Search results for: Random Forest Classification

Authors: M. J. Nassiri, A. Vafaei, A. Monadjemi

Abstract:

Random and natural textures classification is still one of the biggest challenges in the field of image processing and pattern recognition. In this paper, texture feature extraction using Slant Hadamard Transform was studied and compared to other signal processing-based texture classification schemes. A parametric SHT was also introduced and employed for natural textures feature extraction. We showed that a subtly modified parametric SHT can outperform ordinary Walsh-Hadamard transform and discrete cosine transform. Experiments were carried out on a subset of Vistex random natural texture images using a kNN classifier.

Keywords: Texture Analysis, Slant Transform, Hadamard, DCT.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2616

Authors: N. R. P Withana, E. Auch

Abstract:

The purpose of this study was to investigate perceptions of climate change risk to forest ecosystems and forestbased communities as well as perceived effectiveness of adaptation strategies for climate change as well as challenges for adaptation. Data was gathered using a pre-tested semi-structured questionnaire. Simple random selection technique was applied. For the majority of issues, the responses were obtained on multi-point likert scales, and the scores provided were, in turn, used to estimate the means and other useful estimates. A composite knowledge index developed using correct responses to a set of self-rated statements were used to evaluate the issues. The mean of the knowledge index was 0.64. Also all respondents recorded values of the knowledge index above 0.25. Increase forest fire was perceived by respondents as the greatest risk to forest eco-system. Decrease access to water supplies was perceived as the greatest risk to livelihoods of forest based communities. The most effective adaptation strategy relevant to climate change risks to forest eco-systems and forest based communities livelihoods in Kathmandu valley in Nepal as perceived by the respondents was reforestation and afforestation. As well, lack of public awareness was perceived as the major limitation for climate change adaptation. However, perceived risks as well as effective adaptation strategies showed an inconsistent association with knowledge indicators and social-cultural variables. The results provide useful information to any party who involve with climate change issues in Nepal, since such attempts would be more effective once the people’s perceptions on these aspects are taken into account.

Keywords: Climate change, forest ecosystems, forest-based communities, risk perceptions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2249

Authors: Mohammed Sghir Taleb

Abstract:

Forest ecosystems in Morocco are subject increasingly to natural and human pressures. Conscious of this problem, Morocco set a strategy that focuses on programs of in-situ and ex-situ biodiversity conservation. This study is the result of a synthesis of various existing studies on biodiversity and forest ecosystems. It gives an overview of Moroccan mountain forest ecosystems and flora diversity. It also focuses on the efforts made by Morocco to conserve and sustainably manage biodiversity.

Keywords: Mountain, forest, ecosystems, conservation, Morocco.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1308

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. This necessitates increased resource consumption and underscores the importance of addressing sustainable agriculture development along with other environmental considerations. 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 10 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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 172

Authors: Mahtab Davari, Charles Edward Okon, Somayeh Aghanavesi

Abstract:

Every institute of learning is usually interested in the performance of enrolled students. The level of these performances determines the approach an institute of study may adopt in rendering academic services. The focus of this paper is to evaluate students' academic performance in given courses of study using machine learning methods. This study evaluated various supervised machine learning classification algorithms such as Logistic Regression (LR), Support Vector Machine (SVM), Random Forest, Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis (LDA), and Quadratic Discriminant Analysis, using selected features to predict study performance. The accuracy, precision, recall, and F1 score obtained from a 5-Fold Cross-Validation were used to determine the best classification algorithm to predict students’ performances. SVM (using a linear kernel), LDA, and LR were identified as the best-performing machine learning methods. Also, using the LR model, this study identified students' educational habits such as reading and paying attention in class as strong determinants for a student to have an above-average performance. Other important features include the academic history of the student and work. Demographic factors such as age, gender, high school graduation, etc., had no significant effect on a student's performance.

