检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Skryagin, Arseny Ochs, Daniel Dhami, Devendra Singh Kersting, Kristian Computer Science Department TU Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Darmstadt Germany Darmstadt Germany

The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic programming Languages (DPPLs) have been developed for probabilistic logic programming to be carried out via the probability estimations of deep neural networks. However, recent SOTA DPPL approaches allow only for limited conditional probabilistic queries and do not offer the power of true joint probability estimation. In our work, we propose an easy integration of tractable probabilistic inference within a DPPL. To this end, we introduce SLASH, a novel DPPL that consists of Neural-Probabilistic Predicates (NPPs) and a logic program, united via answer set programming (ASP). NPPs are a novel design principle allowing for combining all deep model types and combinations thereof to be represented as a single probabilistic predicate. In this context, we introduce a novel +/− notation for answering various types of probabilistic queries by adjusting the atom notations of a predicate. To scale well, we show how to prune the stochastically insignificant parts of the (ground) program, speeding up reasoning without sacrificing the predictive performance. We evaluate SLASH on a variety of different tasks, including the benchmark task of MNIST addition and Visual Question Answering (VQA). © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Effective Tumor Annotation for Automated Diagnosis of Liver Cancer

引用

IEEE Journal of Translational Engineering in Health and Medicine 2025年 13卷 251-260页

作者： Chuang, Yi-Hsuan Su, Ja-Hwung Lin, Tzu-Chieh Cheng, Hue-Xin Shen, Pin-Hao Ou, Jin-Ping Han, Ding-Hong Liao, Yi-Wen Lee, Yeong-Chyi Cheng, Yu-Fan Hong, Tzung-Pei Shu-Min Li, Katherine Lu, Yi Wang, Chih-Chi Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Liver Transplantation Program Departments of Diagnostic Radiology Niao-Sung District Kaohsiung 833401 Taiwan National University of Kaohsiung Department of Computer Science and Information Engineering Kaohsiung 811 Taiwan National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung 804 Taiwan National Kaohsiung University of Science and Technology Department of Intelligent Commerce Kaohsiung 824004 Taiwan Cheng Shiu University Department of Information Management Kaohsiung 833301 Taiwan Liver Transplantation Center Department of Surgery Kaohsiung Chang Gung Memorial Hospital Niao-Sung District Kaohsiung 833401 Taiwan

In recent years, visual cancer information retrieval using Artificial Intelligence has been shown to be effective in diagnosis and treatment. Especially for a modern liver-cancer diagnosis system, the automated tumor annotation plays a crucial role. So-called tumor annotation refers to tagging the tumor in Biomedical images by computer vision technologies such as Deep Learning. After annotation, the tumor information such as tumor location, tumor size and tumor characteristics can be output into a clinical report. To this end, this paper proposes an effective approach that includes tumor segmentation, tumor location, tumor measuring, and tumor recognition to achieve high-quality tumor annotation, thereby assisting radiologists in efficiently making accurate diagnosis reports. For tumor segmentation, a Multi-Residual Attention Unet is proposed to alleviate problems of vanishing gradient and information diversity. For tumor location, an effective Multi-SeResUnet is proposed to partition the liver into 8 couinaud segments. Based on the partitioned segments, the tumor is located accurately. For tumor recognition, an effective multi-labeling classifier is used to recognize the tumor characteristics by the visual tumor features. For tumor measuring, a regression model is proposed to measure the tumor size. To reveal the effectiveness of individual methods, each method was evaluated on real datasets. The experimental results reveal that the proposed methods are more promising than the state-of-the-art methods in tumor segmentation, tumor measuring, tumor localization and tumor recognition. Specifically, the average tumor size error and the annotation accuracy are 0.432 cm and 91.6%, respectively, which suggest potential for reducing radiologists’ workload. In summary, this paper proposes an effective tumor annotation for an automated diagnosis support system. Clinical and Translational Impact Statement—The proposed methods have been evaluated and shown to significantly imp

关键词： Liver cancer diagnosis liver tumor location liver tumor measuring liver tumor recognition liver tumor segmentation

来源：评论

学校读者我要写书评

暂无评论

Question Classification of University Admission using Named-Entity Recognition (NER)

Question Classification of University Admission using Named-...

