Search results for: speech recognition performance

Authors: Silvia Santano Guillén, Luigi Lo Iacono, Christian Meder

Abstract:

One of the main aims of current social robotic research is to improve the robots’ abilities to interact with humans. In order to achieve an interaction similar to that among humans, robots should be able to communicate in an intuitive and natural way and appropriately interpret human affects during social interactions. Similarly to how humans are able to recognize emotions in other humans, machines are capable of extracting information from the various ways humans convey emotions—including facial expression, speech, gesture or text—and using this information for improved human computer interaction. This can be described as Affective Computing, an interdisciplinary field that expands into otherwise unrelated fields like psychology and cognitive science and involves the research and development of systems that can recognize and interpret human affects. To leverage these emotional capabilities by embedding them in humanoid robots is the foundation of the concept Affective Robots, which has the objective of making robots capable of sensing the user’s current mood and personality traits and adapt their behavior in the most appropriate manner based on that. In this paper, the emotion recognition capabilities of the humanoid robot Pepper are experimentally explored, based on the facial expressions for the so-called basic emotions, as well as how it performs in contrast to other state-of-the-art approaches with both expression databases compiled in academic environments and real subjects showing posed expressions as well as spontaneous emotional reactions. The experiments’ results show that the detection accuracy amongst the evaluated approaches differs substantially. The introduced experiments offer a general structure and approach for conducting such experimental evaluations. The paper further suggests that the most meaningful results are obtained by conducting experiments with real subjects expressing the emotions as spontaneous reactions.

Keywords: affective computing, emotion recognition, humanoid robot, human-robot-interaction (HRI), social robots

Procedia PDF Downloads 235

Authors: Pushpavathi M., Kavya V., Akshatha V.

Abstract:

Introduction: Cleft lip and palate (CLP) is a congenital condition which hinders effectual communication due to associated speech and language difficulties. Expressive language delay (ELD) is a feature seen in this population which is influenced by factors such as type and severity of CLP, age at surgical and linguistic intervention and also the type and intensity of speech and language therapy (SLT). Since CLP is the most common congenital abnormality seen in Indian children, early intervention is a necessity which plays a critical role in enhancing their speech and language skills. The interaction between the timing of intervention and factors which contribute to effective intervention by caregivers is an area which needs to be explored. Objectives: The present study attempts to determine the effect of timing of intervention on the contributing maternal factors for effective linguistic intervention in toddlers with repaired CLP with respect to the awareness, home training patterns, speech and non-speech behaviors of the mothers. Participants: Thirty six toddlers in the age range of 1 to 4 years diagnosed as ELD secondary to repaired CLP, along with their mothers served as participants. Group I (Early Intervention Group, EIG) included 19 mother-child pairs who came to seek SLT soon after corrective surgery and group II (Delayed Intervention Group, DIG) included 16 mother-child pairs who received SLT after the age of 3 years. Further, the groups were divided into group A, and group B. Group ‘A’ received SLT for 60 sessions by Speech Language Pathologist (SLP), while Group B received SLT for 30 sessions by SLP and 30 sessions only by mother without supervision of SLP. Method: The mothers were enrolled for the Early Language Intervention Program and following this, their awareness about CLP was assessed through the Parental awareness questionnaire. The quality of home training was assessed through Mohite’s Inventory. Subsequently, the speech and non-speech behaviors of the mothers were assessed using a Mother’s behavioral checklist. Detailed counseling and orientation was done to the mothers, and SLT was initiated for toddlers. After 60 sessions of intensive SLT, the questionnaire and checklists were re-administered to find out the changes in scores between the pre- and posttest measurements. Results: The scores obtained under different domains in the awareness questionnaire, Mohite’s inventory and Mothers behavior checklist were tabulated and subjected to statistical analysis. Since the data did not follow normal distribution (i.e. p > 0.05), Mann-Whitney U test was conducted which revealed that there was no significant difference between groups I and II as well as groups A and B. Further, Wilcoxon Signed Rank test revealed that mothers had better awareness regarding issues related to CLP and improved home-training abilities post-orientation (p ≤ 0.05). A statistically significant difference was also noted for speech and non-speech behaviors of the mothers (p ≤ 0.05). Conclusions: Extensive orientation and counseling helped mothers of both EI and DI groups to improve their knowledge about CLP. Intensive SLT using focused stimulation and a parent-implemented approach enabled them to carry out the intervention in an effectual manner.

