检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Sadeghi, Zahra Alizadehsani, Roohallah Cifci, Mehmet Akif Kausar, Samina Rehman, Rizwan Mahanta, Priyakshi Bora, Pranjal Kumar Almasri, Ammar Alkhawaldeh, Rami S. Hussain, Sadiq Alatas, Bilal Shoeibi, Afshin Moosaei, Hossein Hladík, Milan Nahavandi, Saeid Pardalo, Panos M. Institute for Big Data Analytics Faculty of Computer Science Dalhousie University Canada Deakin University Geelong Australia The Institute of Computer Technology Tu Wien University Vienna1040 Austria University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Centre for Computer Science and Applications Dibrugarh University Assam India Department of Management Information Sys Al-Balqa Applied University Salt19117 Jordan Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Examination Branch Dibrugarh University Assam Dibrugarh India Department of Software Eng. Firat University Elazig23100 Turkey Data Science and Computational Intelligence Institute University of Granada Spain Department of Informatics Faculty of Science Jan Evangelista Purkyně University in Ústí nad Labem Czech Republic Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States Swinburne University of Technology HawthornVIC3122 Australia Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida Gainesville32611 United States

XAI refers to the techniques and methods for building AI applications which assist end users to interpret output and predictions of AI models. Black box AI applications in high-stakes decision-making situations, such as medical domain have increased the demand for transparency and explainability since wrong predictions may have severe consequences. Model explainability and interpretability are vital successful deployment of AI models in healthcare practices. AI applications' underlying reasoning needs to be transparent to clinicians in order to gain their trust. This paper presents a systematic review of XAI aspects and challenges in the healthcare domain. The primary goals of this study are to review various XAI methods, their challenges, and related machine learning models in healthcare. The methods are discussed under six categories: Features-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric methods. Most importantly, the paper explores XAI role in healthcare problems to clarify its necessity in safety-critical applications. The paper intends to establish a comprehensive understanding of XAI-related applications in the healthcare field by reviewing the related experimental results. To facilitate future research for filling research gaps, the importance of XAI models from different viewpoints and their limitations are investigated. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Loss Decomposition and Centroid Estimation for Positive and Unlabeled Learning

引用

IEEE transactions on pattern analysis and machine intelligence 2021年第3期43卷 918-932页

作者： Chen Gong Hong Shi Tongliang Liu Chuang Zhang Jian Yang Dacheng Tao PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing P.R. China PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security the School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing P.R. China UBTECH Sydney Artificial Intelligence Centre School of Computer Science Faculty of Engineering University of Sydney Darlington NSW Australia

This paper studies Positive and Unlabeled learning (PU learning), of which the target is to build a binary classifier where only positive data and unlabeled data are available for classifier training. To deal with the absence of negative training data, we first regard all unlabeled data as negative examples with false negative labels, and then convert PU learning into the risk minimization problem in the presence of such one-side label noise. Specifically, we propose a novel PU learning algorithm dubbed "Loss Decomposition and Centroid Estimation" (LDCE). By decomposing the loss function of corrupted negative examples into two parts, we show that only the second part is affected by the noisy labels. Thereby, we may estimate the centroid of corrupted negative set via an unbiased way to reduce the adverse impact of such label noise. Furthermore, we propose the "Kernelized LDCE" (KLDCE) by introducing the kernel trick, and show that KLDCE can be easily solved by combining Alternative Convex Search (ACS) and Sequential Minimal Optimization (SMO). Theoretically, we derive the generalization error bound which suggests that the generalization risk of our model converges to the empirical risk with the order of O(1/√k+1/√{n-k}+1/√n) ( n and k are the amounts of training data and positive data correspondingly). Experimentally, we conduct intensive experiments on synthetic dataset, UCI benchmark datasets and real-world datasets, and the results demonstrate that our approaches (LDCE and KLDCE) achieve the top-level performance when compared with both classic and state-of-the-art PU learning methods.

