检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Yunke Du, Bo Xu, Chang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia

Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or negative, we investigate unlabeled imperfect expert demonstrations as they are. A positive-unlabeled adversarial imitation learning algorithm is developed to dynamically sample expert demonstrations that can well match the trajectories from the constantly optimized agent policy. The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations. Theoretical analysis shows that our method learns from the imperfect demonstrations via a self-paced way. Experimental results on MuJoCo and RoboSuite platforms demonstrate the effectiveness of our method from different aspects. Copyright © 2023, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning based Real-Time Application for Engagement Detection 9

A Machine Learning based Real-Time Application for Engagemen...

引用

9th Scholar's Yearly Symposium of Technology, engineering and Mathematics, SYSTEM 2023

作者： Iacobelli, Emanuele Russo, Samuele Napoli, Christian Department of Computer Control and Management Engineering Sapienza University of Rome Roma00185 Italy Department of Psychology Sapienza University of Rome Roma00185 Italy Institute for Systems Analysis and Computer Science Italian National Research Council Roma00185 Italy Department of Computational Intelligence Czestochowa University of Technology Czestochowa42-201 Poland

The study of human engagement has significantly grown in recent years, particularly accelerated by the interaction with a growing number of smart computing machines [1, 2, 3]. Engagement estimation has significant importance across various domains of study, including advertising, marketing, human-computer interaction, and healthcare [4, 5, 6]. In this paper, we propose a real-time application that leverages a single RGB camera to capture user behavior. Our approach implements a novel method for estimating human engagement in real-world scenarios by extracting valuable information from the combination of facial expressions and gaze direction analysis. To acquire this data, we employed fast and accurate machine learning algorithms from the external library dlib, along with custom versions of Residual Neural Networks implemented from scratch. For training our models, we used a modified version of the DAiSEE dataset, a multi-label user affective states classification dataset that collects frontal videos of 112 different people recorded in real-world scenarios. In the absence of a baseline for comparing the results obtained by our application, we conducted experiments to assess its robustness in estimating engagement levels, leading to very encouraging results. © 2023 Copyright for this paper by its authors.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

RGB-D Grasp Detection via Depth Guided Learning with Cross-m...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Ran Qin Haoxiang Ma Boyang Gao Di Huang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Geometry Robotics and the School of Computer Science and Technology Harbin Institute of Technology Harbin China

Planar grasp detection is one of the most fundamental tasks to robotic manipulation, and the recent progress of consumer-grade RGB-D sensors enables delivering more comprehensive features from both the texture and shape modalities. However, depth maps are generally of a relatively lower quality with much stronger noise compared to RGB images, making it challenging to acquire grasp depth and fuse multi-modal clues. To address the two issues, this paper proposes a novel learning based approach to RGB-D grasp detection, namely Depth Guided Cross-modal Attention Network (DGCAN). To better leverage the geometry information recorded in the depth channel, a complete 6-dimensional rectangle representation is adopted with the grasp depth dedicatedly considered in addition to those defined in the common 5-dimensional one. The prediction of the extra grasp depth substantially strengthens feature learning, thereby leading to more accurate results. Moreover, to reduce the negative impact caused by the discrepancy of data quality in two modalities, a Local Cross-modal Attention (LCA) module is designed, where the depth features are refined according to cross-modal relations and concatenated to the RGB ones for more sufficient fusion. Extensive simulation and physical evaluations are conducted and the experimental results highlight the superiority of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis

arXiv

引用

arXiv 2024年

作者： Xu, Kaishuai Hou, Wenjun Cheng, Yi Wang, Jian Li, Wenjie Department of Computing The Hong Kong Polytechnic University Hong Kong Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

Medical dialogue systems have attracted growing research attention as they have the potential to provide rapid diagnoses, treatment plans, and health consultations. In medical dialogues, a proper diagnosis is crucial as it establishes the foundation for future consultations. Clinicians typically employ both intuitive and analytic reasoning to formulate a differential diagnosis. This reasoning process hypothesizes and verifies a variety of possible diseases and strives to generate a comprehensive and rigorous diagnosis. However, recent studies on medical dialogue generation have overlooked the significance of modeling a differential diagnosis, which hinders the practical application of these systems. To address the above issue, we propose a medical dialogue generation framework with the Intuitive-then-Analytic Differential Diagnosis (IADDx). Our method starts with a differential diagnosis via retrieval-based intuitive association and subsequently refines it through a graph-enhanced analytic procedure. The resulting differential diagnosis is then used to retrieve medical knowledge and guide response generation. Experimental results on two datasets validate the efficacy of our method. Besides, we demonstrate how our framework assists both clinicians and patients in understanding the diagnostic process, for instance, by producing intermediate results and graph-based diagnosis paths. © 2024, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Power of AI With Deep Learning: Innovations and Implications

Harnessing the Power of AI With Deep Learning: Innovations a...

