检索结果-内蒙古大学图书馆

Machine learning algorithms predict bark coverages on saguaro cacti (Carnegiea gigantea)

FLORA 2020年第0期263卷 151527-000页

作者： Evans, Lance S. Shackley, Alexander Printy, Olivia Manhattan Coll Lab Plant Morphogenesis Biol Sci Res Labs Bronx NY 10471 USA

Bark coverages lead to the premature death of saguaro cacti (Carnegiea gigantea). Bark coverages on surfaces of more than 20 species of tall, long-lived cacti occur throughout the Americas. This study analyzed data of bark coverages on twelve surfaces on 1149 saguaro cacti from four sampling periods over a period of 23 years. Bark coverage starts on equator-facing surfaces and progresses to polar-facing surfaces. For this population, 45 % of all cacti were dead by the end of the 23-year period of study. In order to understand how bark coverages are related to cactus death, four machine learning programs were used to analyze the data obtained. Decision trees predicted rates of bark coverages and death with time as a variable with probabilities of 90 % and 99 %, respectively. Trough surfaces were better predictors of bark coverage and cactus death than crest surfaces. Left troughs of both polar- and west-facing surfaces were the best predictors of bark coverage and cactus death with probabilities above 99 %. The four machine learning programs gave complimentary results to present a unified view to predict future bark coverages over time and predict eventual cactus death with more than 99 % accuracy.

关键词： Validate Model algorithm WEKA 3.8 decision trees Random Forest algorithm knn algorithm Cactus death

来源：评论

学校读者我要写书评

暂无评论

¹H NMR spectroscopy coupled with multivariate analysis was applied to investigate Italian cherry tomatoes metabolic profile

引用

JOURNAL OF CHEMOMETRICS 2020年第1期34卷 e3191-e3191页

作者： Masetti, Olimpia Nisini, Luigi Ciampa, Alessandra Dell'Abate, Maria Teresa Consiglio Ric Econ Agr Consiglio Ric Agr & Anal CREA AA Res Ctr Agr & Environm Via Navicella 2-4 I-00184 Rome Italy IES DG Joint Res Ctr Ispra VA Italy

Nuclear magnetic resonance (NMR) spectroscopy, in combination with different chemometric methods, was widely used for metabolomic profiling in the geographical determination of food origin. In the present study, spectra data of cherry tomatoes, collected from Pachino (Sicily) and Sabaudia (Latium), were analyzed by principal component analysis (PCA), k nearest neighbors (knn), and partial least-squares discriminant analysis (PLS-DA) in order to discriminate the samples according to their geographical provenance. The PCA analysis of H-1 NMR spectra of Sabaudia cherry tomatoes showed significant differences linked to the production year: phospholipids had higher levels in 2004, but less amounts of polyunsaturated acids and lycopene were observed with respect to the year 2005. Despite the annual differences in H-1 NMR metabolic profile of Sabaudia cherry tomatoes, using unsupervised (PCA) and supervised (PLS-DA, knn) approaches, the geographical origin differentiation was obtained. In fact, the knn algorithm correctly classified approximately 84% to 87% of Pachino samples and 77% of Sabaudia ones with recognition ability varied from 82% to 84.4% and prediction ability (CV) of 76.2% and 94.7%. The PC1 component, with 53% of total variance, greatly separated Pachino cherry tomatoes from Sabaudia ones and PLS-DA model showed a good degree of separation with recognition ability of 100% and prediction ability (CV) of 93% to 100%. PCA and PLS-DA combined analysis highlighted the most prominent spectral areas that well separated the two groups of samples. So, phytosterols were found discriminating compounds according to PCA and PLS-DA and differences in aroma components were observed mainly in PCA analysis.

