检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Liu, Yukun Shi, Daming Lin, Hexiu College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Few-shot learning is often challenged by low generalization performance due to the assumption that the data distribution of novel classes and base classes is similar while the model is trained only on the base classes. To mitigate the above issues, we propose a few-shot learning with representative global prototype method. Specifically, to enhance the generalization to novel classes, we propose a method to jointly train the base classes and the novel classes, using selected representative and non-representative samples to optimize representative global prototypes, respectively. Additionally, a method that organically combines the sample of base classes conditional on semantic embedding to generate new samples of novel classes with the original data is proposed to enhance the data of novel classes. Results show that this training method improves the model's ability to describe novel classes, improving the classification performance for a few shots. Intensive experiments have been conducted on two popular benchmark datasets, and the experimental results show that this method significantly improves the classification ability of few-shot learning tasks and achieves state-of-the-art performance. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-perception large kernel convnet for efficient image super-resolution

引用

四川大学学报(自然科学版) 2025年第1期62卷 67-78页

作者： MIAO Xuan LI Zheng XU Wen-Zheng College of Computer Science(College of Software) Sichuan UniversityChengdu 610065China Tianfu Engineering-Oriented Numerical Simulation&Software Innovation Center Sichuan UniversityChengdu 610207China

Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art *** efforts have explored the incorporation of Transformers to augment network performance in ***,the high computational cost of Transformers makes them less suitable for deployment on lightweight ***,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel *** this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel ***,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these *** addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel *** results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.

关键词： Single Image Super-Resolution Lightweight model Deep learning Large kernel

来源：评论

学校读者我要写书评

暂无评论

A Robust Methodology for Fruit Quality Prediction and Estimation Using Intelligent Learning Based Image Processing Logic

A Robust Methodology for Fruit Quality Prediction and Estima...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Malathi, K. Babu, Vunnava Dinesh Ramkumar, M. Ayyadurai, M. Vivek, K. Aljawawdeh, Hamzeh J. Saveetha University Department of Cse Chennai India Rv Institute of Technology Department of Cse Guntur India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Department of software engineering Faculty of information technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Fruit quality prediction plays a vital role in agricultural and food industries, ensuring that only high-quality produce reaches the consumer. Traditional methods of assessing fruit quality rely on manual inspection, which is both time-consuming and prone to human error. This paper presents a robust methodology for fruit quality prediction and estimation, utilizing a hybrid deep learning model that integrates DenseN et for feature extraction with LightGBM for efficient classification. The proposed model is designed to automate the process of fruit quality assessment by analyzing key attributes such as color, texture, and shape from high-resolution fruit images. The Fruit360 dataset was used for training and testing, with images classified into categories such as fresh, ripe, overripe, and damaged. A comprehensive comparison with nine existing models, including SVM, Random Forest, and XGBoost, was conducted using performance metrics such as accuracy, precision, recall, and Fl-score. The proposed model achieved an accuracy of 96.78%, significantly outperforming all other models. Furthermore, the model's precision and recall reached 95.33% and 95.67%, respectively, demonstrating its reliability in distinguishing high-quality fruits from low-quality ones. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Modified Metaheuristics with Transfer Learning Based Insect Pest Classification for Agricultural Crops

引用

computer Systems science & engineering 2023年第9期46卷 3847-3864页

作者： Saud Yonbawi Sultan Alahmari T.Satyanarayana murthy Ravuri Daniel E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Computer Science and Engineering Prasad V.Potluri Siddhartha Institute of TechnologyVijayawadaIndia Department of Computer Science and Engineering GMR Institute of TechnologyAndhra PradeshRajamIndia School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenangMalaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversitySaudi Arabia Department of Computer Science University of Central AsiaNarynKyrgyzstan Faculty of Computers and Information South Valley UniversityQenaEgypt

Crop insect detection becomes a tedious process for agronomists because a substantial part of the crops is damaged,and due to the pest attacks,the quality is *** are the major reason behind crop quality degradation and diminished crop ***,accurate pest detection is essential to guarantee safety and crop *** identification of insects necessitates highly trained taxonomists to detect insects precisely based on morphological ***,some progress has been made in agriculture by employing machine learning(ML)to classify and detect *** study introduces a Modified Metaheuristics with Transfer Learning based Insect Pest Classification for Agricultural Crops(MMTL-IPCAC)*** presented MMTL-IPCAC technique applies contrast limited adaptive histogram equalization(CLAHE)approach for image *** neural architectural search network(NASNet)model is applied for feature extraction,and a modified grey wolf optimization(MGWO)algorithm is employed for the hyperparameter tuning process,showing the novelty of the *** last,the extreme gradient boosting(XGBoost)model is utilized to carry out the insect classification *** simulation analysis stated the enhanced performance of the MMTL-IPCAC technique in the insect classification process with maximum accuracy of 98.73%.

