Search results for: extra tree classifier

Authors: Carlos Arias-Alcaide, Cristina Soguero-Ruiz, Paloma Santos-Álvarez, Adrián García-Romero, Inmaculada Mora-Jiménez

Abstract:

Analysing clinical data with computers in such a way that have an impact on the practitioners’ workflow is a challenge nowadays. This paper provides a first approach for monitoring the health status of COVID-19 patients through the use of some biomarkers (blood tests) and the simplest Naïve Bayes classifier. Data of two Spanish hospitals were considered, showing the potential of our approach to estimate reasonable posterior probabilities even some days before the event.

Keywords: Bayesian model, blood biomarkers, classification, health tracing, machine learning, posterior probability

Procedia PDF Downloads 195

Authors: Yijie Wang, Tianyue Wang

Abstract:

In the past two decades, there has been a great ‘piano lesson frenzy’ among Chinese middle-class families, with a large number of parents adding piano training to children’s extra-curriculum lists. Superficially, the frenzy reflects a rather ‘leisurely’ attitude: parents typically claim that pianos lessons are ‘just for fun’ and will hopefully render children’s life more exciting. However, a closer scrutiny reveals that there is great social-status anxiety hidden beneath this ‘leisurely’ surface. Based on pre-interviews of six Chinese middle-class parents who have enthusiastically signed their children up for piano lessons, several tentative analysis are made: 1. Owing to a series of historical and social factors, the Chinese middle-class have yet to establish their cultural norms in the past few decades, resulting in great confusion concerning how to cultivate cultural tastes in their offspring. And partly due to the fact that the middle-class status of the past Chinese generation is mostly self-acquired rather than inherited, parents are much less confident about their cultural resources—which require long-time accumulation—than material ones. Both factors combine to lead to a sort of blind, overcompensating enthusiasm in culture-related education, and the piano frenzy is but a demonstration. 2. The piano has been chosen to be the object of the frenzy partly because of its inherent characteristics as well as socially-constructed ones. Costly, large in size, imported from another culture and so forth, the piano has acquired the meaning of being exclusive, high-end and exotic, which renders it a token of top-tier status among Chinese people, and piano lessons for offspring have therefore become parents’ paths towards a kind of ‘symbolic elevation’. A child playing piano is an exhibition as well as psychological assurance of the families’ middle-class status. 3. A closer look at children’s piano training process reveals that there is much more anxiety than leisurely elements involved. Despite parents’ claim that ‘piano is mainly for kids to have fun,’ the whole process is evidently of a rather ‘ascetic’ nature, with the demands of diligence and senses of time urgency throughout, and techniques rather than flair or styles are emphasized. This either means that the apparent ‘piano-for-fun’ stance is unauthentic and is only other motives in disguise, or that the Chinese middle-class parents are not yet capable of shaking off the sense of anxiety even if they sincerely intend to. 4. When viewed in relation to Chinese formal school system as well as the job market at large, it can be said that by signing children up for piano lessons, parents are consciously or unconsciously seeking to prepare for, or reduce the risks of, their children’s future social mobility. In face of possible failures in the highly-crucial, highly-competitive formal school system, piano-playing as an extra-curriculum activity may be conveniently transferred into an alternative career path. Besides, in contemporary China, as the occupational structure goes through change, and the school-related certificates decline in value, aspects such as a person’s overall deportment, which can be gained or proved by piano-learning, have been gaining in significance.

Keywords: extra-curriculum activities, middle class, piano lesson frenzy, status anxiety

Procedia PDF Downloads 224

Authors: Valentina Talu, Giulia Tola

Abstract:

Current researches and applications aimed at exploring the role of spatial configuration as a means for improving the autonomy of people with ASD (Autism Spectrum Disorder), almost exclusively focus on the definition of criteria for the design of closed, separated, private spaces devoted only to people - mainly children - with ASD. In fact, very few researches specifically investigate the relation between the city and people with autism, focusing on their sensory experiences related to the interaction with the urban environment. The growing incidence of ASD and the need to guarantee during adulthood the actual opportunity to exercise the achieved level of autonomy and independency, emphasizes the necessity to ‘broaden’ the research perspective by investigating also the specific contribution of urban mobility policies and urban design to the enhancement of the quality of life of people with ASD. Starting from these considerations, the paper describes an ongoing research focused on the relation between the city and people with autism spectrum disorder, with the specific aim of promoting their possibility of walking across the city at the neighborhood scale, thus making the access to relevant urban spaces and services possible. In the first part, the paper proposes a framework for illustrating the commonly recurring problems that people with ASD face in their daily life when they interact with the urban environment (with reference to the capability approach). Subsequently, with the support of an in depth analysis of existing contributions (researches and projects) and an exchange with different experts (neuropsychiatrists, teachers, parents), are identified two urban requirements, then 'translated' into an integrated system of urban mobility policies and extra-small tactical project aimed at enhancing the actual possibility for people with ASD of walking through the city autonomously and safely. According to this vision, the promotion of the autonomy of people with ASD through the adoption of mobility policies and micro tactical urban projects can represent an opportunity for promoting and improving the overall quality of urban life.

Keywords: city and people with ASD, quality of urban life of disadvantaged people, urban capabilities, urban design

Procedia PDF Downloads 138

Authors: Sofia Matoug, Amr Abdel-Dayem

Abstract:

This paper presents a comprehensive survey of recent research studies to segment and classify brain MR (magnetic resonance) images in order to detect significant changes to brain ventricles. The paper also presents a general framework for detecting regions that atrophy, which can help neurologists in detecting and staging Alzheimer. Furthermore, a prototype was implemented to segment brain MR images in order to extract the region of interest (ROI) and then, a classifier was employed to differentiate between normal and abnormal brain tissues. Experimental results show that the proposed scheme can provide a reliable second opinion that neurologists can benefit from.

