Search results for: Land Classification
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 1532

Search results for: Land Classification

122 Socio-Economic Influences on Soilless Agriculture

Authors: G. V. Byrd, B. B. Ghaley, E. Hayashi

Abstract:

In urban farming, research and innovation are taking place at an unprecedented pace, and soilless growing technologies are emerging at different rates motivated by different objectives in various parts of the world. Local food production is ultimately a main objective everywhere, but adoption rates and expressions vary with socio-economic drivers. Herein, the status of hydroponics and aquaponics is summarized for four countries with diverse socio-economic settings: Europe (Denmark), Asia (Japan and Nepal) and North America (US). In Denmark, with a strong environmental ethic, soilless growing is increasing in urban agriculture because it is considered environmentally friendly. In Japan, soil-based farming is being replaced with commercial plant factories using advanced technology such as complete environmental control and computer monitoring. In Nepal, where rapid loss of agricultural land is occurring near cities, dozens of hydroponics and aquaponics systems have been built in the past decade, particularly in “non-traditional” sites such as roof tops to supplement family food. In the US, where there is also strong interest in locally grown fresh food, backyard and commercial systems have proliferated. Nevertheless, soilless growing is still in the research and development and early adopter stages, and the broad contribution of hydroponics and aquaponics to food security is yet to be fully determined. Nevertheless, current adoption of these technologies in diverse environments in different socio-economic settings highlights the potential contribution to food security with social and environmental benefits which contribute to several Sustainable Development Goals.

Keywords: Aquaponics, hydroponics, soilless agriculture, urban agriculture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 78
121 Quantification of E-Waste: A Case Study in Federal University of Espírito Santo, Brazil

Authors: Andressa S. T. Gomes, Luiza A. Souza, Luciana H. Yamane, Renato R. Siman

Abstract:

The segregation of waste of electrical and electronic equipment (WEEE) in the generating source, its characterization (quali-quantitative) and identification of origin, besides being integral parts of classification reports, are crucial steps to the success of its integrated management. The aim of this paper was to count WEEE generation at the Federal University of Espírito Santo (UFES), Brazil, as well as to define sources, temporary storage sites, main transportations routes and destinations, the most generated WEEE and its recycling potential. Quantification of WEEE generated at the University in the years between 2010 and 2015 was performed using data analysis provided by UFES’s sector of assets management. EEE and WEEE flow in the campuses information were obtained through questionnaires applied to the University workers. It was recorded 6028 WEEEs units of data processing equipment disposed by the university between 2010 and 2015. Among these waste, the most generated were CRT screens, desktops, keyboards and printers. Furthermore, it was observed that these WEEEs are temporarily stored in inappropriate places at the University campuses. In general, these WEEE units are donated to NGOs of the city, or sold through auctions (2010 and 2013). As for recycling potential, from the primary processing and further sale of printed circuit boards (PCB) from the computers, the amount collected could reach U$ 27,839.23. The results highlight the importance of a WEEE management policy at the University.

Keywords: Solid waste, waste of electric and electronic equipment, waste management, institutional generation of solid waste.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1520
120 Technology Identification, Evaluation and Selection Methodology for Industrial Process Water and Waste Water Treatment Plant of 3x150 MWe Tufanbeyli Lignite-Fired Power Plant

Authors: Cigdem Safak Saglam

Abstract:

Most thermal power plants use steam as working fluid in their power cycle. Therefore, in addition to fuel, water is the other main input for thermal plants. Water and steam must be highly pure in order to protect the systems from corrosion, scaling and biofouling. Pure process water is produced in water treatment plants having many several treatment methods. Treatment plant design is selected depending on raw water source and required water quality. Although working principle of fossil-fuel fired thermal power plants are same, there is no standard design and equipment arrangement valid for all thermal power plant utility systems. Besides that, there are many other technology evaluation and selection criteria for designing the most optimal water systems meeting the requirements such as local conditions, environmental restrictions, electricity and other consumables availability and transport, process water sources and scarcity, land use constraints etc. Aim of this study is explaining the adopted methodology for technology selection for process water preparation and industrial waste water treatment plant in a thermal power plant project located in Tufanbeyli, Adana Province in Turkey. Thermal power plant is fired with indigenous lignite coal extracted from adjacent lignite reserves. This paper addresses all above-mentioned factors affecting the thermal power plant water treatment facilities (demineralization + waste water treatment) design and describes the ultimate design of Tufanbeyli Thermal Power Plant Water Treatment Plant.

Keywords: Thermal power plant, lignite coal, pre-treatment, demineralization, electrodialysis, recycling, waste water, process water.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1680
119 Incorporating Lexical-Semantic Knowledge into Convolutional Neural Network Framework for Pediatric Disease Diagnosis

Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen

Abstract:

The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluates the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.

