Search results for: machine language

Authors: Houda Zouar, Hanane Sarnou

Abstract:

In the 21st, century the concept of learners' autonomy is crucial. The concept of self-regulated learning has come forward as a result of enabling learners to direct their learning with autonomy towards academic goals achievement. Academic self-regulation is defined as the process by which learners systematically plan, monitor and asses their learning to achieve their academic established goals. In the field of English as a foreign language, teachers emphasise the role of learners’ autonomy to foster the process of English language learning. Consequently, academic self-regulation is considered as a vehicle to enhance autonomy among English language learners. However, not all learners can be equally self-regulators if not well assisted, mainly those novice pupils of basic education. For this matter, understanding the role of teachers in fostering academic self- regulation must be among the preliminary objectives in searching and developing this area. The present research work targets the role of the Algerian middle school teachers in enhancing academic self-regulation and teaching pupils how to learn, besides their role as models in the trajectory of teaching their pupils to become self-regulators. Despite the considerable endeavours in the field of educational setting on Self-Regulated Learning, the literature of the Algerian context indicates confined endeavours to undertake and divulge this notion. To go deeper into this study, a mixed method approach was employed to confirm our hypothesis. For data collection, teachers were observed and addressed by a questionnaire on their role in enhancing academic self- regulation among their pupils. The result of the research indicates that the attempts of middle school Algerian teachers are implicit and limited. This study emphasises the need to prepare English language teachers with the necessary skills to promote autonomous and self-regulator English learners.

Keywords: Algeria, English as a foreign language, middle school, self-regulation, Teachers' role

Procedia PDF Downloads 140

Authors: Yaojun Wang, Yaoqing Wang

Abstract:

Stock selection is an important decision-making problem. Many machine learning and data mining technologies are employed to build automatic stock-selection system. A profitable stock-selection system should consider the stock’s investment value and the market timing. In this paper, we present a hybrid system including both engage for stock selection. This system uses a case-based reasoning (CBR) model to execute the stock classification, uses a decision-tree model to help with market timing and stock selection. The experiments show that the performance of this hybrid system is better than that of other techniques regarding to the classification accuracy, the average return and the Sharpe ratio.

Keywords: case-based reasoning, decision tree, stock selection, machine learning

Procedia PDF Downloads 415

Authors: Sharon Truter, Ann B. Shuttleworth-Edwards

Abstract:

South Africa is a developing country with significant diversity in languages spoken and quality of education available, creating challenges for fair and accurate neuropsychological assessments when most available neuropsychological tests are obtained from English-speaking developed countries. The aim of this research was to compare normative data on a spectrum of commonly used neuropsychological tests for English- and Afrikaans-speaking South Africans with relatively high quality of education and South Africans with relatively low quality of education who speak Afrikaans, Sesotho, Setswana, Sepedi, Tsonga, Venda, Xhosa or Zulu. The participants were all healthy adults aged 18-60 years, with 8-12 years of education. All the participants were tested in their first language on the following tests: two non-verbal tests (Rey Osterrieth Complex Figure Test and Bell Cancellation Test), four verbal fluency tests (category, phonemic, verb and 'any words'), one verbal learning test (Rey Auditory Verbal Leaning Test) and three tests that have a verbal component (Trail Making Test A & B; Symbol Digit Modalities Test and Digit Span). Descriptive comparisons of mean scores and standard deviations across the language groups and between the groups with relatively high versus low quality of education highlight the importance of using normative data that takes into account language and quality of education.

Keywords: cross-cultural, language, multi-lingual, neuropsychological testing, quality of education

Procedia PDF Downloads 162

Authors: Yuanqing Li, Changyi Lei, Zhaopeng Xue, Zhuo Zheng, Yanbo Long

Abstract:

In agricultural production and breeding, implementing automatic picking robot in orchard farming to reduce human labour and error is challenging. The core function of it is automatic identification based on machine vision. This paper focuses on apple detection and counting in orchards and implements several deep learning methods. Extensive datasets are used and a semi-automatic annotation method is proposed. The proposed deep learning models are in state-of-the-art YOLO family. In view of the essence of the models with various backbones, a multi-dimensional comparison in details is made in terms of counting accuracy, mAP and model memory, laying the foundation for realising automatic precision agriculture.

