检索结果-内蒙古大学图书馆

An Attention-Based Deep Network for Plant Disease Classification

Machine Graphics and Vision 2024年第1期33卷 47-67页

作者： Bera, Asish Bhattacharjee, Debotosh Krejcar, Ondrej Department of Computer Science and Information Systems Birla Institute of Technology and Science Rajasthan Pilani India Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India Center for Basic and Applied Science Faculty of Informatics and Management University of Hradec Králové Czech Republic Škoda Auto University Mladá Boleslav Czech Republic Universiti Teknologi Malaysia Kuala Lumpur Malaysia

Plant disease classification using machine learning in a real agricultural field environment is a difficult task. Often, an automated plant disease diagnosis method might fail to capture and interpret discriminatory information due to small variations among leaf sub-categories. Yet, modern Convolutional Neural Networks (CNNs) have achieved decent success in discriminating various plant diseases using leave images. A few existing methods have applied additional pre-processing modules or sub-networks to tackle this challenge. Sometimes, the feature maps ignore partial information for holistic description by part-mining. A deep CNN that emphasizes integration of partial descriptiveness of leaf regions is proposed in this work. The efficacious attention mechanism is integrated with high-level feature map of a base CNN for enhancing feature representation. The proposed method focuses on important diseased areas in leaves, and employs an attention weighting scheme for utilizing useful neighborhood information. The proposed Attention-based network for Plant Disease Classification (APDC) method has achieved state-of-the-art performances on four public plant datasets containing visual/thermal images. The best top-1 accuracies attained by the proposed APDC are: PlantPathology 97.74%, PaddyCrop 99.62%, PaddyDoctor 99.65%, and PlantVillage 99.97%. These results justify the suitability of proposed method. © 2024 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Strategy for Rapid Diabetic Retinopathy Exposure Based on Enhanced Feature Extraction Processing

引用

computers, Materials & Continua 2023年第6期75卷 5597-5613页

作者： V.Banupriya S.Anusuya Department of Computer Science and Business Systems M.Kumarasamy College of EngineeringKarur639113TamilnaduIndia Department of Information Technology Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSIMATSChennai602117Tamil NaduIndia

In the modern world,one of the most severe eye infections brought on by diabetes is known as diabetic retinopathy(DR),which will result in retinal damage,and,thus,lead to *** retinopathy(DR)can be well treated with early *** fundus images of humans are used to screen for lesions in the ***,detecting DR in the early stages is challenging due to the minimal ***,the occurrence of diseases linked to vascular anomalies brought on by DR aids in diagnosing the ***,the resources required for manually identifying the lesions are ***,training for Convolutional Neural Networks(CNN)is more *** proposed research aims to improve diabetic retinopathy diagnosis by developing an enhanced deep learning model(EDLM)for timely DR identification that is potentially more accurate than existing CNN-based *** proposed model will detect various lesions from retinal images in the early ***,characteristics are retrieved from the retinal fundus picture and put into the EDLM for *** dimensionality reduction,EDLM is ***,the classification and feature extraction processes are optimized using the stochastic gradient descent(SGD)*** EDLM’s effectiveness is assessed on the KAG-GLE dataset with 3459 retinal images,and results are compared over VGG16,VGG19,RESNET18,RESNET34,and *** results show that the EDLM achieves higher average sensitivity by 8.28%for VGG16,by 7.03%for VGG19,by 5.58%for ResNet18,by 4.26%for ResNet 34,and by 2.04%for ResNet 50,respectively.

