检索结果-内蒙古大学图书馆

Weedspedia: Deep Learning-Based Approach for Weed Detection using R-CNN, YoloV3 and Centernet

Weedspedia: Deep Learning-Based Approach for Weed Detection ...

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Sneha, N. Sundaram, Meenakshi Ranjan, Rajeev Abhishek Reva University School of Computer Science and Engineering Bengaluru India Reva University School of Computer Science and Applications India Reva University School of Csa Bengaluru India

ISBN: (纸本)9798350314946

Weed identification is a crucial undertaking in agriculture, where management and identification of weed growth in fields need to be addressed through deep learning algorithms. This study uses the Region-Based Convolutional Neural Network (R-CNN), Yolo, and Centernet object recognition algorithms to identify objects in images. This study also proposes a novel method for weed identification based on weed size. Numerous image-processing applications, including those for healthcare, traffic analysis, and agriculture, frequently use R-CNN. The suggested technique provides a practical and affordable answer for weed identification in precision agriculture. Herbicide use by farmers can be reduced as a result of being able to more precisely identify and control weed growth. Identification of weeds aids in weed growth control, which can harm natural ecosystems, compete with crops, diminish yields, and increase maintenance costs. The methodology of measuring the length and breadth of a weed detected by R-CNN requires extra processing stages, which aid in understanding the growth and subsequent steps required to eliminate weeds dependent on the growth of the weeds. Researchers often begin by gathering a sizable collection of photos of various weed species to construct a deep learning model for weed identification. The paper focus on identification of weed using 3 pre trained models followed by growth prediction to take necessary steps in agricultural land. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction using Feature Selection and Classification with XGBoost

Breast Cancer Prediction using Feature Selection and Classif...

引用

2023 IEEE International Conference on Recent Trends in Electronics and Communication, ICRTEC 2023

作者： Haarika, Raye Babu, Tina Nair, Rekha R. Rajesh, T.M. Bengaluru India School of Engineering Dayananda Sagar University Department of Computer Science and Engineering Bengaluru India School of Engineering Dayananda Sagar University Department of Computer Applications Bengaluru India

ISBN: (纸本)9798350396195

As a result of high population growth, medical research and early sickness identification has become a responsibility. As the inhabitants grows, the likelihood of succumbing to breast cancer rises. A illness detection system that's automated reduces the danger of mortality, provides dependable, efficient, and rapid reaction, and assists doctors in disease diagnosis. to reinforce the predictive efficacy of current models and To estimate the risk of breast cancer, proposed model used Extreme Gradient Boosting (XGBoost) and compared it to Logistic Regression (LR), The Random Forest (RF), and Support Vector Machines (SVM). In this work, target picking the most weighted features using the XGBoost method and training the model with those features was performed. This approach yielded the identical accuracy as training the model with all features, however training the model with all features takes longer. The suggested approach has produced findings that are comparable and may help radiologists provide opinions © 2023 IEEE.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

An Adaptive-based Predicted Nodes Behavior Algorithm in Flying Ad Hoc Networks 5

An Adaptive-based Predicted Nodes Behavior Algorithm in Flyi...

引用

5th International Conference on Smart Systems and Inventive Technology, ICSSIT 2023

作者： Aruna, Orchu Sharma, Amit Vasireddy Venkatadri Institute of Technology Computer Science and Engineering AP India Lovely Professional University School of Computer Applications Andhra Pradesh India

ISBN: (纸本)9781665474672

This paper discusses implementing unmanned aerial vehicles (UAVs) for various military & civil parts with the creation of flying ad-hoc networks (FANETs), as recent applications include remote aerial nodes. Communication among UAVs in FANETs must be flexible, dependable, and delay-bounded so that network can continue to provide the needed level of service while also accommodating the ever-increasing number of UAVs. Data routing between UAVs in a FANET is much more complex than in a MANET due to the more significant mobility requirements of the former. Modifications to the network's topology need real-time adjustments to the routing tables. FANET provides a reliable connection between UAVs by ignoring metric computations of most current routing algorithms. Due to the extreme mobility of nodes in FANET, route reliability is also a significant issue. Based on these findings, this study presents PF-WGTR, a novel routing method. A consistent routine route is determined using a weighted algorithm that predicts the future values of specific parameters at each node in a FANH F. The suggested routing method uses each node's predicted future value to determine the node's weight within the network. This enables the communication nodes to set up a dedicated and stable route over a lengthy period. This dynamic routing system optimizes energy usage by looking ahead and making predictions. It reduces the amount of data lost in transit while maintaining the same or greater throughput than current routing protocols. The proposed protocol PF-WGTR could achieve laetter results than others hised on the valuation of simulation results. © 2023 IEEE.

