Search results for: reasoning gap tasks

Authors: Qitao Xie, Qingquan Zhang, Xiaofei Zhang, Di Tian, Ruixuan Wen, Ting Zhu, Ping Yi, Xin Li

Abstract:

Inspired by the recent movement of digital currency, we are building a question answering system concerning the subject of cryptocurrency using Bidirectional Encoder Representations from Transformers (BERT). The motivation behind this work is to properly assist digital currency investors by directing them to the corresponding knowledge bases that can offer them help and increase the querying speed. BERT, one of newest language models in natural language processing, was investigated to improve the quality of generated responses. We studied different combinations of hyperparameters of the BERT model to obtain the best fit responses. Further, we created an intelligent chatbot for cryptocurrency using BERT. A chatbot using BERT shows great potential for the further advancement of a cryptocurrency market tool. We show that the BERT neural networks generalize well to other tasks by applying it successfully to cryptocurrency.

Keywords: bidirectional encoder representations from transformers, BERT, chatbot, cryptocurrency, deep learning

Procedia PDF Downloads 132

Authors: Salima Behdenna, Fatiha Barigou, Ghalem Belalem

Abstract:

Due to the quick increase in the volume of Arabic opinions posted on various social media, Arabic sentiment analysis has become one of the most important areas of research. Compared to English, there is very little works on Arabic sentiment analysis, in particular aspect-based sentiment analysis (ABSA). In ABSA, aspect extraction is the most important task. In this paper, we propose a semantic aspect-based sentiment analysis approach for standard Arabic reviews to extract explicit aspect terms and identify the polarity of the extracted aspects. The proposed approach was evaluated using HAAD datasets. Experiments showed that the proposed approach achieved a good level of performance compared with baseline results. The F-measure was improved by 19% for the aspect term extraction tasks and 55% aspect term polarity task.

Keywords: sentiment analysis, opinion mining, Arabic, aspect level, opinion, polarity

Procedia PDF Downloads 148

Authors: M. L. McLain, R. Sreelakshmi, Abhishek, Rajeshwaran, Bhavani Rao, Kamal Bijlani, R. Jayakrishnan

Abstract:

Technology enhanced learning has brought drastic changes in the field of education in the modern world. In this study we explore a novel way to improve how high school students learn by building a serious game that uses a pedagogical model developed by Robert Gagne. By integrating serious game with principles of Gagne’s learning model can provide engaging and meaningful instructions to students. The game developed in this study is a waste sorting game that can easily and succinctly demonstrate the principles of this learning model. All the tasks in the game that the player has to accomplish correspond to Gagne’s “Nine Events of Learning”. A quiz is incorporated in order to get data on the progress made by the player in understanding the concept and as well as to assess them. Additionally, an experimental study was conducted which demonstrates that game based learning using Gagne’s event is more effective than a traditional classroom setup.

Keywords: game based learning, sorting and recycling of waste, Gagne’s learning model, e-Learning, technology enhanced learning

Procedia PDF Downloads 620

Authors: Ridzuan Hussin, Mohd Zaihidee Arshad

Abstract:

The creativity of earlier artists and sculptors in designing geometric is extraordinary provided with only a compass. Indeed, geometric in Islamic art and design are unique and have their own aesthetic values. In order to further understand geometric, self-learning with the approach of hands on would be appropriate. For this study, Islamic themed geometric designed and created, concerning only; i. The Square Repetition Unit and √2, ii. The Hexagonal Repetition Unit and √3 and iii. Double Hexagon. The aim of this research is to evaluate the creativity of Islamic geometric pattern artworks, through Fundamental Arts and Gestalt theory. Data was collected using specific tasks, and this research intends to identify the difference of Islamic geometric between 21 untitled selected geometric artworks (conventional design method), and 25 digital untitled geometric pattern artworks method. The evaluation of creativity, colors, layout, pattern and unity is known to be of utmost importance, although there are differences in the conventional or the digital approach.

Keywords: Islamic geometric design, Gestalt, fundamentals of art, patterns

Procedia PDF Downloads 233

Authors: Reem AlKabbi, Hayat Ali, Mariam Yasser

Abstract:

Nowadays, eGovernment websites are becoming indispensable for public, business, personal efficiency or even improvement of livelihoods. Using these websites, citizens undertake number of tasks that would otherwise be difficult or impossible. However, many of these websites are not accessible to all people' types including People with Disabilities (PWDs). Through Web Accessibility Guidelines, Web developers can develop Web applications that are accessible to PWDs. This research is to investigate the Accessibility of eGovernment websites in Kingdom of Bahrain. The accessibility was measured using Web Content Accessibility Guidelines (WCAG) and section 508. For the evaluation purpose, some automatic tools were used. Samples of 43 eGovernment websites were selected. The accessibility of the websites was analyzed by using several automatic evaluation tools such as Total Validator and Functional Accessibility Evaluator (FAE). The evaluation process revealed several errors according to the accessibility guidelines. This research provides few recommendations for further improvement of accessibility features of eGovernment websites based on the highlighted issues and key findings reported in this research.