Keywords: Alzheimer, brain images, classification techniques, Magnetic Resonance Images MRI

Procedia PDF Downloads 283

Authors: Kaleem Ahmed, Jamal A. Khan

Abstract:

Grouping patterns, habitat use, and overlap studies were conducted on five sympatric ungulate species sambar (Cervus unicolor), chital (Axis axis), muntjac (Muntiacus muntjac), goral (Nemorhaedus goral), and serow (Capricornis sumatraensis) in the Dabka watershed area within Indian West Himalayan range. Data on age, sex composition, group size, and various ecological and topographical factors governing the presence/absence of species within the study area were collected using a 250 km of a trail walk, 95 permanent circular plots of 10 m radius, and 3 vantage points with 58 scannings. The highest mean group size was recorded for chital (6.35 ± 0.50), followed by sambar (1.35 ± 0.10), goral (1.25 ±0.63), muntjac (1.12 ± 0.05), and serow (1.00 ± 0.00). Grouping pattern significantly varied among sympatric species (F = 85.10, df. = 6, P = 0.000). The highest mean pellet group density (/ha ± SE) was recorded for sambar (41.56 ± 3.51), followed by goral (23.31 ± 3.45), chital (19.21 ± 3.51), muntjac (7.43 ± 1.21), and serow (1.02 ± 0.10). Two-way variance analysis showed a significant difference in the density of the pellet group of all ungulate species across different study area habitats (F = 6.38, df = 4, P = 0.027). The availability-utilization (AU) analysis reveals that goral was mostly sighted in steep slopes, preferred > 2100 m altitudinal range with low shrub understory, avoided dense forest, and relatively more southern aspects were used. Chital had used a wide range of tree and shrub coverings with a preference towards moderate cover range (26-50%), preferred areas with low slope category ( < 25), avoided areas of high altitude > 900 m. Sambar avoided less tree cover (0-25), preferred slope category (26-500), altitudes between 1600-2100 m, and preferred dense forest with northern aspects. Muntjac used all elevation ranges in the study area with a preference towards the dense forest and northern aspects. Serow preferred high tree cover > 75%, avoided low shrub cover (0-25%), preferred high shrub cover 51-75%, utilized higher elevation > 2100 m, avoided low elevation range and northern aspects. All species occupied similar habitat types, forest or scrub, except for the goral, which preferred open spaces. Between muntjac and sambar, the highest overlap was found (65%), and there was no overlap between chital and serow, chital and goral. Aspect, slope, altitude, and vegetation characteristics were found to be important factors for the overlap of ungulate sympatric species. One major reason for their ecological separation at the fine-scale level is the differential use of altitude by ungulates in the present study. This is confirmed by the avoidance by chital of altitudes > 900 m and serow of < 2100 m.

Keywords: altitude, grouping pattern, Himalayas, overlap, ungulates

Procedia PDF Downloads 121

Authors: Taha Anjamrooz, Sareh Rajabi, Hasan Mahmmud, Ghassan Abulebdeh

Abstract:

Water availability, as well as water demand, are not uniformly distributed in time and space. Numerous extra-large water diversion projects are launched in Amazon to alleviate water scarcities. This research utilizes statistical analysis to examine the temporal and spatial features of 40 extra-large water diversion projects in Amazon. Using a network analysis method, the correlation between seven major basins is measured, while the impact analysis method is employed to explore the associated economic, environmental, and social impacts. The study unearths that the development of water diversion in Amazon has witnessed four stages, from a preliminary or initial period to a phase of rapid development. It is observed that the length of water diversion channels and the quantity of water transferred have amplified significantly in the past five decades. As of 2015, in Amazon, more than 75 billion m³ of water was transferred amidst 12,000 km long channels. These projects extend over half of the Amazon Area. The River Basin E is currently the most significant source of transferred water. Through inter-basin water diversions, Amazon gains the opportunity to enhance the Gross Domestic Product (GDP) by 5%. Nevertheless, the construction costs exceed 70 billion US dollars, which is higher than any other country. The average cost of transferred water per unit has amplified with time and scale but reduced from western to eastern Amazon. Additionally, annual total energy consumption for pumping exceeded 40 billion kilowatt-hours, while the associated greenhouse gas emissions are assessed to be 35 million tons. Noteworthy to comprehend that ecological problems initiated by water diversion influence the River Basin B and River Basin D. Due to water diversion, more than 350 thousand individuals have been relocated, away from their homes. In order to enhance water diversion sustainability, four categories of innovative measures are provided for decision-makers: development of water tradeoff projects strategies, improvement of integrated water resource management, the formation of water-saving inducements, and pricing approach, and application of ex-post assessment.

Keywords: sustainability, water trade-off projects, environment, Amazon

Procedia PDF Downloads 114

Authors: Min Wang, Sergey Utev

Abstract:

The lessons from the 2007-09 global financial crisis have driven scientific research, which considers the design of new methodologies and financial models in the global market. The quantum mechanics approach was introduced in the unpredictable stock market modeling. One famous quantum tool is Feynman path integral method, which was used to model insurance risk by Tamturk and Utev and adapted to formalize the path-dependent option pricing by Hao and Utev. The research is based on the path-dependent calculation method, which is motivated by the Feynman path integral method. The path calculation can be studied in two ways, one way is to label, and the other is computational. Labeling is a part of the representation of objects, and generating functions can provide many different ways of representing share price paths. In this paper, the recent works on graphical theoretical construction of individual share price path via matroid is presented. Firstly, a study is done on the knowledge of matroid, relationship between lattice path matroid and Tutte polynomials and ways to connect points in the lattice path matroid and Tutte polynomials is suggested. Secondly, It is found that a general binary tree can be validly constructed from a connected lattice path matroid rather than general lattice path matroid. Lastly, it is suggested that there is a way to represent share price paths via a general binary tree, and an algorithm is developed to construct share price paths from general binary trees. A relationship is also provided between lattice integer points and Tutte polynomials of a transversal matroid. Use this way of connection together with the algorithm, a share price path can be constructed from a given connected lattice path matroid.

