Search results for: computer-assisted language learning

Authors: Syed Basit Ali Shah Bukhari, Yan Qiang, Saad Abdul Rauf, Syed Saqlaina Bukhari

Abstract:

Text Classification is the methodology to classify any given text into the respective category from a given set of categories. It is highly important and vital to use proper set of pre-processing , feature selection and classification techniques to achieve this purpose. In this paper we have used different ensemble techniques along with variance in feature selection parameters to see the change in overall accuracy of the result and also on some other individual class based features which include precision value of each individual category of the text. After subjecting our data through pre-processing and feature selection techniques , different individual classifiers were tested first and after that classifiers were combined to form ensembles to increase their accuracy. Later we also studied the impact of decreasing the classification categories on over all accuracy of data. Text classification is highly used in sentiment analysis on social media sites such as twitter for realizing people’s opinions about any cause or it is also used to analyze customer’s reviews about certain products or services. Opinion mining is a vital task in data mining and text categorization is a back-bone to opinion mining.

Keywords: Natural Language Processing, Ensemble Classifier, Bagging Classifier, AdaBoost

Procedia PDF Downloads 208

Authors: Pengchao Wei, Xiangzhong Fang

Abstract:

Noise is ubiquitous in this world. Denoising is an essential technology, especially in image semantic segmentation, where noises are generally categorized into two main types i.e. feature noise and label noise. The main focus of this paper is aiming at modeling label noise, investigating the behaviors of different types of label noise on image semantic segmentation tasks using K-Nearest-Neighbor and Convolutional Neural Network classifier. The performance without label noise and with is evaluated and illustrated in this paper. In addition to that, the influence of feature noise on the image semantic segmentation task is researched as well and a feature noise reduction method is applied to mitigate its influence in the learning procedure.

Keywords: convolutional neural network, denoising, feature noise, image semantic segmentation, k-nearest-neighbor, label noise

Procedia PDF Downloads 193

Authors: Baohua Yu

Abstract:

Despite widely reported 'Mainland-Hong Kong conflicts', recent years have witnessed progressive growth in the numbers of Mainland Chinese students in Hong Kong’s universities. This research investigated Mainland Chinese students’ intercultural communication in relation to cross-cultural adaptation in a major university in Hong Kong. The features of intercultural communication examined in this study were competence in the second language (L2) communication and L2 Willingness to Communicate (WTC), while the features of cross-cultural adaptation examined were socio-cultural, psychological and academic adaptation. Based on a questionnaire, structural equation modelling was conducted among a sample of 196 Mainland Chinese students. Results showed that the competence in L2 communication played a significant role in L2 WTC, which had an influential effect on academic adaptation, which was itself identified as a mediator between the psychological adaptation and socio-cultural adaptation. Implications for curriculum design for courses and instructional practice on international students are discussed.

Keywords: L2 willingness to communicate, competence in L2 communication, psychological adaptation, socio-cultural adaptation, academic adaptation, structural equation modelling

Procedia PDF Downloads 330

Authors: Mohd Nazri Latiff Azmi, Mairas Abd Rahman

Abstract:

Traditionally, literacy has been commonly defined as the ability to read and write at an adequate level of proficiency that is necessary for communication. However, as time goes by, literacy has started to refer to reading and writing at a level adequate for communication, or at a level that lets one understand and communicate ideas in a literate society, so as to take part in that society. Meanwhile, visual literacy is a set of abilities that enables an individual to effectively find, interpret, evaluate, use, and create images and visual media. This study aims to investigate the collaboration between visual literacy and literature, eventually to determine how visual literacy can enhance learner’s ability to comprehend literary texts such as poems and short stories and develop his intellectuality, especially critical and creative thinking skills, and also to find out the different impacts of literature in visual literacy at four levels of education: pre-school, primary and secondary schools and university. This study is based on Malaysian environment and involves a qualitative method consisting of observation and interviews. The initial findings show that people with different levels of education grasp visual literacy differently but all levels show outstanding impacts of using literature.

