检索结果-内蒙古大学图书馆

Multi-Label Diabetes Health Intervention dataset 25

学校读者我要写书评

暂无评论

Multi-Label Diabetes Health Intervention Dataset

25th International computer science and Engineering Conference, ICSEC 2021

作者： Keawpradub, Dheeraj Vasupongayya, Sangsuree Wonghirandecha, Aekkorn College of Digital Science Prince of Songkla University Master of Science in Data Science Hat Yai Songkhla Thailand Prince of Songkla University Faculty of Engineering Department of Computer Engineering Hat Yai Songkhla Thailand Myhealthgroup Company Limited Doctor of Medicine Hat Yai Songkhla Thailand

ISBN: (纸本)9781665411974

This research presents the creation of a dataset for training a machine learning model in order to predict health intervention for the treatment in patients with type 2 diabetes. The dataset is designed as a Multi-label dataset. The process of dataset creation is taken medical professionals into account. The datasets are created based on the characteristics and trends of patients with type 2 diabetes in Songkhla Province, Thailand, between 2019 and 2020, together with the factors analyzed by physicians with respect to taking medical history of diabetic patients. The result shows that a dataset is generated having 545 samples with 15 variables and 5 multi-labeled responses. © 2021 IEEE.

关键词： Patient treatment

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

International Conference on computer Supported Cooperative Work in Design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language Processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

Practical and Malicious Private Set Intersection with Improved Efficiency

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhu, Yizhao Chen, Lanxiang Mu, Yi Faculty of Data Science City University of Macau 999078 China College of Computer and Cyber Security Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou China

We propose a novel two-party private set intersection (PSI) protocol, which achieves ideal and constant receiver-to-sender and linear sender-to-receiver communication overhead, linear computational complexity, along with receiver size-hiding and lightweight computation cost. In comparison with other PSI protocols, the proposed protocol is more practical as it does not require any fully homomorphic computation. We propose three variants to demonstrate efficiency optimization, size-hiding feature extension, and online/offline settings for real-world applications, respectively, to offer a practical control between security and efficiency. Finally, we prove that our proposed protocols are secure against malicious participants under our security model. © 2023, The Authors. All rights reserved.

关键词： Efficiency

Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ariai, Farid Mahmoudi, Maryam Tayefeh Moeini, Ali Department of Computer Engineering University of Tehran Kish International Campus Kish Iran Data Analysis & Processing Research Group IT Research Faculty ICT Research Institute Tehran Iran School of Engineering Science College of Engineering University of Tehran Tehran Iran

In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming to amplify the efficiency of language models tailored to the Persian language. Focusing on enhancing the effectiveness of sentiment analysis, our approach employs an aspect-based methodology utilizing the ParsBERT model, augmented with a relevant lexicon. The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala.' The experimental results not only highlight the proposed method's superior semantic capabilities but also showcase its efficiency gains with an accuracy of 88.2% and an F1 score of 61.7. The importance of enhancing language models in this context lies in their pivotal role in extracting nuanced sentiments from user-generated content, ultimately advancing the field of sentiment analysis in Persian text mining by increasing efficiency and accuracy. © 2025, CC BY.

关键词： Latent semantic analysis

TREELEARN: A DEEP LEARNING METHOD FOR SEGMENTING INDIVIDUAL TREES FROM GROUND-BASED LIDAR FOREST POINT CLOUDS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Henrich, Jonathan van Delden, Jan Seidel, Dominik Kneib, Thomas Ecker, Alexander S. Chairs of Statistics and Econometrics Faculty of Economics University of Göttingen Germany Institute of Computer Science University of Göttingen Germany Department Spatial Structures and Digitization of Forests Faculty of Forest Science University of Göttingen Germany Campus Institute Data Science University of Göttingen Max Planck Institute for Dynamics and Self-Organization Göttingen Germany

Laser-scanned point clouds of forests make it possible to extract valuable information for forest management. To consider single trees, a forest point cloud needs to be segmented into individual tree point clouds. Existing segmentation methods are usually based on hand-crafted algorithms, such as identifying trunks and growing trees from them, and face difficulties in dense forests with overlapping tree crowns. In this study, we propose TreeLearn, a deep learning-based approach for tree instance segmentation of forest point clouds. TreeLearn is trained on already segmented point clouds in a data-driven manner, making it less reliant on predefined features and algorithms. Furthermore, TreeLearn is implemented as a fully automatic pipeline and does not rely on extensive hyperparameter tuning, which makes it easy to use. Additionally, we introduce a new manually segmented benchmark forest dataset containing 156 full trees. The data is generated by mobile laser scanning and contributes to create a larger and more diverse data basis for model development and fine-grained instance segmentation evaluation. We trained TreeLearn on forest point clouds of 6665 trees, labeled using the Lidar360 software. An evaluation on the benchmark dataset shows that TreeLearn performs as well as the algorithm used to generate its training data. Furthermore, the performance can be vastly improved by fine-tuning the model using manually annotated datasets. We evaluate TreeLearn on our benchmark dataset and the Wytham Woods dataset, outperforming the recent SegmentAnyTree, ForAINet and TLS2Trees methods. The TreeLearn code and all datasets that were created in the course of this work are made publicly available. © 2023, CC BY-SA.

