检索结果-内蒙古大学图书馆

Dates Detection System for Automatic Harvesting Using Deep Learning 1

International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2022

作者： Zarouit, Yousra Aksasse, Brahim Ouhda, Mohamed Department of Computer Science Faculty of Sciences and Technics Moulay Ismail University Errachidia Morocco MAIS Laboratory Department of Computer Science Faculty of Sciences Moulay Ismail University Meknes Meknes Morocco Department of Computer and Mathematics Higher School of Technology Sultan Moulay Slimane University Khenifra Morocco

ISBN: (数字)9783031352485

ISBN: (纸本)9783031352478

An accurate vision system for detecting and analyzing fruit in real-time requires fast and accurate algorithms for object detection. This will allows robotic systems to analyze and process in real-time identically like to the human visual system making them more efficient and cost-effective. However, success in this domain is still limited. No research has addressed the problem of date fruit detection and localization in an orchard environment. The system of our interest is a date fruit-harvesting robot. The robot will detect, analyze and cut the date bunch from the palm tree. In this work, a state of art object detection algorithm, the You Only Look Once version 3 (YOLOv3), is used to solve the detection and localization of date bunches problem. Unstructured agricultural environments with constantly changing light, and shadow, make date fruit detection challenging. Experimental results show the effectiveness of the proposed algorithm to deal with these problems, giving high accuracy. Based on the model output, the robot can detect and locate dates in images to make the harvesting decision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Harvesting

来源：评论

学校读者我要写书评

暂无评论

HyperplaneGAN: a unified consistent translation framework for facial attribute editing

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Li, Defang Deng, Huiqi Qin, Peng Chen, Weifu Feng, Guocan College of General Education Guangzhou Vocational College of Technology and Business Guangzhou China Department of Computer Science Guangzhou Maritime University Guangzhou China School of Mathematics Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory Sun Yat-sen University Guangzhou China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China

Facial attribute editing has been obtaining remarkable progress as the rapid development in deep generative models. Existing algorithms can be roughly grouped into two distinct categories: attribute-guided models and exemplar-guided models. These models achieve impressive facial attribute editing results, however, there are some limitations. For example, images generated by current attribute-guided models are lack of diversity and attribute styles are not controllable. For exemplar-guided models, low transfer precision and fidelity of generated images are commonly complained issues. In order to generate high-quality attribute-controllable facial images, we propose a novel unified translation framework called HyperplaneGAN which has following advantages: (1) the proposed model can do both attribute-guided facial editing and exemplar-guided facial editing;(2) by employing latent unit swapping and linear separation constraint for learning pair-wise linearly separable disentangled representations, the model can do flexible and controllable translation;(3) cycle-consistency loss and residual attribute vectors are used to guide the model to manipulate specific attributes precisely while other attributes are kept intact. Substantial experimental results demonstrate that HyperplaneGAN outperforms state-of-the-art models on both attribute-guided facial editing and exemplar-guided facial editing, in terms of quantitative evaluation and qualitative evaluation. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Framework for a Stage-Wise Classification of Date Palm White Scale Disease

引用

Big Data Mining and Analytics 2023年第3期6卷 263-272页

作者： Abdelaaziz Hessane Ahmed El Youssefi Yousef Farhaoui Badraddine Aghoutane Fatima Amounas STI Laboratory IDMSFaculty of Sciences and TechniquesMoulay Ismail University of MeknesErrachidia 52000Morocco. IA Laboratory Department of Computer ScienceFaculty of SciencesMoulay Ismail University of MeknesMeknes 50070Morocco. RO.AL&I Group Computer Sciences DepartmentFaculty of Sciences and TechniquesMoulay Ismail University of MeknesErrachidia 52000Morocco.

Date palm production is critical to oasis agriculture,owing to its economic importance and nutritional *** diseases endanger this precious tree,putting a strain on the economy and *** scale Parlatoria blanchardi is a damaging bug that degrades the quality of *** an infestation reaches a specific degree,it might result in the tree’s *** counter this threat,precise detection of infected leaves and its infestation degree is important to decide if chemical treatment is *** decision is crucial for farmers who wish to minimize yield losses while preserving production *** this purpose,we propose a feature extraction and machine learning(ML)technique based framework for classifying the stages of infestation by white scale disease(WSD)in date palm trees by investigating their leaflets images.80 gray level co-occurrence matrix(GLCM)texture features and 9 hue,saturation,and value(HSV)color moments features are extracted from both grayscale and color images of the used *** classify the WSD into its four classes(healthy,low infestation degree,medium infestation degree,and high infestation degree),two types of ML algorithms were tested;classical machine learning methods,namely,support vector machine(SVM)and k-nearest neighbors(KNN),and ensemble learning methods such as random forest(RF)and light gradient boosting machine(LightGBM).The ML models were trained and evaluated using two datasets:the first is composed of the extracted GLCM features only,and the second combines GLCM and HSV *** results indicate that SVM classifier outperformed on combined GLCM and HSV features with an accuracy of 98.29%.The proposed framework could be beneficial to the oasis agricultural community in terms of early detection of date palm white scale disease(DPWSD)and assisting in the adoption of preventive measures to protect both date palm trees and crop yield.