Keywords: visual literacy, literature, language studies, higher education

Procedia PDF Downloads 341

Authors: Qiuyu Dai, Haochong Zhang, Xiangrong Liu

Abstract:

Diagonal sparse matrix-vector multiplication is a well-studied topic in the fields of scientific computing and big data processing. However, when diagonal sparse matrices are stored in DIA format, there can be a significant number of padded zero elements and scattered points, which can lead to a degradation in the performance of the current DIA kernel. This can also lead to excessive consumption of computational and memory resources. In order to address these issues, the authors propose the DIA-Adaptive scheme and its kernel, which leverages the parallel instruction sets on MLU. The researchers analyze the effect of allocating a varying number of threads, clusters, and hardware architectures on the performance of SpMV using different formats. The experimental results indicate that the proposed DIA-Adaptive scheme performs well and offers excellent parallelism.

Keywords: adaptive method, DIA, diagonal sparse matrices, MLU, sparse matrix-vector multiplication

Procedia PDF Downloads 90

Authors: Diana Codat

Abstract:

Tweets' analysis is part of text mining. Each document is a written text. It's possible to apply the usual text search techniques, in particular by switching to the bag-of-words representation. But the tweets induce peculiarities. Some may enrich the analysis. Thus, their length is calibrated (at least as far as public messages are concerned), special characters make it possible to identify authors (@) and themes (#), the tweet and retweet mechanisms make it possible to follow the diffusion of the information. Conversely, other characteristics may disrupt the analyzes. Because space is limited, authors often use abbreviations, emoticons to express feelings, and they do not pay much attention to spelling. All this creates noise that can complicate the task. The tweets carry a lot of potentially interesting information. Their exploitation is one of the main axes of the analysis of the social networks. We show how to access Twitter-related messages. We will initiate a study of the properties of the tweets, and we will follow up on the exploitation of the content of the messages. We will work under R with the package 'twitteR'. The study of tweets is a strong focus of analysis of social networks because Twitter has become an important vector of communication. This example shows that it is easy to initiate an analysis from data extracted directly online. The data preparation phase is of great importance.

Keywords: data mining, language R, social networks, Twitter

Procedia PDF Downloads 155

Authors: Fabrizio Logiurato

Abstract:

Light Polarization has many technological applications, and its discovery was crucial to reveal the transverse nature of the electromagnetic waves. However, despite its fundamental and practical importance, in high school, this property of light is often neglected. This is a pity not only for its conceptual relevance, but also because polarization gives the possibility to perform many brilliant experiments with low cost materials. Moreover, the treatment of this matter lends very well to an interdisciplinary approach between art, biology and technology, which usually makes things more interesting to students. For these reasons, we have developed, and in this work, we introduce a laboratory on light polarization for high school and undergraduate students. They can see beautiful pictures when birefringent materials are set between two crossed polarizing filters. Pupils are very fascinated and drawn into by what they observe. The colourful images remind them of those ones of abstract painting or alien landscapes. With this multidisciplinary teaching method, students are more engaged and participative, and also, the learning process of the respective physics concepts is more effective.

Keywords: light polarization, optical activity, multidisciplinary education, science and art

Procedia PDF Downloads 191

Authors: Fawaz S. Al-Anzi, Dia AbuZeina

Abstract:

Speech recognition is of an important contribution in promoting new technologies in human computer interaction. Today, there is a growing need to employ speech technology in daily life and business activities. However, speech recognition is a challenging task that requires different stages before obtaining the desired output. Among automatic speech recognition (ASR) components is the feature extraction process, which parameterizes the speech signal to produce the corresponding feature vectors. Feature extraction process aims at approximating the linguistic content that is conveyed by the input speech signal. In speech processing field, there are several methods to extract speech features, however, Mel Frequency Cepstral Coefficients (MFCC) is the popular technique. It has been long observed that the MFCC is dominantly used in the well-known recognizers such as the Carnegie Mellon University (CMU) Sphinx and the Markov Model Toolkit (HTK). Hence, this paper focuses on the MFCC method as the standard choice to identify the different speech segments in order to obtain the language phonemes for further training and decoding steps. Due to MFCC good performance, the previous studies show that the MFCC dominates the Arabic ASR research. In this paper, we demonstrate MFCC as well as the intermediate steps that are performed to get these coefficients using the HTK toolkit.