Keywords: Student performance, supervised machine learning, prediction, classification, cross-validation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 469

Authors: Alanoud Moraya Aldalan, Abdulaziz Almaleh

Abstract:

A crucial part of maintaining a customer-oriented business in the telecommunications industry is understanding the reasons and factors that lead to customer churn. Competition between telecom companies has greatly increased in recent years, which has made it more important to understand customers’ needs in this strong market. For those who are looking to turn over their service providers, understanding their needs is especially important. Predictive churn is now a mandatory requirement for retaining customers in the telecommunications industry. Machine learning can be used 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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 328

Authors: Sejong Oh

Abstract:

Classification is an important topic in machine learning and bioinformatics. Many datasets have been introduced for classification tasks. A dataset contains multiple features, and the quality of features influences the classification accuracy of the dataset. The power of classification for each feature differs. In this study, we suggest the Classification Influence Index (CII) as an indicator of classification power for each feature. CII enables evaluation of the features in a dataset and improved classification accuracy by transformation of the dataset. By conducting experiments using CII and the k-nearest neighbor classifier to analyze real datasets, we confirmed that the proposed index provided meaningful improvement of the classification accuracy.

Keywords: accuracy, classification, dataset, data preprocessing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1449

Authors: Fahd Sabry Esmail, M. Badr Senousy, Mohamed Ragaie

Abstract:

In recent years, there has been an explosion in the rate of using technology that help discovering the diseases. For example, DNA microarrays allow us for the first time to obtain a "global" view of the cell. It has great potential to provide accurate medical diagnosis, to help in finding the right treatment and cure for many diseases. Various classification algorithms can be applied on such micro-array datasets to devise methods that can predict the occurrence of Leukemia disease. In this study, we compared the classification accuracy and response time among eleven decision tree methods and six rule classifier methods using five performance criteria. The experiment results show that the performance of Random Tree is producing better result. Also it takes lowest time to build model in tree classifier. The classification rules algorithms such as nearest- neighbor-like algorithm (NNge) is the best algorithm due to the high accuracy and it takes lowest time to build model in classification.

Keywords: Data mining, classification techniques, decision tree, classification rule, leukemia diseases, microarray data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2489

Authors: Sujata Upgupta, Prasoon Kumar Singh

Abstract:

The expansion of large scale coal mining into forest areas is a potential hazard for the local biodiversity and wildlife. The objective of this study is to provide a picture of the threat that coal mining poses to the forests of the East Bokaro landscape. The vulnerable forest areas at risk have been assessed and the priority areas for conservation have been presented. The forested areas at risk in the current scenario have been assessed and compared with the past conditions using classification and buffer based overlay approach. Forest vulnerability has been assessed using an analytical framework based on systematic indicators and composite vulnerability index values. The results indicate that more than 4 km² of forests have been lost from 1973 to 2016. Large patches of forests have been diverted for coal mining projects. Forests in the northern part of the coal field within 1-3 km radius around the coal mines are at immediate risk. The original contiguous forests have been converted into fragmented and degraded forest patches. Most of the collieries are located within or very close to the forests thus threatening the biodiversity and hydrology of the surrounding regions. Based on the vulnerability values estimated, it was concluded that more than 90% of the forested grids in East Bokaro are highly vulnerable to mining. The forests in the sub-districts of Bermo and Chandrapura have been identified as the most vulnerable to coal mining activities. This case study would add to the capacity of the forest managers and mine managers to address the risk and vulnerability of forests at a small landscape level in order to achieve sustainable development.

Keywords: Coal mining, forest, indicators, vulnerability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1117

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2481

Authors: A. Junpen, S. Garivait, S. Bonnet, A. Pongpullponsak

Abstract:

The forest fires in Thailand are annual occurrence which is the cause of air pollutions. This study intended to estimate the emission from forest fire during 2005-2009 using MODerateresolution Imaging Spectro-radiometer (MODIS) sensor aboard the Terra and Aqua satellites, experimental data, and statistical data. The forest fire emission is estimated using equation established by Seiler and Crutzen in 1982. The spatial and temporal variation of forest fire emission is analyzed and displayed in the form of grid density map. From the satellite data analysis suggested between 2005 and 2009, the number of fire hotspots occurred 86,877 fire hotspots with a significant highest (more than 80% of fire hotspots) in the deciduous forest. The peak period of the forest fire is in January to May. The estimation on the emissions from forest fires during 2005 to 2009 indicated that the amount of CO, CO2, CH4, and N2O was about 3,133,845 tons, 47,610.337 tons, 204,905 tons, and 6,027 tons, respectively, or about 6,171,264 tons of CO2eq. They also emitted 256,132 tons of PM10. The year 2007 was found to be the year when the emissions were the largest. Annually, March is the period that has the maximum amount of forest fire emissions. The areas with high density of forest fire emission were the forests situated in the northern, the western, and the upper northeastern parts of the country.

