Search results for: changeable training set

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

The quality of short term load forecasting can improve the efficiency of planning and operation of electric utilities. Artificial Neural Networks (ANNs) are employed for nonlinear short term load forecasting owing to their powerful nonlinear mapping capabilities. At present, there is no systematic methodology for optimal design and training of an artificial neural network. One has often to resort to the trial and error approach. This paper describes the process of developing three layer feed-forward large neural networks for short-term load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. Particle Swarm Optimization (PSO) is used to develop the optimum large neural network structure and connecting weights for one-day ahead electric load forecasting problem. PSO is a novel random optimization method based on swarm intelligence, which has more powerful ability of global optimization. Employing PSO algorithms on the design and training of ANNs allows the ANN architecture and parameters to be easily optimized. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. The experimental results show that the proposed method optimized by PSO can quicken the learning speed of the network and improve the forecasting precision compared with the conventional Back Propagation (BP) method. Moreover, it is not only simple to calculate, but also practical and effective. Also, it provides a greater degree of accuracy in many cases and gives lower percent errors all the time for STLF problem compared to BP method. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Large Neural Network, Short-Term Load Forecasting, Particle Swarm Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2176

Authors: Olivier Mills, Bernard McDonell, Laura A. S. MacDonald

Abstract:

The increasing availability and quality of internet access throughout the developing world provides an opportunity to utilize online spaces to disseminate water, sanitation and hygiene (WASH) knowledge to practitioners. Since 2001, CAWST has provided in-person education, training and consulting services to thousands of WASH practitioners all over the world, supporting them to start, troubleshoot, improve and expand their WASH projects. As CAWST continues to grow, the organization faces challenges in meeting demand from clients and in providing consistent, timely technical support. In 2012, CAWST began utilizing online spaces to expand its reach by developing a series of resources websites and webinars. CAWST has developed a WASH Education and Training resources website, a Biosand Filter (BSF) Knowledge Base, a Household Water Treatment and Safe Storage Knowledge Base, a mobile app for offline users, a live chat support tool, a WASH e-library, and a series of webinar-style online training sessions to complement its in-person capacity development services. In order to determine the preliminary outcomes of providing these online services, CAWST has monitored and analyzed registration to the online spaces, downloads of the educational materials, and webinar attendance; as well as conducted user surveys. The purpose of this analysis was to find out who was using the online spaces, where users came from, and how the resources were being used. CAWST’s WASH Resources website has served over 5,800 registered users from 3,000 organizations in 183 countries. Additionally, the BSF Knowledge Base has served over 1000 registered users from 68 countries, and over 540 people from 73 countries have attended CAWST’s online training sessions. This indicates that the online spaces are effectively reaching a large numbers of users, from a range of countries. A 2016 survey of the Biosand Filter Knowledge Base showed that approximately 61% of users are practitioners, and 39% are either researchers or students. Of the respondents, 46% reported using the BSF Knowledge Base to initiate a BSF project and 43% reported using the information to train BSF technicians. Finally, 61% indicated they would like even greater support from CAWST’s Technical Advisors going forward. The analysis has provided an encouraging indication that CAWST’s online spaces are contributing to its objective of engaging and supporting WASH practitioners to start, improve and expand their initiatives. CAWST has learned several lessons during the development of these online spaces, in particular related to the resources needed to create and maintain the spaces, and respond to the demand created. CAWST plans to continue expanding its online spaces, improving user experience of the sites, and involving new contributors and content types. Through the use of online spaces, CAWST has been able to increase its global reach and impact without significantly increasing its human resources by connecting WASH practitioners with the information they most need, in a practical and accessible manner. This paper presents on CAWST’s use of online spaces through the CAWST-developed platforms discussed above and the analysis of the use of these platforms.

Keywords: Education and training, knowledge sharing, online resources, water and sanitation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1635

Authors: Lorena Alemán de la Garza, Marcela Georgina Gómez-Zermeño

Abstract:

This paper presents the SolarSPELL case study that aims to generate information on the use of indicators that help evaluate the pedagogical quality of a digital library resources. SolarSPELL is a solar-powered digital library with WiFi connectivity. It offers a variety of open educational resources selected for their potential for the digital transformation of educational practices and the achievement of the 2030 Agenda for Sustainable Development, adopted by all United Nations Member States. The case study employed a quantitative methodology and the research instrument was applied to 55 teachers, directors and librarians. The results indicate that it is possible to strengthen the pedagogical quality of open educational resources, through actions focused on improving temporal and technological parameters. They also reveal that users believe that SolarSPELL improves the teaching-learning processes and motivates the teacher to improve his or her development. This study provides valuable information on a tool that supports teaching-learning processes and facilitates connectivity with renewable energies that improves the teacher training in active methodologies for ecosystem learning.

