检索结果-内蒙古大学图书馆

A survey on recent advancements for AI enabled radiomics in neuro-oncology 1

学校读者我要写书评

暂无评论

1st International Workshop on Radiomics and Radiogenomics in Neuro-oncology, RNO-AI 2019, held in conjunction with the 22nd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2019

作者： Anwar, Syed Muhammad Altaf, Tooba Rafique, Khola Raviprakash, Harish Mohy-Ud-din, Hassan Bagci, Ulas Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States Department of Computer Science University of Wah Wah Pakistan Department of Software Engineering University of Engineering and Technology Taxila47050 Pakistan Lahore Pakistan

ISBN: (数字)9783030401245

ISBN: (纸本)9783030401238

Artificial intelligence (AI) enabled radiomics has evolved immensely especially in the field of oncology. Radiomics provide assistance in diagnosis of cancer, planning of treatment strategy, and prediction of survival. Radiomics in neuro-oncology has progressed significantly in the recent past. Deep learning has outperformed conventional machine learning methods in most image-based applications. Convolutional neural networks (CNNs) have seen some popularity in radiomics, since they do not require hand-crafted features and can automatically extract features during the learning process. In this regard, it is observed that CNN based radiomics could provide state-of-the-art results in neuro-oncology, similar to the recent success of such methods in a wide spectrum of medical image analysis applications. Herein we present a review of the most recent best practices and establish the future trends for AI enabled radiomics in neuro-oncology. © Springer Nature Switzerland AG 2020.

关键词： Medical imaging

CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Kaizhong Yu, Shujian Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands Machine Learning Group UiT - Arctic University of Norway Tromsø Norway

There is a recent trend to leverage the power of graph neural networks (GNNs) for brain-network based psychiatric diagnosis, which, in turn, also motivates an urgent need for psychiatrists to fully understand the decision behavior of the used GNNs. However, most of the existing GNN explainers are either post-hoc in which another interpretive model needs to be created to explain a well-trained GNN, or do not consider the causal relationship between the extracted explanation and the decision, such that the explanation itself contains spurious correlations and suffers from weak faithfulness. In this work, we propose a granger causality-inspired graph neural network (CI-GNN), a built-in interpretable model that is able to identify the most influential subgraph (i.e., functional connectivity within brain regions) that is causally related to the decision (e.g., major depressive disorder patients or healthy controls), without the training of an auxillary interpretive network. CI-GNN learns disentangled subgraph-level representations α and β that encode, respectively, the causal and non-causal aspects of original graph under a graph variational autoencoder framework, regularized by a conditional mutual information (CMI) constraint. We theoretically justify the validity of the CMI regulation in capturing the causal relationship. We also empirically evaluate the performance of CI-GNN against three baseline GNNs and four state-of-the-art GNN explainers on synthetic data and three large-scale brain disease datasets. We observe that CI-GNN achieves the best performance in a wide range of metrics and provides more reliable and concise explanations which have clinical evidence. The source code and implementation details of CI-GNN are freely available at GitHub repository (https://***/ZKZ-Brain/CI-GNN/). Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

A Channel Selection Method for Motor Imagery EEG Based on Fisher Score of OVR-CSP

学校读者我要写书评

暂无评论

A Channel Selection Method for Motor Imagery EEG Based on Fi...

International Winter Workshop on Brain-computer Interface (BCI)

作者： Wei Mu Junkongshuai Wang Lu Wang Pengchao Wang Jiaguan Han Lan Niu Jianxiong Bin Lusheng Liu Jing Zhang Jie Jia Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Laboratory for Neural Interface and Brain Computer Interface Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

EEG is widely used in the field of brain computer interfaces. It has the advantages of being non-invasive, easy acquisition, and so on. However, multi-channel EEG signals will bring noise interference and redundant information while improving the resolution, and channel selection can reduce noise signals to obtain more real signals. Therefore, appropriate channel selection is very necessary for BCI system application. This paper proposes a Fisher score calculation method based on OVR-CSP features for channel selection and uses a transformer to classify. The experimental results show that the proposed method achieves 85.54% accuracy in selecting 16.55 channels on the public dataset BCI IV IIa.

