检索结果-内蒙古大学图书馆

Medical Imaging 2025: Digital and Computational Pathology

作者： Kopriva, Ivica Dion-Bertrand, Laura-Isabelle Pačić, Arijana Periša, Marija Milković Hadžija, Marijana Popović Hadžija, Mirko Sitnik, Dario Division of Computing and Data Science Ruđer Bošković Institute Bijenička cesta 54 P.O. Box 180 Zagreb10002 Croatia Department of Physics University of Montreal MontrealQCH2V OB3 Canada Department of Pathology and Cytology Clinical Hospital Dubrava Avenija Gojka Šuška 6 Zagreb10000 Croatia Clinical Hospital Center Zagreb Kišpatićeva 12 Zagreb10000 Croatia Institute of pathology School of Medicine University of Zagreb Šalata 3 Zagreb10000 Croatia Division of Molecular Medicine Ruđer Bošković Institute Bijenička cesta 54 Zagreb10000 Croatia School of Computation Information and Technology Technical University Munich Munich Germany

ISBN: (纸本)9781510686045

Hyperspectral imaging (HSI) is a spatial-spectral modality with significant potential in disease diagnosis and surgical cancer resection. In this case study, we explore the use of two-mode (bright field-BF and dark field-DF) HSI for pixel-wise classification of adenocarcinoma of the colon in the liver, utilizing two co-registered pairs of HSIs from hematoxylin and eosin stained histopathological specimens. They were collected from two patients during intraoperative frozen section analysis. We trained a two-layer perceptron on one pair of concatenated BF and DF HSIs and used it to classify concatenated HSIs of another pair, and vice versa. We then compared the performance against the corresponding bright field HSI as a baseline. The pixel-wise ground truth was established through a majority vote from annotations provided by two pathologists and one medical expert. After twenty evaluations, achieved balanced accuracy and F1 score were: 74.06% ± 3.73% and 63.43% ± 3.80% for two-mode HSIs, and 71.36% ± 3.74% and 62.30% ± 10.82% for bright field HSI. Statistically significant improvement in balanced accuracy with a p value of 0.009 was performed by a two-sample t-test, after the samples passed the Shapiro-Wilk test for normality, and with a p value of 0.022 by a Wilcoxon sum-rank test. While definitive conclusions cannot be made based on results from only two pairs of HSIs from two patients, these findings justify the design and conduction of a more comprehensive study based on co-registered pairs of BF and DF hyperspectral images. © 2025 SPIE.

关键词： Fractography

来源：评论

学校读者我要写书评

暂无评论

ConBERT-RL: A policy-driven deep reinforcement learning based approach for detecting homophobia and transphobia in low-resource languages

Natural Language Processing Journal

引用

Natural Language Processing Journal 2024年 6卷

作者： Vivek Suresh Raj Chinnaudayar Navaneethakrishnan Subalalitha Lavanya Sambath Frank Glavin Bharathi Raja Chakravarthi University of Calgary Calgary Alberta Canada Department of Computing Technologies SRM Institute of Science and Technology Chennai India Department of Information Technology Madras Institute of Technology Chennai India Insight SFI Research Centre for Data Analytics School of Computer Science University of Galway Galway Ireland School of Computer Science University of Galway Galway Ireland

