检索结果-内蒙古大学图书馆

Models to Identify Small Brain White Matter Hyperintensities Lesions

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Castillo, Darwin Rodríguez-Álvarez, María José Samaniego, R. Lakshminarayanan, Vasudevan Departamento de Química Universidad Técnica Particular de Loja LojaAp. 11-01-608 Ecuador Valencia Spain Departmento de Radiología Hospital UTPL Loja Ecuador Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo ON Canada Department of Physics Electrical and Computer Engineering and Systems Design Engineering University of Waterloo ON Canada

According to the World Health Organization (WHO), peripheral and central neurological disorders affect approximately one billion people worldwide. Ischemic stroke, Alzheimer's Disease, and other dementias are the second and fifth leading causes of death, respectively. In this context, detecting and classifying brain lesions constitute a critical area of research in medical imaging processing, significantly impacting both clinical practice and scientific advancement. This project aims to develop and implement deep learning models for detecting and classifying small brain White Matter hyperintensities (WMH) lesions in magnetic resonance images (MRI), specifically lesions concerning ischemic and demyelination diseases. The methods applied to segmentation were the UNet, Segmenting Anything model (SAM), YOLOV8, and Detectron2 (based on MaskRCNN). Experimental results show a Dice coefficient (DSC) of 0.94, 0.50,0.241,0.88 for segmentation of WMH lesion using the UNet, SAM, YOLOv8, and Detectron2, respectively. The Detectron2 model demonstrated an accuracy of 0.98 in detecting and 0.93 in classifying lesions, including small lesions where other models often fail. In conclusion, the methods developed give an outline to detect, segment, and classify small brain lesions, and that could significantly aid clinical diagnostics, providing reliable support for physicians and improving patient outcomes. © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Fictional Worlds, Real Connections: Developing Community Storytelling Social Chatbots through LLMs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Yuqian Wang, Hanyi Chan, Pok Man Tabibi, Morteza Zhang, Yan Lu, Huan Chen, Yuheng Lee, Chang Hee Asadipour, Ali Computer Science Research Centre Royal College of Art United Kingdom United States Hong Kong Rct.ai United States China Affective Systems and Cognition Lab Industrial Design Department College of Engineering KAIST United Kingdom Royal College of Art United Kingdom

We address the integration of storytelling and Large Language Models (LLMs) to develop engaging and believable Social Chatbots (SCs) in community settings. Motivated by the potential of fictional characters to enhance social interactions, we introduce Storytelling Social Chatbots (SSCs) and the concept of story engineering to transform fictional game characters into "live" social entities within player communities. Our story engineering process includes three steps: (1) Character and story creation, defining the SC's personality and worldview, (2) Presenting Live Stories to the Community, allowing the SC to recount challenges and seek suggestions, and (3) Communication with community members, enabling interaction between the SC and users. We employed the LLM GPT-3 to drive our SSC prototypes, "David" and "Catherine," and evaluated their performance in an online gaming community, "DE (Alias)," on Discord. Our mixed-method analysis, based on questionnaires (N=15) and interviews (N=8) with community members, reveals that storytelling significantly enhances the engagement and believability of SCs in community settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Developing countries

TransHD: Spatial Transformer Features Extraction for HDC Synergetic Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Artificial Intelligence

IEEE Transactions on Artificial Intelligence 2025年

作者： Hassan, Eman Bettayeb, Meriem Halawani, Yasmin Genssler, Paul R. Tesfai, Huruy Zweiri, Yahya Amrouch, Hussam Hadjileontiadis, Leontios J. Saleh, Hani Mohammad, Baker Khalifa University System on Chip Lab Department of Computer and Information Engineering Abu Dhabi 127788 United Arab Emirates Abu Dhabi University Department of Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates University of Dubai College of Engineering and IT Dubai United Arab Emirates Munich Institute of Robotics and Machine Intelligence Technical University of Munich TUM School of Computation Information and Technology Chair of AI Processor Design Munich Germany Khalifa University of Science and Technology Department of Aerospace Engineering Advanced Research and Innovation Center (ARIC) Abu Dhabi United Arab Emirates University of Stuttgart Semiconductor Test and Reliability (STAR) Stuttgart Germany Khalifa University of Science and Technology Department of Biomedical Engineering Abu Dhabi United Arab Emirates Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki Greece

Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical. © 2020 IEEE.

