Search results for: deep supervision

Authors: Mohammad Saleem, Neeta Kumar, Anita Sharma, Sazina Muzammil

Abstract:

It is observed that some of the dental students in our setting take less interest in medical subjects. Various teaching methods are focus of research interest currently and being tried to generate interest among students. An approach of interactive integrated tutorial was used to assess its feasibility in teaching medical subjects to dental undergraduates. The aim was to generate interest and promote active self-learning among students. The objectives were to (1) introduce the integrated interactive learning method through two departments, (2) get feedback from the students and faculty on feasibility and effectiveness of this method. Second-year students in Bachelor of Dental Surgery course were divided into two groups. Each group was asked to study physiology and pathology of a common and important condition (anemia and hypertension) in a week’s time. During the tutorial, students asked questions on physiology and pathology of that condition from each other in the presence of teachers of both physiology and pathology departments. The teachers acted only as facilitators. After the session, the feedback from students and faculty on this alternative learning method was obtained. Results: Majority of the students felt that this method of learning is enjoyable, helped to develop reasoning skills and ability to correlate and integrate the knowledge from two related fields. Majority of the students felt that this kind of learning led to better understanding of the topic and motivated them towards deep learning. Teachers observed that the study promoted interdepartmental cross-discipline collaboration and better students’ linkages. Conclusion: Interactive integrated tutorial is effective in motivating dental students for better and deep learning of medical subjects.

Keywords: active learning, education, integrated, interactive, self-learning, tutorials

Procedia PDF Downloads 314

Authors: Ying Zhao, Xingyan Bin

Abstract:

Semi-supervised clustering algorithms have been shown effective to improve clustering process with even limited supervision. However, semi-supervised hierarchical clustering remains challenging due to the complexities of expressing constraints for agglomerative clustering algorithms. This paper proposes novel semi-supervised agglomerative clustering algorithms to build a hierarchy based on a known reference tree. We prove that by enforcing distance constraints defined by a reference tree during the process of hierarchical clustering, the resultant tree is guaranteed to be consistent with the reference tree. We also propose a framework that allows the hierarchical tree generation be aware of levels of levels of the agglomerative tree under creation, so that metric weights can be learned and adopted at each level in a recursive fashion. The experimental evaluation shows that the additional cost of our contraint-based semi-supervised hierarchical clustering algorithm (HAC) is negligible, and our combined semi-supervised HAC algorithm outperforms the state-of-the-art algorithms on real-world datasets. The experiments also show that our proposed methods can improve clustering performance even with a small number of unevenly distributed labeled data.

Keywords: semi-supervised clustering, hierarchical agglomerative clustering, reference trees, distance constraints

Procedia PDF Downloads 547

Authors: Christina Killian, Katie Wall, Séamus Fanning, Guerrino Macori

Abstract:

Deep-level metagenomics offers a useful technical approach to explore the three dynamic One Health axes: healthcare, domiciliary and veterinary. There is currently limited understanding of the composition of complex biofilms, natural abundance of AMR genes and gene transfer occurrence in these ecological niches. By using a newly established small-scale complex biofilm model, COMBAT has the potential to provide new information on microbial diversity, antimicrobial resistance (AMR)-encoding gene abundance, and their transfer in complex biofilms of importance to these three One Health axes. Shotgun metagenomics has been used to sample the genomes of all microbes comprising the complex communities found in each biofilm source. A comparative analysis between untreated and biocide-treated biofilms is described. The basic steps include the purification of genomic DNA, followed by library preparation, sequencing, and finally, data analysis. The use of long-read sequencing facilitates the completion of metagenome-assembled genomes (MAG). Samples were sequenced using a PromethION platform, and following quality checks, binning methods, and bespoke bioinformatics pipelines, we describe the recovery of individual MAGs to identify mobile gene elements (MGE) and the corresponding AMR genotypes that map to these structures. High-throughput sequencing strategies have been deployed to characterize these communities. Accurately defining the profiles of these niches is an essential step towards elucidating the impact of the microbiota on each niche biofilm environment and their evolution.

Keywords: COMBAT, biofilm, metagenomics, high-throughput sequencing

Procedia PDF Downloads 56

Authors: Jixiang Lei, Alexander Fuchs, Franz Pernkopf, Katrin Ellermann

Abstract:

Within the Space@Sea project, funded by the Horizon 2020 program, an island consisting of multiple platforms was designed. The platforms are connected by ropes and fenders. The connection is critical with respect to the safety of the whole system. Therefore, fault detection systems are investigated, which could detect early warning signs for a possible failure in the connection elements. Previously, a model-based method called Extended Kalman Filter was developed to detect the reduction of rope stiffness. This method detected several types of faults reliably, but some types of faults were much more difficult to detect. Furthermore, the model-based method is sensitive to environmental noise. When the wave height is low, a long time is needed to detect a fault and the accuracy is not always satisfactory. In this sense, it is necessary to develop a more accurate and robust technique that can detect all rope faults under a wide range of operational conditions. Inspired by this work on the Space at Sea design, we introduce a fault diagnosis method based on deep neural networks. Our method cannot only detect rope degradation by using the acceleration data from each platform but also estimate the contributions of the specific acceleration sensors using methods from explainable AI. In order to adapt to different operational conditions, the domain adaptation technique DANN is applied. The proposed model can accurately estimate rope degradation under a wide range of environmental conditions and help users understand the relationship between the output and the contributions of each acceleration sensor.