In this work, we present a novel framework for discriminatory comment classification in targeted low-resource languages thereby enabling identification of discriminatory comments for promoting safer online environment in linguistically diverse contexts. Recently proposed literatures with Bidirectional Encoder Representations from Transformers (BERT) and its variants, have produced promising results, particularly in the case of transliterated Tamil words in English. Such approaches are seen as transfer learning and fine-tuning between a general environment and targeted downstream task. However, for an effective transfer of knowledge, from a source task to a targeted task, their feature space has to be correlated (similarity measure as metric, to measure knowledge transfer), which is unexplored in the previous literature works. In practice, such similarity conditions are often violated. We propose a Con catenated representation, powered with BERT in R einforcement L earning (RL) - ConBERT-RL framework, to capture problem-specific features, as well as to understand nuances in case of transliterated Tamil words into English, to make decision in classifying discriminatory comments. ConBERT-RL incorporates a fusion of learned hidden-state representation from our pre-trained Classifier-Model (CM), along with the broader contextualized representation (pooled output) from BERT. The key idea is to utilize this concatenated representation to drive our policy network for hate comment classification. To effectively learn such a policy, we use the REINFORCE algorithm in a reinforcement learning setting, to guide our ConBERT-RL agent, in making informative decisions. To demonstrate the general aspects of ConBERT-RL, we conduct experiments for offensive comment classification on transliterated Tamil words in English dataset. ConBERT-RL obtains results, where it significantly improved the score of micro average accuracy with 90% ( ≈ 1 . 0 % absolute improvement over BERT+FC), 93% (

关键词： Deep reinforcement learning Low resourced language Homophobia detection Transphobia detection

来源：评论

学校读者我要写书评

暂无评论

Neural Brain: A Neuroscience-inspired Framework for Embodied Agents

arXiv

引用

arXiv 2025年

作者： Liu, Jian Shi, Xiongtao Nguyen, Thai Duy Zhang, Haitian Zhang, Tianxiang Sun, Wei Li, Yanjie Vasilakos, Athanasios V. Iacca, Giovanni Khan, Arshad Ali Kumar, Arvind Cho, Jae Won Mian, Ajmal Xie, Lihua Cambria, Erik Wang, Lin School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Robotics Hunan University China School of Intelligence Science and Engineering Harbin Institute of Technology Shenzhen China Department of Information and Communication Technology University of Agder Norway Department of Information Engineering and Computer Science University of Trento Italy Elm Company London United Kingdom Division of Computational Science and Technology KTH Royal Institute of Technology Sweden School of Artificial Intelligence and Data Science Sejong University Korea Republic of Department of Computer Science the University of Western Australia Australia College of Computing and Data Science Nanyang Technological University Singapore

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios. Our project page is at Neural-Brain-for-Embodied-Agents. Copyright © 2025, The Authors. All rights reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

DeepKAF: A Heterogeneous CBR Deep Learning Approach for NLP Prototyping

DeepKAF: A Heterogeneous CBR Deep Learning Approach for NLP ...

引用

2020 International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2020

作者： Amin, Kareem Kapetanakis, Stelios Polatidis, Nikolaos Althoff, Klaus-Dieter Dengel, Andreas Smart Data and Knowledge Services German Research Center for Artificial Intelligence Technische Universität Kaiserslautern Kaiserslautern Germany School of Computing Engineering and Mathematics University of Brighton Brighton United Kingdom Intelligent Information Systems Lab Institute of Computer Science University of Hildesheim Hildesheim Germany

ISBN: (纸本)9781728167992

With widespread modernization, digitization and transformations of most of industries, Artificial Intelligence (AI) has become the key enabler in that modernization journey. AI offers substantial capabilities to solve new problems and optimise existing solutions specialising on specific problems and learning from different domains. AI solutions can be either explainable or black box ones with the latter being urged to improve since they cannot trust. Case-based Reasoning (CBR) is an explainable AI approach where solutions are provided along with relevant explanations in terms of why a solution was selected. However, CBR, like most other explainable approaches, has several limitations in terms of scalability, large data volumes, domain complexity, that reduce its ability to scale any CBR system in industrial applications. In this paper, we provide a heterogeneous CBR framework - DeepKAF where we combine CBR paradigm with Deep Learning architectures to solve complicated Natural Language Processing (NLP) problems (eg. mixed language and grammatically incorrect text).DeepKAF is built based on continuous research in the area of Deep Learning and CBR. DeepKAF has been implemented and used across different domains, test use cases and research models as an ensemble deep learning and CBR Architecture. © 2020 IEEE.