Keywords: speech recognition, acoustic features, mel frequency, cepstral coefficients

Procedia PDF Downloads 235

Authors: Ashenafi Sileshi Etefa, Bezawit Worku Yenealem

Abstract:

Micro-insurance is a relatively new concept that is just being introduced in Ethiopia. For an agrarian economy dominated by small holder farming and vulnerable to natural disasters, mainly drought, the need for an Index-Based Micro Insurance (IBMI) is crucial. Since IBMI solves moral hazard, adverse selection, and access issues to poor clients, it is preferable over traditional insurance products. IBMI is being piloted in drought prone areas of Ethiopia with the aim of learning and expanding the service across the country. This article analyses the demand of IBMI and the barriers to demand and finds that the demand for IBMI has so far been constrained by lack of awareness, trust issues, costliness, and the level of basis risk; and recommends reducing the basis risk and increasing the role of government and farmer cooperatives.

Keywords: agriculture, index based micro-insurance (IBMI), drought, micro-finance institution (MFI)

Procedia PDF Downloads 268

Authors: Aadya Kaktikar

Abstract:

The role of a traditional dance teacher in India revolves around teaching movements and postures that have been a part of the movement vocabulary of dancers from before the 2nd century BC. These movements inscribe on the mind and body of the dancer a complex web of philosophy, culture history, and religion. However, this repository of tradition sits in a fast globalizing India creating a cultural space which is in a constant flux, where identities and meanings are being constantly challenged. The guru-shishya parampara, the traditional way of learning dance, sits uneasily with a modern education space in India. The traditional dance teacher is caught in the cross-currents of tradition and modernity, of preservation and exploration. This paper explores conflicting views on what dance ought to mean and how it should be taught. The paper explores the tensions of the social, economic and cultural spaces that the traditional dance teacher navigates.

Keywords: pedagogy, dance education, dance curriculum, teacher training

Procedia PDF Downloads 285

Authors: Geetishree Mishra, S. Akhila

Abstract:

Embedded System Design, the most challenging course of electronics engineering has always been appreciated and well acclaimed by the students of electronics and its related branches of engineering. Embedded system, being a product of multiple application domains, necessitates skilled man power to be well designed and tested in every important aspect of both hardware and software. In the current industrial scenario, the requirements are even more rigorous and highly demanding and needs to be to be on par with the advanced technologies. Fresh engineers are expected to be thoroughly groomed by the academic system and the teaching community. Graduates with the ability to understand both complex technological processes and technical skills are increasingly sought after in today's embedded industry. So, the need of the day is to restructure the under-graduate course- both theory and lab practice along with the teaching methodologies to meet the industrial requirements. This paper focuses on the importance of such a need in the present education system.

Keywords: embedded system design, industry requirement, syllabus restructuring, project-based learning, teaching methodology

Procedia PDF Downloads 631

Authors: Baratali Monfarediraz

Abstract:

Humans’ identity is not only under the influence of a certain society or social structure but also it is influenced by an international identity. This article is a research on role of education in the manifestation of universally accepted values such as, advancement of science, improvement in the quality of education, preservation of the natural environment, preservation, and spread of peace, exchange of knowledge and technology, equal educational opportunities, benefiting from a universal morality and etc. Therefore, the relation between universal beliefs and values and educational approaches and programs is the first thing to pay attention to. Studies indicate that the first step in achieving the above mentioned goals is offering learning strategies. Therefore the importance of educational approaches and programs as a tool for the transference of ideas, experiences and thoughts becomes quite clear. Proper education gives everyone the opportunity of acquiring knowledge while creating tendency toward social activities paves the way for achieving the universal values.

Keywords: globalization, universal values, education, universal goal, values, society

Procedia PDF Downloads 355

Authors: Secil Kaya Gulen

Abstract:

