[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3087":3,"related-3087":38},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"search_phrases":21,"slug":22,"view_count":15,"doi":23,"paper":24,"created_at":37},3087,"Loss-Aware Residual Learning for Imbalanced Multi-Class Diabetic Retinopathy Diagnosis","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijhpr.vol.11.no2.2026.pg1.41","Diabetic Retinopathy (DR) is a severe complication of diabetes that can lead to vision impairment or blindness, making early detection crucial. Traditional deep learning models often struggle with class imbalance in medical datasets, leading to poor performance for minority classes. This study proposes a novel deep learning model based on Residual Networks (ResNet) to address the multi class classification of DR, with a focus on mitigating class imbalance. Standard Softmax activation functions tend to favor majority classes, thereby worsening the model's performance on minority classes. To address this, the study incorporates a custom loss function, Balanced Softmax Loss, which adjusts class weights to improve the recognition of minority classes. Additionally, the model integrates advanced techniques such as Squeeze-and-Excitation (SE) blocks, learnable wavelet transforms, and multi-head attention mechanisms to enhance feature extraction and model performance. The model was trained and evaluated on the APTOS 2019 Blindness Detection dataset, achieving a micro-average accuracy of 0.83 and a macro-average accuracy of 0.73 in the 5-class classification task. In a 4-class classification task, where severe and proliferative DR were merged, the model achieved a micro-average accuracy of 0.87 and a macro-average accuracy of 0.84. The model's interpretability was further enhanced through Explainable AI (XAI) techniques such as LIME, Grad-CAM, and SHAP. The trained model was deployed as a web-based application using Flask, enabling real-time classification of retinal images. The study highlights the model's effectiveness in addressing class imbalance and its potential for early DR diagnosis, thereby enhancing clinical decision support.","糖尿病视网膜病变（Diabetic Retinopathy, DR）是糖尿病的一种严重并发症，可导致视力损害甚至失明，因此早期检测至关重要。传统的深度学习模型在处理医学数据集中的类别不平衡问题时往往表现不佳，导致少数类别的识别性能较差。本研究提出了一种基于残差网络（Residual Networks, ResNet）的新型深度学习模型，用于DR的多类别分类，重点在于缓解类别不平衡问题。标准Softmax激活函数倾向于偏向多数类别，从而加剧了模型在少数类别上的性能不足。为解决这一问题，本研究引入了一种自定义损失函数——平衡Softmax损失（Balanced Softmax Loss），通过调整类别权重来提升少数类别的识别能力。此外，该模型还集成了挤压-激励（Squeeze-and-Excitation, SE）模块、可学习小波变换和多头注意力机制等先进技术，以增强特征提取和模型性能。该模型在APTOS 2019盲ness Detection数据集上进行了训练和评估，在5分类任务中取得了0.83的微平均准确率和0.73的宏平均准确率。在将严重型和增殖型DR合并的4分类任务中，模型取得了0.87的微平均准确率和0.84的宏平均准确率。通过LIME、Grad-CAM和SHAP等可解释人工智能（Explainable AI, XAI）技术，进一步增强了模型的可解释性。训练后的模型通过Flask部署为基于Web的应用程序，实现了视网膜图像的实时分类。本研究凸显了该模型在解决类别不平衡问题方面的有效性及其在DR早期诊断中的潜力，从而增强了临床决策支持。",null,"INTERNATIONAL JOURNAL OF HEALTH AND PHARMACEUTICAL RESEARCH","2026-09-18T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该论文研究糖尿病视网膜病变的深度学习诊断，属医学影像领域，与三农、农业信息化、智慧农业无关，不建议进入每日精选。",[19],{"name":10,"url":6},[12],[],"Loss-AwareResidualLearningforImbalancedM-3087","10.56201\u002Fijhpr.vol.11.no2.2026.pg1.41",{"doi":23,"openalex_id":25,"authors":26,"venue":10,"cited_by_count":15,"oa_url":29,"card":30,"direction":34,"ingested_from":36},"W7213544946",[27],{"name":28,"orcid":9},"Miracle Ugomma Anunobi","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJHPR\u002FVOL. 11 NO. 2 2026\u002FLOSS AWARE RESIDUAL LEARNING 1-41.pdf",{"tldr":31,"method":32,"finding":33,"direction":34,"opportunity":35},"提出基于ResNet的损失感知残差学习模型，解决糖尿病视网膜病变多分类中的类别不平衡问题。","ResNet结合平衡Softmax损失、SE块、可学习小波变换和多头注意力，在A","5类分类微平均准确率0.83、宏平均0.73；合并严重与增殖期后4类分类微平均0.87、宏平均0.8","农业人工智能与决策模型","将损失感知残差学习与类别不平衡处理策略迁移至农业病害多分类诊断，提升少数类识别能力。","openalex","2026-09-21T23:30:43.782875Z",{"total":39,"page":40,"page_size":39,"items":41},6,1,[42,73,105,143,173,201],{"id":43,"title":44,"url":45,"summary":46,"summary_zh":47,"content":9,"source_name":48,"source_url":45,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":49,"sources":51,"tags":53,"search_phrases":54,"slug":55,"view_count":15,"doi":56,"paper":57,"created_at":72},3085,"Large language models in healthcare: applications, evaluation frameworks, and governance pathways — a scoping review and multidimensional framework","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffdgth.2026.1865568","Background Large language models (LLMs) are increasingly evaluated for healthcare applications spanning clinical documentation, decision support, patient communication, research assistance, and operational workflows. Despite rapid adoption interest, evidence remains heterogeneous and standardised approaches for evaluation and governance are not yet consistently applied. Objective To map healthcare applications of LLMs, synthesise reported outcomes and risks, and propose a multidimensional evaluation and governance framework oriented toward digital-health implementation. Methods A scoping review was conducted following the methodological guidance of Arksey and O'Malley, Levac et al., and the Joanna Briggs Institute, with reporting aligned to the PRISMA-ScR checklist. The protocol was prospectively registered on the Open Science Framework https:\u002F\u002Fdoi.org\u002F10.17605\u002FOSF.IO\u002FSWP78 ). Searches were performed in PubMed\u002FMEDLINE, Embase, Scopus, Web of Science, IEEE Xplore, ACM Digital Library, and the ACL Anthology, supplemented by medRxiv\u002FbioRxiv preprint searches and grey-literature scanning of WHO, FDA, and EU AI-Office guidance, covering 1 January 2019–30 April 2026. Title\u002Fabstract and full-text screening were carried out in duplicate; inter-rater agreement was Cohen's κ = 0.78. Data were extracted in duplicate using a piloted form. Synthesis followed Braun and Clarke's six-phase reflexive thematic analysis. The complete list of 78 included studies is provided in Supplementary File S4. Results Seventy-eight studies met inclusion criteria; 68% were published between 2023 and 2025. Five application domains were identified: (1) clinical documentation and summarisation; (2) clinical decision support and reasoning assistance; (3) patient communication and health-literacy support; (4) biomedical research and knowledge synthesis; and (5) administrative and operational use cases. The evidence base was dominated by benchmark and simulated-workflow studies (89%), with limited prospective workflow-embedded evaluations (11%). Reported benefits concentrated on documentation efficiency, text quality, and knowledge synthesis; safety-relevant risks included