Keywords: agricultural object detection, deep learning, machine vision, YOLO family

Procedia PDF Downloads 193

Authors: N. Soli, B. Chaouachi, M. Bourouis

Abstract:

We propose in this work the thermodynamic feasibility study of the operation of a refrigerating machine with absorption-diffusion with mixtures of hydrocarbons. It is for a refrigerating machine of low power (300 W) functioning on a level of temperature of the generator lower than 150 °C (fossil energy or solar energy) and operative with non-harmful fluids for the environment. According to this study, we determined to start from the digraphs of Oldham of the different binary of hydrocarbons, the minimal and maximum temperature of operation of the generator, as well as possible enrichment. The cooling medium in the condenser and absorber is done by the ambient air with a temperature at 35 °C. Helium is used as inert gas. The total pressure in the cycle is about 17.5 bars. We used suitable software to modulate for the two binary following the system propylene /butane and propylene/pentane. Our model is validated by comparison with the literature’s resultants.

Keywords: absorption, DAR cycle, diffusion, propyléne

Procedia PDF Downloads 271

Authors: Sahar S. Moursi

Abstract:

Due to the unique background of the Saudi female international students who study in western institutes, they face tough challenges as English as a second language (ESL) learners. This paper draws on a Ph.D. study that examines a wide range of challenges faced by Saudi female international students when they study the English language and other academic subjects in a new culture. This research project followed the phenomenological approach and, more specifically, used the in-depth interview to provide an opportunity to the seven female participants to make their voices heard through telling their stories. The data analysis indicated that the Saudi female international students who study in western institutes are faced with religious and cultural challenges that impact their academic performance. This study is significant for the authorities in Saudi Arabia and the hosting universities as it gives essential recommendations to both sides of the aisle. It also provides the Saudi female international students with vital recommendations to better cope with those challenges.

Keywords: English language learners, religious and cultural background, Saudi female students, tough challenges

Procedia PDF Downloads 167

Authors: Stuart Noel

Abstract:

In a streetcar Named Desire, Tennessee Williams presents Blanche DuBois, a most complex and intriguing character who often uses prestige language to project the image of an upper-class speaker and to disguise her darker and complicated self. She embodies various fascinating and contrasting characteristics. Like New Orleans (the locale of the play), Blanche represents two opposing images. One image projects that of genteel, Southern charm and beauty, speaking formally and using prestige language and what some linguists refer to as “hypercorrection,” and the other image reveals that of a soiled, deteriorating façade, full of decadence and illusion. Williams said on more than one occasion that Blanche’s use of such language was a direct reflection of her personality and character (as a high school English teacher). Prestige language is an exaggeratedly elevated, pretentious, and oftentimes melodramatic form of one’s language incorporating superstandard or more standard speech than usual in order to project a highly authoritative individual identity. Speech styles carry personal identification meaning not only because they are closely associated with certain social classes but because they tend to be associated with certain conversational contexts. Features which may be considered to be “elaborated” in form (for example, full forms vs. contractions) tend to cluster together in speech registers/styles which are typically considered to be more formal and/or of higher social prestige, such as academic lectures and news broadcasts. Members of higher social classes have access to the elaborated registers which characterize formal writings and pre-planned speech events, such as lectures, while members of lower classes are relegated to using the more economical registers associated with casual, face-to-face conversational interaction, since they do not participate in as many planned speech events as upper-class speakers. Tennessee Williams’s work is characteristically concerned with the conflict between the illusions of an individual and the reality of his/her situation equated with a conflict between truth and beauty. An examination of Blanche DuBois reveals a recurring theme of art and decay and the use of prestige language to reveal artistry in language and to hide a deteriorating self. His graceful and poetic writing personifies her downfall and deterioration. Her loneliness and disappointment are the things so often strongly feared by the sensitive artists and heroes in the world. Hers is also a special and delicate human spirit that is often misunderstood and repressed by society. Blanche is afflicted with a psychic illness growing out of her inability to face the harshness of human existence. She is a sensitive, artistic, and beauty-haunted creature who is avoiding her own humanity while hiding behind her use of prestige language. And she embodies a partial projection of Williams himself.