引用

Computational, Communication and Information Technology (ICCCIT), International Conference on

作者： Talluri Upender C. Sathiyamoorthy Udayakumar K D. Kirubakaran Purushothaman V Kiruba Thangam Raja Department of CSE CMR College of Engineering and Technology Medchal Hyderabad Telangana Department of Commerce Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamil Nadu India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.K. Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai Tamil Nadu India Department of Software and Systems Engineering School of Computer Science Engineering and Information Systems (SCORE) VIT University Vellore Tamil Nadu India

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512972

The rapid advancements in artificial intelligence (AI) and deep learning have revolutionized various sectors, enabling unprecedented levels of innovation and efficiency. This paper delves into the transformative impact of deep learning across multiple domains, highlighting key innovations and their broader implications. By examining cutting-edge applications in healthcare, finance, autonomous systems, and natural language processing, the study elucidates how deep learning models, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are pushing the boundaries of what's possible. Moreover, the paper explores the integration of deep learning with emerging technologies such as the Internet of Things (IoT), edge computing, and quantum computing, underscoring the synergistic potential of these combinations. The role of deep learning in predictive analytics and personalized solutions is discussed, showcasing its ability to enhance decision-making processes and improve user experiences. Furthermore, the paper discusses the ethical considerations, challenges, and future prospects associated with the widespread adoption of deep learning technologies. The insights provided aim to foster a deeper understanding of how harnessing AI with deep learning can drive progress while addressing critical societal and technological issues.

关键词： Deep learning Technological innovation Ethics Recurrent neural networks Autonomous systems Finance Medical services Safety Internet of Things Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Quantum-based Collaborative Communication Framework for Telehealth

Blockchain and Quantum-based Collaborative Communication Fra...

引用

International Conference on e-health Networking, Applications and Services (HealthCom)

作者： Harshal Gajjar Dirgha Jivani Chinmay Trivedi Rajesh Gupta Nilesh Kumar Jadav Sudeep Tanwar Ashit Kumar Dutta Joel J.P.C. Rodrigues Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat India Department of Computer Science and Information Systems College of Applied Sciences AlMaarefa University Saudi Arabia Amazonas State University Manaus AM Brazil

ISBN: (数字)9798350350548

ISBN: (纸本)9798350350555

This paper introduces a novel telehealth communication system, designed to enhance the security and integrity of medical data exchange. In the rapidly evolving digital healthcare landscape, the protection of sensitive patient information is paramount. To address this, our system uniquely combines quantum cryptography, specifically the BB84 protocol, with blockchain technology, offering a dual-layered security framework. The Quantum Layer, underpinned by the BB84 protocol, establishes quantum-secure communication channels, effectively encrypting data exchanges between patients, doctors, and hospitals. This layer guarantees that medical information remains confidential and safe from potential quantum-level eavesdropping threats. The subsequent Blockchain Layer further strengthens the system by storing these encrypted communications in an immutable blockchain ledger. This approach not only secures the data against unauthorized alterations but also provides a transparent and permanent record of all transactions, thereby enhancing the auditability of medical communications.

关键词： Technological innovation Protocols Hospitals Telemedicine Communication channels Blockchains Electronic healthcare Quantum cryptography Protection Eavesdropping

来源：评论

学校读者我要写书评

暂无评论

An effective approach for detecting deepfake videos using Long Short-Term Memory and ResNet

An effective approach for detecting deepfake videos using Lo...

引用

International Conference on Communication, Computing and Internet of Things (IC3IoT)

作者： S Keerthana N Deepika E Pooja I Nandhini M Shanthalakshmi G R Khanaghavalle Department of Computer Science and Engineering Sri Venkateswara College of Engineering Pennalur Sriperumbudur Tamilnadu India Department of Computer Science and Business Systems Rajalakshmi Institute of Technology Kuthambakkam Tamilnadu India Department of ECE School of Electrical and Communication Vel Tech Rangarajan Dr. Sakunthala R&D Institute of Science and Technology Avadi

ISBN: (数字)9798350352689

ISBN: (纸本)9798350352696

Deep learning algorithms are becoming more potent and producing human-synthesized, undifferentiated footage is a simple process thanks to advances in computing power. A method of synthesizing human images called deep fakes is built on neural network techniques like GAN. These technologies use deep learning algorithms to overlay target pictures onto the source films, producing realistic-looking deep-fake photos and videos. In this work, we provide a novel deep-learning approach that can reliably discriminate between actual and AI-generated fake videos. In this work, we test our method on a large number of balanced and mixed datasets created by mixing various publicly available datasets, such as Face-Forensic++, Deepfake detection, Celeb DF, and other publicly available datasets as images and videos, to emulate real-time scenarios and improve model performance with real-time data by using LSTM and ResNet.

