检索结果-内蒙古大学图书馆

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Xi’an710049 China Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China Peking University School of Computer Science Beijing100871 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University Xi'an710049 China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports 3.12x more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Enhancing data security through an integrated approach of multiple key cryptography and steganography in the wavelet domain 4th

Enhancing data security through an integrated approach of mu...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Hashem, Al-Fariji Ahmed Hussein Medvedeva, Marina A. Agbozo, Ebenezer Department of Big Data Analytics and Methods of Video Analysis Ural Federal University Ekaterinburg Russia

ISBN: (纸本)9781032911571

The quantity of data that may be incorporated and the picture quality must be compromised in order to embed data within an image. As a direct result of this increased distortion, the quality of the stego picture that is generated when more data is hidden within a carrier image will decrease. One thing may be taken into consideration is the difficulty of optimizing the process of embedding a substantial amount of data into an image. This article aims to provide an overview of the many methods of picture steganography and to present the several attempts that have been made to achieve image steganography via the use of deep learning and machine learning techniques. This work concluded with several potential directions for future photo steganographic-based deep learning research, and it indicated that these new directions may be investigated soon. The suggested approach ensures that even comparable letters are encrypted differently by encrypting data using a series of pseudorandom keys created from a single 16-bit seed. By using this strategy, the communication is not only more hidden but also safer against attempts at unauthorized decryption. After encryption, matrix encoding, which is made feasible by discrete wavelet transformation, embeds the encrypted data into the high-frequency sub-band of a cover image. The robust Peak Signal-to-Noise Ratio (PSNR) readings, which often exceed the 40 dB threshold, attest to the cover picture’s preservation as a result of this steganographic technique. These PSNR values, which exhibit relatively minimal optical distortion, will make the stego-image unnoticeable. In tests of performance, the proposed method demonstrated excellent imper-ceptibility, with PSNR values continuously over 46 dB and a low Bit Error Rate (BER) of around 3%, indicating a high degree of fidelity in the recovered data. © 2025 the Author(s).

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Regression Estimator of Multivariable Truncated Spline For Categorical data

引用

IAENG International Journal of Applied Mathematics 2025年第5期55卷 1357-1368页

作者： Suriaslan, Afiqah Saffa Budiantara, I Nyoman Ratnasari, Vita Statistics Department Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Statistics Department Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia

Recent years have witnessed significant interest in truncated spline estimators for nonparametric regression with quantitative data. However, the applicability of these estimators is limited by the frequent occurrence of categorical response variables in real-world applications. A paucity of nonparametric estimators exists for handling categorical response data. This necessitates a method capable of modeling relationships between variables exhibiting pattern shifts across sub-intervals with categorical outcomes. This article thus introduces a novel multivariate truncated spline nonparametric regression estimator for categorical data, developed through a synthesis of literature and theoretical research. The developed method was applied to Indonesia's 2023 poverty depth index data and East Java's 2020 gender development index data. A comparative analysis of the Truncated Spline nonparametric regression model and the binary logistic regression model for estimating categorical data revealed that the Truncated Spline approach yielded superior estimations. Some of the highlights of the proposed method are: 1) This study employs truncated spline nonparametric regression to model categorical response data, 2) Optimal knot placement is determined using the Akaike Information Criterion (AIC), 3) The method's overall performance is demonstrated through its application to two established datasets, and 4) This study compares truncated spline nonparametric regression and logistic regression. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

A novel method based on hybrid deep learning with explainability for olive fruit pest forecasting

引用

Neural Computing and Applications 2025年第5期37卷 3245-3264页

作者： Chacón-Maldonado, A.M. Melgar-García, L. Asencio-Cortés, G. Troncoso, A. Data Science and Big Data Lab Pablo de Olavide University SevilleES-41013 Spain Department of Artificial Intelligence Polytechnic University of Madrid MadridES-28660 Spain

Predicting the occurrence of crop pests is becoming a crucial task in modern agriculture to facilitate farmers’ decision-making. One of the most significant pests is the olive fruit fly, a public concern because it causes damage that compromises oil quality, increasing acidity and altering its flavor. This paper proposes a hybrid deep learning model to predict the presence of olive flies in crops. This model is based on an autoencoder and an automated deep feed-forward neural network. First, the autoencoder neural network learns a representation of the data and then the automated deep feed-forward neural network automatically determines the best values for the hyperparameters in order to obtain the prediction of the number of flies caught in traps from the dataset generated by the autoencoder. On the other hand, farmers to trust the proposed deep learning models need these models to be explainable. Thus, explainable artificial intelligence techniques are applied to the produced models to interpret the results. Results using a dataset from different sources such as satellite image band data, vegetation indices, and meteorological variables are reported. The performance of the proposed model has been compared with classical benchmark algorithms and a deep learning model recently published in the literature. In addition, the comparison includes the automated deep feed-forward neural network individually to show how the autoencoder network improves the accuracy of predictions. © The Author(s) 2024.