Keywords: Educational innovation, digital library, pedagogical quality, solar energy, teacher training, sustainable development.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 868

Authors: Mpofu Vongai, Vhurumuku Elaosi

Abstract:

Many African countries, such as Zimbabwe and South Africa, have curricula reform agendas that include incorporation of Indigenous Knowledge and Nature of Science (NOS) into school Science, Technology, Engineering and Mathematics (STEM) education. It is argued that at high school level, STEM learning, which incorporates understandings of indigenization science and NOS, has the potential to provide a strong foundation for a culturally embedded scientific knowledge essential for their advancement in Science and Technology. Globally, investment in STEM education is recognized as essential for economic development. For this reason, developing countries such as Zimbabwe and South Africa have been investing into training specialized teachers in natural sciences and technology. However, in many cases this training has been detached from the cultural realities and contexts of indigenous learners. For this reason, the STEM curricula reform has provided implementation challenges to teachers. An issue of major concern is the teachers’ pedagogical content knowledge (PCK), which is essential for effective implementation of these STEM curricula. Well-developed Teacher PCK include an understanding of both the nature of indigenous knowledge (NOIK) and of NOS. This paper reports the results of a study that investigated the development of 3 South African and 3 Zimbabwean in-service teachers’ abilities to integrate NOS and NOIK as part of their PCK. A participatory action research design was utilized. The main focus was on capturing, determining and developing teachers STEM knowledge for integrating NOIK and NOS in science classrooms. Their use of indigenous games was used to determine how their subject knowledge for STEM and pedagogical abilities could be developed. Qualitative data were gathered through the use dialogues between the researchers and the in-service teachers, as well as interviewing the participating teachers. Analysis of the data provides a methodological window through which in-service teachers’ PCK can be STEMITIZED and their abilities to integrate NOS and NOIK developed. Implications are raised for developing teachers’ STEM education in universities and teacher training colleges.

Keywords: Indigenous knowledge, nature of science, pedagogical content knowledge, STEM education.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1186

Authors: Walaa Khalaf, Calogero Pace, Manlio Gaudioso

Abstract:

We present an Electronic Nose (ENose), which is aimed at identifying the presence of one out of two gases, possibly detecting the presence of a mixture of the two. Estimation of the concentrations of the components is also performed for a volatile organic compound (VOC) constituted by methanol and acetone, for the ranges 40-400 and 22-220 ppm (parts-per-million), respectively. Our system contains 8 sensors, 5 of them being gas sensors (of the class TGS from FIGARO USA, INC., whose sensing element is a tin dioxide (SnO2) semiconductor), the remaining being a temperature sensor (LM35 from National Semiconductor Corporation), a humidity sensor (HIH–3610 from Honeywell), and a pressure sensor (XFAM from Fujikura Ltd.). Our integrated hardware–software system uses some machine learning principles and least square regression principle to identify at first a new gas sample, or a mixture, and then to estimate the concentrations. In particular we adopt a training model using the Support Vector Machine (SVM) approach with linear kernel to teach the system how discriminate among different gases. Then we apply another training model using the least square regression, to predict the concentrations. The experimental results demonstrate that the proposed multiclassification and regression scheme is effective in the identification of the tested VOCs of methanol and acetone with 96.61% correctness. The concentration prediction is obtained with 0.979 and 0.964 correlation coefficient for the predicted versus real concentrations of methanol and acetone, respectively.