Keywords: lexical semantics, feature representation, semantic decision, convolutional neural network, electronic medical record

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 544
118 Cirrhosis Mortality Prediction as Classification Using Frequent Subgraph Mining

Authors: Abdolghani Ebrahimi, Diego Klabjan, Chenxi Ge, Daniela Ladner, Parker Stride

Abstract:

In this work, we use machine learning and data analysis techniques to predict the one-year mortality of cirrhotic patients. Data from 2,322 patients with liver cirrhosis are collected at a single medical center. Different machine learning models are applied to predict one-year mortality. A comprehensive feature space including demographic information, comorbidity, clinical procedure and laboratory tests is being analyzed. A temporal pattern mining technic called Frequent Subgraph Mining (FSM) is being used. Model for End-stage liver disease (MELD) prediction of mortality is used as a comparator. All of our models statistically significantly outperform the MELD-score model and show an average 10% improvement of the area under the curve (AUC). The FSM technic itself does not improve the model significantly, but FSM, together with a machine learning technique called an ensemble, further improves the model performance. With the abundance of data available in healthcare through electronic health records (EHR), existing predictive models can be refined to identify and treat patients at risk for higher mortality. However, due to the sparsity of the temporal information needed by FSM, the FSM model does not yield significant improvements. Our work applies modern machine learning algorithms and data analysis methods on predicting one-year mortality of cirrhotic patients and builds a model that predicts one-year mortality significantly more accurate than the MELD score. We have also tested the potential of FSM and provided a new perspective of the importance of clinical features.

Keywords: machine learning, liver cirrhosis, subgraph mining, supervised learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 400
117 A Novel Neighborhood Defined Feature Selection on Phase Congruency Images for Recognition of Faces with Extreme Variations

Authors: Satyanadh Gundimada, Vijayan K Asari

Abstract:

A novel feature selection strategy to improve the recognition accuracy on the faces that are affected due to nonuniform illumination, partial occlusions and varying expressions is proposed in this paper. This technique is applicable especially in scenarios where the possibility of obtaining a reliable intra-class probability distribution is minimal due to fewer numbers of training samples. Phase congruency features in an image are defined as the points where the Fourier components of that image are maximally inphase. These features are invariant to brightness and contrast of the image under consideration. This property allows to achieve the goal of lighting invariant face recognition. Phase congruency maps of the training samples are generated and a novel modular feature selection strategy is implemented. Smaller sub regions from a predefined neighborhood within the phase congruency images of the training samples are merged to obtain a large set of features. These features are arranged in the order of increasing distance between the sub regions involved in merging. The assumption behind the proposed implementation of the region merging and arrangement strategy is that, local dependencies among the pixels are more important than global dependencies. The obtained feature sets are then arranged in the decreasing order of discriminating capability using a criterion function, which is the ratio of the between class variance to the within class variance of the sample set, in the PCA domain. The results indicate high improvement in the classification performance compared to baseline algorithms.

Keywords: Discriminant analysis, intra-class probability distribution, principal component analysis, phase congruency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1821
116 Innovative Waste Management Practices in Remote Areas

Authors: Dolores Hidalgo, Jesús M. Martín-Marroquín, Francisco Corona

Abstract:

Municipal waste consist of a variety of items that are everyday discarded by the population. They are usually collected by municipalities and include waste generated by households, commercial activities (local shops) and public buildings. The composition of municipal waste varies greatly from place to place, being mostly related to levels and patterns of consumption, rates of urbanization, lifestyles, and local or national waste management practices. Each year, a huge amount of resources is consumed in the EU, and according to that, also a huge amount of waste is produced. The environmental problems derived from the management and processing of these waste streams are well known, and include impacts on land, water and air. The situation in remote areas is even worst. Difficult access when climatic conditions are adverse, remoteness of centralized municipal treatment systems or dispersion of the population, are all factors that make remote areas a real municipal waste treatment challenge. Furthermore, the scope of the problem increases significantly because the total lack of awareness of the existing risks in this area together with the poor implementation of advanced culture on waste minimization and recycling responsibly. The aim of this work is to analyze the existing situation in remote areas in reference to the production of municipal waste and evaluate the efficiency of different management alternatives. Ideas for improving waste management in remote areas include, for example: the implementation of self-management systems for the organic fraction; establish door-to-door collection models; promote small-scale treatment facilities or adjust the rates of waste generation thereof.

Keywords: Door to door collection, islands, isolated areas, municipal waste, remote areas, rural communities.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2112
115 Ingenious Use of Hypo Sludge in M25 Concrete

Authors: Abhinandan Singh Gill

Abstract:

Paper mill sludge is one of the major economic and environmental problems for paper and board industry, million tonnes quantity of sludge is produced in the world. It is essential to dispose these wastes safely without affecting health of human being, environment, fertile land; sources of water bodies, economy as it adversely affect the strength, durability and other properties of building materials based on them. Moreover, in developing countries like India where there is low availability of non-renewable resources and large need of building material like cement therefore it is essential to develop eco-efficient utilization of paper sludge. Primarily in functional terms paper sludge comprises of cellulose fibers, calcium carbonate, china clay, low silica, residual chemical bonds with water. The material is sticky and full of moisture content which is hard to dry. The manufacturing of paper usually produce loads of solid waste. These paper fibers are recycled in paper mills to limited number of times till they become weak to produce high quality paper. Thereafter, these left out small and weak pieces called as low quality paper fibers are detached out to become paper sludge. The material is by-product of de-inking and re-pulping of paper. This hypo sludge includes all kinds of inks, dyes, coating etc inscribed on the paper. This paper presents an overview of the published work on the use of hypo sludge in M25 concrete formulations as a supplementary cementitious material exploring its properties such as compressive strength, splitting and parameters like modulus of elasticity, density, applications and most importantly investigation of low cost concrete by using hypo sludge are presented.