关键词： H-1 NMR profiling cherry tomatoes geographical origin knn algorithm PCA and PLS-DA analysis tomato lipophilic metabolites

来源：评论

学校读者我要写书评

暂无评论

knn and SVM Classification for Chainsaw Sound Identification in the Forest Areas

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2019年第12期10卷 531-536页

作者： Gnamele, N'tcho Assoukpou Jean Ouattara, Yelakan Berenger Kobea, Toka Arsene Baudoin, Genevieve Laheurte, Jean-Marc UFHB Lab Signaux & Syst Abidjan Cote Ivoire UFHB Lab Phys Atmosphere & Mecan Fluides Abidjan Cote Ivoire UPEM ESIEE PARIS Marne La Vallee France UPEM ESYCOM FRE 2028 Marne La Vallee France

We present in this paper a comparative study of two classifiers, namely, SVM (support vector machine) and knn (K-Nearest Neighbors), which we combine to MFCC (Mel-Frequency Cepstral Coefficients) in order to make possible the detection of chainsaw's sounds in a forest environment. Optimization's calculation of the relevant characteristics of the sounds recorded in the forest and the judicious choice of the key parameters of the classifiers allows us to obtain a true positive rate of 95.63% for the SVM-LOG-KERNEL and 94.02% for the knn. The SVM-LOG-KERNEL classifier offers a better classification result and a processing time 30 times faster than knn.

关键词： knn algorithm SVM algorithm MFCC sound recognition forest monitoring machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing recommendation systems performance using highly-effective similarity measures®

引用

KNOWLEDGE-BASED SYSTEMS 2021年 217卷 106842-106842页

作者： Amer, Ali A. Abdalla, Hassan, I Loc Nguyen TAIZ Univ Comp Sci Dept Taizi Yemen Zayed Univ Coll Technol Innovat POB 144534 Abu Dhabi U Arab Emirates Loc Nguyens Acad Network Board Advisors Long Xuyen Vietnam

In Recommendation Systems (RS) and Collaborative Filtering (CF), the similarity measures have been the operating component upon which CF performance is essentially reliant. A dozen of similarity measures have been proposed to reach the desired performance particularly under the circumstances of data sparsity (the cold-start problem). Nevertheless, these measures still suffer the cold-start problem, and have a complex design. Moreover, a comprehensive experimental work to study the impact of the cold-start problem on CF performance is still missing. To these ends, therefore, this paper introduces three simply-designed similarity measures, namely, difference-based similarity measure (SMD), hybrid difference-based similarity measure (HSMD), and, triangle-based cosine measure (TA). Along with proposing these measures, a comprehensive experimental guide for CF measures using the K-fold cross validation is also presented. In contrary to all previous CF studies, the evaluation process is split into two sub-processes: the estimation process and recommendation process to accurately obtain the desired appropriateness in the evaluation. In addition, a new formula to calculate the dynamic recommendation count is developed depending on both the dataset and rating vectors. To draw a comprehensive experimental analysis, a dozen state-of-the-art similarity measures (30 similarity measures) including the proposed and the most widely-used traditional measures are comparatively tested. The experimental study has critically been made on three datasets with five-fold cross-validation grounded on the K nearest neighbor algorithm (knn). The obtained results on both estimation and recommendation processes prove unquestionably that SMD and TA are preeminent measures with the lowest computational complexity outperforming all state-of-the-art CF measures. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Collaborating filtering Recommendation systems Similarity knn algorithm Cross validation Empirical evaluation

来源：评论

学校读者我要写书评

暂无评论

Research on Indoor Positioning algorithm Based on Neighborhood Partitioning 3

Research on Indoor Positioning Algorithm Based on Neighborho...

引用

3rd IEEE International Conference on Information Communication and Signal Processing (ICICSP)

作者： Shan, Zhilong Zhang, Fan Lv, Na Xiang, Wan South China Nounal Univ Sch Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9781728188232

In order to solve the problem of long matching time caused by a large number of reference fingerprints and inaccurate positioning caused by knn algorithm alone. A method based on knn partitioning is proposed in this paper. Firstly, the fingerprint space is clustered, and then the K nodes closest to the unknown node are obtained in the clustered area according to knn algorithm. Secondly, the maximum and minimum coordinates of K fingerprints are used to determine the region, and then the region is divided by Newton interpolation method to form a virtual fingerprint matrix. Finally, knn algorithm is used to re-determine the region, and then particle swarm optimization algorithm is used to find the optimal location node in this region iteratively. Experiments show that the algorithm can improve the positioning accuracy and reduce the matching time effectively, especially when the reference fingerprints are sparse.

