Search results for: ground truth for supervised learning

Authors: Oscar E. Cariceo, Claudia V. Casal

Abstract:

Machine learning offers a set of techniques to promote social work interventions and can lead to support decisions of practitioners in order to predict new behaviors based on data produced by the organizations, services agencies, users, clients or individuals. Machine learning techniques include a set of generalizable algorithms that are data-driven, which means that rules and solutions are derived by examining data, based on the patterns that are present within any data set. In other words, the goal of machine learning is teaching computers through 'examples', by training data to test specifics hypothesis and predict what would be a certain outcome, based on a current scenario and improve that experience. Machine learning can be classified into two general categories depending on the nature of the problem that this technique needs to tackle. First, supervised learning involves a dataset that is already known in terms of their output. Supervising learning problems are categorized, into regression problems, which involve a prediction from quantitative variables, using a continuous function; and classification problems, which seek predict results from discrete qualitative variables. For social work research, machine learning generates predictions as a key element to improving social interventions on complex social issues by providing better inference from data and establishing more precise estimated effects, for example in services that seek to improve their outcomes. This paper exposes the results of a classification algorithm to predict cyberbullying among adolescents. Data were retrieved from the National Polyvictimization Survey conducted by the government of Chile in 2017. A logistic regression model was created to predict if an adolescent would experience cyberbullying based on the interaction and behavior of gender, age, grade, type of school, and self-esteem sentiments. The model can predict with an accuracy of 59.8% if an adolescent will suffer cyberbullying. These results can help to promote programs to avoid cyberbullying at schools and improve evidence based practice.

Keywords: cyberbullying, evidence based practice, machine learning, social work research

Procedia PDF Downloads 168

Authors: Seyed Sadegh Naseralavi, Sadegh Balaghi, Ehsan Khojastehfar

Abstract:

Time history dynamic analysis of structures is considered as an exact method while being computationally intensive. Filtration of earthquake strong ground motions applying wavelet transform is an approach towards reduction of computational efforts, particularly in optimization of structures against seismic effects. Wavelet transforms are categorized into continuum and discrete transforms. Since earthquake strong ground motion is a discrete function, the discrete wavelet transform is applied in the present paper. Wavelet transform reduces analysis time by filtration of non-effective frequencies of strong ground motion. Filtration process may be repeated several times while the approximation induces more errors. In this paper, strong ground motion of earthquake has been filtered once applying each wavelet. Strong ground motion of Northridge earthquake is filtered applying various wavelets and dynamic analysis of sampled shear and moment frames is implemented. The error, regarding application of each wavelet, is computed based on comparison of dynamic response of sampled structures with exact responses. Exact responses are computed by dynamic analysis of structures applying non-filtered strong ground motion.

Keywords: wavelet transform, computational error, computational duration, strong ground motion data

Procedia PDF Downloads 378

Authors: Nowbuth Manta Devi, Rasmally Mohammed Hussein

Abstract:

Flood is one of the most devastating climate impacts that many countries are facing. Many different causes have been associated with the intensity of floods being recorded over time. Unplanned development, low carrying capacity of drains, clogged drains, construction in flood plains or increasing intensity of rainfall events. While a combination of these causes can certainly aggravate the flood conditions, in many cases, increasing drainage capacity has not reduced flood risk to the level that was expected. The present study analyzed the extent to which land use is contributing to aggravating impacts of flooding in a city. Satellite images have been analyzed over a period of 20 years at intervals of 5 years. Both unsupervised and supervised classification methods have been used with the image processing module of ArcGIS. The unsupervised classification was first compared to the basemap available in ArcGIS to get a first overview of the results. These results also aided in guiding data collection on-site for the supervised classification. The island of Mauritius is small, and there are large variations in land use over small areas, both within the built areas and in agricultural zones involving food crops. Larger plots of agricultural land under sugar cane plantations are relatively more easily identified. However, the growth stage and health of plants vary and this had to be verified during ground truthing. The results show that although there have been changes in land use as expected over a span of 20 years, this was not significant enough to cause a major increase in flood risk levels. A digital elevation model was analyzed for further understanding. It could not be noted that overtime, development tampered with natural flow paths in addition to increasing the impermeable areas. This situation results in backwater flows, hence increasing flood risks.