Keywords: Electronic nose, Least square regression, Mixture ofgases, Support Vector Machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2495

Authors: Dasom Kim, Chen Liu, Myungsu Lim, Soo-Hyeon Jeon, Byeoung Kug Jeon, Kee-Young Kwahk, Namgyu Kim

Abstract:

Recently, numerous documents including large volumes of unstructured data and text have been created because of the rapid increase in the use of social media and the Internet. Usually, these documents are categorized for the convenience of users. Because the accuracy of manual categorization is not guaranteed, and such categorization requires a large amount of time and incurs huge costs. Many studies on automatic categorization have been conducted to help mitigate the limitations of manual categorization. Unfortunately, most of these methods cannot be applied to categorize complex documents with multiple topics because they work on the assumption that individual documents can be categorized into single categories only. Therefore, to overcome this limitation, some studies have attempted to categorize each document into multiple categories. However, the learning process employed in these studies involves training using a multi-categorized document set. These methods therefore cannot be applied to the multi-categorization of most documents unless multi-categorized training sets using traditional multi-categorization algorithms are provided. To overcome this limitation, in this study, we review our novel methodology for extending the category of a single-categorized document to multiple categorizes, and then introduce a survey-based verification scenario for estimating the accuracy of our automatic categorization methodology.

Keywords: Big Data Analysis, Document Classification, Text Mining, Topic Analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1706

Authors: Stamatios A. Theocharis, George A. Tsihrintzis

Abstract:

One of the most important factors for the success of e-government is training and preparing the workforce of the public sector. As changes and innovation in the public sector progress at a very slow pace and more slowly than in the private sector, issues related to human resources require special care. This is because the workforce will eventually seize the opportunities of the technological solutions used in e-Government. Thus, the central administration should provide employees with continuous and focused training not only on new technologies but also on a wide range of subjects and also improve interdepartmental interaction.

To achieve all this, new methods and training tools need to be implemented in addition to assessment of the employees. In this spirit, we propose the development of an educational platform with user personalization features. We propose the development of this platform using Moodle as the basic tool. Incorporating a personalization mechanism is very important since different employees have different backgrounds, education levels, computer skills, or different capability to develop further. Key features of the proposed platform include, besides typical e-learning tools, communities organized in order to exchange experiences and knowledge, groups of users based on certain criteria, automatic evaluation of users and potential self-education and self-assessment. In its fully developed form, this platform can be part of a more comprehensive knowledge management system for the public sector.

Keywords: e-Government, civil employees education, education technologies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1883

Authors: N. Ipiña, R. Basagoiti, O. Jimenez, I. Arriaran

Abstract:

Higher education students are increasingly enrolling in online courses, they are, at the same time, generating data about their learning process in the courses. Data collected in those technology enhanced learning spaces can be used to identify patterns and therefore, offer recommendations/personalized courses to future online students. Moreover, recommendations are considered key aspects for personalization in online learning. Taking into account the above mentioned context, the aim of this paper is to explore the perception of higher education students and teachers towards receiving recommendations in online courses. The study was carried out with 322 students and 10 teachers from two different faculties (Engineering and Education) from Mondragon University. Online questionnaires and face to face interviews were used to gather data from the participants. Results from the questionnaires show that most of the students would like to receive recommendations in their online courses as a guide in their learning process. Findings from the interviews also show that teachers see recommendations useful for their students’ learning process. However, teachers believe that specific pedagogical training is required. Conclusions can also be drawn as regards the importance of personalization in technology enhanced learning. These findings have significant implications for those who train online teachers due to the fact that pedagogy should be the driven force and further training on the topic could be required. Therefore, further research is needed to better understand the impact of recommendations on online students’ learning process and draw some conclusion on pedagogical concerns.

Keywords: Higher education, perceptions, recommendations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1187

Authors: Atef M. Ghaleb, Mohamed Z. Ramadan, Khalid Saad Aljaloud

Abstract:

The aim of this study is to assesses the lifting capabilities of persons experiencing hypoxia. It also examines the behavior of the physiological response induced through the lifting process related to changing in the hypoxia and lifting frequency variables. For this purpose, the study performed two consecutive tests by using; (1) training and acclimatization; and (2) an actual collection of data. A total of 10 male students from King Saud University, Kingdom of Saudi Arabia, were recruited in the study. A two-way repeated measures design, with two independent variables (ambient oxygen (15%, 18% and 21%)) and lifting frequency (1 lift/min and 4 lifts/min) and four dependent variables i.e., maximum acceptable weight of lift (MAWL), Electromyography (EMG) of four muscle groups (anterior deltoid, trapezius, biceps brachii, and erector spinae), rating of perceived exertion (RPE), and rating of oxygen feeling (ROF) were used in this study. The results show that lifting frequency has significantly impacted the MAWL and muscles’ activities. The oxygen content had a significant effect on the RPE and ROE. The study has revealed that acclimatization and training sessions significantly reduce the effect of the hypoxia on the human physiological parameters during the manual materials handling tasks.

