检索结果-内蒙古大学图书馆

Early cancer detection by serum biomolecular fingerprinting spectroscopy with machine learning

eLight 2023年第1期3卷 94-104页

作者： Shilian Dong Dong He Qian Zhang Chaoning Huang Zhiheng Hu Chenyang Zhang Lei Nie Kun Wang Wei Luo Jing Yu Bin Tian Wei Wu Xu Chen Fubing Wang Jing Hu Xiangheng Xiao Department of Physics National Demonstration Center for Experimental Physics EducationWuhan UniversityWuhan 430072China Department of Laboratory Medicine Zhongnan Hospital of Wuhan UniversityWuhan 430071China School of Computer Science Wuhan UniversityWuhan 430072China Department of Hepatobiliary Pancreatic Surgery Hubei Cancer HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430079China Department of Clinical Laboratory Tianjin Medical University General HospitalTianjin 300052China Department of Blood Transfusion Wuhan Hospital of Traditional Chinese and Western MedicineTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Laboratory of Printable Functional Materials and Printed Electronics Research Center for Graphic CommunicationPrinting and PackagingWuhan UniversityWuhan 430072China Sichuan Provincial Key Laboratory for Human Disease Gene Study and the Center for Medical Genetics Department of Laboratory MedicineSichuan Academy of Medical Sciences&Sichuan Provincial People’s HospitalUniversity of Electronic Science and TechnologyChengdu 611731China School of Medicine University of Electronic Science and Technology of ChinaChengdu 611731China Wuhan Research Center for Infectious Diseases and Cancer Chinese Academy of Medical SciencesWuhan 430071China

Label-free surface-enhanced Raman scattering(SERS)technique with ultra-sensitivity becomes more and more desirable in biomedical analysis,which is yet hindered by inefficient follow-up data *** we report an integrative method based on SERS and Artificial Intelligence for Cancer Screening(SERS-AICS)for liquid biopsy such as serum via silver nanowires,combining molecular vibrational signals processing with large-scale data mining *** to 382 healthy controls and 1582 patients from two independent cohorts,SERS-AICS not only distinguishes pan-cancer patients from health controls with 95.81% overall accuracy and 95.87% sensitivity at 95.40% specificity,but also screens out those samples at early cancer *** supereminent efficiency potentiates SERS-AICS a promising tool for detecting cancer with broader types at earlier stage,accompanying with the establishment of a data platform for further deep analysis.

关键词： analysis specificity silver

来源：评论

学校读者我要写书评

暂无评论

The effects of virtual reality on muscle synergies during walking and balancing in healthy adults

引用

Gait & Posture 2024年 113卷 55-56页

作者： Johannes Eichwalder Paul Kaufmann Thomas Mandl Brian Horsak Hans Kainz University of Vienna Centre for Sport Science and University Sports- Department of Sport and Human Movement Science Vienna Austria University of Applied Sciences for Technology and Digitalization Faculty Computer Science- Department Applied Mathematics & Physics Vienna Austria University of Applied Sciences St. Pölten Department of Health Sciences- Center for Digital Health and Social Innovation St. Pölten Austria

来源：评论

学校读者我要写书评

暂无评论

Pre-training Multi-party Dialogue Models with Latent Discourse Inference

arXiv

引用

arXiv 2023年

作者： Li, Yiyang Huang, Xinting Bi, Wei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China NLP Center Tencent AI-Lab Hong Kong

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these obstacles, an effective way is to pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. However, due to the lack of explicitly annotated discourse labels in multi-party dialogue corpora, previous works fail to scale up the pre-training process by putting aside the unlabeled multi-party conversational data for nothing. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model by unsupervised latent variable inference methods. Experiments on multiple downstream tasks show that our pre-trained model outperforms strong baselines by large margins and achieves state-of-the-art (SOTA) results, justifying the effectiveness of our method. The official implementation of this paper is available at https://***/EricLee8/MPD_EMVI. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

引用

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCILab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Case Study of human-AI interactions Using Transparent AI-Driven Autonomous Systems for Improved human-AI Trust Factors 3

A Case Study of Human-AI Interactions Using Transparent AI-D...

