检索结果-内蒙古大学图书馆

RASnet: Recurrent Aggregation Neural Network for Safe and Efficient Drug Recommendation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhu, Qiang Han, Feng Liu, Junping Meng, Yajie Hu, Xinrong Wang, Bangchao Engineering Research Center of Hubei Province for Clothing Information Hubei Wuhan China School of Computer Science and Artificial Intelligence Hubei Wuhan China

Drug recommendation is one of the most important research topics in smart healthcare. Its goal is to provide a set of safe drug combinations based on the patient’s electrical medical records(EHR). Drug recommendation is challenging since it is difficult to obtain an appropriate representation of patients' health states from these personalized historical records. Meanwhile, drug recommendation must prioritize the safety of drug combinations because drug-drug interactions(DDI) can result in side effects. In order to address these issues, we propose a novel recurrent aggregation neural network for safe drug recommendation, called RASNet. RASNet introduces a straightforward but efficient recurrent aggregation neural network to capture historical records related to the patient’s health state of current visit, which can improve the performance of EHR-based healthy state modeling, particularly in cases when the patient’s condition changes periodically. Furthermore, this paper presents a novel exponential controller for DDI to enhance the safety of drug combinations. Our proposed DDI controller not only balances the DDI rate between the safety and accuracy of drug recommendation but also ensures performance even when the DDI rate is low. Extensive experiments on the MIMIC-III dataset demonstrate that RASNet achieves state-of-the-art performance. Moreover, RASNet exhibits excellent efficiency and safety in drug recommendation. © 2023, The Authors. All rights reserved.

关键词： Controllers

SigStyle: Signature Style Transfer via Personalized Text-to-Image Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Ye Bai, Tongyuan Xie, Xuping Yi, Zili Wang, Yilin Ma, Rui School of Artificial Intelligence Jilin University China College of Computer Science and Technology Jilin University China School of Intelligence Science and Technology Nanjing University China Adobe United States Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOE China

Style transfer enables the seamless integration of artistic styles from a style image into a content image, resulting in visually striking and aesthetically enriched outputs. Despite numerous advances in this field, existing methods did not explicitly focus on the signature style, which represents the distinct and recognizable visual traits of the image such as geometric and structural patterns, color palettes and brush strokes etc. In this paper, we introduce SigStyle, a framework that leverages the semantic priors that embedded in a personalized text-to-image diffusion model to capture the signature style representation. This style capture process is powered by a hypernetwork that efficiently fine-tunes the diffusion model for any given single style image. Style transfer then is conceptualized as the reconstruction process of content image through learned style tokens from the personalized diffusion model. Additionally, to ensure the content consistency throughout the style transfer process, we introduce a time-aware attention swapping technique that incorporates content information from the original image into the early denoising steps of target image generation. Beyond enabling high-quality signature style transfer across a wide range of styles, SigStyle supports multiple interesting applications, such as local style transfer, texture transfer, style fusion and style-guided text-to-image generation. Quantitative and qualitative evaluations demonstrate our approach outperforms existing style transfer methods for recognizing and transferring the signature styles. © 2025, CC BY.

关键词：

Optimization of Data Encryption Algorithms in Information Construction

学校读者我要写书评

暂无评论

Optimization of Data Encryption Algorithms in Information Co...

Distributed Systems, computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： Shuai Zhu Yi You Bo Zhou Chuanting Chen Xueqin Yi Network Information Center Hankou University Wuhan China School of Computer Science and Technology Hankou University Wuhan China Library and Information Center Wuhan University of Engineering Science Wuhan China School of Music Hankou University Wuhan China Board Office Hankou University Wuhan China

