Search results for: random forest classifier

Authors: Mojo Mengistu Gelasso

Abstract:

The tropical forest is considered the most important forest ecosystem for mitigating climate change by sequestering a high amount of carbon. The potential carbon stock of the forest can be influenced by many factors. Therefore, studying these factors is crucial for understanding the determinants that affect the potential for woody carbon storage in the forest. This study was conducted to evaluate the potential for woody carbon stock and how it varies based on plant community types, as well as along altitudinal, slope, and aspect gradients in the Munessa dry Afromontane forest. Vegetation data was collected using systematic sampling. Five line transects were established at 100 m intervals along the altitudinal gradient between two consecutive transect lines. On each transect, 10 quadrats (20 x 20 m), separated by 200 m, were established. The woody carbon was estimated using an appropriate allometric equation formulated for tropical forests. The data was analyzed using one-way ANOVA in R software. The results showed that the total woody carbon stock of the Munessa forest was 210.43 ton/ha. The analysis of variance revealed that woody carbon density varied significantly based on environmental factors, while community types had no significant effect. The highest mean carbon stock was found at middle altitudes (2367-2533 m.a.s.l), lower slopes (0-13%), and west-facing aspects. The Podocarpus falcatus-Croton macrostachyus community type also contributed a higher woody carbon stock, as larger tree size classes and older trees dominated it. Overall, the potential for woody carbon sequestration in this study was strongly associated with environmental variables. Additionally, the uneven distribution of species with larger diameter at breast height (DBH) in the study area might be linked to anthropogenic factors, as the current forest growth indicates characteristics of a secondary forest. Therefore, our study suggests that the development and implementation of a sustainable forest management plan is necessary to increase the carbon sequestration potential of this forest and mitigate climate change.

Keywords: munessa forest, woody carbon stock, environmental factors, climate mitigation

Procedia PDF Downloads 37

Authors: Mengistu Gelasso Mojo

Abstract:

The tropical forest is considered the most important forest ecosystem for mitigating climate change by sequestering a high amount of carbon. The potential carbon stock of the forest can be influenced by many factors. Therefore, studying these factors is crucial for understanding the determinants that affect the potential for woody carbon storage in the forest. This study was conducted to evaluate the potential for woody carbon stock and how it varies based on plant community types, as well as along altitudinal, slope, and aspect gradients in the Munessa dry Afromontane forest. Vegetation data was collected using systematic sampling. Five line transects were established at 100 m intervals along the altitudinal gradient between two consecutive transect lines. On each transect, 10 quadrats (20 x 20 m), separated by 200 m, were established. The woody carbon was estimated using an appropriate allometric equation formulated for tropical forests. The data was analyzed using one-way ANOVA in R software. The results showed that the total woody carbon stock of the Munessa forest was 210.43 ton/ha. The analysis of variance revealed that woody carbon density varied significantly based on environmental factors, while community types had no significant effect. The highest mean carbon stock was found at middle altitudes (2367-2533 m.a.s.l), lower slopes (0-13%), and west-facing aspects. The Podocarpus falcatus-Croton macrostachyus community type also contributed a higher woody carbon stock, as larger tree size classes and older trees dominated it. Overall, the potential for woody carbon sequestration in this study was strongly associated with environmental variables. Additionally, the uneven distribution of species with larger diameter at breast height (DBH) in the study area might be linked to anthropogenic factors, as the current forest growth indicates characteristics of a secondary forest. Therefore, our study suggests that the development and implementation of a sustainable forest management plan is necessary to increase the carbon sequestration potential of this forest and mitigate climate change.

Keywords: munessa forest, woody carbon stock, environmental factors, climate mitigation

Procedia PDF Downloads 41

Authors: Said Alshukri, Mazhar Hussain Malik

Abstract:

Green hydrogen is hydrogen produced using renewable energy sources. In the last few years, Oman aimed to reduce its dependency on fossil fuels. Recently, the hydrogen economy has become a global trend, and many countries have started to investigate the feasibility of implementing this sector. Oman created an alliance to establish the policy and rules for this sector. With motivation coming from both global and local interest in green hydrogen, this paper investigates the potential of producing hydrogen from wind and solar energies in three different locations in Oman, namely Duqm, Salalah, and Sohar. By using machine learning-based software “WEKA” and local metrological data, the project was designed to figure out which location has the highest wind and solar energy potential. First, various supervised models were tested to obtain their prediction accuracy, and it was found that the Random Forest (RF) model has the best prediction performance. The RF model was applied to 2021 metrological data for each location, and the results indicated that Duqm has the highest wind and solar energy potential. The system of one wind turbine in Duqm can produce 8335 MWh/year, which could be utilized in the water electrolysis process to produce 88847 kg of hydrogen mass, while a solar system consisting of 2820 solar cells is estimated to produce 1666.223 MWh/ year which is capable of producing 177591 kg of hydrogen mass.

