检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Yawei Li Zhao Zhang Suiyi Zhao Jicong Fan Haijun Zhang Mingliang Xu School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Yunnan Key Laboratory of Software Engineering Kunming China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Computer Science Harbin Institute of Technology Shenzhen China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Surgical Instrument Detection for Laparoscopic Surgery using Deep Learning 19

Surgical Instrument Detection for Laparoscopic Surgery using...

引用

19th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Boonkong, Apiwat Hormdee, Daranee Sonsilphong, Suphachoke Khampitak, Kovit Khon Kaen University Embedded System RandD Group Computer Engineering Khon Kaen Thailand Khon Kaen University Data Science and Health Informatics Program Academic Affairs Khon Kaen Thailand Khon Kaen University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kaen Thailand

ISBN: (纸本)9781665485845

Laparoscopic surgery has transformed conventional open surgery. Robot-Assisted laparoscopic surgery which is minimally invasive is effective for operations in limited space. Nevertheless, the robotic system which is utilized in such surgery can inflict impair to the surgical instruments, organs, or tissues as a consequence of the narrow field of view and space available to operate, and insufficient tactile response. In laparoscopy, the surgeon observes what he operates via digital images which are displayed on a monitor. In addition to the surgeon's expertise, the image-guided surgery system could offer him significant support if that system is capable of understanding those images. computer Vision has been able to proceed due to the emergence of Machine Learning, and especially Deep Learning. This paper applies Deep Learning for surgical instrument detection for laparoscopic surgery. The fastest model, based on results trained on the COCO 2017 dataset on TensorFlow Framework, for each of 4 algorithms-Faster-RCNN, SSD, CenterNet and EfficientDet-from Model Zoo, along with YOLOv4 on Darknet Framework, have been investigated in this work. The evaluation metrics used are Precision, Recall and F1-score. The results reveal that each model plays its part well;however, YOLOv4 seemed to breakthrough this statement by offering grate result for all three accuracy metrics. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

GPTR: Gestalt-Perception Transformer for Diagram Object Detection

arXiv

引用

arXiv 2022年

作者： Hu, Xin Zhang, Lingling Liu, Jun Fan, Jinfu You, Yang Wu, Yaqiang Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University China Department of Control Science and Engineering Tongji University Shanghai China Department of Computer Science National University of Singapore Singapore Lenovo Research Beijing China

Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architecture. Gestalt perception contains a series of laws to explain human perception, that the human visual system tends to perceive patches in an image that are similar, close or connected without abrupt directional changes as a perceptual whole object. Inspired by these thoughts, we build a gestalt-perception graph in transformer encoder, which is composed of diagram patches as nodes and the relationships between patches as edges. This graph aims to group these patches into objects via laws of similarity, proximity, and smoothness implied in these edges, so that the meaningful objects can be effectively detected. The experimental results demonstrate that the proposed GPTR achieves the best results in the diagram object detection task. Our model also obtains comparable results over the competitors in natural image object detection. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PC-based Intelligent Traffic Monitoring System with Real-time Analysis for Smart Cities 14

PC-based Intelligent Traffic Monitoring System with Real-tim...

引用

14th International Conference on COMmunication Systems and NETworkS, COMSNETS 2022

作者： Lau, Chi-Yat Yuen, Man-Ching Yueng, Ka-Ho Fan, Cheuk-Pan Ko, On-Yi Ngan, Lit-Wang Tam, Wing-Chun Yeung, Wai-Nam Vocational Training Council Department of Information Technology Hong Kong Hong Kong Hong Kong Shue Yan University IFREE GROUP Innovation and Research Centre Department of Applied Data Science Hong Kong Hong Kong Limited Hong Kong Hong Kong City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Chinese University of Hong Kong Department of Statistics Hong Kong Hong Kong National Taipei University of Technology Department of Computer Science and Information Engineering Taiwan Taiwan University of the West of England Bristol Department of Computer Science and Creative Technologies Bristol United Kingdom

ISBN: (纸本)9781665421041

In recent years, Hong Kong has been experiencing severe traffic problems and especially traffic congestion. In this paper, we proposed a traffic monitoring system which is PC-based, no infrastructure requirement but suitable for the complex road networks in Hong Kong. Besides, our system is designed to recognize vehicle type and plate number for vehicles commonly used in Hong Kong. By analyzing the data collected on road usage, we present our findings for decision-making regarding traffic policies. © 2022 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Unboxing the black-box of deep learning based reconstruction of undersampled MRIs 4

Unboxing the black-box of deep learning based reconstruction...