Keywords: fault diagnosis, deep learning, domain adaptation, explainable AI

Procedia PDF Downloads 180

Authors: Mohammad Ghiasvand, Babak Khorsandi, Morteza Kolahdoozan

Abstract:

Under the influence of waves, oil in the sea is subject to vertical scattering in the water column. Scientists' knowledge of how oil is dispersed in the water column is one of the lowest levels of knowledge among other processes affecting oil in the marine environment, which highlights the need for research and study in this field. Therefore, this study investigates the distribution of oil in the water column in a turbulent environment with zero velocity characteristics. Lack of laboratory results to analyze the distribution of petroleum pollutants in deep water for information Phenomenon physics on the one hand and using them to calibrate numerical models on the other hand led to the development of laboratory models in research. According to the aim of the present study, which is to investigate the distribution of oil in homogeneous and isotropic turbulence caused by the oscillating Grid, after reaching the ideal conditions, the crude oil flow was poured onto the water surface and oil was distributed in deep water due to turbulence was investigated. In this study, all experimental processes have been implemented and used for the first time in Iran, and the study of oil diffusion in the water column was considered one of the key aspects of pollutant diffusion in the oscillating Grid environment. Finally, the required oscillation velocities were taken at depths of 10, 15, 20, and 25 cm from the water surface and used in the analysis of oil diffusion due to turbulence parameters. The results showed that with the characteristics of the present system in two static modes and network motion with a frequency of 0.8 Hz, the results of oil diffusion in the four mentioned depths at a frequency of 0.8 Hz compared to the static mode from top to bottom at 26.18, 57 31.5, 37.5 and 50% more. Also, after 2.5 minutes of the oil spill at a frequency of 0.8 Hz, oil distribution at the mentioned depths increased by 49, 61.5, 85, and 146.1%, respectively, compared to the base (static) state.

Keywords: homogeneous and isotropic turbulence, oil distribution, oscillating grid, oil spill

Procedia PDF Downloads 75

Authors: Elaine Llantos Elayda, John Mark S. Distor

Abstract:

This paper explores the lived experiences of clinical psychology interns' who have encountered suicidal clients during their internship. Employing qualitative phenomenological investigation, semi-structured interviews were conducted and analyzed using interpretative phenomenological analysis (IPA). The study employed purposive sampling to gather valuable data. The results highlighted that those encounters with suicidal clients triggered various reactions among interns, leading to self-doubt and a sense of unpreparedness in handling such cases. Many interns struggled with managing their own emotions, especially when clients' traumas mirrored their own experiences. The study emphasized the importance of a robust support system in helping interns cope with the challenges of their work. Supervision and professional support played critical roles in interns' development, providing guidance and enhancing their confidence in managing distressing situations. Despite the challenges, the interns found purpose in witnessing significant client progress and emphasized the importance of self-care and ongoing training to prepare future clinicians for similar experiences.

Keywords: polytechnic university of the Philippines, clinical psychology interns, suicidal clients, clinical psychology training

Procedia PDF Downloads 28

Authors: Marlin Mubarak

Abstract:

Background: Endometriosis is a complex disabling disease affecting young females in the reproductive period mainly. The aim of this project is to generate a diagnostic model to predict severity and stage of endometriosis prior to Laparoscopic surgery. This will help to improve the pre-operative diagnostic accuracy of stage 3 & 4 endometriosis and as a result, refer relevant women to a specialist centre for complex Laparoscopic surgery. The model is based on the British Society of Gynaecological Endoscopy (BSGE) pain questionnaire, clinical examination and ultrasound scan. Design: This is a prospective, observational, study, in which women completed the BSGE pain questionnaire, a BSGE requirement. Also, as part of the routine preoperative assessment patient had a routine ultrasound scan and when recto-vaginal and deep infiltrating endometriosis was suspected an MRI was performed. Setting: Luton & Dunstable University Hospital. Patients: Symptomatic women (n = 56) scheduled for laparoscopy due to pelvic pain. The age ranged between 17 – 52 years of age (mean 33.8 years, SD 8.7 years). Interventions: None outside the recognised and established endometriosis centre protocol set up by BSGE. Main Outcome Measure(s): Sensitivity and specificity of endometriosis diagnosis predicted by symptoms based on BSGE pain questionnaire, clinical examinations and imaging. Findings: The prevalence of diagnosed endometriosis was calculated to be 76.8% and the prevalence of advanced stage was 55.4%. Deep infiltrating endometriosis in various locations was diagnosed in 32/56 women (57.1%) and some had DIE involving several locations. Logistic regression analysis was performed on 36 clinical variables to create a simple clinical prediction model. After creating the scoring system using variables with P < 0.05, the model was applied to the whole dataset. The sensitivity was 83.87% and specificity 96%. The positive likelihood ratio was 20.97 and the negative likelihood ratio was 0.17, indicating that the model has a good predictive value and could be useful in predicting advanced stage endometriosis. Conclusions: This is a hypothesis-generating project with one operator, but future proposed research would provide validation of the model and establish its usefulness in the general setting. Predictive tools based on such model could help organise the appropriate investigation in clinical practice, reduce risks associated with surgery and improve outcome. It could be of value for future research to standardise the assessment of women presenting with pelvic pain. The model needs further testing in a general setting to assess if the initial results are reproducible.