Keywords: Emissions, Forest fire, Remote sensing information.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2137

Authors: Suzan Wedyan

Abstract:

Associative classification (AC) is a data mining approach that combines association rule and classification to build classification models (classifiers). AC has attracted a significant attention from several researchers mainly because it derives accurate classifiers that contain simple yet effective rules. In the last decade, a number of associative classification algorithms have been proposed such as Classification based Association (CBA), Classification based on Multiple Association Rules (CMAR), Class based Associative Classification (CACA), and Classification based on Predicted Association Rule (CPAR). This paper surveys major AC algorithms and compares the steps and methods performed in each algorithm including: rule learning, rule sorting, rule pruning, classifier building, and class prediction.

Keywords: Associative Classification, Classification, Data Mining, Learning, Rule Ranking, Rule Pruning, Prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6570

Authors: Chun-Wei Tung, Chyn Liaw, Shinn-Jang Ho, Shinn-Ying Ho

Abstract:

Protein subchloroplast locations are correlated with its functions. In contrast to the large amount of available protein sequences, the information of their locations and functions is less known. The experiment works for identification of protein locations and functions are costly and time consuming. The accurate prediction of protein subchloroplast locations can accelerate the study of functions of proteins in chloroplast. This study proposes a Random Forest based method, ChloroRF, to predict protein subchloroplast locations using interpretable physicochemical properties. In addition to high prediction accuracy, the ChloroRF is able to select important physicochemical properties. The important physicochemical properties are also analyzed to provide insights into the underlying mechanism.

Keywords: Chloroplast, Physicochemical properties, Proteinlocations, Random Forests.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1621

Authors: Makram Ben Jeddou

Abstract:

ABC classification is widely used by managers for inventory control. The classical ABC classification is based on Pareto principle and according to the criterion of the annual use value only. Single criterion classification is often insufficient for a closely inventory control. Multi-criteria inventory classification models have been proposed by researchers in order to consider other important criteria. From these models, we will consider a specific model in order to make a sensitive analysis on the composite score calculated for each item. In fact, this score, based on a normalized average between a good and a bad optimized index, can affect the ABC-item classification. We will focus on items differently assigned to classes and then propose a classification compromise.

Keywords: ABC classification, Multi criteria inventory classification models, ZF-model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2464

Authors: P. Sangarun, W. Srisang, K. Jaroensutasinee, M. Jaroensutasinee

Abstract:

A better understanding of cloud forest characteristic in a tropical montane cloud forest at Khao Nan, Nakhon Si Thammarat on climatic, vegetation, soil and hydrology were studied during 18-21 April 2007. The results showed that as air temperature at Sanyen cloud forest increased, the percent relative humidity decreased. The amount of solar radiation at Sanyen cloud forest had a positive association with the amount of solar radiation at Parah forest. The amount of solar radiation at Sanyen cloud forest was very low with a range of 0-19 W/m2. On the other hand, the amount of solar radiation at Parah forest was high with a range of 0-1000 W/m2. There was no difference between leaf width, leaf length, leaf thickness and leaf area with increasing in elevations. As the elevations increased, bush height and tree height decreased. There was no association between bush width and bush ratio with elevation. As the elevations increased, the percent epiphyte cover and the percent soil moisture increased but water temperature, conductivity, and dissolved oxygen decreased. The percent soil moistures and organic contents were higher at elevations above 900 m than elevations below.