关键词： Learning artificial intelligence Minimisation Pattern Classification Positive data KLDCE Loss Decomposition Centroid Estimation Positive Learning Unlabeled Learning Binary Classifier Unlabeled data Classifier Training Negative Training data False Negative Labels Risk Minimization Problem PU Learning Algorithm Loss Function Corrupted Negative Examples Noisy Labels Corrupted Negative Set Generalization Risk Empirical Risk Kernelized LDCE One Side Label Noise Alternative Convex Search ACS Sequential Minimal Optimization SMO Generalization Error Bound Estimation Training Supervised Learning Noise Measurement Analytical Models Risk Management Kernel PU Learning Loss Decomposition Centroid Estimation Kernel Extension Generalization Bound

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Stego: Training-free diffusion generative steganography via message projection

引用

Information sciences 2025年 718卷

作者： Daegyu Kim Chaehun Shin Jooyoung Choi Dahuin Jung Sungroh Yoon Data Science and AI Laboratory Electrical and Computer Engineering Seoul National University Seoul 08826 Republic of Korea School of Computer Science and Engineering Soongsil University Seoul 06978 Republic of Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul 08826 Republic of Korea AIIS ASRI INMC and ISRC Seoul National University Seoul 08826 Republic of Korea

Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection ability over cover images. However, they create relatively unrealistic stego images because of the inherent limitations of generative models. We propose Diffusion-Stego, a generative steganography approach based on diffusion models that outperform other generative models in image generation. Diffusion-Stego projects secret messages into the latent noise of diffusion models and generates stego images with an iterative denoising process. Since the naive hiding of secret messages into noise boosts visual degradation and decreases extracted message accuracy, we introduce message projection, which hides messages into noise space while addressing these issues. We suggest three options for message projection to adjust the trade-off between extracted message accuracy, anti-detection ability, and image quality. Diffusion-Stego is a training-free approach, so we can apply it to pre-trained diffusion models that generate high-quality images, or even large-scale text-to-image models, such as Stable diffusion. Diffusion-Stego achieved a high capacity of messages as well as high quality that makes it challenging to distinguish from real images in the PNG format.

关键词： Diffusion models Generative models Generative steganography

来源：评论

学校读者我要写书评

暂无评论

Explainable, Domain-Adaptive, and Federated artificial intelligence in Medicine

arXiv

引用

arXiv 2022年

作者： Chaddad, Ahmad Lu, Qizong Li, Jiali Katib, Yousef Kateb, Reem Tanougast, Camel Bouridane, Ahmed Abdulkadir, Ahmed The School of Artificial Intelligence Guilin Universiy of Electronic Technology China The Laboratory for Imagery Vision and Artificial Intelligence Ecole de Technologie Superieure Montreal Canada The College of Medicine Taibah University Madinah Saudi Arabia College of Computer Science and Engineering Taibah University Madinah Saudi Arabia The Laboratory of Design Optimization and Modeling Systems University of Lorraine Metz France University of Sharjah United Arab Emirates The Laboratoire de Recherche en Neuroimagerie Centre Hospitalier Universitaire Vaudois Lausanne Switzerland

artificial intelligence (AI) continues to transform data analysis in many domains. Progress in each domain is driven by a growing body of annotated data, increased computational resources, and technological innovations. In medicine, the sensitivity of the data, the complexity of the tasks, the potentially high stakes, and a requirement of accountability give rise to a particular set of challenges. In this review, we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making. (1) Explainable AI aims to produce a human-interpretable justification for each output. Such models increase confidence if the results appear plausible and match the clinicians expectations. However, the absence of a plausible explanation does not imply an inaccurate model. Especially in highly non-linear, complex models that are tuned to maximize accuracy, such interpretable representations only reflect a small portion of the justification. (2) Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains. For example, a classification task based on images acquired on different acquisition hardware. (3) Federated learning enables learning large-scale models without exposing sensitive personal health information. Unlike centralized AI learning, where the centralized learning machine has access to the entire training data, the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates, not personal health data. This narrative review covers the basic concepts, highlights relevant corner-stone and state-of-the-art research in the field, and discusses perspectives. © 2022, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal

arXiv

引用

arXiv 2025年

作者： Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China Afirstsoft Shenzhen China GuangDong Province Key Laboratory of Information Security Technology China

Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling and Detecting Communities in Node Attributed Networks

arXiv

引用

arXiv 2021年

作者： Ren, Ren Shao, Jinliang Bishop, Adrian N. Zheng, Wei Xing School of Automation Engineering University of Electronic Science and Technology of China 611731 China The Research Center on Crowd Spectrum Intelligence Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518054 China Australia Canberra Research Lab Australia The School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW2751 Australia

As a fundamental structure in real-world networks, in addition to graph topology, communities can also be reflected by abundant node attributes. In attributed community detection, probabilistic generative models (PGMs) have become the mainstream method due to their principled characterization and competitive performances. Here, we propose a novel PGM without imposing any distributional assumptions on attributes, which is superior to the existing PGMs that require attributes to be categorical or Gaussian distributed. Based on the block model of graph structure, our model incorporates the attribute by describing its effect on node popularity. To characterize the effect quantitatively, we analyze the community detectability for our model and then establish the requirements of the node popularity term. This leads to a new scheme for the crucial model selection problem in choosing and solving attributed community detection models. With the model determined, an efficient algorithm is developed to estimate the parameters and to infer the communities. The proposed method is validated from two aspects. First, the effectiveness of our algorithm is theoretically guaranteed by the detectability condition. Second, extensive experiments indicate that our method not only outperforms the competing approaches on the employed datasets, but also shows better applicability to networks with various node attributes. © 2021, CC BY.

关键词： Population dynamics

来源：评论

学校读者我要写书评

暂无评论

eFAirWrite: Bringing energy efficient text entry to next generation smart devices

引用

Expert Systems with Applications 2025年 289卷

作者： Muhammad Mohsin Ghaffar Ahmad Abdullah Junaid Younas Vladimir Rybalkin Jonas Ney Paul Lukowicz Norbert Wehn Microelectronic Systems Design Research Group University of Kaiserslautern-Landau Kaiserslautern 67663 Germany School of Electrical Engineering & Computer Science National University of Sciences & Technology Islamabad 44000 Pakistan German Research Centre for Artificial Intelligence Kaiserslautern 67663 Germany

Text entry tasks for emerging wireless Augmented Reality (AR) and Virtual Reality (VR) devices can be realized in many ways, one of the most promising methods is based on an Inertial Measurement Unit (IMU) sensor, which resembles a human writing style and is called air-writing. An existing air-writing Deep Neural Network (DNN) based algorithm called FAirWrite achieves state-of-the-art accuracy. However, this algorithm is optimized only for accuracy without considering the implementation constraints. State-of-the-art implementation executes the algorithm in a cloud, which is associated with large communication latency; privacy issues with respect to data transfer; and a need for reliable internet connection. A solution that tackles all three challenges is executing the algorithm locally at the edge in the closest proximity to the sensor. However, inference at the edge is challenging due to limited memory and computing resources, which can impact accuracy and increase latency. Additionally, battery-powered edge devices must adhere to strict power and energy consumption limits. All these constraints collectively restrict the model size and computational complexity that can be deployed near the sensor. In this work, we explore various optimizations required to enable state-of-the-art FAirWrite algorithm for a real-world deployment scenario, i.e. executing on an edge device. We perform a multi-layer design-space exploration considering multiple levels of design hierarchy spanning from optimizations applied on algorithmic level down to hardware level, considering various deployment run-times and edge platforms including embedded micro-controller, embedded Central Processing Unit (CPU), embedded Graphics Processing Unit (GPU), Neural Processing Unit (NPU), and Field-Programmable Gate Array (FPGA). The complexity reduction optimizations result in a 37 × smaller eFAirWrite model without any accuracy degradation. We propose and implement a custom hardware architecture of the

关键词： Human computer interaction Air-writing Convolution neural network inference Edge computing Energy efficient acceleration

