Search results for: random forest algorithm

Authors: Nubwimana Rachel, Mugabowindekwe Maurice

Abstract:

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

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

Procedia PDF Downloads 38

Authors: Ji-Suk Kim, Dong-Pil Kim, Kee-Rae Gang, Yoon Ho Choi

Abstract:

This study was conducted to investigate the characteristics of butterfly communities according to the habitat characteristics of Korean veins. The survey sites were 12 mountains located in the vein, and 12~30 quadrats (200 in total) were set. The species richness and biodiversity were different according to land use type. Two types of land use (forest and graveyard) showed lower species diversity index values ​​than other land use types. The species abundance was low in the forest and graveyards, and grasslands, forest tops, cultivated areas and urban areas showed relatively high species richness. The altitude was not statistically significant with the number of species of butterflies and biodiversity index. The degree of canopy closure showed a negative correlation. As a result of interspecific correlation analysis, it was confirmed that there was a very high correlation (R2=0.746) between Lycaena phlaeas and Pseudozizeeria maha argia, Choaspes benjaminii japonica and Argyronome ruslana.

Keywords: land use type, species diversity index, correlation, canopy closure

Procedia PDF Downloads 137

Authors: Deniz Sari, Selahattin İncecik, Nesimi Ozkurt

Abstract:

Surface ozone, which named as one of the most critical pollutants in the 21th century, threats to human health, forest and vegetation. Specifically, in rural areas surface ozone cause significant influences on agricultural productions and trees. In this study, in order to understand to the surface ozone levels in rural areas we focus on the north-western side of Biga Peninsula which covers by the mountainous and forested area. Ozone concentrations were measured for the first time with passive sampling at 10 sites and two online monitoring stations in this rural area from 2013 and 2015. Using with the daytime hourly O3 measurements during light hours (08:00–20:00) exceeding the threshold of 40 ppb over the 3 months (May, June and July) for agricultural crops, and over the six months (April to September) for forest trees AOT40 (Accumulated hourly O3 concentrations Over a Threshold of 40 ppb) cumulative index was calculated. AOT40 is defined by EU Directive 2008/50/EC to evaluate whether ozone pollution is a risk for vegetation, and is calculated by using hourly ozone concentrations from monitoring systems. In the present study, we performed the trajectory analysis by The Hybrid Single-Particle Lagrangian Integrated Trajectory (HYSPLIT) model to follow the long-range transport sources contributing to the high ozone levels in the region. The ozone episodes observed between 2013 and 2015 were analysed using the HYSPLIT model developed by the NOAA-ARL. In addition, the cluster analysis is used to identify homogeneous groups of air mass transport patterns can be conducted through air trajectory clustering by grouping similar trajectories in terms of air mass movement. Backward trajectories produced for 3 years by HYSPLIT model were assigned to different clusters according to their moving speed and direction using a k-means clustering algorithm. According to cluster analysis results, northerly flows to study area cause to high ozone levels in the region. The results present that the ozone values in the study area are above the critical levels for forest and vegetation based on EU Directive 2008/50/EC.

Keywords: AOT40, Biga Peninsula, HYSPLIT, surface ozone

Procedia PDF Downloads 227

Authors: Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim

Abstract:

All currencies around the world look very different from each other. For instance, the size, color, and pattern of the paper are different. With the development of modern banking services, automatic methods for paper currency recognition become important in many applications like vending machines. One of the currency recognition architecture’s phases is Feature detection and description. There are many algorithms that are used for this phase, but they still have some disadvantages. This paper proposes a feature detection algorithm, which merges the advantages given in the current SIFT and SURF algorithms, which we call, Speeded up Robust Scale-Invariant Feature Transform (SR-SIFT) algorithm. Our proposed SR-SIFT algorithm overcomes the problems of both the SIFT and SURF algorithms. The proposed algorithm aims to speed up the SIFT feature detection algorithm and keep it robust. Simulation results demonstrate that the proposed SR-SIFT algorithm decreases the average response time, especially in small and minimum number of best key points, increases the distribution of the number of best key points on the surface of the currency. Furthermore, the proposed algorithm increases the accuracy of the true best point distribution inside the currency edge than the other two algorithms.

Keywords: currency recognition, feature detection and description, SIFT algorithm, SURF algorithm, speeded up and robust features

Procedia PDF Downloads 215

Authors: P. Shrivastava, A. Shukla, K. Verma, S. Rungta

Abstract:

Parkinson's disease is a chronic neurological disorder that directly affects human gait. It leads to slowness of movement, causes muscle rigidity and tremors. Gait serve as a primary outcome measure for studies aiming at early recognition of disease. Using gait techniques, this paper implements efficient binary bat algorithm for an early detection of Parkinson's disease by selecting optimal features required for classification of affected patients from others. The data of 166 people, both fit and affected is collected and optimal feature selection is done using PSO and Bat algorithm. The reduced dataset is then classified using neural network. The experiments indicate that binary bat algorithm outperforms traditional PSO and genetic algorithm and gives a fairly good recognition rate even with the reduced dataset.