Keywords: climate change, flood, natural flow paths, small islands

Procedia PDF Downloads 7

Authors: Puthsodary Tat

Abstract:

Democracy has been categorially accepted and used as foreign and domestic policy agendas for the hope of peace, economic growth and prosperity for more than 25 years in Cambodia. However, the country is now in the grip of dictatorship, human rights violations, and prospective economic sanctions. This paper examines different perceptions and experiences of democratic assistance. In this study, the author employs discourse theory, idealism and realism as a theory-based methodology for debating and assessing the implications of democratization. Discourse theory is used to establish a platform for understanding discursive formations, body of knowledge and the games of truth of democracy. Idealist approaches give rational arguments for adopting key tenets that work well on the ground. In contrast, realism allows for some sweeping critiques of utopian ideal and offers particular views on why Western hegemonic missions do not work well. From idealist views, the research finds that Cambodian people still believe that democracy is a prima facie universality for peace, growth and prosperity. From realism, democratization is on the brink of death in three reasons. Firstly, there are tensions between Western and local discourses about democratic values and norms. Secondly, democratic tenets have been undermined by the ruling party-controlled courts, corruption, structural oppression and political patronage-based institutions. The third pitfall is partly associated with foreign aid dependency and geopolitical power struggles in the region. Finally, the study offers a precise mosaic of democratic principles that may be used to avoid a future geopolitical and economic crisis.

Keywords: corruption, democracy, democratic principles, discourse theory, discursive formations, foreign aid dependency, games of truth, geopolitical and economic crisis, geopolitical power struggle, hegemonic mission, idealism, realism, utopian ideal

Procedia PDF Downloads 200

Authors: Yogita Mishra, Arijit Roy, Dhruval Bhavsar

Abstract:

The study estimates the nitrogen concentration in selected vegetation community’s i.e. chir pine (pinusroxburghii) by using hyperspectral satellite data and also identified the appropriate spectral bands and nitrogen indices. The Short Wave InfraRed reflectance spectrum at 1790 nm and 1680 nm shows the maximum possible absorption by nitrogen in selected species. Among the nitrogen indices, log normalized nitrogen index performed positively and negatively too. The strong positive correlation is taken out from 1510 nm and 760 nm for the pinusroxburghii for leaf nitrogen concentration and leaf nitrogen mass while using NDNI. The regression value of R² developed by using linear equation achieved maximum at 0.7525 for the analysis of satellite image data and R² is maximum at 0.547 for ground truth data for pinusroxburghii respectively.

Keywords: hyperspectral, NDNI, nitrogen concentration, regression value

Procedia PDF Downloads 295

Authors: George D. Hatzigeorgiou, Nikos G. Pnevmatikos

Abstract:

This study examines the inelastic behavior of adjacent planar reinforced concrete (R.C.) frames subjected to strong ground motions. The investigation focuses on the effects of vertical ground motion on the seismic pounding. The examined structures are modeled and analyzed by RUAUMOKO dynamic nonlinear analysis program using reliable hysteretic models for both structural members and contact elements. It is found that the vertical ground motion mildly affects the seismic response of adjacent buildings subjected to structural pounding and, for this reason, it can be ignored from the displacement and interstorey drifts assessment. However, the structural damage is moderately affected by the vertical component of earthquakes.

Keywords: nonlinear seismic behavior, reinforced concrete structures, structural pounding, vertical ground motions

Procedia PDF Downloads 593

Authors: Keisuke Takahata, Hiroshi Suetsugu

Abstract:

Forest height is an important parameter for forest biomass estimation, and precise elevation data is essential for accurate forest height estimation. There are several globally or nationally available digital elevation models (DEMs) like SRTM and ASTER. However, its accuracy is reported to be low particularly in mountainous areas where there are closed canopy or steep slope. Recently, space-borne LiDAR, such as the Global Ecosystem Dynamics Investigation (GEDI), have started to provide sparse but accurate ground elevation and canopy height estimates. Several studies have reported the high degree of accuracy in their elevation products on their exact footprints, while it is not clear how this sparse information can be used for wider area. In this study, we developed a digital terrain model correction algorithm by spatially interpolating the difference between existing DEMs and GEDI elevation products by using Gaussian Process (GP) regression model. The result shows that our GP-based methodology can reduce the mean bias of the elevation data from 3.7m to 0.3m when we use airborne LiDAR-derived elevation information as ground truth. Our algorithm is also capable of quantifying the elevation data uncertainty, which is critical requirement for biomass inventory. Upcoming satellite-LiDAR missions, like MOLI (Multi-footprint Observation Lidar and Imager), are expected to contribute to the more accurate digital terrain model generation.