Keywords: American drama, prestige language, Southern American literature, Tennessee Williams

Procedia PDF Downloads 368

Authors: Jui-Chien Wang

Abstract:

Because of China’s continued economic growth and dominance, increasingly many students of Chinese from western countries are interested in pursuing careers related to China. Unless we do more to teach them about contemporary Chinese society and Chinese cultural codes, however, few will be able to do so successfully. Most traditional language textbooks treat these topics only cursorily, and, because of the rapid pace of China’s social and economic development, what they do cover is frequently outdated and insufficient. However, understanding contemporary Chinese society and Chinese cultural codes is essential to successfully negotiating real-world China. The current paper details one of the main ways in which the presenter has dealt with this educational lacuna: the development and implementation of a series of teaching modules for advanced Chinese language classes. Each module explores a particular area, provides resources, and raises questions to engage students in strengthening their language and cultural competencies. The teaching modules address four main areas: (1) Chinese behavioral culture; (2) critical issues in contemporary China; (3) current events in China; and (4) great social transformations in contemporary China. The presenter will also discuss lessons learned and insights gained during the development and implementation process as well as the benefits of using these modules. In addition, the presenter will offer suggestions for the application of these modules, so that other language teachers will be able to make better use of them in their own classrooms.

Keywords: behavioral culture, contemporary Chinese society, cultural code, teaching module

Procedia PDF Downloads 262

Authors: Rim Bouhaouel, Naoufel Kraïem, Zuhoor Al Khanjari

Abstract:

Unified Modeling Language (UML) is considered as one of the widespread modeling language standardized by the Object Management Group (OMG). Therefore, the model driving engineering (MDE) community attempts to provide reuse of UML diagrams, and do not construct it from scratch. The UML model appears according to a specific software development process. The existing method generation models focused on the different techniques of transformation without considering the development process. Our work aims to construct an UML component from fragments of UML diagram basing on an agile method. We define UML fragment as a portion of a UML diagram, which express a business target. To guide the generation of fragments of UML models using an agile process, we need a flexible approach, which adapts to the agile changes and covers all its activities. We use the software product line (SPL) to derive a fragment of process agile method. This paper explains our approach, named RECUP, to generate UML fragments following an agile process, and overviews the different aspects. In this paper, we present the approach and we define the different phases and artifacts.

Keywords: UML, component, fragment, agile, SPL

Procedia PDF Downloads 393

Authors: Newton Muhury, Armando A. Apan, Tek Maraseni

Abstract:

This study modelled the relationships between vegetation response and available water below the soil surface using the Terra’s Moderate Resolution Imaging Spectroradiometer (MODIS) generated Normalised Difference Vegetation Index (NDVI) and soil water content (SWC) data. The Soil & Water Assessment Tool (SWAT) interface known as ArcSWAT was used in ArcGIS for the groundwater analysis. The SWAT model was calibrated and validated in SWAT-CUP software using 10 years (2001-2010) of monthly streamflow data. The average Nash-Sutcliffe Efficiency during the calibration and validation was 0.54 and 0.51, respectively, indicating that the model performances were good. Twenty years (2001-2020) of monthly MODIS NDVI data for three different types of vegetation (forest, shrub, and grass) and soil water content for 43 sub-basins were analysed using the WEKA, machine learning tool with a selection of two supervised machine learning algorithms, i.e., support vector machine (SVM) and random forest (RF). The modelling results show that different types of vegetation response and soil water content vary in the dry and wet season. For example, the model generated high positive relationships (r=0.76, 0.73, and 0.81) between the measured and predicted NDVI values of all vegetation in the study area against the groundwater flow (GW), soil water content (SWC), and the combination of these two variables, respectively, during the dry season. However, these relationships were reduced by 36.8% (r=0.48) and 13.6% (r=0.63) against GW and SWC, respectively, in the wet season. On the other hand, the model predicted a moderate positive relationship (r=0.63) between shrub vegetation type and soil water content during the dry season, which was reduced by 31.7% (r=0.43) during the wet season. Our models also predicted that vegetation in the top location (upper part) of the sub-basin is highly responsive to GW and SWC (r=0.78, and 0.70) during the dry season. The results of this study indicate the study region is suitable for seasonal crop production in dry season. Moreover, the results predicted that the growth of vegetation in the top-point location is highly dependent on groundwater flow in both dry and wet seasons, and any instability or long-term drought can negatively affect these floodplain vegetation communities. This study has enriched our knowledge of vegetation responses to groundwater in each season, which will facilitate better floodplain vegetation management.