Keywords: deep endometriosis, endometriosis, minimally invasive, MRI, ultrasound.

Procedia PDF Downloads 353

Authors: M. Seguini, D. Nedjar

Abstract:

An accuracy nonlinear analysis of a deep beam resting on elastic perfectly plastic soil is carried out in this study. In fact, a nonlinear finite element modeling for large deflection and moderate rotation of Euler-Bernoulli beam resting on linear and nonlinear random soil is investigated. The geometric nonlinear analysis of the beam is based on the theory of von Kàrmàn, where the Newton-Raphson incremental iteration method is implemented in a Matlab code to solve the nonlinear equation of the soil-beam interaction system. However, two analyses (deterministic and probabilistic) are proposed to verify the accuracy and the efficiency of the proposed model where the theory of the local average based on the Monte Carlo approach is used to analyze the effect of the spatial variability of the soil properties on the nonlinear beam response. The effect of six main parameters are investigated: the external load, the length of a beam, the coefficient of subgrade reaction of the soil, the Young’s modulus of the beam, the coefficient of variation and the correlation length of the soil’s coefficient of subgrade reaction. A comparison between the beam resting on linear and nonlinear soil models is presented for different beam’s length and external load. Numerical results have been obtained for the combination of the geometric nonlinearity of beam and material nonlinearity of random soil. This comparison highlighted the need of including the material nonlinearity and spatial variability of the soil in the geometric nonlinear analysis, when the beam undergoes large deflections.

Keywords: finite element method, geometric nonlinearity, material nonlinearity, soil-structure interaction, spatial variability

Procedia PDF Downloads 414

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 69

Authors: Seyed Armin Hashemi, Somayeh Rahimzadeh

Abstract:

The urban green space and environment should be considered to be among the most fundamental elements of the sustainability of natural and human life in the new citizenship. The present research is intended to evaluate the impact of irrigation using urban wastewater of Cadmium (Cd) in the soil and leaves of the pine trees of Rasht in the forest territories of Rasht. For this purpose, following the exact specification of the geographical and topographical attributes of under treatment area, 100 sample trees were implemented randomly –systematically in each compound studied. Approaching the end of growth season, five trees were selected randomly in each of the plats and samples of leaves were collected from the parts near to the end of the crown and the part which was adjacent to the light. At the foot of each of the trees selected, a soil profile was dug and samples of soil were extracted from three depths of 0-20, centimeters. The measurements done in the laboratory showed that the density of nutritious elements of the samples of leaf and soil in the compound irrigated with wastewater .The results of the present research suggest that urban can be used as a source of irrigation whereas muck can be employed in forestation and irrigation with precise and particular supervision and control.

Keywords: irrigation, forestation, urban waste water, pine, wastewater

Procedia PDF Downloads 454

Authors: H. M. Haytham, E. A. Azza, E.S. Mohamed, E. G. Nesreen

Abstract:

Thoracotomy is a great surgery that has serious pulmonary complications, so purpose of this study was to determine the response of diaphragmatic excursion to inspiratory muscle trainer post thoracotomy. Thirty patients of both sexes (16 men and 14 women) with age ranged from 20 to 40 years old had done thoracotomy participated in this study. The practical work was done in cardiothoracic department, Kasr-El-Aini hospital at faculty of medicine for individuals 3 days Post operatively. Patients were assigned into two groups: group A (study group) included 15 patients (8 men and 7 women) who received inspiratory muscle training by using inspiratory muscle trainer for 20 minutes and routine chest physiotherapy (deep breathing, cough and early ambulation) twice daily, 3 days per week for one month. Group B (control group) included 15 patients (8 men and 7 women) who received the routine chest physiotherapy only (deep breathing, cough and early ambulation) twice daily, 3 days per week for one month. Ultrasonography was used to evaluate the changes in diaphragmatic excursion before and after training program. Statistical analysis revealed a significant increase in diaphragmatic excursion in the study group (59.52%) more than control group (18.66%) after using inspiratory muscle trainer post operatively in patients post thoracotomy. It was concluded that the inspiratory muscle training device increases diaphragmatic excursion in patients post thoracotomy through improving inspiratory muscle strength and improving mechanics of breathing and using of inspiratory muscle trainer as a method of physical therapy rehabilitation to reduce post-operative pulmonary complications post thoracotomy.