Keywords: awareness, cleft lip and palate, early language intervention program, home training, orientation, timing of intervention

Procedia PDF Downloads 122

Authors: Swapna N., Deepthy Ann Joy

Abstract:

One of the major causes of communication disorders in pediatric population is Motor speech disorders. These disorders which affect the motor aspects of speech articulators can have an adverse effect on the communication abilities of children in their developmental period. The motor aspects are dependent on the sensory abilities of children with motor speech disorders. Hence, oral sensorimotor evaluation is an important component in the assessment of children with motor speech disorders. To our knowledge, the importance of oral motor examination has been well established, yet the sensory assessment of the oral structures has received less focus. One of the most common motor speech disorders seen in children is developmental dysarthria. The present study aimed to assess the orosensory aspects in children with developmental dysarthria (CDD). The control group consisted of 240 children in the age range of four and eight years which was divided into four subgroups (4-4.11, 5-5.11, 6-6.11 and 7-7.11 years). The experimental group consisted of 15 children who were diagnosed with developmental dysarthria secondary to cerebral palsy who belonged in the age range of four and eight years. The oro-sensory aspects such as response to touch, temperature, taste, texture, and orofacial sensitivity were evaluated and profiled. For this purpose, the authors used the ‘Oral Sensorimotor Evaluation Protocol- Children’ which was developed by the authors. The oro-sensory section of the protocol was administered and the clinical profile of oro-sensory abilities of typically developing children and CDD was obtained for each of the sensory abilities. The oro-sensory abilities of speech articulators such as lips, tongue, palate, jaw, and cheeks were assessed in detail and scored. The results indicated that experimental group had poorer scores on oro-sensory aspects such as light static touch, kinetic touch, deep pressure, vibration and double simultaneous touch. However, it was also found that the experimental group performed similar to control group on few aspects like temperature, taste, texture and orofacial sensitivity. Apart from the oro-motor abilities which has received utmost interest, the variation in the oro-sensory abilities of experimental and control group is highlighted and discussed in the present study. This emphasizes the need for assessing the oro-sensory abilities in children with developmental dysarthria in addition to oro-motor abilities.

Keywords: cerebral palsy, developmental dysarthria, orosensory assessment, touch

Procedia PDF Downloads 163

Authors: Vivian Franco

Abstract:

There has been a great deal of research about vowel production of second language learners of Spanish, vowel variation across Spanish dialects, and more recently, research related to Spanish heritage speakers’ vowel production based on speech style. However, there is little investigation reported on Spanish heritage speakers’ vowel production in regard to task modality by incorporating own comparison groups of monolinguals and late bilinguals. Thus, the present study investigates the influence of speech style on Spanish heritage speakers’ vowel production by comparing Spanish-English early and late bilinguals and Spanish monolinguals. The study was guided by the following research question: How do early bilinguals (heritage speakers) differ/relate to advanced L2 speakers of Spanish (late bilinguals) and Spanish monolinguals in their vowel quality (acoustic distribution) and quantity (duration) based on speech style? The participants were a total of 11 speakers of Spanish: 7 early Spanish-English bilinguals with a similar linguistic background (simultaneous bilinguals of the second generation); 2 advanced L2 speakers of Spanish; and 2 Spanish monolinguals from Mexico. The study consisted of two tasks. The first one adopted a semi-spontaneous style by a solicited narration of life experiences and a description of a favorite movie with the purpose to collect spontaneous speech. The second task was a reading activity in which the participants read two paragraphs of a Mexican literary essay 'La nuez.' This task aimed to obtain a more controlled speech style. From this study, it can be concluded that early bilinguals and monolinguals show a smaller formant vowel space overall compared to the late bilinguals in both speech styles. In terms of formant values by stress, the early bilinguals and the late bilinguals resembled in the semi-spontaneous speech style as their unstressed vowel space overlapped with that of the unstressed vowels different from the monolinguals who displayed a slightly reduced unstressed vowel space. For the controlled data, the early bilinguals were similar to the monolinguals as their stressed and unstressed vowel spaces overlapped in comparison to the late bilinguals who showed a more clear reduction of unstressed vowel space. In regard to stress, the monolinguals revealed longer vowel duration overall. However, findings of duration by stress showed that the early bilinguals and the monolinguals remained stable with shorter values of unstressed vowels in the semi-spontaneous data and longer duration in the controlled data when compared to the late bilinguals who displayed opposite results. These findings suggest an implication for Spanish heritage speakers and L2 Spanish vowels research as it has been frequently argued that Spanish bilinguals differ from the Spanish monolinguals by their vowel reduction and centralized vowel space influenced by English. However, some Spanish varieties are characterized by vowel reduction especially in certain phonetic contexts so that some vowels present more weakening than others. Consequently, it would not be conclusive to affirm an English influence on the Spanish of these bilinguals.

