检索结果-内蒙古大学图书馆

AI-Driven Pattern Recognition in Medicinal Plants: A Comprehensive Review and Comparative Analysis

computers, Materials & Continua 2024年第11期81卷 2077-2131页

作者： Mohd Asif Hajam Tasleem Arif Akib Mohi Ud Din Khanday Mudasir Ahmad Wani Muhammad Asim Department of Information Technology Baba Ghulam Shah Badshah UniversityRajouriJammu and Kashmir185234India Department of Computer Science Samarkand International University of TechnologySamarkand141500Uzbekistan EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia

The pharmaceutical industry increasingly values medicinal plants due to their perceived safety and costeffectiveness compared to modern *** the extensive history of medicinal plant usage,various plant parts,including flowers,leaves,and roots,have been acknowledged for their healing properties and employed in plant *** images,however,stand out as the preferred and easily accessible source of *** plant identification by plant taxonomists is intricate,time-consuming,and prone to errors,relying heavily on human *** intelligence(AI)techniques offer a solution by automating plant recognition *** study thoroughly examines cutting-edge AI approaches for leaf image-based plant identification,drawing insights from literature across renowned *** paper critically summarizes relevant literature based on AI algorithms,extracted features,and results ***,it analyzes extensively used datasets in automated plant classification *** also offers deep insights into implemented techniques and methods employed for medicinal plant ***,this rigorous review study discusses opportunities and challenges in employing these AI-based ***,in-depth statistical findings and lessons learned from this survey are highlighted with novel research areas with the aim of offering insights to the readers and motivating new research *** review is expected to serve as a foundational resource for future researchers in the field of AI-based identification of medicinal plants.

关键词： Pattern recognition artificial intelligence machine learning deep learning image processing plant leaf identification

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Shukla, Shubhi Dalui, Subhadeep Alam, Manaar Datta, Shubhajit Mondal, Arijit Mukhopadhyay, Debdeep Chakrabarti, Partha Pratim Centre for Computational and Data Sciences Iit Kharagpur India Iit Kharagpur Computer Science and Engineering Department India Center for Cyber Security New York University Abu Dhabi United Arab Emirates Iit Kharagpur Department of Artificial Intelligence India Iit Patna Computer Science and Engineering Department India

ISBN: (纸本)9798331510831

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL © 2025 IEEE.

关键词： adversarial attack decision-boundary diversity defense ensemble models

来源：评论

学校读者我要写书评

暂无评论

Oja's Algorithm for Streaming Sparse PCA 38

Oja's Algorithm for Streaming Sparse PCA

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kumar, Syamantak Sarkar, Purnamrita Department of Computer Science UT Austin United States Department of Statistics and Data Sciences UT Austin United States

Oja's algorithm for Streaming Principal Component Analysis (PCA) for n datapoints in a d dimensional space achieves the same sin-squared error O(reff/n) as the offline algorithm in O(d) space and O(nd) time and a single pass through the datapoints. Here reff is the effective rank (ratio of the trace and the principal eigenvalue of the population covariance matrix Σ). Under this computational budget, we consider the problem of sparse PCA, where the principal eigenvector of Σ is s-sparse, and reff can be large. In this setting, to our knowledge, there are no known single-pass algorithms that achieve the minimax error bound in O(d) space and O(nd) time without either requiring strong initialization conditions or assuming further structure (e.g., spiked) of the covariance matrix. We show that a simple single-pass procedure that thresholds the output of Oja's algorithm (the Oja vector) can achieve the minimax error bound under some regularity conditions in O(d) space and O(nd) time. We present a nontrivial and novel analysis of the entries of the unnormalized Oja vector, which involves the projection of a product of independent random matrices on a random initial vector. This is completely different from previous analyses of Oja's algorithm and matrix products, which have been done when the reff is bounded. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SMOTE Oversampling and Near Miss Undersampling Based Diabetes Diagnosis from Imbalanced dataset with XAI Visualization 28

SMOTE Oversampling and Near Miss Undersampling Based Diabete...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Nayan, Nasim Mahmud Islam, Ashraful Islam, Muhammad Usama Ahmed, Eshtiak Hossain, Mohammad Mobarak Alam, Md Zahangir University of Information Technology and Sciences Department of Computer Science and Engineering Bangladesh Independent University Center for Computational and Data Sciences Bangladesh School of Computing and Informatics University of Louisiana at Lafayette United States Independent University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350300482

This study investigated the predictive ability of ten different machine learning (ML) models for diabetes using a dataset that was not evenly distributed. Additionally, the study evaluated the effectiveness of two oversampling and undersampling methods, namely the Synthetic Minority Oversampling Technique (SMOTE) and the Near-Miss algorithm. Explainable Artificial Intelligence (XAI) techniques were employed to enhance the interpretability of the model's predictions. The results indicate that the extreme gradient boosting (XGB) model combined with SMOTE oversampling technique exhibited the highest accuracy and an F1-score of 99% and 1.00 respectively. Furthermore, the utilization of XAI methods increased the dependability of the model's decision-making process, rendering it more appropriate for clinical use. These results imply that integrating XAI with ML and oversampling techniques can enhance the early detection and management of diabetes, leading to better diagnosis and intervention. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Robust WCET Estimation via Ensemble Learning with Fractional-Order Legendre Function Kernels 5

Robust WCET Estimation via Ensemble Learning with Fractional...