Keywords: digital terrain model, satellite LiDAR, gaussian processes, uncertainty quantification

Procedia PDF Downloads 182

Authors: Utkan Mutman, Cihan Dirlik

Abstract:

Kocaeli/TURKEY district in which wastewater held in a chosen field increased property has made piling in order to improve the ground under the aeration basin. In this study, the degree of improvement the ground after bored piling held in the field were investigated. In this context, improving the ground before and after the investigation was carried out and that the solution values obtained by the finite element method analysis using Plaxis program have been made. The diffuses in the aeration basin whose treatment is to aide is influenced with and without geogrid on the ground. On the ground been improved, for the purpose of control of manufactured bored piles, pile continuity, and pile load tests were made. Taking into consideration both the data in the field as well as dynamic loads in the aeration basic, an analysis was made on Plaxis program and compared the data obtained from the analysis result and data obtained in the field.

Keywords: geogrid, bored pile, soil improvement, plaxis

Procedia PDF Downloads 267

Authors: George C. Yao, Chao-Yu Tu, Wei-Chung Chen, Fung-Wen Kuo, Yu-Shan Chang

Abstract:

Building structures are subjected to both horizontal and vertical ground motions during earthquakes, but only the horizontal ground motion has been extensively studied and considered in design. Most of the prevailing seismic codes assume the vertical component to be 1/2 to 2/3 of the horizontal one. In order to understand the building responses from vertical ground motions, many earthquakes records are studied in this paper. System identification methods (ARX Model) are used to analyze the strong motions and to find out the characteristics of the vertical amplification factors and the natural frequencies of buildings. Analysis results show that the vertical amplification factors for high-rise buildings and low-rise building are 1.78 and 2.52 respectively, and the average vertical amplification factor of all buildings is about 2. The relationship between the vertical natural frequency and building height was regressed to a suggested formula in this study. The result points out an important message; the taller the building is, the greater chance of resonance of vertical vibration on the building will be.

Keywords: vertical ground motion, vertical amplification factor, natural frequency, component

Procedia PDF Downloads 314

Authors: Nur Azlina Mohamed Mokmin, Mona Masood

Abstract:

Guided by the theory of learning style, this study is based on the development of a multimedia learning application for students with mastery learning style. The learning material was developed by applying a graduated difficulty learning strategy. Algebraic fraction was chosen as the learning topic for this application. The effectiveness of this application in helping students learn is measured by giving a pre- and post-test. The result shows that students who learn using the learning material that matches their preferred learning style performs better than the students with a non-personalized learning material.

Keywords: algebraic fractions, graduated difficulty, mastery learning style, multimedia

Procedia PDF Downloads 513

Authors: Keyvanl Yahya

Abstract:

This paper aims to find a algorithmic structure that affords to predict and explain economic choice behaviour particularly under uncertainty (random policies) by manipulating the prevalent Actor-Critic learning method that complies with the requirements we have been entrusted ever since the field of neuroeconomics dawned on us. Whilst skimming some basics of neuroeconomics that might be relevant to our discussion, we will try to outline some of the important works which have so far been done to simulate choice making processes. Concerning neurological findings that suggest the existence of two specific functions that are executed through Basal Ganglia all the way down to sub-cortical areas, namely 'rewards' and 'beliefs', we will offer a modified version of actor/critic algorithm to shed a light on the relation between these functions and most importantly resolve what is referred to as a challenge for actor-critic algorithms, that is lack of inheritance or hierarchy which avoids the system being evolved in continuous time tasks whence the convergence might not emerge.

