Search results for: random forest tree

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 88

Authors: Songul Cinaroglu

Abstract:

Background: Random Forest is an efficient, multi-class machine learning method using for classification, regression and other tasks. This method is operating by constructing each tree using different bootstrap sample of the data. Determining the number of trees in random forests is an open question in the literature for studies about improving classification performance of random forests. Aim: The aim of this study is to analyze whether there is an optimal number of trees in Random Forests and how performance of Random Forests differ according to increase in number of trees using sample health data sets in R programme. Method: In this study we analyzed the performance of Random Forests as the number of trees grows and doubling the number of trees at every iteration using “random forest” package in R programme. For determining minimum and optimal number of trees we performed Mc Nemar test and Area Under ROC Curve respectively. Results: At the end of the analysis it was found that as the number of trees grows, it does not always means that the performance of the forest is better than forests which have fever trees. In other words larger number of trees only increases computational costs but not increases performance results. Conclusion: Despite general practice in using random forests is to generate large number of trees for having high performance results, this study shows that increasing number of trees doesn’t always improves performance. Future studies can compare different kinds of data sets and different performance measures to test whether Random Forest performance results change as number of trees increase or not.

Keywords: classification methods, decision trees, number of trees, random forest

Procedia PDF Downloads 391

Authors: Thota Sai Prakash, B. Yaswanth, Jhade Bhuvaneswar, Marreddy Divakar Reddy, Shyam Ji Gupta

Abstract:

Across the globe, there are a lot of chronic diseases, and heart disease stands out as one of the most perilous. Sadly, many lives are lost to this condition, even though early intervention could prevent such tragedies. However, identifying heart disease in its initial stages is not easy. To address this challenge, we propose an automated system aimed at predicting the presence of heart disease using advanced techniques. By doing so, we hope to empower individuals with the knowledge needed to take proactive measures against this potentially fatal illness. Our approach towards this problem involves meticulous data preprocessing and the development of predictive models utilizing classification algorithms such as Support Vector Machines (SVM), Decision Tree, and Random Forest. We assess the efficiency of every model based on metrics like accuracy, ensuring that we select the most reliable option. Additionally, we conduct thorough data analysis to reveal the importance of different attributes. Among the models considered, Random Forest emerges as the standout performer with an accuracy rate of 96.04% in our study.

Keywords: support vector machines, decision tree, random forest

Procedia PDF Downloads 33

Authors: Nabilah Filzah Mohd Radzuan, Andi Putra, Zalinda Othman, Azuraliza Abu Bakar, Abdul Razak Hamdan

Abstract:

Precipitation forecast is important to avoid natural disaster incident which can cause losses in the involved area. This paper reviews three techniques logistic regression, decision tree, and random forest which are used in making precipitation forecast. These combination techniques through the vector auto-regression (VAR) model help in finding the advantages and strengths of each technique in the forecast process. The data-set contains variables of the rain’s domain. Adaptation of artificial intelligence techniques involved in rain domain enables the forecast process to be easier and systematic for precipitation forecast.

Keywords: logistic regression, decisions tree, random forest, VAR model

Procedia PDF Downloads 442

Authors: Suzan Anwar, Utkarsh Goyal

Abstract:

Heart rate (HR) is a predictor of cardiovascular, cerebrovascular, and all-cause mortality in the general population, as well as in patients with cardio and cerebrovascular diseases. Machine learning (ML) significantly improves the accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment while avoiding unnecessary treatment of others. This research examines relationship between the individual's various heart health inputs like age, sex, cp, trestbps, thalach, oldpeaketc, and the likelihood of developing heart disease. Machine learning techniques like logistic regression and decision tree, and Python are used. The results of testing and evaluating the model using the Heart Failure Prediction Dataset show the chance of a person having a heart disease with variable accuracy. Logistic regression has yielded an accuracy of 80.48% without data handling. With data handling (normalization, standardscaler), the logistic regression resulted in improved accuracy of 87.80%, decision tree 100%, random forest 100%, and SVM 100%.