Keywords: parkinson, gait, feature selection, bat algorithm

Procedia PDF Downloads 520

Authors: Najmeh Mohsenifar, Narjes Mohsenifar, Abbas Kargar

Abstract:

In this paper, has been presented a stable method for predicting the ECG signals through the RBF neural networks, by the PSO algorithm. In spite of quasi-periodic ECG signal from a healthy person, there are distortions in electro cardiographic data for a patient. Therefore, there is no precise mathematical model for prediction. Here, we have exploited neural networks that are capable of complicated nonlinear mapping. Although the architecture and spread of RBF networks are usually selected through trial and error, the PSO algorithm has been used for choosing the best neural network. In this way, 2 second of a recorded ECG signal is employed to predict duration of 20 second in advance. Our simulations show that PSO algorithm can find the RBF neural network with minimum MSE and the accuracy of the predicted ECG signal is 97 %.

Keywords: electrocardiogram, RBF artificial neural network, PSO algorithm, predict, accuracy

Procedia PDF Downloads 604

Authors: Anshu Siwach, Qianlai Zhuang, Ratul Baishya

Abstract:

Context: This study focuses on the influence of moss cover and seasonality on soil microbial biomass and enzymatic activity in different Central Himalayan temperate forest types. Soil microbial biomass and enzymes are key indicators of microbial communities in soil and provide information on soil properties, microbial status, and organic matter dynamics. The activity of microorganisms in the soil varies depending on the vegetation type and environmental conditions. Therefore, this study aims to assess the effects of moss cover, seasons, and different forest types on soil microbial biomass carbon (SMBC), soil microbial biomass nitrogen (SMBN), and soil enzymatic activity in the Central Himalayas, Uttarakhand, India. Research Aim: The aim of this study is to evaluate the levels of SMBC, SMBN, and soil enzymatic activity in different temperate forest types under the influence of two ground covers (soil with and without moss cover) during the rainy and winter seasons. Question Addressed: This study addresses the following questions: 1. How does the presence of moss cover and seasonality affect soil microbial biomass and enzymatic activity? 2. What is the influence of different forest types on SMBC, SMBN, and enzymatic activity? Methodology: Soil samples were collected from different forest types during the rainy and winter seasons. The study utilizes the chloroform-fumigation extraction method to determine SMBC and SMBN. Standard methodologies are followed to measure enzymatic activities, including dehydrogenase, acid phosphatase, aryl sulfatase, β-glucosidase, phenol oxidase, and urease. Findings: The study reveals significant variations in SMBC, SMBN, and enzymatic activity under different ground covers, within the rainy and winter seasons, and among the forest types. Moss cover positively influences SMBC and enzymatic activity during the rainy season, while soil without moss cover shows higher values during the winter season. Quercus-dominated forests, as well as Cupressus torulosa forests, exhibit higher levels of SMBC and enzymatic activity, while Pinus roxburghii forests show lower levels. Theoretical Importance: The findings highlight the importance of considering mosses in forest management plans to improve soil microbial diversity, enzymatic activity, soil quality, and health. Additionally, this research contributes to understanding the role of lower plants, such as mosses, in influencing ecosystem dynamics. Conclusion: The study concludes that moss cover during the rainy season significantly influences soil microbial biomass and enzymatic activity. Quercus and Cupressus torulosa dominated forests demonstrate higher levels of SMBC and enzymatic activity, indicating the importance of these forest types in sustaining soil microbial diversity and soil health. Including mosses in forest management plans can improve soil quality and overall ecosystem dynamics.

Keywords: moss cover, seasons, soil enzymes, soil microbial biomass, temperate forest types

Procedia PDF Downloads 41

Authors: Laxuman Thakuri

Abstract:

Despite the large number of in-depth case studies focused on policy analysis, institutional arrangement, and collective action of common property resource management; how the local institutions take the pricing decision of forest products in community forest management and what kinds of effects produce it, the answers of these questions are largely silent among the policy-makers and researchers alike. The study examined how the local institutions take the pricing decision of forest products in the lowland community forestry of Nepal and how the decisions affect to equitable distribution of benefits and livelihood improvement which are also objectives of Nepalese community forestry. The study assumes that forest products pricing decisions have multiple effects on equitable distribution and livelihood improvement in the areas having heterogeneous socio-economic conditions. The dissertation was carried out at four community forests of lowland, Nepal that has characteristics of high value species, matured-experience of community forest management and better record-keeping system of forest products production, pricing and distribution. The questionnaire survey, individual to group discussions and direct field observation were applied for data collection from the field, and Lorenz curve, gini-coefficient, χ²-text, and SWOT (Strong, Weak, Opportunity, and Threat) analysis were performed for data analysis and results interpretation. The dissertation demonstrates that the low pricing strategy of high-value forest products was supposed crucial to increase the access of socio-economically weak households, and to and control over the important forest products such as timber, but found counter productive as the strategy increased the access of socio-economically better-off households at higher rate. In addition, the strategy contradicts to collect a large-scale community fund and carry out livelihood improvement activities as per the community forestry objectives. The crucial part of the study is despite the fact of low pricing strategy; the timber alone contributed large part of community fund collection. The results revealed close relation between pricing decisions and livelihood objectives. The action research result shows that positive price discrimination can slightly reduce the prevailing inequality and increase the fund. However, it lacks to harness the full price of forest products and collects a large-scale community fund. For broader outcomes of common property resource management in terms of resource sustainability, equity, and livelihood opportunity, the study suggests local institutions to harness the full price of resource products with respect to the local market.