引用

4th Italian Workshop on Explainable Artificial Intelligence, XAI.it 2023

作者： Chatterjee, Soumick Das, Arnab Khatun, Rupali Nürnberger, Andreas Genomics Research Centre Human Technopole Milan Italy Faculty of Computer Science Otto von Guericke University Magdeburg Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Magdeburg Germany German Research Centre for Artificial Intelligence Kaiserslautern Germany Translational Radiobiology Department of Radiation Oncology Universitätsklinikum Erlangen Erlangen Germany Department of Radiation Oncology Universitätsklinikum Erlangen Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen Germany Comprehensive Cancer Centre Erlangen-EMN Erlangen Germany Centre for Behavioural Brain Sciences Magdeburg Germany

Deep learning has emerged as a very important area of research and has shown immense potential in solving different kinds of problem, including in the medical field. For tasks like undersampled MRI reconstruction - the process of speeding up MRI acquisition with the help of undersampling, deep learning has shown its dominance over the years. But one of the major problems with deep learning is trust: Complex reasonings done by these models appear black-box to the users. Therefore, to build trust and better acceptability, it is important to open up this black-box nature of these models. For classification models, several approaches have been proposed. Nevertheless, for models dealing with inverse problems, like the reconstruction of the undersampled MRIs, it is more challenging as the output of the model has the same number of output pixels as the input, making the interpretability of such models more complex. This research explores different methods to understand the working mechanism of a deep learning model for the task of undersampled MRI reconstruction. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

data Cleaning of Binary Sensor Events in Activity Recognition by Cluster-Based Methods 7th

Data Cleaning of Binary Sensor Events in Activity Recognitio...

引用

7th International Conference on Human Aspects of IT for the Aged Population, ITAP 2021, held as part of the 23rd International Conference, HCI International 2021

作者： Zhao, Chunyang Que, Xia Yin, Yue Xing, Xiaoman Yang, Jiaoyun An, Ning Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Medical Imaging Department Chinese Academy of Sciences Suzhou China

ISBN: (纸本)9783030781101

The Ambient Assisted Living (AAL) systems use sensors to detect the daily behavior of older adults and provide necessary assistance based on changes in their cognitive status and physical functions, thus enabling older adults to maintain their independence at home. However, the effectiveness of the AAL systems depends on the accuracy of the data provided by sensors. Namely, when a human error or a hardware failure occurs, the activity recognition model can become inaccurate. This inaccuracy hinders the identification of critical and potentially life-threatening activities. Although there are many methods for cleaning sensor data, there is no method for binary sensors deployed in smart homes. By considering noisy sensor events and unintentional forgetting of turning off the device, this paper proposes two clustering-based methods for denoising and splitting binary sensor events to address possible inaccuracy due to the two mentioned problems. The effectiveness of the proposed methods is verified by the experiments using four machine learning models and three real-world smart home datasets and adopting different sensor configurations. The experimental results demonstrate that compared to the original unprocessed datasets, by combining the two proposed methods, the average accuracy and F-measure are improved by 15.00% and 17.25%, respectively. © 2021, Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Automatic Textual Explanations of Concept Lattices

arXiv

引用

arXiv 2023年

作者： Hirth, Johannes Horn, Viktoria Stumme, Gerd Hanika, Tom Knowledge & Data Engineering Group University of Kassel Germany Partizipative IT-Gestaltung University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany School of Library and Information Science Humboldt-Universität zu Berlin Berlin Germany Institute of Computer Science University of Hildesheim Germany

Lattices and their order diagrams are an essential tool for communicating knowledge and insights about data. This is in particular true when applying Formal Concept Analysis. Such representations, however, are difficult to comprehend by untrained users and in general in cases where lattices are large. We tackle this problem by automatically generating textual explanations for lattices using standard scales. Our method is based on the general notion of ordinal motifs in lattices for the special case of standard scales. We show the computational complexity of identifying a small number of standard scales that cover most of the lattice structure. For these, we provide textual explanation templates, which can be applied to any occurrence of a scale in any data domain. These templates are derived using principles from human-computer interaction and allow for a comprehensive textual explanation of lattices. We demonstrate our approach on the spices planner data set, which is a medium sized formal context comprised of fifty-six meals (objects) and thirty-seven spices (attributes). The resulting 531 formal concepts can be covered by means of about 100 standard *** Codes 06A15 03G10 68T30 68T27 Copyright © 2023, The Authors. All rights reserved.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

Edge-Minimum Saturated k-Planar Drawings 29th

Edge-Minimum Saturated k-Planar Drawings

引用

29th International Symposium on Graph Drawing and Network Visualization, GD 2021

作者： Chaplick, Steven Klute, Fabian Parada, Irene Rollin, Jonathan Ueckerdt, Torsten Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Utrecht University Utrecht Netherlands TU Eindhoven Eindhoven Netherlands Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany Institute of Theoretical Informatics Karlsruhe Institute of Technology Karlsruhe Germany