Keywords: Lifting capabilities, muscle activities (sEMG), oxygen content, perceived exertion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 587

Authors: Luay A. Fraiwan, Natheer Y. Khaswaneh, Khaldon Y. Lweesy

Abstract:

Sleep stage scoring is the process of classifying the stage of the sleep in which the subject is in. Sleep is classified into two states based on the constellation of physiological parameters. The two states are the non-rapid eye movement (NREM) and the rapid eye movement (REM). The NREM sleep is also classified into four stages (1-4). These states and the state wakefulness are distinguished from each other based on the brain activity. In this work, a classification method for automated sleep stage scoring based on a single EEG recording using wavelet packet decomposition was implemented. Thirty two ploysomnographic recording from the MIT-BIH database were used for training and validation of the proposed method. A single EEG recording was extracted and smoothed using Savitzky-Golay filter. Wavelet packets decomposition up to the fourth level based on 20th order Daubechies filter was used to extract features from the EEG signal. A features vector of 54 features was formed. It was reduced to a size of 25 using the gain ratio method and fed into a classifier of regression trees. The regression trees were trained using 67% of the records available. The records for training were selected based on cross validation of the records. The remaining of the records was used for testing the classifier. The overall correct rate of the proposed method was found to be around 75%, which is acceptable compared to the techniques in the literature.

Keywords: Features selection, regression trees, sleep stagescoring, wavelet packets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2282

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: Classification, singing, spectral analysis, vocal emission, vocal register.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1262

Authors: Sabina Jordan, Miha Tomšič, Friderik Knez, Marjana Šijanec Zavrl

Abstract:

To determine the possibilities for the implementation of sustainable building indicators in Slovenia, testing of the first version of the indicators, developed in the CARE4CLIMATE project and based on the EU Level(s) framework, was carried out in 2022. Invited and interested stakeholders of the construction process were provided with video content and instructions on the Slovenian e-platform of sustainable building indicators. In addition, workshops and lectures with individual subjects were also performed. The final phase of the training and testing procedure included a questionnaire, which was used to obtain information about the participants' opinions regarding the indicators. The analysis of the results of the testing, which was focused on level 2, confirmed the key preliminary finding of the development group, namely that currently, due to the lack of certain knowledge, data, and tools, all indicators for this level are not yet feasible in practice. The research also highlighted the greater need for training and specialization of experts in this field. At the same time, it showed that the testing of the first version itself was a big challenge: only 30 experts fully participated and filled out the online questionnaire. This number seems alarmingly low at first glance, but compared to level(s) testing in the EU member states, it is much more than 50 times higher. However, for the further execution of the indicators in Slovenia, it will therefore be necessary to invest a lot of effort and engagement. It is likely that state support will also be needed, for example, in the form of financial mechanisms or incentives and/or legislative background.

Keywords: Sustainability, building indicator, project CARE4CLIMATE, alpha version SLO kTG, Level(s), sustainable construction stakeholders.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 129

Authors: Natanya Meyer, Johann Landsberg

Abstract:

Unemployment among the youth is a significant problem in South Africa. Large corporations and the public sector simply cannot create enough jobs. Too many youths in South Africa currently do not consider entrepreneurship as an option in order to become independent. Unlike the youth of the Netherlands, South African youth prefer to find employment in the public or private sector. The Netherlands has a much lower unemployment rate than South Africa and the Dutch are generally very entrepreneurial. From early on, entrepreneurship is considered a desirable career option in the Netherlands. The purpose of this study was to determine whether there is a difference in the perceptions of some Dutch and South African students in terms of unemployment and entrepreneurship. Questionnaires were distributed to students at the North West University's Vaal Triangle campus in Vanderbijlpark in Gauteng, South Africa and the Technical University of Delft in the Netherlands. A descriptive statistical analysis approach was followed and the means for the independent questions were calculated. The results demonstrate that the Dutch students are not as concerned about unemployment after completion of their studies as this is not as significant a problem as it is in South Africa. Both groups had positive responses towards the posed questions, but the South African group felt more strongly about the issues. Both groups of students felt that there was a need for more practical entrepreneurship training. The South African education system should focus on practical entrepreneurship training from a young age.