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution with an enhanced group convolutional neural network

arXiv

引用

arXiv 2022年

作者： Tian, Chunwei Yuan, Yixuan Zhang, Shichao Lin, Chia-Wen Zuo, Wangmeng Zhang, David School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China Department of Electrical Engineering City University of Hong Kong Hong Kong School of Computer Science and Engineering Central South University Hunan Changsha410083 China Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in general. In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR). Also, a signal enhancement operation in the ESRGCNN is useful to inherit more long-distance contextual information for resolving long-term dependency. An adaptive up-sampling operation is gathered into a CNN to obtain an image super-resolution model with low-resolution images of different sizes. Extensive experiments report that our ESRGCNN surpasses the state-of-the-arts in terms of SISR performance, complexity, execution speed, image quality evaluation and visual effect in SISR. Code is found at https://***/hellloxiaotian/ESRGCNN. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Improved Fitness Dependent Optimizer for Solving Economic Load Dispatch Problem

arXiv

引用

arXiv 2022年

作者： Tahir, Barzan Hussein Rashid, Tarik A. Rauf, Hafiz Tayyab Bacanin, Nebojsa Chhabra, Amit Vimal, S. Yaseen, Zaher Mundher Department of Computer Science and Engineering University of Kurdistan Helwer Erbil Iraq Centre for Smart Systems AI and Cybersecurity Staffordshire University Stoke-on-Trent United Kingdom Singidunum University Danijelova 32 Belgrade11000 Serbia Department of Computer Engineering and Technology Guru Nanak Dev University Amritsar India Department of Artificial Intelligence and Data Science Ramco Institute of Technology North Venganallur Village Virudhunagar District Tamilnadu Rajapalayam626 117 India Department of Earth Sciences and Environment Faculty of Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia USQ's Advanced Data Analytics Research Group School of Mathematics Physics and Computing University of Southern Queensland QLD4350 Australia New era and Development in Civil Engineering Research Group Scientific Research Center Al-Ayen University Thi-Qar64001 Iraq

Economic Load Dispatch depicts a fundamental role in the operation of power systems, as it decreases the environmental load, minimizes the operating cost, and preserves energy resources. The optimal solution to Economic Load Dispatch problems and various constraints can be obtained by evolving several evolutionary and swarm-based algorithms. The major drawback to swarm-based algorithms is premature convergence towards an optimal solution. Fitness Dependent Optimizer is a novel optimization algorithm stimulated by the decision-making and reproductive process of bee swarming. Fitness Dependent Optimizer (FDO) examines the search spaces based on the searching approach of Particle Swarm Optimization. To calculate the pace, the fitness function is utilized to generate weights that direct the search agents in the phases of exploitation and exploration. In this research, the authors have carried out Fitness Dependent Optimizer to solve the Economic Load Dispatch problem by reducing fuel cost, emission allocation, and transmission loss. Moreover, the authors have enhanced a novel variant of Fitness Dependent Optimizer, which incorporates novel population initialization techniques and dynamically employed sine maps to select the weight factor for Fitness Dependent Optimizer. The enhanced population initialization approach incorporates a quasi-random Sabol sequence to generate the initial solution in the multi-dimensional search space. A standard 24-unit system is employed for experimental evaluation with different power demands. Empirical results obtained using the enhanced variant of the Fitness Dependent Optimizer demonstrate superior performance in terms of low transmission loss, low fuel cost, and low emission allocation compared to the conventional Fitness Dependent Optimizer. The experimental study obtained 7.94E-12, the lowest transmission loss using the enhanced Fitness Dependent Optimizer. Correspondingly, various standard estimations are used to prove the stability

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Unsupervised hashing with contrastive information bottleneck

arXiv

引用

arXiv 2021年

作者： Qiu, Zexuan Su, Qinliang Ou, Zijing Yu, Jianxing Chen, Changyou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China CSE Department SUNY at Buffalo Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines. © 2021, CC BY.

关键词： Semantics

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：