Keywords: community, equitable, forest, livelihood, socioeconomic, Nepal

Procedia PDF Downloads 516

Authors: M. Aghili, S. Tabarestani, C. Freytes, M. Shojaie, M. Cabrerizo, A. Barreto, N. Rishe, R. E. Curiel, D. Loewenstein, R. Duara, M. Adjouadi

Abstract:

A major challenge in medical studies, especially those that are longitudinal, is the problem of missing measurements which hinders the effective application of many machine learning algorithms. Furthermore, recent Alzheimer's Disease studies have focused on the delineation of Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI) from cognitively normal controls (CN) which is essential for developing effective and early treatment methods. To address the aforementioned challenges, this paper explores the potential of using the eXtreme Gradient Boosting (XGBoost) algorithm in handling missing values in multiclass classification. We seek a generalized classification scheme where all prodromal stages of the disease are considered simultaneously in the classification and decision-making processes. Given the large number of subjects (1631) included in this study and in the presence of almost 28% missing values, we investigated the performance of XGBoost on the classification of the four classes of AD, NC, EMCI, and LMCI. Using 10-fold cross validation technique, XGBoost is shown to outperform other state-of-the-art classification algorithms by 3% in terms of accuracy and F-score. Our model achieved an accuracy of 80.52%, a precision of 80.62% and recall of 80.51%, supporting the more natural and promising multiclass classification.

Keywords: eXtreme gradient boosting, missing data, Alzheimer disease, early mild cognitive impairment, late mild cognitive impair, multiclass classification, ADNI, support vector machine, random forest

Procedia PDF Downloads 162

Authors: W. Promprom, W. Chatan

Abstract:

Leguminosae is a large plant family and its members are important for local people utilization in the Northeast of Thailand. This research aimed to survey medicinal plants in this family in Kantharalak Community forest. The plant collection and exploration were made from October 2017 to September 2018. Folk medicinal uses were studied by interviewing villagers and folk medicine healers living around the community forest by asking about local names, using parts, preparation and properties. The results showed that 65 species belonging to 40 genera were found. Among these, 30 species were medicinal plant. The most used plant parts were leaf. Decoction and drinking were mostly preparation method and administration mode used. All medicinal plants could be categorized into 17 diseases/symptoms. Most plant (56.66%) were used for fever. The voucher specimens were deposited in Department of Biology, Faculty of Science, Mahasarakham University, Thailand. Therefore, the data from this study might be widely used by the local area and further scientific study.

Keywords: ethnobotany, ethnophamacology, medicinal plant, taxonomy, utilization

Procedia PDF Downloads 133

Authors: Yeliz Sarı Nayim, B. Niyami Nayim

Abstract:

Biotopes such as forest areas rich in biodiversity, wetlands, hedgerows and woodlands play important ecological roles in agricultural landscapes. Of these semi-natural areas and features, hedgerows are the most common landscape elements. Their most significant features are that they serve as a barrier between the agricultural lands, serve as shelter, add aesthetical value to the landscape and contribute significantly to the wildlife and biodiversity. Hedgerows surrounding agricultural landscapes also provide an important habitat for pollinators which are important for agricultural production. This study looks into the identification of hedgerows in agricultural lands in the Mugada rural area within Bartın province, Turkey. From field data and-and satellite images, it is clear that in this area, especially around rural settlements, large forest areas have been cleared for settlement and agriculture. A network of hedgerows is also apparent, which might potentially play an important role in the otherwise open agricultural landscape. We found that these hedgerows serve as an ecological and biological corridor, linking forest ecosystems. Forest patches of different sizes and creating a habitat network across the landscape. Some examples of this will be presented. The overall conclusion from the study is that ecologically, biologically and aesthetically important hedge biotopes should be maintained in the long term in agricultural landscapes such as this. Some suggestions are given for how they could be managed sustainably into the future.