Keywords: combinatorial construction, graphical representation, matroid, path calculation, share price, Tutte polynomial

Procedia PDF Downloads 120

Authors: Deepti Kumari, Upamanyu Hore

Abstract:

Cities are an example of a human-modified environment with few fragments of urban green spaces, which are widely considered for urban biodiversity. The study aims to address the avifaunal diversity in urban parks based on the park size and their urbanization intensity. Also, understanding the key factors affecting species composition and structure as birds are a good indicator of a healthy ecosystem, and they are sensitive to changes in the environment. A 50 m-long line-transect method is used to survey birds in 39 urban parks in Delhi, India. Habitat variables, including vegetation (percentage of non-native trees, percentage of native trees, top canopy cover, sub-canopy cover, diameter at breast height, ground vegetation cover, shrub height) were measured using the quadrat method along the transect, and disturbance variables (distance from water, distance from road, distance from settlement, park area, visitor rate, and urbanization intensity) were measured using ArcGIS and google earth. We analyzed species data for diversity and richness. We explored the relation of species diversity and richness to habitat variables using the multi-model inference approach. Diversity and richness are found significant in different park sizes and their urbanization intensity. Medium size park supports more diversity, whereas large size park has more richness. However, diversity and richness both declined with increasing urbanization intensity. The result of CCA revealed that species composition in urban parks was positively associated with tree diameter at breast height and distance from the settlement. On the model selection approach, disturbance variables, especially distance from road, urbanization intensity, and visitors are the best predictors for the species richness of birds in urban parks. In comparison, multiple regression analysis between habitat variables and bird diversity suggested that native tree species in the park may explain the diversity pattern of birds in urban parks. Feeding guilds such as insectivores, omnivores, carnivores, granivores, and frugivores showed a significant relation with vegetation variables, while carnivores and scavenger bird species mainly responded with disturbance variables. The study highlights the importance of park size in urban areas and their urbanization intensity. It also indicates that distance from the settlement, distance from the road, urbanization intensity, visitors, diameter at breast height, and native tree species can be important determining factors for bird richness and diversity in urban parks. The study also concludes that the response of feeding guilds to vegetation and disturbance in urban parks varies. Therefore, we recommend that park size and surrounding urban matrix should be considered in order to increase bird diversity and richness in urban areas for designing and planning.

Keywords: diversity, feeding guild, urban park, urbanization intensity

Procedia PDF Downloads 82

Authors: Sanjeev Kumar Appicharla

Abstract:

This paper presents the results of the modelling and analysis of the European Railway Traffic Management (ERTMS) safety-critical incident to raise awareness of biases in the systems engineering process on the Cambrian Railway in the UK using the RAIB 17/2019 as a primary input. The RAIB, the UK independent accident investigator, published the Report- RAIB 17/2019 giving the details of their investigation of the focal event in the form of immediate cause, causal factors, and underlying factors and recommendations to prevent a repeat of the safety-critical incident on the Cambrian Line. The Systems for Investigation of Railway Interfaces (SIRI) is the methodology used to model and analyze the safety-critical incident. The SIRI methodology uses the Swiss Cheese Model to model the incident and identify latent failure conditions (potentially less than adequate conditions) by means of the management oversight and risk tree technique. The benefits of the systems for investigation of railway interfaces methodology (SIRI) are threefold: first is that it incorporates the “Heuristics and Biases” approach advanced by 2002 Nobel laureate in Economic Sciences, Prof Daniel Kahneman, in the management oversight and risk tree technique to identify systematic errors. Civil engineering and programme management railway professionals are aware of the role “optimism bias” plays in programme cost overruns and are aware of bow tie (fault and event tree) model-based safety risk modelling techniques. However, the role of systematic errors due to “Heuristics and Biases” is not appreciated as yet. This overcomes the problems of omission of human and organizational factors from accident analysis. Second, the scope of the investigation includes all levels of the socio-technical system, including government, regulatory, railway safety bodies, duty holders, signaling firms and transport planners, and front-line staff such that lessons are learned at the decision making and implementation level as well. Third, the author’s past accident case studies are supplemented with research pieces of evidence drawn from the practitioner's and academic researchers’ publications as well. This is to discuss the role of system thinking to improve the decision-making and risk management processes and practices in the IEC 15288 systems engineering standard and in the industrial context such as the GB railways and artificial intelligence (AI) contexts as well.

Keywords: accident analysis, AI algorithm internal audit, bounded rationality, Byzantine failures, heuristics and biases approach

Procedia PDF Downloads 178

Authors: F. Lazzeri, I. Reiter

Abstract:

Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.

Keywords: time-series, features engineering methods for forecasting, energy demand forecasting, Azure Machine Learning

Procedia PDF Downloads 280

Authors: Hamdy Khamis Korayem, Manal Yehia Tayel, Abeer Shawky El Hadedy, Emmanuel Kamal Aziz Saba, Shimaa Badr Abdelnaby Badr

Abstract:

The aim of the current study was to demonstrate whether serum Interleukin-18 (IL-18) is increased in rheumatoid arthritis (RA) and its correlation with disease activity, functional disability and quality of life in RA patients. The study included 30 RA patients and 20 healthy normal control subjects. The RA patients were diagnosed according to the 2010 ACR/EULAR classification criteria for RA with the exclusion of those who had diabetes mellitus, endocrine disorders, associated rheumatologic diseases, viral hepatitis B or C and other diseases with increased serum IL-18 level. All patients were subjected to clinical evaluation of the musculoskeletal system. Disease activity was assessed by disease activity score 28 with 4 variables (DAS 28). Functional disability was assessed by health assessment questionnaire disability index (HAQ-DI). The quality of life was assessed by Short form-36 (SF-36) questionnaire. Radiological assessment of both hands and feet by Sharp/van der Heijde (SvH) scoring method. Laboratory parameters including erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), rheumatoid factor (RF) and anti-cyclic citrullinated peptide antibody (ACPA) were assessed in patients and serum level of IL-18 in both patients and control subjects. There was no statistically significant difference between patient and control group as regards age and sex. Among patients, 29 % were females and the age range was between 25 to 55 years. Extra-articular manifestations were presented in 56.7% of the patients. The mean of DAS 28 score was 5.73±1.46 and that of HAQ-DI was 1.22±0.72 while that of SF-36 was 40.03±13.96. The level of serum IL-18 was significantly higher in patients than in the control subjects (P= 0.030). Serum IL-18 was correlated with ACPA among the patient group. There were no statistically significant correlations between serum IL-18 and DAS28, HAQ-DI, SF-36, total SvH score and the other laboratory results. In conclusion, IL-18 is significantly higher in RA patient than in healthy control subjects and positively correlated with ACPA level. IL-18 is associated with extra-articular manifestations. However, it is not correlated with other laboratory parameters, disease activity, functional disability, quality of life nor radiological severity.