Keywords: diaphragmatic excursion, inspiratory muscle trainer, ultrasonography, thoracotomy

Procedia PDF Downloads 319

Authors: Agnieszka Misztal

Abstract:

The popularity of the quality management system models continues to grow despite the transitional crisis in 2008. Their development is associated with the demands of the new requirements for entrepreneurs, such as risk analysis projects and more emphasis on supervision of outsourced processes. In parallel appropriate to focus attention on the selection of companies aspiring to quality management system. This is particularly important in the automotive supplier industry, where requirements transferred to the levels in the supply chain should be clear, transparent and fairly satisfied. The author has carried out series of researches aimed at finding the factors that allow for the effective implementation of the quality management system in automotive companies. The research was focused on four groups of companies: 1) manufacturing (parts and assemblies for the purpose of sale or for vehicle manufacturers), 2) service (repair and maintenance of the car), 3) services for the transport of goods or people, 4) commercial (auto parts and vehicles). Identified determinants were divided in two types of criteria into: internal and external, as well as: hard and soft. The article presents hard - technical factors that automotive company must meet in order to achieve the goal of the quality management system implementation.

Keywords: automotive industry, quality management system, automotive technology, automotive company

Procedia PDF Downloads 401

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network

Procedia PDF Downloads 67

Authors: T. Garlan, I. Gabelotaud, S. Lucas, E. Marchès

Abstract:

Production of a global sedimentological seabed map has been initiated in 1995 to provide the necessary tool for searches of aircraft and boats lost at sea, to give sedimentary information for nautical charts, and to provide input data for acoustic propagation modelling. This original approach had already been initiated one century ago when the French hydrographic service and the University of Nancy had produced maps of the distribution of marine sediments of the French coasts and then sediment maps of the continental shelves of Europe and North America. The current map of the sediment of oceans presented was initiated with a UNESCO's general map of the deep ocean floor. This map was adapted using a unique sediment classification to present all types of sediments: from beaches to the deep seabed and from glacial deposits to tropical sediments. In order to allow good visualization and to be adapted to the different applications, only the granularity of sediments is represented. The published seabed maps are studied, if they present an interest, the nature of the seabed is extracted from them, the sediment classification is transcribed and the resulted map is integrated in the world map. Data come also from interpretations of Multibeam Echo Sounder (MES) imagery of large hydrographic surveys of deep-ocean. These allow a very high-quality mapping of areas that until then were represented as homogeneous. The third and principal source of data comes from the integration of regional maps produced specifically for this project. These regional maps are carried out using all the bathymetric and sedimentary data of a region. This step makes it possible to produce a regional synthesis map, with the realization of generalizations in the case of over-precise data. 86 regional maps of the Atlantic Ocean, the Mediterranean Sea, and the Indian Ocean have been produced and integrated into the world sedimentary map. This work is permanent and permits a digital version every two years, with the integration of some new maps. This article describes the choices made in terms of sediment classification, the scale of source data and the zonation of the variability of the quality. This map is the final step in a system comprising the Shom Sedimentary Database, enriched by more than one million punctual and surface items of data, and four series of coastal seabed maps at 1:10,000, 1:50,000, 1:200,000 and 1:1,000,000. This step by step approach makes it possible to take into account the progresses in knowledge made in the field of seabed characterization during the last decades. Thus, the arrival of new classification systems for seafloor has improved the recent seabed maps, and the compilation of these new maps with those previously published allows a gradual enrichment of the world sedimentary map. But there is still a lot of work to enhance some regions, which are still based on data acquired more than half a century ago.

Keywords: marine sedimentology, seabed map, sediment classification, world ocean

Procedia PDF Downloads 232

Authors: Mohd Ibrahim K. Azeez, Mohammed Sani Ibrahim, Rosemawati Mustapa, Maisarah A. Malik, Chandrakala Varatharajoo, Wee Akina Sia Seng Lee

Abstract:

The leadership of the principals is known to be a key indicator in development and school performance. Therefore, this study was undertaken to assess the extent of the influence of instructional leadership in the field of supervision and curriculum focus on capacity development competence in the field of communication and teamwork. In addition, this study also examines self-efficacy mediator school leadership in the field of self-improvement and self-management of school principals. The study involved 383 guest teachers from 55 secondary schools for leadership in schools. Data was analyzed using SEM aid program AMOS 21. The final result shows partial mediation model was the best model fit to obtain the best goodness of fit of (X2/df = 4.663, CFI = 0.922, GFI = 0.778, TLI = 0914, NFI = 0.903, and RMSEA = 0.098) compared to the direct effect model of the findings (X2/df = 5.319, CFI = 0.908, GFI = 0755, TLI = 0.899, NFI = 0.889, and RMSEA = 0.106). While the findings of the fully mediator model with a self-efficacy refers principals as a mediator as follows (X2/df = 4.838, CFI = 0918, GFI = 0772, TLI = 0.910, NFI = 0.899, and RMSEA = 0.100). Therefore, it can be concluded that the findings clearly demonstrate self-efficacy variables principals become a mediator in the relationship between instructional leadership capacity and competency development.