Keywords: ArcSWAT, machine learning, floodplain vegetation, MODIS NDVI, groundwater

Procedia PDF Downloads 111

Authors: Eva Tolmeijer, Emmanuelle Peters, Veena Kumari, Liam Mason

Abstract:

Cognitive behavioral therapy for psychosis (CBTp) is effective in many but not all patients, making it important to better understand the factors that determine treatment outcomes. To date, no studies have examined whether neuroimaging can make clinically useful predictions about who will respond to CBTp. To this end, we used machine learning methods that make predictions about symptom improvement at the individual patient level. Prior to receiving CBTp, 22 patients with a diagnosis of schizophrenia completed a social-affective processing task during functional MRI. Multivariate pattern analysis assessed whether treatment response could be predicted by brain activation responses to facial affect that was either socially threatening or prosocial. The resulting models did significantly predict symptom improvement, with distinct multivariate signatures predicting psychotic (r=0.54, p=0.01) and affective (r=0.32, p=0.05) symptoms. Psychotic symptom improvement was accurately predicted from relatively focal threat-related activation across hippocampal, occipital, and temporal regions; affective symptom improvement was predicted by a more dispersed profile of responses to prosocial affect. These findings enrich our understanding of the neurobiological underpinning of treatment response. This study provides a foundation that will hopefully lead to greater precision and tailoring of the interventions offered to patients.

Keywords: cognitive behavioral therapy, machine learning, psychosis, schizophrenia

Procedia PDF Downloads 273

Authors: Ahmed Mohamed Al-Abdali

Abstract:

Providing English for Specific Purposes (ESP) courses that are more closely geared to the learners’ needs and requirements in their fields of study undoubtedly enhance learners’ interest and success in a highly academic environment. While needs analysis is crucial to the success of ESP courses, it has not received sufficient attention from researchers in the Arab world. Oman is no exception from the Arab countries as this fact is realised in the ESP practices in the Omani higher educational context. This presentation, however, discusses the perceptions of the Language Centre (LC) students at Sultan Qaboos University (SQU), Oman, in relation to the requirements of their science colleges. The discussion of the presentation will be based on a mixed-method-approach study, which included semi-structured interviews, questionnaires and document analyses. These mixed methods have allowed for closer investigation of the participants' views, backgrounds and experiences. It is hoped that the findings of this study will be used to recommend changes to the ESP curriculum in the LC of SQU so that it better meets the needs of its students and requirements of the science colleges.

Keywords: curriculum, ESP, ELT, needs analysis, college requirements

Procedia PDF Downloads 316

Authors: Maryam Maimota

Abstract:

Words are the basic building blocks of a language. In everyday usage of a language, words are used and new words are formed and reformed in order to contain and accommodate all entities, phenomena, qualities and every aspect of the entire human life. This research study seeks to examine and compare some of the word formation processes and how they are used in forming new words in English and Hausa languages. The study focuses its main attention on blending and compounding as word formation processes and how the processes are used adequately in the formation of words in both English and Hausa languages. The research aims to find out, how compounding and blending are used, as processes of word formation in these two languages. And also, to investigate the word formation processes involved in compounding and blending in these languages, and the nature of words that are formed. Therefore, the research tries to find the answers to the following research questions; What types of compound and blended forms are found and how they are formed in the English and Hausa languages? How these compounded and blended forms functioned in both English and Hausa languages in different context such as in phrases and sentences structures? Findings of the study reveal that, there exist new kind of words formed in Hausa and English language under blending, which previous findings did not either reveal or explain in detail. Similarly, there are a lot of similarities found in the way these blends and compounds forms in the two languages, however, the data available shows that, blends in the Hausa language are more, when compared to the blends in English. The data of this study will be gathered based on discourse found in newspaper, articles, novels, and written literature of the Hausa and English languages.

Keywords: blending, compounding, morphology, word formation

Procedia PDF Downloads 377

Authors: Fares Hedayatit, Arnauld Joly, Panagiotis Papadimitriou

Abstract:

Many machine learning tasks such as text annotation usually require training over very big datasets, e.g., millions of web documents, that can be represented in a sparse input space. State-of the-art tree-based ensemble algorithms cannot scale to such datasets, since they include operations whose running time is a function of the input space size rather than a function of the non-zero input elements. In this paper, we propose an efficient splitting algorithm to leverage input sparsity within decision tree methods. Our algorithm improves training time over sparse datasets by more than two orders of magnitude and it has been incorporated in the current version of scikit-learn.org, the most popular open source Python machine learning library.