Keywords: Cloud forest, climate, vegetation, soil, hydrology.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1810

Authors: M. Ben Othmen, M. Sayadi, F. Fnaiech

Abstract:

Wavelet transform provides several important characteristics which can be used in a texture analysis and classification. In this work, an efficient texture classification method, which combines concepts from wavelet and co-occurrence matrices, is presented. An Euclidian distance classifier is used to evaluate the various methods of classification. A comparative study is essential to determine the ideal method. Using this conjecture, we developed a novel feature set for texture classification and demonstrate its effectiveness

Keywords: Classification, Wavelet, Co-occurrence, Euclidian Distance, Classifier, Texture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1435

Authors: Ubonwan Chaiyo, Savitri Garivait, Kobsak Wanthongchai

Abstract:

The study site was located in Ratchaburi Province, Thailand. Four experimental plots in dry dipterocarp forest (DDF) and four plots in mixed deciduous forest (MDF) were set up to estimate the above-ground biomass of tree, sapling and bamboo. The allometry equations were used to investigate above-ground biomass of these vegetation. Seedling and other understory were determined using direct harvesting method. Carbon storage in above-ground biomass was calculated based on IPCC 2006. The results showed that the above-ground biomass of DDF at 20-40% slope, <20% slope and MDF at <20% slope were 91.96, 30.95 and 59.44 ton/ha, respectively. Bamboo covers about half of total aboveground biomass in MDF, which is a specific characteristic of this area. The carbon sequestration potential in above-ground biomass of plot slope range 20-40% DDF, <20% DDF and <20% MDF are 43.22, 14.55 and 27.94 ton C/ha, respectively.

Keywords: Carbon storage, aboveground biomass, tropical deciduous forest, dry dipterocarp forest, mixed deciduous forest.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2906

Authors: Hannu Nurmesniemi, Mikko Mäkelä, Risto Pöykiö, Olli Dahl

Abstract:

Due to the low heavy metal concentrations, the bottom ash from a 32 MW municipal district heating plant was determined to be a potential forest fertilizer as such. However, additional Ca would be needed, because its Ca concentration of 1.9- % (d.w.) was lower than the statutory Finnish minimum limit value of 6.0-% (d.w.) for Ca in forest fertilizer. Due to the elevated As concentration (53.0 mg/kg; d.w.) in the fly ash from the 32 MW municipal district heating plant, and Cr concentration (620 mg/kg; d.w.) in the ash fraction (i.e. mixture of the bottom ash and fly ash) from the 6 MW municipal district heating plant, which exceed the limit values of 30 mg/kg (d.w.) and 300 mg/kg (d.w.) for As and Cr, respectively, these residues are not suitable as forest fertilizers. Although these ash fractions cannot be used as a forest fertilizer as such, they can be used for the landscaping of landfills or in industrial and other areas that are closed to the public. However, an environmental permit is then needed.

Keywords: Ash, fertilizer, peat, forest residue, waste

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1437

Authors: Jorge A. Ruiz-Vanoye, Ocotlán Díaz-Parra, Alejandro Fuentes-Penna, Daniel Vélez-Díaz, Edith Olaco García

Abstract:

In this paper, we present the use of the discriminant analysis to select evolutionary algorithms that better solve instances of the vehicle routing problem with time windows. We use indicators as independent variables to obtain the classification criteria, and the best algorithm from the generic genetic algorithm (GA), random search (RS), steady-state genetic algorithm (SSGA), and sexual genetic algorithm (SXGA) as the dependent variable for the classification. The discriminant classification was trained with classic instances of the vehicle routing problem with time windows obtained from the Solomon benchmark. We obtained a classification of the discriminant analysis of 66.7%.

Keywords: Intelligent transportation systems, data-mining techniques, evolutionary algorithms, discriminant analysis, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1504

Authors: Karim Abouelmehdi, Loubna Dali, Elmoutaoukkil Abdelmajid, Hoda Elsayed Eladnani Fatiha, Benihssane Abderahim

Abstract:

The security of cloud services is the concern of cloud service providers. In this paper, we will mention different classifications of cloud attacks referred by specialized organizations. Each agency has its classification of well-defined properties. The purpose is to present a high-level classification of current research in cloud computing security. This classification is organized around attack strategies and corresponding defenses.

Keywords: Cloud computing, security, classification, risk.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2027

Authors: M. Hamdi, R. Rhouma, S. Belghith

Abstract:

Generating random numbers are mainly used to create secret keys or random sequences. It can be carried out by various techniques. In this paper we present a very simple and efficient pseudo random number generator (PRNG) based on chaotic maps and S-Box tables. This technique adopted two main operations one to generate chaotic values using two logistic maps and the second to transform them into binary words using random S-Box tables. The simulation analysis indicates that our PRNG possessing excellent statistical and cryptographic properties.