Keywords: instructional leadership, capacity development, self-efficacy, competency

Procedia PDF Downloads 725

Authors: Judith Partouche-Sebban, Saeedeh Rezaee Vessal

Abstract:

Because of the rising number of new cases of cancer, especially among women, it is more than essential to better understand how women experience cancer in order to bring them adapted to support and care and enhance their well-being and patient experience. Cancer stands for a traumatic experience in which the diagnosis, its medical treatments, and the related side effects lead to deep physical and psychological changes that may arouse considerable stress and anxiety. In order to reduce these negative emotions, women tend to use various defense mechanisms, among which denial has been defined as the most frequent mechanism used by breast cancer patients. This study aims to better understand the consequences of the experience of cancer and their link with the adoption of a denial strategy. The empirical research was done among female cancer survivors in France. Since the topic of this study is relatively unexplored, a qualitative methodology and open-ended interviews were employed. In total, 25 semi-directive interviews were conducted with a female with different cancers, different stages of treatment, and different ages. A systematic inductive method was performed to analyze data. The content analysis enabled to highlight three different denial-related behaviors among women with cancer, which serve a self-protective function. First, women who expressed high levels of anxiety confessed they tended to completely deny the existence of their cancer immediately after the diagnosis of their illness. These women mainly exhibit many fears and a deep distrust toward the medical context and professionals. This coping mechanism is defined by the patient as being unconscious. Second, other women deliberately decided to deny partial information about their cancer, whether this information is related to the stages of the illness, the emotional consequences, or the behavioral consequences of the illness. These women use this strategy as a way to avoid the reality of the illness and its impact on the different aspects of their life as if cancer does not exist. Third, some women tend to reinterpret and give meaning to their cancer as a way to reduce its impact on their life. To this end, they may use magical thinking or positive reframing, or reinterpretation. Because denial may lead to delays in medical treatments, this topic deserves a deep investigation, especially in the context of oncology. As denial is defined as a specific defense mechanism, this study contributes to the existing literature in service marketing which focuses on emotions and emotional regulation in healthcare services which is a crucial issue. Moreover, this study has several managerial implications for healthcare professionals who interact with patients in order to implement better care and support for the patients.

Keywords: cancer, coping mechanisms, denial, healthcare services

Procedia PDF Downloads 85

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 90

Authors: Mmapula Petunia Tsweleng

Abstract:

This qualitative study presents an exploration and findings thereof the quality of primary caregiving relationships between adolescents orphaned through Acquired Immune Deficiency Syndrome (AIDS) and their grandmothers. This exploration was based on in-depth narratives of 6 stakeholders who provided community-based psychosocial support services to children and families affected by AIDS. The narratives show that grandmothers provided high-quality parental care and support to the orphans. Furthermore, stakeholders categorised grandmother caregiving as genuine. Findings also show that the orphans thrived emotionally, socially, and cognitively and performed well academically. However, it was also identified that grandmothers’ caregiving had elements of overprotectiveness as well as susceptibility to manipulation -which appeared to be a threat to the positive development of the orphans. Relevant interventions, with a special focus on strengthening grandmother caregiving, are needed. Special attention should be on equipping grandmothers with a better understanding of adolescent behaviours and abilities to provide appropriate monitoring and supervision.

Keywords: adolescent orphans, AIDS, caregiving relationships, grandmothers

Procedia PDF Downloads 69

Authors: Yuta Nakano, Kozo Kajiwara, Atsushi Hori, Takeshi Fujita

Abstract:

In association with the wave of electric vehicles (EV), low energy consumption systems have become more and more important. One of the key technologies to realize low energy consumption is a dynamic vision sensor (DVS), or we can call it an event sensor, neuromorphic vision sensor and so on. This sensor has several features, such as high temporal resolution, which can achieve 1 Mframe/s, and a high dynamic range (120 DB). However, the point that can contribute to low energy consumption the most is its sparsity; to be more specific, this sensor only captures the pixels that have intensity change. In other words, there is no signal in the area that does not have any intensity change. That is to say, this sensor is more energy efficient than conventional sensors such as RGB cameras because we can remove redundant data. On the other side of the advantages, it is difficult to handle the data because the data format is completely different from RGB image; for example, acquired signals are asynchronous and sparse, and each signal is composed of x-y coordinate, polarity (two values: +1 or -1) and time stamp, it does not include intensity such as RGB values. Therefore, as we cannot use existing algorithms straightforwardly, we have to design a new processing algorithm to cope with DVS data. In order to solve difficulties caused by data format differences, most of the prior arts make a frame data and feed it to deep learning such as Convolutional Neural Networks (CNN) for object detection and recognition purposes. However, even though we can feed the data, it is still difficult to achieve good performance due to a lack of intensity information. Although polarity is often used as intensity instead of RGB pixel value, it is apparent that polarity information is not rich enough. Considering this context, we proposed to use the timestamp information as a data representation that is fed to deep learning. Concretely, at first, we also make frame data divided by a certain time period, then give intensity value in response to the timestamp in each frame; for example, a high value is given on a recent signal. We expected that this data representation could capture the features, especially of moving objects, because timestamp represents the movement direction and speed. By using this proposal method, we made our own dataset by DVS fixed on a parked car to develop an application for a surveillance system that can detect persons around the car. We think DVS is one of the ideal sensors for surveillance purposes because this sensor can run for a long time with low energy consumption in a NOT dynamic situation. For comparison purposes, we reproduced state of the art method as a benchmark, which makes frames the same as us and feeds polarity information to CNN. Then, we measured the object detection performances of the benchmark and ours on the same dataset. As a result, our method achieved a maximum of 7 points greater than the benchmark in the F1 score.

Keywords: event camera, dynamic vision sensor, deep learning, data representation, object recognition, low energy consumption

Procedia PDF Downloads 97

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 PDF Downloads 148

Authors: William C. Alexander

Abstract:

The oscillating water column (OSC) wave energy converter (WEC) with deep water reactance (DWR) consists of a large hollow sphere filled with seawater at the base, referred to as the ‘stabilizer’, a hollow cylinder at the top of the device, with a said cylinder having a bottom open to the sea and a sealed top save for an orifice which leads to an air turbine, and a long, narrow rod connecting said stabilizer with said cylinder. A small amount of ballast at the bottom of the stabilizer and a small amount of floatation in the cylinder keeps the device upright in the sea. The floatation is set such that the mean water level is nominally halfway up the cylinder. The entire device is loosely moored to the seabed to keep it from drifting away. In the presence of ocean waves, seawater will move up and down within the cylinder, producing the ‘oscillating water column’. This gives rise to air pressure within the cylinder alternating between positive and negative gauge pressure, which in turn causes air to alternately leave and enter the cylinder through said top-cover situated orifice. An air turbine situated within or immediately adjacent to said orifice converts the oscillating airflow into electric power for transport to shore or elsewhere by electric power cable. Said oscillating air pressure produces large up and down forces on the cylinder. Said large forces are opposed through the rod to the large mass of water retained within the stabilizer, which is located deep enough to be mostly free of any wave influence and which provides the deepwater reactance. The cylinder and stabilizer form a spring-mass system which has a vertical (heave) resonant frequency. The diameter of the cylinder largely determines the power rating of the device, while the size (and water mass within) of the stabilizer determines said resonant frequency. Said frequency is chosen to be on the lower end of the wave frequency spectrum to maximize the average power output of the device over a large span of time (such as a year). The upper portion of the device (the cylinder) moves laterally (surge) with the waves. This motion is accommodated with minimal loading on the said rod by having the stabilizer shaped like a sphere, allowing the entire device to rotate about the center of the stabilizer without rotating the seawater within the stabilizer. A full-scale device of this type may have the following dimensions. The cylinder may be 16 meters in diameter and 30 meters high, the stabilizer 25 meters in diameter, and the rod 55 meters long. Simulations predict that this will produce 1,400 kW in waves of 3.5-meter height and 12 second period, with a relatively flat power curve between 5 and 16 second wave periods, as will be suitable for an open-ocean location. This is nominally 10 times higher power than similar-sized WEC spar buoys as reported in the literature, and the device is projected to have only 5% of the mass per unit power of other OWC converters.

Keywords: oscillating water column, wave energy converter, spar bouy, stabilizer

Procedia PDF Downloads 106

Authors: Shraddha Jain Sharma, Ratnalata Gupta

Abstract:

Predicting stock movements in the financial market is both difficult and rewarding. Analysts and academics are increasingly using advanced approaches such as machine learning techniques to anticipate stock price patterns, thanks to the expanding capacity of computing and the recent advent of graphics processing units and tensor processing units. Stock market prediction is a type of time series prediction that is incredibly difficult to do since stock prices are influenced by a variety of financial, socioeconomic, and political factors. Furthermore, even minor mistakes in stock market price forecasts can result in significant losses for companies that employ the findings of stock market price prediction for financial analysis and investment. Soft computing techniques are increasingly being employed for stock market prediction due to their better accuracy than traditional statistical methodologies. The proposed research looks at the need for soft computing techniques in stock market prediction, the numerous soft computing approaches that are important to the field, past work in the area with their prominent features, and the significant problems or issue domain that the area involves. For constructing a predictive model, the major focus is on neural networks and fuzzy logic. The stock market is extremely unpredictable, and it is unquestionably tough to correctly predict based on certain characteristics. This study provides a complete overview of the numerous strategies investigated for high accuracy prediction, with a focus on the most important characteristics.

