检索结果-内蒙古大学图书馆

6th International Conference on Computational Intelligence and Communication Technologies, CCICT 2024

作者： Sharma, Vansheta Rani, Rupa Pathak, Priya Chakraborty, Sudeshna Department of Computer Science & Engineering- Data Science ABES Institute of Technology U.P. Ghaziabad India Department of Computer Science & Engineering Ajay Kumar Garg Engineering College U.P. Ghaziabad India Depatment of Computer Science & Engineering Banasthali Vidyapith Rajasthan India Department School of Computer Application and Technology Galgotias University UP India

ISBN: (纸本)9798350374629

Among the most vital organs that protect the body of a human from the external environment is the skin. Early skin illness identification is essential for reducing mortality because it prevents skin cancer, and any other skin disease from developing. But because it resembles skin patches, insect bites etc in appearance, early detection that might lengthen life expectancy is a fantastic experiment. We would be working with different skin diseases namely ‘Acne’, ‘Eczema or Atopic Dermatitis’, ‘melanoma’. A working model that uses image analysis and machine learning to classify and identify skin conditions. A brand-new, cutting edge automated system that can swiftly and accurately identify skin lesions is needed to deal with biomedical pictures. There is growing curiosity concerning the application of deep learning to the diagnosis and management of different diseases. For the early detection of skin disease, we therefore suggested a deep learning model based on CNN and the merger of the U-Net and ResNet models is presented as a fusion model that has been used to perform encoding decoding of the disorders using skin scans. This model integrates image processing, image enhancement, machine learning and segmentation techniques. The model yielded an overall accuracy of 95.6%. Incorporate additional skin conditions in the future to strengthen our model's suitability for medical applications. ©2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Implicitly Guided Design with PropEn: Match your data to Follow the Gradient 38

Implicitly Guided Design with PropEn: Match your Data to Fol...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tagasovska, Nataša Gligorijević, Vladimir Cho, Kyunghyun Loukas, Andreas Prescient/MLDD Genentech Research and Early Development United States Department of Computer Science Center for Data Science New York University United States

Across scientific domains, generating new models or optimizing existing ones while meeting specific criteria is crucial. Traditional machine learning frameworks for guided design use a generative model and a surrogate model (discriminator), requiring large datasets. However, real-world scientific applications often have limited data and complex landscapes, making data-hungry models inefficient or impractical. We propose a new framework, PropEn, inspired by "matching", which enables implicit guidance without training a discriminator. By matching each sample with a similar one that has a better property value, we create a larger training dataset that inherently indicates the direction of improvement. Matching, combined with an encoder-decoder architecture, forms a domain-agnostic generative framework for property enhancement. We show that training with a matched dataset approximates the gradient of the property of interest while remaining within the data distribution, allowing efficient design optimization. Extensive evaluations in toy problems and scientific applications, such as therapeutic protein design and airfoil optimization, demonstrate PropEn's advantages over common baselines. Notably, the protein design results are validated with wet lab experiments, confirming the competitiveness and effectiveness of our approach. Our code is available at https://***/prescient-design/propen. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scheduling Production in the Flexible Packaging Industry Using Mathematical Models and Genetic Algorithms

Scheduling Production in the Flexible Packaging Industry Usi...

引用

2023 International Conference on Informatics Engineering, science and Technology, INCITEST 2023

作者： Tarigan, Masmur Gaol, Ford Lumban Mauritsius, Tuga Budiharto, Widodo Esa Unggul University Bina Nusantara University Computer Science Department / Computer Science Graduate Program Jakarta Indonesia Binus Graduate Program Bina Nusantara University Computer Science Department Jakarta Indonesia Management Bina Nusantara University Department of Information System Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350317862