关键词： Case based reasoning

来源：评论

学校读者我要写书评

暂无评论

FedPHE: A Secure and Efficient Federated Learning via Packed Homomorphic Encryption

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Li, Yuqing Yan, Nan Chen, Jing Wang, Xiong Hong, Jianan He, Kun Wang, Wei Li, Bo Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Wuhan University RiZhao Information Technology Institute Rizhao276800 China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China Shanghai Jiao Tong University School of Cyber Science and Engineering Shanghai200240 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE assumes all clients share a single private key, making the system vulnerable to security threats of ciphertexts being intercepted and decrypted by honest-but-curious clients. Also, it does not consider the heterogeneity among different clients, resulting in undermined training efficiency with slow convergence and stragglers. To address these challenges, we propose FedPHE, a secure and efficient FL framework with PHE by jointly exploiting contribution-aware secure aggregation and straggler-resistant client selection. Using CKKS with sparsification and blinding, FedPHE achieves efficient secure aggregation that allows clients to only provide obscured encrypted updates while the server can perform aggregation by accounting for contributions of local updates. To mitigate the straggler effect, we devise a perturbed sketch-based selection to cherry-pick representative clients with heterogeneous models and computing capabilities in a communication-efficient and privacy-preserving manner. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients' privacy, achieve 2.45-6.56× training speedup, cut the communication overhead by 1.32-24.85×, and reduce straggler effects by 1.89-2.78×. © 2004-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

BayesDose: Comprehensive proton dose prediction with model uncertainty using Bayesian LSTMs

arXiv

引用

arXiv 2023年

作者： Voss, Luke Neishabouri, Ahmad Ortkamp, Tim Mairani, Andrea Wahl, Niklas Department of Medical Physics in Radiation Oncology German Cancer Research Center – DKFZ Im Neuenheimer Feld 280 Heidelberg69120 Germany Heidelberg Institute for Radiation Oncology – HIRO Im Neuenheimer Feld 280 Heidelberg69120 Germany Ruprecht Karl University of Heidelberg Institute of Computer Science Heidelberg Germany Clinical Cooperation Unit Radiation Oncology German Cancer Research Center – DKFZ Heidelberg Germany Steinbuch Centre for Computing Karlsruhe Germany Heidelberg Germany HIDSS4Health – Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Im Neuenheimer Feld 450 HeidelbergD-69120 Germany

Purpose: Fast dose calculation techniques are needed in proton therapy, particularly in light of time restrictions in adaptive workflows. Neural network models show the potential to substitute conventional dose calculation algorithms with fast and accurate dose predictions, while lacking measures to quantify an individual prediction’s quality. We propose to use a Bayesian approach to learn uncertainty of AI-based dose prediction. Methods: Our resulting BayesDose-Framework is based on a previously published deterministic LSTM. Similarly, it is trained and evaluated on Monte Carlo beamlet doses simulated on (1) 2500 water phantoms with slab inserts and (2) 1000 geometries extracted from a lung patient for a single initial energy. The network’s weights are parameterized with 2D Gaussian mixture models, and 100 ensemble predictions are used to quantify mean dose predictions and their standard deviation. Generalizability as well as re-training of the model is evaluated on smaller datasets with two different initial energies as well as five additional patients. Results: The averaged predictions of the BayesDose model performed similarly to its deterministic variant and at least as good the original published long short-term memory (LSTM) model. Predictions of the uncertainty (measured through the sampled predictions’ standard deviation) seemed conservative, particularly for the phantom dataset, however regions of high uncertainty correlated spatially with the largest dose differences between the prediction and Monte Carlo calculated reference. Large average uncertainty within a prediction correlates strongly with dosimetric differences (up to ρ = −0.74). This correlation is reduced when applying the model to patient data with unseen HU value ranges. Runtime overhead could be decreased to 9x of a deterministic prediction for an ensemble size of 100 by parallelizing predictions and presampling network weights. Conclusion: Bayesian models for dose prediction can produce fast