Keywords: Chaotic map, Cryptography, Random Numbers, Statistical tests, S-box.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3823

Authors: Piyush Samant, Ravinder Agarwal

Abstract:

Complementary and Alternative Medicine (CAM) techniques are quite popular and effective for chronic diseases. Iridology is more than 150 years old CAM technique which analyzes the patterns, tissue weakness, color, shape, structure, etc. for disease diagnosis. The objective of this paper is to validate the use of iridology for the diagnosis of the diabetes. The suggested model was applied in a systemic disease with ocular effects. 200 subject data of 100 each diabetic and non-diabetic were evaluated. Complete procedure was kept very simple and free from the involvement of any iridologist. From the normalized iris, the region of interest was cropped. All 63 features were extracted using statistical, texture analysis, and two-dimensional discrete wavelet transformation. A comparison of accuracies of six different classifiers has been presented. The result shows 89.66% accuracy by the random forest classifier.

Keywords: Complementary and alternative medicine, Iridology, iris, feature extraction, classification, disease prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1774

Authors: Behrouz Fathi-Vajargah, Sara Ghasemalipour

Abstract:

This paper studies a random fuzzy queueing system that the interarrival times of customers arriving at the server and the service times are independent and identically distributed random fuzzy variables. We match the random fuzzy queueing system with the random fuzzy alternating renewal process and we do not use from α-pessimistic and α-optimistic values to estimate the average chance of the event ”random fuzzy queueing system is busy at time t”, we employ the fuzzy simulation method in practical applications. Some theorem is proved and finally we solve a numerical example with fuzzy simulation method.

Keywords: Random fuzzy variables, Fuzzy simulation, Queueing system, Interarrival times.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2031

Authors: Helyane B. Borges, Julio Cesar Nievola

Abstract:

Hierarchical classification is a problem with applications in many areas as protein function prediction where the dates are hierarchically structured. Therefore, it is necessary the development of algorithms able to induce hierarchical classification models. This paper presents experimenters using the algorithm for hierarchical classification called Multi-label Hierarchical Classification using a Competitive Neural Network (MHC-CNN). It was tested in ten datasets the Gene Ontology (GO) Cellular Component Domain. The results are compared with the Clus-HMC and Clus-HSC using the hF-Measure.

Keywords: Hierarchical Classification, Competitive Neural Network, Global Classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2339

Authors: S. Loumi, H. Merrad, F. Alilat, B. Sansal

Abstract:

In this article, we propose a methodology for the characterization of the suspended matter along Algiers-s bay. An approach by multi layers perceptron (MLP) with training by back propagation of the gradient optimized by the algorithm of Levenberg Marquardt (LM) is used. The accent was put on the choice of the components of the base of training where a comparative study made for four methods: Random and three alternatives of classification by K-Means. The samples are taken from suspended matter image, obtained by analytical model based on polynomial regression by taking account of in situ measurements. The mask which selects the zone of interest (water in our case) was carried out by using a multi spectral classification by ISODATA algorithm. To improve the result of classification, a cleaning of this mask was carried out using the tools of mathematical morphology. The results of this study presented in the forms of curves, tables and of images show the founded good of our methodology.

Keywords: Classification K-means, mathematical morphology, neural network MLP, remote sensing, suspended particulate matter

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1480

Authors: L. A. Muhammad, M. S. Argungu

Abstract:

Educational data mining (EDM) has recorded substantial considerations. Techniques of data mining in one way or the other have been proposed to dig out out-of-sight knowledge in educational data. The result of the study got assists academic institutions in further enhancing their process of learning and methods of passing knowledge to students. Consequently, the performance of students boasts and the educational products are by no doubt enhanced. This study adopted a student performance prediction model premised on techniques of data mining with Students' Essential Features (SEF). SEF are linked to the learner's interactivity with the e-learning management system. The performance of the student's predictive model is assessed by a set of classifiers, viz. Bayes Network, Logistic Regression, and Reduce Error Pruning Tree (REP). Consequently, ensemble methods of Bagging, Boosting, and Random Forest (RF) are applied to improve the performance of these single classifiers. The study reveals that the result shows a robust affinity between learners' behaviors and their academic attainment. Result from the study shows that the REP Tree and its ensemble record the highest accuracy of 83.33% using SEF. Hence, in terms of the Receiver Operating Curve (ROC), boosting method of REP Tree records 0.903, which is the best. This result further demonstrates the dependability of the proposed model.