关键词： fingerprint library knn algorithm K-Means newton interpolation particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Braille Book Reader using Raspberry Pi

Braille Book Reader using Raspberry Pi

引用

International Conference on Computational Performance Evaluation (ComPE)

作者： Sharma, Abhishek Devi, Suman Verma, Jitendra Kumar Galgotias Univ Sch Comp Sci & Engn Greater Noida India Amity Univ Haryana Amity Sch Engn & Technol Gurgram Manesar India

ISBN: (纸本)9781728166445

The aim of this research paper is to understand the braille system and read the book for visually impaired person without any difficulty. Braille system is used by the people who are visually impaired. Braille system consist six raised dots in each cell and each cell represent one letter in English alphabet. In this undertaking we are using knn algorithm for find the nearest neighbors from the base dot and calculate the distance between the dots. After finding the letter raspberry pi module convert that letter into speech form by using text to speech convertor. Camera module, voice output module is attached with the Raspberry pi module. We propose a Camera based framework integrated with Image processing algorithms, knn algorithm and text to speech module.

关键词： Raspberry Pi knn algorithm Text to speech module Image processing algorithm

来源：评论

学校读者我要写书评

暂无评论

Theory, Analyses and Predictions of Multifractal Formalism and Multifractal Modelling for Stroke Subtypes' Classification 20th

Theory, Analyses and Predictions of Multifractal Formalism a...

引用

20th International Conference on Computational Science and Its Applications (ICCSA)

作者： Karaca, Yeliz Baleanu, Dumitru Moonis, Majaz Zhang, Yu-Dong Univ Massachusetts Med Sch Worcester MA 01655 USA Cankaya Univ Dept Math TR-1406530 Ankara Turkey Inst Space Sci Bucharest Romania Univ Leicester Dept Informat Leicester LE1 7RH Leics England

ISBN: (纸本)9783030588021;9783030588014

Fractal and multifractal analysis interplay within complementary methodology is of pivotal importance in ubiquitously natural and man-made systems. Since the brain as a complex system operates on multitude of scales, the characterization of its dynamics through detection of self-similarity and regularity presents certain challenges. One framework to dig into complex dynamics and structure is to use intricate properties of multifractals. Morphological and functional points of view guide the analysis of the central nervous system (CNS). The former focuses on the fractal and self-similar geometry at various levels of analysis ranging from one single cell to complicated networks of cells. The latter point of view is defined by a hierarchical organization where self-similar elements are embedded within one another. Stroke is a CNS disorder that occurs via a complex network of vessels and arteries. Considering this profound complexity, the principal aim of this study is to develop a complementary methodology to enable the detection of subtle details concerning stroke which may easily be overlooked during the regular treatment procedures. In the proposed method of our study, multifractal regularization method has been employed for singularity analysis to extract the hidden patterns in stroke dataset with two different approaches. As the first approach, decision tree, Naive bayes, knn and MLP algorithms were applied to the stroke dataset. The second approach is made up of two stages: i) multifractal regularization (kulback normalization) method was applied to the stroke dataset and mFr stroke dataset was generated. ii) the four algorithms stated above were applied to the mFr stroke dataset. When we compared the experimental results obtained from the stroke dataset and mFr stroke dataset based on accuracy (specificity, sensitivity, precision, F1-score and Matthews Correlation Coefficient), it was revealed that mFr stroke dataset achieved higher accuracy rates. Our novel prop

关键词： Multifractal Formalism Fractional brownian motion Hurst exponent Fractal pattern Self-similar process Stroke Prediction algorithms Naive Bayes algorithm knn algorithm Multilayer Perceptron algorithm Multifractal regularization

来源：评论

学校读者我要写书评

暂无评论

CNN algorithm for plant classification in deep learning

引用

Materials Today: Proceedings 2021年 46卷 3684-3689页

作者： G. Valarmathi S.U. Suganthi V. Subashini R. Janaki R. Sivasankari S. Dhanasekar ECE Sri Sairam Institute of Technology Chennai 600044 India ECE Sri Eshwar College of Engineering Coimbatore 641202 India

The prior methodology of characterizing the plants for dependent on surface based order and another strategy depends on knn classifier. This paper presents qualities examination of plants utilizing picture preparing methods for robotized vision framework utilized at horticultural field. In farming examination, the programmed plant attributes recognition is fundamental one in observing huge field. The proposed dynamic framework uses picture content portrayal and regulated classifier sort of neural organization. This will naturally distinguish the plant species when we import its picture as info. Picture preparing strategies for this sort of choice investigation includes pre-processing and characterization stage. At Processing, an info picture will be resized and commotion expulsion procedure is applied. At definite stage the neural organization orders the pictures as farming plant, harmful plant and therapeutic plant separately. At that point it will show the attributes of each plant.