Keywords: disease activity score, Interleukin-18, quality of life assessment, rheumatoid arthritis

Procedia PDF Downloads 308

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 58

Authors: Mohammed Hmimou, Khalid Amediaz, Imane Sebari, Nabil Bounajma

Abstract:

Annual crop production is one of the most important macroeconomic indicators for the majority of countries around the world. This information is valuable, especially for exporting countries which need a yield estimation before harvest in order to correctly plan the supply chain. When it comes to estimating agricultural yield, especially for arboriculture, conventional methods are mostly applied. In the case of the citrus industry, the sale before harvest is largely practiced, which requires an estimation of the production when the fruit is on the tree. However, conventional method based on the sampling surveys of some trees within the field is always used to perform yield estimation, and the success of this process mainly depends on the expertise of the ‘estimator agent’. The present study aims to propose a methodology based on the combination of unmanned aerial vehicle (UAV) images and terrestrial laser scanner (TLS) point cloud to estimate citrus production. During data acquisition, a fixed wing and rotatory drones, as well as a terrestrial laser scanner, were tested. After that, a pre-processing step was performed in order to generate point cloud and digital surface model. At the processing stage, a machine vision workflow was implemented to extract points corresponding to fruits from the whole tree point cloud, cluster them into fruits, and model them geometrically in a 3D space. By linking the resulting geometric properties to the fruit weight, the yield can be estimated, and the statistical distribution of fruits size can be generated. This later property, which is information required by importing countries of citrus, cannot be estimated before harvest using the conventional method. Since terrestrial laser scanner is static, data gathering using this technology can be performed over only some trees. So, integration of drone data was thought in order to estimate the yield over a whole orchard. To achieve that, features derived from drone digital surface model were linked to yield estimation by laser scanner of some trees to build a regression model that predicts the yield of a tree given its features. Several missions were carried out to collect drone and laser scanner data within citrus orchards of different varieties by testing several data acquisition parameters (fly height, images overlap, fly mission plan). The accuracy of the obtained results by the proposed methodology in comparison to the yield estimation results by the conventional method varies from 65% to 94% depending mainly on the phenological stage of the studied citrus variety during the data acquisition mission. The proposed approach demonstrates its strong potential for early estimation of citrus production and the possibility of its extension to other fruit trees.

Keywords: citrus, digital surface model, point cloud, terrestrial laser scanner, UAV, yield estimation, 3D modeling

Procedia PDF Downloads 121

Authors: M. T. Alodat

Abstract:

In this paper, we propose a mechanism for skewing any symmetric distribution. The new distribution is called the deflation-inflation distribution (DID). We discuss some statistical properties of the DID such moments, stochastic representation, log-concavity. Also we fit the distribution to real data and we compare it to normal distribution and Azzlaini's skew normal distribution. Numerical results show that the DID fits the the tree ring data better than the other two distributions.

Keywords: normal distribution, moments, Fisher information, symmetric distributions

Procedia PDF Downloads 641

Authors: Amine Ganibardi, Cherif Arab Ali

Abstract:

This paper addresses the data cleaning issue as a part of web usage data preprocessing within the scope of Web Usage Mining. Weblog data recorded by web servers within log files reflect usage activity, i.e., End-users’ clicks and underlying user-agents’ hits. As Web Usage Mining is interested in End-users’ behavior, user-agents’ hits are referred to as noise to be cleaned-off before mining. Filtering hits from clicks is not trivial for two reasons, i.e., a server records requests interlaced in sequential order regardless of their source or type, website resources may be set up as requestable interchangeably by end-users and user-agents. The current methods are content-centric based on filtering heuristics of relevant/irrelevant items in terms of some cleaning attributes, i.e., website’s resources filetype extensions, website’s resources pointed by hyperlinks/URIs, http methods, user-agents, etc. These methods need exhaustive extra-weblog data and prior knowledge on the relevant and/or irrelevant items to be assumed as clicks or hits within the filtering heuristics. Such methods are not appropriate for dynamic/responsive Web for three reasons, i.e., resources may be set up to as clickable by end-users regardless of their type, website’s resources are indexed by frame names without filetype extensions, web contents are generated and cancelled differently from an end-user to another. In order to overcome these constraints, a clustering-based cleaning method centered on the logging structure is proposed. This method focuses on the statistical properties of the logging structure at the requested and referring resources attributes levels. It is insensitive to logging content and does not need extra-weblog data. The used statistical property takes on the structure of the generated logging feature by webpage requests in terms of clicks and hits. Since a webpage consists of its single URI and several components, these feature results in a single click to multiple hits ratio in terms of the requested and referring resources. Thus, the clustering-based method is meant to identify two clusters based on the application of the appropriate distance to the frequency matrix of the requested and referring resources levels. As the ratio clicks to hits is single to multiple, the clicks’ cluster is the smallest one in requests number. Hierarchical Agglomerative Clustering based on a pairwise distance (Gower) and average linkage has been applied to four logfiles of dynamic/responsive websites whose click to hits ratio range from 1/2 to 1/15. The optimal clustering set on the basis of average linkage and maximum inter-cluster inertia results always in two clusters. The evaluation of the smallest cluster referred to as clicks cluster under the terms of confusion matrix indicators results in 97% of true positive rate. The content-centric cleaning methods, i.e., conventional and advanced cleaning, resulted in a lower rate 91%. Thus, the proposed clustering-based cleaning outperforms the content-centric methods within dynamic and responsive web design without the need of any extra-weblog. Such an improvement in cleaning quality is likely to refine dependent analysis.