Keywords: Ensemble, bagging, Random Forest, boosting, data mining, classifiers, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 663

Authors: Gamze Uslu, Sebnem Baydere, Alper K. Demir

Abstract:

In this study, data loss tolerance of Support Vector Machines (SVM) based activity recognition model and multi activity classification performance when data are received over a lossy wireless sensor network is examined. Initially, the classification algorithm we use is evaluated in terms of resilience to random data loss with 3D acceleration sensor data for sitting, lying, walking and standing actions. The results show that the proposed classification method can recognize these activities successfully despite high data loss. Secondly, the effect of differentiated quality of service performance on activity recognition success is measured with activity data acquired from a multi hop wireless sensor network, which introduces  high data loss. The effect of number of nodes on the reliability and multi activity classification success is demonstrated in simulation environment. To the best of our knowledge, the effect of data loss in a wireless sensor network on activity detection success rate of an SVM based classification algorithm has not been studied before.

Keywords: Activity recognition, support vector machines, acceleration sensor, wireless sensor networks, packet loss.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2820

Authors: Mohamed E. Salem Abozaed

Abstract:

Detection and classification of power quality (PQ) disturbances is an important consideration to electrical utilities and many industrial customers so that diagnosis and mitigation of such disturbance can be implemented quickly. S-transform algorithm and continuous wavelet transforms (CWT) are time-frequency algorithms, and both of them are powerful in detection and classification of PQ disturbances. This paper presents detection and classification of PQ disturbances using S-transform and CWT algorithms. The results of detection and classification, provides that S-transform is more accurate in detection and classification for most PQ disturbance than CWT algorithm, where as CWT algorithm more powerful in detection in some disturbances like notching

Keywords: CWT, Disturbances classification, Disturbances detection, Power quality, S-transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2550

Authors: Jun Wan, Zehua Chen, Yingwu Chen, Zhidong Bai

Abstract:

Classification is an interesting problem in functional data analysis (FDA), because many science and application problems end up with classification problems, such as recognition, prediction, control, decision making, management, etc. As the high dimension and high correlation in functional data (FD), it is a key problem to extract features from FD whereas keeping its global characters, which relates to the classification efficiency and precision to heavens. In this paper, a novel automatic method which combined Genetic Algorithm (GA) and classification algorithm to extract classification features is proposed. In this method, the optimal features and classification model are approached via evolutional study step by step. It is proved by theory analysis and experiment test that this method has advantages in improving classification efficiency, precision and robustness whereas using less features and the dimension of extracted classification features can be controlled.

Keywords: Classification, functional data, feature extraction, genetic algorithm, wavelet.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1510

Authors: Aya Salama

Abstract:

Digital Twin has emerged as a compelling research area, capturing the attention of scholars over the past decade. It finds applications across diverse fields, including smart manufacturing and healthcare, offering significant time and cost savings. Notably, it often intersects with other cutting-edge technologies such as Data Mining, Artificial Intelligence, and Machine Learning. However, the concept of a Human Digital Twin (HDT) is still in its infancy and requires further demonstration of its practicality. HDT takes the notion of Digital Twin a step further by extending it to living entities, notably humans, who are vastly different from inanimate physical objects. The primary objective of this research was to create an HDT capable of automating real-time human responses by simulating human behavior. To achieve this, the study delved into various areas, including clustering, supervised classification, topic extraction, and sentiment analysis. The paper successfully demonstrated the feasibility of HDT for generating personalized responses in social messaging applications. Notably, the proposed approach achieved an overall accuracy of 63%, a highly promising result that could pave the way for further exploration of the HDT concept. The methodology employed Random Forest for clustering the question database and matching new questions, while K-nearest neighbor was utilized for sentiment analysis.

Keywords: Human Digital twin, sentiment analysis, topic extraction, supervised machine learning, unsupervised machine learning, classification and clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 116