Keywords: heart rate, machine learning, SVM, decision tree, logistic regression, random forest

Procedia PDF Downloads 135

Authors: Kiomars Sefidi

Abstract:

Dead and habitat tree such as fallen logs, snags, stumps and cracks and loos bark etc. is regarded as an important ecological component of forests on which many forest dwelling species depend, yet its relation to management history in Caspian forest has gone unreported. The aim of research was to compare the amounts of dead tree and habitat in the forests with historically different intensities of management, including: forests with the long term implication of management (PS), the short-term implication of management (NS) which were compared with semi virgin forest (GS). The number of 405 individual dead and habitat trees were recorded and measured at 109 sampling locations. ANOVA revealed volume of the dead tree in the form and decay classes significantly differ within sites and dead volume in the semi virgin forest significantly higher than managed sites. Comparing the amount of dead and habitat tree in three sites showed that dead tree volume related with management history and significantly differ in three study sites. Also, the numbers of habitat trees including cavities, Cracks and loose bark and Fork split trees significantly vary among sites. Reaching their highest in virgin site and their lowest in the site with the long term implication of management, it was concluded that forest management cause reduction of the amount of dead and habitat tree. Forest management history affect the forest's ability to generate dead tree especially in a large size, thus managing this forest according to ecological sustainable principles require a commitment to maintaining stand structure that allow, continued generation of dead tree in a full range of size.

Keywords: forest biodiversity, cracks trees, fork split trees, sustainable management, Fagus orientalis, Iran

Procedia PDF Downloads 548

Authors: Neha Ahirwar

Abstract:

In the contemporary digital era, the rise of credit card fraud poses a significant threat to both financial institutions and consumers. As fraudulent activities become more sophisticated, there is an escalating demand for robust and effective fraud detection mechanisms. Advanced machine learning algorithms have become crucial tools in addressing this challenge. This paper conducts a thorough examination of the design and evaluation of a credit card fraud detection system, utilizing four prominent machine learning algorithms: random forest, logistic regression, decision tree, and XGBoost. The surge in digital transactions has opened avenues for fraudsters to exploit vulnerabilities within payment systems. Consequently, there is an urgent need for proactive and adaptable fraud detection systems. This study addresses this imperative by exploring the efficacy of machine learning algorithms in identifying fraudulent credit card transactions. The selection of random forest, logistic regression, decision tree, and XGBoost for scrutiny in this study is based on their documented effectiveness in diverse domains, particularly in credit card fraud detection. These algorithms are renowned for their capability to model intricate patterns and provide accurate predictions. Each algorithm is implemented and evaluated for its performance in a controlled environment, utilizing a diverse dataset comprising both genuine and fraudulent credit card transactions.

Keywords: efficient credit card fraud detection, random forest, logistic regression, XGBoost, decision tree

Procedia PDF Downloads 57

Authors: Seun Mayowa Sunday

Abstract:

Loan prediction is one of the most significant and recognised fields of research in the banking, insurance, and the financial security industries. Some prediction systems on the market include the construction of static software. However, due to the fact that static software only operates with strictly regulated rules, they cannot aid customers beyond these limitations. Application of many machine learning (ML) techniques are required for loan prediction. Four separate machine learning models, random forest (RF), decision tree (DT), k-nearest neighbour (KNN), and logistic regression, are used to create the loan prediction model. Using the anaconda navigator and the required machine learning (ML) libraries, models are created and evaluated using the appropriate measuring metrics. From the finding, the random forest performs with the highest accuracy of 80.17% which was later implemented into the Django framework. For real-time testing, the web application is deployed on the Alibabacloud which is among the top 4 biggest cloud computing provider. Hence, to the best of our knowledge, this research will serve as the first academic paper which combines the model development and the Django framework, with the deployment into the Alibaba cloud computing application.

Keywords: k-nearest neighbor, random forest, logistic regression, decision tree, django, cloud computing, alibaba cloud

Procedia PDF Downloads 125

Authors: Mark Joseph Quinto, Roan Beronilla, Guiller Damian, Eliza Camaso, Ronaldo Alberto

Abstract:

Forest inventories are essential to assess the composition, structure and distribution of forest vegetation that can be used as baseline information for management decisions. Classical forest inventory is labor intensive and time-consuming and sometimes even dangerous. The use of Light Detection and Ranging (LiDAR) in forest inventory would improve and overcome these restrictions. This study was conducted to determine the possibility of using LiDAR derived data in extracting high accuracy forest biophysical parameters and as a non-destructive method for forest status analysis of San Manual, Pangasinan. Forest resources extraction was carried out using LAS tools, GIS, Envi and .bat scripts with the available LiDAR data. The process includes the generation of derivatives such as Digital Terrain Model (DTM), Canopy Height Model (CHM) and Canopy Cover Model (CCM) in .bat scripts followed by the generation of 17 composite bands to be used in the extraction of forest classification covers using ENVI 4.8 and GIS software. The Diameter in Breast Height (DBH), Above Ground Biomass (AGB) and Carbon Stock (CS) were estimated for each classified forest cover and Tree Count Extraction was carried out using GIS. Subsequently, field validation was conducted for accuracy assessment. Results showed that the forest of San Manuel has 73% Forest Cover, which is relatively much higher as compared to the 10% canopy cover requirement. On the extracted canopy height, 80% of the tree’s height ranges from 12 m to 17 m. CS of the three forest covers based on the AGB were: 20819.59 kg/20x20 m for closed broadleaf, 8609.82 kg/20x20 m for broadleaf plantation and 15545.57 kg/20x20m for open broadleaf. Average tree counts for the tree forest plantation was 413 trees/ha. As such, the forest of San Manuel has high percent forest cover and high CS.

