检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Jeyarangani, J. Sumanth, Gorla Buchayyagari Raviram, Chakala Sreekanth, Mangala Venkata Srm Madurai College for Engineering and Technology Department of Infomration Technology Sivagangai India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Virudhunagar India

ISBN: (纸本)9798350308846

In a variety of problem domains, including sales, finance, healthcare, the stock market, etc., forecasting techniques are applied. The supermarket sales forecast aids in increasing sales in a professional setting. The method aids in problem-domain decision-making. Most supermarket chains estimate and evaluate sales for the following year using, at most, ad hoc techniques and technologies. Many issues remain unresolved as a result of using traditional statistical methods to anticipate grocery sales. Supermarkets are in need of accurate sales forecasts. Most supermarket chain stores, use informal strategies and methodologies to analyze and forecast sales. This is due to a lack of knowledge about optimizing the prediction result. In order to solve this problem, this study creates the most accurate model for forecasting product sales at the supermarket based on training and testing results. Three models are created in this study to forecast product sales in a supermarket. These models, which forecast product sales in supermarkets across branches, are trained using historical supermarket data collected in diverse places. It investigates and compares the three machine learning models - Random Forest, Decision Tree, and Linear regression for forecasting supermarket sales. This makes it easier for supermarkets to forecast product sales and helps them turn a profit. To identify the most accurate model, the prediction errors are computed. © 2023 IEEE.

关键词： Prediction regression algorithms Strategies and methodologies Supermarket sales

来源：评论

学校读者我要写书评

暂无评论

Advanced ML Techniques for Real-Time Air Quality Prediction in Megacities: A Comparative Study 2

Advanced ML Techniques for Real-Time Air Quality Prediction ...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Vignesh, U. Elakya, R. Selvi, R. Thanga Shanthana, S. School of Computer Science and Engineering Vellore Institute of Technology VIT- Kelambakkam - Vandalur Road Tamil Nadu Chennai India Information Technology Sri Venkateswara College of Engineering Sriperumbudur Chennai India Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Avadi Chennai India Rajalakshmi Institute of Technology Chennai India

ISBN: (纸本)9798350340235

It is impossible to imagine humans surviving without oxygen. Due to the recent developments in almost all aspects of civilization, air quality has continually decreased. The day-to-day industrial, transportation, and home activities produce harmful pollutants into our surroundings. Monitori ng and forecasting air quality have become crucial in the modern era, particularly in the developing countries like India. In comparison to more traditional methodologies, new prediction technologies based on machine learning have emerged as the most useful tools for analyzing those unique threats. The current study analyses air quality data from 23 Indian cities over a period of six years in order to make air quality projections. Correlation analysis is used to identify the most significant aspects of the dataset and to complete the preprocessing. Pollutants with a direct impact on the air quality index are identified using exploratory data analysis, which is used to identify hidden patterns in the dataset. Due to pandemic situation, almost all pollutants were greatly reduced in the year 2020. After addressing the data imbalance issue with a resampling method, five machine learning models are employed to predict air quality. There are comparisons between these models and the gold standard metrics. The Gaussi an Naive Bayes model has the highest accuracy, while the S upport Vector Machine model has the lowest. When compared to other existing models, XGBoost has the maximum linearity between the predicted and actual data. © 2023 IEEE.

关键词： Air quality prediction comparative analysis Environmental data Machine learning Real- time processing regression algorithms Sensor data Time-series data

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Temperature Prediction Using SVR Models

Atmospheric Temperature Prediction Using SVR Models

引用

2024 IEEE International Conference on Future Machine Learning and Data Science, FMLDS 2024

作者： Abdikov, Artem Flores, Bernardo San Jose State University Computer Engineering Department San JoseCA United States

ISBN: (纸本)9798350391213

The weather is the state of atmosphere that can be described with various categorical and quantitative parameters. A lot of everyday operations (ex: logistics) depend on these parameters and meteorologists all over the world are trying to predict them as accurately as they can. In this paper, one atmospheric temperature prediction method is proposed using Support Vector Regressor (SVR) Machine Learning model. This study goes through the preprocessing stages and features selection based on a realworld dataset, determining which features are predictable by SVR, proposed hyperparameters and other adjustments. Extensive tests were conducted which demonstrated the proposed solution's potential: the algorithm produces reasonable 1-day predictions with an acceptable margin of error considering the volatility of the matter. © 2024 IEEE.