Keywords: neuroeconomics, choice behaviour, decision making, reinforcement learning, actor-critic algorithm

Procedia PDF Downloads 397

Authors: Esra Zengin, Sinan Akkar

Abstract:

Reliable and accurate prediction of nonlinear structural response requires specification of appropriate earthquake ground motions to be used in nonlinear time history analysis. The current research has mainly focused on selection and manipulation of real earthquake records that can be seen as the most critical step in the performance based seismic design and assessment of the structures. Utilizing amplitude scaled ground motions that matches with the target spectra is commonly used technique for the estimation of nonlinear structural response. Representative ground motion ensembles are selected to match target spectrum such as scenario-based spectrum derived from ground motion prediction equations, Uniform Hazard Spectrum (UHS), Conditional Mean Spectrum (CMS) or Conditional Spectrum (CS). Different sets of criteria exist among those developed methodologies to select and scale ground motions with the objective of obtaining robust estimation of the structural performance. This study presents ground motion selection and scaling procedure that considers the spectral variability at target demand with the level of ground motion dispersion. The proposed methodology provides a set of ground motions whose response spectra match target median and corresponding variance within a specified period interval. The efficient and simple algorithm is used to assemble the ground motion sets. The scaling stage is based on the minimization of the error between scaled median and the target spectra where the dispersion of the earthquake shaking is preserved along the period interval. The impact of the spectral variability on nonlinear response distribution is investigated at the level of inelastic single degree of freedom systems. In order to see the effect of different selection and scaling methodologies on fragility curve estimations, results are compared with those obtained by CMS-based scaling methodology. The variability in fragility curves due to the consideration of dispersion in ground motion selection process is also examined.

Keywords: ground motion selection, scaling, uncertainty, fragility curve

Procedia PDF Downloads 583

Authors: Ashwini Mahesh Jagatap

Abstract:

This paper presents the language learning strategy with respect to speaking skill with collaborative learning approach. Collaborative learning has been proven to be efficient learning methodology for all kinds of students. Students are working in groups of two or more, reciprocally searching for understanding, Solutions, or meanings, or creating a product. The presentation highlights the different stages which can be implemented during actual implementation of the methodology in the class room teaching learning process.

Keywords: collaborative classroom, collaborative learning approach, language skills, traditional teaching

Procedia PDF Downloads 573

Authors: SKhan Park, Seok Jin Lee, Jong Sun Kim, Jun Ho Lee, Bong Chan Kim

Abstract:

Because of the large economic losses caused by traffic congestion in metropolitan areas, various studies on the underground network design and construction techniques has been performed various studies in the developed countries. In Korea, it has performed a study to develop a versatile double-deck of deep tunnel model. This paper is an introduction to develop a ground reinforcement method to enable the safe tunnel construction in the weakened pillar section like as junction of tunnel. Applicable ground reinforcement method in the weakened section is proposed and it is expected to verify the method by the field application tests.

Keywords: double-deck tunnel, ground reinforcement, tunnel construction, weakened pillar section

Procedia PDF Downloads 409

Authors: Raghad A. Altowairgi

Abstract:

With the wide spread of social media platforms, young people tend to use them extensively as the first means of communication due to their ease and modernity. But these platforms often create a fertile ground for bullies to practice their aggressive behavior against their victims. Platform usage cannot be reduced, but intelligent mechanisms can be implemented to reduce the abuse. This is where machine learning comes in. Understanding and classifying text can be helpful in order to minimize the act of cyberbullying. Artificial intelligence techniques have expanded to formulate an applied tool to address the phenomenon of cyberbullying. In this research, machine learning models are built to classify text into two classes; cyberbullying and non-cyberbullying. After preprocessing the data in 4 stages; removing characters that do not provide meaningful information to the models, tokenization, removing stop words, and lowering text. BoW and TF-IDF are used as the main features for the five classifiers, which are; logistic regression, Naïve Bayes, Random Forest, XGboost, and Catboost classifiers. Each of them scores 92%, 90%, 92%, 91%, 86% respectively.