Keywords: Spanish-English bilinguals, Spanish monolinguals, spontaneous and controlled speech, vowel production.

Procedia PDF Downloads 129

Authors: Jayanth C., Anirudh Sai Yetikuri, Kavitha S. N.

Abstract:

This paper explores the development and application of computer vision and machine learning techniques for real-time pose detection, facial recognition, and number plate extraction. Utilizing MediaPipe for pose estimation, the research presents methods for detecting hand raises and ducking postures through real-time video analysis. Complementarily, facial recognition is employed to compare and verify individual identities using the face recognition library. Additionally, the paper demonstrates a robust approach for extracting and storing vehicle number plates from images, integrating Optical Character Recognition (OCR) with a database management system. The study highlights the effectiveness and versatility of these technologies in practical scenarios, including security and surveillance applications. The findings underscore the potential of combining computer vision techniques to address diverse challenges and enhance automated systems for both individual and vehicular identification. This research contributes to the fields of computer vision and machine learning by providing scalable solutions and demonstrating their applicability in real-world contexts.

Keywords: computer vision, pose detection, facial recognition, number plate extraction, machine learning, real-time analysis, OCR, database management

Procedia PDF Downloads 26

Authors: Chander Kant, Arun Kumar

Abstract:

Biometric systems automatically recognize an individual based on his/her physiological and behavioral characteristics. There are also some traits like weight, age, height etc. that may not provide reliable user recognition because of there common and temporary nature. These traits are called soft bio metric traits. Although soft bio metric traits are lack of permanence to uniquely and reliably identify an individual, yet they provide some beneficial evidence about the user identity and may improve the system performance. Here in this paper, we have proposed an approach for integrating the soft bio metrics with fingerprint and face to improve the performance of personal authentication system. In our approach we have proposed a combined architecture of three different sensors to elevate the system performance. The approach includes, soft bio metrics, fingerprint and face traits. We have also proven the efficiency of proposed system regarding FAR (False Acceptance Ratio) and total response time, with the help of MUBI (Multimodal Bio metrics Integration) software.

Keywords: FAR, minutiae point, multimodal bio metrics, primary bio metric, soft bio metric

Procedia PDF Downloads 346

Authors: Marek Maruszczak

Abstract:

Gamified applications have been used successfully in education for years. The rapid development of technologies such as augmented reality and image recognition increases their availability and reduces their prices. Thus, there is an increasing possibility and need for a wide use of such applications in education. The main purpose of this article is to present the effects of work on a mobile application with augmented reality, the aim of which is to motivate tourists to pay more attention to the attractions and increase the likelihood of moving from one attraction to the next while visiting the Palácio Nacional de Sintra in Portugal. Work on the application was carried out together with the employees of Parques de Sintra from 2019 to 2021. Their effect was the preparation of a mobile application using augmented reality and image recognition. The application was tested on the palace premises by both Parques de Sintra employees and tourists visiting Palácio Nacional de Sintra. The collected conclusions allowed for the formulation of good practices and guidelines that can be used when designing gamified apps for the purpose of cultural education.

Keywords: augmented reality, cultural education, gamification, image recognition, mobile games

Procedia PDF Downloads 190

Authors: Zunjarrao Kadam, Vikas Minchekar

Abstract:

The facial recognition is an important task in criminal investigation procedure. The security guards-constantly watching the persons-can help to identify the suspected accused. The forensic psychologists are tackled such cases in the criminal justice system. The security personnel may loss their ability to correctly identify the persons due to constant stress while performing the duty. The present study aimed at to identify the effect of experimentally induced stress on facial recognition ability of security personnel’s. For this study 50, security guards from Sangli, Miraj & Jaysingpur city of the Maharashtra States of India were recruited in the experimental study. The randomized two group design was employed to carry out the research. In the initial condition twenty identity card size photographs were shown to both groups. Afterward, artificial stress was induced in the experimental group through the difficultpuzzle-solvingtask in a limited period. In the second condition, both groups were presented earlier photographs with another additional thirty new photographs. The subjects were asked to recognize the photographs which are shown earliest. The analyzed data revealed that control group has ahighest mean score of facial recognition than experimental group. The results were discussed in the present research.