Keywords: green hydrogen, machine learning, wind and solar energies, WEKA, supervised models, random forest

Procedia PDF Downloads 39

Authors: Emmanuel Osaze Oshoiribhor, Adetokunbo MacGregor John-Otumu

Abstract:

In recent years, there has been a desire to forecast student academic achievement prior to graduation. This is to help them improve their grades, particularly for individuals with poor performance. The goal of this study is to employ supervised learning techniques to construct a predictive model for student academic achievement. Many academics have already constructed models that predict student academic achievement based on factors such as smoking, demography, culture, social media, parent educational background, parent finances, and family background, to name a few. This feature and the model employed may not have correctly classified the students in terms of their academic performance. This model is built using a logistic regression classifier with basic features such as the previous semester's course score, attendance to class, class participation, and the total number of course materials or resources the student is able to cover per semester as a prerequisite to predict if the student will perform well in future on related courses. The model outperformed other classifiers such as Naive bayes, Support vector machine (SVM), Decision Tree, Random forest, and Adaboost, returning a 96.7% accuracy. This model is available as a desktop application, allowing both instructors and students to benefit from user-friendly interfaces for predicting student academic achievement. As a result, it is recommended that both students and professors use this tool to better forecast outcomes.

Keywords: artificial intelligence, ML, logistic regression, performance, prediction

Procedia PDF Downloads 64

Authors: Walid Moudani

Abstract:

The healthcare environment is generally perceived as being information rich yet knowledge poor. However, there is a lack of effective analysis tools to discover hidden relationships and trends in data. In fact, valuable knowledge can be discovered from application of data mining techniques in healthcare system. In this study, a proficient methodology for the extraction of significant patterns from the coronary heart disease warehouses for heart attack prediction, which unfortunately continues to be a leading cause of mortality in the whole world, has been presented. For this purpose, we propose to enumerate dynamically the optimal subsets of the reduced features of high interest by using rough sets technique associated to dynamic programming. Therefore, we propose to validate the classification using Random Forest (RF) decision tree to identify the risky heart disease cases. This work is based on a large amount of data collected from several clinical institutions based on the medical profile of patient. Moreover, the experts’ knowledge in this field has been taken into consideration in order to define the disease, its risk factors, and to establish significant knowledge relationships among the medical factors. A computer-aided system is developed for this purpose based on a population of 525 adults. The performance of the proposed model is analyzed and evaluated based on set of benchmark techniques applied in this classification problem.

Keywords: multi-classifier decisions tree, features reduction, dynamic programming, rough sets

Procedia PDF Downloads 381

Authors: Saba Gachpaz, Hamid Reza Heidari

Abstract:

The sharp increase in population growth leads to more pressure on agricultural areas to satisfy the food supply. To achieve this, more resources should be consumed and, besides other environmental concerns, highlight sustainable agricultural development. Land-use management is a crucial factor in obtaining optimum productivity. Machine learning is a widely used technique in the agricultural sector, from yield prediction to customer behavior. This method focuses on learning and provides patterns and correlations from our data set. In this study, nine physical control factors, namely, soil classification, electrical conductivity, normalized difference water index (NDWI), groundwater level, elevation, annual precipitation, pH of water, annual mean temperature, and slope in the alluvial plain in Khuzestan (an agricultural hotspot in Iran) are used to decide the best agricultural land use for both rainfed and irrigated agriculture for ten different crops. For this purpose, each variable was imported into Arc GIS, and a raster layer was obtained. In the next level, by using training samples, all layers were imported into the python environment. A random forest model was applied, and the weight of each variable was specified. In the final step, results were visualized using a digital elevation model, and the importance of all factors for each one of the crops was obtained. Our results show that despite 62% of the study area being allocated to agricultural purposes, only 42.9% of these areas can be defined as a suitable class for cultivation purposes.

Keywords: land suitability, machine learning, random forest, sustainable agriculture

Procedia PDF Downloads 53

Authors: Songul Cinaroglu

Abstract:

Regional planning in health has gained speed for developing countries in recent years. In Turkey, 89 different Public Hospital Unions (PHUs) were conducted based on provincial levels. In this study technical efficiencies of 89 PHUs were examined by using Data Envelopment Analysis (DEA) and machine learning techniques by dividing them into two clusters in terms of similarities of input and output indicators. Number of beds, physicians and nurses determined as input variables and number of outpatients, inpatients and surgical operations determined as output indicators. Before performing DEA, PHUs were grouped into two clusters. It is seen that the first cluster represents PHUs which have higher population, demand and service density than the others. The difference between clusters was statistically significant in terms of all study variables (p ˂ 0.001). After clustering, DEA was performed for general and for two clusters separately. It was found that 11% of PHUs were efficient in general, additionally 21% and 17% of them were efficient for the first and second clusters respectively. It is seen that PHUs, which are representing urban parts of the country and have higher population and service density, are more efficient than others. Random forest decision tree graph shows that number of inpatients is a determinative factor of efficiency of PHUs, which is a measure of service density. It is advisable for public health policy makers to use statistical learning methods in resource planning decisions to improve efficiency in health care.