Keywords: cyberbullying, machine learning, Bag-of-Words, term frequency-inverse document frequency, natural language processing, Catboost

Procedia PDF Downloads 130

Authors: A. Threepanich, S. Youngme, P. Praipipat

Abstract:

Although ground egg shells had the ability to eliminate lead in water, their efficiency may decrease in a case of contaminating of other cations such as Na⁺, Ca²⁺ in the water. The development of ground egg shells may solve this problem in which metal oxides are a good choice for this case since they have the ability to remove any heavy metals including lead in the water. Therefore, this study attempts to use this advantage for improving ground egg shells for the specific lead removal efficiency in the water. X-ray fluorescence (XRF) technique was used for the chemical element contents analysis of ground egg shells (GES) and ground egg shells with metal oxide (GESM), and Transmission electron microscope (TEM) technique was used to examine the material sizes. The batch test studies were designed to investigate the factor effects on dose (5, 10, 15 grams), pH (5, 7, 9), and settling time (1, 3, 5 hours) for the lead removal efficiency in the water. The XRF analysis results showed GES contained calcium (Ca) 91.41% and Silicon (Si) 4.03% and GESM contained calcium (Ca) 91.41%, Silicon (Si) 4.03%, and Iron (Fe) 3.05%. TEM results confirmed the sizes of GES and GESM in the range of 1-20 nm. The batch test studies showed the best optimum conditions for the lead removal in the water of GES and GESM in dose, pH, and settling time were 10 grams, pH 9, 5 hours and 5 grams, pH 9, 3 hours, respectively. The competing ions (Na⁺ and Ca²⁺) study reported GESM had the higher % lead removal efficiency than GES at 90% and 60%, respectively. Therefore, this result can confirm that adding of metal oxide to ground egg shells helps to improve the lead removal efficiency in the water.

Keywords: nano material, ground egg shells, metal oxide, lead

Procedia PDF Downloads 135

Authors: L. Parisi

Abstract:

In this research work, neural networks were applied to classify two types of hip joint implants based on the relative hip joint implant side speed and three components of each ground reaction force. The condition of walking gait at normal velocity was used and carried out with each of the two hip joint implants assessed. Ground reaction forces’ kinetic temporal changes were considered in the first approach followed but discarded in the second one. Ground reaction force components were obtained from eighteen patients under such gait condition, half of which had a hip implant type I-II, whilst the other half had the hip implant, defined as type III by Orthoload®. After pre-processing raw gait kinetic data and selecting the time frames needed for the analysis, the ground reaction force components were used to train a MLP neural network, which learnt to distinguish the two hip joint implants in the abovementioned condition. Further to training, unknown hip implant side and ground reaction force components were presented to the neural networks, which assigned those features into the right class with a reasonably high accuracy for the hip implant type I-II and the type III. The results suggest that neural networks could be successfully applied in the performance assessment of hip joint implants.

Keywords: kinemic gait data, neural networks, hip joint implant, hip arthroplasty, rehabilitation engineering

Procedia PDF Downloads 354

Authors: Darshana Lal, Sonu Rana

Abstract:

Learning Resource Centers (LRC) are acquiring different kinds of documents like books, journals, thesis, dissertations, standard, databases etc. in print and e-form. This article deals with the different types of sources available in LRC. It also discusses the concept of the web, as a tool, as a multimedia system and the different interfaces available on the web. The reasons for establishing LRC are highlighted along with the assignments of LRC. Different features of LRC‘S like self-learning and group learning are described. It also implements a group of activities like reading, learning, educational etc. The use of LRC by students and faculties are given and concluded with the benefits.

Keywords: internet, search engine, resource centre, opac, self-learning, group learning

Procedia PDF Downloads 377

Authors: K. Urukundu, K. A. Aravind, Pradeep M. Nirgude, K. Sandhya

Abstract:

Transmission of bulk power over a long distance through HVDC transmission lines is gaining importance. This is because the transfer of bulk power through HVDC, from generating stations to load centers over long distances is more economical. However, these HVDC transmission lines create environmental and interference effects under the right of way of the line due to the ionization of the surrounding atmosphere in the vicinity of HVDC lines. The measurement of ground-level electric field and ionic current density is essential for the evaluation of human effects due to electromagnetic interference of the HVDC transmission line. In this paper, experimental laboratory results of the ground-level electric field under the miniature model of 800 kV monopole HVDC line of length 8 meters are presented in lateral configuration with different heights of the conductor from the ground plane. The results are compared with the simulated test results obtained through Finite Element based software.