Keywords: experimentally induced stress, facial recognition, cognition, security personnel

Procedia PDF Downloads 261

Authors: Redouane Tlemsani, Redouane, Belkacem Kouninef, Abdelkader Benyettou

Abstract:

In this paper, our system is a Markovien system which we can see it like a Dynamic Bayesian Networks. One of the major interests of these systems resides in the complete training of the models (topology and parameters) starting from training data. The Bayesian Networks are representing models of dubious knowledge on complex phenomena. They are a union between the theory of probability and the graph theory in order to give effective tools to represent a joined probability distribution on a set of random variables. The representation of knowledge bases on description, by graphs, relations of causality existing between the variables defining the field of study. The theory of Dynamic Bayesian Networks is a generalization of the Bayesians networks to the dynamic processes. Our objective amounts finding the better structure which represents the relationships (dependencies) between the variables of a dynamic bayesian network. In applications in pattern recognition, one will carry out the fixing of the structure which obliges us to admit some strong assumptions (for example independence between some variables).

Keywords: Arabic on line character recognition, dynamic Bayesian network, pattern recognition, networks

Procedia PDF Downloads 617

Authors: Jutta Hämmerle-Uhl, Georg Penn, Gerhard Pötzelsberger, Andreas Uhl

Abstract:

Iris codes contain bits with different entropy. This work investigates different strategies to reduce the size of iris code templates with the aim of reducing storage requirements and computational demand in the matching process. Besides simple sub-sampling schemes, also a binary multi-resolution representation as used in the JBIG hierarchical coding mode is assessed. We find that iris code template size can be reduced significantly while maintaining recognition accuracy. Besides, we propose a two stage identification approach, using small-sized iris code templates in a pre-selection satge, and full resolution templates for final identification, which shows promising recognition behaviour.

Keywords: iris recognition, compact iris code, fast matching, best bits, pre-selection identification, two-stage identification

Procedia PDF Downloads 440

Authors: Tanu Aneja, Harsha Malaviya

Abstract:

Capturing pose information in cricket shots poses several challenges, such as low-resolution videos, noisy data, and joint occlusions caused by the nature of the shots. In response to these challenges, we propose a CondDGConv-based framework specifically for cricket shot prediction. By analyzing the spatial-temporal relationships in batsman shot sequences from an annotated 2D cricket dataset, our model achieves a 97% accuracy in predicting shot types. This performance is made possible by conditioning the graph network on batsman 2D poses, allowing for precise prediction of shot outcomes based on pose dynamics. Our approach highlights the potential for enhancing shot prediction in cricket analytics, offering a robust solution for overcoming pose-related challenges in sports analysis.

Keywords: action recognition, cricket. sports video analytics, computer vision, graph convolutional networks

Procedia PDF Downloads 18

Authors: Negar Riazifar, Nigel G. Stocks

Abstract:

This paper proposes strategies in level crossing (LC) sampling and reconstruction that provide high fidelity signal reconstruction for speech signals; these strategies circumvent the problem of exponentially increasing number of samples as the bit-depth is increased and hence are highly efficient. Specifically, the results indicate that the distribution of the intervals between samples is one of the key factors in the quality of signal reconstruction; including samples with short intervals do not improve the accuracy of the signal reconstruction, whilst samples with large intervals lead to numerical instability. The proposed sampling method, termed reduced conventional level crossing (RCLC) sampling, exploits redundancy between samples to improve the efficiency of the sampling without compromising performance. A reconstruction technique is also proposed that enhances the numerical stability through linear interpolation of samples separated by large intervals. Interpolation is demonstrated to improve the accuracy of the signal reconstruction in addition to the numerical stability. We further demonstrate that the RCLC and interpolation methods can give useful levels of signal recovery even if the average sampling rate is less than the Nyquist rate.