关键词： Brain-inspired Computing Hyperdimensional Computing Image Classification Spatial Transformers

A Survey on Resource Management in Joint Communication and Computing-Embedded SAGIN

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Qian Guo, Zheng Meng, Weixiao Han, Shuai Li, Cheng Quek, Tony Q.S. The School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China The School of Engineering Science Simon Fraser University BurnabyBCV5A 1S6 Canada Electrical and Computer Engineering Memorial University St. John'sNLA1B 3X5 Canada The Singapore University of Technology and Design Singapore487372 Singapore The Yonsei Frontier Lab Yonsei University Korea Republic of

The advent of the 6G era aims for ubiquitous connectivity, with the integration of non-terrestrial networks (NTN) offering extensive coverage and enhanced capacity. As manufacturing advances and user demands evolve, space-air-ground integrated networks (SAGIN) with computational capabilities emerge as a viable solution for services requiring low latency and high computational power. Resource management within joint communication and computing-embedded SAGIN (JCC-SAGIN) presents greater complexity than traditional terrestrial networks. This complexity arises from the spatiotemporal dynamics of network topology and service demand, the interdependency of large-scale resource variables, and intricate tradeoffs among various performance metrics. Thus, a thorough examination of resource management strategies in JCC-SAGIN is crucial, emphasizing the role of non-terrestrial platforms with processing capabilities in 6G. This paper begins by reviewing the architecture, enabling technologies, and applications in JCC-SAGIN. Then, we offer a detailed overview of resource management modeling and optimization methods, encompassing both traditional optimization approaches and learning-based intelligent decision-making frameworks. Finally, we outline the prospective research directions in JCC-SAGIN. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

CHECKING CONTINUOUS STOCHASTIC LOGIC AGAINST QUANTUM CONTINUOUS-TIME MARKOV CHAINS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mei, Jingyi Xu, Ming Guan, Ji Deng, Yuxin Yu, Nengkun Shanghai Key Lab of Trustworthy Computing East China Normal University China Shanghai Key Lab of Trustworthy Computing & MoE Engineering Research Center of Software/Hardware Co-design Technology and Application East China Normal University China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences China Department of Computer Science Stony Brook University United States

Verifying quantum systems has attracted a lot of interest in the last decades. In this paper, we study the quantitative model-checking of quantum continuous-time Markov chains (quantum CTMCs). The branching-time properties of quantum CTMCs are specified by continuous stochastic logic (CSL), which is famous for verifying real-time systems, including classical CTMCs. The core of checking the CSL formulas lies in tackling multiphase until formulas. We develop an algebraic method using proper projection, matrix exponentiation, and definite integration to symbolically calculate the probability measures of path formulas. Thus the decidability of CSL is established. To be efficient, numerical methods are incorporated to guarantee that the time complexity is polynomial in the encoding size of the input model and linear in the size of the input formula. A running example of Apollonian networks is further provided to demonstrate our method. © 2022, CC BY.

关键词： Stochastic systems

AI Agent for Education: Von Neumann Multi-Agent System Framework

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Yuan-Hao Li, Ruijia Zhou, Yizhou Qi, Changyong Hu, Hanglei Wei, Yuang Jiang, Bo Wu, Yonghe Lab of Artificial Intelligence for Education East China Normal University China Shanghai Institute of Artificial Intelligence for Education East China Normal University China School of Computer Science and Technology East China Normal University China Department of Educational Information Technology East China Normal University China School of Design and Engineering National University of Singapore Singapore

The development of large language models has ushered in new paradigms for education. This paper centers on the multi-Agent system in education and proposes the von Neumann multi-Agent system framework. It breaks down each AI Agent into four modules: control unit, logic unit, storage unit, and input-output devices, defining four types of operations: task deconstruction, self-reflection, memory processing, and tool invocation. Furthermore, it introduces related technologies such as Chain-of-Thought, Reson+Act, and Multi-Agent Debate associated with these four types of operations. The paper also discusses the ability enhancement cycle of a multi-Agent system for education, including the outer circulation for human learners to promote knowledge construction and the inner circulation for LLM-based-Agents to enhance swarm intelligence. Through collaboration and reflection, the multi-Agent system can better facilitate human learners' learning and enhance their teaching abilities in this process. Copyright © 2024, The Authors. All rights reserved.