Keywords: big data, sparsely representable data, tree-based models, scalable learning

Procedia PDF Downloads 259

Authors: Muhammad Saleem

Abstract:

The research paper entitled above would be a comprehensive and critical study of translations of the meanings of the Holy Qur’an. The discussion will deal with the targets & purposes of Urdu (National Language of Pakistan) translators of the meanings of the Holy Qur’an. There are more than 400 translations of the meanings of the Holy Qur’an in the Urdu Language. Muslims, non-Muslims and some organizations have made translations of the meanings of the Holy Qur’an to meet various targets. It is observed that all Urdu translators have not translated the Qur’an with a single objective and motivation; rather, some are biased and strive to discredit the Qur’an. Thus, they have made unauthentic and fabricated translations of the Qur’an. Some optimistically believe that they intend to do a service, whereas others pessimistically hold that they treacherously seek to further their rule. Some of them have been observed to be against Islam, starting their activities with spite, but after perceiving the truths of Islam and the miracle and greatness of the Holy Qur’an, they submitted to Islam, embracing it with pure hearts. Some translators made their translations of the meanings of the Holy Qur’an to serve Allah, and some of them have done their translations to earn only. All these translations vary from one to another due to style, trend, type, method and style. Some Urdu translations have been made to fulfill the lingual requirements. Some translations have been made by Muslim scholars to reduce the influence of Urdu translations of the meanings of the Holy Qur’an by Non-Muslims. The article deals with the various purposes of the translators of the meanings of the Holy Qur’an.

Keywords: Qur'an, translation, urdu, language

Procedia PDF Downloads 33

Authors: Ugahara Bin Mahyuddin Yunus

Abstract:

In English Language Teaching, it cannot be denied that the backgrounds of English teachers do affect the way they teach English to their students, which in turn will affect their students’ English learning itself. Thus, it is very important to understand who the English teachers are so that how they teach English to their students can be understood. One of their backgrounds that is essential to be highlighted is their culture. Certainly, they wittingly or not will bring the perspectives and values of their culture into their daily teaching practices. In other words, their cultural identities do shape how they teach their students. Cultural identities themselves actually consist of some elements, one of which is regional identity. Indeed, the culture of the region in which English teachers identify with has impact on their beliefs and actions during teaching. For this reason, this study aims to understand how the regional identity of English teachers influence the way they teach English to their students. This study is a qualitative study conducted in a multilingual and multicultural setting, namely Aceh, Indonesia. Here, four Acehnese English teachers were involved as the research participants. In addition, this study adopted poststructuralist perspective to identity as the theoretical framework. Three research instruments were used in this study, namely semi-structured interviews, classroom observation, and teacher journal. The data gained from these instruments were then analyzed by using thematic analysis. Obviously, the research about the regional identity of English teachers in English Language Teaching has been studied worldwide. However, little is still known about it in Indonesian context, let alone Indonesia itself is a super diverse country with 34 regions. As a result, this study presents a good opportunity to advance the knowledge of how the regional identity construction of English teachers in this setting is. The findings of the study revealed that their regional identity construction in teaching was highly influenced by their indigenous language and religious faith. Even, how they teach English in classroom, in fact, is related to these two things. The conclusion that can be drawn from this study is for these English teachers, in fact, their regional identity itself constitutes their use of local language and religious identity, which are considered by them as their core identity.

Keywords: English language teaching, English teachers, identity construction, regional identity

Procedia PDF Downloads 242

Authors: Bruno Trstenjak, Dzenana Donko

Abstract:

Data mining and classification of objects is the process of data analysis, using various machine learning techniques, which is used today in various fields of research. This paper presents a concept of hybrid classification model improved with the expert knowledge. The hybrid model in its algorithm has integrated several machine learning techniques (Information Gain, K-means, and Case-Based Reasoning) and the expert’s knowledge into one. The knowledge of experts is used to determine the importance of features. The paper presents the model algorithm and the results of the case study in which the emphasis was put on achieving the maximum classification accuracy without reducing the number of features.

Keywords: case based reasoning, classification, expert's knowledge, hybrid model

Procedia PDF Downloads 365

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 114

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 68

Authors: Huan Ting Liao

Abstract:

In a typical manufacturing environment, computer numerical control (CNC) machining is essential for automating production through precise computer-controlled tool operations, significantly enhancing efficiency and ensuring consistent product quality. However, traditional CNC production lines often rely on manual loading and unloading, limiting operational efficiency and scalability. Although automated loading systems have been developed, they frequently lack sufficient intelligence and configuration efficiency, requiring extensive setup adjustments for different products and impacting overall productivity. This research addresses the job shop scheduling problem (JSSP) in CNC machining environments, aiming to minimize total completion time (makespan) and maximize CNC machine utilization. We propose a novel approach using reinforcement learning (RL), specifically the Q-learning algorithm, to optimize scheduling decisions. The study simulates the JSSP, incorporating robotic arm operations, machine processing times, and work order demand allocation to determine optimal processing sequences. The Q-learning algorithm enhances machine utilization by dynamically balancing workloads across CNC machines, adapting to varying job demands and machine states. This approach offers robust solutions for complex manufacturing environments by automating decision-making processes for job assignments. Additionally, we evaluate various layout configurations to identify the most efficient setup. By integrating RL-based scheduling optimization with layout analysis, this research aims to provide a comprehensive solution for improving manufacturing efficiency and productivity in CNC-based job shops. The proposed method's adaptability and automation potential promise significant advancements in tackling dynamic manufacturing challenges.

