检索结果-内蒙古大学图书馆

Deep Learning Framework With Essential pre-processing techniques for Improving Mixed-Gas Concentration prediction

IEEE ACCESS 2023年 11卷 25467-25479页

作者： Eo, Moonjung Han, Jeongyun Rhee, Wonjong Seoul Natl Univ Dept Intelligence & Informat Seoul 08826 South Korea Ctr Open Middle & High Sch Future Educ Res Div Chungcheongbuk Do 27873 South Korea Seoul Natl Univ Interdisciplinary Program Artificial Intelligence Seoul 08826 South Korea Seoul Natl Univ AI Inst Seoul 08826 South Korea

Multiple gas detection in mixed-gas environments is a challenging issue in many engineering industries because some of the gases can raise defect rates and reduce production efficiency. For chemo-resistive gas sensors, a precise estimation can be challenging because of the measurement variance and non-linear nature of the gas sensors, especially in a low concentration environment. A simple application of the deep learning models, however, does not yield sufficiently accurate predictions of the concentrations of multiple gases in gas mixtures;thus, it is essential to develop basic strategies for enhancing the accuracy in all possible ways. In this study, we develop a deep learning framework for achieving high accuracy of gas concentration prediction by studying the essential pre-processing techniques, learning task design, and architecture design. For the pre-processing, we study several aspects of processing time-series sensor data and identify the key techniques for complementing deep learning models' limitations. We utilize the mixed-gas nature for the learning task design and show that multi-task learning can generate a synergistic effect. Additionally, we show that a further improvement is possible by considering on-off classification as a part of the hybrid learning task. Concerning architecture design, we investigate Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) models after applying the identified pre-processing techniques. CNN outperformed other models in a joint analysis with the learning task. The effectiveness of our framework is confirmed with the UCI gas mixture dataset acquired using a chemical detection platform where 16 chemical sensors are exposed to ethylene, CO, and methane gases. Using the dataset, we study the basic techniques that can be effective to mixed-gas prediction. For the UCI dataset, our deep learning framework achieves a significant improvement in estimation accuracy when compared

关键词： Chemical sensors gas concentration prediction deep neural network pre-processing techniques mixed-gas framework hybrid-task

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effects of pre-processing techniques on Topic Modeling of an Arabic News Article Data Set

引用

APPLIED SCIENCES-BASEL 2024年第23期14卷 11350页

作者： Alangari, Haya Algethami, Nahlah Saudi Elect Univ Coll Comp & Informat Comp Sci Dept Riyadh 1167 Saudi Arabia

This research investigates the impacts of pre-processing techniques on the effectiveness of topic modeling algorithms for Arabic texts, focusing on a comparison between BERTopic, Latent Dirichlet Allocation (LDA), and Non-Negative Matrix Factorization (NMF). Using the Single-label Arabic News Article Data set (SANAD), which includes 195,174 Arabic news articles, this study explores pre-processing methods such as cleaning, stemming, normalization, and stop word removal, which are crucial processes given the complex morphology of Arabic. Additionally, the influence of six different embedding models on the topic modeling performance was assessed. The originality of this work lies in addressing the lack of previous studies that optimize BERTopic through adjusting the n-gram range parameter and combining it with different embedding models for effective Arabic topic modeling. pre-processing techniques were fine-tuned to improve data quality before applying BERTopic, LDA, and NMF, and the performance was assessed using metrics such as topic coherence and diversity. Coherence was measured using Normalized Pointwise Mutual Information (NPMI). The results show that the Tashaphyne stemmer significantly enhanced the performance of LDA and NMF. BERTopic, optimized with pre-processing and bi-grams, outperformed LDA and NMF in both coherence and diversity. The CAMeL-Lab/bert-base-arabic-camelbert-da embedding yielded the best results, emphasizing the importance of pre-processing in Arabic topic modeling.