Keywords: clustering approach, data cleaning, data preprocessing, weblog data, web usage data

Procedia PDF Downloads 160

Authors: Athanasia Eirini Zarkadi, Despoina Balli, Olga Elpis Kolokitha

Abstract:

Objective: Impacted maxillary canines are a frequent condition and a common reason for patients seeking orthodontic treatment. Their simultaneous presence with dental anomalies raises a question about their possible connection. The aim of this study was to investigate the association of maxillary impacted canines with dental anomalies. Materials and Methods: Files of 874 patients from an orthodontic private practice in Greece were evaluated for the presence of maxillary impacted canines. From this sample, a group of 97 patients (39 males and 58 females) with at least one impacted maxillary canine were selected and consisted of the study group (canine impaction group) of this study. This group was compared to a control group of 97 patients (42 males and 55 females) that was created by random selection from the initial sample without maxillary canine impaction. The impaction diagnosis was made from the panoramic radiographs and confirmed from the surgery. The association between maxillary canine impaction and dental anomalies was examined with the chi-square test. A classification tree was created to further investigate the relations between impaction and dental anomalies. The reproducibility of diagnoses was assessed by re-examining the records of 25 patients two weeks after the first examination. Results: The found associated anomalies were cone-shaped upper lateral incisors and infraocclusion of deciduous molars. There is a significant increase in the prevalence of 12,4% of distal displacement of the unerupted mandibular second premolar in the canine impaction group compared to the control group that was 7,2%. The classification tree showed that the presence of a cone-shaped maxillary lateral incisor gave rise to the probability of an impacted canine to 83,3%. Conclusions: The presence of cone-shaped maxillary lateral incisors and infraocclusion of deciduous molars can be considered valuable early risk indicators for maxillary canine impaction.

Keywords: cone-shaped maxillary lateral incisors, dental anomalies, impacted canines, infraoccluded deciduous molars

Procedia PDF Downloads 131

Authors: Abdullah Al Farwan, Ya Zhang

Abstract:

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

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

Procedia PDF Downloads 144

Authors: Mohammad Rajabalinejad

Abstract:

Safety is often seen as a requirement or a performance indicator through the design process, and this does not always result in optimally safe products or systems. This paper suggests integrating the best safety practices with the design process to enrich the exploration experience for designers and add extra values for customers. For this purpose, the commonly practiced safety standards and design methods have been reviewed and their common blocks have been merged forming Safety Cube. Safety Cube combines common blocks for design, hazard identification, risk assessment and risk reduction through an integral approach. An example application presents the use of Safety Cube for design of machinery.

Keywords: safety, safety cube, product, system, machinery, design

Procedia PDF Downloads 222

Authors: Ashu Rastogi, Uttam Thakur, Jimmy Pathak, Rajesh Gupta, Anil Bhansali

Abstract:

Introduction: Liraglutide is known to induce weight loss and metabolic benefits in obese individuals. However, its effect after sleeve gastrectomy are not known. Methods: People with obesity (BMI>27.5 kg/m2) underwent LSG. Subsequently, participants were randomized to receive either 0.6mg liraglutide subcutaneously daily from 6 week post to be continued till 24 week (L-L group) or placebo (L-P group). Patients were assessed before surgery (baseline) and 6 weeks, 12weeks, 18weeks and 24weeks after surgery for height, weight, waist and hip circumference, BMI, body fat percentage, HbA1c, fasting C-peptide, fasting insulin, HOMA-IR, HOMA-β, GLP-1 levels (after standard OGTT). MRI abdomen was performed prior to surgery and at 24weeks post operatively for the estimation of intrapancreatic and intrahepatic fat content. Outcome measures: Primary outcomes were changes in metabolic variables of fasting and stimulated GLP-1 levels, insulin, c-peptide, plasma glucose levels. Secondary variables were indices of insulin resistance HOMA-IR, Matsuda index; and pancreatic and hepatic steatosis. Results: Thirty-eight patients undergoing LSG were screened and 29 participants were enrolled. Two patients withdrew consent and one patient died of acute coronary event. 26 patients were randomized and data analysed. Median BMI was 40.73±3.66 and 46.25±6.51; EBW of 49.225±11.14 and 651.48±4.85 in the L-P and L-L group, respectively. Baseline FPG was 132±51.48, 125±39.68; fasting insulin 21.5±13.99, 13.15±9.20, fasting GLP-1 2.4± .37, 2.4± .32, AUC GLP-1 340.78± 44 and 332.32 ± 44.1, HOMA-IR 7.0±4.2 and 4.42±4.5 in the L-P and L-L group, respectively. EBW loss was 47± 13.20 and 65.59± 24.20 (p<0.05) in the placebo versus liraglutide group. However, we did not observe inter-group difference in metabolic parameters between the groups in spite of significant intra-group changes after 6 months of LSG. Intra-pancreatic fat prior to surgery was 3.21±1.7 and 2.2±0.9 (p=0.38) that decreased to 2.14±1.8 and 1.06±0.8 (p=0.25) at 6 months in L-P and L-L group, respectively. Similarly, intra-pancreatic fat was 1.97±0.27 and 1.88±0.36 (p=0.361) at baseline that decreased to 1.14±0.44 and 1.36±0.47 (p=0.465) at 6 months in L-P and L-L group, respectively. Conclusion: Liraglutide augments extra body weight loss after sleeve gastrectomy. A decrease in intra-pancreatic and intra-hepatic fat is noticed after bariatric surgery without additive benefit of liraglutide administration.