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Nondestructive Chicken Egg Fertility Detection Using CNN-Transfer Learning Algorithms

arXiv

引用

arXiv 2023年

作者： Saifullah, Shoffan Drezewski, Rafal Yudhana, Anton Pranolo, Andri Kaswijanti, Wilis Suryotomo, Andiko Putro Putra, Seno Aji Khaliduzzaman, Alin Prabuwono, Anton Satria Japkowicz, Nathalie Institute of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Center of Knowledge Engineering and Data Science Department of Electrical Engineering and Informatics Universitas Negeri Malang Malang65145 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia College of Computer and Information Hohai University Nanjing211100 China Department of Informatics Faculty of Industrial Technology Universitas Ahmad Dahlan Yogyakarta55166 Indonesia Faculty of Agricultural Engineering and Technology Sylhet Agricultural University Sylhet3100 Bangladesh Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science American University WashingtonDC20016 United States

This study explored the application of CNN-Transfer Learning for nondestructive chicken egg fertility detection for precise poultry hatchery practices. Four models, VGG16, ResNet50, InceptionNet, and MobileNet, were trained and evaluated on a dataset (200 single egg images) using augmented images (rotation, flip, scale, translation, and reflection). The training results demonstrated that all models achieved high accuracy, indicating their ability to learn and classify chicken eggs’ fertility. However, variations in accuracy and performance were observed when these models were evaluated on the testing datasets. The InceptionNet exhibited the best overall performance, accurately classifying fertile and non-fertile eggs. It demonstrated excellent performance in all parameters of the evaluation metrics for both training and testing datasets. When evaluated on the testing datasets, it achieved an accuracy of 0.98, a sensitivity of 1 for detecting fertile eggs, and a specificity of 0.96 for identifying non-fertile eggs. The higher performance is attributed to its unique architecture, efficiently capturing features at different scales, which leads to improved accuracy and robustness. Further optimization and fine-tuning of the models might be necessary to address the limitations in accurately detecting fertile and non-fertile eggs using other models. This study highlighted the potential of CNN-transfer learning for nondestructive fertility detection and emphasized the need for further research to enhance the models’ capabilities and to ensure accurate *** Codes CS-Class: 68T07, 68T45, 68U10, ICT-Class: 94A08 © 2023, CC BY-SA.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Nie, Lang Lin, Chunyu Liao, Kang Zhang, Yun Liu, Shuaicheng Zhao, Yao Beijing Jiaotong University Institute of Information Science Beijing100044 China Visual Intelligence +X International Cooperation Joint Laboratory of MOE Beijing100044 China Nanyang Technological University School of Computing and Data Science Singapore Communication University of Zhejiang School of Media Engineering Hangzhou310018 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China

We retarget video stitching to an emerging issue, named warping shake, which unveils the temporal content shakes induced by sequentially unsmooth warps when extending image stitching to video stitching. Even if the input videos are stable, the stitched video can inevitably cause undesired warping shakes and affect the visual experience. To address this issue, we propose StabStitch++, a novel video stitching framework to realize spatial stitching and temporal stabilization with unsupervised learning simultaneously. First, different from existing learning-based image stitching solutions that typically warp one image to align with another, we suppose a virtual midplane between original image planes and project them onto it. Concretely, we design a differentiable bidirectional decomposition module to disentangle the homography transformation and incorporate it into our spatial warp, evenly spreading alignment burdens and projective distortions across two views. Then, inspired by camera paths in video stabilization, we derive the mathematical expression of stitching trajectories in video stitching by elaborately integrating spatial and temporal warps. Finally, a warp smoothing model is presented to produce stable stitched videos with a hybrid loss to simultaneously encourage content alignment, trajectory smoothness, and online collaboration. Compared with StabStitch that sacrifices alignment for stabilization, StabStitch++ makes no compromise and optimizes both of them simultaneously, especially in the online mode. To establish an evaluation benchmark and train the learning framework, we build a video stitching dataset with a rich diversity in camera motions and scenes. Experiments exhibit that StabStitch++ surpasses current solutions in stitching performance, robustness, and efficiency, offering compelling advancements in this field by building a real-time online video stitching system. © 1979-2012 IEEE.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

Multi-label Contrastive Focal Loss for Pedestrian Attribute Recognition

Multi-label Contrastive Focal Loss for Pedestrian Attribute ...