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

Data encryption algorithms play a crucial role in information construction, effectively protecting data security. The problems in traditional research include a lack of targeting, a balance between efficiency and safety, and a lack of comprehensive consideration. Therefore, this article proposed targeted optimization strategies and methods by in-depth analyzing the needs and scenarios of information construction, combined with the characteristics and problems of data encryption algorithms. Meanwhile, this article also comprehensively considered the integration, deployment, management, and maintenance of algorithms to achieve optimal matching and collaborative work between algorithms and information systems. Through research, this article aimed to promote the application and development of data encryption algorithms in information construction, and improve the efficiency, security, and availability of data encryption algorithms in protecting data security. The results showed that the efficiency of the data encryption algorithm based on RSA (Rivest-Shamir-Adleman) reached the highest of 89.6%. This article provides strong support for the application and development of data encryption algorithms, promoting the sustainable development of information construction and the protection of data security.

关键词： Protocols Data security Distributed databases Encryption Protection Sustainable development Optimal matching Optimization Standards Information systems

Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Zhiwei Fu, Kexue Duan, Minghong Qu, Linhao Wang, Shuo Song, Zhijian Academy for Engineering and Technology Fudan University China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention China Shandong Computer Science Center National Supercomputer Center in Jinan China

Attributed to the frequent coupling of co-occurring objects and the limited supervision from image-level labels, the challenging co-occurrence problem is widely present and leads to false activation of objects in weakly supervised semantic segmentation (WSSS). In this work, we devise a’Separate and Conquer’ scheme SeCo to tackle this issue from dimensions of image space and feature space. In the image space, we propose to’separate’ the co-occurring objects with image decomposition by subdividing images into patches. Importantly, we assign each patch a category tag from Class Activation Maps (CAMs), which spatially helps remove the co-context bias and guide the subsequent representation. In the feature space, we propose to’conquer’ the false activation by enhancing semantic representation with multi-granularity knowledge contrast. To this end, a dual-teacher-single-student architecture is designed and tag-guided contrast is conducted to guarantee the correctness of knowledge and further facilitate the discrepancy among co-occurring objects. We streamline the multi-staged WSSS pipeline end-to-end and tackle co-occurrence without external supervision. Extensive experiments are conducted, validating the efficiency of our method tackling co-occurrence and the superiority over previous single-staged and even multi-staged competitors on PASCAL VOC and MS COCO. Code will be available here. Copyright © 2024, The Authors. All rights reserved.

关键词： Chemical activation

Hard-Label Black-Box Attacks on 3D Point Clouds

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Daizong Tao, Yunbo Zhou, Pan Hu, Wei Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

With the maturity of depth sensors in various 3D safety-critical applications, 3D point cloud models have been shown to be vulnerable to adversarial attacks. Almost all existing 3D attackers simply follow the white-box or black-box setting to iteratively update coordinate perturbations based on back-propagated or estimated gradients. However, these methods are hard to deploy in real-world scenarios (no model details are provided) as they severely rely on parameters or output logits of victim models. To this end, we propose point cloud attacks from a more practical setting, i.e., hard-label black-box attack, in which attackers can only access the prediction label of 3D input. We introduce a novel 3D attack method based on a new spectrum-aware decision boundary algorithm to generate high-quality adversarial samples. In particular, we first construct a class-aware model decision boundary, by developing a learnable spectrum-fusion strategy to adaptively fuse point clouds of different classes in the spectral domain, aiming to craft their intermediate samples without distorting the original geometry. Then, we devise an iterative coordinate-spectrum optimization method with curvature-aware boundary search to move the intermediate sample along the decision boundary for generating adversarial point clouds with trivial perturbations. Experiments demonstrate that our attack competitively outperforms existing white/black-box attackers in terms of attack performance and adversary quality. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital elevation model

Lateralized Learning for Multi-Class Visual Classification Tasks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Siddique, Abubakar Browne, Will N. Grimshaw, Gina M. The School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand The Faculty of Engineering School of Electrical Engineering & Robotics Queensland University of Technology Brisbane4000 Australia The Cognitive the School of Psychology Victoria University of Wellington PO Box 600 Wellington6140 New Zealand