Keywords: sleeve gastrectomy, liraglutide, intra-pancreatic fat, insulin

Procedia PDF Downloads 172

Authors: D. Touil, L. Ouadah

Abstract:

An industrial model of cement grinding circuit is proposed on the basis of sampling surveys undertaken in the Meftah cement plant in Algiers, Algeria. The ball mill is described by a series of equal fully mixed stages that incorporates the effect of air sweeping. The kinetic parameters of this material in the energy normalized form obtained using the data of batch dry ball milling are taken into account in developing the present scale-up procedure. The dynamic separator is represented by the air classifier selectivity equation corrected by empirical factors. The model is incorporated in computer program that predict full size distributions and mass flow rates for all streams in a circuit under a particular set of operating conditions.

Keywords: grinding circuit, clinker, cement, modeling, population balance, energy

Procedia PDF Downloads 508

Authors: Srushti Patil, Preethi Baligar, Gopalkrishna Joshi, Gururaj N. Bhadri

Abstract:

In designing learning environments, the instructional strategies can be tailored to suit the learning style of an individual to ensure effective learning. In this study, the information shared on social media like Facebook is being used to predict learning style of a learner. Previous research studies have shown that Facebook data can be used to predict user personality. Users with a particular personality exhibit an inherent pattern in their digital footprint on Facebook. The proposed work aims to correlate the user's’ personality, predicted from Facebook data to the learning styles, predicted through questionnaires. For Millennial learners, Facebook has become a primary means for information sharing and interaction with peers. Thus, it can serve as a rich bed for research and direct the design of learning environments. The authors have conducted this study in an undergraduate freshman engineering course. Data from 320 freshmen Facebook users was collected. The same users also participated in the learning style and personality prediction survey. The Kolb’s Learning style questionnaires and Big 5 personality Inventory were adopted for the survey. The users have agreed to participate in this research and have signed individual consent forms. A specific page was created on Facebook to collect user data like personal details, status updates, comments, demographic characteristics and egocentric network parameters. This data was captured by an application created using Python program. The data captured from Facebook was subjected to text analysis process using the Linguistic Inquiry and Word Count dictionary. An analysis of the data collected from the questionnaires performed reveals individual student personality and learning style. The results obtained from analysis of Facebook, learning style and personality data were then fed into an automatic classifier that was trained by using the data mining techniques like Rule-based classifiers and Decision trees. This helps to predict the user personality and learning styles by analysing the common patterns. Rule-based classifiers applied for text analysis helps to categorize Facebook data into positive, negative and neutral. There were totally two models trained, one to predict the personality from Facebook data; another one to predict the learning styles from the personalities. The results show that the classifier model has high accuracy which makes the proposed method to be a reliable one for predicting the user personality and learning styles.

Keywords: educational data mining, Facebook, learning styles, personality traits

Procedia PDF Downloads 209

Authors: Suzan Wedyan

Abstract:

Data mining is one of the main phases in the Knowledge Discovery Database (KDD) which is responsible of finding hidden and useful knowledge from databases. There are many different tasks for data mining including regression, pattern recognition, clustering, classification, and association rule. In recent years a promising data mining approach called associative classification (AC) has been proposed, AC integrates classification and association rule discovery to build classification models (classifiers). This paper surveys and critically compares several AC algorithms with reference of the different procedures are used in each algorithm, such as rule learning, rule sorting, rule pruning, classifier building, and class allocation for test cases.

Keywords: associative classification, classification, data mining, learning, rule ranking, rule pruning, prediction

Procedia PDF Downloads 517

Authors: Tamirat Solomon, Aberash Yohannis, Efrem Gulfo

Abstract:

The plantation of trees, which harmonizes the agroecology of the environment, has been implemented in Ethiopia with great concern for a noticeably degraded environment. This study was designed to evaluate the effectiveness of green legacy, species selection and, the rate of survival, and the management status in the study areas. A systematic sampling method was employed to collect the required data from 144 quadrants measuring a 15m radius with an interval of 40m apart. Additionally, 244 sample households were selected for the socioeconomic study in addition to secondary data collected from office recordings. The data collected was analyzed using multivariate analysis, considering exposure and outcome variables. The findings of this study indicated that four exotic tree species, namely; A. salgina, C. fistula, A. indica, and G. robusta, were commonly selected tree species for degraded land restoration in the study areas. Among the seedlings planted at the four study sites, a total of 79.9% survived, and A. salgina was the dominant and best performed species, A. indica was the least survived species in the entire study area. The age of the seedling before planting significantly (p = 0.05) affected the survival potential of most seedlings of species, and the majority (82%) of local communities expressed their positive attitudes and willingness to manage the restoration works in the study areas. It was recommended to consider the inclusion of native species in the restoration effort and evaluate the co-existence of native flora with exotic and its competition for nutrients, water, and light in addition to the invading potentials in the ecosystem. In general, before embarking on degraded land restoration, species selection, adequate preparation of seedlings, and species diversity composition that exactly fit the socioeconomic and ecological demands of the areas must get the attention for the success of the restoration.

Keywords: plantation forest, degraded land, forest restoration, plantation survival, species selection

Procedia PDF Downloads 56

Authors: Nelly S. Aggangan, Julieta A. Anarna

Abstract:

Indigenous tree species are priority planting materials for the National Greening Program of the Department of Environment and Natural Resources. Areas for reforestation are marginal grasslands where plant growth is stunted and seedling survival is low. This experiment was conducted to compare growth rates and seedling survival of seven indigenous reforestation species. Narra (Pterocarpus indicus), salago (Wikstroemia lanceolata), kisubeng (Sapindus saponaria), tuai (Biscofia javanica), batino (Alstonia macrophylla), bani (Pongamina pinnata) and ipil (Intsia bijuga) were inoculated with Mykovam® (mycorrhizal fungi) and Bio-N® (N2-fixing bacteria) during pricking. After five months in the nursery, the treated seedlings were planted in degraded upland acidic red soil in Cavinti, Laguna (Luzon). During outplanting, all mycorrhiza inoculated seedlings had 50-80% mycorrhizal roots while the control ones had 5-10% mycorrhizal roots. Mykovam increased height of narra, salago and kisubeng. Stem diameter was bigger in mycorrhizal salago than the control. After two years in the field, Mykovam®+Bio-N® inoculated narra, salago and bani gave 95% survival while non-mycorrhizal tuai gave the lowest survival (25%). Inoculated seedlings grew faster than the control. Highest height increase was in batino (103%), followed by bani (95%), ipil (59%), narra (58%), tuai (53%) and kisubeng was the lowest (10%). Stem diameter was increased by Mykovam® from 13-39% over the control. Highest stem diameter was obtained from narra (50%), followed by bani (40%), batino (36%), ipil (33%), salago (28%), kisubeng and tuai (12%) had the lowest. In conclusion, Mykovam® inoculated batino, bani, narra, salago and ipil can be selected to restore degraded upland acidic red soil in the Philippines.