Keywords: carbon stock, forest inventory, LiDAR, tree count

Procedia PDF Downloads 380

Authors: S. Ghorbani, N. I. Polushin

Abstract:

The machinability of workpieces (AISI 1045 Steel, AA2024 aluminum alloy, A48-class30 gray cast iron) in turning operation has been carried out using different types of cutting tool (conventional, cutting tool with holes in toolholder and cutting tool filled up with composite material) under dry conditions on a turning machine at different stages of spindle speed (630-1000 rpm), feed rate (0.05-0.075 mm/rev), depth of cut (0.05-0.15 mm) and tool overhang (41-65 mm). Experimentation was performed as per Taguchi’s orthogonal array. To evaluate the relative importance of factors affecting surface roughness the single decision tree (SDT), Decision tree forest (DTF) and Group method of data handling (GMDH) were applied.

Keywords: decision tree forest, GMDH, surface roughness, Taguchi method, turning process

Procedia PDF Downloads 435

Authors: Abhigyan Hedau, Priya Shelke, Riddhi Mirajkar, Shreyash Chaple, Mrunali Gadekar, Himanshu Akula

Abstract:

The heart is the coordinating centre of the major endocrine glandular structure of the body, which produces hormones that profoundly affect the operations of the body, and diagnosing cardiovascular disease is a difficult but critical task. By extracting knowledge and information about the disease from patient data, data mining is a more practical technique to help doctors detect disorders. We use a variety of machine learning methods here, including logistic regression and support vector classifiers (SVC), K-nearest neighbours Classifiers (KNN), Decision Tree Classifiers, Random Forest classifiers and Gradient Boosting classifiers. These algorithms are applied to patient data containing 13 different factors to build a system that predicts heart disease in less time with more accuracy.

Keywords: logistic regression, support vector classifier, k-nearest neighbour, decision tree, random forest and gradient boosting

Procedia PDF Downloads 44

Authors: Ashish Dhamaniya, Vineet Jain, Rajesh Chouhan

Abstract:

Traffic management is one of the gigantic issue in most of the urban roads in al-most all metropolitan cities in India. Speed is one of the critical traffic parameters for effective Intelligent Transportation System (ITS) implementation as it decides the arrival rate of vehicles on an intersection which are majorly the point of con-gestions. The study aimed to leverage Machine Learning (ML) models to produce precise predictions of speed on urban roadway links. The research objective was to assess how categorized traffic volume and road width, serving as variables, in-fluence speed prediction. Four tree-based regression models namely: Decision Tree (DT), Random Forest (RF), Extra Tree (ET), and Extreme Gradient Boost (XGB)are employed for this purpose. The models' performances were validated using test data, and the results demonstrate that Random Forest surpasses other machine learning techniques and a conventional utility theory-based model in speed prediction. The study is useful for managing the urban roadway network performance under mixed traffic conditions and effective implementation of ITS.

Keywords: stream speed, urban roads, machine learning, traffic flow

Procedia PDF Downloads 65

Authors: Sharon Li, Zhonghang Xia

Abstract:

Post-database search is an essential phase in peptide identification using tandem mass spectrometry (MS/MS) to refine peptide-spectrum matches (PSMs) produced by database search engines. These engines frequently face difficulty differentiating between correct and incorrect peptide assignments. Despite advances in statistical and machine learning methods aimed at improving the accuracy of peptide identification, challenges remain in selecting critical features for these models. In this study, two machine learning models—a random forest tree and a support vector machine—were applied to three datasets to enhance PSMs. SHAP values were utilized to determine the significance of each feature within the models. The experimental results indicate that the random forest model consistently outperformed the SVM across all datasets. Further analysis of SHAP values revealed that the importance of features varies depending on the dataset, indicating that a feature's role in model predictions can differ significantly. This variability in feature selection can lead to substantial differences in model performance, with false discovery rate (FDR) differences exceeding 50% between different feature combinations. Through SHAP value analysis, the most effective feature combinations were identified, significantly enhancing model performance.