关键词： BERTopic topic modeling pre-processing techniques LDA NMF NPMI topic diversity Tashaphyne ISRI

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Diagnostic Evaluation of Thyroid Functionality Using Diffuse Reflectance Spectroscopy and Regression Models

引用

JOURNAL OF BIOPHOTONICS 2025年第0期 e70010页

作者： Shalini, W. Anto Win Rajalakshmi, T. Suryakala, S. Vasanthadev SRM Inst Sci & Technol Coll Engn & Technol Dept Elect & Commun Engn Kattankulathur India

Thyroid dysfunction is a prevalent global health concern that necessitates the development of effective and non-invasive screening methods to enable early detection. The application of Diffuse Reflectance Spectroscopy (DRS) in conjunction with pre-processing and predictive models for thyroid dysfunction diagnosis is investigated. The raw spectral data captured from 31 individuals with thyroid dysfunction are subjected to spectral preprocessing techniques like, Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC), and Baseline Correction. The preprocessed data subjected to regression models like Partial Least Squares Regression (PLSR), Principal Component Regression (PCR), LASSO, Random Forest, Ridge Regression, Gaussian Process Regression (GPR), and Bayesian Regression were employed to analyse the efficacy of the models. The PLSR model in concurrence with SNV outperforms other regression models by achieving an R-2 of 0.93, RMSE of 0.29, and MSE of 0.08, indicating low predictive error. The goodness of fit was also evaluated using Pearson's chi-squared test.

关键词： diffuse reflectance spectroscopy non-invasive pre-processing techniques regression thyroid thyroid assessment

来源：评论

学校读者我要写书评

暂无评论

A systematic quantitative review on the performance of some of the recent short-term rainfall forecasting techniques

引用

JOURNAL OF WATER AND CLIMATE CHANGE 2022年第8期13卷 3004-3029页

作者： Ashok, Shejule Priya Pekkat, Sreeja Indian Inst Technol Guwahati Dept Civil Engn Gauhati 781039 Assam India

Rainfall forecasting is a high-priority research problem due to the complex interplay of multiple factors. Despite extensive studies, a systematic quantitative review of recent developments in rainfall forecasting is lacking in the literature. This study conducted a systematic quantitative review of statistical, numerical weather prediction (NWP) and machine learning (ML) techniques for rainfall forecasting. The review adopted the preferred reporting items for systematic reviews and meta-analyses (PRISMA) technique for screening keywords and abstracts, leading to 110 qualified papers from multiple databases. The impact of rainfall threshold, meteorological parameters, topography, algorithm techniques, geographic location, the horizontal resolution of the model, and lead time on rainfall forecast was examined. The review shows the importance of precipitable water vapor (PWV) along with other meteorological parameters for accurate nowcasting in coastal and mountainous regions. An increase in rainfall forecast uncertainty with an increase in the lead time makes the NWP model less popular for the short-term forecast. The pre-processing techniques increased the accuracy of ML techniques by considering extreme values and detecting the irregularly distributed multi-scale features of rainfall in space and time. Future research can focus on hybrid models with improved accuracy for nowcasting. The output from the hybrid model serves as input for the decision support system required for urban flood risk management.

关键词： forecast skill lead time pre-processing techniques rainfall forecast resolution systematic review

来源：评论

学校读者我要写书评

暂无评论

predicting macronutrients and energy content of snack products using FT-NIR analysis and chemometric techniques

引用

JOURNAL OF FOOD ENGINEERING 2020年 280卷 109954-000页

作者： Benes, Eszter Gere, Attila Fodor, Marietta Szent Istvan Univ Fac Food Sci Dept Appl Chem Villanyi Str 29-31 H-1118 Budapest Hungary Szent Istvan Univ Fac Food Sci Dept Postharvest & Sensory Evaluat Villanyi Str 29-31 H-1118 Budapest Hungary

Nowadays, the consumption of snack products is permanently increasing. Because of the growing trend of snack consumption, it is more and more difficult to guarantee the quality and safety of the products. Near infrared spectroscopy (NIRS) method, combined with chemometric techniques provide outstanding solutions, due to its rapidity and simple sample preparation. The objective of this study was to investigate the possibilities of using NIRS to predict fat, protein, carbohydrate, sugar and salt content of all in all 155 commercially available snack products from 25 countries. The prediction models were performed using partial least squares regression (PLSR) with different spectral pre-processing methods. Different pre-processing methods proved to be the best to predict the five macronutrients, however, the final models showed good accuracy vertical bar R-2/Q(2) > 0.94/0.82 vertical bar. The energy content of the samples was calculated from the measured parameters and interval PLS regression was accomplished to improve prediction parameters. The methods developed are suitable for analyzing snacks made from single or mixed raw materials.