Keywords: public hospital unions, efficiency, data envelopment analysis, random forest

Procedia PDF Downloads 103

Authors: Ehikhamele Isaac Erhomosele, Ogbogu Sunday Sylvester

Abstract:

A biodiversity survey was conducted in Shasha Forest Reserve, Ife southern, Osun State, Nigeria between May 2019 to April 2021 with a view to determining the nature of Odonata fauna of the forest. A total number of 1055 individuals of adult dragonflies and damselflies belonging to 8 families (Aeshnidae, Calopterygidae, Chlorocyphidae, Coenagrionidae, Gomphidae, Lestidae, Libellulidae and Platycnemididae) were recorded. Five (5) of these families of which belong to the suborder Zygoptera, and the remaining three (3) to Anisoptera. Libellulidae was the most abundant family while Gomphidae recorded the least representative. No new species of Odonata was recorded. Most of the families reported were previously been documented in the tropical region. Logging activities and human disturbance have been attributed to the nature of Odonata species in the Forest. It is therefore recommended that logging should be restricted to designated areas of the forest and regulated by the Department of Forestry of Osun State Ministry of Agriculture and Natural Resources in conjunction with the Federal Ministry of Environment.

Keywords: checklist, Odonata, Shasha, families

Procedia PDF Downloads 66

Authors: K. E. Ch. Vidyasagar, M. Moghavvemi, T. S. S. T. Prabhat

Abstract:

Epilepsy is a global problem, and with seizures eluding even the smartest of diagnoses a requirement for automatic detection of the same using electroencephalogram (EEG) would have a huge impact in diagnosis of the disorder. Among a multitude of methods for automatic epilepsy detection, one should find the best method out, based on accuracy, for classification. This paper reasons out, and rationalizes, the best methods for classification. Accuracy is based on the classifier, and thus this paper discusses classifiers like quadratic discriminant analysis (QDA), classification and regression tree (CART), support vector machine (SVM), naive Bayes classifier (NBC), linear discriminant analysis (LDA), K-nearest neighbor (KNN) and artificial neural networks (ANN). Results show that ANN is the most accurate of all the above stated classifiers with 97.7% accuracy, 97.25% specificity and 98.28% sensitivity in its merit. This is followed closely by SVM with 1% variation in result. These results would certainly help researchers choose the best classifier for detection of epilepsy.

Keywords: classification, seizure, KNN, SVM, LDA, ANN, epilepsy

Procedia PDF Downloads 489

Authors: John White

Abstract:

This study investigated the effects of practice schedules on learning and performance in golf putting, specifically focusing on the impact of increasing contextual interference (CI). University students (n=7) were randomly assigned to blocked, random, or increasing practice schedules. During acquisition, participants performed 135 putting trials using different weighted golf balls. The blocked group followed a specific sequence of ball weights, while the random group practiced with the balls in a random order. The increasing group started with a blocked schedule, transitioned to a serial schedule, and concluded with a random schedule. Retention and transfer tests were conducted 24 hours later. The results indicated that high levels of CI (random practice) were more beneficial for learning than low levels of CI (blocked practice). The increasing practice schedule, incorporating blocked, serial, and random practice, demonstrated advantages over traditional blocked and random schedules. Additionally, EEG was used to explore the neurophysiological effects of the increasing practice schedule.

Keywords: skill acquisition, motor control, learning, contextual interference

Procedia PDF Downloads 61

Authors: Qing Li, Maiko Kobayashi, Shigeyoshi Kumeda, Hiroko Ochiai, Toshiya Ochiai, Takashi Miura, Takahide Kagawa, Michiko Imai, Toshiaki Otsuka, Tomoyuki Kawada

Abstract:

In the present study, we investigated the effects of a forest bathing program on cardiovascular and metabolic parameters. Nineteen healthy male subjects (mean age: 51.3 ± 8.8 years) were selected after obtaining informed consent. These subjects took day trips to a forest park named Akasawa Shizen Kyuyourin, Agematsu, Nagano Prefecture (situated in central Japan), and to an urban area of Nagano Prefecture as a control in August 2015. On both trips, they walked 2.6 km for 80 min each in the morning and afternoon on Saturdays. Blood and urine were sampled in the morning before and after each trip. Cardiovascular and metabolic parameters were measured. Blood pressure and pulse rate were measured by an ambulatory automatic blood pressure monitor. The Japanese version of the profile of mood states (POMS) test was conducted before, during and after the trips. Ambient temperature and humidity were monitoring during the trips. The forest bathing program significantly reduced pulse rate, and significantly increased the score for vigor and decreased the scores for depression, fatigue, and confusion in the POMS test. The levels of urinary noradrenaline and dopamine after forest bathing were significantly lower than those after urban area walking, suggesting the relaxing effect of the forest bathing program. The level of adiponectin in serum after the forest bathing program was significantly greater than that after urban area walking. There was no significant difference in blood pressure between forest and urban area trips during the trips.