Keywords: peptide identification, SHAP value, feature selection, random forest tree, support vector machine

Procedia PDF Downloads 0

Authors: S. Y. Cicekli

Abstract:

In this study, tree-dimensional model of tree was created by using terrestrial close range photogrammetry. For this close range photos were taken. Photomodeler Pro 5 software was used for camera calibration and create three-dimensional model of trees. In first test, three-dimensional model of a tree was created, in the second test three-dimensional model of three trees were created. This study aim is creating three-dimensional model of trees and indicate the use of close-range photogrammetry in forestry. At the end of the study, three-dimensional model of tree and three trees were created. This study showed that usability of close-range photogrammetry for monitoring tree and forests three-dimensional model.

Keywords: close- range photogrammetry, forest, tree, three-dimensional model

Procedia PDF Downloads 383

Authors: Teng-Chiu Lin, Pei-Jen Lee Shaner, Shin-Yu Lin

Abstract:

Both forest age and physical damages due to weather events such as tropical cyclones can influence forest characteristics and subsequently its capacity to sequester carbon. Detangling these influences is therefore a pressing issue under climate change. In this study, we compared the compositional and structural characteristics of three forests in Taiwan differing in age and severity of typhoon disturbances. We found that the two forests (one old-growth forest and one secondary forest) experiencing more severe typhoon disturbances had shorter stature, higher wood density, higher tree species diversity, and lower typhoon-induced tree mortality than the other secondary forest experiencing less severe typhoon disturbances. On the other hand, the old-growth forest had a larger amount of woody debris than the two secondary forests, suggesting a dominant role of forest age on woody debris accumulation. Of the three forests, only the two experiencing more severe typhoon disturbances formed new gaps following two 2015 typhoons, and between these two forests, the secondary forest gained more gaps than the old-growth forest. Consider that older forests generally have more gaps due to a higher background tree mortality, our findings suggest that the age effects on gap dynamics may be reversed by typhoon disturbances. This study demonstrated the effects of typhoons on forest characteristics, some of which could negate the age effects and rejuvenate older forests. If cyclone disturbances were to intensity under climate change, the capacity of older forests to sequester carbon may be reduced.

Keywords: typhoon, canpy gap, coarse woody debris, forest stature, forest age

Procedia PDF Downloads 264

Authors: Bharatendra Rai

Abstract:

Cutting tools are widely used in manufacturing processes and drilling is the most commonly used machining process. Although drill-bits used in drilling may not be expensive, their breakage can cause damage to expensive work piece being drilled and at the same time has major impact on productivity. Predicting drill-bit breakage, therefore, is important in reducing cost and improving productivity. This study uses twenty features extracted from two degradation signals viz., thrust force and torque. The methodology used involves developing and comparing decision tree, random forest, and multinomial logistic regression models for classifying and predicting drill-bit breakage using degradation signals.

Keywords: degradation signal, drill-bit breakage, random forest, multinomial logistic regression

Procedia PDF Downloads 348

Authors: Saurav Kumar Suman, P. Karthigayani

Abstract:

In this paper the height of the tree is estimated and forest types is classified from the multi temporal RISAT-1 Horizontal-Horizontal (HH) and Horizontal-Vertical (HV) Polarised Satellite Aperture Radar (SAR) data. The novelty of the proposed project is combined use of the Back-scattering Coefficients (Sigma Naught) and the Coherence. It uses Water Cloud Model (WCM). The approaches use two main steps. (a) Extraction of the different forest parameter data from the Product.xml, BAND-META file and from Grid-xxx.txt file come with the HH & HV polarized data from the ISRO (Indian Space Research Centre). These file contains the required parameter during height estimation. (b) Calculation of the Vegetation and Ground Backscattering, Coherence and other Forest Parameters. (c) Classification of Forest Types using the ENVI 5.0 Tool and ROI (Region of Interest) calculation.