Keywords: Concrete, sludge waste, hypo sludge, supplementary cementitious material.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1226
114 LIDAR Obstacle Warning and Avoidance System for Unmanned Aircraft

Authors: Roberto Sabatini, Alessandro Gardi, Mark A. Richardson

Abstract:

The availability of powerful eye-safe laser sources and the recent advancements in electro-optical and mechanical beam-steering components have allowed laser-based Light Detection and Ranging (LIDAR) to become a promising technology for obstacle warning and avoidance in a variety of manned and unmanned aircraft applications. LIDAR outstanding angular resolution and accuracy characteristics are coupled to its good detection performance in a wide range of incidence angles and weather conditions, providing an ideal obstacle avoidance solution, which is especially attractive in low-level flying platforms such as helicopters and small-to-medium size Unmanned Aircraft (UA). The Laser Obstacle Avoidance Marconi (LOAM) system is one of such systems, which was jointly developed and tested by SELEX-ES and the Italian Air Force Research and Flight Test Centre. The system was originally conceived for military rotorcraft platforms and, in this paper, we briefly review the previous work and discuss in more details some of the key development activities required for integration of LOAM on UA platforms. The main hardware and software design features of this LOAM variant are presented, including a brief description of the system interfaces and sensor characteristics, together with the system performance models and data processing algorithms for obstacle detection, classification and avoidance. In particular, the paper focuses on the algorithm proposed for optimal avoidance trajectory generation in UA applications.

Keywords: LIDAR, Low-Level Flight, Nap-of-the-Earth Flight, Near Infra-Red, Obstacle Avoidance, Obstacle Detection, Obstacle Warning System, Sense and Avoid, Trajectory Optimisation, Unmanned Aircraft.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7015
113 Fertigation Use in Agriculture and Biosorption of Residual Nitrogen by Soil Microorganisms

Authors: A. Irina Mikajlo, B. Jakub Elbl, C. Antonín Kintl, D. Jindřich Kynický, E. Martin Brtnický, F. Jaroslav Záhora

Abstract:

Present work deals with the possible use of fertigation in agriculture and its impact on the availability of mineral nitrogen (Nmin) in topsoil and subsoil horizons. The aim of the present study is to demonstrate the effect of the organic matter presence in fertigation on microbial transformation and availability of mineral nitrogen forms. The main investigation reason is the potential use of pretreated waste water, as a source of organic carbon (Corg) and residual nutrients (Nmin) for fertigation. Laboratory experiment has been conducted to demonstrate the effect of the arable land fertilization method on the Nmin availability in different depths of the soil with the usage of model experimental containers filled with soil from topsoil and podsoil horizons that were taken from the precise area. Tufted hairgrass (Deschampsia caespitosa) has been chosen as a model plant. The water source protection zone Brezova nad Svitavou has been a research area where significant underground reservoirs of drinking water of the highest quality are located. From the second half of the last century local sources of drinking water show nitrogenous compounds increase that get here almost only from arable lands. Therefore, an attention of the following text focuses on the fate of mineral nitrogen in the complex plant-soil. Research results show that the fertigation application with Corg in a combination with mineral fertilizer can reduce the amount of Nmin leached from topsoil horizon of agricultural soils. In addition, some plants biomass production reduces may occur.

Keywords: Fertigation, fertilizers, mineral nitrogen, soil microorganisms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1933
112 Advanced Stochastic Models for Partially Developed Speckle

Authors: Jihad S. Daba (Jean-Pierre Dubois), Philip Jreije

Abstract:

Speckled images arise when coherent microwave, optical, and acoustic imaging techniques are used to image an object, surface or scene. Examples of coherent imaging systems include synthetic aperture radar, laser imaging systems, imaging sonar systems, and medical ultrasound systems. Speckle noise is a form of object or target induced noise that results when the surface of the object is Rayleigh rough compared to the wavelength of the illuminating radiation. Detection and estimation in images corrupted by speckle noise is complicated by the nature of the noise and is not as straightforward as detection and estimation in additive noise. In this work, we derive stochastic models for speckle noise, with an emphasis on speckle as it arises in medical ultrasound images. The motivation for this work is the problem of segmentation and tissue classification using ultrasound imaging. Modeling of speckle in this context involves partially developed speckle model where an underlying Poisson point process modulates a Gram-Charlier series of Laguerre weighted exponential functions, resulting in a doubly stochastic filtered Poisson point process. The statistical distribution of partially developed speckle is derived in a closed canonical form. It is observed that as the mean number of scatterers in a resolution cell is increased, the probability density function approaches an exponential distribution. This is consistent with fully developed speckle noise as demonstrated by the Central Limit theorem.

Keywords: Doubly stochastic filtered process, Poisson point process, segmentation, speckle, ultrasound

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1713
111 Influence of Compactive Efforts on Cement- Bagasse Ash Treatment of Expansive Black Cotton Soil

Authors: Moses, G, Osinubi, K. J.