Minimizing time wastage is a crucial objective for all production operations. Reliable manufacturing scheduling The objective is to mitigate time-based production waste caused by excessive processing, waiting, and transportation. Industry 4.0 promotes technological innovation across all industrial sectors to increase efficiency and effectiveness while preserving high competitiveness. The implementation of artificial intelligence in Industry 4.0 is expected to result in a reduction in time wastage. Non-dominance sequencing genetic algorithms (NSGA), genetic algorithms (GA), and evolutionary algorithms (EA) are the three most common scheduling approaches, according to literature-indexed research summaries from the past five years. The examination of production scheduling in the flexible packaging business, which involves the utilization of different machines and processes and is produced on demand, had not been conducted before in this study. A mathematical scheduling model will be developed in this research to ascertain the shortest production time span in the flexible packaging industry. As a form of technological innovation, this mathematical model will be utilized in experiments employing a genetic algorithm approach. For the genetic algorithm to generate a minimum makespan in the flexible packaging industry's production scheduling process. © 2023 IEEE.

关键词： Genetic algorithms

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) 10

Question Classification of University Admission using Named-...

引用

10th International Conference on Information Technology, computer, and Electrical Engineering, ICITACEE 2023

作者： Yossy, Emny Harna Suhartono, Derwin Trisetyarso, Agung Budiharto, Widodo Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta11480 Indonesia Bina Nusantara University Computer Science Department School of Computer Science Jakarta11480 Indonesia Bina Nusantara University Mathematics Department School of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9798350322729

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. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

In the Eyes of the Bystander: Are the Stances on Different Conflicts Correlated?

In the Eyes of the Bystander: Are the Stances on Different C...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Tao, Yiyao Zhang, Hengyu Dey, Babli Tulga, Selenge Lyu, Hanjia Luo, Jiebo University of Rochester Goergen Institute for Data Science RochesterNY United States University of Rochester Department of Computer Science RochesterNY United States

ISBN: (纸本)9798350362480

Public opinion on international conflicts, such as the concurrent Russia-Ukraine and Israel-Palestine crises, often reflects a society's values, beliefs, and history. These simultaneous conflicts have sparked heated global online discussions, offering a unique opportunity to explore the dynamics of public opinion in multiple international crises. This study investigates how public opinions toward one conflict might influence or relate to another, a relatively unexplored area in contemporary research. Focusing on Chinese netizens, who represent a significant online population, this study examines their perspectives, which are increasingly influential in global discourse due to China's unique cultural and political landscape. The research finds a range of opinions, including an overall neutral stance towards both conflicts and a statistical correlation between attitudes towards each, indicating interconnected or mutually influenced viewpoints. The study also highlights the significant role of news media in impacting public opinion, particularly in China, where state policies and global politics shape conflict portrayal. © 2024 IEEE.

关键词： opinion mining social media stance detection

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 4

Hoax Detection in Social Media: A Literature Review

引用

4th International Conference on Artificial Intelligence and data sciences, AiDAS 2023

作者： Saputra, Carsten Sebastian Wijaya, Norbert Anggreainy, Maria Susan Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350318432

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. © 2023 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

TOWARDS ROBUST OUT-OF-DISTRIBUTION GENERALIZATION BOUNDS VIA SHARPNESS 12

TOWARDS ROBUST OUT-OF-DISTRIBUTION GENERALIZATION BOUNDS VIA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zou, Yingtian Kawaguchi, Kenji Liu, Yingnan Liu, Jiashuo Lee, Mong-Li Hsu, Wynne School of Computing National University of Singapore Institute of Data Science National University of Singapore Singapore Department of Computer Science & Technology Tsinghua University China

Generalizing to out-of-distribution (OOD) data or unseen domain, termed OOD generalization, still lacks appropriate theoretical guarantees. Canonical OOD bounds focus on different distance measurements between source and target domains but fail to consider the optimization property of the learned model. As empirically shown in recent work, the sharpness of learned minima influences OOD generalization. To bridge this gap between optimization and OOD generalization, we study the effect of sharpness on how a model tolerates data change in domain shift which is usually captured by "robustness" in generalization. In this paper, we give a rigorous connection between sharpness and robustness, which gives better OOD guarantees for robust algorithms. It also provides a theoretical backing for "flat minima leads to better OOD generalization". Overall, we propose a sharpness-based OOD generalization bound by taking robustness into consideration, resulting in a tighter bound than non-robust guarantees. Our findings are supported by the experiments on a ridge regression model, as well as the experiments on deep learning classification tasks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Comparative Model Evaluation of Lightweight Transformer-Based and CNN-Based Architechture for Degenerative Lumbar Spine Classification

Comparative Model Evaluation of Lightweight Transformer-Base...