Face to face and virtual classrooms that came up with different conditions and environments, but similar purposes have different characteristics. Although virtual classrooms have some similar facilities with face-to-face classes such as program, students, and administrators, they have no walls and corridors. Therefore, students can attend the courses from a distance and can control their own learning spaces. Virtual classrooms defined as simultaneous online environments where students in different places come together at the same time with the guidance of a teacher. Distance education and virtual classes require different intellectual and managerial skills and models. Therefore, for effective use of virtual classrooms, the virtual property should be taken into consideration. One of the most important factors that affect the spread and effective use of the virtual classrooms is the perceptions and opinions of students -as one the main participants-. Student opinions and recommendations are important in terms of providing information about the fulfillment of expectation. This will help to improve the applications and contribute to the more efficient implementations. In this context, ideas and perceptions of the students related to the virtual classrooms, in general, were determined in this study. Advantages and disadvantages of virtual classrooms expected contributions to the educational system and expected characteristics of virtual classrooms have examined in this study. Students of an online distance education graduate program in which all the courses offered by virtual classrooms have asked for their opinions. Online Distance Education Graduate Program has totally 19 students. The questionnaire that consists of open-ended and multiple choice questions sent to these 19 students and finally 12 of them answered the questionnaire. Analysis of the data presented as frequencies and percentages for each item. SPSS for multiple-choice questions and Nvivo for open-ended questions were used for analyses. According to the results obtained by the analysis, participants stated that they did not get any training on virtual classes before the courses; but they emphasize that newly enrolled students should be educated about the virtual classrooms. In addition, all participants mentioned that virtual classroom contribute their personal development and they want to improve their skills by gaining more experience. The participants, who mainly emphasize the advantages of virtual classrooms, express that the dissemination of virtual classrooms will contribute to the Turkish Education System. Within the advantages of virtual classrooms, ‘recordable and repeatable lessons’ and ‘eliminating the access and transportation costs’ are most common advantages according to the participants. On the other hand, they mentioned ‘technological features and keyboard usage skills affect the attendance’ is the most common disadvantage. Participants' most obvious problem during virtual lectures is ‘lack of technical support’. Finally ‘easy to use’, ‘support possibilities’, ‘communication level’ and ‘flexibility’ come to the forefront in the scope of expected features of virtual classrooms. Last of all, students' opinions about the virtual classrooms seems to be generally positive. Designing and managing virtual classrooms according to the prioritized features will increase the students’ satisfaction and will contribute to improve applications that are more effective.

Keywords: distance education, virtual classrooms, higher education, e-learning

Procedia PDF Downloads 241

Authors: Soni Ariawan

Abstract:

The study aims to explore the cultural diversity highlighted in EFL textbook for Senior High School grade 10 in Indonesia. The visual images are selected as the data and qualitatively analysed using content analysis. The reason to choose visual images because images are not always neutral and they might impact teaching and learning process. In the current study, cultural diversity aspects are focused on religion (Muslim, Protestant, Catholic, Hindu, Buddhist, Confucian), gender (male, female, unclear), ethnic (Melanesian, Austronesian, Foreigner) and socioeconomic (low, middle, high, undetermined) diversity as the theoretical framework. The four aspects of cultural diversity are sufficiently representative to draw a conclusion in investigating Indonesian culture representation in EFL textbook. The finding shows that cultural diversity is not proportionally reflected in the textbook, particularly in the visual images.

Keywords: EFL textbook, cultural diversity, visual images, Indonesia

Procedia PDF Downloads 292

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Generally, absorption and bioavailability increase if solubility increases; therefore, it is crucial to predict them in drug discovery applications. Molecular descriptors and Molecular properties are traditionally used for the prediction of water solubility. There are various key descriptors that are used for this purpose, namely Drogan Descriptors, Morgan Descriptors, Maccs keys, etc., and each has different prediction capabilities with differentiating successes between different data sets. Another source for the prediction of solubility is structural features; they are commonly used for the prediction of solubility. However, there are little to no studies that combine three or more properties or descriptors for prediction to produce a more powerful prediction model. Unlike available models, we used a combination of those features in a random forest machine learning model for improved solubility prediction to better predict and, therefore, contribute to drug discovery systems.

Keywords: solubility, random forest, molecular descriptors, maccs keys

Procedia PDF Downloads 5

Authors: Kamna Solanki, Yudhvir Singh, Sandeep Dalal

Abstract:

Software testing is a time and cost intensive process. A scrutiny of the code and rigorous testing is required to identify and rectify the putative bugs. The process of bug identification and its consequent correction is continuous in nature and often some of the bugs are removed after the software has been launched in the market. This process of code validation of the altered software during the maintenance phase is termed as Regression testing. Regression testing ubiquitously considers resource constraints; therefore, the deduction of an appropriate set of test cases, from the ensemble of the entire gamut of test cases, is a critical issue for regression test planning. This paper presents a novel method for designing a suitable prioritization process to optimize fault detection rate and performance of regression test on predefined constraints. The proposed method for test case prioritization m-ACO alters the food source selection criteria of natural ants and is basically a modified version of Ant Colony Optimization (ACO). The proposed m-ACO approach has been coded in 'Perl' language and results are validated using three examples by computation of Average Percentage of Faults Detected (APFD) metric.