关键词： Atmospheric Temperature Machine Learning regression algorithms Support Vector Regressor Time Series

来源：评论

学校读者我要写书评

暂无评论

Crop yield forecasting through novel machine learning dynamic ensemble selection techniques 15

Crop yield forecasting through novel machine learning dynami...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chanti, Suragali Vydehi, Kasichainula Penumatsa, Hima Keerthi Rao, K. Narayana Rao, Nynalasetti Kondala Kameswara Lakshmanarao, A. Gmr Institute of Technology Department of Cse A.P Rajam India Aditya University Department of Cse Surampalem India Gitam Department of Cse Vishakapatnam India Rise Krishna Sai Prakasam Group of Institutions Deparmtent of Cse Ongole India Sagi Rama Krishnam Raju Engineering College Department of Cse China Amiram Bhimavaram India Aditya University Department of It Surampalem India

ISBN: (纸本)9798350370249

Crop yield prediction is a crucial aspect of agricultural planning and decision-making. This study utilizes a Kaggle dataset featuring State, Year, Season, Crop, Area, Production, etc., employing extensive data preprocessing and one-hot encoding of categorical features to enhance predictive performance. Initially, ML regression methods including Multiple Linear regression, Random Forest regression, XGBoost, and Decision Tree regression (DTR) were applied. Later, Stacking Regressor and Voting Regressor were employed. Subsequently, dynamic ensemble techniques, specifically Voting Regressor, integrated these models, dynamically selecting the best-performing ones for prediction. Remarkably, achieving an R-squared value of 99%, the dynamic ensemble significantly improved prediction performance. The study showcases the efficacy of dynamic ensemble techniques in crop yield prediction, offering valuable insights for agricultural decision-making and resource allocation strategies. Experimental results underscore the effectiveness of the approach, highlighting its potential for practical application in agricultural management and policy formulation. © 2024 IEEE.

关键词： Crop yield prediction Data preprocessing Ensemble techniques Kaggle regression algorithms

来源：评论

学校读者我要写书评

暂无评论

A COMPARATIVE STUDY ON POWER CALCULATION METHODS FOR CONVEYOR BELTS IN MINING INDUSTRY

引用

INTERNATIONAL JOURNAL OF MINING RECLAMATION AND ENVIRONMENT 2022年第1期36卷 26-45页

作者： Koken, Ekin Lawal, Abiodun Ismail Onifade, Moshood Ozarslan, Ahmet Abdullah Gul Univ Dept Nanotechnol Engn Kayseri Turkey Fed Univ Technol Akure Dept Min Engn Akure Nigeria Univ Nambia Dept Civil & Min Engn Ongwediva Namibia Zonguldak Bulent Ecevit Univ Dept Min Engn Zonguldak Turkey

This paper covers different methods to evaluate the power consumption of several conveyor belt systems (CBSs) used in the Turkish Mining Industry (TMI). Based on each CBS's operational features, the power consumption (P-c, kW) was measured directly on motorised head-pulleys. The P-c was investigated through several conventional, statistical, and machine learning methods. This study shows that the DIN 22,101 could be the most convenient conventional method for the investigated CBSs. On the other hand, based on the nonlinear regression (NLR) and genetic expression programming (GEP) models, two new approaches were suggested for the design and optimisation of the P-c.

关键词： Conveyor belt mining power calculation regression algorithms gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Predicting the precise number of software defects: Are we there yet?

引用

INFORMATION AND SOFTWARE TECHNOLOGY 2022年 146卷

作者： Yu, Xiao Keung, Jacky Xiao, Yan Feng, Shuo Li, Fuyang Dai, Heng Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan Peoples R China Wuhan Univ Technol Chongqing Res Inst Chongqing Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Natl Univ Singapore Sch Comp Singapore Singapore Nanjing Inst Intelligent Technol Nanjing Peoples R China Wuhan Qingchuan Univ Sch Mech & Elect Engn Wuhan Peoples R China