关键词： machine learning feature extraction ensemble learning diseases precision agriculture date palm

来源：评论

学校读者我要写书评

暂无评论

CRP2-VCS: Contrast-Oriented Region-based Progressive Probabilistic Visual Cryptography Schemes

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5501-5517页

作者： Wu, Xiaotian Song, Bofan Fang, Jia Yan, WeiQi Peng, Qing-Yu Jinan University Guangdong Key Laboratory of Data Security and Privacy Preserving College of Cyber Security College of Information Science and Technology Guangzhou China Auckland University of Technology Department of Computer and Information Systems Auckland New Zealand Jinan University Sino-French Joint Laboratory for Astrometry Dynamics and Space Science Guangzhou China

Most visual cryptography schemes (VCSs) are condition-oriented which implies their designs focus on satisfying the contrast and security conditions in VCS. In this paper, we explore a new architecture of VCS: contrast-oriented region-based progressive probabilistic VCS (CRP2-VCS). The term contrast-oriented indicates the optimality of multi-contrast is taken into consideration when producing shadows. First of all, new requirements for CRP2-VCS, described by probabilities, are introduced. As a non-interference requirement is proposed, the secret interference problem in existing region-based progressive VCS can be avoided. Then, a construction of CRP2-VCS based on a multi-contrast-maximizing model is provided. The multi-contrast-maximizing problem is essentially a probabilistic VCS model that fuses region-based sharing, multi-contrast optimization, and general access structure (GAS) together. Finally, a Max-Min based technique is adopted to solve the multi-objective optimization problem. Moreover, to further boost the visual quality, the proposed method is extended to allow employing XOR operation for image recovery. Experimental results and comparisons are demonstrated to show the effectiveness and advantages, such as optimal visual quality, non-expansible shadow and GAS sharing policy, are provided by the proposed technique. © 2025 IEEE.

关键词： Visualization Cryptography Probabilistic logic Interference Encoding Circuits and systems Polynomials Optimization Minimax techniques Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Mapper4Live: Using Control Structures to Embed Complex Mapping Tools into Ableton Live

Mapper4Live: Using Control Structures to Embed Complex Mappi...

引用

International Conference on New Interfaces for Musical Expression, NIME 2022

作者： Boettcher, Brady Malloch, Joseph Wang, Johnty Wanderley, Marcelo M. Input Devices and Musical Interaction Laboratory CIRMMT McGill University Canada Graphics and Experiential Media Laboratory Faculty of Computer Science Dalhousie University Canada

This paper presents Mapper4Live, a software plugin made for the popular digital audio workstation software Ableton Live. Mapper4Live exposes Ableton’s synthesis and effect parameters on the distributed libmapper signal mapping network, providing new opportunities for interaction between software and hardware synths, audio effects, and controllers. The plugin’s uses and relevance in research, music production and musical performance settings are explored, detailing the development journey and ideas for future work on the project. © 2022, International Conference on New Interfaces for Musical Expression. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

FUNKNN: NEURAL INTERPOLATION FOR FUNCTIONAL GENERATION 11

FUNKNN: NEURAL INTERPOLATION FOR FUNCTIONAL GENERATION

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Khorashadizadeh, AmirEhsan Chaman, Anadi Debarnot, Valentin Dokmanić, Ivan Department of Mathematics and Computer Science University of Basel Switzerland Coordinated Science Laboratory University of Illinois at Urbana-Champaign United States

Can we build continuous generative models which generalize across scales, can be evaluated at any coordinate, admit calculation of exact derivatives, and are conceptually simple? Existing MLP-based architectures generate worse samples than the grid-based generators with favorable convolutional inductive biases. Models that focus on generating images at different scales do better, but employ complex architectures not designed for continuous evaluation of images and derivatives. We take a signal-processing perspective and treat continuous image generation as interpolation from samples. Indeed, correctly sampled discrete images contain all information about the low spatial frequencies. The question is then how to extrapolate the spectrum in a data-driven way while meeting the above design criteria. Our answer is FunkNN-a new convolutional network which learns how to reconstruct continuous images at arbitrary coordinates and can be applied to any image dataset. Combined with a discrete generative model it becomes a functional generator which can act as a prior in continuous ill-posed inverse problems. We show that FunkNN generates high-quality continuous images and exhibits strong out-of-distribution performance thanks to its patch-based design. We further showcase its performance in several stylized inverse problems with exact spatial derivatives. Our implementation is available at https://***/swing-research/FunkNN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

CIL4EMTD: A Novel Class Incremental Learning Method for Encrypted Malware Traffic Detection 9

CIL4EMTD: A Novel Class Incremental Learning Method for Encr...