关键词： Plant classification knn algorithm SVM classifier Feature extraction CNN algorithm

来源：评论

学校读者我要写书评

暂无评论

algorithms predict morbidity and mortality of Saguaro Cacti ( Carnegiea gigantea ) from sunlight exposures

引用

FLORA 2021年 276卷 151775-151775页

作者： Evans, Lance S. New York Bot Garden Bronx NY 10458 USA

Bark coverages on stem surfaces lead to premature death of saguaro cacti (Carnegiea gigantea). Bark coverages have occurred on surfaces of more than 50 species of tall, long-lived cacti throughout the Americas. This study analyzed data of bark coverages on 12 surfaces of C. gigantea. Among 1,149 saguaro cacti, from four sampling periods over 23 years, data of four independent algorithm programs were used to predict bark coverages and cactus death. On saguaros, bark coverage originates on south-facing surfaces and progresses to north-facing surfaces, prior to cactus death. For this population, bark coverages increased over time and 45% of all cacti were dead by the end of the 23-year study period. Validate Model and WEKA 3.8 predicted bark coverages with over 96% accuracy. Random Forest predicted cactus death with 99.6% accuracy and knn predicted cactus death with 100% accuracy. Since trough surfaces occur after crest surfaces, trough surfaces were better predictors of bark coverages and cactus death. Cactus death was best predicted (above 99%) with north-right troughs with west-facing surfaces. Taken together, the four machine programs gave complimentary results and predicted (above 99%) both increased bark coverages from south-facing surfaces to north-facing surfaces over time and death of individual cacti over an eight-year period when north-facing right troughs had more than 80% bark coverages.

关键词： Validate Model algorithm WEKA 3 8 decision trees Random Forest algorithm knn algorithm Cactus death Machine learning program Bark coverages

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence application for classification and selection of fish gelatin packaging film produced with incorporation of palm oil and plant essential oils

引用

FOOD PACKAGING AND SHELF LIFE 2021年 27卷

作者： e Silva, Natacia da Silva Farias, Fabricio de Souza dos Santos Freitas, Mauricio Madson Gregorio Pino Hernandez, Enrique Jose Dantas, Vanderson Vasconcelos Chaves Oliveira, Marcos Ene Sarkis Peixoto Joele, Maria Regina Henriques Lourenco, Lucia de Fatima Fed Univ Para LAPOA FEA Fac Food Engn Rua Augusto Correa 01 BR-66075900 Belem Para Brazil Estadual Univ Para Food Technol Dept UEPA Cameta Para Brazil Fed Univ Para UFPA Fac Informat Syst Cameta Para Brazil Univ Minho CEB Ctr Biol Engn P-4710057 Braga Portugal Embrapa Eastern Amazon Belem Para Brazil Fed Inst Educ Sci & Technol Dept Food & Sci Campus Castanhal Para Brazil

The k-Nearest Neighbor (knn) algorithm was used to classify and select biodegradable packaging produced from fish gelatine incorporated with palm oil and clove and oregano essential oils. All reinforced films are highly resistant to attraction, with an emphasis on a sample of clove essential oil with a value of 53.18 MPa. Also, the addition of palm oil and essential oils increases the elasticity and thickness of the packages. The packages have antioxidant and antimicrobial properties with an inhibition zone for S. aureus of 11.73 and 11.23 mm for the film with essential oil of oregano and film with palm oil, respectively. knn proved to be efficient for the classification and selection of packaging. The results highlighted the packaging with clove essential oil as the best for presenting the highest values of antioxidant activity, tensile strength, and elongation. Palm oil is an interesting alternative for applications in biodegradable films due to its antimicrobial activity, antioxidant properties, abundance, and low cost. Packaging made of fish gelatin with the addition of vegetable oils is a promising alternative for food applications.

关键词： Waste Artificial intelligence knn algorithm Oil palm Active packaging

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：