关键词： pre-processing techniques Extruded and fried snacks PLS Interval PLS Nutrition label

来源：评论

学校读者我要写书评

暂无评论

Performance assessment of rainfall forecasting models for urban Guwahati City using machine learning techniques and singular spectrum analysis

引用

JOURNAL OF WATER AND CLIMATE CHANGE 2024年第4期15卷 1565-1587页

作者： Shejule, Priya Ashok Pekkat, Sreeja Indian Inst Technol Guwahati Dept Civil Engn Gauhati 781039 Assam India

Rainfall forecasting is pivotal in improving the lead time for issuing flood warnings and flood management. Machine learning (ML) models are popular as they can effectively manage extensive data and non-stationarity of the data series with improved performance and cost-effective solutions. However, more studies are required to understand the dynamic characteristics of rainfall. This study proposes a hybrid model and demonstrates its efficiency in improving the daily rainfall forecast. Singular spectrum analysis (SSA) was used as a data pre-processing technique (successfully removing and identifying the nature of noise) and coupled with ML models (artificial neural network (ANN) and support vector machine (SVM)) improving daily scale forecast. Since the current response of the hydrological system depends on previous responses, rainfall at the next time step was derived with the previous 2, 3, 5 and 7 days of rainfall. Study shows that the first eigen vector derived through SSA is the trend component which has a maximum contribution of 18.75%, suggesting it can explain 18.75% of the given rainfall series. The 16.42% (eigen vector 2-9) contributes to periodicity, with period of 1 year, 6 months, and 4 months within the data. Conclusively, the hybrid SSA-ML model outperformed the single model for daily rainfall forecasts.

关键词： dynamic characteristics hybrid model machine learning pre-processing techniques rainfall forecast singular spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

On the capability of preprocessing techniques for suspended sediment load prediction using artificial intelligence methods

引用

HYDROLOGICAL SCIENCES JOURNAL 2022年第3期67卷 369-384页

作者： Ahmadi, Hiva Mastouri, Reza Jafarinia, Reza Islamic Azad Univ Dept Civil Engn Arak Branch Arak Iran

With growing interest in global environmental change, it is crucial to have a reliable model to accurately predict the suspended sediment load (SSL). This study investigates the efficiency and capability of two time-series data decomposition algorithms, namely empirical mode decomposition (EMD) and ensemble EMD (EEMD), to address the complexity and non-stationary behaviour of the monthly SSL time series data. These algorithms were coupled with three artificial intelligence models - gene expression programming (GEP), extreme learning machine (ELM), and extreme gradient boosting (XGBoost) - to predict SSL at two stations in Tajan Basin, northern Iran. The results indicate that EEMD, with coefficient of determination values higher than 0.9, performed better than EMD when coupled with XGBoost as the ensemble model. To verify the the predicted SSL data, Monte Carlo simulation was used. The results confirmed the lower uncertainty of the EEMD-XGBoost model in predicting SSL at a monthly scale.

关键词： suspended sediment load pre-processing techniques extreme gradient boosting ensemble empirical mode decomposition Monte Carlo simulation Tajan Basin

来源：评论

学校读者我要写书评

暂无评论

Assessing the data complexity of imbalanced datasets

引用

INFORMATION SCIENCES 2021年 553卷 83-109页

作者： Barella, Victor H. Garcia, Luis P. F. de Souto, Marcilio C. P. Lorena, Ana C. de Carvalho, Andre C. P. L. F. Univ Sao Paulo Inst Math & Comp Sci Trabalhador Sao Carlense Av 400 BR-13560970 Sao Paulo SP Brazil Univ Brasilia Comp Sci Dept BR-70910900 Brasilia DF Brazil Univ Orleans Leonard de Vinci Fundamental Comp Sci Lab BP 6759 F-45067 Orleans 2 France Aeronaut Inst Technol Praca Marechal Eduardo Gomes 50 BR-12228900 Sao Jose Dos Campos SP Brazil