Keywords: RISAT-1, classification, forest, SAR data

Procedia PDF Downloads 401

Authors: Lucky Dartsa Wakawa, Friday Nwabueze Ogana, Temitope Elizabeth Adeniyi

Abstract:

Timely and reliable information on the status of a forest is essential for assessing the extent of regeneration and degradation. However, when such information is lacking effective forest management practices becomes impossible. Therefore, this study assessed the tree species composition, richness, diversity, structure of Oluwa forest reserve with the view of ascertaining it conservation status. A systematic line transect was used in the laying of eight (8) temporary sample plots (TSPs) of size 50m x 50m. Trees with Dbh ≥ 10cm in the selected plots were enumerated, identified and measured. The results indicate that 535 individual trees were enumerated cutting across 26 families and 58 species. The family Sterculiaceae recorded the highest number of species (10) and occurrence (112) representing 17.2% and 20.93% respectively. Celtis zenkeri is the species with the highest number of occurrence of tree per hectare and importance value index (IVI) of 59 and 53.81 respectively. The reserve has the Margalef's index of species richness, Shannon-Weiner diversity Index (H') and Pielou's Species Evenness Index (EH) of 9.07, 3.43 and 0.84 respectively. The forest has a mean Dbh (cm), mean height (m), total basal area/ha (m2) and total volume/ha (m3) of 24.7, 16.9, 36.63 and 602.09 respectively. The important tropical tree species identified includes Diospyros crassiflora Milicia excels, Mansonia altisima, Triplochiton scleroxylon. Despite the level of exploitation in the forest, the forest seems to be resilience. Given the right attention, it could regenerate and replenish to save some of the original species composition of the reserve.

Keywords: forest conservation, forest structure, Lowland tropical forest, South-west Nigeria

Procedia PDF Downloads 338

Authors: Arjun G. Koppad

Abstract:

The study was conducted in Joida taluk of Uttara Kannada district, Karnataka, India, to assess the land use land cover (LULC) and forest aboveground biomass using L band SAR data. The study area covered has dense, moderately dense, and sparse forests. The sampled area was 0.01 percent of the forest area with 30 sampling plots which were selected randomly. The point center quadrate (PCQ) method was used to select the tree and collected the tree growth parameters viz., tree height, diameter at breast height (DBH), and diameter at the tree base. The tree crown density was measured with a densitometer. Each sample plot biomass was estimated using the standard formula. In this study, the LULC classification was done using Freeman-Durden, Yamaghuchi and Pauli polarimetric decompositions. It was observed that the Freeman-Durden decomposition showed better LULC classification with an accuracy of 88 percent. An attempt was made to estimate the aboveground biomass using SAR backscatter. The ALOS-2 PALSAR-2 L-band data (HH, HV, VV &VH) fully polarimetric quad-pol SAR data was used. SAR backscatter-based regression model was implemented to retrieve forest aboveground biomass of the study area. Cross-polarization (HV) has shown a good correlation with forest above-ground biomass. The Multi Linear Regression analysis was done to estimate aboveground biomass of the natural forest areas of the Joida taluk. The different polarizations (HH &HV, VV &HH, HV & VH, VV&VH) combination of HH and HV polarization shows a good correlation with field and predicted biomass. The RMSE and value for HH & HV and HH & VV were 78 t/ha and 0.861, 81 t/ha and 0.853, respectively. Hence the model can be recommended for estimating AGB for the dense, moderately dense, and sparse forest.

Keywords: forest, biomass, LULC, back scatter, SAR, regression

Procedia PDF Downloads 22

Authors: Sudabe Amini, Jamasb Nozari, Somaye Rahimi

Abstract:

Bark beetles are one of the most destructive groups of pests in the forest and green space. Mediterranean pine Engraver Orthotomicus erosus (Wollston) is the dominant species in the pine forests of Iran. Pine forests are considered a crucial region in the world and need high protection. Although there is no effective control method, mass trapping is the most common method to suppress the bark beetle population. Due to this, from 2018-to 2020, a survey was conducted on bark beetles mass trapping by using two kinds of traps, including pheromone and tree trap. These traps were evaluated in 10 different sites of pine forests. The statistical results proved that significant differences between the pheromone trap and tree trap were observed. It confirmed that the pheromone trap attracted more beetles than the tree trap. The results of this study suggest that the most effective and applicable method in bark beetle’s management of pines forest is using a pheromone trap that suppresses and maintains bark beetle’s population at an economic level, although tree traps attract bark beetles too. In the future, using tree-pheromone traps, which would synergist attraction of more bark beetles, is recommended.