Keywords: regression testing, software testing, test case prioritization, test suite optimization

Procedia PDF Downloads 310

Authors: Muhammad Ammar, Talha Ali, Abdul Basit, Bakhtawar Rajput, Zobia Sohail

Abstract:

Music note detection is an area of study for the past few years and has its own influence in music file generation from sheet music. We proposed a method to detect music notes on sheet music using basic thresholding and blob detection. Subsequently, we created a notes dictionary using a semi-supervised learning approach. After notes detection, for each test image, the new symbols are added to the dictionary. This makes the notes detection semi-automatic. The experiments are done on images from a dataset and also on the captured images. The developed approach showed almost 100% accuracy on the dataset images, whereas varying results have been seen on captured images.

Keywords: music note, sheet music, optical music recognition, blob detection, thresholding, dictionary generation

Procedia PDF Downloads 148

Authors: Mohammad Reza Ostad Ali Naghi Kashani, Esfanji Elia

Abstract:

Nowadays, the amounts of companies which tend to have an Enterprise Resource Planning (ERP) application are increasing particularly in developing countries like Iran. ERP projects are expensive, time consuming, and complex, in addition the failure rate is high among these projects. It is important to know whether these projects could meet their goals or not. Furthermore, the area which should be improved should be identified. In this paper we made a framework to evaluate ERP projects success implementation. First, based on literature review we made a framework based on BSC model, financial, customer, processes, learning and knowledge, because of the importance of change management it was added to model. Then an organization was divided in three layers. We choose corporate, managerial, and operational levels. Then to find criteria to assess each aspect, we use Delphi method in two rounds. And for the second round we made a questionnaire and did some statistical tasks on them. Based on the statistical results some of them are accepted and others are rejected.

Keywords: ERP, BSC, ERP project evaluation, IT projects

Procedia PDF Downloads 300

Authors: Aly Elshafei, Daniela Romano

Abstract:

With the development of autonomous vehicles, a human-machine interaction (HMI) system is needed for a safe transition of control when a takeover request (TOR) is required. An important part of the HMI system is the ability to monitor the level of situational awareness (SA) of any driver in real-time, in different scenarios, and without any pre-calibration. Presenting state-of-the-art machine learning models used to measure SA is the purpose of this systematic review. Investigating the limitations of each type of sensor, the gaps, and the most suited sensor and computational model that can be used in driving applications. To the author’s best knowledge this is the first literature review identifying online and offline classification methods used to measure SA, explaining which measurements are subject or session-specific, and how many classifications can be done with each classification model. This information can be very useful for researchers measuring SA to identify the most suited model to measure SA for different applications.

Keywords: situational awareness, autonomous driving, gaze metrics, EEG, ECG

Procedia PDF Downloads 98

Authors: Emma Louise McKinney

Abstract:

There is a global move to integrate children who are Deaf and Hearing Impaired into regular classrooms with their hearing peers with an inclusive education framework. This paper examines the current education situation for children who are Deaf and Hearing Impaired in South Africa, Madagascar, Malawi, Zimbabwe, and Namibia. Qualitative data for this paper was obtained from the author’s experiences working as the Southern African Education Advisor for an international organization funding disability projects. It examines some of the challenges facing these children and their teachers relating to education. Challenges include cultural stigma relating to disability and deafness, a lack of hearing screening and early identification of deafness, schools in rural areas, special schools, specialist teacher training, equipment, understanding of how to implement policy, support, appropriate teaching methodologies, and sign language training and proficiency. On the other hand, in spite of the challenges some teachers are able to provide quality education to children who are Deaf and Hearing Impaired. This paper examines both the challenges as well as what teachers are doing to overcome these.

Keywords: education of children who are deaf and hearing impaired, Southern African experiences, challenges, triumphs

Procedia PDF Downloads 215

Authors: D. Hassell, D. De Focatiis

Abstract:

This paper presents work on the application of wiki based coursework for a fourth-year engineering module delivered as part of both a MEng and MSc programme in Chemical Engineering. The module was taught with an equivalent structure simultaneously on two separate campuses, one in the United Kingdom (UK) and one in Malaysia, and the subsequent results were compared. Student feedback was sought via questionnaires, with 45 respondents from the UK and 49 from Malaysia. Results include discussion on; perceived difficulty; student enjoyment and experiences; differences between MEng and MSc students; differences between cohorts on different campuses. The response of students to the use of wiki-based coursework was found to vary based on their experiences and background, with UK students being generally more positive on its application than those in Malaysia.

