro, and nanoscale, and its study has had great significance according to the perspective of posing hazardous impacts on living organisms. Given the high demand for functional textiles, the textile industries are supporting the coating of different polymeric based finishes on the surface of textile products. The plastic debris emitted from these coated finishes are in the ranges of nanometric scale, so-called polymeric nanoplastics (PNPs). With the new terminology, polymeric nanoplastics (PNPs) released from textile finishes or coatings are being increasingly mentioned, and the term fibrous microplastics (FMPs) can be seen as outdated. This study is based on an intensive review of a very novel category of debris plastics (PNPs) mostly produced from textile finishes or coatings. In fact, FMPs and PNPs released from synthetic textiles and textiles coated with plastic-based finishes during washing activities are considered to be a major cause that contributes to the current overall load of microplastics (MPs) in the environment. A link between the concentration of NPs from textile fibers and NPs from textile polymeric-based coatings in freshwater and sediments within a particular local setting and the extent of activities of the textile industry has been demonstrated. Invested efforts have been paid to consider and concentrate on plastic pollution (nanoplastics from textile polymeric coatings). We also summarize existing methodologies to elucidate the identification and proactive quantification of nanoplastics shed from the textile polymeric coatings. To this end, more than 40 studies have been done to identify the physical, chemical, and mechanical parameters and to characterize nanoplastics.

Tectonic evolution of the eastern margin of the Northern South Yellow Sea Basin in the Yellow Sea since the Late Cretaceous

The South Yellow Sea Basin is the largest sedimentary basin in the Yellow Sea. The Gunsan Basin in the central eastern part of the Northern South Yellow Sea Basin comprises the Western, Central, and Eastern Subbasins. The Eastern Subbasin marks the eastern margin of the South Yellow Sea Basin. Interpretation of multi-channel seismic profiles and balanced cross-section restoration of depth-converted seismic profiles reveal the structural characteristics and evolution of the Eastern Subbasin. The subbasin comprises three groups of faults: NW-SE, NE-SW, and NNE-SSW trending faults. The subsidence pattern of the subbasin, derived from the cross-section restoration analysis, indicates five distinguished evolution phases: (i) rapid subsidence in the Late Cretaceous, (ii) slow subsidence from the Paleocene to the Eocene, (iii) accelerated subsidence in the Oligocene, (iv) alternation of the uplift and subsidence in the Early Miocene, and (v) gradual subsidence since the Middle Miocene. The main and moderate subsidence can be explained by the combination of extension in the SE and NE-SW directions that formed double duplex structures. We suggest that the NW oblique subduction of the Pacific Plate under the NE Asia margin induced both extension toward the trench and dextral strike-slip parallel to the margin. The extension toward the trench caused SE transtension in a local pull-apart setting, whereas the dextral strike-slip parallel to the margin caused NE-SW extension, inducing more significant subsidence. The combined processes resulted in the progressive development of nested duplex structures. The evolution of the Eastern Subbasin is not compatible with previously suggested models for the western part of the South Yellow Sea Basin including foreland basin formation and transtension induced by branch faults of the Tan-Lu Fault.

A Reaction Paper: Task-based Language Teaching in a Local EFL Context

This reaction paper provided a detailed summary and reflection on the implementation of Task-Based Language Teaching (TBLT) in a local EFL context based on Liu and Ren s (2021) research. It highlighted various aspects, including the understanding of TBLT among Chinese university teachers, obstacles faced in adopting TBLT, roles of teachers and students, curriculum design, difficulties in implementation, and implications for improving TBLT in the Chinese EFL setting. The paper began with an introduction to TBLT and the methodology used in the research, which involved semi-structured interviews to understand teachers perspectives on TBLT. The findings were divided into sections focusing on teachers and students roles, implementation of TBLT, difficulties faced, and implications for improvement. The reflection delved into the criteria for TBLT tasks, emphasizing the need for tasks to focus on meaning while integrating form and meaning effectively. It discussed the challenges teachers faced in designing tasks and assessing students performance within the TBLT framework. The reflection also touched on the need for ongoing professional development and autonomy for teachers in curriculum design and assessment. The conclusion acknowledges the potential of TBLT to enhance language learning but calls for ongoing support and training for teachers, alongside institutional backing in curriculum development and assessment strategies. This paper underscores the significance of adapting TBLT to fit the local educational settings and suggests directions for future research and practice in the context of Chinese EFL education.