Keywords: agricultural biotopes, Hedgerows, landscape ecology, Turkey

Procedia PDF Downloads 286

Authors: Xiuqin Ma, Hongwu Qin

Abstract:

A new efficient normal parameter reduction algorithm of soft set in decision making was proposed. However, up to the present, few documents have focused on real-life applications of this algorithm. Accordingly, we apply a New Efficient Normal Parameter Reduction algorithm into real-life datasets of online shopping, such as Blackberry Mobile Phone Dataset. Experimental results show that this algorithm is not only suitable but feasible for dealing with the online shopping.

Keywords: soft sets, parameter reduction, normal parameter reduction, online shopping

Procedia PDF Downloads 489

Authors: Narissara Nuthammachot, Dimitris Stratoulias

Abstract:

Fire is one of the main causes of environmental and ecosystem change. Therefore, it is a challenging task for fire risk assessment fire potential mapping. The study area is Hua Sai district, Nakorn Sri Thammarat province, which covers in a part of peat swamp forest areas. 55 fire points in peat swamp areas were reported from 2012 to 2016. Analytic Hierarchy Process (AHP) and Geographic Information System (GIS) methods were selected for this study. The risk fire area map was arranged on these factors; elevation, slope, aspect, precipitation, distance from the river, distance from town, and land use. The results showed that the predicted fire risk areas are found to be in appreciable reliability with past fire events. The fire risk map can be used for the planning and management of fire areas in the future.

Keywords: analytic hierarchy process, fire risk assessment, geographic information system, peat swamp forest

Procedia PDF Downloads 182

Authors: Elham Kazemi

Abstract:

Quadratic Assignment Problem (QAP) is one the combinatorial optimization problems about which research has been done in many companies for allocating some facilities to some locations. The issue of particular importance in this process is the costs of this allocation and the attempt in this problem is to minimize this group of costs. Since the QAP’s are from NP-hard problem, they cannot be solved by exact solution methods. Cuckoo Optimization Algorithm is a Meta-heuristicmethod which has higher capability to find the global optimal points. It is an algorithm which is basically raised to search a continuous space. The Quadratic Assignment Problem is the issue which can be solved in the discrete space, thus the standard arithmetic operators of Cuckoo Optimization Algorithm need to be redefined on the discrete space in order to apply the Cuckoo Optimization Algorithm on the discrete searching space. This paper represents the way of discretizing the Cuckoo optimization algorithm for solving the quadratic assignment problem.

Keywords: Quadratic Assignment Problem (QAP), Discrete Cuckoo Optimization Algorithm (DCOA), meta-heuristic algorithms, optimization algorithms

Procedia PDF Downloads 489

Authors: Sophia Liang Zhou

Abstract:

For investors, businesses, consumers, and governments, an accurate assessment of future housing prices is crucial to critical decisions in resource allocation, policy formation, and investment strategies. Previous studies are contradictory about macroeconomic determinants of housing price and largely focused on one or two areas using point prediction. This study aims to develop data-driven models to accurately predict future housing market trends in different markets. This work studied five different metropolitan areas representing different market trends and compared three-time lagging situations: no lag, 6-month lag, and 12-month lag. Linear regression (LR), random forest (RF), and artificial neural network (ANN) were employed to model the real estate price using datasets with S&P/Case-Shiller home price index and 12 demographic and macroeconomic features, such as gross domestic product (GDP), resident population, personal income, etc. in five metropolitan areas: Boston, Dallas, New York, Chicago, and San Francisco. The data from March 2005 to December 2018 were collected from the Federal Reserve Bank, FBI, and Freddie Mac. In the original data, some factors are monthly, some quarterly, and some yearly. Thus, two methods to compensate missing values, backfill or interpolation, were compared. The models were evaluated by accuracy, mean absolute error, and root mean square error. The LR and ANN models outperformed the RF model due to RF’s inherent limitations. Both ANN and LR methods generated predictive models with high accuracy ( > 95%). It was found that personal income, GDP, population, and measures of debt consistently appeared as the most important factors. It also showed that technique to compensate missing values in the dataset and implementation of time lag can have a significant influence on the model performance and require further investigation. The best performing models varied for each area, but the backfilled 12-month lag LR models and the interpolated no lag ANN models showed the best stable performance overall, with accuracies > 95% for each city. This study reveals the influence of input variables in different markets. It also provides evidence to support future studies to identify the optimal time lag and data imputing methods for establishing accurate predictive models.

Keywords: linear regression, random forest, artificial neural network, real estate price prediction

Procedia PDF Downloads 81

Authors: M. F. Haroun, T. A. Gulliver

Abstract:

In this paper, an encryption algorithm is proposed for real-time image encryption. The scheme employs a dual chaotic generator based on a three dimensional (3D) discrete Lorenz attractor. Encryption is achieved using non-autonomous modulation where the data is injected into the dynamics of the master chaotic generator. The second generator is used to permute the dynamics of the master generator using the same approach. Since the data stream can be regarded as a random source, the resulting permutations of the generator dynamics greatly increase the security of the transmitted signal. In addition, a technique is proposed to mitigate the error propagation due to the finite precision arithmetic of digital hardware. In particular, truncation and rounding errors are eliminated by employing an integer representation of the data which can easily be implemented. The simple hardware architecture of the algorithm makes it suitable for secure real-time applications.