关键词： Sustainable agriculture crop monitoring pest management insect classification computer vision

来源：评论

学校读者我要写书评

暂无评论

Semantic Auto-Encoder with L2-norm Constraint for Zero-Shot Learning 2021

Semantic Auto-Encoder with L2-norm Constraint for Zero-Shot ...

引用

2021 13th International Conference on Machine Learning and Computing, ICMLC 2021

作者： Wu, Yuhao Cao, Weipeng Liu, Ye Ming, Zhong Li, Jianqiang Lu, Bo College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781450389310

Zero-Shot Learning (ZSL) is an effective paradigm to solve label prediction when some classes have no training samples. In recent years, many ZSL algorithms have been proposed. Among them, semantic autoencoder (SAE) is widely used because of its simplicity and good generalization ability. However, our research found that most of the existing SAE based methods use implicit constraints to guarantee the mapping quality between feature space and semantic space. In fact, the implicit constraints are insufficient in minimizing the structural risk of the model and easy to cause the over-fitting problem. To solve this problem, we propose a novel SAE algorithm with the L2-norm constraint (SAE-L2) in this study. SAE-L2 adds the L2 regularization constraint to the mapping parameters in its optimization objective, which explicitly guarantees the structural risk minimization of the model. Extensive experiments on four benchmark datasets show that our proposed SAE-L2 can achieve better performance than the original SAE model and other ZSL algorithms. © 2021 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Self-Attention Enhanced Arcface Towards Improved Deep Face Recognitions

SSRN

引用

SSRN 2023年

作者： Xin, Yang Zhou, Yu Jiang, Jianmin College of Computer Science and Software Engineering Shenzhen University Shenzhen518000 China

Being known in characterizing details and edge information well for images, the state-of-the-art margin-based face recognition model, ArcFace, currently employs ResNet as its backbone and utilizes a class center loss penalty to achieve compact intra-class feature representations, during which ResNet is trained on large-scale and in-the-wild face datasets with millions of samples to extract highly discriminative face features. As training of deep neural networks requires massive computing and labeled data, however, ResNet has limitations in terms of receptive fields and long-range feature learnings. To this end, we propose to add a self-attention mechanism to enhance ResNet and alleviate the local restriction of convolutional networks in order to better exploit the correlations and dependencies throughout the entire face images, leading to a so-called SA-ArcFace (i.e. self-attention ArcFace) towards improved face recognitions and enhanced learning efficiencies. Compared with the existing ArcFace, extensive experiments validate that our proposed SA-ArcFace not only achieves faster convergence to optimal parameters, but also better recognition performances on a number of benchmarking datasets. For LFW dataset, specifically, SA-ArcFace achieves 51% faster convergence than ArcFace without compromise on the accuracy of face recognitions. For other benchmarking datasets, SA-ArcFace achieves an improvement of 9% to 23% in terms of face recognition accuracy than that of ArcFace. © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Presentation Attack Detection by Learning in Frequency Domain 2

Fingerprint Presentation Attack Detection by Learning in Fre...

引用

2nd IEEE International Conference on Pattern Recognition and Machine Learning, PRML 2021

作者： Zhang, Wentian Liu, Haozhe Liu, Feng Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9781665443838

The anti-spoofing ability is of great importance to the development of automated fingerprint recognition systems. This paper proposes a novel Optical Coherence Technology (OCT)-based fingerprint Presentation Attack Detection (PAD) method from frequency domain. Unlike previous approaches, we design an Frequency Feature Disentangling (FFD) model to decompose OCT-based fingerprint B-scans into four different frequency subbands like Discrete Wavelet Transform (DWT). Through such disentangling, information superimposed in original image in spatial domain (e.g. discriminative PAD feature, invalid and redundant feature) can be separated respectively. We then let it learn different frequency codes to form their corresponding latent codes. Spoofness score which is used to distinguish PAs from bonafides is finally designed based on the latent codes. The experimental results, evaluated on the dataset with 93,200 bonafide B-scans from 137 fingers and 48,400 B-scans from 121 PAs, show that our method can remove some useless interference information superimposed in spatial domain by disentangling into frequency domain for effective PAD. In the instance-wise case, the proposed method achieves a minimum error (Err.) of 0.67%, which outperforms other compared methods and improves 81.89% than the best one. © 2021 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Forensic Investigation Metamodel (BBFIM) for Investigating IoT Cybercrimes

Blockchain-Based Forensic Investigation Metamodel (BBFIM) fo...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Daifallah Zaid Alotaibe Department of Software Engineering College of Computer Science and Engineering University of Hafr Al Batin Hafr Al Batin Kingdom of Saudi Arabia