Keywords: job shop scheduling problem, reinforcement learning, operations sequence, layout optimization, q-learning

Procedia PDF Downloads 13

Authors: Neha Ahirwar

Abstract:

In the contemporary digital era, the rise of credit card fraud poses a significant threat to both financial institutions and consumers. As fraudulent activities become more sophisticated, there is an escalating demand for robust and effective fraud detection mechanisms. Advanced machine learning algorithms have become crucial tools in addressing this challenge. This paper conducts a thorough examination of the design and evaluation of a credit card fraud detection system, utilizing four prominent machine learning algorithms: random forest, logistic regression, decision tree, and XGBoost. The surge in digital transactions has opened avenues for fraudsters to exploit vulnerabilities within payment systems. Consequently, there is an urgent need for proactive and adaptable fraud detection systems. This study addresses this imperative by exploring the efficacy of machine learning algorithms in identifying fraudulent credit card transactions. The selection of random forest, logistic regression, decision tree, and XGBoost for scrutiny in this study is based on their documented effectiveness in diverse domains, particularly in credit card fraud detection. These algorithms are renowned for their capability to model intricate patterns and provide accurate predictions. Each algorithm is implemented and evaluated for its performance in a controlled environment, utilizing a diverse dataset comprising both genuine and fraudulent credit card transactions.

Keywords: efficient credit card fraud detection, random forest, logistic regression, XGBoost, decision tree

Procedia PDF Downloads 59

Authors: Sabrine Ammar, Mohamed Tahar Bhiri

Abstract:

Automatic planning has a de facto standard language called Planning Domain Definition Language (PDDL) for describing planning problems. It aims to formalize the planning problems described by the concept of state space. PDDL-related dynamic analysis tools, namely planners and validators, are insufficient for verifying and validating PDDL descriptions. Indeed, these tools made it possible to detect errors a posteriori by means of test activity. In this paper, we recommend a formal approach coupling the two languages Event-B and PDDL, for automatic planning. Event-B is used for formal modeling by stepwise refinement with mathematical proofs of planning problems. Thus, this paper proposes a refinement strategy allowing to obtain reliable PDDL descriptions from an ultimate Event-B model correct by construction. The ultimate Event-B model, correct by construction which is supposed to be translatable into PDDL, is automatically translated into PDDL using our MDE Event-B2PDDL tool.

Keywords: code generation, event-b, PDDL, refinement strategy, translation rules

Procedia PDF Downloads 187

Authors: Zahra Alimorad

Abstract:

There is a strong belief that language teachers' actual practices in the classroom context are largely determined by the underlying perceptions they hold about the nature of language and language learning. That being so, it can be envisaged that teaching procedures of ESP (English for Specific Purposes) teachers teaching reading comprehension will mainly be driven by their perceptions about the nature of reading. To examine this issue, four Iranian university professors holding Ph.D. in either TEFL (Teaching English as a Foreign Language) or English Literature who were teaching English to Engineering and Sciences students were recruited to participate in this study. To collect the necessary data, classroom observations and follow-up semi-structured interviews were used. Furthermore, the materials utilized by the teachers such as textbooks, syllabuses, and tests were also examined. Although it can be argued that their perceptions were partially compatible with the established principles, results of the study pointed to a lack of congruence between these teachers' perceptions and their practices, on the one hand, and between the established principles and the practices, on the other. While the literature mostly supports a metacognitive-strategy approach to reading comprehension, the teachers were mainly adopting a skills-based approach to the teaching of reading. That is, they primarily focused on translation as the core activity in the classroom followed by reading aloud, defining words, and explaining grammatical structures. This divergence was partly attributed to the contextual constraints and partly to students' lack of motivation by the teachers.