引用

5th National and the 1st International Conference on Applied Research in Electrical Engineering, AREE 2025

作者： Monfared, Amir Hussein Ataei Moghaddam, Mahdi Movahedian Sharif-Bakhtiar, Sheedeh Parand, Kourosh Borna, Keivan Kharazmi University Faculty of Mathematics and Computer Science Department of Computer Science Tehran Iran Shahid Beheshti University Faculty of Mathematical Sciences Department of Computer and Data Sciences Tehran Iran Institute for Cognitive and Brain Sciences Shahid Beheshti University Department of Cognitive Modeling Tehran Iran

ISBN: (纸本)9798350377170

Estimating Worst-Case Execution Time (WCET) as a regression problem has become increasingly challenging due to the complexity of modern hardware and software systems. Traditional statistical methods often fall short of providing accurate and reliable estimates. To address these limitations, ensemble learning methods have emerged as a promising approach for capturing edge cases in execution scenarios. This paper proposes a novel ensemble model that integrates fractional-order Legendre functions (FLF) to enrich feature representation. This integration reduces correlations between individual models within the ensemble, enhancing generalization capabilities. Our method achieves significant reductions in Mean Squared Error (MSE) for WCET estimates while maintaining high levels of safeness. Specifically, the proposed model maintained an error below one across most benchmarks, with safeness levels of %100 in 13 out of 16 benchmarks. These findings underscore the efficacy of our approach and its potential to provide robust and accurate WCET estimates for complex systems. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LegoDroid: flexible Android app decomposition and instant installation

引用

science China(Information sciences) 2023年第4期66卷 155-173页

作者： Yi LIU Yun MA Xusheng XIAO Tao XIE Xuanzhe LIU School of Computer Science Peking University Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of Education Institute for Artificial Intelligence Peking University Department of Computer and Data Sciences Case Western Reserve University

Current mobile applications(apps) have become increasingly complicated with increasing features that are represented on the graphical user interface associated with application programming interfaces(APIs) to access backend functionality and data. Meanwhile, apps suffer from the “software bloat” in volume. Some app features may be redundant, with respect to those features(from other apps) that the users already desirably and frequently use. However, the current app release model forces users to download and install a full-size installation package rather than optionally choosing only their desired features. Large-size apps can not only increase the local resource consumption, such as CPU, memory, and energy, but also inevitably compromise the user experience, such as the slow load time in the app. In this article, we first conduct an empirical study to characterize the app feature usage when users interact with Android apps,and surprisingly find that users access only a very small subset of app features. Based on these findings,we design a new approach named Lego Droid, which automatically decomposes an Android app for flexible loading and installation, while preserving the expected functionality with a fast and instant app load. With such a method, a slimmer bundle will be downloaded and host the target APIs inside the original app to satisfy users' requirements. We implement a system for Lego Droid and evaluate it with 1000 real-world Android apps. Compared to the original full-size apps, apps optimized by Lego Droid can substantially improve the load time by reducing the base bundle and feature bundles by 13.06% and 10.93%, respectively,along with the app-package installation size by 44.17%. In addition, we also demonstrate that Lego Droid is quite practical with evolving versions, as it can produce substantial reusable code to alleviate the developers' efforts when releasing new app versions.

关键词： performance software bloat instant installation mobile applications program analysis

来源：评论

学校读者我要写书评

暂无评论

Development of an ML Model of a Wind Turbine for Fault Detection

Development of an ML Model of a Wind Turbine for Fault Detec...

引用

AITU: Digital Generation, IEEE

作者： Syrym Adelshiyev Dias Kurmashev Department of Computational and Data Sciences Computer Science Astana IT University Astana Kazakhstan

ISBN: (数字)9798350364378

ISBN: (纸本)9798350364385

In recent years, the advancement of renewable energy technologies has gained significant momentum, with wind energy emerging as a prominent source of clean electricity generation. The efficient operation and maintenance of wind turbines are crucial for maximizing energy production while minimizing costs. This paper presents the development of a machine learning (ML) model tailored specifically for wind turbine performance optimization. The proposed ML model integrates various data sources including meteorological conditions, turbine sensor data, historical performance records, and maintenance logs. Leveraging these datasets, the model employs sophisticated algorithms such as neural networks, decision trees, and ensemble methods to predict turbine performance, detect anomalies, and optimize maintenance schedules.