Keywords: engineering education, student differences, student learning, web based coursework

Procedia PDF Downloads 276

Authors: Zheng Baichuan, Li Shenghui, Li Bingqian, Zhang Ning, Chen Kai

Abstract:

Entity alignment (EA) tasks in knowledge graphs often play a pivotal role in the integration of knowledge graphs, where structural differences often exist between the source and target graphs, such as the presence or absence of attribute information and the types of attribute information (text, timestamps, images, etc.). However, most current research efforts are focused on improving alignment accuracy, often along with an increased reliance on specific structures -a dependency that inevitably diminishes their practical value and causes difficulties when facing knowledge graph alignment tasks with varying structures. Therefore, we propose a universal knowledge graph alignment approach that only utilizes the common basic structures shared by knowledge graphs. We have demonstrated through experiments that our method achieves state-of-the-art performance in fair comparisons.

Keywords: knowledge graph, entity alignment, transformer, deep learning

Procedia PDF Downloads 21

Authors: Richard Ren

Abstract:

Air pollution is a serious danger to international well-being and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.Air pollution is a serious danger to international wellbeing and economies - it will kill an estimated 7 million people every year, costing world economies $2.6 trillion by 2060 due to sick days, healthcare costs, and reduced productivity. In the United States alone, 60,000 premature deaths are caused by poor air quality. For this reason, there is a crucial need to develop effective methods to forecast air quality, which can mitigate air pollution’s detrimental public health effects and associated costs by helping people plan ahead and avoid exposure. The goal of this study is to propose an artificial intelligence framework for predicting future air quality based on timing variables (i.e. season, weekday/weekend), future weather forecasts, as well as past pollutant and air quality measurements. The proposed framework utilizes multiple machine learning algorithms (logistic regression, random forest, neural network) with different specifications and averages the results of the three top-performing models to eliminate inaccuracies, weaknesses, and biases from any one individual model. Over time, the proposed framework uses new data to self-adjust model parameters and increase prediction accuracy. To demonstrate its applicability, a prototype of this framework was created to forecast air quality in Los Angeles, California using datasets from the RP4 weather data repository and EPA pollutant measurement data. The results showed good agreement between the framework’s predictions and real-life observations, with an overall 92% model accuracy. The combined model is able to predict more accurately than any of the individual models, and it is able to reliably forecast season-based variations in air quality levels. Top air quality predictor variables were identified through the measurement of mean decrease in accuracy. This study proposed and demonstrated the efficacy of a comprehensive air quality prediction framework leveraging multiple machine learning algorithms to overcome individual algorithm shortcomings. Future enhancements should focus on expanding and testing a greater variety of modeling techniques within the proposed framework, testing the framework in different locations, and developing a platform to automatically publish future predictions in the form of a web or mobile application. Accurate predictions from this artificial intelligence framework can in turn be used to save and improve lives by allowing individuals to protect their health and allowing governments to implement effective pollution control measures.

Keywords: air quality prediction, air pollution, artificial intelligence, machine learning algorithms

Procedia PDF Downloads 95

Authors: Aulia F. Hadining, Atya Nur Aisha, Dimas Kurninatoro Aji

Abstract:

Utilization of social media as a marketing tool is growing rapidly, including for SMEs. Social media allows the user to give product evaluation and recommendations to the public. In addition, the social media facilitate word-of-mouth marketing communication. One of the social media that can be used is Facebook, with Facebook Ads. This study aimed to evaluate the location of Facebook Ads, to obtain an appropriate advertising design. There are three alternatives location consist of desktop, right-hand column and mobile. The effectiveness and efficiency of advertising will be measured based on advertising metrics such as reach, click, Cost per Click (CUC) and Unique Click-Through-Rate (UCTR). Facebook's Ads Manager was used for seven days, targeted by age (18-24), location (Bandung), language (Indonesia) and keywords. The result was 13,999 total reach, as well as 342 clicks. Based on the results of comparison using ANOVA, there was a significant difference for each placement location based on advertising metrics. Mobile location was chosen to be successful ads, because it produces the lowest CUC, amounting to Rp 691,- per click and 14% UCTR. Results of this study showed Facebook Ads was useful and cost-effective media to promote the product of SME, because it could be view by many people in the same time.