Keywords: ambient temperature, blood pressure, forest bathing, forest therapy, human health, POMS, pulse rate

Procedia PDF Downloads 407

Authors: Arzyana Sunkar, Yanto Santosa, Intan Purnamasari, Yohanna Dalimunthe

Abstract:

A variety of negative allegations have criticized the Indonesian oil palm plantations as being environmentally unfriendly. One of the important allegations thus must be verified is that expansion of Indonesian oil palm plantation has increased the deforestation rate of primary tropical forest. In relation to this, a research was conducted to study the origin or history of the status and land use of 8 private oil palm plantations (with a total of 46,372.38 ha) located in Riau Province. Several methods were employed: (1) conducting analysis of overlay maps between oil palm plantation studied with the 1986 Forest Map Governance Agreement (TGHK) and the 1994 and 2014 Riau Provincial Spatial Plans(RTRWP); (2) studying the Cultivation Right on Land (HGU) documents including the Forestry Ministerial Decree on the release of forest area and (3) interpretation of lands at imagery of bands 542, covering 3 years before and after the oil palm industries operated. In addition, field cross-checked, and interviews were conducted with National Land Agency, Plantation and Forestry Office and community figures. The results indicated that as much as 1.95% of the oil palm plantations under study were converted from production forest, 30.34% from limited production forest and 67.70% from area for other usage /conversion production forest. One year prior to the establishment of the plantations, the land cover types comprised of rubber plantations (49.96%), secondary forest (35.99%), bare land (10.17%), shrubs (3.03%) and mixed dryland farming-shrubs (0.84%), whereas the land use types comprised of 35.99% forest concession areas, 14.04% migrants dryland farms, and 49.96% Cultivation Right on Land of other companies. These results indicated that most of the private oil palm plantations under study, resulted from the conversion of production forests and the previous land use were not primary forest but rubber plantations and secondary forests.

Keywords: land cover types, land use history, primary forest, private oil palm plantations

Procedia PDF Downloads 199

Authors: Asma A. Alsufyani, Maram A. Alharthi, Maha J. Althobaiti, Manal S. Alharthi, Huda Rizq

Abstract:

Twitter is one of the most popular microblogging sites that allows users to publish short text messages called 'tweets'. Increasing the number of accounts to follow (followings) increases the number of tweets that will be displayed from different topics in an unclassified manner in the timeline of the user. Therefore, it can be a vital solution for many Twitter users to have their tweets in a timeline classified into general categories to save the user’s time and to provide easy and quick access to tweets based on topics. In this paper, we developed a classifier for timeline tweets trained on a dataset consisting of 3600 tweets in total, which were collected from Saudi Twitter and annotated manually. We experimented with the well-known Bag-of-Words approach to text classification, and we used support vector machines (SVM) in the training process. The trained classifier performed well on a test dataset, with an average F1-measure equal to 92.3%. The classifier has been integrated into an application, which practically proved the classifier’s ability to classify timeline tweets of the user.

Keywords: corpus creation, feature extraction, machine learning, short text classification, social media, support vector machine, Twitter

Procedia PDF Downloads 125

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 52

Authors: Manal Suleiman, George Abu-Aqil, Uraib Sharaha, Klaris Riesenberg, Itshak Lapidot, Ahmad Salman, Mahmoud Huleihel

Abstract:

Klebsiella pneumoniae is one of the most aggressive multidrug-resistant bacteria associated with human infections resulting in high mortality and morbidity. Thus, for an effective treatment, it is important to diagnose both the species of infecting bacteria and their susceptibility to antibiotics. Current used methods for diagnosing the bacterial susceptibility to antibiotics are time-consuming (about 24h following the first culture). Thus, there is a clear need for rapid methods to determine the bacterial susceptibility to antibiotics. Infrared spectroscopy is a well-known method that is known as sensitive and simple which is able to detect minor biomolecular changes in biological samples associated with developing abnormalities. The main goal of this study is to evaluate the potential of infrared spectroscopy in tandem with Random Forest and XGBoost machine learning algorithms to diagnose the susceptibility of Klebsiella pneumoniae to antibiotics within approximately 20 minutes following the first culture. In this study, 1190 Klebsiella pneumoniae isolates were obtained from different patients with urinary tract infections. The isolates were measured by the infrared spectrometer, and the spectra were analyzed by machine learning algorithms Random Forest and XGBoost to determine their susceptibility regarding nine specific antibiotics. Our results confirm that it was possible to classify the isolates into sensitive and resistant to specific antibiotics with a success rate range of 80%-85% for the different tested antibiotics. These results prove the promising potential of infrared spectroscopy as a powerful diagnostic method for determining the Klebsiella pneumoniae susceptibility to antibiotics.

Keywords: urinary tract infection (UTI), Klebsiella pneumoniae, bacterial susceptibility, infrared spectroscopy, machine learning

Procedia PDF Downloads 133

Authors: Yasuyo Makido, Vivek Shandas, David J. Sailor, M. Salim Ferwati

Abstract:

Mitigating extreme urban heat is challenging in a desert climate such as Doha, Qatar, since outdoor daytime temperature area often too high for the human body to tolerate. Recent studies demonstrate that cities in arid and semiarid areas can exhibit ‘urban cool islands’ - urban areas that are cooler than the surrounding desert. However, the variation of temperatures as a result of the time of day and factors leading to temperature change remain at the question. To address these questions, we examined the spatial and temporal variation of air temperature in Doha, Qatar by conducting multiple vehicle-base local temperature observations. We also employed three statistical approaches to model surface temperatures using relevant predictors: (1) Ordinary Least Squares, (2) Regression Tree Analysis and (3) Random Forest for three time periods. Although the most important determinant factors varied by day and time, distance to the coast was the significant determinant at midday. A 70%/30% holdout method was used to create a testing dataset to validate the results through Pearson’s correlation coefficient. The Pearson’s analysis suggests that the Random Forest model more accurately predicts the surface temperatures than the other methods. We conclude with recommendations about the types of development patterns that show the greatest potential for reducing extreme heat in air climates.