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous manner such that different parts of a "locality-sensitive hashing table" are often not connected, meaning higher-order patterns are not discovered. Hence these systems are not robust against noisy, irrelevant, and redundant data, resulting in the wrong prediction being made with high confidence. Conversely, vertebrate brains afford heterogeneous knowledge representation through lateralization, enabling modular learning at different levels of abstraction. This work aims to verify the effectiveness, scalability, and robustness of a lateralized approach to real-world problems that contain noisy, irrelevant, and redundant data. The experimental results of multi-class (200 classes) image classification show that the novel system effectively learns knowledge representation at multiple levels of abstraction making it more robust than other state-of-the-art techniques. Crucially, the novel lateralized system outperformed all the state-of-the-art deep learning-based systems for the classification of normal and adversarial images by 19.05% − 41.02% and 1.36% − 49.22%, respectively. Findings demonstrate the value of heterogeneous and lateralized learning for computer vision applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

A DEEP INVERSE-MAPPING MODEL FOR A FLAPPING ROBOTIC WING

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sharvit, Hadar Karl, Raz Beatus, Tsevi School of Computer Science and EngineerinG The Hebrew University of Jerusalem 9190401 Israel The Institute of Life ScienceS The Hebrew University of Jerusalem 9190401 Israel Center for Bioengineering The Hebrew University of Jerusalem 9190401 Israel

In systems control, the dynamics of a system are governed by modulating its inputs to achieve a desired outcome. For example, to control the thrust of a quad-copter propeller the controller modulates its rotation rate, relying on a straightforward mapping between the input rotation rate and the resulting thrust. This mapping can be inverted to determine the rotation rate needed to generate a desired thrust. However, in complex systems, such as flapping-wing robots where intricate fluid motions are involved, mapping inputs (wing kinematics) to outcomes (aerodynamic forces) is nontrivial and inverting this mapping for real-time control is computationally impractical. Here, we report a machine-learning solution1 for the inverse mapping of a flapping-wing system based on data from an experimental system we have developed. Our model learns the input wing motion required to generate a desired aerodynamic force outcome. We used a sequence-to-sequence model tailored for time-series data and augmented it with a novel adaptive-spectrum layer that implements representation learning in the frequency domain. To train our model, we developed a flapping wing system that simultaneously measures the wing’s aerodynamic force and its 3D motion using high-speed cameras. We demonstrate the performance of our system on an additional open-source dataset of a flapping wing in a different flow regime. Results show superior performance compared with more complex state-of-the-art transformer-based models, with 11% improvement on the test datasets median loss . Moreover, our model shows superior inference time, making it practical for onboard robotic control. Our open-source data and framework may improve modeling and real-time control of systems governed by complex dynamics, from biomimetic robots to biomedical devices. © 2025, CC BY.

关键词： Inverse problems

NIR-Responsive Methotrexate-Modified Iron Selenide Nanorods for Synergistic Magnetic Hyperthermic, Photothermal, and Chemodynamic Therapy

学校读者我要写书评

暂无评论

ACS Applied Materials and Interfaces 2024年第20期16卷 25622-25636页

作者： Thirumurugan, Senthilkumar Muthiah, Kayalvizhi Samuvel Lin, Yu-Chien Dhawan, Udesh Liu, Wai-Ching Wang, An-Ni Liu, Xinke Hsiao, Michael Tseng, Ching-Li Chung, Ren-Jei No. 1 Section 3 Zhongxiao East Road Taipei10608 Taiwan Centre for the Cellular Microenvironment Division of Biomedical Engineering James Watt School of Engineering Mazumdar-Shaw Advanced Research Centre University of Glasgow GlasgowG116EW United Kingdom Faculty of Science and Technology Technological and Higher Education Institute of Hong Kong Hong Kong New Territories999077 Hong Kong Scrona AG Grubenstrasse 9 Zürich8045 Switzerland College of Materials Science and Engineering Chinese Engineering and Research Institute of Microelectronics Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Genomics Research Center Academia Sinica Taipei115 Taiwan Department and Graduate Institute of Veterinary Medicine School of Veterinary Medicine National Taiwan University Taipei10617 Taiwan Graduate Institute of Biomedical Materials and Tissue Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan International Ph.D. Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Research Center of Biomedical Device College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan International Ph.D. Program in Cell Therapy and Regenerative Medicine College of Medicine Taipei Medical University Taipei11031 Taiwan Taipei10608 Taiwan