Keywords: stock market prediction, artificial intelligence, artificial neural networks, fuzzy logic, accuracy, deep learning, machine learning, stock price, trading volume

Procedia PDF Downloads 90

Authors: Mesfin Angaw Tesfay

Abstract:

L-Xylulose is a potentially valuable rare sugar used as starting material for antiviral and anticancer drug development in pharmaceutical industries. L-Xylulose exist in a very low concentration in nature and have to be synthesized from cheap starting materials such as xylitol through biotechnological approaches. In this study, cofactor engineering and deep eutectic solvent were applied to improve the efficiency of L-xylulose production from xylitol. A water-forming NAD+ regeneration enzyme (NADH oxidase) from Streptococcus mutans ATCC 25175 was introduced into E. coli with xylitol-4-dehydrogenase (XDH) of Pantoea ananatis resulting in recombinant cells harboring the vector pETDuet-xdh-SmNox. Further, three deep eutectic solvents (DES) including, Choline chloride/glycerol (ChCl/G), Choline chloride/urea (ChCl/U), and Choline chloride/ethylene glycol (ChCl/EG) have been employed to facilitate the conversion efficiency of L-xylulose from xylitol. The co-expression system exhibited optimal activity at a temperature of 37 ℃ and pH 8.5, and the addition of Mg2+ enhanced the catalytic activity by 1.19-fold. Co-expression of NADH oxidase with XDH enzyme resulted in increased L-xylulose concentration and productivity from xylitol as well as the intracellular NAD+ concentration. Two of the DES used (ChCl/U and ChCl/EG) show positive effects on product yield and the ChCl/G has inhibiting effects. The optimum concentration of ChCl/U was 2.5%, which increased the L-xylulose yields compared to the control without DES. In a 1 L fermenter the final concentration and productivity of L-xylulose from 50 g/L of xylitol reached 48.45 g/L, and 2.42 g/L.h respectively, which was the highest report. Overall, this study is a suitable approach for large-scale production of L-xylulose from xylitol using the engineered E. coli cell.

Keywords: Xylitol-4-dehydrogenase, NADH oxidase, L-xylulose, Xylitol, Coexpression, DESs

Procedia PDF Downloads 23

Authors: Hayriye Anıl, Görkem Kar

Abstract:

In addition to being rich in renewable energy resources, Turkey is one of the countries that promise potential in geothermal energy production with its high installed power, cheapness, and sustainability. Increasing imbalance penalties become an economic burden for organizations since geothermal generation plants cannot maintain the balance of supply and demand due to the inadequacy of the production forecasts given in the day-ahead market. A better production forecast reduces the imbalance penalties of market participants and provides a better imbalance in the day ahead market. In this study, using machine learning, deep learning, and, time series methods, the total generation of the power plants belonging to Zorlu Natural Electricity Generation, which has a high installed capacity in terms of geothermal, was estimated for the first one and two weeks of March, then the imbalance penalties were calculated with these estimates and compared with the real values. These modeling operations were carried out on two datasets, the basic dataset and the dataset created by extracting new features from this dataset with the feature engineering method. According to the results, Support Vector Regression from traditional machine learning models outperformed other models and exhibited the best performance. In addition, the estimation results in the feature engineering dataset showed lower error rates than the basic dataset. It has been concluded that the estimated imbalance penalty calculated for the selected organization is lower than the actual imbalance penalty, optimum and profitable accounts.

Keywords: machine learning, deep learning, time series models, feature engineering, geothermal energy production forecasting

Procedia PDF Downloads 110

Authors: Tsega Asresa, Getahun Tigistu, Melaku Bayih

Abstract:

Computer vision is a subfield of artificial intelligence that allows computers and systems to extract meaning from digital images and video. It is used in a wide range of fields of study, including self-driving cars, video surveillance, medical diagnosis, manufacturing, law, agriculture, quality control, health care, facial recognition, and military applications. Aromatic medicinal plants are botanical raw materials used in cosmetics, medicines, health foods, essential oils, decoration, cleaning, and other natural health products for therapeutic and Aromatic culinary purposes. These plants and their products not only serve as a valuable source of income for farmers and entrepreneurs but also going to export for valuable foreign currency exchange. In Ethiopia, there is a lack of technologies for the classification and identification of Aromatic medicinal plant parts and disease type cured by aromatic medicinal plants. Farmers, industry personnel, academicians, and pharmacists find it difficult to identify plant parts and disease types cured by plants before ingredient extraction in the laboratory. Manual plant identification is a time-consuming, labor-intensive, and lengthy process. To alleviate these challenges, few studies have been conducted in the area to address these issues. One way to overcome these problems is to develop a deep learning model for efficient identification of Aromatic medicinal plant parts with their corresponding disease type. The objective of the proposed study is to identify the aromatic medicinal plant parts and their disease type classification using computer vision technology. Therefore, this research initiated a model for the classification of aromatic medicinal plant parts and their disease type by exploring computer vision technology. Morphological characteristics are still the most important tools for the identification of plants. Leaves are the most widely used parts of plants besides roots, flowers, fruits, and latex. For this study, the researcher used RGB leaf images with a size of 128x128 x3. In this study, the researchers trained five cutting-edge models: convolutional neural network, Inception V3, Residual Neural Network, Mobile Network, and Visual Geometry Group. Those models were chosen after a comprehensive review of the best-performing models. The 80/20 percentage split is used to evaluate the model, and classification metrics are used to compare models. The pre-trained Inception V3 model outperforms well, with training and validation accuracy of 99.8% and 98.7%, respectively.

Keywords: aromatic medicinal plant, computer vision, convolutional neural network, deep learning, plant classification, residual neural network

Procedia PDF Downloads 186

Authors: Qingsong Xiong, Cheng Yuan, Qingzhao Kong, Haibei Xiong

Abstract:

Deep-learning-driven approaches based on vibration responses have attracted larger attention in rapid structural condition assessment while obtaining sufficient measured training data with corresponding labels is relevantly costly and even inaccessible in practical engineering. This study proposes an integrated label propagation network for structural condition assessment, which is able to diffuse the labels from continuously-generating measurements by intact structure to those of missing labels of damage scenarios. The integrated network is embedded with damage-sensitive features extraction by deep autoencoder and pseudo-labels propagation by optimized fuzzy clustering, the architecture and mechanism which are elaborated. With a sophisticated network design and specified strategies for improving performance, the present network achieves to extends the superiority of self-supervised representation learning, unsupervised fuzzy clustering and supervised classification algorithms into an integration aiming at assessing damage conditions. Both numerical simulations and full-scale laboratory shaking table tests of a two-story building structure were conducted to validate its capability of detecting post-earthquake damage. The identifying accuracy of a present network was 0.95 in numerical validations and an average 0.86 in laboratory case studies, respectively. It should be noted that the whole training procedure of all involved models in the network stringently doesn’t rely upon any labeled data of damage scenarios but only several samples of intact structure, which indicates a significant superiority in model adaptability and feasible applicability in practice.

Keywords: autoencoder, condition assessment, fuzzy clustering, label propagation

Procedia PDF Downloads 97

Authors: Rafael do Amaral Teodoro, Leandro Augusto da Silva

Abstract:

Originated from graphite, graphene is a two-dimensional (2D) material that promises to revolutionize technology in many different areas, such as energy, telecommunications, civil construction, aviation, textile, and medicine. This is possible because its structure, formed by carbon bonds, provides desirable optical, thermal, and mechanical characteristics that are interesting to multiple areas of the market. Thus, several research and development centers are studying different manufacturing methods and material applications of graphene, which are often compromised by the scarcity of more agile and accurate methodologies to characterize the material – that is to determine its composition, shape, size, and the number of layers and crystals. To engage in this search, this study proposes a computational methodology that applies deep learning to identify graphene oxide crystals in order to characterize samples by crystal sizes. To achieve this, a fully convolutional neural network called U-net has been trained to segment SEM graphene oxide images. The segmentation generated by the U-net is fine-tuned with a standard deviation technique by classes, which allows crystals to be distinguished with different labels through an object delimitation algorithm. As a next step, the characteristics of the position, area, perimeter, and lateral measures of each detected crystal are extracted from the images. This information generates a database with the dimensions of the crystals that compose the samples. Finally, graphs are automatically created showing the frequency distributions by area size and perimeter of the crystals. This methodological process resulted in a high capacity of segmentation of graphene oxide crystals, presenting accuracy and F-score equal to 95% and 94%, respectively, over the test set. Such performance demonstrates a high generalization capacity of the method in crystal segmentation, since its performance considers significant changes in image extraction quality. The measurement of non-overlapping crystals presented an average error of 6% for the different measurement metrics, thus suggesting that the model provides a high-performance measurement for non-overlapping segmentations. For overlapping crystals, however, a limitation of the model was identified. To overcome this limitation, it is important to ensure that the samples to be analyzed are properly prepared. This will minimize crystal overlap in the SEM image acquisition and guarantee a lower error in the measurements without greater efforts for data handling. All in all, the method developed is a time optimizer with a high measurement value, considering that it is capable of measuring hundreds of graphene oxide crystals in seconds, saving weeks of manual work.

Keywords: characterization, graphene oxide, nanomaterials, U-net, deep learning

Procedia PDF Downloads 160

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 64

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 114

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 (RTE), sentence-to-sentence relation

Procedia PDF Downloads 348