引用

Advancement in data science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Jennifer Ardelia Limicia Wilbert Chandra Alexander Agung Santoso Gunawan Jeffrey Junior Tedjasulaksana Data Science Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Low back pain is a leading cause of disability globally, is often associated with degenerative lumbar spine conditions. Accurate diagnosis of these conditions is critical but challenging due to the subjective nature of MRI interpretation and the weak correlation between imaging findings and symptoms. Thus, the purpose of this study is to evaluate the performance of CNN-based architectures (VGG-16, EfficientNetB0, EfficientNetV2) and transformer-based architecture specifically Vision Transformers (ViT) in classifying lumbar spine conditions as normal, moderate, or severe. Using the RSNA 2024 Lumbar Spine Degenerative Classification dataset. The models are evaluated using the ROC-AUC and PRAUC as the performance metrics due to the dataset imbalance. Results indicate that EfficientNetB0 achieved the highest overall performance, with an average ROC-AUC of 0.784 and PR-AUC of 0.528, demonstrating strong adaptability to imbalanced datasets. EfficientNetV2 also performed competitively, while VGG-16 showed moderate effectiveness. The Vision Transformer (ViT), however, underperformed due to its reliance on larger datasets and challenges in capturing fine-grained spatial features. The findings highlight the potential of EfficientNet-based models for accurate and efficient lumbar spine diagnostics. This study underscores the potential of advanced deep learning approaches in improving diagnostic workflows for degenerative lumbar spine conditions.

关键词： computer vision Adaptation models Accuracy Magnetic resonance imaging Soft sensors Spine Transforms Transformers data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6315-6332页

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan Fuzhou University College of Computer and Data Science Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Fuzhou University Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China University of Exeter Department of Computer Science Faculty of Environment Science and Economy ExeterEX4 4QF United Kingdom Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China University of Oslo Department of Informatics Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. © 2025 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Utilizing Semi-supervised Method in Predicting BRCA1 Pathogenicity Variants 8

Utilizing Semi-supervised Method in Predicting BRCA1 Pathoge...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Hidayat, Alam Ahmad Trinugroho, Joko Pebrianto Nirwantono, Rudi Sudigyo, Digdo Pardamean, Bens Department of Mathematics School of Computer Science Bina Nusantara University 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

Quantifying the effect of mutations in the BRCA1 gene is useful for understanding their clinical consequences on breast cancer. Machine learning models can be applied to predict the landscape of protein variant effects that might not be always accessible by experiments. In this work, we propose a simple semi-supervised learning method using a Gaussian mixture model to predict ~90% of the unlabeled missense variants of the BRCA1 gene collected from the ClinVar database. High-quality embeddings are used as a feature of the protein sequences, extracted using the latest pre-trained transformer-based language protein model. A statistical test show that the protein embeddings are effective and robust for predicting pathogenicity. Further, the lower representations of the features are then fed into the semi-supervised model. The prediction performance of the model only for the labeled testing data achieves an AUC score and an accuracy of 79.27% and 71.58%, respectively. Using our defined pathogenic probability score, we find that ~94% of variants in our unlabeled dataset are well-separated into either benign or pathogenic classes according to that scoring. Our scores obtain a moderate Spearman rank correlation with the results of established unsupervised variant effect models. Finally, our approach can potentially be developed for more accurate and biologically reliable predictions of the variant effects. © 2023 The Authors. Published by Elsevier B.V.

关键词： embeddings language model mutation effect protein sequence semi-supervised learning

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：