Keywords: English teachers, perceptions, practice, principles, reading comprehension

Procedia PDF Downloads 250

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 66

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 191

Authors: M. Rilliard

Abstract:

Based on a Multiliteracies-inspired and sociolinguistically-informed advanced French composition class, this study employed autobiographical narratives from speakers traditionally considered non-legitimate models for L2 teaching purposes of inspiring students to develop an authentic L2 voice and to see themselves as legitimate L2 speakers. Students explored their L2 identities in French through a self-inspired fictional character. Two autobiographical narratives of identity quest by non-traditional French speakers provided them guidance through this process: the novel Le Bleu des Abeilles (2013) and the film Qu’Allah Bénisse la France (2014). Written and French oral productions for different genres, as well as metalinguistic reflections in English, were collected and analyzed. Results indicate that ideas and materials that were relatable to students, namely relatable experiences and relatable language, were most useful to them in developing their L2 voices and achieving authentic and legitimate L2 speakership. These results point towards the benefits of using non-traditional speakers as pedagogical models, as they serve to legitimize students’ sense of their own L2-speakership, which ultimately leads them towards a better, more informed, mastery of the language.

Keywords: foreign language classroom, L2 identity, L2 learning and teaching, L2 writing, sociolinguistics

Procedia PDF Downloads 130

Authors: Ioannis Souris

Abstract:

In this paper, we would like to present how we taught German through playwriting and analyze the usefulness of this method for teaching languages and cultivating a sense of political agency in students and teachers alike. Last academic year, we worked at the German Saturday School in Greenwich, London. This school offers Saturday German lessons to children whose parents are German, living in London. The lessons are two hours long, and the children’s level of German varies according to how often or how much German is spoken at home or how often the families visit Germany (as well as other factors which will be discussed in more detail in the paper). The directors of the school provide teachers with learning material and course books, but they strongly encourage individual input on lesson structure and methods of teaching German. The class we taught consisted of six eight-to-nine-year-olds. Midway into the academic year, we ran out of teaching material, and we, therefore, decided to write a play. In the paper, we would like to explore the process we followed in creating or writing this play and how this encouraged the children to collaborate and exercise their skills in writing, storytelling, speaking, and opinion-sharing. We want to examine the impact this project had on the children who wrote and performed the play, the wider community of the Saturday school, and the development of our language teaching practice. We found, for instance, that some students, who were quiet or shy, became very open and outspoken in the process of writing and performing the play. They took the initiative and led the process, putting us, their teachers, in the role of simple observers or facilitators. When we showed the play in front of the school, the other children and teachers, as audience members, also became part of the process as they commented on the plot, language, and characters and gave feedback on further development. In the paper, we will discuss how this teaching project fits into recent developments in the research of creativity and the teaching of languages and how engagement with creative approaches to teaching has the potential to question and subvert traditional notions of ‘lesson’, ‘teacher’, and ‘student’. From the moment a questioning of norms takes place, we inadvertently raise questions about politics, agency, and resistance. We will conclude the paper with a definition of what we mean by ‘political agency’ within the context of our teaching project and education, in general, and why inspiring creativity and imagination within teaching can be considered a political act. Finally, our aim in this paper will be to propose the possibility of analyzing teaching languages through creativity and political agency theories.

Keywords: innovation in language teaching and learning, language acquisition and learning, language curriculum development, language education

Procedia PDF Downloads 79

Authors: Hoora Dehghani, Meisam Shahbazi, Reza Zare

Abstract:

During the previous decade, a significant evolution has occurred in the number of private educational centers and, accordingly, the increase in the number of providers and students of these centers around the world. The number of language teaching institutes in Iran that are considered private educational sectors is also growing exponentially as the request for learning foreign languages has extremely increased in recent years. This fact caused competition among the institutions in improving better services tailored to the students’ demands to win the competition. Along with the growth in the industry of education, higher education institutes should apply the marketing-related concepts and view students as customers because students’ outlooks are similar to consumers with education. Studying the influential factors in the selection of an institute has multiple benefits. Firstly, it acknowledges the institutions of the students’ choice factors. Secondly, the institutions use the obtained information to improve their marketing methods. It also helps institutions know students’ outlooks that can be applied to expand the student know-how. Moreover, it provides practical evidence for educational centers to plan useful amenities and programs, and use efficient policies to cater to the market, and also helps them execute the methods that increase students’ feeling of contentment and assurance. Thus, this study explored the influencing factors in the selection of a language learning institute by language learners and examined and compared the importance among the varying age groups and genders. In the first phase of the study, the researchers selected 15 language learners as representative cases within the specified age ranges and genders purposefully and interviewed them to explore the comprising elements in their language institute selection process and analyzed the results qualitatively. In the second phase, the researchers identified elements as specified items of a questionnaire, and 1000 English learners across varying educational contexts rated them. The TOPSIS method was used to analyze the data quantitatively by representing the level of importance of the items for the participants generally and specifically in each subcategory; genders and age groups. The results indicated that the educational quality, teaching method, duration of training course, establishing need-oriented courses, and easy access were the most important elements. On the other hand, offering training in different languages, the specialized education of only one language, the uniform and appropriate appearance of office staff, having native professors to the language of instruction, applying Computer or online tests instead of the usual paper tests respectively as the least important choice factors in selecting a language institute. Besides, some comparisons among different groups’ ratings of choice factors were made, which revealed the differences among different groups' priorities in choosing a language institute.