引用

International Conference on Information Technology, computer and Electrical Engineering (ICITACEE)

作者： Emny Harna Yossy Derwin Suhartono Agung Trisetyarso Widodo Budiharto Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Mathematics Department School of Computer Science Bina Nusantara University Jakarta Indonesia

The university admission process can be overwhelming for applicants and admission officers, with many questions being asked and answered every year. The manual classification of these questions can be time-consuming and may lead to errors, making exploring automated solutions to this problem essential. In recent years, advances in natural language processing (NLP), including question classification. The research proposes an architecture for a question classification system using the Indonesian Language in closed-domain question answering. The purpose of this research is to find out the classification of questions. We created a system with the Named-Entity Recognition method to recognize the next word that will be used as a candidate type of question and candidate answer. The type of question used is a factoid question. Research makes patterns and rules for extracting important words as features to determine the taxonomy of question classification. Datasets are collected from one private university in Indonesia. Data sources from Binus Online Learning websites and data on questions frequently asked by users, especially prospective students. The results of the question classification are presented using descriptive statistics. The results show that the question classification with users’ most frequent question type is “What” by 63.3%, and the answer category is “tuition fees” by 22.4%. It can be concluded that the most frequent question type asked by users is “What”, and the most frequent topic of interest is “tuition fees”. Organizations can use this information to improve customer service by providing more relevant information and resources about tuition fees.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universal hydrogel adhesives with robust chain entanglement for bridging soft electronic materials

引用

npj Flexible Electronics 2024年第1期8卷 509-522页

作者： Yejin Jo Yurim Lee Jeong Hyun Heo Yeonzu Son Tae Young Kim Kijun Park Soye Kim Seo Jung Kim Yoonhee Jin Seongjun Park Jungmok Seo School of Electrical and Electronic Engineering Yonsei UniversitySeoul03722Republic of Korea Department of Physiology Yonsei University College of MedicineSeoul03722Republic of Korea Program of Brain and Cognitive Engineering Korea Advanced Institute of Science and Technology(KAIST)291 Daehak-roYuseong-guDaejeon34141Republic of Korea Department of Pediatrics Severance Children’s HospitalYonsei University College of MedicineSeoul03722Republic of Korea Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology(KAIST)291 Daehak-roYuseong-guDaejeon34141Republic of Korea Department of Materials Science and Engineering Korea Advanced Institute of Science and Technology(KAIST)291 Daehak-roYuseong-guDaejeon34141Republic of Korea KAIST Institute for Nano Century(KINC) 291 Daehak-roYuseong-guDaejeon34141Republic of Korea

Ensuring stable integration of diverse soft electronic components for reliable operation under dynamic conditions is ***,integrating soft electronics,comprising various materials like polymers,metals,and hydrogels,poses challenges due to their different mechanical and chemical *** study introduces a dried-hydrogel adhesive made of poly(vinyl alcohol)and tannic acid multilayers(d-HAPT),which integrates soft electronic materials through moisture-derived chain entanglement.d-HAPT is a thin(~1μm)and highly transparent(over 85%transmittance in the visible light region)adhesive,showing robust bonding(up to 3.6 MPa)within a short time(<1 min).d-HAPT demonstrates practical application in wearable devices,including a hydrogel touch panel and strain ***,the potential of d-HAPT for use in implantable electronics is demonstrated through in vivo neuromodulation and electrocardiographic recording experiments while confirming its biocompatibility both in vitro and in *** is expected that d-HAPT will provide a reliable platform for integrating soft electronic applications.