The role of administrative categories in the globalisation of a psychiatric concept: Case studies of autism in Japan

This paper explores how what I call ‘administrative categories’ have been adopted by the Japanese government and experts in autism support and what roles these categories have played in local settings. Since support practices for children and adults with autism began in the 1950s in Japan, the Japanese government and people engaging in autism support have used Japanese-specific administrative categories, instead of relying on a medical concept of autism, such as ‘severe moving disabilities’ (SMD), ‘emotional disturbance’, and ‘extremely disruptive behavioural disorders’ (EDBD).To understand the emergence of these three autism-related administrative categories in Japan, historical materials published from the 1950s to the 1990s by Japanese authors (doctors, psychologists, teachers, educationalists, welfare workers, government officials, and parents) and interview data with 19 leading experts of autism in Japan were collected and analysed thematically.The analysis revealed that the governmental ministries aimed to focus on establishing administrative support by avoiding engaging in aetiological debates among doctors, and to describe the political agenda more vividly. Administrative categories filled the gap between local interests and international medical concepts, enabling the concept of autism to be rooted in Japan's administrative systems. Three roles of administrative categories were identified: i) separation from medicine, ii) describing local problems, and iii) claimsmaking to wider actors and the public.I concluded that looking purely at medical and specifically diagnostic concepts limits our understanding of the formation of practices regarding disabilities, and thus more focus should be placed on categorisation practices outside of medicine. In addition, to the literature on the globalisation of Euro-American psychiatric concepts, this study contributes to our knowledge of a form of locality that has not been central in the exploration of the influence of globalisation on local settings and the relationships between the local and the global.

The impact of PET imaging on triple negative breast cancer: an updated evidence-based perspective.

Triple-negative breast cancer (TNBC) is a subtype of breast cancer characterized by the absence of estrogen, progesterone, and HER2 receptors. It predominantly affects younger women and is associated with a poor prognosis. This systematic review aims to evaluate the current role of positron emission tomography (PET) in the management of TNBC patients and to identify future research directions. We systematically searched the PubMed, Scopus, and Web of Science databases up to February 2024. A team of five researchers conducted data extraction and analysis. The quality of the selected studies was assessed using a specific evaluation form. Twenty-eight studies involving 2870 TNBC patients were included in the review. Key clinical applications of PET in TNBC included predicting pathological complete response (pCR) in patients undergoing neoadjuvant chemotherapy (NAC), assessing the prognostic value of baseline PET, and initial disease staging. Two studies utilized PSMA-ligand agents, while the majority used [18F]FDG-based PET. Significant associations were found between baseline [18F]FDG uptake and molecular biomarkers such as PDL-1, androgen receptor, and Ki67. Baseline [18F]FDG PET led to the upstaging of patients from stage IIB to stage IV, influencing treatment decisions and survival outcomes. In the NAC setting, serial PET scans measuring changes in [18F]FDG uptake, indicated by maximum standardized uptake value (SUVmax), predicted pCR with varying cut-off values correlated with different response rates. Semiquantitative parameters such as metabolic tumor volume (MTV) and PET lung index were prognostic for metastatic disease. In TNBC patients, [18F]FDG PET is essential for initial disease staging in both localized and metastatic settings. It is also useful for assessing treatment response to NAC. The ability of PET to correlate metabolic activity with molecular markers and predict treatment outcomes highlights its potential in TNBC management. Further prospective studies are needed to refine these clinical indications and establish its definitive role.

GRADE guidance 39: using GRADE-ADOLOPMENT to adopt, adapt or create contextualized recommendations from source guidelines and evidence syntheses