Keywords: website accessibility, W3C, PWD, e-government

Procedia PDF Downloads 434

Authors: O. Gubnitsyna, O. Zakoretskaya, O. Russova

Abstract:

It is generally recognized that the main task of modern society is human development. The quality of human capital has been identified as a key driver of economic development in the region. In this article, considered the quality of human capital as one of the main types of social and economic potential for the region’s development. The phenomenon of human capital represents both material and intellectual components of human activity. It is show that the necessary population characterized by certain quantitative and qualitative indicators (qualification and professional structure, education or social general condition and others) and is an necessary resource for the development of the regional economy. The connection of the regional goals with the quality of human capital is discussed in the article and a number of recommendations on its improvement were given. Solving the tasks stated in the article, the authors used analytical and statistical methods of research, scientific publications of domestic and foreign scientists on this issue. The results can be used in this implementation of the concept of regional development.

Keywords: human capital, the quality of human capital, economic development, social general condition

Procedia PDF Downloads 277

Authors: Musaab Riyadh, Norwati Mustapha, Dina Riyadh

Abstract:

Trajectory similarity can be defined as the cost of transforming one trajectory into another based on certain similarity method. It is the core of numerous mining tasks such as clustering, classification, and indexing. Various approaches have been suggested to measure similarity based on the geometric and dynamic properties of trajectory, the overlapping between trajectory segments, and the confined area between entire trajectories. In this article, an evaluation of these approaches has been done based on computational cost, usage memory, accuracy, and the amount of data which is needed in advance to determine its suitability to stream mining applications. The evaluation results show that the stream mining applications support similarity methods which have low computational cost and memory, single scan on data, and free of mathematical complexity due to the high-speed generation of data.

Keywords: global distance measure, local distance measure, semantic trajectory, spatial dimension, stream data mining

Procedia PDF Downloads 385

Authors: Yixin Zhu, Lishengsa Yue, Jian Sun, Lanyue Tang

Abstract:

Modeling driving distraction in microscopic traffic simulation is crucial for enhancing simulation accuracy. Current driving distraction models are mainly derived from physical motion constraints under distracted states, in which distraction-related error terms are added to existing microscopic driver models. However, the model accuracy is not very satisfying, due to a lack of modeling the cognitive mechanism underlying the distraction. This study models driving distraction based on the Queueing Network Human Processor model (QN-MHP). This study utilizes the queuing structure of the model to perform task invocation and switching for distracted operation and control of the vehicle under driver distraction. Based on the assumption of the QN-MHP model about the cognitive sub-network, server F is a structural bottleneck. The latter information must wait for the previous information to leave server F before it can be processed in server F. Therefore, the waiting time for task switching needs to be calculated. Since the QN-MHP model has different information processing paths for auditory information and visual information, this study divides driving distraction into two types: auditory distraction and visual distraction. For visual distraction, both the visual distraction task and the driving task need to go through the visual perception sub-network, and the stimuli of the two are asynchronous, which is called stimulus on asynchrony (SOA), so when calculating the waiting time for switching tasks, it is necessary to consider it. In the case of auditory distraction, the auditory distraction task and the driving task do not need to compete for the server resources of the perceptual sub-network, and their stimuli can be synchronized without considering the time difference in receiving the stimuli. According to the Theory of Planned Behavior for drivers (TPB), this study uses risk entropy as the decision criterion for driver task switching. A logistic regression model is used with risk entropy as the independent variable to determine whether the driver performs a distraction task, to explain the relationship between perceived risk and distraction. Furthermore, to model a driver’s perception characteristics, a neurophysiological model of visual distraction tasks is incorporated into the QN-MHP, and executes the classical Intelligent Driver Model. The proposed driving distraction model integrates the psychological cognitive process of a driver with the physical motion characteristics, resulting in both high accuracy and interpretability. This paper uses 773 segments of distracted car-following in Shanghai Naturalistic Driving Study data (SH-NDS) to classify the patterns of distracted behavior on different road facilities and obtains three types of distraction patterns: numbness, delay, and aggressiveness. The model was calibrated and verified by simulation. The results indicate that the model can effectively simulate the distracted car-following behavior of different patterns on various roadway facilities, and its performance is better than the traditional IDM model with distraction-related error terms. The proposed model overcomes the limitations of physical-constraints-based models in replicating dangerous driving behaviors, and internal characteristics of an individual. Moreover, the model is demonstrated to effectively generate more dangerous distracted driving scenarios, which can be used to construct high-value automated driving test scenarios.