Abstract:

A laboratory study on the influence of compactive effort on expansive black cotton specimens treated with up to 8% ordinary Portland cement (OPC) admixed with up to 8% bagasse ash (BA) by dry weight of soil and compacted using the energies of the standard Proctor (SP), West African Standard (WAS) or “intermediate” and modified Proctor (MP) were undertaken. The expansive black cotton soil was classified as A-7-6 (16) or CL using the American Association of Highway and Transportation Officials (AASHTO) and Unified Soil Classification System (USCS), respectively. The 7day unconfined compressive strength (UCS) values of the natural soil for SP, WAS and MP compactive efforts are 286, 401 and 515kN/m2 respectively, while peak values of 1019, 1328 and 1420kN/m2 recorded at 8% OPC/ 6% BA, 8% OPC/ 2% BA and 6% OPC/ 4% BA treatments, respectively were less than the UCS value of 1710kN/m2 conventionally used as criterion for adequate cement stabilization. The soaked California bearing ratio (CBR) values of the OPC/BA stabilized soil increased with higher energy level from 2, 4 and 10% for the natural soil to Peak values of 55, 18 and 8% were recorded at 8% OPC/4% BA 8% OPC/2% BA and 8% OPC/4% BA, treatments when SP, WAS and MP compactive effort were used, respectively. The durability of specimens was determined by immersion in water. Soils treatment at 8% OPC/ 4% BA blend gave a value of 50% resistance to loss in strength value which is acceptable because of the harsh test condition of 7 days soaking period specimens were subjected instead of the 4 days soaking period that specified a minimum resistance to loss in strength of 80%. Finally An optimal blend of is 8% OPC/ 4% BA is recommended for treatment of expansive black cotton soil for use as a sub-base material.

Keywords: Bagasse ash, California bearing ratio, Compaction, Durability, Ordinary Portland cement, Unconfined compressive strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3529
110 Productivity Effect of Urea Deep Placement Technology: An Empirical Analysis from Irrigation Rice Farmers in the Northern Region of Ghana

Authors: Shaibu Baanni Azumah, Ignatius Tindjina, Stella Obanyi, Tara N. Wood

Abstract:

This study examined the effect of Urea Deep Placement (UDP) technology on the output of irrigated rice farmers in the northern region of Ghana. Multi-stage sampling technique was used to select 142 rice farmers from the Golinga and Bontanga irrigation schemes, around Tamale. A treatment effect model was estimated at two stages; firstly, to determine the factors that influenced farmers’ decision to adopt the UDP technology and secondly, to determine the effect of the adoption of the UDP technology on the output of rice farmers. The significant variables that influenced rice farmers’ adoption of the UPD technology were sex of the farmer, land ownership, off-farm activity, extension service, farmer group participation and training. The results also revealed that farm size and the adoption of UDP technology significantly influenced the output of rice farmers in the northern region of Ghana. In addition to the potential of the technology to improve yields, it also presents an employment opportunity for women and youth, who are engaged in the deep placement of Urea Super Granules (USG), as well as in the transplantation of rice. It is recommended that the government of Ghana work closely with the IFDC to embed the UDP technology in the national agricultural programmes and policies. The study also recommends an effective collaboration between the government, through the Ministry of Food and Agriculture (MoFA) and the International Fertilizer Development Center (IFDC) to train agricultural extension agents on UDP technology in the rice producing areas of the country.

Keywords: Northern Ghana, output, irrigation rice farmers, treatment effect model, urea deep placement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1098
109 Assessing the Actual Status and Farmer’s Attitude towards Agroforestry in Chiniot, Pakistan

Authors: M. F. Nawaz, S. Gul, T. H. Farooq, M. T. Siddiqui, M. Asif, I. Ahmad, N. K. Niazi

Abstract:

In Pakistan, major demands of fuel wood and timber wood are fulfilled by agroforestry. However, the information regarding economic significance of agroforestry and its productivity in Pakistan is still insufficient and unreliable. Survey of field conditions to examine the agroforestry status at local level helps us to know the future trends and to formulate the policies for sustainable wood supply. The objectives of this research were to examine the actual status and potential of agroforestry and to point out the barriers that are faced by farmers in the adoption of agroforestry. Research was carried out in Chiniot district, Pakistan because it is the famous city for furniture industry that is largely dependent on farm trees. A detailed survey of district Chiniot was carried out from 150 randomly selected farmer respondents using multi-objective oriented and pre-tested questionnaire. It was found that linear tree planting method was more adopted (45%) as compared to linear + interplanting (42%) and/or compact planting (12.6%). Chi-square values at P-value <0.5 showed that age (11.35) and education (17.09) were two more important factors in the quick adoption of agroforestry as compared to land holdings (P-value of 0.7). The major reason of agroforestry adoption was to obtain income, fodder and fuelwood. The most dominant species in farmlands was shisham (Dalbergia sissoo) but since last five years, mostly farmers were growing Sufeida (Eucalyptus camaldulensis), kikar (Acacia nilotica) and popular (Populus deltoides) on their fields due to “Shisham die-back” problem. It was found that agro-forestry can be increased by providing good quality planting material to farmers and improving wood markets.