Keywords: choice factors, EFL institute selection, english learning, need analysis, TOPSIS

Procedia PDF Downloads 162

Authors: Waqas Ahmed Khan Afridi, Subhas Chandra Mukhopadhyay, Bandita Mainali

Abstract:

The research paper presents a unique approach to evapotranspiration (ET) prediction using a Support Vector Machine (SVM) learning algorithm. The study leverages real-time sensor node data to develop an accurate and adaptable prediction model, addressing the inherent challenges of traditional ET estimation methods. The integration of the SVM algorithm with real-time sensor node data offers great potential to improve spatial and temporal resolution in ET predictions. In the model development, key input features are measured and computed using mathematical equations such as Penman-Monteith (FAO56) and soil water balance (SWB), which include soil-environmental parameters such as; solar radiation (Rs), air temperature (T), atmospheric pressure (P), relative humidity (RH), wind speed (u2), rain (R), deep percolation (DP), soil temperature (ST), and change in soil moisture (∆SM). The one-year field data are split into combinations of three proportions i.e. train, test, and validation sets. While kernel functions with tuning hyperparameters have been used to train and improve the accuracy of the prediction model with multiple iterations. This paper also outlines the existing methods and the machine learning techniques to determine Evapotranspiration, data collection and preprocessing, model construction, and evaluation metrics, highlighting the significance of SVM in advancing the field of ET prediction. The results demonstrate the robustness and high predictability of the developed model on the basis of performance evaluation metrics (R2, RMSE, MAE). The effectiveness of the proposed model in capturing complex relationships within soil and environmental parameters provide insights into its potential applications for water resource management and hydrological ecosystem.

Keywords: evapotranspiration, FAO56, KNIME, machine learning, RStudio, SVM, sensors

Procedia PDF Downloads 61

Authors: Afia Shahid

Abstract:

The writing of Samuel Beckett is associated with meaning in the meaninglessness and the production of what he calls ‘literature of unword’. The casual escape from the world of words in the form of silences and pauses, in his play Waiting for Godot, urges to ask question of their existence and ultimately leads to investigate the theory behind their use in the play. This paper proposes that these absences (silence and pause) in Beckett’s play force to think ‘beyond’ language. This paper asks how silence and pause in Beckett’s text speak for the emergence of poststructuralist text. It aims to identify the significant features of the philosophy of deconstruction in the play of Beckett to demystify the hostile complicity between literature and philosophy. With the interpretive paradigm of poststructuralism this research focuses on the text as a research data. It attempts to delineate the relationship between poststructuralist theoretical concerns and text of Beckett. Keeping in view the theoretical concerns of Poststructuralist theorist Jacques Derrida, the main concern of the discussion is directed towards the notion of ‘beyond’ language into the absences that are aimed at silencing the existing discourse with the ‘radical irony’ of this anti-formal art that contains its own denial and thus represents the idea of ceaseless questioning and radical contradiction in art and any text. This article asks how text of Beckett vibrates with loud silence and has disrupted language to demonstrate the emptiness of words and thus exploring the limitless void of absences. Beckett’s text resonates with silence and pause that is neither negation nor affirmation rather a poststructuralist’s suspension of reality that is ever changing with the undecidablity of all meanings. Within the theoretical notion of Derrida’s Différance this study interprets silence and pause in Beckett’s art. The silence and pause behave like Derrida’s Différance and have questioned their own existence in the text to deconstruct any definiteness and finality of reality to extend an undecidable threshold of poststructuralists that aims to evade the ‘labyrinth of language’.

Keywords: Différance, language, pause, poststructuralism, silence, text

Procedia PDF Downloads 206