Imbalanced datasets are an important challenge in supervised Machine Learning (ML). According to the literature, class imbalance does not necessarily impose difficulties for ML algorithms. Difficulties mainly arise from other characteristics, such as overlapping between classes and complex decision boundaries. For binary classification tasks, calculating imbalance is straightforward, e.g., the ratio between class sizes. However, measuring more relevant characteristics, such as class overlapping, is not trivial. In the past years, complexity measures able to assess more relevant dataset characteristics have been proposed. In this paper, we investigate their effectiveness on real imbalanced datasets and how they are affected by applying different data imbalance treatments (DIT). For such, we perform two data-driven experiments: (1) We adapt the complexity measures to the context of imbalanced datasets. The experimental results show that our proposed measures assess the difficulty of imbalanced problems better than the original ones. We also compare the results with the state-of-art on data complexity measures for imbalanced datasets. (2) We analyze the behavior of complexity measures before and after applying DITs. According to the results, the difference in data complexity, in general, correlates to the predictive performance improvement obtained by applying DITs to the original datasets. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Classification Imbalanced dataset Complexity measures pre-processing techniques

来源：评论

学校读者我要写书评

暂无评论

Detection of Alzheimer's disease using pre-trained deep learning models through transfer learning: a review

引用

ARTIFICIAL INTELLIGENCE REVIEW 2024年第10期57卷 275页

作者： Heenaye-Mamode Khan, Maleika Reesaul, Pushtika Auzine, Muhammad Muzzammil Taylor, Amelia Univ Mauritius Dept Software & Informat Syst Reduit Mauritius Malawi Univ Business & Appl Sci Comp & Informat Technol Dept Blantyre Malawi

Due to the progress in image processing and Artificial Intelligence (AI), it is now possible to develop automated tool for the early detection and diagnosis of Alzheimer's Disease (AD). Handcrafted techniques developed so far, lack generality, leading to the development of deep learning (DL) techniques, which can extract more relevant features. To cater for the limited labelled datasets and requirement in terms of high computational power, transfer learning models can be adopted as a baseline. In recent years, considerable research efforts have been devoted to developing machine learning-based techniques for AD detection and classification using medical imaging data. This survey paper comprehensively reviews the existing literature on various methodologies and approaches employed for AD detection and classification, with a focus on neuroimaging techniques such as structural MRI, PET, and fMRI. The main objective of this survey is to analyse the different transfer learning models that can be used for the deployment of deep convolution neural network for AD detection and classification. The phases involved in the development namely image capture, pre-processing, feature extraction and selection are also discussed in the view of shedding light on the different phases and challenges that need to be addressed. The research perspectives may provide research directions on the development of automated applications for AD detection and classification.

关键词： Alzheimer's disease Detection Classification Neuroimaging modalities Datasets Data augmentation pre-processing techniques Input data management Transfer learning models

来源：评论

学校读者我要写书评

暂无评论

Input size independent efficient quality meshing of the interior of 2D point cloud data

引用

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING 2019年第3期6卷 316-326页

作者： Singh, Neha Ray, Tathagata Parimi, Chandu Kuchibhotla, Srivastava Birla Inst Technol & Sci Pilani Dept Comp Sci & Informat Syst Hyderabad Campus Hyderabad Telangana India Birla Inst Technol & Sci Pilani Dept Civil Engn Hyderabad Campus Hyderabad Telangana India

This paper describes a framework to generate an unstructured Delaunay mesh of a two-dimensional domain whose boundary is specified by a point cloud data (PCD). The assumption is that the PCD is sampled from a smooth 1-manifold without a boundary definition and is significantly dense (at least epsilon-sampled where epsilon < 1). presently meshing of such a domain requires two explicit steps, namely the extraction of model definition from the PCD and the use of model definition to guide the unstructured mesh generation. For a densely sampled PCD, the curve reconstruction process is dependent on the size of input PCD and can become a time-consuming overhead. We propose an optimized technique that bypasses the explicit step of curve reconstruction by implicit access to the model information from a well-sampled PCD. A mesh thus generated will be optimal, as the fineness of the mesh is not dictated by the sampling of PCD, but only the geometric complexity of the underlying curve. The implementation and experiments of the proposed framework show significant improvement in expense over the traditional methodology. The main contribution of this paper is the circumvention of the explicit time-consuming step of boundary computation which is a function of the PCD sampling size and a direct generation of a mesh whose complexity is dictated by the geometry of the domain. (C) 2018 Society for Computational Design and Engineering. Publishing Services by Elsevier.

关键词： Mesh generation Delaunay triangulation Point cloud data Curve reconstruction pre-processing techniques

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：