Keywords: computational cognitive model, driving distraction, microscopic traffic simulation, psychological-physical constraints

Procedia PDF Downloads 73

Authors: Khenfer-Koummich Fatima, Mesbahi Larbi, Hendel Fatiha

Abstract:

This paper presents a recognition system for isolated words like robot commands. It’s carried out by Time Delay Neural Networks; TDNN. To teleoperate a robot for specific tasks as turn, close, etc… In industrial environment and taking into account the noise coming from the machine. The choice of TDNN is based on its generalization in terms of accuracy, in more it acts as a filter that allows the passage of certain desirable frequency characteristics of speech; the goal is to determine the parameters of this filter for making an adaptable system to the variability of speech signal and to noise especially, for this the back propagation technique was used in learning phase. The approach was applied on commands pronounced in two languages separately: The French and Arabic. The results for two test bases of 300 spoken words for each one are 87%, 97.6% in neutral environment and 77.67%, 92.67% when the white Gaussian noisy was added with a SNR of 35 dB.

Keywords: TDNN, neural networks, noise, speech recognition

Procedia PDF Downloads 279

Authors: Britt Erni, Aldara Vazquez Fernandez, Roland Maurer

Abstract:

Visuospatial perspective taking (VSPT) is a process that allows to integrate spatial information from different points of view, and to transform the mental images we have of the environment to properly orient our movements and anticipate the location of landmarks during navigation. VSPT is also related to egocentric perspective transformations (imagined rotations or translations of one's point of view) and to infer the visuospatial experiences of another person (e.g. if and how another person sees objects). This process is deeply related to a wide-ranging capacity called the theory of mind (ToM), an essential cognitive function that allows us to regulate our social behaviour by attributing mental representations to individuals in order to make behavioural predictions. VSPT is often considered in the literature as the starting point of the development of the theory of mind. VSPT and ToM include several levels of knowledge that have to be assessed by specific tasks. Unfortunately, the lack of tasks assessing these functions in clinical neuropsychology leads to underestimate, in brain-damaged patients, deficits of these functions which are essential, in everyday life, to regulate our social behaviour (ToM) and to navigate in known and unknown environments (VSPT). Therefore, this study aims to create and standardize a VSPT task in order to explore the cognitive requirements of VSPT and ToM, and to specify their relationship in healthy adults and thereafter in brain-damaged patients. Two versions of a computerized VSPT task were administered to healthy participants (M = 28.18, SD = 4.8 years). In both versions the environment was a 3D representation of 10 different geometric shapes placed on a circular base. Two sets of eight pictures were generated from this: of the environment with an avatar somewhere on its periphery (locations) and of what the avatar sees from that place (views). Two types of questions were asked: a) identify the location from the view, and b) identify the view from the location. Twenty participants completed version 1 of the task and 20 completed the second version, where the views were offset by ±15° (i.e., clockwise or counterclockwise) and participants were asked to choose the closest location or the closest view. The preliminary findings revealed that version 1 is significantly easier than version 2 for accuracy (with ceiling scores for version 1). In version 2, participants responded significantly slower when they had to infer the avatar's view from the latter's location, probably because they spent more time visually exploring the different views (responses). Furthermore, men significantly performed better than women in version 1 but not in version 2. Most importantly, a sensitive task (version 2) has been created for which the participants do not seem to easily and automatically compute what someone is looking at yet which does not involve more heavily other cognitive functions. This study is further completed by including analysis on non-clinical participants with low and high degrees of schizotypy, different socio-educational status, and with a range of older adults to examine age-related and other differences in VSPT processing.

Keywords: mental transformation, spatial cognition, theory of mind, visuospatial perspective taking

Procedia PDF Downloads 188

Authors: Tom D. Gedeon, Ujala Rampaul

Abstract:

The evaluation of electronic consumer goods are most often done from the perspective of analysing the latest models, comparing their advantages and disadvantages with respect to price. This style of evaluation is often performed by one or a few product experts on a wide range of features that may not be applicable to each user. We instead used a scenario-based approach to evaluate a number of e-readers. The setting is similar to a user who is interested in a new product or technology and has allocated a limited budget. We evaluate the quality and usability of e-readers available within that budget range. This is based on the assumption of a rational market which prices older second hand devices the same as functionally equivalent new devices. We describe our evaluation and comparison of four branded eReaders, as the initial stage of a larger project. The scenario has a range of tasks approximating a busy person who does not bother to read the manual. We found that navigation within books to be the most significant differentiator between the eReaders in our scenario based evaluation process.

Keywords: eReader, scenario based, price comparison, Kindle, Kobo, Nook, Sony, technology adoption

Procedia PDF Downloads 519

Authors: Cheng Chieh Hsu, Alfred Chen, Yu-Pin Ma, Meng-Jie Lin, Fu Pai Chiu, Yi-Yan Sie

Abstract:

In this study, it is attempted to construct an augmented reality display platform (ARDP), and its objectives are two facets, i.e. 1) providing a creative display mode for museums/historical heritages and 2) providing a benchmark for human-computer interaction professionals to build an augmented reality display platform. A general augmented reality theory has been explored in the very beginning and afterwards a systematic process model is proposed. There are three major core tasks to be done for the platform, i.e. 1) constructing the physical interactive table, 2) designing the media, and 3) designing the media carrier. In order to describe how the platform manipulates, the authors have introduced Tainan Confucius Temple, a cultural heritage in Taiwan, as a case study. As a result, a systematic process with thirteen steps has been developed and it aims at providing a rational method for constructing the platform.

Keywords: human-computer interaction, media, media carrier, augmented reality display platform

Procedia PDF Downloads 403

Authors: Najiba Ouled Omar, Azza Harbaoui, Henda Ben Ghezala

Abstract:

Current research practices sentiment analysis with a focus on social networks, DEfi Fouille de Texte (DEFT) (Text Mining Challenge) evaluation campaign focuses on opinion mining and sentiment analysis on social networks, especially social network Twitter. It aims to confront the systems produced by several teams from public and private research laboratories. DEFT offers participants the opportunity to work on regularly renewed themes and proposes to work on opinion mining in several editions. The purpose of this article is to scrutinize and analyze the works relating to opinions mining and sentiment analysis in the Twitter social network realized by DEFT. It examines the tasks proposed by the organizers of the challenge and the methods used by the participants.

Keywords: opinion mining, sentiment analysis, emotion, polarity, annotation, OSEE, figurative language, DEFT, Twitter, Tweet

Procedia PDF Downloads 124

Authors: Asma Rebaya, Imen Amari, Kaouther Gasmi, Salem Hasnaoui

Abstract:

Over these last years, the number of cores witnessed a spectacular increase in digital signal and general use processors. Concurrently, significant researches are done to get benefit from the high degree of parallelism. Indeed, these researches are focused to provide an efficient scheduling from hardware/software systems to multicores architecture. The scheduling process consists on statically choose one core to execute one task and to specify an execution order for the application tasks. In this paper, we describe an efficient scheduler that calculates the optimal number of cores required to schedule an application, gives a heuristic scheduling solution and evaluates its cost. Our proposal results are evaluated and compared with Preesm scheduler results and we prove that ours allows better scheduling in terms of latency, computation time and number of cores.

Keywords: computation time, hardware/software system, latency, optimization, multi-cores platform, scheduling

Procedia PDF Downloads 271

Authors: Michaela Porubanova

Abstract:

In this exploratory study to examine the effects of emotional significance on change detection using the flicker paradigm, three different categories of scenes were randomly presented (neutral, positive and negative) in three different blocks. We hypothesized that because of the different effects on attention, performance in change detection tasks differs for scenes with different effective values. We found the greatest accuracy of change detection was for changes occurring in positive and negative scenes (compared with neutral scenes). Secondly and most importantly, changes in negative scenes (and also positive scenes, though not with statistical significance) were detected faster than changes in neutral scenes. Interestingly, women were less accurate than men in detecting changes in emotionally significant scenes (both negative and positive), i.e., women detected fewer changes in emotional scenes in the time limit of 40s. But on the other hand, women were quicker to detect changes in positive and negative images than men. The study makes important contributions to the area of the role of emotions on information processing. The role of emotion in attention will be discussed.

Keywords: attention, emotion, flicker task, IAPS

Procedia PDF Downloads 341

Authors: Signe Svensson, Remy Rey, Anna-Lisa Osvalder, Henrik Artman, Lars Nordström

Abstract:

The electric power system is undergoing significant changes. Thereby, the operation and control are becoming partly modified, more multifaceted and automated, and thereby supplementary operator skills might be required. This paper discusses developing operational challenges in future power system control rooms, posed by the evolving landscape of sustainable power systems, driven in turn by the shift towards electrification and renewable energy sources. A literature review followed by interviews and a comparison to other related domains with similar characteristics, a descriptive analysis was performed from a human factors perspective. Analysis is meant to identify trends, relationships, and challenges. A power control domain taxonomy includes a temporal domain (planning and real-time operation) and three operational domains within the power system (generation, switching and balancing). Within each operational domain, there are different control actions, either in the planning stage or in the real-time operation, that affect the overall operation of the power system. In addition to the temporal dimension, the control domains are divided in space between a multitude of different actors distributed across many different locations. A control room is a central location where different types of information are monitored and controlled, alarms are responded to, and deviations are handled by the control room operators. The operators’ competencies, teamwork skills, team shift patterns as well as control system designs are all important factors in ensuring efficient and safe electricity grid management. As the power system evolves with sustainable energy technologies, challenges are found. Questions are raised regarding whether the operators’ tacit knowledge, experience and operation skills of today are sufficient to make constructive decisions to solve modified and new control tasks, especially during disturbed operations or abnormalities. Which new skills need to be developed in planning and real-time operation to provide efficient generation and delivery of energy through the system? How should the user interfaces be developed to assist operators in processing the increasing amount of information? Are some skills at risk of being lost when the systems change? How should the physical environment and collaborations between different stakeholders within and outside the control room develop to support operator control? To conclude, the system change will provide many benefits related to electrification and renewable energy sources, but it is important to address the operators’ challenges with increasing complexity. The control tasks will be modified, and additional operator skills are needed to perform efficient and safe operations. Also, the whole human-technology-organization system needs to be considered, including the physical environment, the technical aids and the information systems, the operators’ physical and mental well-being, as well as the social and organizational systems.