Keywords: Entrepreneurship development, entrepreneurship development programmes, entrepreneurship intention, Netherlands, South Africa, unemployment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1869

Authors: M. Athar Hussain, N.B. Jumani, Munazza Sultana., M. Zafar Iqbal

Abstract:

Language Reforms and potential use of ICTs has been a focal area of Higher Education Commission of Pakistan. Efforts are being accelerated to incorporate fast expanding ICTs to bring qualitative improvement in language instruction in higher education. This paper explores how university teachers are benefitting from ICTs to make their English class effective and what type of problems they face in practicing ICTs during their lectures. An in-depth qualitative study was employed to understand why language teachers tend to use ICTs in their instruction and how they are practicing it. A sample of twenty teachers from five universities located in Islamabad, three from public sector and two from private sector, was selected on non-random (Snowball) sampling basis. An interview with 15 semi-structured items was used as research instruments to collect data. The findings reveal that business English teaching is facilitated and improved through the use of ICTs. The language teachers need special training regarding the practices and implementation of ICTs. It is recommended that initiatives might be taken to equip university language teachers with modern methodology incorporating ICTs as focal area and efforts might be made to remove barriers regarding the training of language teachers and proper usage of ICTs.

Keywords: Information and communication technologies, internet assisted learning, teaching business English, online instructional content.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1896

Authors: Thanasit Suksutdhi

Abstract:

This survey research aims to study the standard of service quality of food and beverage service staffs in hotel business by studying the service standard of three sample hotels, Siam Kempinski Hotel Bangkok, Four Seasons Resort Chiang Mai, and Banyan Tree Phuket. In order to find the international service standard of food and beverage service, triangular research, i.e. quantitative, qualitative, and survey were employed. In this research, questionnaires and in-depth interview were used for getting the information on the sequences and method of services. There were three parts of modified questionnaires to measure service quality and guest’s satisfaction including service facilities, attentiveness, responsibility, reliability, and circumspection. This study used sample random sampling to derive subjects with the return rate of the questionnaires was 70% or 280. Data were analyzed by SPSS to find arithmetic mean, SD, percentage, and comparison by t-test and One-way ANOVA. The results revealed that the service quality of the three hotels were in the international level which could create high satisfaction to the international customers. Recommendations for research implementations were to maintain the area of good service quality, and to improve some dimensions of service quality such as reliability. Training in service standard, product knowledge, and new technology for employees should be provided. Furthermore, in order to develop the service quality of the industry, training collaboration between hotel organization and educational institutions in food and beverage service should be considered.

Keywords: Service standard, food and beverage department, sequence of service, service method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7754

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: Stacking, multi-layers, ensemble, multi-class.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1044

Authors: Josiel Delgadillo, Johnson Kinyua, Charles Mutigwe

Abstract:

The purpose of sentiment analysis is to determine the sentiment strength (e.g., positive, negative, neutral) from a textual source for good decision-making. Natural Language Processing (NLP) in domains such as financial markets requires knowledge of domain ontology, and pre-trained language models, such as BERT, have made significant breakthroughs in various NLP tasks by training on large-scale un-labeled generic corpora such as Wikipedia. However, sentiment analysis is a strong domain-dependent task. The rapid growth of social media has given users a platform to share their experiences and views about products, services, and processes, including financial markets. StockTwits and Twitter are social networks that allow the public to express their sentiments in real time. Hence, leveraging the success of unsupervised pre-training and a large amount of financial text available on social media platforms could potentially benefit a wide range of financial applications. This work is focused on sentiment analysis using social media text on platforms such as StockTwits and Twitter. To meet this need, SkyBERT, a domain-specific language model pre-trained and fine-tuned on financial corpora, has been developed. The results show that SkyBERT outperforms current state-of-the-art models in financial sentiment analysis. Extensive experimental results demonstrate the effectiveness and robustness of SkyBERT.

Keywords: BERT, financial markets, Twitter, sentiment analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 587

Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota

Abstract:

Understanding the causes of a road accident and predicting their occurrence is key to prevent deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network. 

