检索结果-内蒙古大学图书馆

11th International Conference on Computer, Control, informatics and its Applications, IC3INA 2024

作者： Zain, Rafi Mahmud Anggai, Sajarwo Tukiyat Musyafa, Ahmad Waskita, A.A. Graduate Program of Informatics Engineering Universitas Pamulang Pamulang Indonesia Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331542313

This paper analyzes presidential speeches from the United States, delivered by the current president, Joe Biden, from his inauguration until April 3, 2024, using BERT-based topic modeling techniques. Since the role and actions of the United States affect global affairs, inferring latent topics from these speeches are important for making informed decisions and also useful to researchers. We provide experiments combining different embedding methods and clustering algorithms for dimensionality reduction. Our experiment results demonstrated that using DistilBERT embeddings followed by HDBSCAN clustering and UMAP dimensionality reduction consistently produced meaningful and interpretable topics, and this paper introduces the UMASS and NPMI metrics for evaluating topic coherence, with the best values of these metrics among the other schemes investigated. Some of the dominant themes conveyed in the American president’s state of the union speech that were successfully revealed in this study include international cooperation, alongside significant attention to environmental, community, health, and economic issues. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Fine Tuning Swin Transformer Based Pretrained Model for Microscopic Fungi Images Classification 11

Fine Tuning Swin Transformer Based Pretrained Model for Micr...

引用

11th International Conference on Computer, Control, informatics and its Applications, IC3INA 2024

作者： Anggara, Muchamad Galih Hindasyah, Ahmad Amda, Julfa Muhammad Waskita, A.A. Graduate Program of Informatics Engineering Universitas Pamulang Pamulang Indonesia Research Center for Computing National Research and Innovation Agency Cibinong Indonesia Research Center for Data and Information Sciences National Research and Innovation Agency Bandung Indonesia

ISBN: (纸本)9798331542313

Accurate image classification of microscopic pathogenic fungi is a challenge in the field of mycology. This study proposes a Swin Transformer-based approach to automate the identification process. The Swin Transformer model, known for its ability to capture complex spatial interactions, is adapted from ImageNet’s pre-trained model. The adaptation process is focused on fine-tuning the final classification layer to match the 5 classes of fungi present in the dataset. This classification layer is replaced by a new fully-connected layer that has the number of output according to the number of fungal classes. The weights on these layers are randomly initialized and trained in conjunction with several final convolutional layers. In addition, regularization techniques such as dropouts are applied to prevent overfitting. Adaptation using 5-fold cross-validation was carried out to find the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−3, StepLR scheduler, batch size of 128 images, and a total of 9 epochs / iterations. After that, fine-tuning is carried out on the best fold with hyperparameters including AdamW optimizer with a learning rate of 10−5, StepLR scheduler, batch size of 32 images, and a total of 100 epochs / iterations. The final result showed excellent performance, with accuracy, precision, recall and an average F1-score of 95%. These results show the potential of the Swin Transformer in becoming an effective tool for mycologists. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Training of Monocular Depth Estimators via Self-Supervised Federated Learning 100

Privacy-Preserving Training of Monocular Depth Estimators vi...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： De S. Soares, Elton F. Campos, Carlos Alberto V. Ibm Research Brazil Research Lab RJ Rio de Janeiro20031-170 Brazil Federal University of the State of Rio de Janeiro Graduate Program in Informatics RJ Rio de Janeiro22290-255 Brazil

ISBN: (纸本)9798331517786

Monocular depth estimation is gaining attention in computer vision for autonomous driving due to its cost-effectiveness and versatility. Recent works have used self-supervised learning to tackle this problem. However, they overlook crucial challenges for real-world deployment, such as data privacy, network consumption, computational cost, and unstable connectivity. Recent studies have shown the potential benefits of federated learning in addressing these challenges. Thus, we introduce FedSCDepth, a novel method that combines federated learning and deep self-supervision to efficiently learn monocular depth estimators with performance comparable to the state-of-the-art. Our evaluation using the KITTI dataset's Eigen's Split reveals that FedSCDepth achieves high efficacy, with a test loss below 0.13. It also demonstrates impressive efficiency, requiring only an average of 1.5k training steps and up to 0.415 GB of weight data transfer per autonomous vehicle in each round. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Towards Continual Federated Learning of Monocular Depth for Autonomous Vehicles 100