关键词： Electrodes Interference Transformers Feature extraction Electroencephalography Brain-computer interfaces Physiology

CONIC10K: A Challenging Math Problem Understanding and Reasoning Dataset

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Haoyi Hui, Wenyang Chen, Yezeng Wu, Weiqi Tu, Kewei Zhou, Yi School of Information Science and Technology ShanghaiTech University China Shanghai Engineering Research Center of Intelligent Vision and Imaging China School of Information Science and Technology University of Science and Technology of China China National Engineering Laboratory for Brain-inspired Intelligence Technology and Application China Key Laboratory of Brain Cognition and Education Sciences Ministry of Education China Shanghai Innovation Center for Processor Technologies China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Mathematical understanding and reasoning are crucial tasks for assessing the capabilities of artificial intelligence (AI). However, existing benchmarks either require just a few steps of reasoning, or only contain a small amount of data in one specific topic, making it hard to analyse AI's behaviour with reference to different problems within a specific topic in detail. In this work, we propose CONIC10K, a challenging math problem dataset on conic sections in Chinese senior high school education. Our dataset contains various problems with different reasoning depths, while only the knowledge from conic sections is required. Since the dataset only involves a narrow range of knowledge, it is easy to separately analyse the knowledge a model possesses and the reasoning ability it has. For each problem, we provide a high-quality formal representation, the reasoning steps, and the final solution. Experiments show that existing large language models, including GPT-4, exhibit weak performance on complex reasoning. We hope that our findings could inspire more advanced techniques for precise natural language understanding and reasoning. Our dataset and codes are available at https://***/whyNLP/Conic10K. © 2023, CC BY.

关键词：

Optimal Landing of Tilt-rotor Aircraft after Engine Failure Considering Pilot Inherent Limitations

学校读者我要写书评

暂无评论

Optimal Landing of Tilt-rotor Aircraft after Engine Failure ...

IEEE International Conference on robotics and Biomimetics

作者： Xufei Yan Renliang Chen Shiqiang Zhu Anhuan Xie Jason Gu Research Center for Intelligent Robotics Zhejiang Lab Hangzhou 311100 China. Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou China National Key Laboratory of Science and Technology on Rotorcraft Aeromechanics College of Aeronautics Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China Intelligent Robot Research Center Zhejiang Lab Hangzhou Zhejiang China Department of Electrical and Computer Engineering Dalhousie University Halifax NS Canada

ISBN: (纸本)9781665481106

An augmented longitudinal rigid-body model is developed with a set of algebra equations describing the controls in the cockpit and the differential equations describing the pilot inherent limitations. The landing procedure after one engine failure is formulated into a nonlinear optimal control problem. XV-15 tilt-rotor aircraft is taken as the sample for the demonstration of landing in one engine failure during short takeoff. The results show that the total power required, thrust coefficient, longitudinal flapping angle and optimal controls are more relatively gentle than the solutions without considering the pilot inherent limitations. Compared with the basic longitudinal rigid-body model, the optimal solutions involve more control information.

关键词： Atmospheric modeling Optimal control Rotors Mathematical models History Aircraft propulsion Aircraft

An Illumination-Robust Feature Extractor Augmented by Relightable 3D Reconstruction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Shunyi Yu, Zehuan Fan, Zuxin Zhou, Zhihao Ruan, Lecheng Wang, Qining College of Engineering Peking University Beijing100871 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Institute for Artificial Intelligence Peking University Beijing100871 China Beijing Engineering Research Center of Intelligent Rehabilitation Engineering Beijing100871 China Department of Advanced Manufacturing and Robotics College of Engineering Peking University Beijing100871 China University of Health and Rehabilitation Sciences Qingdao China

Visual features, whose description often relies on the local intensity and gradient direction, have found wide applications in robot navigation and localization in recent years. However, the extraction of visual features is usually disturbed by the variation of illumination conditions, making it challenging for real-world applications. Previous works have addressed this issue by establishing datasets with variations in illumination conditions, but can be costly and time-consuming. This paper proposes a design procedure for an illuminationrobust feature extractor, where the recently developed relightable 3D reconstruction techniques are adopted for rapid and direct data generation with varying illumination conditions. A self-supervised framework is proposed for extracting features with advantages in repeatability for key points and similarity for descriptors across good and bad illumination conditions. Experiments are conducted to demonstrate the effectiveness of the proposed method for robust feature extraction. Ablation studies also indicate the effectiveness of the self-supervised framework design. © 2024, CC BY.

关键词： Feature extraction

A Survey on Large Language Models: Applications, Challenges, Limitations, and Practical Usage

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2025年

作者： Hadi, Muhammad Usman Al-Tashi, Qasem Qureshi, Rizwan Shah, Abbas Muneer, Amgad Irfan, Muhammad Zafar, Anas Shaikh, Muhammad Bilal Akhtar, Naveed Al-Garadi, Mohammed Ali Hassan, Syed Zohaib Shoman, Maged Wu, Jia Mirjalili, Seyedali Shah, Mubarak School of Engineering Ulster University BelfastBT15 1AP United Kingdom Department of Imaging Physics The University of Texas MD Anderson Cancer Center HoustonTX77030 United States Department of Electronics Engineering Mehran University of Engineering and Technology Jamshoro76062 Pakistan of Engineering Sciences and Technology Swabi23460 Pakistan Department of Computer Science National University of Computer and Emerging Sciences Karachi Pakistan Edith Cowan University 270 Joondalup Drive Joondalup PerthWA6027 Australia Computing and Information Systems The University of Melbourne 700 Swanston Street CarltonVIC3010 Australia Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Civil Environmental and Construction Engineering The University of Central Florida OrlandoFL United States Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley BrisbaneQLD4006 Australia University Research and Innovation Center Obuda University Budapest1034 Hungary Center for Research in Computer Vision The University of Central Florida OrlandoFL United States