hallucinated content, omission of clinically critical information, demographic bias, privacy vulnerabilities, limited explainability, and automation bias. Studies were geographically concentrated in North America and East Asia, with limited representation from Sub-Saharan Africa, South Asia, and Latin America. Conclusions Current evidence supports cautious deployment of LLMs in selected healthcare tasks under structured oversight. Translational progress depends on prospective evaluation, standardised reporting, equity-focused audits, and lifecycle governance with continuous monitoring. The proposed five-dimensional framework (technical performance, clinical validity, equity, workflow integration, governance) coupled with a three-tier risk model is intended to support researchers and healthcare organisations in assessing readiness and implementing LLM-enabled tools responsibly.","背景 大语言模型（Large Language Models, LLMs）在医疗健康领域的应用评估日益增多，涵盖临床文档、决策支持、患者沟通、研究辅助和运营工作流程。尽管应用兴趣迅速增长，但证据仍呈现异质性，评估与治理的标准化方法尚未得到一致应用。目的 梳理大语言模型在医疗健康领域的应用，综合已报告的结局与风险，并提出面向数字健康实施的多维评估与治理框架。方法 按照Arksey和O'Malley、Levac等人以及乔安娜布里格斯研究所的方法学指导开展范围综述，报告遵循PRISMA-ScR清单。研究方案已在开放科学框架（Open Science Framework）前瞻性注册（https:\u002F\u002Fdoi.org\u002F10.17605\u002FOSF.IO\u002FSWP78）。检索在PubMed\u002FMEDLINE、Embase、Scopus、Web of Science、IEEE Xplore、ACM Digital Library和ACL Anthology中进行，并补充检索medRxiv\u002FbioRxiv预印本以及世界卫生组织（WHO）、美国食品药品监督管理局（FDA）和欧盟人工智能办公室（EU AI-Office）指南的灰色文献，覆盖2019年1月1日至2026年4月30日。标题\u002F摘要和全文筛选由两人独立完成；评分者间一致性为Cohen's κ = 0.78。数据采用经预试验的表格由两人独立提取。综合采用Braun和Clarke的六阶段反思性主题分析法。78项纳入研究的完整列表见补充文件S4。结果 78项研究符合纳入标准；68%发表于2023年至2025年间。识别出五个应用领域：（1）临床文档与摘要生成；（2）临床决策支持与推理辅助；（3）患者沟通与健康素养支持；（4）生物医学研究与知识综合；（5）行政与运营用例。证据基础以基准测试和模拟工作流程研究为主（89%），前瞻性嵌入工作流程的评估有限（11%）。已报告的获益集中在文档效率、文本质量和知识综合方面；与安全相关的风险包括幻觉内容、临床关键信息遗漏、人口统计学偏倚、隐私漏洞、可解释性有限和自动化偏倚。研究在地理上集中于北美和东亚，撒哈拉以南非洲、南亚和拉丁美洲的代表性有限。结论 Cu","Frontiers in Digital Health",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":50},"该文为医疗领域大语言模型的范围综述，与三农、农业信息化、智慧农业等主题无关，不予入选。",[52],{"name":48,"url":45},[12],[],"Largelanguagemodelsinhealthcare:applicat-3085","10.3389\u002Ffdgth.2026.1865568",{"doi":56,"openalex_id":58,"authors":59,"venue":48,"cited_by_count":15,"oa_url":64,"card":65,"direction":71,"ingested_from":36},"W7213552002",[60,62],{"name":61,"orcid":9},"João C. Ferreira",{"name":63,"orcid":9},"Isabel Rosa","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fdigital-health\u002Farticles\u002F10.3389\u002Ffdgth.2026.1865568\u002Fpdf",{"tldr":66,"method":67,"finding":68,"direction":69,"opportunity":70},"综述医疗大模型应用，提出多维评估与治理框架。","范围综述，检索7大数据库及灰色文献，主题分析78项研究。","应用分五域，证据多为基准测试，缺前瞻性嵌入评估，风险含幻觉与偏见。","其他","医疗LLM评估治理框架可迁移至农业大模型，填补农业场景前瞻性验证空白。","数字乡村与农业信息化","2026-09-21T23:30:36.936121Z",{"id":74,"title":75,"url":76,"summary":77,"summary_zh":78,"content":9,"source_name":79,"source_url":76,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":80,"sources":82,"tags":84,"search_phrases":85,"slug":86,"view_count":15,"doi":87,"paper":88,"created_at":104},3077,"A Computer Vision Survey of the Northern San Juan","https:\u002F\u002Fdoi.org\u002F10.1017\u002Faaq.2026.10223","Abstract As computer vision becomes more popular in archaeology, it is imperative to develop best practices that balance the interpretive and analytically critical tendencies of manual survey with the systemization and efficiency promised by machine learning. Using a case study from the northern US Southwest, we demonstrate an iterative image classification approach that reflects the methodological processes that play out in field research and preserves the role of humans as nuanced decision-makers. We develop a model to identify ancestral Pueblo residential sites and use it to survey an area larger than 16,000 km 2 . The semiautomated survey identified 4,905 likely archaeological features, marking one of the largest remote archaeological surveys in North America. Results not only emphasize the value of integrated computer vision for archaeological survey and site prediction but also demonstrate a research design that capitalizes on the computational value of computer vision while maintaining active engagement by the researcher.","摘要 随着计算机视觉在考古学中日益普及，亟需制定最佳实践，以平衡人工调查的解释性与分析批判性倾向同机器学习所承诺的系统化与效率之间的关系。通过美国西南部北部的一个案例研究，我们展示了一种迭代式图像分类方法，该方法反映了田野研究中实际展开的方法论过程，并保留了人类作为细致决策者的角色。我们开发了一个模型来识别祖先普韦布洛（Pueblo）居住遗址，并用其调查了超过16,000平方公里的区域。这种半自动化调查识别出4,905个可能的考古特征，是北美规模最大的远程考古调查之一。研究结果不仅强调了集成计算机视觉在考古调查与遗址预测中的价值，还展示了一种研究设计，该设计在利用计算机视觉计算价值的同时，保持了研究者的积极参与。","American Antiquity",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":81},"考古学计算机视觉调查论文，与三农、农业信息化、智慧农业主题无关，不予入选。",[83],{"name":79,"url":76},[12],[],"AComputerVisionSurveyoftheNorthernSanJua-3077","10.1017\u002Faaq.2026.10223",{"doi":87,"openalex_id":89,"authors":90,"venue":79,"cited_by_count":15,"oa_url":97,"card":98,"direction":102,"ingested_from":36},"W7213548823",[91,94],{"name":92,"orcid":93},"Sean Field","https:\u002F\u002Forcid.org\u002F0000-0002-3144-5796",{"name":95,"orcid":96},"L. A. Dean","https:\u002F\u002Forcid.org\u002F0009-0000-7038-8176","https:\u002F\u002Fwww.cambridge.org\u002Fcore\u002Fservices\u002Faop-cambridge-core\u002Fcontent\u002Fview\u002F6BE98BA78AE0BFF7A688E579B669BB8F\u002FS0002731626102236a.pdf\u002Fdiv-class-title-a-computer-vision-survey-of-the-northern-san-juan-div.pdf",{"tldr":99,"method":100,"finding":101,"direction":102,"opportunity":103},"用迭代图像分类模型识别祖先普韦布洛居住遗址，半自动调查超1.6万平方公里区域。","迭代图像分类、计算机视觉模型，遥感影像，考古遗址识别。","识别出4905个可能考古特征，是北美最大远程考古调查之一。","农业遥感与作物表型","可借鉴其迭代人机协同方法，用于农业遗址或耕地遥感识别与制图。","2026-09-21T23:30:25.985394Z",{"id":106,"title":107,"url":108,"summary":109,"summary_zh":110,"content":9,"source_name":111,"source_url":108,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":112,"sources":114,"tags":116,"search_phrases":117,"slug":118,"view_count":15,"doi":119,"paper":120,"created_at":142},3063,"The Impact of AI-Powered Decision Support Systems on Decision-Making Effectiveness","https:\u002F\u002Fdoi.org\u002F10.26877\u002Fasset.v8i4.2432","AI-powered Decision Support Systems (AI-DSS) enhance analytical capabilities through advanced data processing, predictive analytics, and intelligent decision support. This study investigates the impact of AI-powered DSS on decision-making effectiveness across multiple sectors. A quantitative research design was employed using a structured questionnaire distributed to 33 professionals and decision-makers experienced in AI-based DSS. Decision-making effectiveness was assessed through decision accuracy, decision-making speed, operational efficiency, and user satisfaction. Data were analyzed using