Keywords: bundle, conductor, hexagonal, transmission line, ground-level electric field

Procedia PDF Downloads 221

Authors: Ola Hall, Ibrahim Wahab, Thorsteinn Rognvaldsson, Mattias Ohlsson

Abstract:

The subfield of poverty and welfare estimation that applies machine learning tools and methods on satellite imagery is a nascent but rapidly growing one. This is in part driven by the sustainable development goal, whose overarching principle is that no region is left behind. Among other things, this requires that welfare levels can be accurately and rapidly estimated at different spatial scales and resolutions. Conventional tools of household surveys and interviews do not suffice in this regard. While they are useful for gaining a longitudinal understanding of the welfare levels of populations, they do not offer adequate spatial coverage for the accuracy that is needed, nor are their implementation sufficiently swift to gain an accurate insight into people and places. It is this void that satellite imagery fills. Previously, this was near-impossible to implement due to the sheer volume of data that needed processing. Recent advances in machine learning, especially the deep learning subtype, such as deep neural networks, have made this a rapidly growing area of scholarship. Despite their unprecedented levels of performance, such models lack transparency and explainability and thus have seen limited downstream applications as humans generally are apprehensive of techniques that are not inherently interpretable and trustworthy. While several studies have demonstrated the superhuman performance of AI models, none has directly compared the performance of such models and human readers in the domain of poverty studies. In the present study, we directly compare the performance of human readers and a DL model using different resolutions of satellite imagery to estimate the welfare levels of demographic and health survey clusters in Tanzania, using the wealth quintile ratings from the same survey as the ground truth data. The cluster-level imagery covers all 608 cluster locations, of which 428 were classified as rural. The imagery for the human readers was sourced from the Google Maps Platform at an ultra-high resolution of 0.6m per pixel at zoom level 18, while that of the machine learning model was sourced from the comparatively lower resolution Sentinel-2 10m per pixel data for the same cluster locations. Rank correlation coefficients of between 0.31 and 0.32 achieved by the human readers were much lower when compared to those attained by the machine learning model – 0.69-0.79. This superhuman performance by the model is even more significant given that it was trained on the relatively lower 10-meter resolution satellite data while the human readers estimated welfare levels from the higher 0.6m spatial resolution data from which key markers of poverty and slums – roofing and road quality – are discernible. It is important to note, however, that the human readers did not receive any training before ratings, and had this been done, their performance might have improved. The stellar performance of the model also comes with the inevitable shortfall relating to limited transparency and explainability. The findings have significant implications for attaining the objective of the current frontier of deep learning models in this domain of scholarship – eXplainable Artificial Intelligence through a collaborative rather than a comparative framework.

Keywords: poverty prediction, satellite imagery, human readers, machine learning, Tanzania

Procedia PDF Downloads 105

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 170

Authors: Jihan Albayati, Kim Abdullah

Abstract:

This poster focuses on the significance of active learning strategies and their usage in the ESL classroom. Active learning is a big shift from traditional lecturing to active student engagement which can enhance and enrich student learning; therefore, engaging students is the core of this approach. Students learn more when they participate in the process of learning such as discussions, debates, analysis, synthesis, or any form of activity that requires student involvement. In order to achieve active learning, teachers can use different instructional strategies that are conducive to learning and the selection of these strategies depends on student learning outcomes. Active learning techniques must be carefully designed and integrated into the classroom to increase critical thinking and student participation. This poster provides a concise definition of active learning and its importance, instructional strategies, active learning techniques and their impact on student engagement. Also, it demonstrates the differences between passive and active learners.

Keywords: active learning, learner engagement, student-centered, teaching strategies

Procedia PDF Downloads 494

Authors: Shao-Di Feng, Von-Wun Soo

Abstract:

To generate symbolic music with specific emotions is a challenging task due to symbolic music datasets that have emotion labels are scarce and incomplete. This research aims to generate more refined emotions based on the training datasets that are only labeled with four quadrants in Russel’s 2D emotion model. We focus on the theory of Music Fadernet and map arousal and valence to the low-level attributes, and build a symbolic music generation model by combining transformer and GM-VAE. We adopt an in-attention mechanism for the model and improve it by allowing modulation by conditional information. And we show the music generation model could control the generation of music according to the emotions specified by users in terms of high-level linguistic expression and by manipulating their corresponding low-level musical attributes. Finally, we evaluate the model performance using a pre-trained emotion classifier against a pop piano midi dataset called EMOPIA, and by subjective listening evaluation, we demonstrate that the model could generate music with more refined emotions correctly.