关键词： Diabetic retinopathy deep learning classification retinal fundus

来源：评论

学校读者我要写书评

暂无评论

CRAFT: Criticality-Aware Fault-Tolerance Enhancement Techniques for Emerging Memories-Based Deep Neural Networks

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2023年第10期42卷 3289-3300页

作者： Nguyen, Thai-Hoang Imran, Muhammad Choi, Jaehyuk Yang, Joon-Sung Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical Engineering School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad44000 Pakistan Department of Semiconductor Systems Engineering Sungkyunkwan University Suwon16419 Korea Republic of School of Electrical and Electronic Engineering Department of System Semiconductor Engineering Yonsei University Seoul03722 Korea Republic of

Deep neural networks (DNNs) have emerged as the most effective programming paradigm for computer vision and natural language processing applications. With the rapid development of DNNs, efficient hardware architectures for deploying DNN-based applications on edge devices have been extensively studied. Emerging nonvolatile memories (NVMs), with their better scalability, nonvolatility, and good read performance, are found to be promising candidates for deploying DNNs. However, despite the promise, emerging NVMs often suffer from reliability issues, such as stuck-at faults, which decrease the chip yield/memory lifetime and severely impact the accuracy of DNNs. A stuck-at cell can be read but not reprogrammed, thus, stuck-at faults in NVMs may or may not result in errors depending on the data to be stored. By reducing the number of errors caused by stuck-at faults, the reliability of a DNN-based system can be enhanced. This article proposes CRAFT, i.e., criticality-aware fault-tolerance enhancement techniques to enhance the reliability of NVM-based DNNs in the presence of stuck-at faults. A data block remapping technique is used to reduce the impact of stuck-at faults on DNNs accuracy. Additionally, by performing bit-level criticality analysis on various DNNs, the critical-bit positions in network parameters that can significantly impact the accuracy are identified. Based on this analysis, we propose an encoding method which effectively swaps the critical bit positions with that of noncritical bits when more errors (due to stuck-at faults) are present in the critical bits. Experiments of CRAFT architecture with various DNN models indicate that the robustness of a DNN against stuck-at faults can be enhanced by up to 105 times on the CIFAR-10 dataset and up to 29 times on ImageNet dataset with only a minimal amount of storage overhead, i.e., 1.17%. Being orthogonal, CRAFT can be integrated with existing fault-tolerance schemes to further enhance the robustness of DNNs aga

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Proportional Fairness Based Energy Efficient Routing in Wireless Sensor Network

引用

computer systems science & engineering 2022年第6期41卷 1071-1082页

作者： Abolfazl Mehbodniya Surbhi Bhatia Arwa Mashat Mohanraj Elangovan Sudhakar Sengan Department of Electronics and Communications Engineering Kuwait College of Science and TechnologyKuwait Department of Information Systems College of Computer Sciences and Information TechnologyKing Faisal UniversitySaudi Arabia Department of Information Systems College of Computing and Information TechnologyKing Abdulaziz UniversityRabighSaudi Arabia Department of Computer Science and Engineering K.S.Rangasamy College of TechnologyTiruchengode637215Tamil NaduIndia Department of Computer Science and Engineering PSN College of Engineering and TechnologyTirunelveli627152Tamil NaduIndia

Wireless Sensor Network (WSN) is an independent device that comprises a discrete collection of Sensor Nodes (SN) to sense environmental positions,device monitoring, and collection of information. Due to limited energy resourcesavailable at SN, the primary issue is to present an energy-efficient framework andconserve the energy while constructing a route path along with each sensor ***, many energy-efficient techniques focused drastically on energy harvesting and reduced energy consumption but failed to support energy-efficient routingwith minimal energy consumption in WSN. This paper presents an energy-efficientrouting system called Energy-aware Proportional Fairness Multi-user Routing(EPFMR) framework in WSN. EPFMR is deployed in the WSN environment usingthe instance time. The request time sent for the route discovery is the foremost stepdesigned in the EPFMR framework to reduce the energy consumption rate. Theproportional fairness routing in WSN selects the best route path for the packet flowbased on the relationship between the periods of requests between different *** path discovered for packet flow also measure energy on multi-user route pathusing the Greedy Instance Fair Method (GIFM). The GIFM in EPFMR developsnode dependent energy-efficient localized route path, improving the *** energy-aware framework maximizes the throughput rate and performs experimental evaluation on factors such as energy consumption rate during routing,Throughput, RST, node density and average energy per packet in WSN. The RouteSearching Time (RST) is reduced using the Boltzmann Distribution (BD), and as aresult, the energy is minimized on multi-user WSN. Finally, GIFM applies aninstance time difference-based route searching on WSN to attain an optimal energyminimization system. Experimental analysis shows that the EPFMR framework canreduce the RST by 23.47% and improve the throughput by 6.79% compared withthe state-of-the-art works.