Keywords: Agroforestry, trees, services, agriculture, farmers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1687
108 Obesity and Bone Mineral Density in Patients with Large Joint Osteoarthritis

Authors: Vladyslav Povoroznyuk, Anna Musiienko, Nataliia Zaverukha, Roksolana Povoroznyuk

Abstract:

Along with the global aging of population, the number of people with somatic diseases is increasing, including such interrelated pathologies as obesity, osteoarthritis (OA) and osteoporosis (OP). The objective of the study is to examine the connection between body mass index (BMI), OA and bone mineral density (BMD) of lumbar spine, femoral neck and trabecular bone score (TBS) in postmenopausal women with OA. We have observed 359 postmenopausal women (50-89 years old) and divided them into four groups by age: 50-59 yrs, 60-69 yrs, 70-79 yrs and over 80 years old. In addition, according to the American College of Rheumatology (ACR) Clinical classification criteria for knee and hip OA, we divided them into 2 groups: group I – 117 females with symptomatic OA (including 89 patients with knee OA, 28 patients with hip OA) and group II –242 women with a normal functional activity of large joints. Analysis of data was performed taking into account their BMI, classified by World Health Organization (WHO). Diagnosis of obesity was established when BMI was above 30 kg/m2. In woman with obesity, a symptomatic OA was detected in 44 postmenopausal women (41.1%), a normal functional activity of large joints - in 63 women (58.9%). However, in women with normal BMI – 73 women, who account for 29.0% of cases, a symptomatic OA was detected. According to a chi-squared (χ2) test, a significantly higher level of BMI was detected in postmenopausal women with OA (χ2 = 5.05, p = 0.02). Women with a symptomatic OA had a significantly higher BMD of lumbar spine compared with women who had a normal functional activity of large joints. No significant differences of BMD of femoral necks or TBS were detected in either the group with OA or with a normal functional activity of large joints.

Keywords: Bone mineral density, BMD, body mass index, BMI, obesity, overweight, postmenopausal women, osteoarthritis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 634
107 Customer Churn Prediction Using Four Machine Learning Algorithms Integrating Feature Selection and Normalization in the Telecom Sector

Authors: Alanoud Moraya Aldalan, Abdulaziz Almaleh

Abstract:

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

Keywords: Machine Learning, Gradient Boosting, Logistic Regression, Churn, Random Forest, Decision Tree, ROC, AUC, F1-score.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 352
106 Development of an Ensemble Classification Model Based on Hybrid Filter-Wrapper Feature Selection for Email Phishing Detection

Authors: R. B. Ibrahim, M. S. Argungu, I. M. Mungadi

Abstract:

It is obvious in this present time, internet has become an indispensable part of human life since its inception. The Internet has provided diverse opportunities to make life so easy for human beings, through the adoption of various channels. Among these channels are email, internet banking, video conferencing, and the like. Email is one of the easiest means of communication hugely accepted among individuals and organizations globally. But over decades the security integrity of this platform has been challenged with malicious activities like Phishing. Email phishing is designed by phishers to fool the recipient into handing over sensitive personal information such as passwords, credit card numbers, account credentials, social security numbers, etc. This activity has caused a lot of financial damage to email users globally which has resulted in bankruptcy, sudden death of victims, and other health-related sicknesses. Although many methods have been proposed to detect email phishing, in this research, the results of multiple machine-learning methods for predicting email phishing have been compared with the use of filter-wrapper feature selection. It is worth noting that all three models performed substantially but one outperformed the other. The dataset used for these models is obtained from Kaggle online data repository, while three classifiers: decision tree, Naïve Bayes, and Logistic regression are ensemble (Bagging) respectively. Results from the study show that the Decision Tree (CART) bagging ensemble recorded the highest accuracy of 98.13% using PEF (Phishing Essential Features). This result further demonstrates the dependability of the proposed model.

Keywords: Ensemble, hybrid, filter-wrapper, phishing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 132
105 Determining the Spatial Vulnerability Levels and Typologies of Coastal Cities to Climate Change: Case of Turkey

Authors: Mediha B. Sılaydın Aydın, Emine D. Kahraman

Abstract:

One of the important impacts of climate change is the sea level rise. Turkey is a peninsula, so the coastal areas of the country are threatened by the problem of sea level rise. Therefore, the urbanized coastal areas are highly vulnerable to climate change. At the aim of enhancing spatial resilience of urbanized areas, this question arises: What should be the priority intervention subject in the urban planning process for a given city. To answer this question, by focusing on the problem of sea level rise, this study aims to determine spatial vulnerability typologies and levels of Turkey coastal cities based on morphological, physical and social characteristics. As a method, spatial vulnerability of coastal cities is determined by two steps as level and type. Firstly, physical structure, morphological structure and social structure were examined in determining spatial vulnerability levels. By determining these levels, most vulnerable areas were revealed as a priority in adaptation studies. Secondly, all parameters are also used to determine spatial typologies. Typologies are determined for coastal cities in order to use as a base for urban planning studies. Adaptation to climate change is crucial for developing countries like Turkey so, this methodology and created typologies could be a guide for urban planners as spatial directors and an example for other developing countries in the context of adaptation to climate change. The results demonstrate that the urban settlements located on the coasts of the Marmara Sea, the Aegean Sea and the Mediterranean respectively, are more vulnerable than the cities located on the Black Sea’s coasts to sea level rise.