descriptive statistics, Pearson correlation, and simple linear regression. The results show a moderate positive correlation between AI usage and decision-making effectiveness (r = 0.550, p \u003C 0.001). Regression analysis further demonstrates that AI utilization significantly predicts decision-making effectiveness (B = 0.265, t = 3.664, p \u003C 0.001). These findings indicate that greater utilization of AI-powered DSS is associated with improved decision outcomes, particularly in decision accuracy, response speed, and operational efficiency. The study also demonstrates the applicability of AI techniques, including machine learning, neural networks, fuzzy logic, and Bayesian modelling, across diverse industrial contexts. Overall, the findings provide empirical evidence that AI-powered DSS contribute significantly to organizational decision-making effectiveness across multiple sectors.","人工智能驱动的决策支持系统（AI-DSS）通过先进的数据处理、预测分析和智能决策支持增强分析能力。本研究探讨了人工智能驱动的决策支持系统在多个行业中对决策有效性的影响。研究采用定量研究设计，使用结构化问卷，向33位具有基于人工智能的决策支持系统经验的专业人士和决策者发放。决策有效性通过决策准确性、决策速度、运营效率和用户满意度进行评估。数据采用描述性统计、皮尔逊相关和简单线性回归进行分析。结果显示，人工智能使用与决策有效性之间存在中等程度的正相关（r = 0.550，p \u003C 0.001）。回归分析进一步表明，人工智能的使用显著预测决策有效性（B = 0.265，t = 3.664，p \u003C 0.001）。这些发现表明，人工智能驱动的决策支持系统使用程度越高，决策结果越好，尤其是在决策准确性、响应速度和运营效率方面。研究还展示了人工智能技术（包括机器学习、神经网络、模糊逻辑和贝叶斯建模）在不同工业场景中的适用性。总体而言，研究结果提供了实证证据，表明人工智能驱动的决策支持系统对多个行业中的组织决策有效性具有显著贡献。","Advance Sustainable Science Engineering and Technology",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":113},"研究AI决策支持系统对决策效能的影响，属通用管理信息系统议题，未涉及三农或农业信息化场景，相关性不足。",[115],{"name":111,"url":108},[12],[],"TheImpactofAI-PoweredDecisionSupportSyst-3063","10.26877\u002Fasset.v8i4.2432",{"doi":119,"openalex_id":121,"authors":122,"venue":111,"cited_by_count":15,"oa_url":135,"card":136,"direction":141,"ingested_from":36},"W7213533827",[123,126,129,132],{"name":124,"orcid":125},"Edi Priyanto","https:\u002F\u002Forcid.org\u002F0000-0002-9819-7598",{"name":127,"orcid":128},"Nur Wening","https:\u002F\u002Forcid.org\u002F0000-0002-9513-5201",{"name":130,"orcid":131},"Rianto Rianto","https:\u002F\u002Forcid.org\u002F0000-0002-5058-4580",{"name":133,"orcid":134},"Tri Gunarsih","https:\u002F\u002Forcid.org\u002F0000-0001-6827-2510","https:\u002F\u002Fjournal2.upgris.ac.id\u002Findex.php\u002Fasset\u002Farticle\u002Fdownload\u002F2432\u002F1735",{"tldr":137,"method":138,"finding":139,"direction":34,"opportunity":140},"研究AI决策支持系统对多行业决策效果的影响，发现使用越多效果越好。","对33名AI-DSS使用者问卷调查，用相关与回归分析。","AI使用与决策效果中度正相关，能显著预测决策准确性、速度与效率。","可将该框架迁移到农业场景，验证AI-DSS对农户与农企决策效果的因果影响。","智慧农业 \u002F 农业物联网","2026-09-21T23:30:10.625088Z",{"id":144,"title":145,"url":146,"summary":147,"summary_zh":148,"content":9,"source_name":149,"source_url":146,"published_at":150,"category":12,"cover_url":9,"hotness":151,"is_selected":14,"score":15,"score_detail":152,"sources":154,"tags":158,"search_phrases":159,"slug":160,"view_count":15,"doi":161,"paper":162,"created_at":172},3011,"Absence of Rashba, Winding, and Möbius Topology in Submitted Abstracts — E8 Intelligence Research","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22841585","FINDING: The submitted abstracts contain no direct research on Rashba spin-orbit coupling, winding numbers, or Möbius momentum-space topology. The closest mathematical content is in graph recoloring (treewidth 2) and fine-structure constant wavelength precision. | MATH: No equations, constants, or ratios from the target domain appear. The graph theory result references Jerrum's theorem on $(d+2)$-colorings of $d$-degenerate graphs; the astrophysics item cites a precision threshold of $6 \\times 10^{-8}$ for laboratory wavelengths. | CONNECTION: None to 0.382, 0.618, 0.786, 1.618, 2.618, base-60, or crystallographic symmetries. The treewidth-2 graph class relates to series-parallel graphs, which have a recursive decomposition but no direct golden-ratio or root-system link. | DEPTH: 1 — The query's target domain is entirely absent; the retrieved items are unrelated (hexaquark decay, traffic hydrodynamics, graph recoloring, atomic spectroscopy, plant phenotyping). No mathematical essence f Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com","发现：所提交的摘要中没有关于Rashba自旋轨道耦合、绕数或莫比乌斯动量空间拓扑的直接研究。最接近的数学内容在图重着色（树宽为2）和精细结构常数波长精度方面。| 数学：目标领域中没有出现方程、常数或比率。图论结果引用了Jerrum关于$d$-退化图的$(d+2)$着色定理；天体物理学条目引用了实验室波长$6 \\times 10^{-8}$的精度阈值。| 联系：与0.382、0.618、0.786、1.618、2.618、六十进制或晶体学对称性均无联系。树宽为2的图类与串并联图相关，后者具有递归分解，但与黄金比例或根系统没有直接联系。| 深度：1——查询的目标领域完全缺失；检索到的条目不相关（六夸克衰变、交通流体动力学、图重着色、原子光谱学、植物表型分析）。没有数学本质 f 作者：Andrew Stewart Caldin，独立研究员，英国。E8 Intelligence Research系列的一部分。平台：e8intelligence.com","Zenodo (CERN European Organization for Nuclear Research)","2026-09-19T00:00:00Z",25,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":153},"该资讯为独立研究者关于Rashba自旋轨道耦合、绕数与Möbius拓扑缺失的数学物理预印本，与三农、农业信息化、智慧农业、数字乡村等主题完全无关，不具备入选价值。",[155,156],{"name":149,"url":146},{"name":149,"url":157},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22841584",[12],[],"AbsenceofRashba,Winding,andMöbiusTopolog-3011","10.5281\u002Fzenodo.22841585",{"doi":161,"openalex_id":163,"authors":164,"venue":149,"cited_by_count":15,"oa_url":146,"card":167,"direction":102,"ingested_from":36},"W7213652043",[165],{"name":166,"orcid":9},"Andrew Stewart Caldin",{"tldr":168,"method":169,"finding":170,"direction":69,"opportunity":171},"检索提交摘要，确认其中没有关于Rashba自旋轨道耦合、绕数或莫比乌斯动量空间拓扑的研究。","对提交摘要做关键词与数学内容检索，比对目标域常数与图论、天体物理条目。","目标域完全缺失，最接近内容仅为树宽2图重着色与精细结构常数波长精度。","可探索图论递归分解与凝聚态拓扑不变量之间是否存在未被识别的数学联系。","2026-09-20T23:30:18.563518Z",{"id":174,"title":175,"url":176,"summary":177,"summary_zh":178,"content":9,"source_name":179,"source_url":176,"published_at":180,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":181,"sources":183,"tags":185,"search_phrases":186,"slug":187,"view_count":15,"doi":188,"paper":189,"created_at":200},2957,"Multi-Criteria Evaluation Of Student Career Readiness Using An Intelligent Topsis-Based Decision Support System","https:\u002F\u002Fdoi.org\u002F10.59435\u002Fjocstec.v4i3.871","The assessment of student career readiness requires a systematic approach that considers multiple competencies and experiences relevant to workplace demands. This study develops an intelligent decision support system based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to evaluate and map student career readiness. The study uses 20 student samples and five assessment criteria: field-specific competence (C1), internship experience (C2), communication skills (C3), digital literacy (C4), and English language proficiency (C5). Each criterion is assigned a weight based on its relative importance. The