Keywords: chaotic systems, image encryption, non-autonomous modulation, FPGA

Procedia PDF Downloads 485

Authors: Karl D. Humm

Abstract:

The United Nations’ Community-based REDD+ (Reducing Emissions from Deforestation and forest Degradation) (CBR+) is a programme that directly finances grassroots climate change mitigation strategies that uplift Indigenous Peoples (IPs) and other marginalised groups. A pilot for it in six countries was developed in response to criticism of the REDD+ programme for excluding IPs from dialogues about climate change mitigation strategies affecting their lands and livelihoods. Despite the pilot’s conclusion in 2017, no complete report has yet been produced on the results of CBR+. To fill this gap, this study investigated the experiences with involving IPs in the CBR+ programmes and local projects across all six pilot countries. A literature review of official UN reports and academic articles identified challenges and successes with IP participation in REDD+ which became the basis for a framework guiding data collection. A mixed methods approach was used to collect and analyse qualitative and quantitative data from CBR+ documents and written interviews with CBR+ National Coordinators in each country for a cross-country comparative analysis. The study found that the most frequent challenges were lack of organisational capacity, illegal forest activities, and historically-based contentious relationships in IP and forest-dependent communities. Successful programmes included IPs and incorporated respect and recognition of IPs as major stakeholders in managing sustainable forests. Findings are summarized and shared with a set of recommendations for improvement of future projects.

Keywords: climate change, forests, indigenous peoples, REDD+

Procedia PDF Downloads 103

Authors: Sanam Haseen, Abdul Bari

Abstract:

In this paper a three stage multivariate programming problem with random survey cost and variances as random variables has been formulated as a non-linear stochastic programming problem. The problem has been converted into an equivalent deterministic form using chance constraint programming and modified E-modeling. An empirical study of the problem has been done at the end of the paper using R-simulation.

Keywords: chance constraint programming, modified E-model, stochastic programming, stratified sample surveys, three stage sample surveys

Procedia PDF Downloads 435

Authors: Sandhya Rijal, Saroj Adhikari, Ramesh R. Pant

Abstract:

Non-Timber Forest Products (NTFPs) have attracted substantial interest in the recent years with the increasing recognition that these can provide essential community needs for improved and diversified rural livelihood and support the objectives of biodiversity conservation. Nevertheless, various challenges are witnessed in their sustainable harvest and management. Assuming that sustainable management with community stewardship can offer one of the solutions to existing challenges, the study assesses the linkages between NTFPs and rural livelihood in Lamabagar village of Dolakha, Nepal. The major objective was to document the status of NTFPs and their contributions in households of Lamabagar. For status documentation, vegetation sampling was done using systematic random sampling technique. 30 plots of 10 m × 10 m were laid down in six parallel transect lines at horizontal distance of 160 m in two different community forests. A structured questionnaire survey was conducted in 76 households (excluding non-response rate) using stratified random sampling technique for contribution analysis. Likewise, key informant interview and focus group discussions were also conducted for data triangulations. 36 different NTFPs were recorded from the vegetation sample in two community forests of which 50% were used for medicinal purposes. The other uses include fodder, religious value, and edible fruits and vegetables. Species like Juniperus indica, Daphne bholua Aconitum spicatum, and Lyonia ovalifolia were frequently used for trade as a source of income, which was sold in local market. The protected species like Taxus wallichiana and Neopicrorhiza scrophulariiflora were also recorded in the area for which the trade is prohibited. The protection of these species urgently needs community stewardship. More than half of the surveyed households (55%) were depending on NTFPs for their daily uses, other than economic purpose whereas 45% of them sold those products in the market directly or in the form of local handmade products as a source of livelihood. NTFPs were the major source of primary health curing agents especially for the poor and unemployed people in the study area. Hence, the NTFPs contributed to livelihood under three different categories: subsistence, supplement income and emergency support, depending upon the economic status of the households. Although the status of forest improved after handover to the user group, the availability of valuable medicinal herbs like Rhododendron anthopogon, Swertia nervosa, Neopicrorhiza scrophulariiflora, and Aconitum spicatum were declining. Inadequacy of technology, lack of easy transport access, and absence of good market facility were the major limitations for external trade of NTFPs in the study site. It was observed that people were interested towards conservation only if they could get some returns: economic in terms of rural settlements. Thus, the study concludes that NTFPs could contribute rural livelihood and support conservation objectives only if local communities are provided with the easy access of technology, market and capital.