关键词： Military vehicles

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Assessment Using Hybrid Neuro-Fuzzy Model

引用

computer Systems science & engineering 2022年第6期41卷 891-902页

作者： Parul Gandhi Mohammad Zubair Khan Ravi Kumar Sharma Omar H.Alhazmi Surbhi Bhatia Chinmay Chakraborty Department of Computer Applications Manav Rachna International Institute of Research and StudiesFaridabad121006India Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinahSaudi Arabia Department of Computer Applications Chandigarh Group of CollegesLandran140307India College of Computer Sciences and Information Technology King Faisal UniversitySaudi Arabia Department of Electronics&Communication Engineering Birla Institute of TechnologyMesra JharkhandIndia

Software reliability is the primary concern of software developmentorganizations, and the exponentially increasing demand for reliable softwarerequires modeling techniques to be developed in the present era. Small unnoticeable drifts in the software can culminate into a disaster. Early removal of theseerrors helps the organization improve and enhance the software’s reliability andsave money, time, and effort. Many soft computing techniques are available toget solutions for critical problems but selecting the appropriate technique is abig challenge. This paper proposed an efficient algorithm that can be used forthe prediction of software reliability. The proposed algorithm is implementedusing a hybrid approach named Neuro-Fuzzy Inference System and has also beenapplied to test data. In this work, a comparison among different techniques of softcomputing has been performed. After testing and training the real time data withthe reliability prediction in terms of mean relative error and mean absolute relativeerror as 0.0060 and 0.0121, respectively, the claim has been verified. The resultsclaim that the proposed algorithm predicts attractive outcomes in terms of meanabsolute relative error plus mean relative error compared to the other existingmodels that justify the reliability prediction of the proposed model. Thus, thisnovel technique intends to make this model as simple as possible to improvethe software reliability.

关键词： Software quality reliability neural networks fuzzy logic neuro-fuzzy inference system

来源：评论

学校读者我要写书评

暂无评论

Prediction of Algae Growth: A Machine Learning Perspective 2023

Prediction of Algae Growth: A Machine Learning Perspective

引用

15th International Conference on Contemporary Computing, IC3 2023

作者： Tiwary, Sanjeeb Darshana, Subhashree Mohanty, Debabrata Dash, Adyasha Rupsa, Potnuru Barik, Rabindra K School of Computer Science Engineering Kalinga Institute of Industrial Technology Bhubaneswar India School of Computer Applications KIIT Deemed to Be University Bhubaneswar India

ISBN: (纸本)9798400700224

Algal blooms pose a significant threat to aquatic ecosystems and human health. To address this issue, this paper proposes a machine learning-based approach for predicting harmful algal blooms (HABs) by analyzing environmental features. Algae, as primary organic matter and oxygen producers, play a vital role in the biosphere. However, the exponential increase in algal growth worldwide poses significant challenges to economic development and long-term sustainability. The paper employs three popular machine learning algorithms: Artificial Neural Network (ANN), Gradient Boosting Decision Tree (GBDT), and Support Vector Machine (SVM) to predict algal blooms. The research utilizes real-time data from two locations: the Sassafras River in the United States Chesapeake Bay and Lake Okeechobee in Florida, USA. These locations have experienced frequent HABs due to factors like chemical runoff and nutrient-rich conditions. By analyzing the collected data, the paper identifies and selects the most important features to optimize the prediction models' accuracy. Preliminary results demonstrate promising accuracy in predicting algal growth and identifying key characteristics associated with HABs. These findings contribute to a better understanding of algal blooms and pave the way for effective mitigation strategies to combat this global environmental challenge. © 2023 ACM.

关键词： Algae

来源：评论

学校读者我要写书评

暂无评论

Object Detection in Real-Time Surveillance Using Deep Learning-Based YOLO Framework

Object Detection in Real-Time Surveillance Using Deep Learni...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Kukreti, Sanjeev Praveen, R.V.S. Bansal, Saloni Raju, Hemanth Singh, Navdeep Begum, Rowsonara Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India LTIMindtree Limited Telangana Hyderabad India GLA University Department of Computer Engineering and Applications Mathura India New Horizon College of Engineering Department of Mechanical Engineering Bangalore India Lovely Professional University Phagwara India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798331512965

The continual growth of the computer vision and artificial intelligence fields overtime have provided the basis for more efficient and accurate surveillance. This paper examines the use of YOLO, a deep learning model that is used in the detection of objects, for use in real-time surveillance systems. The added benefits of identifying and labeling multiple objects in a single pass forward makes YOLO ideal for real-time surveillance. Unlike other approaches to object detection such as region-based methods or methods with multiple stages of detection, YOLO cast object detection as a regression problem where boxes and class probabilities are predicted jointly. This leads to a far improved performance when compared with their slower counterparts without the sacrifice of precision. In this work, the YOLO model is finetuned on a large database of surveillance videos to improve object detection at low lighting and in the presence of occlusion and crowding. The developed system has a high detection speed and accuracy;the application areas will include uses such as security inspection, traffic regulation, and anomaly detection. This is done to affirm that using YOLO is more efficient and faster than the other object detection algorithms in real-time surveillance tasks. The results indicate directions for further improvements to guarantee public safety and improve efficient surveillance systems. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approaches for Stocks Price Prediction: A New Institutive Way of Neural Architecture Design

Hybrid Approaches for Stocks Price Prediction: A New Institu...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Sharma, Vikram Rakhra, Manik Sharma, Vikrant Sarkar, Tiyas Singh, Amanpreet Jairath, Kapil Lovely Professional University Department of Computer Science and Engineering Phagwara India Graphic Era Deemed to be University Department of Computer Science and Engineering Graphic Era Hill University Phagwara India Lovely Professional University School of Computer Science and Engineering Phagwara India Lovely Professional University Department of Computer Scienceand Applications Phagwara India Trinity College Department of Sciences Jalandhar India

ISBN: (纸本)9798350378092

Stock price prediction is a critical aspect of financial decision-making for both individual investors and institutions. Traditional methods such as ARIMA and deep learning techniques like ANNs, LSTM, and GRU have demonstrated effectiveness in forecasting stock prices but suffer from inherent limitations. In recent years, hybrid models have emerged as a promising approach to address these shortcomings. This research paper introduces and evaluates three novel hybrid models for stock price prediction. First model integrates GRU, LSTM, and attention mechanisms to leverage the strengths of each component. By employing attention mechanisms, the model can focus on relevant information, thereby enhancing prediction accuracy. The second model combines GRU and LSTM networks with attention mechanisms, incorporating additional architectural elements to further refine predictive capabilities. The third proposed model is a fusion of the first two, augmented with additional features and enhancements to achieve superior performance in stock price prediction tasks. Evaluation of these proposed models utilizes commonly used metrics to assess predictive accuracy and generalizability. The results demonstrate the effectiveness of the proposed hybrid approaches in improving stock price prediction performance. This research contributes to the advancement of stock price prediction methodologies by proposing innovative hybrid models, offering valuable tools for researchers and practitioners in the finance industry seeking enhanced forecasting accuracy and decision-making capabilities. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction 38

Long-Tailed Object Detection Pre-training: Dynamic Rebalanci...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Duan, Chen-Long Li, Yong Wei, Xiu-Shen Zhao, Lin Nanjing University of Science and Technology China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University China

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters, often fall short when confronted with long-tailed distributions, especially in detection tasks. This is largely due to extreme data imbalance and the issue of simplicity bias. In this paper, we introduce a novel pre-training framework for object detection, called Dynamic Rebalancing Contrastive Learning with Dual Reconstruction (2DRCL). Our method builds on a Holistic-Local Contrastive Learning mechanism, which aligns pre-training with object detection by capturing both global contextual semantics and detailed local patterns. To tackle the imbalance inherent in long-tailed data, we design a dynamic rebalancing strategy that adjusts the sampling of underrepresented instances throughout the pre-training process, ensuring better representation of tail classes. Moreover, Dual Reconstruction addresses simplicity bias by enforcing a reconstruction task aligned with the self-consistency principle, specifically benefiting underrepresented tail classes. Experiments on COCO and LVIS v1.0 datasets demonstrate the effectiveness of our method, particularly in improving the mAP/AP scores for tail classes. © 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

IoT-based System for Multi-Head Dual Attention Generative Adversarial Network-based Soil Nutrition and Plant Disease Detection in Smart Agriculture 8

IoT-based System for Multi-Head Dual Attention Generative Ad...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Shukla, Arvind Kumar Krishnaraj, Kowsalyadevi Venkatesh, R.J. Santhanalakshmi, M. Iftm University Department of Computer Applications Uttar Pradesh Moradabad India Sona College of Technology Department of Computer Science and Engineering Tamil Nadu Salem India Sri Venkateswara College of Engineering Department of Eee Tamil Nadu Chennai India Department of Computer Science and Engineering Tamil Nadu Dindigul India

ISBN: (纸本)9798350376425

The Internet of Things (IoT) has been increasingly popular in recent years due to its many uses. Regarding the agricultural industry, automated systems for identifying plant diseases offer mixed benefits and some drawbacks. Hence Multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) based plant disease detection in IoT is proposed. In order to address the absence of infrastructure in this area, the proposed approach seeks to identify stress to plants caused by crop diseases, environmental imbalance, and soil fertility. The proposed scheme uses nodes to capture plant leaf images, with a sink node collecting information from an automated module for IoT-based monitoring. The Combined Bilateral Parametric Filtering (CBPF) is used to pre-process the nodes' images so they are appropriate for the plant disease detection. After pre-processing, DenseNet201is proposed for extracting the Statistical features of the images. Then Multi-Head Dual Attention Generative Adversarial Network (MHDAGAN) is proposed for segmenting and classifying the plant leaf as healthy and disease. In order to improve the classification accuracy, Humboldt Squid Optimization Algorithm is proposed. Utilizing criteria such as sensitivity, accuracy, energy of nodes and specificity on various IoT environments, the detection performance is verified overall. According to the simulation findings, the suggested strategy performs better in terms of detection, with an accuracy of 99.46%. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

A quantitative investigation of immigrants integration and detention in Europe

引用

Quality and Quantity 2025年第1期59卷 253-274页

作者： Ballerini, Veronica Seri, Emiliano Department of Statistics Computer Science Applications “G. Parenti” University of Florence Florence Italy Department of Enterprise Engineering “Mario Lucertini” University of Rome Tor Vergata Rome Italy

In this paper, we question whether different attitudes of European countries’ policies toward migrant integration correspond to different propensities to hold foreigners in prison. As a first attempt to test the existence of such an association, we cluster 34 European countries for the year 2019, modelling the dimensions of the Migrant Integration Policy Index (MIPEX). Leveraging finite mixtures of multivariate Gaussian, we identify three groups of countries with a similar level of integration. Then, we estimate the relative proportion of foreigners held in prison among clusters, relying on UNODC and UNDESA data and exploiting Fisher’s noncentral hypergeometric (FNCH) model. We aim to introduce the FNCH model on clusters as a new quantitative tool to investigate demographic and social research issues. Results show that, in the less virtuous cluster in terms of migrants’ integration, foreigners are almost twice more exposed to detention than in the other clusters. Moreover, looking at the differences within clusters, we find that foreigners have a different propensity to be held in prison with respect to citizens. The proposed approach adds new valuable insights to the MIPEX and provides a novel perspective on an important and highly debated phenomenon, such as foreigners in prison, through the lenses of migrants’ integration. From a policymaking perspective, there emerges a need for more attention and further investigation on the paths underlying such an association between migrants’ integration and detention. To this aim, it is essential that countries enhance data collection and access, especially on migrant incarceration. © The Author(s) 2024.

关键词： Foreigners in prison MIPEX Model-based clustering Noncentral hypergeometric distribution Odds ratios

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：