Context: Defect Number Prediction (DNP) models can offer more benefits than classification-based defect prediction. Recently, many researchers proposed to employ regression algorithms for DNP, and found that the algorithms achieve low Average Absolute Error (AAE) and high Pred(0.3) values. However, since the defect datasets generally contain many non-defective modules, even if a DNP model predicts the number of defects in all modules as zero, the AAE value of the model will be low and Pred(0.3) value will be high. Therefore, the good performance of the regression algorithms in terms of AAE and Pred(0.3) may be questioned due to the imbalanced distribution of the number of ***: To revisit the impact of regression algorithms for predicting the precise number of ***: We examine the practical effects of 12 widely-used regression algorithms, two data resampling algorithm (SmoteR and ROS), and three ensemble learning algorithms (gradient boosting regression, AdaBoost.R2, and Bagging), one feature selection method (information gain) and one parameter optimization method (grid search) for predicting the precise number of defects on the 18 PROMISE datasets. We propose to evaluate the AAE and Pred(0.3) values for the modules with different numbers of defects ***: The AAE values for defective modules are very high and the Pred(0.3) values are very low, i.e., the regression algorithms are very inaccurate for predicting the precise number of defects in defective ***: The problem of predicting the precise number of defects via regression algorithms is far from being solved. We recommend that software testers use regression algorithms to rank modules for testing resource allocation, rather than predict the precise number of defects to evaluate the software reliability and maintenance effort. In addition, most existing DNP studies employing the whole AAE and Pred(0.3) values of all modules as the evaluation metrics for the prop

关键词： Software Defect Prediction Number of defects regression algorithms Empirical software engineering

来源：评论

学校读者我要写书评

暂无评论

Contributions to Power Grid System Analysis Based on Clustering Techniques

引用

SENSORS 2023年第4期23卷 1895页

作者： Grigoras, Gheorghe Raboaca, Maria Simona Dumitrescu, Catalin Manea, Daniela Lucia Mihaltan, Traian Candin Niculescu, Violeta-Carolina Neagu, Bogdan Constantin Gheorghe Asachi Tech Univ Iasi Dept Power Engn Iasi 700050 Romania Natl Res & Dev Inst Cryogen & Isotop Technol ICSI Uzinei St 4POB 7 Raureni Ramnicu Valcea 240050 Romania Stefan Cel Mare Univ Suceava Fac Elect Engn & Comp Sci Suceava 720229 Romania Univ Bucharest Doctoral Sch Polytech Bucharest 060042 Romania Univ Politehn Bucuresti Dept Telemat & Elect Transports Bucharest 060042 Romania Tech Univ Cluj Napoca Fac Civil Engn Constantin Daicoviciu St 15 Cluj Napoca 400020 Romania Tech Univ Cluj Napoca Fac Bldg Serv Engn Bd 21 Decembrie 1989128-130 Cluj Napoca 400604 Romania

The topic addressed in this article is part of the current concerns of modernizing power systems by promoting and implementing the concept of smart grid(s). The concepts of smart metering, a smart home, and an electric car are developing simultaneously with the idea of a smart city by developing high-performance electrical equipment and systems, telecommunications technologies, and computing and infrastructure based on artificial intelligence algorithms. The article presents contributions regarding the modeling of consumer classification and load profiling in electrical power networks and the efficiency of clustering techniques in their profiling as well as the simulation of the load of medium-voltage/low-voltage network distribution transformers to electricity meters.

关键词： smart grid clustering techniques pattern clustering power distribution planning regression algorithms

来源：评论

学校读者我要写书评

暂无评论

Design and Experiment of a Portable Near-Infrared Spectroscopy Device for Convenient Prediction of Leaf Chlorophyll Content

引用

SENSORS 2023年第20期23卷 8585页

作者： Li, Longjie Guo, Junxian Wang, Qian Wang, Jun Liu, Ya Shi, Yong Xinjiang Agr Univ Coll Mech & Elect Engn Urumqi 830052 Peoples R China Key Lab Xinjiang Intelligent Agr Equipment Urumqi 830052 Peoples R China

This study designs a spectrum data collection device and system based on the Internet of Things technology, aiming to solve the tedious process of chlorophyll collection and provide a more convenient and accurate method for predicting chlorophyll content. The device has the advantages of integrated design, portability, ease of operation, low power consumption, low cost, and low maintenance requirements, making it suitable for outdoor spectrum data collection and analysis in fields such as agriculture, environment, and geology. The core processor of the device uses the ESP8266-12F microcontroller to collect spectrum data by communicating with the spectrum sensor. The spectrum sensor used is the AS7341 model, but its limited number of spectral acquisition channels and low resolution may limit the exploration and analysis of spectral data. To verify the performance of the device and system, this experiment collected spectral data of Hami melon leaf samples and combined it with a chlorophyll meter for related measurements and analysis. In the experiment, twelve regression algorithms were tested, including linear regression, decision tree, and support vector regression. The results showed that in the original spectral data, the ETR method had the best prediction effect at a wavelength of 515 nm. In the training set, RMSEc was 0.3429, and Rc2 was 0.9905. In the prediction set, RMSEp was 1.5670, and Rp2 was 0.8035. In addition, eight preprocessing methods were used to denoise the original data, but the improvement in prediction accuracy was not significant. To further improve the accuracy of data analysis, principal component analysis and isolation forest algorithm were used to detect and remove outliers in the spectral data. After removing the outliers, the RFR model performed best in predicting all wavelength combinations of denoised spectral data using PBOR. In the training set, RMSEc was 0.8721, and Rc2 was 0.9429. In the prediction set, RMSEp was 1.1810, and Rp2 was 0