关键词： Deep learning

Semantic-Enhanced Attention Network for Image-Text Matching

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention Network for Image-Text Matching

International Conference on computer Supported Cooperative Work in Design

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention Network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

Dadm: Enhancing Eeg Artifact Removal by Fusing Artifact Representation into the Time-Frequency Domain

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Haoran Feng, Fan Kang, Jiarong Zhang, Jin Gong, Xiaoli Lu, Tingjuan Sun, Zhe Solé-Casals, Jordi College of Computer Science Nankai University Tianjin China Department of Biomedical Engineering School of Medicine Tsinghua University Beijing China Tianjin Key Laboratory of Brain Science and Intelligent Rehabilitation Nankai University Tianjin China State Key Laboratory of High-end Server and Storage Technology China 903rd Hospital of PLA China Faculty of Medicine Faculty of Health Data Science Juntendo University Japan Data and Signal Processing Group University of Vic Central University of Catalonia Catalonia Vic08500 Spain

The electroencephalogram (EEG) provides essential data for analyzing brain activities. However, artifacts such as electrooculography (EOG) and electromyography (EMG) often interleave with the EEG signals, significantly affecting the quality of EEG signal analysis. The heterogeneous distribution of these artifacts in the time-frequency domain makes it challenging to remove multiple artifacts using a unified model. In this paper, we propose an Artifact-Aware EEG Denoising Model, referred to as DADM, to effectively remove various types of artifacts in a unified manner. We first obtain an artifact representation that indicates the type of artifact from a pre-trained artifact classification model. This artifact representation is then used as prior knowledge, which is fused into the denoising model in the frequency-time domain. This enables the model to become aware of the artifact type and precisely remove artifacts based on their type. Due to the heterogeneous distributions of artifacts in the frequency domain, we introduce a frequency enhancement module that can identify specific types of artifacts based on their representation and remove them using a hard attention mechanism. Additionally, we design a time-domain compensation module to enhance the denoising capability of DADM by compensating for potential losses of global information. Comprehensive experiments demonstrate that DADM significantly outperforms the Novel CNN in denoising EEG signals, showing a notable 7.77% improvement in correlation coefficient (CC) metrics. © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sedova, Anastasiia Zellinger, Lena Roth, Benjamin Research Group Data Mining and Machine Learning University of Vienna Austria UniVie Doctoral School Computer Science University of Vienna Austria Faculty of Philological and Cultural Studies University of Vienna Austria

An accurate and substantial dataset is essential for training a reliable and well-performing model. However, even manually annotated datasets contain label errors, not to mention automatically labeled ones. Previous methods for label denoising have primarily focused on detecting outliers and their permanent removal – a process that is likely to over- or underfilter the dataset. In this work, we propose AGRA: a new method for learning with noisy labels by using Adaptive GRAdient-based outlier removal1. Instead of cleaning the dataset prior to model training, the dataset is dynamically adjusted during the training process. By comparing the aggregated gradient of a batch of samples and an individual example gradient, our method dynamically decides whether a corresponding example is helpful for the model at this point or is counter-productive and should be left out for the current update. Extensive evaluation on several datasets demonstrates AGRA’s effectiveness, while a comprehensive results analysis supports our initial hypothesis: permanent hard outlier removal is not always what model benefits the most from. © 2023, CC BY.

关键词： Statistics

Ugly Ducklings or Swans: A Tiered Quadruplet Network with Patient-Specific Mining for Improved Skin Lesion Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Naranpanawa, Nathasha Soyer, H. Peter Mothershaw, Adam Kulatilleke, Gayan K. Ge, Zongyuan Betz-Stablein, Brigid Chandra, Shekhar S. School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia Frazer Institute The University of Queensland Dermatology Research Centre Brisbane Australia Monash Medical AI Monash University Australia Department of Data Science and AI Faculty of IT Monash University Australia

An ugly duckling is an obviously different skin lesion from surrounding lesions of an individual, and the ugly duckling sign is a criterion used to aid in the diagnosis of cutaneous melanoma by differentiating between highly suspicious and benign lesions. However, the appearance of pigmented lesions, can change drastically from one patient to another, resulting in difficulties in visual separation of ugly ducklings. Hence, we propose DMT-Quadruplet - a deep metric learning network to learn lesion features at two tiers - patient-level and lesion-level. We introduce a patient-specific quadruplet mining approach together with a tiered quadruplet network, to drive the network to learn more contextual information both globally and locally between the two tiers. We further incorporate a dynamic margin within the patient-specific mining to allow more useful quadruplets to be mined within individuals. Comprehensive experiments show that our proposed method outperforms traditional classifiers, achieving 54% higher sensitivity than a baseline ResNet18 CNN and 37% higher than a naive triplet network in classifying ugly duckling lesions. Visualisation of the data manifold in the metric space further illustrates that DMT-Quadruplet is capable of classifying ugly duckling lesions in both patient-specific and patient-agnostic manner successfully. © 2023, CC BY.

关键词： Dermatology