Keywords: Climate change, coastal cities, sea level rise, urban land use planning, vulnerability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1496
104 Estimating Spatial Disaggregation of Urban Thermal Responsiveness on Summer Diurnal Range with a Numerical Modeling Approach in Bangkok, Thailand

Authors: Manat Srivanit, Hokao Kazunori

Abstract:

Facing the concern of the population to its environment and to climatic change, city planners are now considering the urban climate in their choices of planning. The urban climate, representing different urban morphologies across central Bangkok metropolitan area (BMA), are used to investigates the effects of both the composition and configuration of variables of urban morphology indicators on the summer diurnal range of urban climate, using correlation analyses and multiple linear regressions. Results show first indicate that approximately 92.6% of the variation in the average maximum daytime near-surface air temperature (Ta) was explained jointly by the two composition variables of urban morphology indicators including open space ratio (OSR) and floor area ratio (FAR). It has been possible to determine the membership of sample areas to the local climate zones (LCZs) using these urban morphology descriptors automatically computed with GIS and remote sensed data. Finally result found the temperature differences among zones of large separation, such as the city center could be respectively from 35.48±1.04ºC (Mean±S.D.) warmer than the outskirt of Bangkok on average for maximum daytime near surface temperature to 28.27±0.21ºC for extreme event and, can exceed as 8ºC. A spatially disaggregation of urban thermal responsiveness map would be helpful for several reasons. First, it would localize urban areas concerned by different climate behavior over summer daytime and be a good indicator of urban climate variability. Second, when overlaid with a land cover map, this map may contribute to identify possible urban management strategies to reduce heat wave effects in BMA.

Keywords: Urban climate, Urban morphology, Local climate zone, Urban planning, GIS and remote sensing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2427
103 Real Time Classification of Political Tendency of Twitter Spanish Users based on Sentiment Analysis

Authors: Marc Solé, Francesc Giné, Magda Valls, Nina Bijedic

Abstract:

What people say on social media has turned into a rich source of information to understand social behavior. Specifically, the growing use of Twitter social media for political communication has arisen high opportunities to know the opinion of large numbers of politically active individuals in real time and predict the global political tendencies of a specific country. It has led to an increasing body of research on this topic. The majority of these studies have been focused on polarized political contexts characterized by only two alternatives. Unlike them, this paper tackles the challenge of forecasting Spanish political trends, characterized by multiple political parties, by means of analyzing the Twitters Users political tendency. According to this, a new strategy, named Tweets Analysis Strategy (TAS), is proposed. This is based on analyzing the users tweets by means of discovering its sentiment (positive, negative or neutral) and classifying them according to the political party they support. From this individual political tendency, the global political prediction for each political party is calculated. In order to do this, two different strategies for analyzing the sentiment analysis are proposed: one is based on Positive and Negative words Matching (PNM) and the second one is based on a Neural Networks Strategy (NNS). The complete TAS strategy has been performed in a Big-Data environment. The experimental results presented in this paper reveal that NNS strategy performs much better than PNM strategy to analyze the tweet sentiment. In addition, this research analyzes the viability of the TAS strategy to obtain the global trend in a political context make up by multiple parties with an error lower than 23%.

Keywords: Political tendency, prediction, sentiment analysis, Twitter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 809
102 Author Profiling: Prediction of Learners’ Gender on a MOOC Platform Based on Learners’ Comments

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: Deep learning, data mining, gender predication, MOOCs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1321
101 Assessing the Suitability of South African Waste Foundry Sand as an Additive in Clay Masonry Products

Authors: Nthabiseng Portia Mahumapelo, Andre van Niekerk, Ndabenhle Sosibo, Nirdesh Singh

Abstract:

The foundry industry generates large quantities of solid waste in the form of waste foundry sand. The ever-increasing quantities of this type of industrial waste put pressure on land-filling space and its proper management has become a global concern. The South African foundry industry is not different when it comes to this solid waste generation. Utilizing the foundry waste sand in other applications has become an attractive avenue to deal with this waste stream. In the present paper, an evaluation was done on the suitability of foundry waste sand as an additive in clay masonry products. Purchased clay was added to the foundry waste sand sample in a 50/50 ratio. The mixture was named FC sample. The FC sample was mixed with water in a pan mixer until the mixture was consistent and suitable for extrusion. The FC sample was extruded and cut into briquettes. Water absorption, shrinkage and modulus of rupture tests were conducted on the resultant briquettes. Foundry waste sand and FC samples were respectively characterized mineralogically using X-Ray Diffraction, and the major and trace elements were determined using Inductively Coupled Plasma Optical Emission Spectroscopy. Adding purchased clay to the foundry waste sand positively influenced the workability of the test sample. Another positive characteristic was the low linear shrinkage, which indicated that products manufactured from the FC sample would not be susceptible to cracking. The water absorption values were acceptable and the unfired and fired strength values of the briquette’s samples were acceptable. In conclusion, tests showed that foundry waste sand can be used as an additive in masonry clay bricks, provided it is blended with good quality clay.