关键词： Agriculture Deep learning Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

引用

Computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan Md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：评论

学校读者我要写书评

暂无评论

GMFLDA: Improved prediction of IncRNA-disease association via graph convolutional network

引用

IEEE Access 2025年 13卷 85330-85341页

作者： Kim, Kwangsu Ha, Jihwan Pukyong National University Department of Scientific Computing Busan48513 Korea Republic of Pukyong National University Major of Big Data Convergence Division of Data Information Science Busan48513 Korea Republic of

The rapid expansion of diverse networks has created a growing need to integrate multiple heterogeneous structures to effectively capture both inter- and intra-entity relationships. This integration helps preserve the intrinsic meaning of complex biological interactions. Network-based approaches have been highly effective in predicting node labels and uncovering hidden associations between entities. These methods have been widely applied in areas such as user-item recommendations, gene-gene interactions, and lncRNA-disease association prediction. In this study, we present GMFLDA, an advanced machine learning framework for inferring lncRNA-disease associations (LDA) by synergizing graph convolutional networks (GCNs) with deep matrix factorization. Specifically, GCNs are leveraged to extract and encode high-fidelity feature representations of lncRNAs and diseases, while deep matrix factorization, implemented via a multi-layer perceptron, facilitates the discovery of potential disease-associated lncRNAs. Our model exhibits outstanding predictive performance, achieving AUCs of 0.9183 and 0.9057 in leave-one-out and five-fold cross-validation experiments, respectively. Extensive comparative evaluations demonstrate that GMFLDA surpasses four state-of-the-art methods, underscoring its superior predictive capability. We anticipate that GMFLDA will serve as a powerful computational tool for biomarker discovery, significantly accelerating the identification of disease-associated lncRNAs while mitigating the time and cost constraints of traditional wet-lab experiments. © 2013 IEEE.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Domain Reductions After Preprocessing: Effects on Dynamic Variable Ordering Heuristics in Constraint Satisfaction Search 23rd

Domain Reductions After Preprocessing: Effects on Dynamic V...

引用

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Wallace, Richard J. Insight Centre for Data Analytics and Department of Computer Science University College Cork Cork Ireland

ISBN: (纸本)9783031734991

We still do not have an adequate understanding of heuristic methods used for solving constraint satisfaction problems (CSPs). An example involves the effects of preprocessing, an essential means of improving CSP search. The traditional explanation for its beneficial effect is that the resulting "problem reduction" leaves fewer possibilities to explore. Recently, however, it was shown that when dynamic variable ordering heuristics are used, other factors related to domain size reduction are much more important. This paper extends this analysis and explores some implications of this new perspective. The key idea is that pattern of domain reductions produced by preprocessing transmits information that guides heuristic decisions. Treating domain reduction as a code and the set of reductions as a message of length n transmitted to the search algorithm, we distinguish two factors, message discriminability and code quality, and show that greater problem reduction enhances both. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Online forecasting using neighbor-based incremental learning for electricity markets

引用

Neural Computing and Applications 2025年 1-18页

作者： Melgar-García, L. Gutiérrez-Avilés, D. Rubio-Escudero, C. Troncoso, A. Department of Artificial Intelligence Universidad Politécnica de Madrid Madrid28660 Spain Department of Computer Science University of Seville Avda. Reina Mercedes s/n Seville41012 Spain Data Science and Big Data Lab Pablo de Olavide University Seville41013 Spain

Electricity market forecasting is very useful for the different actors involved in the energy sector to plan both the supply chain and market operation. Nowadays, energy demand data are data coming from smart meters and have to be processed in real-time for more efficient demand management. In addition, electricity prices data can present changes over time such as new patterns and new trends. Therefore, real-time forecasting algorithms for both demand and prices have to adapt and adjust to online data in order to provide timely and accurate responses. This work presents a new algorithm for electricity demand and prices forecasting in real-time. The proposed algorithm generates a prediction model based on the k-nearest neighbors algorithm, which is incrementally updated in an online scenario considering both changes to existing patterns and adding new detected patterns to the model. Both time-frequency and error threshold based model updates have been evaluated. Results using energy demand from 2007 to 2016 and prices data for different time periods from the Spanish electricity market are reported and compared with other benchmark algorithms. © The Author(s) 2025.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

HFANet: Hierarchical Feature-Enhanced Aggregation Network for Camouflaged Object Detection

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Zhang, Xinchao Zhu, Hengliang Mao, Guojun Department of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China

Camouflaged object detection (COD) aims to identify target objects in complex scenes with extremely high similarity to their surroundings, and has significant applications in military, medical, and other fields. This paper proposes a hierarchical feature-enhanced aggregation network (HFANet) for COD, aiming to address the situations that the target object is highly similar to the background. First, we adopt the pyramid vision Transformer model as the backbone for feature extraction. On top of it, the object-region amplification module and deep interaction guidance module are stacked to enhance the perception of camouflaged objects in complex scenes. Second, an enhanced receptive field module is designed to improve edge perception of camouflaged objects. At last, a multi-scale interactive fusion module is designed by cross-scale connection through adjacent layers, effectively improving the accuracy of COD. The proposed method is evaluated on three challenging datasets: CAMO, CHAMELEON, and COD10K. Evaluation results demonstrate superior performance compared to the state-of-the-art methods. © Shanghai Jiao Tong University 2024.

关键词： Object detection

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：