关键词： Wireless sensor network proportional fairness multi-user routing energy consumption greedy instance fair Boltzmann distribution

来源：评论

学校读者我要写书评

暂无评论

Hybrid Grey Wolf and Dipper Throated Optimization in Network Intrusion Detection systems

引用

computers, Materials & Continua 2023年第2期74卷 2695-2709页

作者： Reem Alkanhel Doaa Sami Khafaga El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Rashid Amin Mostafa Abotaleb B.M.El-den Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science University of Engineering and TechnologyTaxilaPakistan Department of System Programming South Ural State UniversityChelyabinsk454080Russia

The Internet of Things(IoT)is a modern approach that enables connection with a wide variety of devices *** to the resource constraints and open nature of IoT nodes,the routing protocol for low power and lossy(RPL)networks may be vulnerable to several routing ***’s why a network intrusion detection system(NIDS)is needed to guard against routing assaults on RPL-based IoT *** imbalance between the false and valid attacks in the training set degrades the performance of machine learning employed to detect network ***,we propose in this paper a novel approach to balance the dataset classes based on metaheuristic optimization applied to locality-sensitive hashing and synthetic minority oversampling technique(LSH-SMOTE).The proposed optimization approach is based on a new hybrid between the grey wolf and dipper throated optimization *** prove the effectiveness of the proposed approach,a set of experiments were conducted to evaluate the performance of NIDS for three cases,namely,detection without dataset balancing,detection with SMOTE balancing,and detection with the proposed optimized LSHSOMTE *** results showed that the proposed approach outperforms the other approaches and could boost the detection *** addition,a statistical analysis is performed to study the significance and stability of the proposed *** conducted experiments include seven different types of attack cases in the RPL-NIDS17 *** on the 2696 CMC,2023,vol.74,no.2 proposed approach,the achieved accuracy is(98.1%),sensitivity is(97.8%),and specificity is(98.8%).

关键词： Metaheuristics grey wolf optimization dipper throated optimization dataset balancing locality sensitive hashing SMOTE

来源：评论

学校读者我要写书评

暂无评论

Snippet Policy Network V2: Knee-Guided Neuroevolution for Multi-Lead ECG Early Classification

引用

IEEE Transactions on Neural Networks and Learning systems 2024年第2期35卷 2167-2181页

作者： Huang, Yu Yen, Gary G. Tseng, Vincent S. National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States National Chung Hsing University Department of Management Information Systems Taichung402 Taiwan

Early time series classification predicts the class label of a given time series before it is completely observed. In time-critical applications, such as arrhythmia monitoring in ICU, early treatment contributes to the patient's fast recovery, and early warning could even save lives. Hence, in these cases, it is worthy of trading, to some extent, classification accuracy in favor of earlier decisions when the time series data are collected over time. In this article, we propose a novel deep reinforcement learning-based framework, snippet policy network V2 (SPN-V2), for long and varied-length multi-lead electrocardiogram (ECG) early classification. The proposed SNP-V2 contains two main components: snippet representation learning (SRL) and early classification timing learning (ECTL). The SRL is proposed to encode inner-snippet spatial correlations and inter-snippet temporal correlations into the hidden representations of the subsegment (snippet) of the input ECG. ECTL aims to learn a decision agent to classify the time series early and accurately. To optimize the proposed framework, we design a novel knee-guided neuroevolution algorithm (KGNA) to solve cardiovascular diseases' early classification problem, automatically optimizing the proposed SPN-V2 regarding the tradeoff between accuracy and earliness. In addition, we conduct a series of experiments on two real-world ECG datasets. The experimental results show the superiority of the proposed algorithm over the state-of-the-art competing methods. © 2012 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Employing Feature engineering for River Stage Forecasting to Improve Hybrid Model Performance 32

Employing Feature Engineering for River Stage Forecasting to...