引用

3rd IEEE International Conference on human-Machine Systems, ICHMS 2022

作者： Pham, Daniel Menon, Vineetha Tenhundfeld, Nathan Weger, Kristin Mesmer, Bryan Gholston, Sampson Davis, Thomas The University of Alabama in Huntsville Department of Computer Science HuntsvilleAL United States The University of Alabama in Huntsville Department of Psychology HuntsvilleAL United States The University of Alabama in Huntsville Department of Iseem HuntsvilleAL United States Human Systems Integration Division Devcom Data and Analysis Center HuntsvilleAL United States

ISBN: (数字)9781665452380

ISBN: (纸本)9781665452380

human interactions with Artificial Intelligence (AI) have become a ubiquitous phenomenon in our society. It plays a major role in defense and espionage in the context of AI-based autonomous systems such as drones and ground robots that are sent to the front lines to navigate terrains, map the surroundings, and identify adversaries in the environment. In these types of scenarios, hostages may be spread out over a larger geographical area. Reliance on ground vision alone may not only be obscured and insufficient but also can expose soldiers or human rescuers to danger. Since time is of great essence, such an intense situation calls for decisions to be made swiftly and efficiently as the lives of hostages are at stake. This makes such a scenario ideal to evaluate the effectiveness of an AI-driven drone autonomous system for combat search and rescue (CSAR) missions. Here the focus is to gather information about the operational environment (detect hostages and other targets-of-interest) in a short amount of time that spans a varying geographic terrain. This allows for targeted rescue operations with AI-informed decision-making outcomes to ensure that the rescuers at ground level can be directed along the most optimal path, and casualties will be either minimized or entirely averted. In this work, we study the feasibility of our drone-based AI target detection autonomous system to evaluate the classification accuracy of multi-view targets-of-interest in the CSAR environment. The overarching goal of this study is to understand the role of AI-driven autonomous systems as an assistive support tool for efficient, swift and accurate decision making, navigating a complex and ever-changing environment, and identification of targets. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Benefits of the Immersive Space to Think

Evaluating the Benefits of the Immersive Space to Think

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Lee Lisle Xiaoyu Chen J.K. Edward Gitre Chris North Doug A. Bowman Department of Computer Science Center for Human-Computer Interaction Grado Department of Industrial and Systems Engineering Virginia Tech Department of History Virginia Tech Center for Human-Computer Interaction

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

Sensemaking with large multimedia dataset is a cognitively intensive task that requires analysts to understand the underlying stories that the dataset tells. Often, analysts use tools in order to offload cognition as well as convey their new understanding of the dataset; however, existing tools are limited by their underlying technologies. We have proposed a novel virtual reality tool to support sensemaking called the Immersive Space to Think (IST). IST can aid the process of analyzing multimedia data, but it remains unproven whether IST improves sensemaking performance over a traditional desktop setting. In a study performed over six weeks, one participant used both IST and traditional methods of sensemaking with a dataset of 100 text documents of transcribed survey responses from World War 2 soldiers to perform historical analysis. The participant was asked guided questions that produced three essays with their understanding of the data. After conducting a blind evaluation of the participant’s interpretation of the data, a team of three experts in historical analysis concluded that the essays written with IST displayed a better understanding of the dataset. Furthermore, the participant gave positive feedback on IST, and also suggested possible improvements.

关键词： Tools Visualization Task analysis human computer interaction Virtual reality Three-dimensional displays Information analysis

来源：评论

学校读者我要写书评

暂无评论

Applied intelligence with deep learning assisted automated sarcasm recognition in twitter data

引用

Alexandria Engineering Journal 2025年 128卷 79-91页

作者： Alzaidi, Muhammad Swaileh A. Alsudais, Taghreed Ali Eltahir, Majdy M. Ebad, Shouki A. Alshuhail, Asma Alshahrani, Mohammed Alanazi, Sultan Department of English Language College of Language Sciences King Saud University P. O. Box 145111 Riyadh Saudi Arabia Department of Teaching and Learning College of Education and Human Development Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Computer Department Applied College Najran University Najran66462 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj16273 Saudi Arabia

Sarcasm is essential in human interaction, particularly on social networking, where individuals share their feelings through criticism, humour, and satire. Sarcasm detection is vital in understanding the context of communication and the sentiment on platforms such as Twitter. This presents sarcasm detection as a complex problem in natural language processing (NLP). The challenges and importance upsurge, particularly in languages such as Arabic and Urdu, where resources for NLP are inadequate. The classical rule-based techniques need to improve performance owing to sarcasm's context-based and subtle nature. On the other hand, the current developments in deep learning (DL) and NLP offer efficient solutions. Therefore, this study presents an Applied Intelligence with Deep Learning Assisted Automated Sarcasm Recognition Approach (AIDL-ASRA) on Twitter Data. The presented AIDL-ASRA technique concentrates on identifying sarcastic and non-sarcastic contexts in tweets. In the AIDL-ASRA technique, the initial pre-processing stage is executed with different subprocesses. Next, Global Vectors for Word Representation (GloVe)-based word embedding process occurs. The AIDL-ASRA technique utilizes the Discriminative Deep Belief Networks (DDBN) method for sarcasm recognition. The DBN model's effectiveness is improved using the cat swarm optimization (CSO) model. A set of experiments were involved in evaluating the performance of the AIDL-ASRA method under the Arabic sarcastic dataset comprising 10,000 tweets. The experimental validation of the AIDL-ASRA method attained a superior accuracy value of 91.25 % over existing techniques under distinct measures. © 2025 The Authors