Within the vast expanse of computerized language processing, a revolutionary entity known as Large Language Models (LLMs) has emerged, wielding immense power in its capacity to comprehend intricate linguistic patterns and conjure coherent and contextually fitting responses. LLMs are a type of artificial intelligence (AI) that have emerged as powerful tools for a wide range of tasks, including natural language processing (NLP), machine translation, vision applications, and question-answering. This survey provides a comprehensive overview of LLMs, including their history, architecture, datasets, training methods, applications, challenges, and future prospects. We begin by discussing the fundamental concepts of generative AI and the architecture of generative pre-trained transformers (GPT). We then provide an overview of the history of LLMs, their evolution over time, and the different training methods. We also present benchmark dataset for training and fine-tuning and evaluating LLMs. We then discuss the wide range of tasks where they are used and also discuss applications of LLMs in different domains, including medicine, education, finance, engineering, agriculture, media, entertainment, politics, and law. We also discuss how LLMs are shaping the future of AI and their increasing role in scientific discovery, and how they can be used to solve real-world problems. Next, we explore the challenges associated with deploying LLMs in real-world scenarios, including ethical considerations, model biases, interpretability, privacy concerns, and computational resource requirements. This survey also highlights techniques for enhancing the robustness and controllability of LLMs and addressing bias, fairness, and quality issues in Generative AI. Finally, we conclude by highlighting the future of LLM research and the challenges that need to be addressed in order to make this technology more reliable and useful. This survey is intended to provide researchers, practitioners, and ent

关键词： Natural language processing systems

Towards Cross-device and Training-free Robotic Grasping in 3D Open World

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Weiguang Jiang, Chenru Zhang, Chengrui Sun, Jie Yan, Yuyao Zhang, Rui Huang, Kaizhu Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom Data Science Research Center Duke Kunshan University Suzhou215316 China Department of Electrical Engineering University of Liverpool LiverpoolL69 7ZX United Kingdom Department of Mechatronics and Robotics Xi’an-Jiaotong Liverpool University Suzhou215123 China School of Robotic Xi’an Jiaotong-Liverpool University Suzhou215123 China Department of Foundational Mathematics Xi’an Jiaotong-Liverpool University Suzhou215123 China

— Robotic grasping in the open world is a critical component of manufacturing and automation processes. While numerous existing approaches depend on 2D segmentation output to facilitate the grasping procedure, accurately determining depth from 2D imagery remains a challenge, often leading to limited performance in complex stacking scenarios. In contrast, techniques utilizing 3D point cloud data inherently capture depth information, thus enabling adeptly navigating and manipulating a diverse range of complex stacking scenes. However, such efforts are considerably hindered by the variance in data capture devices and the unstructured nature of the data, which limits their generalizability. Consequently, much research is narrowly concentrated on managing designated objects within specific settings, which confines their real-world applicability. This paper presents a novel pipeline capable of executing object grasping tasks in open-world scenarios even on previously unseen objects without the necessity for training. Additionally, our pipeline supports the flexible use of different 3D point cloud segmentation models across a variety of scenes. Leveraging the segmentation results, we propose to engage a training-free binary clustering algorithm that not only improves segmentation precision but also possesses the capability to cluster and localize unseen objects for executing grasping operations. In our experiments, we investigate a range of open-world scenarios, and the outcomes underscore the remarkable robustness and generalizability of our pipeline, consistent across various environments, robots, cameras, and objects. The code will be made available upon acceptance of the paper. © 2024, CC BY-NC-ND.

关键词： Image segmentation

Transductive zero-shot learning by decoupled feature generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Marmoreo, Federico Cavazza, Jacopo Murino, Vittorio Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Italy University of Genova Italy Huawei Technologies Ltd. Ireland Research Center Ireland Department of Computer Science University of Verona Italy

In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen classes is available. State-of-the-art paradigms in ZSL typically exploit generative adversarial networks to synthesize visual features from semantic attributes. We posit that the main limitation of these approaches is to adopt a single model to face two problems: 1) generating realistic visual features, and 2) translating semantic attributes into visual cues. Differently, we propose to decouple such tasks, solving them separately. In particular, we train an unconditional generator to solely capture the complexity of the distribution of visual data and we subsequently pair it with a conditional generator devoted to enrich the prior knowledge of the data distribution with the semantic content of the class embeddings. We present a detailed ablation study to dissect the effect of our proposed decoupling approach, while demonstrating its superiority over the related state-of-the-art. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks