检索结果-内蒙古大学图书馆

OTP-NMS: Toward Optimal Threshold prediction of NMS for Crowded Pedestrian Detection

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 3176-3187页

作者： Tang, Yi Liu, Min Li, Baopu Wang, Yaonan Ouyang, Wanli Hunan Univ Coll Elect & Informat Engn Changsha 410082 Peoples R China Natl Engn Res Ctr Robot Visual Percept & Control T Changsha 410082 Peoples R China Oracle Pleasanton CA 94588 USA Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

Pedestrian detection is still a challenging task for computer vision, especially in crowded scenes where the overlaps between pedestrians tend to be large. The non-maximum suppression (NMS) plays an important role in removing the redundant false positive detection proposals while retaining the true positive detection proposals. However, the highly overlapped results may be suppressed if the threshold of NMS is lower. Meanwhile, a higher threshold of NMS will introduce a larger number of false positive results. To solve this problem, we propose an optimal threshold prediction (OTP) based NMS method that predicts a suitable threshold of NMS for each human instance. First, a visibility estimation module is designed to obtain the visibility ratio. Then, we propose a threshold prediction subnet to determine the optimal threshold of NMS automatically according to the visibility ratio and classification score. Finally, we re-formulate the objective function of the subnet and utilize the reward-guided gradient estimation algorithm to update the subnet. Comprehensive experiments on CrowdHuman and CityPersons show the superior performance of the proposed method in pedestrian detection, especially in crowded scenes.

关键词： Estimation Correlation Proposals Detectors Task analysis Standards prediction algorithms Pedestrian detection non-maximum suppression gradient estimation

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of Machine Learning algorithms for Agricultural Crop prediction

An Empirical Analysis of Machine Learning Algorithms for Agr...

引用

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

作者： Ujwal Pai Jakarbet Suhas S P Savithramma R M Ashwini B P Department of CSE Siddaganga Institute of Technology Visvesvaraya Technological University Tumakuru Karnataka India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

In recent years, machine learning has rightfully claimed its position across multiple industries, streamlining various aspects of daily life. With the growing need for sustainable agricultural practices, there is a rising request for advanced decision-making machines that can boost crop productivity while reducing resource consumption. This study digs deeper into the use of machine learning algorithms to create an intelligent crop recommendation system. Many researchers globally are focusing on this challenge. By leveraging diverse datasets from Kaggle, covering factors such as soil and climate conditions. This research aims to suggest suitable machine learning model for implementing crop-prediction application which in-turn provide farmers with data-driven insights to make optimal crop selection decisions. Several ML algorithms, including Linear Regression, Naïve Bayes, Lasso Regression, Support Vector Regression (SVR), Decision Tree, Random Forest, K-Nearest Neighbors (k-NN), and Gradient Boosted Regression Trees (GBRT), were assessed for their ability to predict suitable crops based on environmental parameters. The models were trained and validated using Indian climatic conditions-based data. Among these, the Random Forest algorithm performed the best, achieving 96% accuracy based on the R2 score.

关键词： Support vector machines Productivity Machine learning algorithms Crops Soil Nearest neighbor methods prediction algorithms Random forests Regression tree analysis Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Diabetes prediction: A Comparative Analysis of Machine Learning algorithms with SMOTE

Diabetes Prediction: A Comparative Analysis of Machine Learn...

引用

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Shoyeb Mahmud Baki Ul Islam Nazmul Haque Anik Tonmoy Ghosh Dept. of EEE Pabna University of Science and Technology Pabna Bangladesh Dept. of ECE University of Alabama Tuscaloosa AL USA

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

This paper conducts a comprehensive investigation into diabetes prediction utilizing diverse machine-learning algorithms, including Random Forest, Ada Boost, Gradient Tree Boosting, Gaussian Naive Bayes, SVM, and KNN. The principle goal is to identify the best and sustainable algorithm for diabetes prediction by evaluating their performance on a dataset of 100,000 samples. Predictor attributes encompass gender, age, BMI, hypertension, smoking history, etc. Performance evaluations employed a 5-fold cross-validation method. Due to class imbalance, a Synthetic Minority Over-sampling Technique (SMOTE) was implemented for classifier training. The best performance was achieved using SMOTE and the Gradient Tree Boosting classifier, attaining an accuracy of 96.99%, precision of 91.99%, recall of 70.76%, and F1 score of 79.975%. This proposed approach demonstrates significant advancement in diabetes prediction, contributing valuable insights for optimizing machine learning models in healthcare applications.

关键词： Machine learning algorithms Medical services Predictive models prediction algorithms Boosting Diabetes Classification algorithms Random forests Medical diagnostic imaging Context modeling

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning algorithms in Fish Survival prediction

Comparative Analysis of Machine Learning Algorithms in Fish ...

引用

Bangalore Humanitarian Technology Conference (B-HTC), IEEE

作者： Rudresh D. Shirwaikar Lyzandra D’Souza Anirudh Santosh Bhangle Sarang Deepak Joshi Nupur Ajit Jathar Jonathan Elroy Alvares Department of Computer Engineering Agnel Institute of Technology and Design Mapusa India

ISBN: (数字)9798350344509

ISBN: (纸本)9798350344516

This research paper conducts an exploration of prevalent machine learning classification algorithms, emphasizing the refinement of Random Forest models to optimize performance. The initial phase involves a comparative analysis of Random Forest, k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Logistic Regression, and Naive Bayes Classification algorithms across the dataset, resulting in Random forest to be best performed among all with average accuracy of 61%. Subsequently, then we focus on enhancement of the Random Forest algorithm with random train-test split dataset, resulting in an enhanced average accuracy of 65% which is about 4% improvement to the previous accuracy and choosing the best traintest split dataset, along with fine tuning the model, improved the average accuracy to 73% which is about 12% improvement to previous accuracy which is significantly higher showcasing the significance of precise algorithmic tuning. The completion of our investigation lies in the creation of an integrated model which incorporates multiple Random Forest classifier models, each specifically trained for binary class classification, along with a comprehensive model designed for multiclass classification. This combined model excels with a peak accuracy of 82.75% for the best split, demonstrating its strong performance in classification tasks. This research not only contributes to the theoretical understanding of algorithm performance and optimization but also offers practical insights for the application of machine learning in challenging classification scenarios.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms prediction algorithms Classification algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

Early Diabetes prediction using Machine Learning algorithms

Early Diabetes Prediction using Machine Learning Algorithms

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Riya Sinha Bandi Sai Vennela S. Babu Department of Computing Technologies SRM Institute of Science & Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

A chronic metabolic illness called “Diabetes mellitus”, with its rising prevalence and related consequences, poses a serious threat to global health. Early diabetes detection is essential for prompt intervention and efficient care, which lowers the risk of complications. Machine learning approaches have recently become more popular in the healthcare industry due to their capacity to analyze big datasets and uncover insightful patterns. This work suggests a thorough strategy for predicting early diabetes using machine learning *** construction and assessment of predictive models based on various clinical and lifestyle parameters is the main goal of the study. An individual’s dietary preferences, medical history, and patterns of physical activity are all included in the dataset. The most pertinent variables are found using feature selection approaches, which improves the prediction models’ precision and effectiveness. The importance of several machine learning methods, such as decision trees, neural networks, SVM in predicting diabetes is tested.

关键词： Support vector machines Machine learning algorithms Accuracy Neural networks Medical services Predictive models prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Conflict Area prediction for Boosting Search-Based Multi-Agent Pathfinding algorithms

Conflict Area Prediction for Boosting Search-Based Multi-Age...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jaesung Ryu Youngjoon Kwon Sangho Yoon Kyungjae Lee Department of Artificial Intelligence Chung-Ang University Seoul Republic of Korea

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We address the challenge of efficiently controlling multi-agent systems, crucial in fields like logistics and traffic management. We propose a novel approach that combines learning-based techniques with search-based methods, focusing on enhancing the conflict-based search (CBS). The CBS ensures optimality but suffers from increasing complexity as agents or maps grow. To tackle this, we leverage learning-based approaches to enhance computational efficiency. By training a conflict area prediction (CAP) network, we anticipate potential conflict areas, allowing for low-level path planners to explore conflict-free paths. Our experiments demonstrate the effectiveness of our method in reducing computational demands compared to existing approaches.

关键词： Training Learning systems Deep learning Neural networks Focusing prediction algorithms Search problems

来源：评论

学校读者我要写书评

暂无评论

prediction of Breast Cancer Using Simple Machine Learning algorithms

Prediction of Breast Cancer Using Simple Machine Learning Al...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Seeta Devi Dipali Dumbre Ranjana Chavan Symbiosis College of Nursing (SCON) Symbiosis International (Deemed University) (SIU) Pune India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Breast cancer is a significant cause of morbidity and mortality among women, especially in developing countries. Early prediction, and accurate treatment are critical to reduce death rates. Using artificial intelligence and machine learning techniques, this project will evaluate the performance of several models in predicting breast cancer. The prediction models such as Decision Tree, Gradient Boosting, Naïve Bayes, Neural Network, SGD, kNN, and CN 2 rule inducer are employed utilizing Orange tools. This study used publicly accessible secondary data from Keggle, enabling transparency and accessibility in the evaluation approach. The findings disply that the DT, GB, Neural Network, and CN2 rule inducer had higher accuracy ratings of $0.992,0.998,0.997$, and 0.997, respectively, with exceptional AUC values of $0.989,1.000,1.000$, and 0.990. Additionally, their recall and accuracy scores are 0.992, $0.987,0.998$, and 0.997, demonstrating their strong performance in breast cancer prediction. Among the most popular classifier models, GB and Neural Network, are the outperformed models than others.

关键词： Accuracy Machine learning algorithms Computational modeling Neural networks Predictive models Developing countries prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Heart Disease prediction Using Machine Learning algorithms

Heart Disease Prediction Using Machine Learning Algorithms

引用

Knowledge Engineering and Communication Systems (ICKECS), International Conference on

作者： Poreddy AmoghVarshith Dontamsetti Harika Paluri Priyanka S Sujit Kumar D. Haritha Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

This study investigates the efficacy of various machine intelligence algorithms in predicting congestive heart failure risk using a comprehensive dataset. The algorithms studied include Decision Trees, Random Forests, Support Vector Machines, Logistic Regression, K Nearest Neighbors, and Convolutional Neural Networks (CNN). Results reveal varying levels of effectiveness, with Random Forests demonstrating notable accuracy and reliability in predicting risk. CNNs excel in capturing complex relationships within the dataset, occasionally surpassing Random Forests in accuracy. Support Vector Machines and Logistic Regression also exhibit commendable performance in assessing coronary thrombosis risk.

关键词： Heart Support vector machines Logistic regression Machine learning algorithms Accuracy Nearest neighbor methods prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Validating ML algorithms for efficient Breast Cancer prediction using K-fold

Validating ML algorithms for efficient Breast Cancer Predict...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： P. Asha J. Refonaa S. L. Jany Shabu Janapati Karthik A. Harsha Vardhan L. Padma Suresh Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Computer Science and Engineering Baselios Mathews II College of Engineering Kollam India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Breast cancer has always been a disease that affects a lot of people. There is vast range of factors that may lead to breast cancer and this makes it more difficult to detect at an early stage. The tissues called benign or malignant present in the breast profile are so identical that it makes detecting cancer very complex for the doctors. Performing various tests like uniformity of cell shape and thickness of tissues may result in no valuable insights. This gives rise to machine learning and artificial intelligence that can be used in the prognosis of breast cancer. Here we attempt at correlating diverse machine learning algorithms to effectively predict breast cancer over a dataset. The five diverse machine learning algorithms employed are Naïve Bayes, Decision Tree, Neural Networks (Multilayer Perceptron), SVM and K-nearest Neighbour. An effective comparative study has been done to filter out the best Algorithm based on their Performance.

关键词： Support vector machines Machine learning algorithms Shape Neural networks Multilayer perceptrons prediction algorithms Breast cancer

来源：评论

学校读者我要写书评

暂无评论

A Study on the Thermal Deformation prediction Model of a Motorized Spindle Based on Swarm Intelligence Optimization algorithms

A Study on the Thermal Deformation Prediction Model of a Mot...

引用

International Conference on Information Systems and Computer Aided Education (ICISCAE)

作者： Wei Wei Ruizhe Wang Department of Information and Control Engineering Shenyang Institute of Science and Technology Shenyang China School of Electrical Engineering Suihua University Suihua China

ISBN: (数字)9798350350760

ISBN: (纸本)9798350350777

Thermal deformation of the motorized spindle significantly impacts the machining accuracy of CNC machine tools. The thermal expansion coefficient, a critical parameter affecting thermal deformation, is highly nonlinear, making it challenging to determine an accurate coefficient that enhances machining precision. This study proposes a thermal deformation model for the motorized spindle based on an improved Grasshopper Optimization Algorithm, aimed at optimizing the thermal expansion coefficient. Experimental studies were conducted on the motorized spindle at various rotational speeds. The results demonstrate that the thermal expansion coefficient obtained using the improved Grasshopper Optimization Algorithm yields more accurate predictions of thermal deformation, with smaller errors compared to actual measurements, than those obtained using an empirical thermal expansion coefficient.

关键词： Deformable models Thermal expansion Accuracy Deformation Velocity control Machining prediction algorithms Machine tools Finite element analysis 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：