TOPSIS method involves decision matrix construction, normalization, weighted normalization, determination of positive and negative ideal solutions, distance calculation, and preference value calculation. The results show that Y11 achieved the highest preference value of 0.8296, followed by Y6 (0.7951), Y19 (0.7274), Y5 (0.7116), and Y2 (0.6999), while Y9 obtained the lowest preference value of 0.3112. Based on the classification results, 1 student (5%) was categorized as Highly Ready, 5 students (25%) as Ready, 12 students (60%) as Moderately Ready, and 2 students (10%) as Not Ready. These findings demonstrate that TOPSIS can effectively rank and classify student career readiness based on multiple assessment criteria. The proposed system can support higher education institutions in identifying students’ readiness levels and developing more objective, targeted, and data-driven career development strategies.","学生职业准备度的评估需要一种系统化方法，综合考虑与职场需求相关的多种能力和经历。本研究开发了一种基于逼近理想解排序法（TOPSIS）的智能决策支持系统，用于评估和映射学生的职业准备度。研究采用20个学生样本和五项评估标准：专业领域能力（C1）、实习经历（C2）、沟通能力（C3）、数字素养（C4）和英语语言能力（C5）。每项标准根据其相对重要性赋予权重。TOPSIS方法包括决策矩阵构建、归一化、加权归一化、正负理想解的确定、距离计算以及偏好值计算。结果表明，Y11获得了最高偏好值0.8296，其次是Y6（0.7951）、Y19（0.7274）、Y5（0.7116）和Y2（0.6999），而Y9获得了最低偏好值0.3112。根据分类结果，1名学生（5%）被归类为高度准备，5名学生（25%）为准备充分，12名学生（60%）为中等准备，2名学生（10%）为尚未准备。这些发现表明，TOPSIS能够基于多项评估标准有效对学生职业准备度进行排序和分类。所提出的系统可以支持高等教育机构识别学生的准备水平，并制定更加客观、有针对性和数据驱动的职业发展策略。","Journal Of Computer Science And Technology (JOCSTEC)","2026-09-17T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":182},"该论文研究基于TOPSIS的学生职业准备度评估，属教育信息化领域，与三农、农业信息化、智慧农业、数字乡村等主题无关，不予入选。",[184],{"name":179,"url":176},[12],[],"Multi-CriteriaEvaluationOfStudentCareerR-2957","10.59435\u002Fjocstec.v4i3.871",{"doi":188,"openalex_id":190,"authors":191,"venue":179,"cited_by_count":15,"oa_url":194,"card":195,"direction":71,"ingested_from":36},"W7213442254",[192],{"name":193,"orcid":9},"Revi Gusriva","https:\u002F\u002Fjurnal.padangtekno.com\u002Findex.php\u002Fjocstec\u002Farticle\u002Fdownload\u002F871\u002F550",{"tldr":196,"method":197,"finding":198,"direction":34,"opportunity":199},"用TOPSIS多准则决策系统评估20名学生的职业准备度并排序分类。","TOPSIS方法，5项准则，20个学生样本，加权决策矩阵。","Y11得分最高0.8296，60%学生为中等准备，仅5%高度准备。","可将TOPSIS多准则决策迁移至农业人才或新型职业农民能力评估与精准培训。","2026-09-19T23:30:41.966555Z",{"id":202,"title":203,"url":204,"summary":205,"summary_zh":206,"content":9,"source_name":207,"source_url":204,"published_at":180,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":208,"sources":210,"tags":212,"search_phrases":213,"slug":214,"view_count":15,"doi":215,"paper":216,"created_at":239},2938,"TEKNO Method: Total Evaluation based on Knowledge-driven Normalized Optimization for Multi-Criteria Decision Making","https:\u002F\u002Fdoi.org\u002F10.67449\u002Fjodesma.v1i2.7","Multi-criteria decision making (MCDM) methods play an important role in supporting decisions involving multiple criteria with different characteristics and levels of importance. However, differences in normalization procedures, criterion treatment, and aggregation mechanisms can lead to variations in the resulting preference structures. This study proposes a new MCDM method, namely total evaluation based on knowledge-driven normalized optimization (TEKNO), which integrates normalization, relative evaluation, criterion