Keywords: bark beetle, pines forest, Orthotomicus erosus, pheromone trap, tree trap

Procedia PDF Downloads 161

Authors: Mindaye Teshome, Nesibu Yahya, Carlos Moreira Miquelino Eleto Torres, Pedro Manuel Villaa, Mehari Alebachew

Abstract:

Arbagugu forest is one of the remnant dry Afromontane forests under severe anthropogenic disturbances in central Ethiopia. Despite this fact, up-to-date information is lacking about the status of the forest and its role in climate change mitigation. In this study, we evaluated the woody species composition, structure, biomass, and carbon stock in this forest. We employed a systematic random sampling design and established fifty-three sample plots (20 × 100 m) to collect the vegetation data. A total of 37 woody species belonging to 25 families were recorded. The density of seedlings, saplings, and matured trees were 1174, 101, and 84 stems ha-1, respectively. The total basal area of trees with DBH (diameter at breast height) ≥ 2 cm was 21.3 m2 ha-1. The characteristic trees of dry Afromontane Forest such as Podocarpus falcatus, Juniperus procera, and Olea europaea subsp. cuspidata exhibited a fair regeneration status. On the contrary, the least abundant species Lepidotrichilia volkensii, Canthium oligocarpum, Dovyalis verrucosa, Calpurnia aurea, and Maesa lanceolata exhibited good regeneration status. Some tree species such as Polyscias fulva, Schefflera abyssinica, Erythrina brucei, and Apodytes dimidiata lack regeneration. The total carbon stored in the forest ranged between 6.3 Mg C ha-1 and 835.6 Mg C ha-1. This value is equivalent to 639.6 Mg C ha-1. The forest had a very low number of woody species composition and diversity. The regeneration study also revealed that a significant number of tree species had unsatisfactory regeneration status. Besides, the forest had a lower carbon stock density compared with other dry Afromontane forests. This implies the urgent need for forest conservation and restoration activities by the local government, conservation practitioners, and other concerned bodies to maintain the forest and sustain the various ecosystem goods and services provided by the Arbagugu forest.

Keywords: aboveground biomass, forest regeneration, climate change, biodiversity conservation, restoration

Procedia PDF Downloads 100

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 316

Authors: Nubwimana Rachel, Mugabowindekwe Maurice

Abstract:

Trees play a crucial role in maintaining biodiversity and providing various ecological services. Traditional methods of counting trees are time-consuming, and there is a need for more efficient techniques. However, deep learning makes it feasible to identify the multi-scale elements hidden in aerial imagery. This research focuses on the application of deep learning techniques for tree detection and counting in both forest and non-forest areas through the exploration of the deep learning application for automated tree detection and counting using satellite imagery. The objective is to identify the most effective model for automated tree counting. We used different deep learning models such as YOLOV7, SSD, and UNET, along with Generative Adversarial Networks to generate synthetic samples for training and other augmentation techniques, including Random Resized Crop, AutoAugment, and Linear Contrast Enhancement. These models were trained and fine-tuned using satellite imagery to identify and count trees. The performance of the models was assessed through multiple trials; after training and fine-tuning the models, UNET demonstrated the best performance with a validation loss of 0.1211, validation accuracy of 0.9509, and validation precision of 0.9799. This research showcases the success of deep learning in accurate tree counting through remote sensing, particularly with the UNET model. It represents a significant contribution to the field by offering an efficient and precise alternative to conventional tree-counting methods.

Keywords: remote sensing, deep learning, tree counting, image segmentation, object detection, visualization

Procedia PDF Downloads 64

Authors: Funmilayo Sarah Eguakun, Peter Oluremi Adesoye

Abstract:

One of the major problems being faced by human society is that the global temperature is believed to be rising due to human activity that releases carbon IV oxide (CO2) to the atmosphere. Carbon IV oxide is the most important greenhouse gas influencing global warming and possible climate change. With climate change becoming alarming, reducing CO2 in our atmosphere has become a primary goal of international efforts. Forest landsare major sink and could absorb large quantities of carbon if the trees are judiciously managed. The study aims at estimating the carbon sequestration capacity of Pinus caribaea (pine)and Tectona grandis (Teak) under the prevailing environmental conditions and exploring tree growth variables that influencesthe carbon sequestration capacity in Omo Forest Reserve, Ogun State, Nigeria. Improving forest management by manipulating growth characteristics that influences carbon sequestration could be an adaptive strategy of forestry to climate change. Random sampling was used to select Temporary Sample Plots (TSPs) in the study area from where complete enumeration of growth variables was carried out within the plots. The data collected were subjected to descriptive and correlational analyses. The results showed that average carbon stored by Pine and Teak are 994.4±188.3 Kg and 1350.7±180.6 Kg respectively. The difference in carbon stored in the species is significant enough to consider choice of species relevant in climate change adaptation strategy. Tree growth variables influence the capacity of the tree to sequester carbon. Height, diameter, volume, wood density and age are positively correlated to carbon sequestration. These tree growth variables could be manipulated by the forest manager as an adaptive strategy for climate change while plantations of high wood density speciescould be relevant for management strategy to increase carbon storage.