Keywords: operator, process control, energy system, sustainability, future control room, skill

Procedia PDF Downloads 73

Authors: Lotfi Beji, Laredj Benchikh

Abstract:

Underground tunnel face bolting and pipe umbrella reinforcement are one of the most challenging tasks in construction whether industrial or not, and infrastructures such as roads or pipelines. It is one of the first sectors of economic activity in the world. Through a variety of soil and rock, a cyclic Conventional Tunneling Method (CTM) remains the best one for projects with highly variable ground conditions or shapes. CTM is the only alternative for the renovation of existing tunnels and creating emergency exit. During the drilling process, a wide variety of non-desired vibrations may arise, and a method using a robot arm is proposed. The main kinds of drilling through vibration here is the bit-bouncing phenomenon (resonant axial vibration). Hence, assisting the task by a robot arm may play an important role on drilling performances and security. We propose to control the axial-vibration phenomenon along the drillstring at a practical resonant frequency, and embed a Resonant Sonic Drilling Head (RSDH) as a robot end effector for drilling. Many questionable industry drilling criteria and stability are discussed in this paper.

Keywords: drilling, resonant vibration, robot arm, control

Procedia PDF Downloads 278

Authors: Jason Digalakis, John Cotronis

Abstract:

Memetic algorithms (MAs) are useful for solving optimization problems. It is quite difficult to search the search space of the optimization problem with large dimensions. There is a challenge to use all the cores of the system. In this study, a sequential implementation of the memetic algorithm is converted into a concurrent version, which is executed on the cores of both CPU and GPU. For this reason, CUDA and OpenMP libraries are operated on the parallel algorithm to make a concurrent execution on CPU and GPU, respectively. The aim of this study is to compare CPU and GPU implementation of the memetic algorithm. For this purpose, fourteen benchmark functions are selected as test problems. The obtained results indicate that our approach leads to speedups up to five thousand times higher compared to one CPU thread while maintaining a reasonable results quality. This clearly shows that GPUs have the potential to acceleration of MAs and allow them to solve much more complex tasks.

Keywords: memetic algorithm, CUDA, GPU-based memetic algorithm, open multi processing, multimodal functions, unimodal functions, non-linear optimization problems

Procedia PDF Downloads 81

Authors: Monika Michałowska, Anna Alichniewicz

Abstract:

Detrimental outcomes of advanced maternal age on the chances of fertilization, pregnancy as well as mother and fetus health have been recognized for several decades. It seemed interesting to investigate whether there is a comparable awareness of the detrimental influence on the reproductive outcomes of late fatherhood, given that it has been already ten years since an intense and growing interest concerning later-age fatherhood commenced in medical research. To address that issue a two-step research was done. First, we performed a review of the subject literature to answer the following questions: 1) What age is defined as advanced?; 2) Is the same age defined as advanced in both genders?; 3) What terminology concerning age issues is used?; 4) Is the same age terminology used regarding both genders? The second part of our studies was devoted to the views of medical students. This part of our research comprised both quantitative and qualitative studies. Opinions of medical students in one of the Polish medical universities on several issues connected with assisted reproduction technology (ART) were gathered: 1) students’ attitude to in vitro fertilization (IVF) for women over 40 and for postmenopausal women; 2) students’ attitude to late fatherhood; 3) students’ reasoning given against acceptability of IVF procedure for all of these group of patients involved in an IVF procedure. Our analyses revealed that: First, there is no universal definition of the term ‘advanced age’; secondly, there is a general tendency to adopt different age limits depending on whether they refer to maternal or paternal age, but no justification is provided by the researchers explaining why they set different age limits for women and men; thirdly, the image of postponed fatherhood stands in stark contrast to postponed motherhood - while postponed fatherhood is frequently portrayed as a reasonable and conscious decision enabling a stable family environment for a child, the reasonableness of postponed motherhood is often questioned; finally, the bias regarding maternal versus paternal age is deeply embedded in medical students’ attitude to IVF for women over 40 and for postmenopausal women.