引用

9th IEEE International Conference on Data science in Cyberspace, DSC 2024

作者： Li, Jiarui Du, Lei Chen, Yilu Zeng, Liyi Li, Hao Gu, Zhaoquan School of Computer Science and Technology Shenzhen China Pengcheng Laboratory Department of New Networks Shenzhen China National Key Laboratory of Advanced Communication Networks Shijiazhuang China

ISBN: (纸本)9798350391367

With the widespread adoption of traffic encryption technologies, detecting attack behaviors in encrypted malware traffic has become a critical and challenging problem. The encrypted malware traffic contains a lot of redundant information and noise, which necessitates additional computational resources. In addition, new attack categories continue to emerge over time, resulting in traditional detection methods losing effectiveness in identifying these new attacks. To handle the above challenge, in this paper, we propose CIL4EMTD, a novel Class Incremental Learning method targeted for Encrypted Malware Traffic Detection. Our method leverages clustering techniques to enrich the extraction of dataset features, while specifically customizing LwF for detecting encrypted malware to optimize the stability of model training via efficient knowledge distillation. To verify the effectiveness of CIL4EMTD, we conduct experiments comparing it with other class incremental learning methods. The experiment results show that CIL4EMTD demonstrates state-of-the-art performance on a real-world dataset, achieving a recognition accuracy of 94.34% for new categories while maintaining the average accuracy for known categories within a margin of less than a 10% decline. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring BERT and ELMo for Bangla Spam SMS Dataset Creation and Detection 26

Exploring BERT and ELMo for Bangla Spam SMS Dataset Creation...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Khan, Fariba Mustafa, Rashed Tasnim, Farzana Mahmud, Tanjim Hossain, Mohammad Shahadat Andersson, Karl University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh International Islamic University Chittagong Department of Computer Science and Engineering Chittagong4318 Bangladesh Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Luleå971 87 Sweden

ISBN: (纸本)9798350359015

The proliferation of digital communication and social media platforms has led to an upsurge in spam messages across various languages, including Bangla. These intrusive messages not only cause user annoyance but also elevate the risk of important messages going unnoticed. To address this concern, we harnessed the power of natural language processing (NLP) techniques in conjunction with machine-learning models. This study delves into the efficacy of diverse machine-learning and deep-learning models in detecting spam messages in the Bangla language. Particularly, deep-learning methodologies such as ELMo and BERT have exhibited promising results in spam detection across other languages. However, the realm of Bangla spam detection remains underexplored, with a dearth of deep-learning approaches. To bridge this gap, we constructed a unique Bangla SMS dataset, given the scarcity of available Bangla Spam SMS datasets, and proceeded to evaluate the performance of ELMo, BERT, and conventional machine learning models. The findings from our experiments underscore the superior performance of deep learning-based models over traditional methods, with Elmo surpassing BERT in Bangla spam detection, achieving an impressive accuracy of approximately 94%. This endeavor bears the potential to not only enhance SMS utilization efficiency but also bolster cybersecurity measures against phishing attacks. © 2023 IEEE.

关键词： BERT ELMo Machine Learning Spam SMS Word Embedding

来源：评论

学校读者我要写书评

暂无评论

Research on the behaviour of Bluetooth Low Energy protocol in the heart rate monitoring application

引用

Procedia computer science 2023年 225卷 63-69页

作者： Zuzanna Balas Krzysztof Tokarz Bartłomiej Zieliński Tomasz Guźniczak Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

In the paper, the authors check the behaviour of Bluetooth Low Energy protocol in a popular smart wristband and a microcontroller in the heart rate monitoring application. The measurements were collected using a development board with the ESP32 System on Chip. The authors tested measurement period stability and measurement reliability in various conditions.

关键词： Smart wristband Internet of Things Health monitoring Bluetooth Low Energy Wireless data transmission

来源：评论

学校读者我要写书评

暂无评论

Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View 41

Diagnosing the Compositional Knowledge of Vision Language Mo...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Jin Dong, Shichao Zhu, Yapeng Yao, Kelu Zhao, Weidong Li, Chao Luo, Ping Department of Computer Science The University of Hong Kong Hong Kong Shanghai AI Laboratory China Zhejiang Laboratory Hangzhou China Baidu Inc. Beijing China

Compositional reasoning capabilities are usually considered as fundamental skills to characterize human perception. Recent studies show that current Vision Language Models (VLMs) surprisingly lack sufficient knowledge with respect to such capabilities. To this end, we propose to thoroughly diagnose the composition representations encoded by VLMs, systematically revealing the potential cause for this weakness. Specifically, we propose evaluation methods from a novel game-theoretic view to assess the vulnerability of VLMs on different aspects of compositional understanding, e.g., relations and attributes. Extensive experimental results demonstrate and validate several insights to understand the incapabilities of VLMs on compositional reasoning, which provide useful and reliable guidance for future studies. The deliverables will be updated here. Copyright 2024 by the author(s)

关键词： Visual languages

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：