Keywords: contribution, medicinal, subsistence, sustainable harvest

Procedia PDF Downloads 106

Authors: J. Yang, Y. Ma, X. Zhang, S. Li, Y. Zhang

Abstract:

The traditional k-means algorithm has been widely used as a simple and efficient clustering method. However, the algorithm often converges to local minima for the reason that it is sensitive to the initial cluster centers. In this paper, an algorithm for selecting initial cluster centers on the basis of minimum spanning tree (MST) is presented. The set of vertices in MST with same degree are regarded as a whole which is used to find the skeleton data points. Furthermore, a distance measure between the skeleton data points with consideration of degree and Euclidean distance is presented. Finally, MST-based initialization method for the k-means algorithm is presented, and the corresponding time complexity is analyzed as well. The presented algorithm is tested on five data sets from the UCI Machine Learning Repository. The experimental results illustrate the effectiveness of the presented algorithm compared to three existing initialization methods.

Keywords: degree, initial cluster center, k-means, minimum spanning tree

Procedia PDF Downloads 385

Authors: K. Kanja, M. Mweemba, K. Malungwa

Abstract:

Due to the rampant population growth coupled with retrenchments currently going on in the Copper mines in Zambia, a number of people are resorting to land clearing for agriculture, illegal settlements as well as charcoal production among other vices. This study aims at assessing the rate of expansion of agricultural fields and illegal settlements in protected areas using remote sensing and Geographic Information System. Zambia’s Mwekera National Forest Reserve was used as a case study. Iterative Self-Organizing Data Analysis Technique (ISODATA), as well as maximum likelihood, supervised classification on four Landsat images as well as an accuracy assessment of the classifications was performed. Over the period under observation, results indicate annual percentage changes to be -0.03, -0.49 and 1.26 for agriculture, forests and settlement respectively indicating a higher conversion of forests into human settlements and agriculture.

Keywords: geographic information system, land cover change, Landsat TM and ETM+, Mwekera forest reserve, remote sensing

Procedia PDF Downloads 122

Authors: Archana Singh, Jyoti Agarwal, Ajay Rana

Abstract:

Data Mining is an efficient technology to discover patterns in large databases. Association Rule Mining techniques are used to find the correlation between the various item sets in a database, and this co-relation between various item sets are used in decision making and pattern analysis. In recent years, the problem of finding association rules from large datasets has been proposed by many researchers. Various research papers on association rule mining (ARM) are studied and analyzed first to understand the existing algorithms. Apriori algorithm is the basic ARM algorithm, but it requires so many database scans. In DIC algorithm, less amount of database scan is needed but complex data structure lattice is used. The main focus of this paper is to propose a new optimized algorithm (Friendly Algorithm) and compare its performance with the existing algorithms A data set is used to find out frequent itemsets and association rules with the help of existing and proposed (Friendly Algorithm) and it has been observed that the proposed algorithm also finds all the frequent itemsets and essential association rules from databases as compared to existing algorithms in less amount of database scan. In the proposed algorithm, an optimized data structure is used i.e. Graph and Adjacency Matrix.

Keywords: association rules, data mining, dynamic item set counting, FP-growth, friendly algorithm, graph

Procedia PDF Downloads 395

Authors: Ji Eun Shin, Dong Hoon Lim

Abstract:

Data clustering is a common technique used in data analysis and is used in many applications, such as artificial intelligence, pattern recognition, economics, ecology, psychiatry and marketing. K-means clustering is a well-known clustering algorithm aiming to cluster a set of data points to a predefined number of clusters. In this paper, we implement K-means algorithm based on MapReduce framework with RHadoop to make the clustering method applicable to large scale data. RHadoop is a collection of R packages that allow users to manage and analyze data with Hadoop. The main idea is to introduce a combiner as a function of our map output to decrease the amount of data needed to be processed by reducers. The experimental results demonstrated that K-means algorithm using RHadoop can scale well and efficiently process large data sets on commodity hardware. We also showed that our K-means algorithm using RHadoop with combiner was faster than regular algorithm without combiner as the size of data set increases.

Keywords: big data, combiner, K-means clustering, RHadoop

Procedia PDF Downloads 406

Authors: J. Kaabi, Y. Harrath

Abstract:

This paper studied the flow shop scheduling problem under machine availability constraints. The machines are subject to flexible preventive maintenance activities. The nonresumable scenario for the jobs was considered. That is, when a job is interrupted by an unavailability period of a machine it should be restarted from the beginning. The objective is to minimize the total tardiness time for the jobs and the advance/tardiness for the maintenance activities. To solve the problem, a genetic algorithm was developed and successfully tested and validated on many problem instances. The computational results showed that the new genetic algorithm outperforms another earlier proposed algorithm.