Keywords: desert cities, tree-structure regression model, urban cool Island, vehicle temperature traverse

Procedia PDF Downloads 365

Authors: Hu Ding, Kai Liu, Guoan Tang

Abstract:

The Chinese Loess Plateau suffers from serious gully erosion induced by natural and human causes. Gully features detection including gully-affected area and its two dimension parameters (length, width, area et al.), is a significant task not only for researchers but also for policy-makers. This study aims at gully-affected area detection in three catchments of Chinese Loess Plateau, which were selected in Changwu, Ansai, and Suide by using unmanned aerial vehicle (UAV). The methodology includes a sequence of UAV data generation, image segmentation, feature calculation and selection, and random forest classification. Two experiments were conducted to investigate the influences of segmentation strategy and feature selection. Results showed that vertical and horizontal root-mean-square errors were below 0.5 and 0.2 m, respectively, which were ideal for the Loess Plateau region. The segmentation strategy adopted in this paper, which considers the topographic information, and optimal parameter combination can improve the segmentation results. Besides, the overall extraction accuracy in Changwu, Ansai, and Suide achieved was 84.62%, 86.46%, and 93.06%, respectively, which indicated that the proposed method for detecting gully-affected area is more objective and effective than traditional methods. This study demonstrated that UAV can bridge the gap between field measurement and satellite-based remote sensing, obtaining a balance in resolution and efficiency for catchment-scale gully erosion research.

Keywords: unmanned aerial vehicle (UAV), object-analysis image analysis, gully erosion, gully-affected area, Loess Plateau, random forest

Procedia PDF Downloads 190

Authors: Alanoud Moraya Aldalan, Abdulaziz Almaleh

Abstract:

A crucial component of maintaining a customer-oriented business as in the telecom industry is understanding the reasons and factors that lead to customer churn. Competition between telecom companies has greatly increased in recent years. It has become more important to understand customers’ needs in this strong market of telecom industries, especially for those who are looking to turn over their service providers. So, predictive churn is now a mandatory requirement for retaining those customers. Machine learning can be utilized to accomplish this. Churn Prediction has become a very important topic in terms of machine learning classification in the telecommunications industry. Understanding the factors of customer churn and how they behave is very important to building an effective churn prediction model. This paper aims to predict churn and identify factors of customers’ churn based on their past service usage history. Aiming at this objective, the study makes use of feature selection, normalization, and feature engineering. Then, this study compared the performance of four different machine learning algorithms on the Orange dataset: Logistic Regression, Random Forest, Decision Tree, and Gradient Boosting. Evaluation of the performance was conducted by using the F1 score and ROC-AUC. Comparing the results of this study with existing models has proven to produce better results. The results showed the Gradients Boosting with feature selection technique outperformed in this study by achieving a 99% F1-score and 99% AUC, and all other experiments achieved good results as well.

Keywords: machine learning, gradient boosting, logistic regression, churn, random forest, decision tree, ROC, AUC, F1-score

Procedia PDF Downloads 106

Authors: D. S. Palimkar

Abstract:

Random fixed point theory has received much attention in recent years, and it is needed for the study of various classes of random equations. The study of random fixed point theorems was initiated by the Prague school of probabilistic in the 1950s. The existence and uniqueness of fixed points for the self-maps of a metric space by altering distances between the points with the use of a control function is an interesting aspect in the classical fixed point theory. In a new category of fixed point problems for a single self-map with the help of a control function that alters the distance between two points in a metric space which they called an altering distance function. In this paper, we prove the results of existence of random common fixed point and its uniqueness for a pair of random mappings under weakly contractive condition for generalizing alter distance function in polish spaces using Random Common Fixed Point Theorem for Generalized Weakly Contractions.

Keywords: Polish space, random common fixed point theorem, weakly contractive mapping, altering function

Procedia PDF Downloads 245

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 205

Authors: Sudhir Kumar Singh, Debashish Chakravarty

Abstract:

Slope stability analysis is an important aspect in the field of geotechnical engineering. It is also important from safety, and economic point of view as any slope failure leads to loss of valuable lives and damage to property worth millions. This paper aims at mitigating the risk of slope failure by studying the effect of different joint sets on the stability of mine pit slopes under the influence of various external factors, namely degree of saturation, rainfall intensity, and seismic coefficients. Supervised machine learning approach has been utilized for making accurate and reliable predictions regarding the stability of slopes based on the value of Factor of Safety. Numerous cases have been studied for analyzing the stability of slopes using the popular Finite Element Method, and the data thus obtained has been used as training data for the supervised machine learning models. The input data has been trained on different supervised machine learning models, namely Random Forest, Decision Tree, Support vector Machine, and XGBoost. Distinct test data that is not present in training data has been used for measuring the performance and accuracy of different models. Although all models have performed well on the test dataset but Random Forest stands out from others due to its high accuracy of greater than 95%, thus helping us by providing a valuable tool at our disposition which is neither computationally expensive nor time consuming and in good accordance with the numerical analysis result.