Breast cancer is a malignant tumor with a high mortality rate among women. Therefore, it is necessary to develop novel therapies to effectively treat this disease. In this study, iron selenide nanorods (FeSe2 NRs) were designed for use in magnetic hyperthermic, photothermal, and chemodynamic therapy (MHT/PTT/CDT) for breast cancer. To illustrate their efficacy, FeSe2 NRs were modified with the chemotherapeutic agent methotrexate (MTX). MTX-modified FeSe2 (FeSe2-MTX) exhibited excellent controlled drug release properties. Fe2+ released from FeSe2 NRs induced the release of •OH from H2O2 via a Fenton/Fenton-like reaction, enhancing the efficacy of CDT. Under alternating magnetic field (AMF) stimulation and 808 nm laser irradiation, FeSe2-MTX exerted potent hyperthermic and photothermal effects by suppressing tumor growth in a breast cancer nude mouse model. In addition, FeSe2 NRs can be used for magnetic resonance imaging in vivo by incorporating their superparamagnetic characteristics into a single nanomaterial. Overall, we presented a novel technique for the precise delivery of functional nanosystems to tumors that can enhance the efficacy of breast cancer treatment. © 2024 The Authors. Published by American Chemical Society

关键词： Magnetic resonance imaging

Open-Pose 3D zero-shot learning: Benchmark and challenges

学校读者我要写书评

暂无评论

Neural Networks 2025年 181卷 106775页

作者： Zhao, Weiguang Yang, Guanyu Zhang, Rui Jiang, Chenru Yang, Chaolong Yan, Yuyao Hussain, Amir Huang, Kaizhu Department of Computer Science University of Liverpool LiverpoolL69 7ZX United Kingdom Department of Foundational Mathematics Xi'an Jiaotong-Liverpool University Suzhou215123 China Department of Mechatronics and Robotics Xi'an Jiaotong-Liverpool University Suzhou215123 China School of Robotics Xi'an Jiaotong-Liverpool University Suzhou215123 China School of Computing Edinburgh Napier University EdinburghEH11 4BN United Kingdom Data Science Research Center Duke Kunshan University Kunshan215316 China

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image Pre-training (CLIP) to 3D vision have made significant progress in the 3D zero-shot classification task. These methods primarily focus on 3D object classification with an aligned pose;such a setting is, however, rather restrictive, which overlooks the recognition of 3D objects with open poses typically encountered in real-world scenarios, such as an overturned chair or a lying teddy bear. To this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation. First, we revisit the current research on 3D zero-shot classification and propose two benchmark datasets specifically designed for the open-pose setting. We empirically validate many of the most popular methods in the proposed open-pose benchmark. Our investigations reveal that most current 3D zero-shot classification models suffer from poor performance, indicating a substantial exploration room towards the new direction. Furthermore, we study a concise pipeline with an iterative angle refinement mechanism that automatically optimizes one ideal angle to classify these open-pose 3D objects. In particular, to make validation more compelling and not just limited to existing CLIP-based methods, we also pioneer the exploration of knowledge transfer based on Diffusion models. While the proposed solutions can serve as a new benchmark for open-pose 3D zero-shot classification, we discuss the complexities and challenges of this scenario that remain for further research development. The code is available publicly at https://***/weiguangzhao/Diff-OP3D © 2024

关键词： Zero-shot 3D classification Open-pose Text–image matching