引用

International Conference on Pattern Recognition

作者： Xiaoqiang Zheng Zhenxia Yu Lin Chen Fan Zhu Shilong Wang Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China School of computer science Chengdu University Of Information Technology Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Pedestrian Attribute Recognition (PAR) has received extensive attention during the past few years. With the advances of deep convolutional neural networks (CNNs), the performance of PAR has been significantly improved. Existing methods tend to acquire attribute-specific features by designing various complex network structures with additional modules. Such additional modules, however, dramatically increase the number of network parameters. Meanwhile, the problems of class imbalance and hard attribute retrieving remain underestimated in PAR. In this paper, we explore the optimization mechanism of the training processing to account for these problems and propose a new loss function called Multi-label Contrastive Focal Loss (MCFL). This proposed MCFL emphasizes the hard and minority attributes by using a separated re-weighting mechanism for different positive and negative classes to alleviate the impact of the imbalance. MCFL is also able to enlarge the gaps between the intra-class of multi-label attributes, to force CNNs to extract more subtle discriminative features. We evaluate the proposed MCFL on three large public pedestrian datasets, including RAP, PA-100K, and PETA. The experimental results indicate that the proposed MCFL with the ResNet-50 backbone is able to outperform other state-of-the-art approaches in term of mean accuracy.

关键词： Training Visualization Force Complex networks Feature extraction Pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Comparison of Collaborative Filtering Technology for Product Suggestions in E-Commerce

Design and Comparison of Collaborative Filtering Technology ...

引用

Automation, computing and Renewable Systems (ICACRS), International Conference on

作者： P. Rajasekar B. Mohanraj S. N. Padhi N. Sivakumar Lavanya J Charles Prabu V Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Information Technology Karpagam College of Engineering Coimbatore Tamil Nadu India Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering Panimalar Engineering College Chennai City Campus Chennai Tamil Nadu India Department of Fashion Designing SRM Institute of Science and Technology CSH Kattankulathur Campus Chennai Tamil Nadu India Department of Computer Science Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (纸本)9781665460859

E-commerce websites and internet purchasing have never been more necessary. Product recommendations are a key tactic employed by online buying platforms. This study compares two different filtering algorithms that are used in product recommendationson websites like Amazon and Flipkart. Reviews of electrical devices, user data, and timestamps were all gathered from Kaggle and put into a dataset. These specifics then undergo several preprocessing steps. The steps are data visualization, duplicate value analysis, missing value analysis, and datatype analysis. The exhibited data is then used to train and test the machine learning models. For this purpose, two machine learning models are developed using two different algorithms. The algorithms K-Nearest Neighbor(KNN) and Support Vector Decomposition (SVD) are employed. The models are then trained to acquire used in the prediction procedure after that. The best models for the prediction process are then determined by scrutinizing the results of both models. The Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) values are located and compared because the findings of the analysis weren't *** erroneous data are plotted into a graph and evaluated to further demonstrate the point. As the SVD method is discovered to be the best of the group, the algorithm's greatest and worst predictions are discovered and examined. Even the poorest model constructed for the study's predictions turned out to be superior to several other prediction algorithms used for product suggestions. This algorithm can be deployed into the backend of any e-commerce website making it more effective.

关键词： Training Support vector machines Analytical models Machine learning algorithms data visualization Machine learning Predictive models

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：