Keywords: gender stereotypes, reproductive medicine, maternal age, paternal age

Procedia PDF Downloads 256

Authors: Sylvain Devie, Pierre-Philippe Robet, Yannick Aoustin, Maxime Gautier

Abstract:

The aim of this paper is to show that the observation of the external effort and the sensor-less control of a system is limited by the mechanical system. First, the model of a one-joint robot with a prismatic joint is presented. Based on this model, two different procedures were performed in order to identify the mechanical parameters of the system and observe the external effort applied on it. Experiments have proven that the accuracy of the force observer, based on the DC motor current, is limited by the mechanics of the robot. The sensor-less control will be limited by the accuracy in estimation of the mechanical parameters and by the maximum static friction force, that is the minimum force which can be observed in this case. The consequence of this limitation is that industrial robots without specific design are not well adapted to perform sensor-less precision tasks. Finally, an efficient control law is presented for high effort applications.

Keywords: control, identification, robot, co-manipulation, sensor-less

Procedia PDF Downloads 150

Authors: A. Jomartov, A. Tuleshov, B. Tultaev

Abstract:

One of the main tasks in the development of textile machinery is to increase the rapidity of automatic looms, and consequently, their productivity. With increasing automatic loom speeds, the dynamic loads on their separate mechanisms and moving joints sharply increase. Dynamic research allows us to determine the weakest mechanisms of the automatic loom. The modern automatic loom consists of a large number of structurally different mechanisms. These are cam, lever, gear, friction and combined cyclic mechanisms. The modern automatic loom contains various mechatronic devices: A device for the automatic removal of faulty weft, electromechanical drive warp yarns, electronic controllers, servos, etc. In the paper, we consider the multibody dynamic model of the automatic loom on the software complex SimulationX. SimulationX is multidisciplinary software for modeling complex physical and technical facilities and systems. The multibody dynamic model of the automatic loom allows consideration of: The transition processes, backlash at the joints and nodes, the force of resistance and electric motor performance.

Keywords: automatic loom, dynamics, model, multibody, SimulationX

Procedia PDF Downloads 335

Authors: Sara Rejeb, Catherine Duveau, Tabea Rebafka

Abstract:

To monitor the production process of turbofan aircraft engines, multiple measurements of various geometrical parameters are systematically recorded on manufactured parts. Engine parts are subject to extremely high standards as they can impact the performance of the engine. Therefore, it is essential to analyze these databases to better understand the influence of the different parameters on the engine's performance. Self-organizing maps are unsupervised neural networks which achieve two tasks simultaneously: they visualize high-dimensional data by projection onto a 2-dimensional map and provide clustering of the data. This technique has become very popular for data exploration since it provides easily interpretable results and a meaningful global view of the data. As such, self-organizing maps are usually applied to aircraft engine condition monitoring. As databases in this field are huge and complex, they naturally contain multiple missing entries for various reasons. The classical Kohonen algorithm to compute self-organizing maps is conceived for complete data only. A naive approach to deal with partially observed data consists in deleting items or variables with missing entries. However, this requires a sufficient number of complete individuals to be fairly representative of the population; otherwise, deletion leads to a considerable loss of information. Moreover, deletion can also induce bias in the analysis results. Alternatively, one can first apply a common imputation method to create a complete dataset and then apply the Kohonen algorithm. However, the choice of the imputation method may have a strong impact on the resulting self-organizing map. Our approach is to address simultaneously the two problems of computing a self-organizing map and imputing missing values, as these tasks are not independent. In this work, we propose an extension of self-organizing maps for partially observed data, referred to as missSOM. First, we introduce a criterion to be optimized, that aims at defining simultaneously the best self-organizing map and the best imputations for the missing entries. As such, missSOM is also an imputation method for missing values. To minimize the criterion, we propose an iterative algorithm that alternates the learning of a self-organizing map and the imputation of missing values. Moreover, we develop an accelerated version of the algorithm by entwining the iterations of the Kohonen algorithm with the updates of the imputed values. This method is efficiently implemented in R and will soon be released on CRAN. Compared to the standard Kohonen algorithm, it does not come with any additional cost in terms of computing time. Numerical experiments illustrate that missSOM performs well in terms of both clustering and imputation compared to the state of the art. In particular, it turns out that missSOM is robust to the missingness mechanism, which is in contrast to many imputation methods that are appropriate for only a single mechanism. This is an important property of missSOM as, in practice, the missingness mechanism is often unknown. An application to measurements on one type of part is also provided and shows the practical interest of missSOM.