Keywords: finite element method, geotechnical engineering, machine learning, slope stability

Procedia PDF Downloads 71

Authors: Huong Nguyen Thi Thanh, Van Mai Thi Khanh

Abstract:

For around the world, payments for environmental services have been implemented since the late 1970s in Europe and North America; then, it was spread to Latin America, Asia, Africa, and finally Oceania in 2008. In Vietnam, payments for environmental services are an interesting issue recently with the forest as the main focus and therefore known as the program on payment for forest environmental services (PFES). PFES was piloted in Lam Dong and Son La in 2008 and has been widely applied in many provinces after 2010. PFES is in the orientation for the socialization of national forest protection in Vietnam and has made great strides in the last decade. By using the primary data and secondary data simultaneously, the paper clarifies two cases of implementing PFES in the Vietnam North Central area with the different mechanisms of payment. In the first case at Phu Loc district (Thua Thien Hue province), PFES is an indirect method by a water supply company via the Forest Protection and Development Fund. In the second one at Phong Nha – Ke Bang National Park (Quang Binh Province), tourism companies are the direct payers to forest owners. The paper describes the PFES implementation process at each site, clarifies the payment mechanism, and models the relationship between stakeholders in PFES implementation. Based on the current status of PFES sites, the paper compares and analyzes the advantages and disadvantages of the two payment methods. Finally, the paper proposes recommendations to improve the existing shortcomings in each payment mechanism.

Keywords: advantages and disadvantages, forest environmental services, forest protection, payment mechanism

Procedia PDF Downloads 95

Authors: Usiobaifo Agharese Rosemary, Osaseri Roseline Oghogho

Abstract:

Diabetes is a complex group of disease with a variety of causes; it is a disorder of the body metabolism in the digestion of carbohydrates food. The application of machine learning in the field of medical diagnosis has been the focus of many researchers and the use of recognition and classification model as a decision support tools has help the medical expert in diagnosis of diseases. Considering the large volume of medical data which require special techniques, experience, and high diagnostic skill in the diagnosis of diseases, the application of an artificial intelligent system to assist medical personnel in order to enhance their efficiency and accuracy in diagnosis will be an invaluable tool. In this study will propose a diabetes diagnosis model using rough set and K-nearest Neighbor classifier algorithm. The system consists of two modules: the feature extraction module and predictor module, rough data set is used to preprocess the attributes while K-nearest neighbor classifier is used to classify the given data. The dataset used for this model was taken for University of Benin Teaching Hospital (UBTH) database. Half of the data was used in the training while the other half was used in testing the system. The proposed model was able to achieve over 80% accuracy.

Keywords: classifier algorithm, diabetes, diagnostic model, machine learning

Procedia PDF Downloads 304

Authors: Ayuko Itsuki, Sachiyo Aburatani

Abstract:

Soil neutral sugar contents in Kasuga-yama Hill Primeval Forest, which is a World Heritage Site in Nara, Japan consisting of lowland laurel-leaved forest where natural conditions have been preserved for more than 1,000 years, were examined using the two-step hydrolysis to clarify the source of the neutral sugar and relations with the neutral sugar constituted the soil organic matter and the microbial biomass. Samples were selected from the soil (L, F, H and A horizons) surrounding laurel-leaved (BB-1) and Carpinus japonica (BB-2 and PW) trees for analysis. The neutral sugars were one factor of increasing the fungal and bacterial biomass in the laurel-leaved forest soil (BB-1). The more neutral sugar contents in the Cryptomeria japonica forest soil (PW) contributed to the growth of the bacteria and fungi than those of in the Cryptomeria japonica forest soil (BB-2). The neutral sugars had higher correlation with the numbers of bacteria and fungi counted by the dilution plate count method than by the direct microscopic count method. The numbers of fungi had higher correlation with those of bacteria by the dilution plate method.

Keywords: forest soil, neutral sugars, soil organic matter, two-step hydrolysis

Procedia PDF Downloads 235

Authors: Maffo Maffo Nicole Liliane, Mounmemi Kpoumie Hubert, Libalah Moses, Ouandji Angele, Zapfack Louis

Abstract:

Forest degradation causes biodiversity and carbon loss and thus indirectly contributes to climate change. In order to assess the contribution of forests to climate change mitigation, the present study was conducted in the Ngambe-Ndom-Nyanon Communal Forest with the main objective of assessing the floristic diversity and estimating the carbon stock in the different reservoirs of the said forest. Nine plots of 2000 m² each were installed in 3 TOSs of the forest (young secondary forests, gallery forests and fallow lands) with a total area of 18,000 m² or 1,8 ha. All trees with a Diameter at Breast Height (DBH) ≥ 5 cm were inventoried at 1.30 m from the ground in each plot. Species richness, floristic diversity indices, and structural parameters were studied. 1542 trees divided into 162 species, 122 genera and 44 families were identified. The most important families were listed: Myristicaceae (30.22%), Apocynaceae (25.20%), Fabaceae (24.41%), Euphorbiaceae (22.91%) and Phyllanthaceae (20.23%). The richest genera are: Cola, Macaranga, Oncoba (4 species each); the genera Diospyros, Trichilia, Vitex and Zanthoxylum (3 species each). The ecologically important species within the forest studied are: Funtumia africana (26.14%), Coelocaryon preussii (18.46%), Pycnanthus angolensis (15.57%), Tabernaemontana crassa (14.85%) and Olax subscorpioidea (13.04%). Assessment of carbon stocks in the six forest reservoirs studied (living trees and roots, understorey, dead wood, litter and rootlets) shows that they vary according to the land-use types. It is 119.41 t.C.ha-¹ in gallery forest, 115.2 t.C.ha-¹ in young secondary forest and 90.56 t.C.ha-¹ in fallow. The Wilcoxon statistical test shows that the carbon in the young secondary forest is identical to that in the fallow, which is identical to the carbon in the gallery forest. At the individual species level, the largest diameter class [25-35[ sequesters the most carbon (232.94 tC/ha). This work shows that the quantity of carbon sequestered by a biotope is a function of the age of the stand.

Keywords: floristic diversity, carbon stocks, evergreen forests, communal forest, Ngambé-Ndom-Nyanon

Procedia PDF Downloads 20

Authors: Zohreh Mohammadi, Jan Kaspar, Peter Lohmander, Robert Marusak, Harald Vacik, Ljusk Ola Eriksson

Abstract:

Storms are important damaging agents in European forest ecosystems. In the latest decades, significant economic losses in European forestry occurred due to storms. This study investigates the problem of optimal harvest planning when forest stands risk to be felled by storms. One of the most applicable mathematical methods which are being used to optimize forest management is stochastic dynamic programming (SDP). This method belongs to the adaptive optimization class. Sequential decisions, such as harvest decisions, can be optimized based on sequential information about events that cannot be perfectly predicted, such as the future storms and the future states of wind protection from other forest stands. In this paper, stochastic dynamic programming is used to maximize the expected present value of the profits from an area consisting of several forest stands. The region of analysis is the Czech Republic. The harvest decisions, in a particular time period, should be simultaneously taken in all neighbor stands. The reason is that different stands protect each other from possible winds. The optimal harvest age of a particular stand is a function of wind speed and different wind protection effects. The optimal harvest age often decreases with wind speed, but it cannot be determined for one stand at a time. When we consider a particular stand, this stand also protects other stands. Furthermore, the particular stand is protected by neighbor stands. In some forest stands, it may even be rational to increase the harvest age under the influence of stronger winds, in order to protect more valuable stands in the neighborhood. It is important to integrate wind risk in forestry decision-making.

Keywords: Czech republic, forest stands, stochastic dynamic programming, wind risk

Procedia PDF Downloads 112

Authors: Muhammad Nur Haniff Mohd Noor, Rokiah Kadir, Suriyani Muhamad

Abstract:

The National Forestry Act (NFA) 1984 is the primary forest law that regulates forest-related activities in Peninsular Malaysia. In the 1990s, abundance of illegal logging cases have called for legislative reform of the NFA 1984. As a result, NFA 1984 was amended in 1993 with the principal goal of controlling illegal forest encroachment in the forms of illegal logging, unauthorized harvesting, unlicensed forest settlement and other forms of unlawful activities. At a conceptual level, this paper discusses the policies and strategies implemented under the NFA 1984 (Amendment 1993) that are dedicated to overcome illegal logging. Then, the policies and strategies employed are reviewed and evaluated. Next, this paper conceptually discusses the loopholes of NFA 1984 (Amendment 1993) in relation to aspects where the regulation is considered insufficient to curb illegal logging. In the final section, vital actions and suggested improvements to improve the overall effectiveness of NFA 1984 (Amendment 1993) are examined.

Keywords: forest law and regulation, illegal logging, National Forestry Act 1984, NFA 1984, Amendment 1993, Peninsular Malaysia

Procedia PDF Downloads 232

Authors: Medani Prasad Rijal

Abstract:

The study outlines the impacts of decentralized forest policy on natural Sal (shorea robusta) forests in the Terai region of Nepal. The government has implemented community forestry program to manage the forest resources and improve the livelihood of local people collectively. The forest management authorities such as conserve, manage, develop and use of forest resources were shifted to the local communities, however, the ownership right of the forestland retained by the government. Local communities took the decision on harvesting, distribution, and sell of forest products by fixing the prices independently. The local communities were putting the low value of forest products and distributed among the user households on the name of collective decision. The decision of low valuation is devaluating the worth of forest products. Therefore, the study hypothesized that decision-making capacities are equally prominent next to the decentralized policy and program formulation. To accomplish the study, individual to group level discussions and questionnaire survey methods were applied with executive committee members and user households. The study revealed that the local intuition called Community Forest User Group (CFUG) committee normally took the decisions on consensus basis. Considering to the access and affording capacity of user households having poor economic backgrounds, low pricing mechanism of forest products has been practiced, even though the Sal timber is far expensive in the local market. The local communities thought that low pricing mechanism is accessible to all user households from poor to better off households. However, the analysis of forest products distribution opposed the assumption as most of the Sal timber, which is the most valuable forest product of community forest only purchased by the limited households of better economic conditions. Since the Terai region is heterogeneous by socio-economic conditions, better off households always have higher affording capacity and possibility of taking higher timber benefits because of low price mechanism. On the other hand, the minimum price rate of forest products has poor contribution in community fund collection. Consequently, it has poor support to carry out poverty alleviation activities to poor people. The local communities have been fixed Sal timber price rate around three times cheaper than normal market price, which is a strong evidence of forest product devaluation itself. Finally, the study concluded that the capacity building of local executives as the decision-makers of natural Sal forests is equally indispensable next to the policy and program formulation for effective decentralized forest management. Unilateral decentralized forest policy may devaluate the forest products rather than devolve of power to the local communities and empower to them.