关键词： Internet of Things technology spectral data analysis chlorophyll content prediction regression algorithms data preprocessing

来源：评论

学校读者我要写书评

暂无评论

Analysis and price prediction of secondhand vehicles in T?rkiye with big data and machine learning techniques

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2023年第4期38卷 2279-2289页

作者： Gulmez, Burak Kulluk, Sinem Erciyes Univ Fac Engn Dept Ind Engn TR-38039 Kayseri Turkiye

Purpose: The purpose of this study is to analyze the secondhand vehicle dataset in Turkiye and to estimate the price of cars with Apache Spark and Apache Spark machine learning *** and Methods: Information such as the most popular cars, most expensive cars, most popular models, the relationship between price and year are extracted by analyzing the dataset. Then linear regression, decision tree regression, random forest regression, GBT regression, and isotonic regression algorithms are used to estimate vehicle prices. Also, statistical analyzes are carried out to test whether the difference between the results obtained by the algorithms are statistically ***: The random forest algorithm is given the best results in price prediction with 21435.09 RMSE and 0.887 R2. As a result of the statistical tests performed to control the significance of the differences between the RMSE and R2 values obtained with the random forest and other algorithms, it is concluded that the random forest algorithm is statistically better than other ***: The random forest algorithm is particularly successful in big data regression problems and can be used in this area. The success of the algorithm depends on performing training on multiple decision trees, its flexibility and strong hyperparameters.

关键词： Apache Spark Big data regression algorithms

来源：评论

学校读者我要写书评

暂无评论

Schrödinger spectrum based continuous cuff-less blood pressure estimation using clinically relevant features from PPG signal and its second derivative

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 166卷 107558-107558页

作者： Sarkar, Sayan Ghosh, Aayushman Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China Indian Inst Engn Sci & Technol Dept Elect & Telecommun Engn Howrah 11103 India Univ Illinois Dept Elect & Comp Engn Urbana IL 61801 USA

The presented study estimates cuff-less blood pressure (BP) from photoplethysmography (PPG) signals using multiple machine-learning (ML) models and the semi-classical signal analysis (SCSA) technique. The study proposes a novel signal reconstruction algorithm, which optimizes the semi-classical constant of the SCSA approach and eliminates the trade-off between complexity and accuracy during signal reconstruction. It predicts BP values using regression algorithms by processing reconstructed PPG signals' spectral features, extracting clinically relevant PPG and its second derivative's (SDPPG) morphological features. The developed method was assessed using a virtual in-silico dataset with more than 4000 subjects and the Multi-Parameter Intelligent Monitoring in Intensive Care Units (MIMIC-II) dataset. Results showed that the method attained a mean absolute error (MAE) of 5.37 and 2.96 mmHg for systolic and diastolic BP, respectively, using the CatBoost algorithm. This approach met the Association for the Advancement of Medical Instrumentation's standard and achieved Grade A for all BP categories in the British Hypertension Society protocol. The proposed framework performs well even when applied to a combined clinically relevant database originating from MIMIC-III and the Queensland dataset. The proposed method's performance is further evaluated in a non-clinical setting with noisy and deformed PPG signals to validate the efficacy of the SCSA method. The noise stress tests further showed that the algorithm maintained its key feature detection, signal reconstruction capability, and estimation accuracy up to a 10 dB SNR ratio. The proposed cuff-less BP estimation technique has the potential to perform well in mobile healthcare devices due to its straightforward implementation approach.

关键词： Continuous BP monitoring regression algorithms Photoplethysmogram Pulse Wave Analysis Pulse wave decomposition Bio-signal database Signal processing framework

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：