Towards Continual Federated Learning of Monocular Depth for ...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

ISBN: (纸本)9798331517786

Recent investigations in computer vision for autonomous vehicles have focused on depth estimation from images, owing to its cost-efficiency and adaptability. Monocular depth estimation, using a single camera, is notable for its adaptability compared to binocular techniques that require two fixed cameras. Sophisticated methodologies employ self-supervised deep neural networks, while latest research proposes the use of federated learning to tackle crucial challenges for autonomous driving, such as data privacy, network usage, computation distribution, and connectivity robustness. Nevertheless, continual learning presents an additional challenge for both centralized and federated training, as updating models with novel datasets may induce the forgetting of previously acquired samples, thereby diminishing the model's versatility. Meanwhile, recent research indicates that experience replay strategies can be used to alleviate forgetting in autonomous driving use cases. We introduce ERFedSCDepth, an innovative approach amalgamating experience replay, federated learning, and deep self-supervision to allow the training of monocular depth estimators with high effectiveness and efficiency. Assessment using KITTI and DDAD datasets shows the efficacy of our approach, achieving enhanced continual learning performance over state-of-the-art baseline at standard depth metrics. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning Graph Neural Networks for Cancer Prognosis Prediction with Genomic Data 46

Multi-task Learning Graph Neural Networks for Cancer Prognos...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Lin, Tsung-Wei Arriagada, Sofia Ormazabal Lin, Che Taiwan Taiwan International Graduate Program AIoT Ntu Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering Ntu Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taiwan Smart Medicine and Health Informatics Program Ntu Taiwan

ISBN: (纸本)9798350371499

Providing robust prognosis predictions for cancers with limited data samples remains a challenge for precision oncology. In this study, we propose a novel approach that combines multi-task learning (MTL) and graph neural networks (GNNs) to address this issue. By representing gene-gene interactions as a graph network, our approach leverages multi-task learning to effectively capture the relationships of genes relevant to the oncogenesis and progression of breast, lung, and colon cancer. We demonstrate that our approach improves the cancer prognosis prediction for cancers with fewer samples, such as colon adenocarcinoma, by leveraging the shared gene-gene interactions across different cancer types, obtaining increases in the area under the precision-recall curve (AUPRC) of 24%. Our work contributes to the field of smart healthcare by demonstrating the potential of MTL and GNNs for enhancing cancer prognosis prediction, even with limited data samples. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Coevolution of Myoelectric Hand Control under the Tactile Interaction among Fingers and Objects

引用

Cyborg and Bionic Systems 2022年第1期2022卷 285-302页

作者： Yuki Kuroda Yusuke Yamanoi Shunta Togo Yinlai Jiang Hiroshi Yokoi Joint Doctoral Program for Sustainability Research Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyoJapan Department of Mechan ical and Intelligent System Engineering Graduate School of Informatics and Engineering The University of Electro Communications TokyoJapan Center for Neuroscience and Biomedical Engineering The University of Electro Communications TokyoJapan Bejing Innovation Center for Inelligent Robots and Systems BeijingChina

The usability of a prosthetic hand difers significantly from that of a real ***,the complexity of manipulation increases as the number of degrees of freedom to be controlled increases,making manipulation with biological signals extremely *** overcome this problem,users need to select a grasping posture that is adaptive to the object and a stable grasping method that prevents the object from *** previous studies,these have been left to the operating skills of the user,which is extremely difficult to *** this study,we demonstrate how stable and adaptive grasping can be achieved according to the object regardless of the user's operation *** required grasping technique is achieved by determining the correlation bet ween the motor output and each sensor through the interaction between the prosthetic hand and the surrounding stimuli,such as myoelectricity,sense of touch,and grasping *** agents of the 16 DOF robot hand were trained with the myoelectric signals of six participants,including one child with a congenital forearm ***,each agent could open and close the hand in response to the myoeletric stimuli and could accomplish the object pickup *** the tasks,the agents successfully identified grasping patterns suitable for practical and stable positioning of the *** addition,the agents were able to pick up the object in a similar posture regardless of the partiipant,suggesting that the hand was optimized by evolutionary computation to a posture that prevents the object from being dropped.