Background and ObjectiveThe Grading of Recommendations, Assessment, Development and Evaluations (GRADE)-ADOLOPMENT methodology has been widely used to adopt, adapt, or de novo develop recommendations from existing or new guideline and evidence synthesis efforts. The objective of this guidance is to refine the operationalization for applying GRADE-ADOLOPMENT. MethodsThrough iterative discussions, online meetings, and email communications, the GRADE-ADOLOPMENT project group drafted the updated guidance. We then conducted a review of handbooks of guideline-producing organizations, and a scoping review of published and planned adolopment guideline projects. The lead authors refined the existing approach based on the scoping review findings and feedback from members of the GRADE working group. We presented the revised approach to the group in November 2022 (approximately 115 people), in May 2023 (approximately 100 people), and twice in September 2023 (approximately 60 and 90 people) for approval. ResultsThis GRADE guidance shows how to effectively and efficiently contextualize recommendations using the GRADE-ADOLOPMENT approach by doing the following: (1) showcasing alternative pathways for starting an adolopment effort; (2) elaborating on the different essential steps of this approach, such as building on existing evidence-to-decision (EtDs), when available or developing new EtDs, if necessary; and (3) providing examples from adolopment case studies to facilitate the application of the approach. We demonstrate how to use contextual evidence to make judgments about EtD criteria, and highlight the importance of making the resulting EtDs available to facilitate adolopment efforts by others. ConclusionThis updated GRADE guidance further operationalizes the application of GRADE-ADOLOPMENT based on over 6 years of experience. It serves to support uptake and application by end users interested in contextualizing recommendations to a local setting or specific reality in a short period of time or with limited resources.

Research on the Construction of Ethnic Piano Music Culture in the Teaching of Local Colleges and Universities

Ethnic piano music, as a distinctive cultural form, embodies a rich tapestry of national sentiment and cultural significance. Local higher education institutions, serving as crucial bastions of cultural preservation, integrate ethnic music culture into their piano instruction. This integration not only enhances students' musical proficiency but also fosters the continuation and evolution of ethnic culture. However, local higher education institutions currently face challenges such as uniform curriculum design and outdated teaching methods, which hinder the effective dissemination of ethnic piano music culture. This study, through literature review, empirical investigation, and case analysis, explores strategies for constructing ethnic piano music culture within local higher education settings. The research identifies that optimizing teaching content and curriculum design, innovating teaching methods and approaches, enhancing teacher training and professional development, and improving student engagement and evaluation mechanisms can significantly advance the spread and application of ethnic piano music culture in local higher education institutions. It is hoped that this study will provide valuable insights and guidance for piano teaching in local higher education institutions, thereby promoting the further development and preservation of ethnic music culture.

Evaluation of an innovative, open-source and quantitative approach for the kinematic analysis of rock slopes based on UAV based Digital Outcrop Model: A case study from a railway tunnel portal (Finale Ligure, Italy)

This paper presents a novel, cost-effective method for a rapid and quantitative characterization of discontinuities in fractured rock cliffs using Unmanned Aerial Vehicle-derived Digital Outcrop Models (DOMs). The proposed workflow combines manual extraction of discontinuity data from the DOM with a kinematic analysis using an automated algorithm (ROKA), which upgrades and renews the traditional Markland's test. The case study, a designed railway tunnel portal in NW Italy (Finale Ligure) demonstrates the advantages and limitations of this approach compared to current methods. Manual mapping is compared with (semi-)automatic extraction of discontinuity data from the DOM and validated with field-based scan lines. The results show that in complex geological settings, manual mapping provides more statistically robust and geologically reliable measurements of discontinuity orientation, validated by the user's expertise. Traditional stereographic approaches in kinematic analysis are limited in characterizing spatially variable slopes and discontinuity networks, providing only generic estimations of unstable slope surfaces and discontinuity intersections. This limitation is overcome by new algorithms that incorporate 3D spatial relationships of both the discontinuity network and the rock slope, resulting in a more accurate and site-specific kinematic characterization of the rock cliff, emphasized by 3D visualizations of the critical planes and potential rock failure volumes. The new approach significantly impacts the time, effort, and cost of the engineering projects, allowing to quantitatively define the potential unstable areas with a fast analysis. The Authors stress the importance of integrating digital workflows with comprehensive field-based characterizations of the local litho-stratigraphic and structural setting to effectively utilize large datasets and partially automated procedures.