Keywords: adaptation, carbon sequestration, climate change, growth variables, wood density

Procedia PDF Downloads 374

Authors: Bilel Chalghaf, Mathieu Varin

Abstract:

Forest characterization in Quebec, Canada, is usually assessed based on photo-interpretation at the stand level. For species identification, this often results in a lack of precision. Very high spatial resolution imagery, such as DigitalGlobe, and Light Detection and Ranging (LiDAR), have the potential to overcome the limitations of aerial imagery. To date, few studies have used that data to map a large number of species at the tree level using machine learning techniques. The main objective of this study is to map 11 individual high tree species ( > 17m) at the tree level using an object-based approach in the broadleaf forest of Kenauk Nature, Quebec. For the individual tree crown segmentation, three canopy-height models (CHMs) from LiDAR data were assessed: 1) the original, 2) a filtered, and 3) a corrected model. The corrected CHM gave the best accuracy and was then coupled with imagery to refine tree species crown identification. When compared with photo-interpretation, 90% of the objects represented a single species. For modeling, 313 variables were derived from 16-band WorldView-3 imagery and LiDAR data, using radiance, reflectance, pixel, and object-based calculation techniques. Variable selection procedures were employed to reduce their number from 313 to 16, using only 11 bands to aid reproducibility. For classification, a global approach using all 11 species was compared to a semi-hierarchical hybrid classification approach at two levels: (1) tree type (broadleaf/conifer) and (2) individual broadleaf (five) and conifer (six) species. Five different model techniques were used: (1) support vector machine (SVM), (2) classification and regression tree (CART), (3) random forest (RF), (4) k-nearest neighbors (k-NN), and (5) linear discriminant analysis (LDA). Each model was tuned separately for all approaches and levels. For the global approach, the best model was the SVM using eight variables (overall accuracy (OA): 80%, Kappa: 0.77). With the semi-hierarchical hybrid approach, at the tree type level, the best model was the k-NN using six variables (OA: 100% and Kappa: 1.00). At the level of identifying broadleaf and conifer species, the best model was the SVM, with OA of 80% and 97% and Kappa values of 0.74 and 0.97, respectively, using seven variables for both models. This paper demonstrates that a hybrid classification approach gives better results and that using 16-band WorldView-3 with LiDAR data leads to more precise predictions for tree segmentation and classification, especially when the number of tree species is large.

Keywords: tree species, object-based, classification, multispectral, machine learning, WorldView-3, LiDAR

Procedia PDF Downloads 127

Authors: Miral Selim, May Haggag, Ibrahim Abotaleb

Abstract:

The aging of transportation infrastructure presents significant challenges, particularly concerning the monitoring and maintenance of bridges. This study investigates the application of Random Forest algorithms for predictive modeling of bridge conditions, utilizing data from the US National Bridge Inventory (NBI). The research is significant as it aims to improve bridge management through data-driven insights that can enhance maintenance strategies and contribute to overall safety. Random Forest is chosen for its robustness, ability to handle complex, non-linear relationships among variables, and its effectiveness in feature importance evaluation. The study begins with comprehensive data collection and cleaning, followed by the identification of key variables influencing bridge condition ratings, including age, construction materials, environmental factors, and maintenance history. Random Forest is utilized to examine the relationships between these variables and the predicted bridge conditions. The dataset is divided into training and testing subsets to evaluate the model's performance. The findings demonstrate that the Random Forest model effectively enhances the understanding of factors affecting bridge conditions. By identifying bridges at greater risk of deterioration, the model facilitates proactive maintenance strategies, which can help avoid costly repairs and minimize service disruptions. Additionally, this research underscores the value of data-driven decision-making, enabling better resource allocation to prioritize maintenance efforts where they are most necessary. In summary, this study highlights the efficiency and applicability of Random Forest in predictive modeling for bridge management. Ultimately, these findings pave the way for more resilient and proactive management of bridge systems, ensuring their longevity and reliability for future use.