Keywords: level crossing sampling, numerical stability, speech processing, trigonometric polynomial

Procedia PDF Downloads 145

Authors: Bruce X. B. Yu, Yan Liu, Keith C. C. Chan

Abstract:

We propose to record Activities of Daily Living (ADLs) of elderly people using a vision-based system so as to provide better assistive and personalization technologies. Current ADL-related research is based on data collected with help from non-elderly subjects in laboratory environments and the activities performed are predetermined for the sole purpose of data collection. To obtain more realistic datasets for the application, we recorded ADLs for the elderly with data collected from real-world environment involving real elderly subjects. Motivated by the need to collect data for more effective research related to elderly care, we chose to collect data in the room of an elderly person. Specifically, we installed Kinect, a vision-based sensor on the ceiling, to capture the activities that the elderly subject performs in the morning every day. Based on the data, we identified 12 morning activities that the elderly person performs daily. To recognize these activities, we created a HARELCARE framework to investigate into the effectiveness of existing Human Activity Recognition (HAR) algorithms and propose the use of a transfer learning algorithm for HAR. We compared the performance, in terms of accuracy, and training progress. Although the collected dataset is relatively small, the proposed algorithm has a good potential to be applied to all daily routine activities for healthcare purposes such as evidence-based diagnosis and treatment.

Keywords: daily activity recognition, healthcare, IoT sensors, transfer learning

Procedia PDF Downloads 132

Authors: Joy Aworo-Okoroh

Abstract:

Literary texts are mirrors of a real-life situation. Thus, authors choose the linguistic items that would best encode their intended meanings and messages. However, words mean more than they seem. The meaning of words is not static rather, it is dynamic as they constantly enter into relationships within a context. Literary texts can only be meaningful if all pragmatic cues are identified and interpreted. Drawing upon Teun Van Djik's theory of local pragmatic coherence, it is established that words enter into relations in a text and these relations account for sequential speech acts in the texts. Comprehension of the text is dependent on the interpretation of these relations.To show the relevance of pragmatic coherence in literary text analysis, ten conversations were selected in Americanah in order to give a clear idea of the pragmatic relations used. The conversations were analysed, identifying the speech act and epistemic relations inherent in them. A subtle analysis of the structure of the conversations was also carried out. It was discovered that justification is the most commonly used relation and the meaning of the text is dependent on the interpretation of these instances' pragmatic coherence. The study concludes that to effectively teach literature in English, pragmatic coherence should be incorporated as words mean more than they say.

Keywords: pragmatic coherence, epistemic coherence, speech act, Americanah

Procedia PDF Downloads 136

Authors: Keyi Wang

Abstract:

Similar to the touchscreen, hand gesture based human-computer interaction (HCI) is a technology that could allow people to perform a variety of tasks faster and more conveniently. This paper proposes a training method of an image-based hand gesture image and video clip recognition system using a CNN (Convolutional Neural Network) with a dataset. A dataset containing 6 hand gesture images is used to train a 2D CNN model. ~98% accuracy is achieved. Furthermore, a 3D CNN model is trained on a dataset containing 4 hand gesture video clips resulting in ~83% accuracy. It is demonstrated that a Cozmo robot loaded with pre-trained models is able to recognize static and dynamic hand gestures.

Keywords: deep learning, hand gesture recognition, computer vision, image processing

Procedia PDF Downloads 139

Authors: P. Shrivastava, A. Shukla, K. Verma, S. Rungta

Abstract:

Parkinson's disease is a chronic neurological disorder that directly affects human gait. It leads to slowness of movement, causes muscle rigidity and tremors. Gait serve as a primary outcome measure for studies aiming at early recognition of disease. Using gait techniques, this paper implements efficient binary bat algorithm for an early detection of Parkinson's disease by selecting optimal features required for classification of affected patients from others. The data of 166 people, both fit and affected is collected and optimal feature selection is done using PSO and Bat algorithm. The reduced dataset is then classified using neural network. The experiments indicate that binary bat algorithm outperforms traditional PSO and genetic algorithm and gives a fairly good recognition rate even with the reduced dataset.