ISBN: (纸本)9783030929305

For a class D of drawings of loopless (multi-)graphs in the plane, a drawing D∈ D is saturated when the addition of any edge to D results in D′∉ D —this is analogous to saturated graphs in a graph class as introduced by Turán (1941) and Erdős, Hajnal, and Moon (1964). We focus on k-planar drawings, that is, graphs drawn in the plane where each edge is crossed at most k times, and the classes D of all k-planar drawings obeying a number of restrictions, such as having no crossing incident edges, no pair of edges crossing more than once, or no edge crossing itself. While saturated k-planar drawings are the focus of several prior works, tight bounds on how sparse these can be are not well understood. We establish a generic framework to determine the minimum number of edges among all n-vertex saturated k-planar drawings in many natural classes. For example, when incident crossings, multicrossings and selfcrossings are all allowed, the sparsest n-vertex saturated k-planar drawings have 2k-(kmod2)(n-1) edges for any k≥ 4, while if all that is forbidden, the sparsest such drawings have 2(k+1)k(k-1)(n-1) edges for any k≥ 6. © 2021, Springer Nature Switzerland AG.

关键词： Drawing (graphics)

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Instructor-Trainee Dance dataset Using Cosine similarity, Euclidean distance, and Angular difference

A Comparison of the Instructor-Trainee Dance Dataset Using C...

引用

International computer science and engineering Conference (ICSEC)

作者： Thanawat Srikaewsiew Khatadet Khianchainat Atima Tharatipyakul Suporn Pongnumkul Sarunya Kanjanawattana Department of Computer Engineering Institute of Engineering Suranaree University of Technology Nakhon Ratchasima Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center (NECTEC) Pathumthani Thailand

ISBN: (纸本)9781665462730

The COVID-19 outbreak has restricted most outdoor activities, leads to increasing interest in exercise at home with online trainers. One issue of online exercise technology is the safety since improper motion might result in injury. As a basis to prevent improper motion, methods for evaluating the motion similarity between an instructor and a trainee are essential. Cosine similarity, Angular difference, and Euclidean distance are three general ways for the motion evaluation. This study aimed to determine the most effective way for analyzing the similarity of human motion on the dataset of instructor-led dances. We first experimented with the data to find the appropriate cut-off value for classifying posture into two classes based on the similarity score. Confusion matrix, precision, recall, F1-score, accuracy of the results were then used to compare the efficiency. We discovered that Cosine similarity had the highest accuracy, 82.77 percent at cut-off 93.

关键词： computer science COVID-19 Humanities Euclidean distance Safety Injuries

来源：评论

学校读者我要写书评

暂无评论

dataDecon: data Cleansing Tools for Large Language Model with Efficient Decontamination Techniques

DataDecon: Data Cleansing Tools for Large Language Model wit...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Sumeth Yuenyong Norapat Buppodom Koravich Sangkaew Konthee Boonmeeprakob Prachya Boonkwan Jillaphat Jaroenkantasima Pitikorn Khlaisamniang Anuruth Lertpiya Apivadee Piyatumrong Peerawat Rojratchadakorn Thaweewat Rugsujarit Teerapol Saengsukhiran Kriangkrai Saetan Isada Sukprapa Thanachot Thavornmongkol Nucharee Thongthungwong Patteera Triamamornwooth Chanon Utupon Kobkrit Viriyayudhakorn Phoochit Witchutanon Sadit Wongprayon Thepchai Supnithi Department of Computer Engineering Faculty of Engineering Mahidol University National Electronics and Computer Technology Center Pathumthani Thailand Artificial Intelligence Asssociation of Thailand Big Data Institute (Public Organization) Bangkok Department of Electrical Engineering Faculty of Engineering Kasetsart University Looloo Technology Faculty of Engineering Kasetsart University Kasikorn Labs Kasikorn Business Technology Group Faculty of Science King Mongkut’s Institute of Technology Ladkrabang School of Information Computer and Communication Technology Sirindhorn International Institute of Technology Thammasat University Next AI Solutions Department of Biomedical Engineering Faculty of Engineering Mahidol University Department of Computer Science University of Liverpool Department of Mechanical Engineering King Mongkut’s University of Technology North Bangkok Artificial Intelligence Entrepreneur Association of Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

Large language models (LLMs) play an important role in modern NLP technology as they are versatile for a wide array of NLP tasks. However, constructing an LLM is challenging due to concealed construction pipelines, the lack of cleansed datasets, and hyperparameter settings, making it almost irreproducible. This paper presents an efficient pipeline for constructing an LLM tailored to a low-to-medium-sourced language with a high level of data contamination and tools to cleanse the dataset. Following our pipeline, we constructed OpenThaiGPT, an LLM for Thai, with only open-sourced datasets such as CC100, OSCAR, and mC4, and achieved the state-of-the-art accuracies on our downstream tasks. Here, we disclosed the data statistics and all hyperparameter settings for reproducibility.

关键词： Accuracy Large language models Decontamination Pipelines data visualization data models Natural language processing Reproducibility of results Arrays Contamination

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：