Keywords: data analysis, random forest, predictive modeling, bridge management

Procedia PDF Downloads 2

Authors: Saba Ebrahimi, Hedieh Ashrafi

Abstract:

Predicting the cover type of forests is a challenge for natural resource managers. In this project, we aim to perform a comprehensive comparative study of two well-known classification methods, support vector machine (SVM) and decision tree (DT). The comparison is first performed among different types of each classifier, and then the best of each classifier will be compared by considering different evaluation metrics. The effect of boosting and bagging for decision trees is also explored. Furthermore, the effect of principal component analysis (PCA) and feature selection is also investigated. During the project, the forest cover-type dataset from the remote sensing and GIS program is used in all computations.

Keywords: classification methods, support vector machine, decision tree, forest cover-type dataset

Procedia PDF Downloads 209

Authors: Abdullah Al Farwan, Ya Zhang

Abstract:

In today’s educational arena, it is critical to understand educational data and be able to evaluate important aspects, particularly data on student achievement. Educational Data Mining (EDM) is a research area that focusing on uncovering patterns and information in data from educational institutions. Teachers, if they are able to predict their students' class performance, can use this information to improve their teaching abilities. It has evolved into valuable knowledge that can be used for a wide range of objectives; for example, a strategic plan can be used to generate high-quality education. Based on previous data, this paper recommends employing data mining techniques to forecast students' final grades. In this study, five data mining methods, Decision Tree, JRip, Naive Bayes, Multi-layer Perceptron, and Random Forest with wrapper feature selection, were used on two datasets relating to Portuguese language and mathematics classes lessons. The results showed the effectiveness of using data mining learning methodologies in predicting student academic success. The classification accuracy achieved with selected algorithms lies in the range of 80-94%. Among all the selected classification algorithms, the lowest accuracy is achieved by the Multi-layer Perceptron algorithm, which is close to 70.45%, and the highest accuracy is achieved by the Random Forest algorithm, which is close to 94.10%. This proposed work can assist educational administrators to identify poor performing students at an early stage and perhaps implement motivational interventions to improve their academic success and prevent educational dropout.

Keywords: classification algorithms, decision tree, feature selection, multi-layer perceptron, Naïve Bayes, random forest, students’ academic performance

Procedia PDF Downloads 160

Authors: Jian Yang, Atsushi Yagi

Abstract:

Tree-grass coexistence system is of great importance for forest ecology. Mathematical models are being proposed to study the dynamics of tree-grass coexistence and the stability of the systems. However, few of the models concentrates on spatial dynamics of the tree-grass coexistence. In this study, we modified an age-structured continuous-space population model for forests, obtaining an age-structured continuous-space population model for the tree-grass competition model. In the model, for thermal competitions, adult trees can out-compete grass, and grass can out-compete seedlings. We mathematically studied the model to make sure tree-grass coexistence solutions exist. Numerical experiments demonstrated that a fraction of area that trees or grass occupies can affect whether the coexistence is stable or not. We also tried regulating the mortality of adult trees with other parameters and the fraction of area trees and grass occupies were fixed; results show that the mortality of adult trees is also a factor affecting the stability of the tree-grass coexistence in this model.

Keywords: population-structured models, stabilities of ecosystems, thermal competitions, tree-grass coexistence systems

Procedia PDF Downloads 150

Authors: Anjali Chouksey, Riya Nimje, Jahanvi Saraf

Abstract:

Online transactions have increased dramatically in this new ‘social-distancing’ era. With online transactions, Fraud in online payments has also increased significantly. Frauds are a significant problem in various industries like insurance companies, baking, etc. These frauds include leaking sensitive information related to the credit card, which can be easily misused. Due to the government also pushing online transactions, E-commerce is on a boom. But due to increasing frauds in online payments, these E-commerce industries are suffering a great loss of trust from their customers. These companies are finding credit card fraud to be a big problem. People have started using online payment options and thus are becoming easy targets of credit card fraud. In this research paper, we will be discussing machine learning algorithms. We have used a decision tree, XGBOOST, k-nearest neighbour, logistic-regression, random forest, and SVM on a dataset in which there are transactions done online mode using credit cards. We will test all these algorithms for detecting fraud cases using the confusion matrix, F1 score, and calculating the accuracy score for each model to identify which algorithm can be used in detecting frauds.

Keywords: machine learning, fraud detection, artificial intelligence, decision tree, k nearest neighbour, random forest, XGBOOST, logistic regression, support vector machine

Procedia PDF Downloads 143