Keywords: imputation method of missing data, partially observed data, robustness to missingness mechanism, self-organizing maps

Procedia PDF Downloads 138

Authors: Anna-Maria Ramezanzadeh

Abstract:

Demand for Arabic language is growing worldwide, driven by increased interest in the multifarious purposes the language serves, both for the population of heritage learners and those studying Arabic as a foreign language. The diglossic, or indeed multiglossic nature of the language as used in Arabic speaking communities however, is seldom represented in the content of classroom courses. This disjoint between the nature of provision and students’ expectations can severely impact their engagement with course material, and their motivation to either commence or continue learning the language. The nature of motivation and its relationship to multiglossia is sparsely explored in current literature on Arabic. The theoretical framework here proposed aims to address this gap by presenting a model and instruments for the measurement of Arabic learners’ motivation in relation to the multiple strands of the language. It adopts and develops the Second Language Motivation Self-System model (L2MSS), originally proposed by Zoltan Dörnyei, which measures motivation as the desire to reduce the discrepancy between leaners’ current and future self-concepts in terms of the second language (L2). The tripartite structure incorporates measures of the Current L2 Self, Future L2 Self (consisting of an Ideal L2 Self, and an Ought-To Self), and the L2 Learning Experience. The strength of the self-concepts is measured across three different domains of Arabic: Classical, Modern Standard and Colloquial. The focus on learners’ self-concepts allows for an exploration of the effect of multiple factors on motivation towards Arabic, including religion. The relationship between Islam and Arabic is often given as a prominent reason behind some students’ desire to learn the language. Exactly how and why this factor features in learners’ L2 self-concepts has not yet been explored. Specifically designed surveys and interview protocols are proposed to facilitate the exploration of these constructs. The L2 Learning Experience component of the model is operationalized as learners’ task-based engagement. Engagement is conceptualised as multi-dimensional and malleable. In this model, situation-specific measures of cognitive, behavioural, and affective components of engagement are collected via specially designed repeated post-task self-report surveys on Personal Digital Assistant over multiple Arabic lessons. Tasks are categorised according to language learning skill. Given the domain-specific uses of the different varieties of Arabic, the relationship between learners’ engagement with different types of tasks and their overall motivational profiles will be examined to determine the extent of the interaction between the two constructs. A framework for this data analysis is proposed and hypotheses discussed. The unique combination of situation-specific measures of engagement and a person-oriented approach to measuring motivation allows for a macro- and micro-analysis of the interaction between learners and the Arabic learning process. By combining cross-sectional and longitudinal elements with a mixed-methods design, the model proposed offers the potential for capturing a comprehensive and detailed picture of the motivation and engagement of Arabic learners. The application of this framework offers a number of numerous potential pedagogical and research implications which will also be discussed.

Keywords: Arabic, diglossia, engagement, motivation, multiglossia, sociolinguistics

Procedia PDF Downloads 155

Authors: Shilan Rahmani Azr, Siavash Emtiyaz

Abstract:

Recent development in computing and communicative technologies leads to much easier mobile accessibility to the information. Users can access to the information in different places using various deceives in which the care variety of abilities. Meanwhile, the format and details of electronic documents are changing each day. In these cases, a mismatch is created between content and client’s abilities. Recently the service-oriented content adaption has been developed which the adapting tasks are dedicated to some extended services. In this method, the main problem is to choose the best appropriate service among accessible and distributed services. In this paper, a method for determining the optimal path to the best services, based on the quality control parameters and user preferences, is proposed using max heap tree. The efficiency of this method in contrast to the other previous methods of the content adaptation is related to the determining the optimal path of the best services which are measured. The results show the advantages and progresses of this method in compare of the others.

Keywords: service-oriented content adaption, QoS, max heap tree, web services

Procedia PDF Downloads 242

Authors: Shuqi Zhang

Abstract:

Federated learning allows users to participate in collaborative model training without sending data to third-party servers, reducing the risk of user data privacy leakage, and is widely used in smart finance and smart healthcare. However, the distributed architecture design of federation learning itself and the existence of secure aggregation protocols make it inherently vulnerable to backdoor attacks. To solve this problem, the federated learning backdoor defense framework FLEX based on group aggregation, cluster analysis, and neuron pruning is proposed, and inter-compatibility with secure aggregation protocols is achieved. The good performance of FLEX is verified by building a horizontal federated learning framework on the CIFAR-10 dataset for experiments, which achieves 98% success rate of backdoor detection and reduces the success rate of backdoor tasks to 0% ~ 10%.