Keywords: community forestry program, decentralized forest policy, Nepal, Sal forests, Terai

Procedia PDF Downloads 300

Authors: István Fekete, Imre Berki, Áron Béni, Katalin Juhos, Marianna Makádi, Zsolt Kotroczó

Abstract:

The average annual precipitation significantly influences the moisture content of the soils and, through this, the decomposition of the organic substances in the soils, the leaching of nutrients from the soils, and the pH of the soils. Climate change, together with the lengthening of the vegetation period and the increasing CO₂ level, can increase the amount of biomass that is formed. Degradation processes, which accelerate as the temperature increases and slow down due to the drying climate, and the change in the degree of leaching can cancel out or strengthen each other's effects. In the course of our research, we looked for oak forests with climate-zonal soils where the geological, geographical and ecological background conditions are as similar as possible, apart from the different annual precipitation averages and the differences that can arise from them. We examined 5 dry and 5 humid Hungarian oak soils. Climate change affects the soils of drier and wetter forests differently. The aim of our research was to compare the content of carbon, nitrogen and some other nutrients, as well as the pH of the soils of humid and dry forests. Showing the effects of the drier climate on the tested soil parameters. In the case of the examined forest soils, we found a significant difference between the soils of dry and humid forests: in the case of the annual average precipitation values (p≥ 0.0001, for dry forest soils: 564±5.2 mm; for humid forest soils: 716±3.8 mm) for pH (p= 0.0004, for dry forest soils: 5.49±0.16; for wet forest soils: 5.36±0.21); for C content (p= 0.0054, for dry forest soils: 6.92%±0.59; for humid forest soils 3.09%±0.24), for N content (p= 0.0022, dry forest in the case of soils: 0.44%±0.047; in the case of humid forest soils: 0.23%±0.013), for the K content (p=0.0017, in the case of dry forest soils: 5684±732 (mg/kg); in the case of humid forest soils 2169±196 (mg/kg)), for the Ca content (p= 0.0096, for dry forest soils: 8207±2118 (mg/kg); for wet forest soils 957±320 (mg/kg)). No significant difference was found in the case of Mg. In a wetter environment, especially if the moisture content of the soil is also optimal for the decomposing organisms during the growing season, the decomposition of organic residues accelerates, and the processes of leaching from the soil are also intensified. The different intensity of the leaching processes is also well reflected in the quantitative differences of Ca and K, and in connection with these, it is also reflected in the difference in pH values. The differences in the C and N content can be explained by differences in the intensity of the decomposition processes. In addition to warming, drying is expected in a significant part of Hungary due to climate change. Thus, the comparison of the soils of dry and humid forests allows us to predict the subsequent changes in the case of the examined parameters.

Keywords: soil nutrients, precipitation difference, climate change, organic matter decomposition, leaching

Procedia PDF Downloads 48

Authors: Anil Kumar Kursenge

Abstract:

In the State of united Andhra Pradesh, many Adivasi People live in areas rich in living and non-living resources, including forests that contain abundant biodiversity, water and minerals. Of united Andhra Pradesh 76.2m population, over five million are Adivasi population of forest landscape. They depend on forests for a substantial part of their livelihoods and close cultural affinity with forests. However, they are the most impoverished population of the State, and the high levels of poverty in Andhra Pradesh forest landscapes are largely an outcome of historically-rooted institutionalised marginalisation. As the State appropriated forests and forest land for itself, it deprived local people of their customary rights in the forest. The local realities of the forest rights deprivations are extremely complex, reflecting a century and a half of compounded processes. With growing population pressure and ever-increasing demands for natural and mineral resources, Adivasi Peoples' lands, which are often relatively rich in resources, become more and more attractive to 'developers.' The development projects and institutionalised marginalisation have been deprived Adivasi people's rights over natural resources has resulted in serious negative effects on Adivasi people and on their lands. Historically, the desire for development for such resources has resulted in the removal, decimation, or extermination of many tribal communities. These deprivations have led to highly conflictual relations between the State and the Adivasi people and forest areas in Andhra Pradesh. Today, the survival of the Adivasi Peoples requires recognition of their rights to the forest resources found in their lands and territories on which they depend for their economic, cultural, survival, spiritual and physical well-being. In this context, this paper attempts to discuss the issues of deprivation with regard to access to forest resources and development projects where many Adivasis in State uprooted from their homes and lands.

Keywords: tribal people, forest rights, livelihoods, deprivation, marginalisation, Andhra Pradesh

Procedia PDF Downloads 171