Keywords: marketing communication, social media, Facebook Ads, mobile location

Procedia PDF Downloads 323

Authors: Rahma Abed, Sahbi Bahroun, Ezzeddine Zagrouba

Abstract:

Due to the huge amount of data in videos, extracting the relevant frames became a necessity and an essential step prior to performing face recognition. In this context, we propose a method for extracting keyframes from videos based on face quality and deep learning for a face recognition task. This method has two steps. We start by generating face quality scores for each face image based on the use of three face feature extractors, including Gabor, LBP, and HOG. The second step consists in training a Deep Convolutional Neural Network in a supervised manner in order to select the frames that have the best face quality. The obtained results show the effectiveness of the proposed method compared to the methods of the state of the art.

Keywords: keyframe extraction, face quality assessment, face in video recognition, convolution neural network

Procedia PDF Downloads 201

Authors: Choedchoo Kwanhathai

Abstract:

This study explores attitudes towards ASEAN plus ONE (namely ASEAN plus China) accents of English as a Lingua Franca. The study draws attention to features of ASEAN’s diversity of English and specifically examines the extent of which the English accent in ASEAN countries of three of the ten members plus one were perceived in terms of correctness, acceptability, pleasantness, and familiarity. Three accents were used for this study; Chinese, Philippine and Thai. The participants were ninety eight Thai students enrolled in a foundation course of Suan Dusit Rajabhat University, Bangkok Thailand. The students were asked in questionnaires to rank how they perceived each specifically ASEAN plus One English accent after listening to audio recordings of three stories spoken by the three different ASEAN plus ONE English speakers. SPSS was used to analyze the data. The findings of attitudes towards varieties of English accent from the 98 respondents regarding correctness, acceptability, pleasantness, and familiarity of Thai English accents found that Thai accent was overall at level 3 (X = 2.757, SD= o.33), %Then Philippines accents was at level 2 (X = 2.326, SD = 16.12), and Chinese accents w2as at level 3 (X 3.198, SD = 0.18). Finally, the present study proposes pedagogical implications for teaching regarding awareness of ‘Englishes’ of ASEAN and their respective accents and their lingua cultural background of instructors.

Keywords: English as a lingua franca, English accents, English as an international language, ASEAN plus one, ASEAN English varieties

Procedia PDF Downloads 401

Authors: Catherine Cheetam, Alan Harper, Melody Elliott, Mika Ito

Abstract:

This paper describes a pilot study conducted with English as a foreign language (EFL) students at a private university in Japan who used graded readers and the MReader website in class or independently to enhance their English reading skills. Each semester students who read 100,000 words with MReader quizzes passed enter into the ‘MReader Challenge,’ a reading contest that recognizes students for their achievement. The study focused specifically on the attitudes of thirty-six EFL students who successfully completed the Challenge in the 2015 spring semester using graded readers and MReader, and their motivation to continue using English in the future. The attitudes of these students were measured using their responses to statements on a Likert scaled survey. Follow-up semi-structured interviews were conducted with eleven students to gain additional insight into their opinions. The results from this study suggest that reading graded readers in general promoted intrinsic motivation among a majority of the participants. This study is preliminary and needs to be expanded and continued to assess the lasting impact of the extensive reading program. Limitations and future directions of the study are also summarized and discussed.

Keywords: attitudes, extensive, intrinsic, methodolgies, motivation, reading

Procedia PDF Downloads 183

Authors: Ebru Thwaites Diken

Abstract:

This article analyzes the works of certain directors in Danish cinema, namely Susanne Bier and Lone Sherfig, in the context of transnationalisation of Danish cinema. It looks at how the films' narratives negotiate and reconstruct the local / national / regional and the global. Scholars such as Nestingen & Elkington (2005), Hjort (2010), Higbee and Lim (2010), Bondebjerg and Redvall (2011) address transnationalism of Danish cinema in terms of production and distribution processes and how film making trascends national boundaries. This paper employs a particular understanding of transnationalism - in terms of how ideas and characters travel - to analyze how the storytelling and style has evolved to connect the national, the regional and the global on the basis of the works of these two directors. Strategies such as Hollywoodization - i.e. focus on stardom and classical narration, adhering to conventional European genre formulas, producing Danish films in English language have been identifiable strategies in Danish cinema in the period after the 2000s. Susanne Bier and Lone Scherfig are significant for employing some of these strategies simultaneously. For this reason, this article will look at how these two directors have employed these strategies and negotiated the cultural boundaries and exchanges.