Keywords: Foundry waste sand, masonry clay bricks, modulus of rupture, shrinkage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 623
100 Semantic Enhanced Social Media Sentiments for Stock Market Prediction

Authors: K. Nirmala Devi, V. Murali Bhaskaran

Abstract:

Traditional document representation for classification follows Bag of Words (BoW) approach to represent the term weights. The conventional method uses the Vector Space Model (VSM) to exploit the statistical information of terms in the documents and they fail to address the semantic information as well as order of the terms present in the documents. Although, the phrase based approach follows the order of the terms present in the documents rather than semantics behind the word. Therefore, a semantic concept based approach is used in this paper for enhancing the semantics by incorporating the ontology information. In this paper a novel method is proposed to forecast the intraday stock market price directional movement based on the sentiments from Twitter and money control news articles. The stock market forecasting is a very difficult and highly complicated task because it is affected by many factors such as economic conditions, political events and investor’s sentiment etc. The stock market series are generally dynamic, nonparametric, noisy and chaotic by nature. The sentiment analysis along with wisdom of crowds can automatically compute the collective intelligence of future performance in many areas like stock market, box office sales and election outcomes. The proposed method utilizes collective sentiments for stock market to predict the stock price directional movements. The collective sentiments in the above social media have powerful prediction on the stock price directional movements as up/down by using Granger Causality test.

Keywords: Bag of Words, Collective Sentiments, Ontology, Semantic relations, Sentiments, Social media, Stock Prediction, Twitter, Vector Space Model and wisdom of crowds.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2769
99 Influence of Drought on Yield and Yield Components in White Bean

Authors: Gholamreza Habibi

Abstract:

In order to study seed yield and seed yield components in bean under reduced irrigation condition and assessment drought tolerance of genotypes, 15 lines of White beans were evaluated in two separate RCB design with 3 replications under stress and non stress conditions. Analysis of variance showed that there were significant differences among varieties in terms of traits under study, indicating the existence of genetic variation among varieties. The results indicate that drought stress reduced seed yield, number of seed per plant, biological yield and number of pod in White been. In non stress condition, yield was highly correlated with the biological yield, whereas in stress condition it was highly correlated with harvest index. Results of stepwise regression showed that, selection can we done based on, biological yield, harvest index, number of seed per pod, seed length, 100 seed weight. Result of path analysis showed that the highest direct effect, being positive, was related to biological yield in non stress and to harvest index in stress conditions. Factor analysis were accomplished in stress and nonstress condition a, there were 4 factors that explained more than 76 percent of total variations. We used several selection indices such as Stress Susceptibility Index ( SSI ), Geometric Mean Productivity ( GMP ), Mean Productivity ( MP ), Stress Tolerance Index ( STI ) and Tolerance Index ( TOL ) to study drought tolerance of genotypes, we found that the best Stress Index for selection tolerance genotypes were STI, GMP and MP were the greatest correlations between these Indices and seed yield under stress and non stress conditions. In classification of genotypes base on phenotypic characteristics, using cluster analysis ( UPGMA ), all allels classified in 5 separate groups in stress and non stress conditions.

Keywords: Cluster analysis, factor analysis, path analysis, selection index, White bean

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2111
98 Trend Analysis of Annual Total Precipitation Data in Konya

Authors: Naci Büyükkaracığan

Abstract:

Hydroclimatic observation values ​​are used in the planning of the project of water resources. Climate variables are the first of the values ​​used in planning projects. At the same time, the climate system is a complex and interactive system involving the atmosphere, land surfaces, snow and bubbles, the oceans and other water structures. The amount and distribution of precipitation, which is an important climate parameter, is a limiting environmental factor for dispersed living things. Trend analysis is applied to the detection of the presence of a pattern or trend in the data set. Many trends work in different parts of the world are usually made for the determination of climate change. The detection and attribution of past trends and variability in climatic variables is essential for explaining potential future alteration resulting from anthropogenic activities. Parametric and non-parametric tests are used for determining the trends in climatic variables. In this study, trend tests were applied to annual total precipitation data obtained in period of 1972 and 2012, in the Konya Basin. Non-parametric trend tests, (Sen’s T, Spearman’s Rho, Mann-Kendal, Sen’s T trend, Wald-Wolfowitz) and parametric test (mean square) were applied to annual total precipitations of 15 stations for trend analysis. The linear slopes (change per unit time) of trends are calculated by using a non-parametric estimator developed by Sen. The beginning of trends is determined by using the Mann-Kendall rank correlation test. In addition, homogeneities in precipitation trends are tested by using a method developed by Van Belle and Hughes. As a result of tests, negative linear slopes were found in annual total precipitations in Konya.

Keywords: Trend analysis, precipitation, hydroclimatology, Konya, Turkey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 979
97 Investigation and Identification of a Number of Precious and Semi-Precious Stones Related to Bam Historical Citadel Using Micro Raman Spectroscopy and Scanning Electron Microscopy

Authors: Nazli Darkhal

Abstract:

The use of gems and ornaments has been common in Iran since the beginning of history. The prosperity of the country, the wealth, and the interest of the people of this land in a luxurious and glorious life, combined with beauty, have always attracted the attention of Iranian people to gems and jewelry. Iranians are famous in the world for having a long history of collecting and recognizing precious stones. In this case, we can use the unique treasure of national jewelry. Raman spectroscopy method is one of the oscillating spectroscopy methods that is classified in the group of nondestructive study methods, and like other methods, in addition to several advantages, it also has disadvantages and problems. Micro Raman spectroscopy is one of the different types of Raman spectroscopy in which an optical microscope is combined with a Raman device to provide more capabilities and advantages than its original method. In this way, with the help of Raman spectroscopy and a light microscope, while observing more details from different parts of the historical sample, natural or artificial pigments can be identified in a small part of it. The EDX (Energy Dispersive X ray) electron microscope also functions as the basis for the interaction of the electron beam with the matter. The beams emitted from this interaction can be used to examine samples. In this article, in addition to introducing the micro-Raman spectroscopy method, studies have been conducted on the structure of three samples of existing stones in the historic citadel of Bam. Using this method of study on precious and semi-precious stones, in addition to requiring a short time, can provide us with complete information about the structure and theme of these samples. The results of experiments and gemology of the stones showed that the selected beads are agate and jasper, and they can be placed in the chalcedony group.