关键词： Support vector machines Renewable energy sources Fault detection Neural networks Feature extraction Wind turbines Maintenance

来源：评论

学校读者我要写书评

暂无评论

Late and Early Blight Diseases Identification of Potatoes with a Light Weight Hybrid Transfer Learning Model

Late and Early Blight Diseases Identification of Potatoes wi...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Siddique, Abu Zobayer Bin Das, Shoibal Tabassum, Poonam Tasir, All Moon Roy, Shovon Rahman, Md. Saifur Mridha, M.F. Islam, Ashraful Bangladesh University of Business and Technology Department of Computer Science and Engineering Dhaka Bangladesh American International University-Bangladesh Department of Computer Science Dhaka Bangladesh Independent University Bangladesh Center for Computational and Data Sciences Dhaka Bangladesh

ISBN: (纸本)9798350337617

Potatoes are one of the world's most important commodities, and leaf maladies such as early and late blight can substantially reduce their yield and quality. Hence, both farmers and researchers must prioritize quick and precise illness diagnosis. In our research, we propose a strategy based on transfer learning for classifying toxic and diseased potato leaf tissue. We specifically used our dataset of potato leaf photos to fine-tune the Mobile-Net model, which was a pre-trained convolutional neural network. To enhance the model's functionality, we also added a few more layers. Our study found that, in comparison to other state-of-the-art methods, our methodology outperformed them all by achieving a multi-class classification accuracy of 99%. Our method can be used to detect and monitor potato leaf maladies in real-world situations, which could eventually contribute to enhancing potato productivity and food security. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Security Metrics and Authentication-based RouTing (SMART) Protocol for Vehicular IoT Networks

引用

SN computer science 2024年第2期5卷 1-14页

作者： Kumar, Rakesh Singh, Sunil K. Lobiyal, D.K. Kumar, Sudhakar Jawla, Shashi Department of Applied Computational Sciences & Engineering GLBITM Greater Uttar Pradesh Noida India Department of Computer Science & Engineering CCET Panjab University Chandigarh India School of Computer & Systems Sciences Jawaharlal Nehru University New Delhi India Department of Computer Science & Engineering SVIET Mohali India

Routing protocols, responsible for determining optimal paths, fall into two main categories: reactive and proactive protocols. In the realm of reactive routing protocols, exemplified by Ad hoc On-demand Distance Vector (AODV), routes are created only when there is an actual data transmission requirement. In contrast, proactive routing protocols maintain pre-computed paths to all potential destinations, resulting in reduced resource utilization within reactive protocols and continuous route maintenance within proactive ones. Reactive routing protocols are resource efficient as they establish routes as needed, while proactive counterparts maintain routing tables for all possible destinations, ensuring constant route availability regardless of data transmission demands. This paper primarily concentrates on the reactive routing protocol category, focusing on real-time path optimization and routing information updates. In the context of Vehicular Internet of Things (VIoT) networks, where malicious entities might attempt to flood, mislead, or impersonate routing packets, it is imperative to ensure robust security measures within the routing protocol. Unfortunately, secure routing protocols in VIoT networks, including AODV, SAODV, and SGHRP, often exhibit inefficiencies and impose a high overhead. To address these challenges, this research paper introduces the Security Metrics and Authentication-based RouTing (SMART) protocol for VIoT networks, with a focus on enhancing security while minimizing overhead. The SMART protocol utilizes the Merkle tree for hash (digest) generation, which is then encrypted using Elliptic Curve Cryptography (ECC) to reduce overhead. This proposed protocol enhances security by authenticating the source and incorporating security metrics into the routing information. To assess the performance of the SMART protocol, simulations were conducted using Network Simulator-2 (NS₂). The results demonstrated an improved packet delivery ratio, red

关键词： AODV Authentication ECC Hash digest Merkle Tree OBU Routing Protocol SAODV VIoT Networks

来源：评论

学校读者我要写书评

暂无评论

Expand-and-Cluster: Parameter Recovery of Neural Networks 41

Expand-and-Cluster: Parameter Recovery of Neural Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Martinelli, Flavio Şimşek, Berfin Gerstner, Wulfram Brea, Johanni Department of Life Sciences and Computer Sciences EPFL Lausanne Switzerland Center for Data Science NYU New York United States

Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparameterisation and activation function symmetries. Yet, we show that the incoming weight vector of each neuron is identifiable up to sign or scaling, depending on the activation function. Our novel method 'Expand-and-Cluster' can identify layer sizes and weights of a target network for all commonly used activation functions. Expand- and-Cluster consists of two phases: (i) to relax the non-convex optimisation problem, we train multiple overparameterised student networks to best imitate the target function;(ii) to reverse engineer the target network's weights, we employ an ad-hoc clustering procedure that reveals the learnt weight vectors shared between students - these correspond to the target weight vectors. We demonstrate successful weights and size recovery of trained shallow and deep networks with less than 10% overhead in the layer size and describe an 'ease-of-identifiability' axis by analysing 150 synthetic problems of variable difficulty. Copyright 2024 by the author(s)

关键词： Convex optimization

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：