引用

32nd International Conference on Software, Telecommunications and computer Networks, SoftCOM 2024

作者： Mihel, Anna Maria Pecnik, Spela Vrbancic, Grega Lerga, Jonatan Krvavica, Nino University of Rijeka Faculty of Engineering Department of Computer Engineering Rijeka Croatia University of Maribor Intelligent Systems Laboratory Faculty of Electrical Engineering and Computer Science Maribor Slovenia University of Rijeka Faculty of Civil Engineering Department of Hydrotechnics and Geotechnics Rijeka Croatia

ISBN: (纸本)9789532901382

Establishing early warning systems and efficient management of water resources in tidal reaches is crucial for achieving adequate flood protection. In tidal reaches, the river stage interacts non-linearly with tides (downstream) and discharge (upstream), making the modeling of river processes extremely complex. Data-driven methods have proven helpful for predicting the river stage parameter. This contrasts with existing numerical approaches, which suffer from several limitations. The aim of this study was to predict the river stage of the upstream part of the tidal river, where the influence of salinity is present during the summer months. Using the CNN-LSTM model trained on historical records of the discharge (station of the variable to be predicted), the river stage of three downstream stations, and the point of interest, the prediction was carried out up to 24 hours in advance. By incorporating feature engineering, we achieved an improvement in model results for the longest horizon, confirmed by standard performance metrics, and considered it efficient and effective for risk mitigation. Introducing feature engineering into the data preprocessing resulted in a predictive performance improvement of 0.98% for the Nash-Sutcliffe Efficiency (NSE) metric, 7.0% for the root mean squared error (RMSE) metric, and 7.25% for the mean absolute error (MAE) metric over the second and third-best scenarios using a spectrogram and time-series data. © 2024 University of Split, FESB.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Three-Dimensional Real-Time Gait-Based Age Detection System Using Machine Learning

引用

computers, Materials & Continua 2023年第4期75卷 165-182页

作者： Muhammad Azhar Sehat Ullah Khalil Ullah Habib Shah Abdallah Namoun Khaliq Ur Rahman Department of Computer Science&IT University of MalakandChakdara18800Pakistan Department of Software Engineering University of MalakandChakdara18800Pakistan College of Computer Science King Khalid UniversityAbha62529Saudi Arabia Faculty of Computer and Information Systems Islamic University of MadinahMadinah42351Saudi Arabia Department of Statistics Abdul Wali Khan UniversityMardan23200Pakistan

Human biometric analysis has gotten much attention due to itswidespread use in different research areas, such as security, surveillance,health, human identification, and classification. Human gait is one of the keyhuman traits that can identify and classify humans based on their age, gender,and ethnicity. Different approaches have been proposed for the estimation ofhuman age based on gait so far. However, challenges are there, for which anefficient, low-cost technique or algorithm is needed. In this paper, we proposea three-dimensional real-time gait-based age detection system using a machinelearning approach. The proposed system consists of training and testingphases. The proposed training phase consists of gait features extraction usingthe Microsoft Kinect (MS Kinect) controller, dataset generation based onjoints’ position, pre-processing of gait features, feature selection by calculatingthe Standard error and Standard deviation of the arithmetic mean and bestmodel selection using R2 and adjusted R2 techniques. T-test and ANOVAtechniques show that nine joints (right shoulder, right elbow, right hand, leftknee, right knee, right ankle, left ankle, left, and right foot) are statisticallysignificant at a 5% level of significance for age estimation. The proposedtesting phase correctly predicts the age of a walking person using the resultsobtained from the training phase. The proposed approach is evaluated on thedata that is experimentally recorded from the user in a real-time *** (50) volunteers of different ages participated in the experimental *** the limited features, the proposed method estimates the age with 98.0%accuracy on experimental images acquired in real-time via a classical generallinear regression model.