Keywords: flow shop scheduling, genetic algorithm, maintenance, priority rules

Procedia PDF Downloads 451

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 262

Authors: Nelson Bii, Christopher Ouma, John Odhiambo

Abstract:

Non-response is a potential source of errors in sample surveys. It introduces bias and large variance in the estimation of finite population parameters. Regression models have been recognized as one of the techniques of reducing bias and variance due to random non-response using auxiliary data. In this study, it is assumed that random non-response occurs in the survey variable in the second stage of cluster sampling, assuming full auxiliary information is available throughout. Auxiliary information is used at the estimation stage via a regression model to address the problem of random non-response. In particular, the auxiliary information is used via an improved Nadaraya-Watson kernel regression technique to compensate for random non-response. The asymptotic bias and mean squared error of the estimator proposed are derived. Besides, a simulation study conducted indicates that the proposed estimator has smaller values of the bias and smaller mean squared error values compared to existing estimators of finite population mean. The proposed estimator is also shown to have tighter confidence interval lengths at a 95% coverage rate. The results obtained in this study are useful, for instance, in choosing efficient estimators of the finite population mean in demographic sample surveys.

Keywords: mean squared error, random non-response, two-stage cluster sampling, confidence interval lengths

Procedia PDF Downloads 114

Authors: Ibrahim Ilker Ozyigit, Ertugrul Filiz, Seda Birbilener, Semsettin Kulac, Zeki Severoglu

Abstract:

In this study, we have performed genetic diversity analysis of Tilia tomentosa genotypes by using randomly amplified polymorphic DNA (RAPD) primers. A total of 28 genotypes, including 25 members from the urban ecosystem and 3 genotypes from forest ecosystem as outgroup were used. 8 RAPD primers produced a total of 53 bands, of which 48 (90.6 %) were polymorphic. Percentage of polymorphic loci (P), observed number of alleles (Na), effective number of alleles (Ne), Nei's (1973) gene diversity (h), and Shannon's information index (I) were found as 94.29 %, 1.94, 1.60, 0.34, and 0.50, respectively. The unweighted pair-group method with arithmetic average (UPGMA) cluster analysis revealed that two major groups were observed. The genotypes of urban and forest ecosystems showed a high genetic similarity between 28% and 92% and these genotypes did not separate from each other in UPGMA tree. Also, urban and forest genotypes clustered together in principal component analysis (PCA).

Keywords: Tilia tomentosa, genetic diversity, urban ecosystem, RAPD, UPGMA

Procedia PDF Downloads 489

Authors: Menuka Maharjan

Abstract:

In the name of food security, agriculture intensification through conventional farming is being implemented in Nepal. Government focus on increasing agriculture production completely ignores soil as well human health. This leads to create serious soil degradation, i.e., reduction of soil fertility and microbial activity and health hazard in the country. On this note, organic farming is sustainable agriculture approach which can address challenge of sustaining food security while protecting the environment. This creates a win-win situation both for people and the environment. However, people have limited knowledge on significance of organic farming for environment conservation and food security especially developing countries like Nepal. Thus, the objective of the study was to assess the impacts of organic farming on soil fertility and microbial activity compared to conventional farming and forest in Chitwan, Nepal. Total soil organic carbon (C) was highest in organic farming (24 mg C g⁻¹ soil) followed by conventional farming (15 mg C g⁻¹ soil) and forest (9 mg C g⁻¹ soil) in the topsoil layer (0-10 cm depth). A similar trend was found for total nitrogen (N) content in all three land uses with organic farming soil possessing the highest total N content in both 0-10 cm and 10-20 cm depth. Microbial biomass C and N were also highest under organic farming, especially in the topsoil layer (350 and 46 mg g⁻¹ soil, respectively). Similarly, microbial biomass phosphorus (P) was higher (3.6 and 1.0 mg P kg⁻¹ at 0-10 and 10-20 cm depth, respectively) in organic farming compared to conventional farming and forest at both depths. However, conventional farming and forest soils had similar microbial biomass (C, N, and P) content. After conversion of forest, the P stock significantly increased by 373% and 170% in soil under organic farming at 0-10 and 10-20 cm depth, respectively. In conventional farming, the P stock increased by 64% and 36% at 0-10 cm and 10-20 cm depth, respectively, compared to forest. Overall, organic farming practices, i.e., crop rotation, residue input and farmyard manure application, significantly alters soil fertility and microbial activity. Organic farming system is emerging as a sustainable land use system which can address the issues of food security and environment conservation by increasing sustainable agriculture production and carbon sequestration, respectively, supporting to achieve goals of sustainable development.