Keywords: Accident risks estimation, artificial neural network, deep learning, K-mean, road safety.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 858

Authors: Gaofetoge Lenetha, Malerato Moloi, Ntsoaki Malebo

Abstract:

Microbial contamination of ready-to-eat foods and beverages sold by street vendors has become an important public health issue. In developing countries including South Africa, health risks related to such kinds of foods are thought to be common. Thus, this study assessed knowledge, attitude and practices of street food vendors. Street vendors in the city of Mangaung Metro were investigated in order to assess their knowledge, attitudes and handling practices. A semi-structured questionnaire and checklist were used in interviews to determine the status of the vending sites and associa. ted food-handling practices. Data was collected by means of a face-to-face interview. The majority of respondents were black females. Hundred percent (100%) of the participants did not have any food safety training. However, street vendors showed a positive attitude towards food safety. Despite the positive attitude, vendors showed some non-compliance when it comes to handling food. During the survey, it was also observed that the vending stalls lack basic infrastructures like toilets and potable water that is currently a major problem. This study indicates a need for improvements in the environmental conditions at these sites to prevent foodborne diseases. Moreover, based on the results observed food safety and food hygiene training or workshops for street vendors are highly recommended.

Keywords: Food hygiene, foodborne illnesses, food safety, street foods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1069

Authors: Ion Smeureanu, Marian Dardala, Adriana Reveiu

Abstract:

The new programming technologies allow for the creation of components which can be automatically or manually assembled to reach a new experience in knowledge understanding and mastering or in getting skills for a specific knowledge area. The project proposes an interactive framework that permits the creation, combination and utilization of components that are specific to mathematical training in high schools. The main framework-s objectives are: • authoring lessons by the teacher or the students; all they need are simple operating skills for Equation Editor (or something similar, or Latex); the rest are just drag & drop operations, inserting data into a grid, or navigating through menus • allowing sonorous presentations of mathematical texts and solving hints (easier understood by the students) • offering graphical representations of a mathematical function edited in Equation • storing of learning objects in a database • storing of predefined lessons (efficient for expressions and commands, the rest being calculations; allows a high compression) • viewing and/or modifying predefined lessons, according to the curricula The whole thing is focused on a mathematical expressions minicompiler, storing the code that will be later used for different purposes (tables, graphics, and optimisations). Programming technologies used. A Visual C# .NET implementation is proposed. New and innovative digital learning objects for mathematics will be developed; they are capable to interpret, contextualize and react depending on the architecture where they are assembled.

Keywords: Adaptor, automatic assembly learning component and user control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1656

Authors: P. Maheshwari, M. Shapurkar

Abstract:

The present research aimed at studying the awareness and attitudes of teachers towards inclusive education. The sample consisted of 60 teachers, teaching in the primary section (1st – 4th) of regular schools affiliated to the SSC board in Mumbai. Sample was selected by Multi-stage cluster sampling technique. A semi-structured self-constructed interview schedule and a self-constructed attitude scale was used to study the awareness of teachers about disability and Inclusive education, and their attitudes towards inclusive education respectively. Themes were extracted from the interview data and quantitative data was analyzed using SPSS package. Results revealed that teachers had some amount of awareness but an inadequate amount of information on disabilities and inclusive education. Disability to most (37) teachers meant “an inability to do something”. The difference between disability and handicap was stated by most as former being cognitive while handicap being physical in nature. With regard to Inclusive education, a large number (46) stated that they were unaware of the term and did not know what it meant. Majority (52) of them perceived maximum challenges for themselves in an inclusive set up, and emphasized on the role of teacher training courses in the area of providing knowledge (49) and training in teaching methodology (53). Although, 83.3% of teachers held a moderately positive attitude towards inclusive education, a large percentage (61.6%) of participants felt that being in inclusive set up would be very challenging for both children with special needs and without special needs. Though, most (49) of the teachers stated that children with special needs should be educated in regular classroom but they further clarified that only those should be in a regular classroom who have physical impairments of mild or moderate degree.

Keywords: Attitudes, awareness, inclusive education, teachers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3330

Authors: Yazan M. Alatrash, Han-ok Kang, Hyun-gi Yoon, Shen Zhang, Juhyeon Yoon

Abstract:

Flow coastdown phenomena are very important to secure nuclear fuel integrity during loss of off-site power accidents. In this study, primary coolant flow coastdown phenomena are investigated for the Jordan Research and Training Reactor (JRTR) using a simulation software package, Modular Modeling System (MMS). Two MMS models are built. The first one is a simple model to investigate the characteristics of the primary coolant pump only. The second one is a model for a simulation of the Primary Coolant System (PCS) loop, in which all the detailed design data of the JRTR PCS system are modeled, including the geometrical arrangement data. The same design data for a PCS pump are used for both models. Coastdown curves obtained from the two models are compared to study the PCS loop coolant inertia effect on a flow coastdown. Results showed that the loop coolant inertia effect is found to be small in the JRTR PCS loop, i.e., about one second increases in a coastdown half time required to halve the coolant flow rate. The effects of different flywheel inertia on the flow coastdown are also investigated. It is demonstrated that the coastdown half time increases with the flywheel inertia linearly. The designed coastdown half time is proved to be well above the design requirement for the fuel integrity.