Keywords: federated learning, secure aggregation, backdoor attack, cluster analysis, neuron pruning

Procedia PDF Downloads 86

Authors: Aleksandra Jonas, Aleksandra Gronowska, Maciej Ścigacz, Szymon Jadczak

Abstract:

Exact Data is a smart tool which helps with meaningful marketing content creation. It helps marketers achieve this by analyzing the text of an advertisement before and after its publication on social media sites like Facebook or Instagram. In our research we focus on four areas of natural language processing (NLP): grammar correction, sentiment analysis, irony detection and advertisement interpretation. Our research has identified a considerable lack of NLP tools for the Polish language, which specifically aid online marketers. In light of this, our research team has set out to create a robust and versatile NLP tool for the Polish language. The primary objective of our research is to develop a tool that can perform a range of language processing tasks in this language, such as sentiment analysis, text classification, text correction and text interpretation. Our team has been working diligently to create a tool that is accurate, reliable, and adaptable to the specific linguistic features of Polish, and that can provide valuable insights for a wide range of marketers needs. In addition to the Polish language version, we are also developing an English version of the tool, which will enable us to expand the reach and impact of our research to a wider audience. Another area of focus in our research involves tackling the challenge of the limited availability of linguistically diverse corpora for non-English languages, which presents a significant barrier in the development of NLP applications. One approach we have been pursuing is the translation of existing English corpora, which would enable us to use the wealth of linguistic resources available in English for other languages. Furthermore, we are looking into other methods, such as gathering language samples from social media platforms. By analyzing the language used in social media posts, we can collect a wide range of data that reflects the unique linguistic characteristics of specific regions and communities, which can then be used to enhance the accuracy and performance of NLP algorithms for non-English languages. In doing so, we hope to broaden the scope and capabilities of NLP applications. Our research focuses on several key NLP techniques including sentiment analysis, text classification, text interpretation and text correction. To ensure that we can achieve the best possible performance for these techniques, we are evaluating and comparing different approaches and strategies for implementing them. We are exploring a range of different methods, including transformers and convolutional neural networks (CNNs), to determine which ones are most effective for different types of NLP tasks. By analyzing the strengths and weaknesses of each approach, we can identify the most effective techniques for specific use cases, and further enhance the performance of our tool. Our research aims to create a tool, which can provide a comprehensive analysis of advertising effectiveness, allowing marketers to identify areas for improvement and optimize their advertising strategies. The results of this study suggest that a smart tool for advertisement analysis can provide valuable insights for businesses seeking to create effective advertising campaigns.

Keywords: NLP, AI, IT, language, marketing, analysis

Procedia PDF Downloads 72

Authors: Rosa L. Figueroa, Christopher A. Flores, Qing Zeng-Treitler

Abstract:

A regular expression consists of sequence characters which allow describing a text path. Usually, in clinical research, regular expressions are manually created by programmers together with domain experts. Lately, there have been several efforts to investigate how to generate them automatically. This article presents a text classification algorithm based on regexes. The algorithm named REX was designed, and then, implemented as a simplified method to create regexes to classify Spanish text automatically. In order to classify ambiguous cases, such as, when multiple labels are assigned to a testing example, REX includes an information gain method Two sets of data were used to evaluate the algorithm’s effectiveness in clinical text classification tasks. The results indicate that the regular expression based classifier proposed in this work performs statically better regarding accuracy and F-measure than Support Vector Machine and Naïve Bayes for both datasets.

Keywords: information gain, regular expressions, smith-waterman algorithm, text classification

Procedia PDF Downloads 306

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, unsupervised training, text retrieval

Procedia PDF Downloads 57

Authors: Jeevan Balaji, Shreyas Chigurupati

Abstract:

Pneumatic gripper use compressed air to operate its actuators (fingers). Unlike the conventional metallic gripper, a soft pneumatic actuator (SPA) can be used for relocating fragile objects. An added advantage for this gripper is that the pressure exerted on the object can be varied by changing the dimensions of the air chambers and also by the number of chambers. SPAs have many benefits over conventional robots in the military, medical fields because of their compliance nature and are easily produced using the 3D printing process. In the paper, SPA is proposed to perform pick and place tasks. A design was developed for the actuators, which is convenient for gripping any fragile objects. Thermoplastic polyurethane (TPU) is used for 3D printing the actuators. The actuator model behaves differently as the parameters such as its chamber height, number of chambers change. A detailed FEM model of the actuator is drafted for different pressure inputs using ABAQUS CAE software, and a safe loading pressure range is found.

Keywords: soft robotics, pneumatic actuator, design and modelling, bending analysis

Procedia PDF Downloads 152

Authors: Carla Michelle Gastelum Knight

Abstract:

In an era where teacher educators and student teachers have almost unrestricted access to all kinds of sources through the internet, a research project carried out with a group of student-teachers has revealed how self-made videos are an exciting new way to motivate and engage students. The project was carried out at Universidad de Sonora, a public university in Northern Mexico, where 39 students of the Bachelor in Arts in English Language Teaching (B.A. in ELT) programme participated creating their own videos. In the process, they worked collaboratively, they exploited their creativity, they were highly motivated and showed more interest in the subject. The videos were shared in a private YouTube channel where students had the opportunity to review their peers’ work and where videos are available at any time for later viewing. This experience has led course instructor to face the challenge of planning and designing meaningful tasks that can and to find ways of exploiting the use of these resources for learning and training purposes.

Keywords: self-made materials, student-teachers, teacher education programme, teacher training

Procedia PDF Downloads 215