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

As smart devices are rapidly being developed, and people trust data transfer mechanisms such as Wi-Fi and the way they use them, as well as the fact that they rely heavily on data transfer mechanics, there has been an increase in cyber-attacks. Therefore, examining IoT safety threats and potential countermeasures can support investigators in determining how to deal with a range of stressful scenarios encountered when conducting cyber-crime studies to develop acceptable methods for dealing with them. The goal of this paper is to develop Blockchain-Based Forensic Investigation Metamodel for Investigating IoT Cybercrimes called (BBFIM). The purpose of the developed BBFIM is to improve the productivity and accuracy of examinations by providing a safe and decentralized environment where digital evidence, related to IoT-related crimes, can be stored, and analyzed to improve the productivity and accuracy of examinations. Through the integration of blockchain technologies the developed BBFIM ensures that the reliability of the evidence is retained throughout the investigation. It also provides transparency throughout the process. This study utilizes design science methods for development and validation purposes. Therefore, 889 IoT forensic models and frameworks have been reviewed in this study, and 15 models have been selected to develop the BBFIM. The developed BBFIM consists of three main IoT forensic practices: Forensic investigation phases, Forensic Tools and Techniques, and Blockchain Infrastructure. Compared to the existing IoT forensics models the developed BBFIM is fully decentralized which can guarantee the authority, consistency, and privacy of the data.

关键词： Productivity Accuracy Forensics Design methodology Data transfer Blockchains Safety Smart devices Cyberattack Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

A Novel Drug-Drug Interaction Prediction Model Based on Line Subgraph Generation Strategy

A Novel Drug-Drug Interaction Prediction Model Based on Line...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Bai, Tian Li, Chu Peng, Xinyue Guan, Haotian Zhang, Zefan Wang, Guishen Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China Jilin University College of Software Changchun China Jilin University School of Nursing Changchun China Jilin University School of Life Sciences Changchun China Changchun University of Technology College of Computer Science and Engineering Changchun China

ISBN: (纸本)9798350337488

Drug-Drug Interaction (DDI) prediction task is helpful for better-understanding drugs. In this paper, we propose a novel drug-drug interaction prediction model based on line subgraph generation strategy, named DDI-LSG model. Our DDI-LSG model consists of three main parts which include drug relation graph construction, line subgraph generation strategy, and graph-level classification. To consider more relationships among drugs, we propose a node feature-enhancing method to encode drug features in drug relation graph construction process. To consider drugs and DDI as equivalent factors of our DDI-LSG model, we introduce line graph transformation to integrate DDI with drug feature enhancing vector. Combining Jaccard similarity with cosine similarity, we propose a line subgraph generation strategy to evaluate node relation and extract key structures around target DDI in the line graph. Then, we reformulate the DDI prediction task into a graph-level classification task for the line subgraph of the target DDI. Therefore, in the final part of our DDI-LSG model, we use a graph-level classifier to classify the line subgraphs. Our DDI-LSG model outperforms better experiment results than baselines. Ablation results have validated the node feature enhancing method and line subgraph generation strategy. © 2023 IEEE.

关键词： drug-drug interaction prediction graph-level classification line graph line subgraph strategy node feature enhancing method

来源：评论

学校读者我要写书评

暂无评论

Detection of Misinformation Related to Pandemic Diseases Using Machine Learning 7th

Detection of Misinformation Related to Pandemic Diseases Usi...

引用

7th EAI International Conference on Robotics and Networks, ROSENET 2023

作者： Naeem, Javaria Gül, Ömer Melih Parlak, Ismail Burak Karpouzis, Kostas Kadry, Seifedine Nimer Salman, Yücel Batu Department of Computer Engineering Bahçeşehir University İstanbul Turkey Department of Computer Engineering Galatasaray University İstanbul Turkey Panteion Uninversity of Social and Political Sciences Kallithea Greece Department of Applied Data Science Noroff College Kristiansand Norway Ajman University Ajman United Arab Emirates Department of Software Engineering Bahcesehir University İstanbul Turkey

ISBN: (纸本)9783031644948

The advent of the COVID-19 pandemic has brought with it not only a global health crisis but also an infodemic characterized by the rampant spread of misinformation on social media platforms. In response to the urgent need for effective misinformation detection, this study presents a comprehensive approach harnessing machine learning and deep learning techniques, culminating in ensemble methods, to combat the proliferation of COVID-19 misinformation on Facebook, Twitter, Instagram, and YouTube. Drawing from a rich dataset comprising user comments on these platforms, encompassing diverse COVID-19-related discussions, our research applies SVM, decision tree, logistic regression, and neural networks to perform in-depth analysis and classification of comments into two categories: positive and negative information. The innovation of our approach lies in the final phase, where we employ ensemble methods to consolidate the strengths of various machine learning and deep learning algorithms. After applying ensemble learning, accuracy reached 91% for Facebook content, 79% for Instagram, 80% for Twitter, and 95% for YouTube. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： COVID-19

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：