Keywords: Azospirillum spp., Bio-N®, Mykovam®, nitrogen fixing bacteria, acidic red soil

Procedia PDF Downloads 276

Authors: Marlene Yu Lilin Wätzold, Wisnu Harto Adiwijoyo, Meike Wollni

Abstract:

Land-use conversion from tropical forests to cash crop production in the form of monocultures has drastic consequences for biodiversity. Meanwhile, high dependence on cash crop production is often associated with a decrease in other food crop production, thereby affecting household dietary diversity. Additionally, deforestation rates have been found to reduce households’ dietary diversity, as forests often offer various food sources. Agroforestry systems are seen as a potential solution to improve local biodiversity as well as provide a range of provisioning ecosystem services, such as timber and other food crops. While a number of studies have analyzed the effects of agroforestry on biodiversity, as well as household livelihood indicators, little is understood between potential trade-offs or synergies between the two. This interdisciplinary study aims to fill this gap by assessing cacao agroforestry’s role in enhancing local bird diversity, as well as farm household dietary diversity. Additionally, we will take a landscape perspective and investigate in what ways the landscape composition, such as the proximity to forests and forest patches, are able to contribute to the local bird diversity, as well as households’ dietary diversity. Our study will take place in two agro-ecological zones in Ghana, based on household surveys of 500 cacao farm households. Using a subsample of 120 cacao plots, we will assess the degree of shade tree diversity and density using drone flights and a computer vision tree detection algorithm. Bird density and diversity will be assessed using sound recordings that will be kept in the cacao plots for 24 hours. Landscape compositions will be assessed via remote sensing images. The results of our study are of high importance as they will allow us to understand the effects of agroforestry and landscape composition in improving simultaneous ecosystem services.

Keywords: agroforestry, biodiversity, landscape composition, nutrition

Procedia PDF Downloads 90

Authors: John Gichimu Mbaka, Jan Helmrich Martin von Baumbach, Celia Somlai, Denis Köpfer, Andreas Maeck, Andreas Lorke, Ralf Schäfer

Abstract:

Leaf litter decomposition is an important process providing energy to biotic communities. Additionally, methane gas (CH4) has been identified as an important alternative source of carbon and energy in some freshwater food webs.Flow regulation and dams can strongly alter freshwater ecosystems, but little is known about the effect of small impoundments on leaf litter decomposition and methane derived carbon in streams. In this study, we tested the effect of small water storage impoundments on leaf litter decomposition rates and methane derived carbon. Leaf litter decomposition rates were assessed by comparing treatment sites located close to nine impoundments (Rheinland Pfalz state, Germany) and reference sites located far away from the impoundments.CH4 concentrations were measured in eleven impoundments and correlated with the δ13C values of two subfamilies of chironomid larvae (i.e. Chironomini and Tanypodinae). Leaf litter break down rates were significantly lower in study sites located immediately above the impoundments, especially associated with a reduction in the abundance of shredders. Chironomini larvae had the lower mean δ13C values (‒29.2 to ‒25.5 ‰), than Tanypodinae larvae (‒26.9 to ‒25.3 ‰).No significant relationships were established between CH4 concentrations and δ13C values of chironomids (p> 0.05).Mean δ13C values of chironomid larvae (mean: ‒26.8‰, range: ‒ 29.2‰ to ‒ 25.3‰) were similar to those of sedimentary organic matter (SOM) (mean: ‒28.4‰, range: ‒ 29.3‰ to ‒ 27.1‰) and tree leaf litter (mean: ‒29.8 ‰, range: ‒ 30.5‰ to ‒ 29.1‰). In conclusion, this study demonstrates that small impoundments may have a negative effect on leaf litter decomposition in forest streams and that CH4 has limited influence on the benthic food web in stream impoundments.

Keywords: river functioning, chironomids, Alder tree, stable isotopes, methane oxidation, shredder

Procedia PDF Downloads 715

Authors: Yanto Santosa, Dede Aulia Rahman, Cory Wulan, Abdul Haris Mustari

Abstract:

The global demand for long-tailed macaques for medical experimentation has continued to increase. Fulfillment of Indonesian export demands has been mostly from natural habitats, based on a harvesting quota. This quota has been determined according to the total catch for a given year, and not based on consideration of any demographic parameters or physical environmental factors with regard to the animal; hence threatening the sustainability of the various populations. It is therefore necessary to formulate a method for calculating a sustainable harvesting quota, based on population parameters in natural habitats. Considering the possibility of variations in habitat characteristics and population parameters, a time series observation of demographic and physical/biotic parameters, in various habitats, was performed on 13 groups of long-tailed macaques, distributed throughout the West Java, Lampung and Yogyakarta areas of Indonesia. These provinces were selected for comparison of the influence of human/tourism activities. Data on population parameters that was collected included data on life expectancy according to age class, numbers of individuals by sex and age class, and ‘ratio of infants to reproductive females’. The estimation of population growth was based on a population dynamic growth model: the Leslie matrix. The harvesting quota was calculated as being the difference between the actual population size and the MVP (minimum viable population) for each sex and age class. Observation indicated that there were variations within group size (24 – 106 individuals), gender (sex) ratio (1:1 to 1:1.3), life expectancy value (0.30 to 0.93), and ‘ratio of infants to reproductive females’ (0.23 to 1.56). Results of subsequent calculations showed that sustainable harvesting quotas for each studied group of long-tailed macaques, ranged from 29 to 110 individuals. An estimation model of the MVP for each age class was formulated as Log Y = 0.315 + 0.884 Log Ni (number of individual on ith age class). This study also found that life expectancy for the juvenile age class was affected by the humidity under tree stands, and dietary plants’ density at sapling, pole and tree stages (equation: Y= 2.296 – 1.535 RH + 0.002 Kpcg – 0.002 Ktg – 0.001 Kphn, R2 = 89.6% with a significance value of 0.001). By contrast, for the sub-adult-adult age class, life expectancy was significantly affected by slope (equation: Y=0.377 = 0.012 Kml, R2 = 50.4%, with significance level of 0.007). The infant to reproductive female ratio was affected by humidity under tree stands, and dietary plant density at sapling and pole stages (equation: Y = -1.432 + 2.172 RH – 0.004 Kpcg + 0.003 Ktg, R2 = 82.0% with significance level of 0.001). This research confirmed the importance of population parameters in determining the minimum viable population, and that MVP varied according to habitat characteristics (especially food availability). It would be difficult therefore, to formulate a general mathematical equation model for determining a harvesting quota for the species as a whole.