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Event-Guided Attention Network for Low Light Image Enhancement

Event-Guided Attention Network for Low Light Image Enhanceme...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qiaobin Wang Haiyan Jin Haonan Su Zhaolin Xiao Department of Computer Science and Engineering Engineering Research Center Shaanxi Key Laboratory for Network Computing and Security Technology Human-Machine Integration Intelligent Robot Shaanxi University Xi'an University of Technology

In the low-light conditions, images are corrupted by low contrast and severe noise, but event cameras can capture event streams with clear edge structures. Therefore, we propose an Event-Guided Attention Network for Low-light Image Enhancement (EGAN) using a dual branch Network and recover clear structure with the guide of events. To overcome the lack of paired training datasets, we first synthesize the dataset containing low-light event streams, low-light images, and the ground truth (GT) normal-light images. Then, we develop an end-to-end dual branch network consisting of a Image Enhancement Branch (IEB) and a Gradient Reconstruction Branch (GRB). The GRB branch reconstructs image gradients using events, and the IEB enhances low-light images using reconstructed gradients. Moreover, we develops the Attention based Event-Image Feature Fusion Module (AEIFFM) which selectively fuses the event and low-light image features using the spatial and channel attention mechanism, and the fused features are concatenated into the IEB and GRB, which respectively generate the enhanced images with clear structure and more accurate gradient images. Extensive experiments on synthetic and real datasets demonstrate that the proposed EGAN produces visually more appealing enhancement images, and achieves a good performance in structure preservation and denoising over state-of-the-arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fractal scaling and the aesthetics of trees

arXiv

引用

arXiv 2024年

作者： Gao, Jingyi Newberry, Mitchell University of Wisconsin Madison Department of Computer Science United States University of New Mexico Department of Biology United States University of Michigan Center for the Study of Complex Systems United States Max Planck Institute for Evolutionary Anthropology Department of Human Behaviour Ecology and Culture Germany

Trees in works of art have stirred emotions in viewers for millennia. Leonardo da Vinci described geometric proportions in trees to provide both guidelines for painting and insights into tree form and function. Da Vinci’s Rule of trees further implies fractal branching with a particular scaling exponent α = 2 governing both proportions between the diameters of adjoining boughs and the number of boughs of a given diameter. Contemporary biology increasingly supports an analogous rule with α = 3 known as Murray’s Law. Here we relate trees in art to a theory of proportion inspired by both da Vinci and modern tree physiology. We measure α in 16th century Islamic architecture, Edo period Japanese painting and 20th century European art, finding α in the range 1.5 to 2.5. We find that both conformity and deviations from ideal branching create stylistic effect and accommodate constraints on design and implementation. Finally, we analyze an abstract tree by Piet Mondrian which forgoes explicit branching but accurately captures the modern scaling exponent α = 3, anticipating Murray’s Law by 15 years. This perspective extends classical mathematical, biological and artistic ways to understand, recreate and appreciate the beauty of trees. © 2024, CC BY-SA.

关键词： Fractals

来源：评论

学校读者我要写书评

暂无评论

Redundancy-aware unsupervised ranking based on game theory - application to gene enrichment analysis

arXiv

引用

arXiv 2022年

作者： Balestra, Chiara Maj, Carlo Müller, Emmanuel Mayr, Andreas Department of Computer Science TU Dortmund Germany University Hospital of Bonn Germany Center for Human Genetics University Hospital of Marburg Germany

Gene set collections are a common ground to study the enrichment of genes for specific phenotypic traits. Gene set enrichment analysis aims to identify genes that are over-represented in gene sets collections and might be associated with a specific phenotypic trait. However, as this involves a massive number of hypothesis testing, it is often questionable whether a pre-processing step to reduce gene sets collections' sizes is helpful. Moreover, the often highly overlapping gene sets and the consequent low interpretability of gene sets' collections demand for a reduction of the included gene sets. Inspired by this bioinformatics context, we propose a method to rank sets within a family of sets based on the distribution of the singletons and their size. We obtain sets' importance scores by computing Shapley values without incurring into the usual exponential number of evaluations of the value function. Moreover, we address the challenge of including a redundancy awareness in the rankings obtained where, in our case, sets are redundant if they show prominent intersections. We finally evaluate our approach for gene sets collections;the rankings obtained show low redundancy and high coverage of the genes. The unsupervised nature of the proposed ranking does not allow for an evident increase in the number of significant gene sets for specific phenotypic traits when reducing the size of the collections. However, we believe that the rankings proposed are of use in bioinformatics to increase interpretability of the gene sets collections and a step forward to include redundancy into Shapley values computations. Copyright © 2022, The Authors. All rights reserved.

关键词： Game theory

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：