关键词： properties hydrogel electronic

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter optimization of orthogonal functions in the numerical solution of differential equations

arXiv

引用

arXiv 2023年

作者： Aghaei, Alireza Afzal Parand, Kourosh Department of Computer and Data Science Faculty of Mathematical Science Shahid Beheshti University Tehran Iran Department of Cognitive Modeling Institute for Cognitive and Brain Sciences Shahid Beheshti University Tehran Iran

This paper considers the hyperparameter optimization problem of mathematical techniques that arise in the numerical solution of differential and integral equations. The well-known approaches grid and random search, in a parallel algorithm manner, are developed to find the optimal set of hyperparameters. Employing rational Jacobi functions, we ran these algorithms on two nonlinear benchmark differential equations on the semi-infinite domain. The configurations contain different rational mappings along with their length scale parameter and the Jacobi functions parameters. These trials are configured on the collocation Least-Squares Support Vector Regression (CLS-SVR), a novel numerical simulation approach based on spectral methods. In addition, we have addressed the sensitivity of these hyperparameters on the numerical stability and convergence of the CLS-SVR model. The experiments show that this technique can effectively improve state-of-the-art results. © 2023, CC BY.

关键词： Orthogonal functions

来源：评论

学校读者我要写书评

暂无评论

Hoax Detection in Social Media: A Literature Review

Hoax Detection in Social Media: A Literature Review

引用

International Conference on Artificial Intelligence and Data sciences (AiDAS)

作者： Carsten Sebastian Saputra Norbert Wijaya Maria Susan Anggreainy Afdhal Kurniawan Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia

For both print and digital media, the accuracy of the information has long been a problem that has impacted society and the business world. Information travels so quickly on social networks and is amplified that it can be skewed, false, or misleading. Inaccurate or incorrect information has great potential to affect millions of real-world users directly. Therefore, finding or getting accurate, trusted, and precise information becomes a problem. People start to spread fake news, which can cause certain events, such as mental disturbance, riots, and unnecessary anxiety. To prevent these problems, we will solve/research them with CountVectorizer and TF-IDF, which is what this study is all about (Discusses the detection of hoax news using CountVectorizer and TF-IDF). It was found that using these methods makes it possible to detect which words are most common in fake news and real news.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptation and Generalization from Human-Inspired Meta-Reinforcement Learning Using Bayesian Knowledge and Analysis 6

Learning Adaptation and Generalization from Human-Inspired M...

引用

6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023

作者： Ho, Joshua Wang, Chien-Min King, Chung-Ta You, Yi-Hsin Feng, Chi-Wei Chen, Yen-Min Kuo, Bo-Yi Institute of Information Science Academia Sinica Taipei11529 Taiwan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Tsing Hua University Hsinchu30013 Taiwan Department of Computer Science National Taiwan University Taipei10631 Taiwan Center of Intelligent Healthcare National Taiwan University Hospital Taipei10022 Taiwan

ISBN: (纸本)9798350331288

Over the last decades, there has been growing interest in research in multiple and interdisciplinary fields of human-AI computing. In particular, approaches integrating the intersecting design with reinforcement learning (RL) have received more attention. However, the current research on RL may need to consider its enhancement from a humaninspired approach further. In the present work, we focus on enabling a meta-reinforcement learning (meta-RL) agent to achieve adaptation and generalization according to modeling Markov decision processes using Bayesian knowledge and analysis. By introducing a novel framework called human-inspired meta-RL (HMRL), we incorporate the agent performing resilient actions to leverage the dynamic dense reward based on the knowledge and prediction of a Bayesian analysis. The proposed framework can make the agent learn generalization and prevent the agent from failing catastrophically. The experimental results show that our approach helps the agent reduce computational costs with learning adaptation. Finally, we conclude and anticipate that integrating human-inspired meta-RL can enable learning more formulations relating to robustness and scalability, leading to promising directions and more complex AI goals in the future. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Investigating Student and Teacher Perceptions in e-Learning with Learning Analytics and Ontologies

International Journal of Emerging Technologies in Learning

引用

International Journal of Emerging Technologies in Learning 2023年第8期18卷 26-47页

作者： Costa, Laécio A. Silveira, Aleph C. Souza, Marlo Salvador, Laís N. Santos, Celso A. S. Informatics Collegiate Instituto Federal do Sertão Pernambucano PE Petrolina Brazil Computer Science Graduate Program Federal University of Bahia BA Salvador Brazil Department of Informatics Federal University of Espírito Santo ES Vitória Brazil