Keywords: Bam citadel, precious stones, semi-precious stones, Raman spectroscopy, scanning electron microscope.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 346
96 Experimental Investigation on Geosynthetic-Reinforced Soil Sections via California Bearing Ratio Test

Authors: S. Abdi Goudazri, R. Ziaie Moayed, A. Nazeri

Abstract:

Loose soils normally are of weak bearing capacity due to their structural nature. Being exposed to heavy traffic loads, they would fail in most cases. To tackle the aforementioned issue, geotechnical engineers have come up with different approaches; one of which is making use of geosynthetic-reinforced soil-aggregate systems. As these polymeric reinforcements have highlighted economic and environmentally-friendly features, they have become widespread in practice during the last decades. The present research investigates the efficiency of four different types of these reinforcements in increasing the bearing capacity of two-layered soil sections using a series California Bearing Ratio (CBR) test. The studied sections are comprised of a 10 cm-thick layer of no. 161 Firouzkooh sand (weak subgrade) and a 10 cm-thick layer of compacted aggregate materials (base course) classified as SP and GW according to the United Soil Classification System (USCS), respectively. The aggregate layer was compacted to the relative density (Dr) of 95% at the optimum water content (Wopt) of 6.5%. The applied reinforcements were including two kinds of geocomposites (type A and B), a geotextile, and a geogrid that were embedded at the interface of the lower and the upper layers of the soil-aggregate system. As the standard CBR mold was not appropriate in height for this study, the mold used for soaked CBR tests were utilized. To make a comparison between the results of stress-settlement behavior in the studied specimens, CBR values pertinent to the penetrations of 2.5 mm and 5 mm were considered. The obtained results demonstrated 21% and 24.5% increments in the amount of CBR value in the presence of geocomposite type A and geogrid, respectively. On the other hand, the effect of both geotextile and geocomposite type B on CBR values was generally insignificant in this research.

Keywords: Geosynthetics, geogrid, geotextile, CBR test, increasing bearing capacity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 639
95 Water and Soil Environment Pollution Reduction by Filter Strips

Authors: Roy R. Gu, Mahesh Sahu, Xianggui Zhao

Abstract:

Contour filter strips planted with perennial vegetation can be used to improve surface and ground water quality by reducing pollutant, such as NO3-N, and sediment outflow from cropland to a river or lake. Meanwhile, the filter strips of perennial grass with biofuel potentials also have economic benefits of producing ethanol. In this study, The Soil and Water Assessment Tool (SWAT) model was applied to the Walnut Creek Watershed to examine the effectiveness of contour strips in reducing NO3-N outflows from crop fields to the river or lake. Required input data include watershed topography, slope, soil type, land-use, management practices in the watershed and climate parameters (precipitation, maximum/minimum air temperature, solar radiation, wind speed and relative humidity). Numerical experiments were conducted to identify potential subbasins in the watershed that have high water quality impact, and to examine the effects of strip size and location on NO3-N reduction in the subbasins under various meteorological conditions (dry, average and wet). Variable sizes of contour strips (10%, 20%, 30% and 50%, respectively, of a subbasin area) planted with perennial switchgrass were selected for simulating the effects of strip size and location on stream water quality. Simulation results showed that a filter strip having 10%-50% of the subbasin area could lead to 55%- 90% NO3-N reduction in the subbasin during an average rainfall year. Strips occupying 10-20% of the subbasin area were found to be more efficient in reducing NO3-N when placed along the contour than that when placed along the river. The results of this study can assist in cost-benefit analysis and decision-making in best water resources management practices for environmental protection.

Keywords: modeling, SWAT, water quality, NO3-N, watershed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1710
94 Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data

Authors: Cheng Zeng, George Michailidis, Hitoshi Iyatomi, Leo L Duan

Abstract:

The conditional density characterizes the distribution of a response variable y given other predictor x, and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts a motivating starting point. In this work, we extend NF neural networks when external x is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional y and a latent z that comprises two components [zP , zN]. The zP component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for x, such as logistic/linear regression. The zN component is a high-dimensional independent Gaussian vector, which explains the variations in y not or less related to x. Unlike existing CDE methods, the proposed approach, coined Augmented Posterior CDE (AP-CDE), only requires a simple modification on the common normalizing flow framework, while significantly improving the interpretation of the latent component, since zP represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of x-related variations due to factors such as lighting condition and subject id, from the other random variations. Further, the experiments show that an unconditional NF neural network, based on an unsupervised model of z, such as Gaussian mixture, fails to generate interpretable results.

Keywords: Conditional density estimation, image generation, normalizing flow, supervised dimension reduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 89
93 A Sentence-to-Sentence Relation Network for Recognizing Textual Entailment

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: Deep neural models, natural language inference, recognizing textual entailment, sentence-to-sentence relation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1428