Keywords: harvesting, long-tailed macaque, population, quota

Procedia PDF Downloads 407

Authors: Lucas A. Silva, Carla R. Aguiar

Abstract:

This work presents a proposal to perform contextual sentiment analysis using a supervised learning algorithm and disregarding the extensive training of annotators. To achieve this goal, a web platform was developed to perform the entire procedure outlined in this paper. The main contribution of the pipeline described in this article is to simplify and automate the annotation process through a system of analysis of congruence between the notes. This ensured satisfactory results even without using specialized annotators in the context of the research, avoiding the generation of biased training data for the classifiers. For this, a case study was conducted in a blog of entrepreneurship. The experimental results were consistent with the literature related annotation using formalized process with experts.

Keywords: sentiment analysis, untrained annotators, naive bayes, entrepreneurship, contextualized classifier

Procedia PDF Downloads 374

Authors: Lydia Murugi Mugendi

Abstract:

The promotion of tree growing as a lucrative enterprise is the focus of this paper as management practices have shifted focus from protection of natural forest resources to community/government partnerships with the aim of resource conservation, management and increase of on-farm tree growing. Using KEFRI as (the source) of information pertaining Melia volkensii (the medium or message) being transferred, this paper investigates the current perception towards forestry and the behavioural attitudes of recipients of forest intervention activities. The two objectives explored in this paper are to find out the level of adoption of Mukau in Kitui, Kibwezi and Samburu/Taru and secondly, to find out the characteristics of the adoption process between Kitui, Kibwezi and Samburu/Taru. The methodologies used during data collection were participatory rural appraisal tools in conjunction with the social survey questionnaires. Simple random sampling and snowball sampling were used to identify respondents within the three target sites and analysis was done using SPSS. Results of the study of indicating that adoption rates of the Mukau in Samburu/Taru, where forestry-related activities were introduced within the past one decade had significantly increase despite initial resistance. The other areas, which had benefited from numerous decades of intense forestry extension projects and activities, indicated a decline in re-adoption rates of Mukau as an enterprise. This study has brought out the reality of adoption trends and state of Mukau population within the three counties while providing a glimpse towards the communities’ perception in regards to adoption of forestry and other environmental innovations. The outcome of the study is to provide a guideline for extension/ dissemination officers in KEFRI and related stakeholders to promote seamless cohesive interaction between the recipient communities of the proposed interventions.

Keywords: adoption, innovation, enterprise, extension, DOI Theory

Procedia PDF Downloads 89

Authors: Vivek Mahadev, Manoj Kumar, Neelu Mathur, Brahm Dutt Pandey

Abstract:

Perimeter guarding and protection of critical installations require prompt intrusion detection and assessment to take effective countermeasures. Currently, visual and electronic surveillance are the primary methods used for perimeter guarding. These methods can be costly and complicated, requiring careful planning according to the location and terrain. Moreover, these methods often struggle to detect stealthy and camouflaged insurgents. The object of the present work is to devise a surveillance technique using seismic sensors that overcomes the limitations of existing systems. The aim is to improve intrusion detection, assessment, and characterization by utilizing seismic sensors. Most of the similar systems have only two types of intrusion detection capability viz., human or vehicle. In our work we could even categorize further to identify types of intrusion activity such as walking, running, group walking, fence jumping, tunnel digging and vehicular movements. A virtual fence of 60 meters at GCNEP, Bahadurgarh, Haryana, India, was created by installing four underground geophones at a distance of 15 meters each. The signals received from these geophones are then processed to find unique seismic signatures called features. Various feature optimization and selection methodologies, such as LightGBM, Boruta, Random Forest, Logistics, Recursive Feature Elimination, Chi-2 and Pearson Ratio were used to identify the best features for training the machine learning models. The trained models were developed using algorithms such as supervised support vector machine (SVM) classifier, kNN, Decision Tree, Logistic Regression, Naïve Bayes, and Artificial Neural Networks. These models were then used to predict the category of events, employing weighted ensemble voting to analyze and combine their results. The models were trained with 1940 training events and results were evaluated with 831 test events. It was observed that using the weighted ensemble voting increased the efficiency of predictions. In this study we successfully developed and deployed the virtual fence using geophones. Since these sensors are passive, do not radiate any energy and are installed underground, it is impossible for intruders to locate and nullify them. Their flexibility, quick and easy installation, low costs, hidden deployment and unattended surveillance make such systems especially suitable for critical installations and remote facilities with difficult terrain. This work demonstrates the potential of utilizing seismic sensors for creating better perimeter guarding and protection systems using multiple machine learning models in weighted ensemble voting. In this study the virtual fence achieved an intruder detection efficiency of over 97%.

Keywords: geophone, seismic perimeter surveillance, machine learning, weighted ensemble method

Procedia PDF Downloads 61