关键词： robot Objects overcome

来源：评论

学校读者我要写书评

暂无评论

GPU Acceleration of MIP Intra Prediction in VVC 31

GPU Acceleration of MIP Intra Prediction in VVC

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Storch, Iago Roma, Nuno Palomino, Daniel Bampi, Sergio Graduate Program in Computing Institute of Informatics Federal University of Rio Grande do Sul Porto Alegre Brazil Lisboa Portugal Instituto Superior Técnico Universidade de Lisboa Lisboa Portugal Federal University of Pelotas Graduate Program in Computing Video Technology Research Group Pelotas Brazil

ISBN: (纸本)9789464593600

The Versatile Video Coding (VVC) standard introduced several novel encoding tools for intra frame prediction, increasing the encoder complexity when compared to previous standards. Among these novelties is the MIP tool, whose acceleration has not been tackled in the literature. Therefore, an efficient parallelization of MIP prediction targeting GPU platforms is now proposed. The presented technique makes use of alternative reference samples and computes the distortion in an approximate manner to expose and potentiate massive parallelism. Moreover, the adopted prediction scheduling and memory communication were tailored by considering the GPUs' architecture and memory hierarchy. When compared with a CPU execution, this work is capable to accelerate the MIP prediction up to 105 times at the cost of a negligible coding efficiency loss of 0.284% BD-BR. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Single-cell transcriptomics uncovers EGFR signaling-mediated gastric progenitor cell differentiation in stomach homeostasis (vol 14, 3750, 2023)

引用

NATURE COMMUNICATIONS 2023年第1期14卷 1-16页

作者： Takada, Hitomi Sasagawa, Yohei Yoshimura, Mika Tanaka, Kaori Iwayama, Yoshimi Hayashi, Tetsutaro Isomura-Matoba, Ayako Nikaido, Itoshi Kurisaki, Akira Laboratory of Stem Cell Technologies Graduate School of Science and Technology Nara Institute of Science and Technology Takayama-cho Ikoma Nara Japan Laboratory for Bioinformatics Research RIKEN Center for Biosystems Dynamics Research Wako Saitama Japan Department of Functional Genome Informatics Biological Data Science Medical Research Institute Tokyo Medical and Dental University Bunkyo Tokyo Japan Master’s/Doctoral Program in Life Science Innovation (Bioinformatics) Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba Ibaraki Japan

Defects in gastric progenitor cell differentiation are associated with various gastric disorders, including atrophic gastritis, intestinal metaplasia, and gastric cancer. However, the mechanisms underlying the multilineage differentiation of gastric progenitor cells during healthy homeostasis remain poorly understood. Here, using a single-cell RNA sequencing method, Quartz-Seq2, we analyzed the gene expression dynamics of progenitor cell differentiation toward pit cell, neck cell, and parietal cell lineages in healthy adult mouse corpus tissues. Enrichment analysis of pseudotime-dependent genes and a gastric organoid assay revealed that EGFR-ERK signaling promotes pit cell differentiation, whereas NF-κB signaling maintains gastric progenitor cells in an undifferentiated state. In addition, pharmacological inhibition of EGFR in vivo resulted in a decreased number of pit cells. Although activation of EGFR signaling in gastric progenitor cells has been suggested as one of the major inducers of gastric cancers, our findings unexpectedly identified that EGFR signaling exerts a differentiation-promoting function, not a mitogenic function, in normal gastric homeostasis.

关键词： Adult stem cells Stem-cell differentiation Stem-cell niche

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification 6

ConvNeXt Model for Breast Cancer Image Classification

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Setiawan, Devin Karnyoto, Andrea Stevens Intan, Indo Pardamean, Bens Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83. © 2024 IEEE.

关键词： Lung cancer

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：