States of Resistance: nosocomial and environmental approaches to antimicrobial resistance in Lebanon

Drawing on institutional historical records, interviews and student theses, this article charts the intersection of hospital acquired illness, the emergence of antimicrobial resistance (AMR), environments of armed conflict, and larger questions of social governance in the specific case of the American University of Beirut Medical Center (AUBMC) in Lebanon. Taking a methodological cue from approaches in contemporary scientific work that understand non-clinical settings as a fundamental aspect of the history and development of AMR, we treat the hospital as not just nested in a set of social and environmental contexts, but frequently housing within itself elements of social and environmental history. AMR in Lebanon differs in important ways from the settings in which global protocols for infection control or rubrics for risk factor identification for resistant nosocomial outbreaks were originally generated. While such differences are all too often depicted as failures of low and middle-income countries (LMIC) to maintain universal standards, the historical question before us is quite the reverse: how have the putatively universal rubrics of AMR and hospital infection control failed to take account of social and environmental conditions that clearly matter deeply in the evolution and spread of resistance? Focusing on conditions of war as an organized chaos in which social, environmental and clinical factors shift dramatically, on the social and political topography of patient transfer, and on a missing “meso” level of AMR surveillance between the local and global settings, we show how a multisectoral One Health approach to AMR could be enriched by an answering multisectoral methodology in history, particularly one that unsettles a canonical focus on the story of AMR in the Euro-American context.

“They don't have the luxury of time”: interviews exploring the determinants of public health research activity that contextualise embedded researcher roles in local government

BackgroundEmbedded researchers are a novel intervention to improve the translation of research evidence into policy and practice settings, including public health. These roles are being implemented with increasing popularity, but they often lack clear evaluative frameworks. Understanding initial levels of research activity, including associated barriers and opportunities, is essential to developing theories of change and thus shaping the roles and defining expectations. We aimed to identify the principal determinants of research activity in public health that contextualise embedded researcher roles, including attributes of the embedded researcher themselves.MethodsWe undertook seventeen semi-structured interviews with embedded researchers in diverse public health settings in English local government. Interviews were analysed using thematic analysis.ResultsWe identified thirteen interlinked determinants of research activity within local government public health settings. Research and interpersonal skills, as well as pre-existing connections and knowledge within local government, were highly valued individual attributes for embedded researchers. Resource deficiencies (funding, time, and infrastructure) were primary barriers to research activity, whereas a strong local appetite for evidence informed decision making presented a valuable opportunity. However, there was inconsistencies across public health teams relating to perceptions of what constituted “research” and the resources that would be required.ConclusionsOur results suggest that successful embedded researchers will have equally strong research and communication skills and should be offered mentorship and clear career progression pathways. Perceptions of research within local government are closely linked to resource deficiencies and senior endorsement. Embedded researchers could benefit from taking the time to develop locally contextualised knowledge of this research culture. Theories of change for embedded researchers should conceptualise the interconnections across individual, interpersonal, and organisational barriers and opportunities underlying local government research activity. Further research is needed to identify methods for exploring the influence of embedded researchers as well as to unpack the stages of research activity within local government and the associated behaviours.

Automatic Quality Assessment of Pork Belly via Deep Learning and Ultrasound Imaging.

Pork belly, prized for its unique flavor and texture, is often overlooked in breeding programs that prioritize lean meat production. The quality of pork belly is determined by the number and distribution of muscle and fat layers. This study aimed to assess the number of pork belly layers using deep learning techniques. Initially, semantic segmentation was considered, but the intersection over union (IoU) scores for the segmented parts were below 70%, which is insufficient for practical application. Consequently, the focus shifted to image classification methods. Based on the number of fat and muscle layers, a dataset was categorized into three groups: three layers (n = 1811), five layers (n = 1294), and seven layers (n = 879). Drawing upon established model architectures, the initial model was refined for the task of learning and predicting layer traits from B-ultrasound images of pork belly. After a thorough evaluation of various performance metrics, the ResNet18 model emerged as the most effective, achieving a remarkable training set accuracy of 99.99% and a validation set accuracy of 96.22%, with corresponding loss values of 0.1478 and 0.1976. The robustness of the model was confirmed through three interpretable analysis methods, including grad-CAM, ensuring its reliability. Furthermore, the model was successfully deployed in a local setting to process B-ultrasound video frames in real time, consistently identifying the pork belly layer count with a confidence level exceeding 70%. By employing a scoring system with 100 points as the threshold, the number of pork belly layers in vivo was categorized into superior and inferior grades. This innovative system offers immediate decision-making support for breeding determinations and presents a highly efficient and precise method for assessment of pork belly layers.