Keywords: Flow Coastdown, Loop Coolant Inertia, Modeling, Research Reactor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3748

Authors: M. Analoui, M. Fadavi Amiri

Abstract:

The design of a pattern classifier includes an attempt to select, among a set of possible features, a minimum subset of weakly correlated features that better discriminate the pattern classes. This is usually a difficult task in practice, normally requiring the application of heuristic knowledge about the specific problem domain. The selection and quality of the features representing each pattern have a considerable bearing on the success of subsequent pattern classification. Feature extraction is the process of deriving new features from the original features in order to reduce the cost of feature measurement, increase classifier efficiency, and allow higher classification accuracy. Many current feature extraction techniques involve linear transformations of the original pattern vectors to new vectors of lower dimensionality. While this is useful for data visualization and increasing classification efficiency, it does not necessarily reduce the number of features that must be measured since each new feature may be a linear combination of all of the features in the original pattern vector. In this paper a new approach is presented to feature extraction in which feature selection, feature extraction, and classifier training are performed simultaneously using a genetic algorithm. In this approach each feature value is first normalized by a linear equation, then scaled by the associated weight prior to training, testing, and classification. A knn classifier is used to evaluate each set of feature weights. The genetic algorithm optimizes a vector of feature weights, which are used to scale the individual features in the original pattern vectors in either a linear or a nonlinear fashion. By this approach, the number of features used in classifying can be finely reduced.

Keywords: Feature reduction, genetic algorithm, pattern classification, nearest neighbor rule classifiers (k-NNR).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1725

Authors: Chia-Jou Hsieh, Feng-Chuan Pan

Abstract:

Oral health is particular important to the hospitalized patients with chronic schizophrenia for an extreme high potential of the respiratory infections. Due to the degeneration of physical capability, patients of this kind typically fall dependent in the activity of daily living (ADL). A very high percentage of patients had dental problems of which mostly could be easily avoid by easy regular tooth brushing. Purpose of the project is to develop a mechanism in helping the schizophrenia patients in rebuilding a tooth-cleaning habit. The project observed and evaluated the tooth-cleaning behavior of 100 male patients in a psychiatric hospital, and found the majority of them ignored such an activity in a three-month period of time. In the meantime, the primary care-givers were not aware or not convinced the importance of such a need of dental hygiene, and thus few if any tooth cleaning training or knowledge on dental hygiene were given to the patients. The project then developed a program based on the numerous observations and discussions. The improvement program included patients- group education, care-givers- training, and a tool-kit for tooth-brush holding was erected. The project launched with some incentive package. The outcomes were encouraging with 87% of the patients had rebuilt their tooth-brushing habits against previous 22%, and the tooth cleaning kits were 100% kept against 22% in the past. This project had significantly improved the oral health of the patients. The project, included the procedure and the tool-kit holder specific for this purpose, was a good examples for psychiatric hospitals.

Keywords: Schizophrenia, dental hygiene, tool-kit holder, health education

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1909

Authors: Abd Aziz Bin Abd Shukor, Eftah Binti Moh Hj Abdullah

Abstract:

This case study aims to identify teachers’ perception as regards integrity in School-Ba sed Assessment (PBS) practice. This descriptive study involved 9 teachers from 4 secondary schools in 3 districts in the state of Perak. The respondents had undergone an integrity in PBS Practice interview using a focused group discussion method. The overall findings showed that the teachers believed that integrity in PBS practice could be achieved by adjusting the teaching methods align with learning objectives and the students’ characteristics. Many teachers, parents and student did not understand the best practice of PBS. This would affect the integrity in PBS practice. Teachers did not emphasis the principles and ethics. Their integrity as an innovative public servant may also be affected with the frequently changing assessment system, lack of training and no prior action research. The analysis of findings showed that the teachers viewed that organizational integrity involving the integrity of PBS was difficult to be implemented based on the expectations determined by Malaysia Ministry of Education (KPM). A few elements which assisted in the achievement of PBS integrity were the training, students’ understanding, the parents’ understanding of PBS, environment (involving human resources such as support and appreciation and non-human resources such as technology infrastructure readiness and media). The implications of this study show that teachers, as the PBS implementers, have a strong influence on the integrity of PBS. However, the transformation of behavior involving PBS integrity among teachers requires the stabilisation of support and infrastructure in order to enable the teachers to implement PBS in an ethical manner.