This work is an approach that brings together Learning Analytics and Ontologies for a data classification that promotes improvements and behavioral changes for students and teachers on e-Learning platforms. Combining training courses, dashboards, user’s evaluations, and based on Design science Research (DSR) methodology, artifacts were created. One of the most important artifacts of our work is the Sapes tool that aims to improve students’ perceptions of their learning path and to promote a better teacher overview to follow their students’ progress. The results showed high approval by the participating students and teachers, who perceived the Sapes tool as a good facilitator of the teaching-learning process, with possibilities for self-monitoring, dynamization of the learning sequence and better interactivity with colleagues, highlighted as absent in standard e-Learning courses. In addition, the application changed the behavior of users towards the content provided by the teacher, with students performing self-management and self-regulation that were not commonly performed previously. © 2023, International Journal of Emerging Technologies in Learning. All Rights Reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning Classifier Based on Genetic Algorithms and Data Importance Reformatting

arXiv

引用

arXiv 2024年

作者： Alkhayyat, A.K. Hewahi, N.M. Big Data Science and Analytics Program College of Science University of Bahrain Bahrain Department of Computer Science College of Information Technology University of Bahrain Bahrain

In this paper, a novel classification algorithm that is based on Data Importance (DI) reformatting and Genetic Algorithms (GA) named GADIC is proposed to overcome the issues related to the nature of data which may hinder the performance of the Machine Learning (ML) classifiers. GADIC comprises three phases which are data reformatting phase which depends on DI concept, training phase where GA is applied on the reformatted training dataset, and testing phase where the instances of the reformatted testing dataset are being averaged based on similar instances in the training dataset. GADIC is an approach that utilizes the exiting ML classifiers with involvement of data reformatting, using GA to tune the inputs, and averaging the similar instances to the unknown instance. The averaging of the instances becomes the unknown instance to be classified in the stage of testing. GADIC has been tested on five existing ML classifiers which are Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Logistic Regression (LR), Decision Tree (DT), and Naïve Bayes (NB). All were evaluated using seven open-source UCI ML repository and Kaggle datasets which are Cleveland heart disease, Indian liver patient, Pima Indian diabetes, employee future prediction, telecom churn prediction, bank customer churn, and tech students. In terms of accuracy, the results showed that, with the exception of approximately 1% decrease in the accuracy of NB classifier in Cleveland heart disease dataset, GADIC significantly enhanced the performance of most ML classifiers using various datasets. In addition, KNN with GADIC showed the greatest performance gain when compared with other ML classifiers with GADIC followed by SVM while LR had the lowest improvement. The lowest average improvement that GADIC could achieve is 5.96%, whereas the maximum average improvement reached 16.79%. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Digital Enterprise Architecture: Perspectives, Trends, and Technologies 9

Intelligent Digital Enterprise Architecture: Perspectives, T...

引用

9th International Conference on ICT for Smart Society, ICISS 2022

作者： Afriliana, Nunik Gaol, Ford Lumban Supangkat, Suhono Harso Ranti, Benny Computer Science Bina Nusantara University Computer Science Department Binus Graduate Program Jakarta11480 Indonesia Smart Cities and Communities Innovation Center Institut Teknologi Bandung Bandung40312 Indonesia

ISBN: (数字)9781665471350

ISBN: (纸本)9781665471350

Nowadays, many companies, industries, and organizations deal with digital disruption issues. They have to deal with it and take the initiative properly to keep their sustainability. Initiating a digital transformation by creating intelligent digital systems is one of many initiatives that could be considered to overcome these issues. Developing an intelligent digital system will maintain a company's performance, efficiency, and compliance. Numerous organizations are willing to create an intelligent digital system for their governance. However, they do not have sufficient knowledge on how to do it, including its enterprise architecture. Knowledge of enterprise architecture is an important part of properly developing an intelligent digital system. This research aimed to conduct a literature review to determine the perspective of the enterprise architecture model in intelligent digital system development. The second goal is to find recent trends and technology in intelligent digital enterprise architecture. Theoretically, it gives a contribution to providing a new perspective of more intelligent Enterprise Architecture with its trends and technologies compared to the old paradigm. Practically, it will contribute to providing an overview of how an enterprise could align the IT and business perspectives in building an intelligent enterprise with its cognitive characteristics © 2022 IEEE.

关键词： Architecture Digital transformation Bibliographies Buildings Companies Market research Sustainable development

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：