Keywords: organic farming, soil fertility, micobial biomas, food security

Procedia PDF Downloads 151

Authors: Rosa Tsegaye Aga, Xuan Jiang, Pavel Vazquez Faci, Siqing Liu, Simon Rayner, Endalkachew Alemu, Markos Abebe

Abstract:

Tuberculosis (TB) is a major cause of disease globally. In most cases, TB is treatable and curable, but only with the proper treatment. There is a time when drug-resistant TB occurs when bacteria become resistant to the drugs that are used to treat TB. Current strategies to identify drug-resistant TB bacteria are laboratory-based, and it takes a longer time to identify the drug-resistant bacteria and treat the patient accordingly. But machine learning (ML) and data science approaches can offer new approaches to the problem. In this study, we propose to develop an ML-based model to predict the antibiotic resistance phenotypes of TB isolates in minutes and give the right treatment to the patient immediately. The study has been using the whole genome sequence (WGS) of TB isolates as training data that have been extracted from the NCBI repository and contain different countries’ samples to build the ML models. The reason that different countries’ samples have been included is to generalize the large group of TB isolates from different regions in the world. This supports the model to train different behaviors of the TB bacteria and makes the model robust. The model training has been considering three pieces of information that have been extracted from the WGS data to train the model. These are all variants that have been found within the candidate genes (F1), predetermined resistance-associated variants (F2), and only resistance-associated gene information for the particular drug. Two major datasets have been constructed using these three information. F1 and F2 information have been considered as two independent datasets, and the third information is used as a class to label the two datasets. Five machine learning algorithms have been considered to train the model. These are Support Vector Machine (SVM), Random forest (RF), Logistic regression (LR), Gradient Boosting, and Ada boost algorithms. The models have been trained on the datasets F1, F2, and F1F2 that is the F1 and the F2 dataset merged. Additionally, an ensemble approach has been used to train the model. The ensemble approach has been considered to run F1 and F2 datasets on gradient boosting algorithm and use the output as one dataset that is called F1F2 ensemble dataset and train a model using this dataset on the five algorithms. As the experiment shows, the ensemble approach model that has been trained on the Gradient Boosting algorithm outperformed the rest of the models. In conclusion, this study suggests the ensemble approach, that is, the RF + Gradient boosting model, to predict the antibiotic resistance phenotypes of TB isolates by outperforming the rest of the models.

Keywords: machine learning, MTB, WGS, drug resistant TB

Procedia PDF Downloads 27

Authors: Marielcio Lacerda, Angelo Paulino, Elcio Shiguemori, Alvaro Damiao, Lamartine Guimaraes, Camila Anjos

Abstract:

Accurate information about the terrain is extremely important in disaster management activities or conflict. This paper proposes the use of the Unmanned Aircraft Systems (UAS) at the identification of Airdrop Zones (AZs) and Helicopter Landing Zones (HLZs). In this paper we consider the AZs the zones where troops or supplies are dropped by parachute, and HLZs areas where victims can be rescued. The use of digital image processing enables the automatic generation of an orthorectified mosaic and an actual Digital Surface Model (DSM). This methodology allows obtaining this fundamental information to the terrain’s comprehension post-disaster in a short amount of time and with good accuracy. In order to get the identification and classification of AZs and HLZs images from DJI drone, model Phantom 4 have been used. The images were obtained with the knowledge and authorization of the responsible sectors and were duly registered in the control agencies. The flight was performed on May 24, 2017, and approximately 1,300 images were obtained during approximately 1 hour of flight. Afterward, new attributes were generated by Feature Extraction (FE) from the original images. The use of multispectral images and complementary attributes generated independently from them increases the accuracy of classification. The attributes of this work include the Declivity Map and Principal Component Analysis (PCA). For the classification four distinct classes were considered: HLZ 1 – small size (18m x 18m); HLZ 2 – medium size (23m x 23m); HLZ 3 – large size (28m x 28m); AZ (100m x 100m). The Decision Tree method Random Forest (RF) was used in this work. RF is a classification method that uses a large collection of de-correlated decision trees. Different random sets of samples are used as sampled objects. The results of classification from each tree and for each object is called a class vote. The resulting classification is decided by a majority of class votes. In this case, we used 200 trees for the execution of RF in the software WEKA 3.8. The classification result was visualized on QGIS Desktop 2.12.3. Through the methodology used, it was possible to classify in the study area: 6 areas as HLZ 1, 6 areas as HLZ 2, 4 areas as HLZ 3; and 2 areas as AZ. It should be noted that an area classified as AZ covers the classifications of the other classes, and may be used as AZ, HLZ of large size (HLZ3), medium size (HLZ2) and small size helicopters (HLZ1). Likewise, an area classified as HLZ for large rotary wing aircraft (HLZ3) covers the smaller area classifications, and so on. It was concluded that images obtained through small UAV are of great use in calamity situations since they can provide data with high accuracy, with low cost, low risk and ease and agility in obtaining aerial photographs. This allows the generation, in a short time, of information about the features of the terrain in order to serve as an important decision support tool.

Keywords: disaster management, unmanned aircraft systems, helicopter landing zones, airdrop zones, random forest

Procedia PDF Downloads 151