Keywords: music generation, music emotion controlling, deep learning, semi-supervised learning

Procedia PDF Downloads 89

Authors: Warda Khan, Remo Lachmann, Adarsh S. Garakahally

Abstract:

The increasing complexity of software and its applicability in a wide range of industries, e.g., automotive, call for enhanced quality assurance techniques. Test automation is one option to tackle the prevailing challenges by supporting test engineers with fast, parallel, and repetitive test executions. A high degree of test automation allows for a shift from mundane (manual) testing tasks to a more analytical assessment of the software under test. However, a high initial investment of test resources is required to establish test automation, which is, in most cases, a limitation to the time constraints provided for quality assurance of complex software systems. Hence, a computer-aided creation of automated test cases is crucial to increase the benefit of test automation. This paper proposes the application of machine learning for the generation of automated test cases. It is based on supervised learning to analyze test specifications and existing test implementations. The analysis facilitates the identification of patterns between test steps and their implementation with test automation components. For the test case generation, this approach exploits historical data of test automation projects. The identified patterns are the foundation to predict the implementation of unknown test case specifications. Based on this support, a test engineer solely has to review and parameterize the test automation components instead of writing them manually, resulting in a significant time reduction for establishing test automation. Compared to other generation approaches, this ML-based solution can handle different writing styles, authors, application domains, and even languages. Furthermore, test automation tools require expert knowledge by means of programming skills, whereas this approach only requires historical data to generate test cases. The proposed solution is evaluated using various multi-label evaluation criteria (EC) and two small-sized real-world systems. The most prominent EC is ‘Subset Accuracy’. The promising results show an accuracy of at least 86% for test cases, where a 1:1 relationship (Multi-Class) between test step specification and test automation component exists. For complex multi-label problems, i.e., one test step can be implemented by several components, the prediction accuracy is still at 60%. It is better than the current state-of-the-art results. It is expected the prediction quality to increase for larger systems with respective historical data. Consequently, this technique facilitates the time reduction for establishing test automation and is thereby independent of the application domain and project. As a work in progress, the next steps are to investigate incremental and active learning as additions to increase the usability of this approach, e.g., in case labelled historical data is scarce.

Keywords: machine learning, multi-class, multi-label, supervised learning, test automation

Procedia PDF Downloads 132

Authors: Konstantinos Sofianos, Michail Stefanidakis

Abstract:

Nowadays, despite the great advances in technology, most educational frameworks lack a strong educational design basis. E-learning has become prevalent, but it faces various challenges such as student isolation and lack of quality in the learning process. An intelligent learning system provides a student with educational material according to their learning background and learning preferences. It records full information about the student, such as demographic information, learning styles, and academic performance. This information allows the system to be fully adapted to the student’s needs. In this paper, we propose a framework and an ontology for music education, consisting of the learner model and all elements of the learning process (learning objects, teaching methods, learning activities, assessment). This framework can be integrated into an intelligent learning system and used for music education in schools for the development of professional skills and beyond.

Keywords: intelligent learning systems, e-learning, music education, ontology, semantic web

Procedia PDF Downloads 139

Authors: Daoudi Abdelaziz, Mahmoudi Saïd, Chikh Mohamed Amine

Abstract:

This paper presents a fully automatic segmentation method of the left ventricle at End Systolic (ES) and End Diastolic (ED) in the ultrasound images by means of an implicit deformable model (level set) based on Geodesic Active Contour model. A pre-processing Gaussian smoothing stage is applied to the image, which is essential for a good segmentation. Before the segmentation phase, we locate automatically the area of the left ventricle by using a detection approach based on the Hough Transform method. Consequently, the result obtained is used to automate the initialization of the level set model. This initial curve (zero level set) deforms to search the Endocardial border in the image. On the other hand, quantitative evaluation was performed on a data set composed of 15 subjects with a comparison to ground truth (manual segmentation).

Keywords: level set method, transform Hough, Gaussian smoothing, left ventricle, ultrasound images.

Procedia PDF Downloads 465

Authors: Orsolya Kegyes-Brassai, Zsolt Szilvágyi, Ákos Wolf, Richard P. Ray

Abstract:

Local ground conditions have a substantial influence on the seismic response of structures. Their inclusion in seismic hazard assessment and structural design can be realized at different levels of sophistication. However, response results based on more advanced calculation methods e.g. nonlinear or equivalent linear site analysis tend to show significant discrepancies when compared to simpler approaches. This project's main objective was to compare results from several 1-D response programs to Eurocode 8 design spectra. Data from in-situ site investigations were used for assessing local ground conditions at several locations in Hungary. After discussion of the in-situ measurements and calculation methods used, a comprehensive evaluation of all major contributing factors for site response is given. While the Eurocode spectra should account for local ground conditions based on soil classification, there is a wide variation in peak ground acceleration determined from 1-D analyses versus Eurocode. Results show that current Eurocode 8 design spectra may not be conservative enough to account for local ground conditions typical for Hungary.

Keywords: 1-D site response analysis, multichannel analysis of surface waves (MASW), seismic CPT, seismic hazard assessment

Procedia PDF Downloads 246

Authors: Thomas Yeboah, Gifty Akouko Sarpong

Abstract:

Every learner has a specific learning style that helps him/her to study best. This means that any learning method (e-learning method or traditional face-to-face method) a learner chooses should address the learning style of the learner. Therefore, the main purpose of this research is to investigate whether learners’ grade achievement in e-learning environment is improved for learners with a particular learning style. In this research, purposive sampling technique was employed for selecting the sample size of three hundred and twenty (320) students studying a course UGRC 140 Science and Technology in our Lives at Christian Service University College. Data were analyzed by using, percentages, T -test, and one-way ANOVA. A thorough analysis was done on the data collected and the results revealed that learners with the Assimilator learning style and the converger learning style obtained higher grade achievement than both diverger learning style and accommodative learning style. Again, the results also revealed that accommodative learning style was not good enough for e-learning method.

Keywords: e-learning, learning style, grade achievement, accomodative, divergent, convergent, assimilative

Procedia PDF Downloads 432

Authors: Kuhelee Chandel, Julia Åhlén, Stefan Seipel

Abstract:

This study evaluates the accuracy of Microsoft HoloLens (Version 1) for small-scale industrial activities, comparing its measurements to ground truth data from a Kuka Robotics arm. Two experiments were conducted to assess its position-tracking capabilities, revealing that the HoloLens device is effective for measuring the position of dynamic objects with small dimensions. However, its precision is affected by the velocity of the trajectory and its position within the device's field of view. While the HoloLens device may be suitable for small-scale tasks, its limitations for more complex and demanding applications requiring high precision and accuracy must be considered. The findings can guide the use of HoloLens devices in industrial applications and contribute to the development of more effective and reliable position-tracking systems.

Keywords: augmented reality (AR), Microsoft HoloLens, object tracking, industrial processes, manufacturing processes

Procedia PDF Downloads 136

Authors: Bongsoo Jeon, Jayoung Kim, Jihong Lee

Abstract:

Methods for measuring or estimating of ground shape by a laser range finder and a vision sensor (exteroceptive sensors) have critical weakness in terms that these methods need prior database built to distinguish acquired data as unique surface condition for driving. Also, ground information by exteroceptive sensors does not reflect the deflection of ground surface caused by the movement of UGVs. Therefore, this paper proposes a method of recognizing exact and precise ground shape using Inertial Measurement Unit (IMU) as a proprioceptive sensor. In this paper, firstly this method recognizes attitude of a robot in real-time using IMU and compensates attitude data of a robot with angle errors through analysis of vehicle dynamics. This method is verified by outdoor driving experiments of a real mobile robot.

Keywords: inertial measurement unit, laser range finder, real-time recognition of the ground shape, proprioceptive sensor

Procedia PDF Downloads 286