Keywords: Assessment integrity, integrity, perception, school-based assessment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1546

Authors: Shao-Hsia Chang, Nan-Ying Yu

Abstract:

The objective of this study was to test how advanced digital technology enables a more effective training on the handwriting of children with handwriting deficit. This study implemented the graphomotor apparatuses to a computer-assisted instruction system. In a randomized controlled trial, the experiments for verifying the intervention effect were conducted. Forty two children with handwriting deficit were assigned to computer-assisted instruction, sensorimotor training or control (no intervention) group. Handwriting performance was measured using the Elementary reading/writing test and computerized handwriting evaluation before and after 6 weeks of intervention. Analysis of variance of change scores were conducted to show whether statistically significant difference across the three groups. Significant difference was found among three groups. Computer group shows significant difference from the other two groups. Significance was denoted in near-point, far-point copy, dictation test, and writing from phonetic symbols. Writing speed and mean stroke velocity in near-, far-point and short paragraph copy were found significantly difference among three groups. Computer group shows significant improvement from the other groups. For clinicians and school teachers, the results of this study provide a motor control based insight for the improvement of handwriting difficulties.

Keywords: Dysgraphia, computerized handwriting evaluation, sensorimotor program, computer assisted program.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2023

Authors: Parvinder S. Sandhu, Sandeep Khimta, Kiranpreet Kaur

Abstract:

The prediction of Software quality during development life cycle of software project helps the development organization to make efficient use of available resource to produce the product of highest quality. “Whether a module is faulty or not" approach can be used to predict quality of a software module. There are numbers of software quality prediction models described in the literature based upon genetic algorithms, artificial neural network and other data mining algorithms. One of the promising aspects for quality prediction is based on clustering techniques. Most quality prediction models that are based on clustering techniques make use of K-means, Mixture-of-Guassians, Self-Organizing Map, Neural Gas and fuzzy K-means algorithm for prediction. In all these techniques a predefined structure is required that is number of neurons or clusters should be known before we start clustering process. But in case of Growing Neural Gas there is no need of predetermining the quantity of neurons and the topology of the structure to be used and it starts with a minimal neurons structure that is incremented during training until it reaches a maximum number user defined limits for clusters. Hence, in this work we have used Growing Neural Gas as underlying cluster algorithm that produces the initial set of labeled cluster from training data set and thereafter this set of clusters is used to predict the quality of test data set of software modules. The best testing results shows 80% accuracy in evaluating the quality of software modules. Hence, the proposed technique can be used by programmers in evaluating the quality of modules during software development.

Keywords: Growing Neural Gas, data clustering, fault prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1817

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: Visual search, deep learning, convolutional neural network, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 772

Authors: Yehjune Heo

Abstract:

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Keywords: Anti-spoofing, CNN, fingerprint recognition, GAN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 532

Authors: Kyu Jin Kim, Byung Kwan Oh, Hyo Seon Park

Abstract:

The seismic responses-based structural health monitoring system has been performed to prevent seismic damage. Structural seismic damage of building is caused by the instantaneous stress concentration which is related with dynamic characteristic of earthquake. Meanwhile, seismic response analysis to estimate the dynamic responses of building demands significantly high computational cost. To prevent the failure of structural members from the characteristic of the earthquake and the significantly high computational cost for seismic response analysis, this paper presents an artificial neural network (ANN) based prediction model for dynamic responses of building considering specific time length. Through the measured dynamic responses, input and output node of the ANN are formed by the length of specific time, and adopted for the training. In the model, evolutionary radial basis function neural network (ERBFNN), that radial basis function network (RBFN) is integrated with evolutionary optimization algorithm to find variables in RBF, is implemented. The effectiveness of the proposed model is verified through an analytical study applying responses from dynamic analysis for multi-degree of freedom system to training data in ERBFNN.

Keywords: Structural health monitoring, dynamic response, artificial neural network, radial basis function network, genetic algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 370