关键词： Age estimation gait biometrics classical linear regression model

来源：评论

学校读者我要写书评

暂无评论

Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4893-4904页

作者： Liu, Yexin Zhang, Weiming Zhao, Guoyang Zhu, Jinjing Vasilakos, Athanasios V. Wang, Lin Robotics and Autonomous Systems Thrust Guangzhou511458 China Grimstad4879 Norway Artificial Intelligence Thrust Guangzhou511458 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong999077 Hong Kong

The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for color-thermal semantic segmentation. However, it is essentially hampered by two critical problems: 1) the day-night gap of color images is larger than that of thermal images;and 2) the classwise performance of color images at night is not consistently higher or lower than that of thermal images. We propose the first test-time adaptation (TTA) framework, dubbed Night-TTA, to address the problems for nighttime color-thermal semantic segmentation without access to the source (daytime) data during adaptation. Our method enjoys three key technical parts. First, as one modality (e.g., color) suffers from a larger domain gap than that of the other (e.g., thermal), imaging heterogeneity refinement (IHR) employs an interaction branch on the basis of color and thermal branches to prevent cross-modal discrepancy and performance degradation. Then, class aware refinement (CAR) is introduced to obtain reliable ensemble logits based on pixel-level distribution aggregation of the three branches. In addition, we also design a specific learning scheme for our TTA framework, which enables the ensemble logits and three student logits to collaboratively learn to improve the quality of predictions during the testing phase of our Night-TTA. Extensive experiments show that our method achieves state-of-the-art (SoTA) performance with a 13.07% boost in mean intersection over union (mIoU). © 2020 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

FOOTBALLTrace: An AI-Based System for Football Player Tracking with Occlusion Detection and Trajectory Correction 11

FOOTBALLTrace: An AI-Based System for Football Player Tracki...

引用

11th International Conference on Sport sciences Research and Technology Support, icSPORTS 2023

作者： Mostafa, Abdelrahman H. Rushdi, Muhammad A. Basha, Tamer A. Sayed, Khaled Department of Systems and Biomedical Engineering Faculty of Engineering Cairo University Giza Egypt Department of Computer Science New Giza University Giza Egypt Department of Electrical and Computer Engineering and Computer Science University of New Haven West HavenCT United States

ISBN: (纸本)9789897586736

Data analytics have had a significant impact on tactical and workload planning in football. Football data is divided into two categories: event data, which captures on-the-ball events like passes and shots, and tracking data, which captures off-the-ball movements. However, traditional methods of collecting tracking data are expensive and inconvenient. Recently, AI solutions have emerged as low-cost and user-friendly alternatives to track players' movements from video streams. This paper introduces FOOTBALLTrace, an end-to-end AI system for tracking multiple football players from a panoramic game view. The system also incorporates a novel algorithm that detects potential occlusion events and ensures trajectory continuity for occluded players. The workflow involves five stages: panoramic view creation, player detection, player ID association, occlusion detection, and trajectory correction. The system utilizes YOLOv7 for multiple object detection and employs a pre-trained deep affinity network to assign unique IDs to players throughout the game. Occlusion detection and trajectory correction are achieved by extracting geometric features from discontinuous player trajectories. The system's performance was evaluated on full-length video data of a football game, with occlusion events manually extracted for training and testing the occlusion detection and trajectory correction algorithm. The system achieved an 87.5% trajectory correction rate for occluded trajectories. © 2023 by SCITEPRESS – science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： Trajectories

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：