weighting, optimization-based normalization, and total evaluation into a unified decision-making framework. The proposed method is designed to transform heterogeneous decision information into comparable evaluation values while preserving the relative contribution of each criterion. The applicability of TEKNO is evaluated through two decision-making case studies involving new store location selection and leasing customer selection. The evaluation framework includes ranking analysis, comparison with established MCDM methods, Spearman rank correlation analysis, and sensitivity analysis under variations in criterion weights. The results show that TEKNO achieves a Spearman rank correlation coefficient of 1.0000 for the new store location case and 0.9964 for the leasing customer selection case, indicating very strong agreement with the reference rankings. In addition, the ranking remains unchanged across the tested sensitivity scenarios, demonstrating the stability of TEKNO under variations in criterion weights. These findings indicate that TEKNO provides a transparent, systematic, and stable alternative for MCDM applications for practical decision support where reliable ranking, methodological transparency, and robustness across alternative evaluation conditions are required. Nevertheless, broader validation using diverse datasets, decision domains, weighting schemes, and statistical evaluation techniques is required to further establish its generalizability and comparative performance.","多准则决策（MCDM）方法在支持涉及多个具有不同特征和重要性水平的准则的决策中发挥着重要作用。然而，归一化程序、准则处理和聚合机制的差异可能导致所得偏好结构发生变化。本研究提出了一种新的MCDM方法，即基于知识驱动归一化优化的总体评价（TEKNO），该方法将归一化、相对评价、准则赋权、基于优化的归一化和总体评价整合到一个统一的决策框架中。所提出的方法旨在将异构决策信息转化为可比较的评价值，同时保留每个准则的相对贡献。TEKNO的适用性通过两个决策案例研究进行评估，分别涉及新店选址和租赁客户选择。评价框架包括排序分析、与已有MCDM方法的比较、Spearman秩相关分析以及准则权重变化下的敏感性分析。结果表明，TEKNO在新店选址案例中的Spearman秩相关系数为1.0000，在租赁客户选择案例中为0.9964，表明与参考排序具有极强的一致性。此外，在测试的敏感性情景下排序保持不变，表明TEKNO在准则权重变化下具有稳定性。这些发现表明，TEKNO为MCDM应用提供了一种透明、系统且稳定的替代方案，适用于需要可靠排序、方法透明性以及在不同评价条件下具有稳健性的实际决策支持。然而，仍需使用多样化的数据集、决策领域、赋权方案和统计评价技术进行更广泛的验证，以进一步确立其普适性和比较性能。","OpenAlex",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":209},"该论文为通用多准则决策方法研究，与三农、农业信息化、智慧农业等主题无关，不予入选。",[211],{"name":207,"url":204},[12],[],"TEKNOMethod:TotalEvaluationbasedonKnowle-2938","10.67449\u002Fjodesma.v1i2.7",{"doi":215,"openalex_id":217,"authors":218,"venue":232,"cited_by_count":15,"oa_url":233,"card":234,"direction":141,"ingested_from":36},"W7213447260",[219,222,225,227,229],{"name":220,"orcid":221},"Yuri Rahmanto","https:\u002F\u002Forcid.org\u002F0000-0001-9673-4364",{"name":223,"orcid":224},"Ryan Randy Suryono","https:\u002F\u002Forcid.org\u002F0000-0001-9378-8148",{"name":226,"orcid":9},"Dedi Darwis",{"name":228,"orcid":9},"Abhishek R. Mehta",{"name":230,"orcid":231},"Auliya Rahman Isnain","https:\u002F\u002Forcid.org\u002F0000-0002-8468-6366","Journal of Decision Support Systems and Multi-Criteria Decision Making","https:\u002F\u002Fresearch.pilar.or.id\u002Findex.php\u002Fjodesma\u002Farticle\u002Fdownload\u002F7\u002F16",{"tldr":235,"method":236,"finding":237,"direction":34,"opportunity":238},"提出TEKNO多准则决策方法，统一归一化、加权与优化，实现稳定排序。","知识驱动归一化优化，结合Spearman相关与敏感性分析，用选址和客户选择案例验","TEKNO与参考排序高度一致（相关系数1.0000和0.9964），权重变化下排序稳定。","可将TEKNO用于农业多准则决策（如品种选择、灌溉方案），验证跨领域泛化性。","2026-09-19T23:30:17.840172Z"]