关键词： Swarm intelligence

Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gomrokchi, Maziar Amin, Susan Aboutalebi, Hossein Wong, Alexander Precup, Doina Department of Computer Science McGill University Mila Canada Cheriton School of Computer Science University of Waterloo VIP Lab Canada Department of Systems Design Engineering University of Waterloo VIP Lab DarwinAI Canada Department of Computer Science McGill University Mila DeepMind Canada

While significant research advances have been made in the field of deep reinforcement learning, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. In such attacking systems, the adversary targets the set of collected input data on which the deep reinforcement learning algorithm has been trained. To address this gap, we propose an adversarial attack framework designed for testing the vulnerability of a state-of-the-art deep reinforcement learning algorithm to a membership inference attack. In particular, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Moreover, we compare the performance of collective and individual membership attacks against the deep reinforcement learning algorithm. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring data with an accuracy exceeding 84% in individual and 97% in collective modes in three different continuous control Mujoco tasks, which raises serious privacy concerns in this regard. Finally, we show that the learning state of the reinforcement learning algorithm influences the level of privacy breaches significantly. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cai, Runze Janaka, Nuwan Kim, Hyeongcheol Chen, Yang Zhao, Shengdong Huang, Yun Hsu, David Synteraction Lab School of Computing National University of Singapore Singapore Synteraction Lab Smart Systems Institute National University of Singapore Singapore Synteraction Lab National University of Singapore Singapore College of Design and Engineering National University of Singapore Singapore Synteraction Lab School of Creative Media Department of Computer Science City University of Hong Kong Hong Kong China School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL United States School of Computing Smart Systems Institute National University of Singapore Singapore

Unlike the free exploration of childhood, the demands of daily life reduce our motivation to explore our surroundings, leading to missed opportunities for informal learning. Traditional tools for knowledge acquisition are reactive, relying on user initiative and limiting their ability to uncover hidden interests. Through formative studies, we introduce AiGet, a proactive AI assistant integrated with AR smart glasses, designed to seamlessly embed informal learning into low-demand daily activities (e.g., casual walking and shopping). AiGet analyzes real-time user gaze patterns, environmental context, and user profiles, leveraging large language models to deliver personalized, context-aware knowledge with low disruption to primary tasks. In-lab evaluations and real-world testing, including continued use over multiple days, demonstrate AiGet’s effectiveness in uncovering overlooked yet surprising interests, enhancing primary task enjoyment, reviving curiosity, and deepening connections with the environment. We further propose design guidelines for AI-assisted informal learning, focused on transforming everyday moments into enriching learning experiences. © 2025, CC BY.

关键词： Contrastive Learning

Application of an enhanced deep super-resolution network in retinal image analysis 30

学校读者我要写书评

暂无评论

Application of an enhanced deep super-resolution network in ...

30th Conference on Ophthalmic Technologies

作者： Gulati, Tanmay Sengupta, Sourya Lakshminarayanan, Vasudevan Department of Computer Science and Engineering Manipal Institute of Technology Manipal India Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo ON Canada Department of Systems Design Engineering University of Waterloo ON Canada

ISBN: (纸本)9781510631991

Fundus imaging is widely used for the diagnosis of retinal diseases. Major ophthalmic diseases like glaucoma, diabetic retinopathy (DR), age-related macular degeneration (AMD) are diagnosed by examining retinal fundus images. Therefore, the efficient and reliable diagnosis largely depends upon the resolution of the images. In different diseased conditions, different pathologies and landmarks (haemorrhages, microaneurysms, exudates, blood vessels, optic disc and optic cup, fovea) of the retina get affected. In clinical situations it is often not possible to obtain good high-resolution images. Here, the techniques of super-resolution can be applied. The objective of super-resolution is to obtain a high-resolution image from a low-resolution input image. In this paper, we present results of the application of enhanced deep residual networks for single image super-resolution (EDSR) on retinal fundus images. This network is based on the SRResNet architecture involving skip connections. Using the public RIGA dataset, which consists of glaucoma and normal fundus images, we have trained the model using 2x, 4x and 8x scaling with three different optimizers each (namely ADAM, Stochastic Gradient Descent and RMSprop) to determine which optimizer is best for the different scales. We have also provided results obtained by varying the residual blocks in the network. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Diagnosis