关键词： Deep learning Deepfakes Films Neural networks Generative adversarial networks Real-time systems Telecommunication computing

来源：评论

学校读者我要写书评

暂无评论

NUMA-Aware Optimization of Sparse Matrix-Vector Multiplication on ARMv8-Based Many-Core Architectures 17th

NUMA-Aware Optimization of Sparse Matrix-Vector Multiplicati...

引用

17th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2020

作者： Yu, Xiaosong Ma, Huihui Qu, Zhengyu Fang, Jianbin Liu, Weifeng Super Scientific Software Laboratory Department of Computer Science and Technology China University of Petroleum-Beijing Beijing China Institute for Computer Systems College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9783030794774

As a fundamental operation, sparse matrix-vector multiplication (SpMV) plays a key role in solving a number of scientific and engineering problems. This paper presents a NUMA-Aware optimization technique for the SpMV operation on the Phytium 2000+ ARMv8-based 64-core processor. We first provide a performance evaluation of the NUMA architecture of the Phytium 2000+ processor, then reorder the input sparse matrix with hypergraph partitioning for better cache locality, and redesign the SpMV algorithm with NUMA tools. The experimental results on Phytium 2000+ show that our approach utilizes the bandwidth in a much more efficient way, and improves the performance of SpMV by an average speedup of 1.76x on Phytium 2000+. © 2021, IFIP International Federation for Information Processing.

关键词： ARM processors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Severity Detection in Alzheimer's Disease: A Comprehensive Study on Cognitive Impairment

Deep Learning-Based Severity Detection in Alzheimer's Diseas...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： M Kayalvizhi G Senthil Kumar V Tushal M Yashvanth G Santhosh Department of Biomedical Engineering Chennai Institute of Technology Chennai India Department of Computer Science and Business Systems Chennai Institute of Technology Chennai India

Alzheimer's disease is a neurodegenerative disorder affecting millions worldwide, causing cognitive decline. Early detection is crucial for effective treatment, but manual diagnosis is error-prone and time-consuming. This study proposes a deep learning-based model for diagnosing and classifying Alzheimer's disease using VGG-16 CNN architectures. The model uses the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which includes MRI scans from individuals with Alzheimer's and healthy controls. The model uses a pre-trained VGG-16 convolutional neural network as the base, fine-tuning on the dataset, and data augmentation techniques. The trained model achieves a 96.75% accuracy on the testing dataset, distinguishing MRI scans between Alzheimer's patients and healthy controls. The VGG-16 architecture demonstrated superior performance during training and testing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural NILM Learning Paradigms: From Centralised to Decentralised Learning 5

Neural NILM Learning Paradigms: From Centralised to Decentra...

引用

5th International Conference on Signal Processing and Information Security, ICSPIS 2022

作者： Bousbiat, Hafsa Klemenjak, Christoph Himeur, Yassine Elmenreich, Wilfried Amira, Abbes Mansoor, Wathiq Atalla, Shadi University of Klagenfurt Institute of Networked and Embedded Systems Klagenfurt Austria University of Dubai College of Engineering and IT Dubai United Arab Emirates University of Sharjah Department of Computer Science United Arab Emirates

ISBN: (纸本)9781665492652

Non-intrusive Load Monitoring (NILM) is becoming a paramount in both industrial and residential sectors to achieve efficient energy consumption. Thus, research on this matter flourished in recent years, where deep neural networks gained the highest interest from the research community, commonly referred to as neural NILM. As a predominant practice, neural NILM models follow a centralised based learning scheme where the energy data is assumed to be available in a central node for training. However, this practice and the enormous amount of data required by these algorithms raise privacy and security concerns from the consumer's side since energy data can reveal in-home activities and occupancy records if intercepted. Federated Learning (FL), also referred to as collaborative learning, is seen as viable solution to address these issues. Nonetheless, its application in neural NILM is still in its infancy and many challenges are yet to be addressed. The current paper presents an overview of neural NILM models following both a centralised and a federated learning paradigm. Furthermore, it identifies the main challenges with regard to both learning paradigms along with potential future research directions for more robust, secure and privacy-preserving models in the neural NILM industry. © 2022 IEEE.

关键词： Deep neural networks

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：