Keywords: transnational cinema, danish cinema, susanne bier, lone scherfig

Procedia PDF Downloads 52

Authors: Matthew J. Zagumny

Abstract:

The current study reports an examination of the QUEST-25 (Q-Assessment of Undergraduate Epistemology and Scientific Thinking) online version for assessing the dispositional attitudes toward scientific thinking and intellectual curiosity among undergraduate students. The QUEST-25 consists of scientific thinking (SIQ-25) and intellectual curiosity (ICIQ-25), which were correlated in hypothesized directions with the Religious Commitment Inventory, Curiosity and Exploration Inventory, Belief in Science scale, and measures of academic self-efficacy. Additionally, concurrent validity was established by the resulting significant differences between those identifying the centrality of religious belief in their lives and those who do not self-identify as being guided daily by religious beliefs. This study demonstrates the utility of the QUEST-25 for research, evaluation, and theory development.

Keywords: guided-inquiry learning, intellectual curiosity, psychometric assessment, scientific thinking

Procedia PDF Downloads 239

Authors: Yao-Ying Lai, Maria Pinango, Ashwini Deo

Abstract:

While grammatical devices are essential to language processing, how comprehension utilizes cognitive mechanisms is less emphasized. This study addresses this issue by probing the complement coercion phenomenon: an entity-denoting complement following verbs like begin and finish receives an eventive interpretation. For example, (1) “The queen began the book” receives an agentive reading like (2) “The queen began [reading/writing/etc.…] the book.” Such sentences engender additional processing cost in real-time comprehension. The traditional account attributes this cost to an operation that coerces the entity-denoting complement to an event, assuming that these verbs require eventive complements. However, in closer examination, examples like “Chapter 1 began the book” undermine this assumption. An alternative, Structured Individual (SI) hypothesis, proposes that the complement following aspectual verbs (AspV; e.g. begin, finish) is conceptualized as a structured individual, construed as an axis along various dimensions (e.g. spatial, eventive, temporal, informational). The composition of an animate subject and an AspV such as (1) engenders an ambiguity between an agentive reading along the eventive dimension like (2), and a constitutive reading along the informational/spatial dimension like (3) “[The story of the queen] began the book,” in which the subject is interpreted as a subpart of the complement denotation. Comprehenders need to resolve the ambiguity by searching contextual information, resulting in additional cost. To evaluate the SI hypothesis, a questionnaire was employed. Method: Target AspV sentences such as “Shakespeare began the volume.” were preceded by one of the following types of context sentence: (A) Agentive-biasing, in which an event was mentioned (…writers often read…), (C) Constitutive-biasing, in which a constitutive meaning was hinted (Larry owns collections of Renaissance literature.), (N) Neutral context, which allowed both interpretations. Thirty-nine native speakers of English were asked to (i) rate each context-target sentence pair from a 1~5 scale (5=fully understandable), and (ii) choose possible interpretations for the target sentence given the context. The SI hypothesis predicts that comprehension is harder for the Neutral condition, as compared to the biasing conditions because no contextual information is provided to resolve an ambiguity. Also, comprehenders should obtain the specific interpretation corresponding to the context type. Results: (A) Agentive-biasing and (C) Constitutive-biasing were rated higher than (N) Neutral conditions (p< .001), while all conditions were within the acceptable range (> 3.5 on the 1~5 scale). This suggests that when lacking relevant contextual information, semantic ambiguity decreases comprehensibility. The interpretation task shows that the participants selected the biased agentive/constitutive reading for condition (A) and (C) respectively. For the Neutral condition, the agentive and constitutive readings were chosen equally often. Conclusion: These findings support the SI hypothesis: the meaning of AspV sentences is conceptualized as a parthood relation involving structured individuals. We argue that semantic representation makes reference to spatial structured-ness (abstracted axis). To obtain an appropriate interpretation, comprehenders utilize contextual information to enrich the conceptual representation of the sentence in question. This study connects semantic structure to human’s conceptual structure, and provides a processing model that incorporates contextual retrieval.

Keywords: ambiguity resolution, contextual retrieval, spatial structured-ness, structured individual

Procedia PDF Downloads 303