Keywords: parkinson, gait, feature selection, bat algorithm

Procedia PDF Downloads 545

Authors: Dawood Al Chanti, Alice Caplier

Abstract:

Sparse representations of signals have received a great deal of attention in recent years. In this paper, the interest of using sparse representation as a mean for performing sparse discriminative analysis between spontaneous facial expressions is demonstrated. An automatic facial expressions recognition system is presented. It uses a KSVD-SVM approach which is made of three main stages: A pre-processing and feature extraction stage, which solves the problem of shared subspace distribution based on the random projection theory, to obtain low dimensional discriminative and reconstructive features; A dictionary learning and sparse coding stage, which uses the KSVD model to learn discriminative under or over dictionaries for sparse coding; Finally a classification stage, which uses a SVM classifier for facial expressions recognition. Our main concern is to be able to recognize non-basic affective states and non-acted expressions. Extensive experiments on the JAFFE static acted facial expressions database but also on the DynEmo dynamic spontaneous facial expressions database exhibit very good recognition rates.

Keywords: dictionary learning, random projection, pose and spontaneous facial expression, sparse representation

Procedia PDF Downloads 305

Authors: Tiago do Carmo Nogueira, Cássio Dener Noronha Vinhal, Gélson da Cruz Júnior, Matheus Rudolfo Diedrich Ullmann

Abstract:

Generating automatic image descriptions through natural language is a challenging task. Image captioning is a task that consistently describes an image by combining computer vision and natural language processing techniques. To accomplish this task, cutting-edge models use encoder-decoder structures. Thus, Convolutional Neural Networks (CNN) are used to extract the characteristics of the images, and Recurrent Neural Networks (RNN) generate the descriptive sentences of the images. However, cutting-edge approaches still suffer from problems of generating incorrect captions and accumulating errors in the decoders. To solve this problem, we propose a model based on the encoder-decoder structure, introducing a module that generates the weights according to the importance of the word to form the sentence, using the part-of-speech (PoS). Thus, the results demonstrate that our model surpasses state-of-the-art models.

Keywords: gated recurrent units, caption generation, convolutional neural network, part-of-speech

Procedia PDF Downloads 102

Authors: Sadeq Al Yaari, Fayza Al Hammadi, Ayman Al Yaari, Adham Al Yaari, Montaha Al Yaari, Aayah Al Yaari, Sajedah Al Yaari, Salah Al Yami

Abstract:

Background: When we further take Arabic grammatical issues into account in accordance with applied linguistic investigations on Arabic as Second Language (ASL) learners, a fundamental issue arises at this point as to the production of speech in Arabic: Oral grammatical errors committed by ASL learners. Aims: Using manual rating as well as computational analytic methodology to test a corpus of recorded speech by Second Language (ASL) learners of Arabic, this study aims to find the areas of difficulties in learning Arabic grammar. More specifically, it examines how and why ASL learners make grammatical errors in their oral speech. Methods: Tape recordings of four (4) Arabic as Second Language (ASL) learners who ranged in age from 23 to 30 were naturally collected. All participants have completed an intensive Arabic program (two years) and 20 minute-speech was recorded for each participant. Having the collected corpus, the next procedure was to rate them against Arabic standard grammar. The rating includes four processes: Description, analysis and assessment. Conclusions: Outcomes made from the issues addressed in this paper can be summarized in the fact that ASL learners face many grammatical difficulties when studying Arabic word order, tenses and aspects, function words, subject-verb agreement, verb form, active-passive voice, global and local errors, processes-based errors including addition, omission, substitution or a combination of any of them.

Keywords: grammar, error, oral, Arabic, second language, learner, applied linguistics.

Procedia PDF Downloads 45

Authors: Abdullah A. AlShaher

Abstract:

In this paper, we demonstrate how regression curves can be used to recognize 2D non-rigid handwritten shapes. Each shape is represented by a set of non-overlapping uniformly distributed landmarks. The underlying models utilize 2^nd order of polynomials to model shapes within a training set. To estimate the regression models, we need to extract the required coefficients which describe the variations for a set of shape class. Hence, a least square method is used to estimate such modes. We then proceed by training these coefficients using the apparatus Expectation Maximization algorithm. Recognition is carried out by finding the least error landmarks displacement with respect to the model curves. Handwritten isolated Arabic characters are used to evaluate our approach.

Keywords: character recognition, regression curves, handwritten Arabic letters, expectation maximization algorithm

Procedia PDF Downloads 145

Authors: Thuy Bui Anh, Ngan Nguyen Thi Thanh

Abstract:

Currently, social work in Vietnam is entering the first step in the development process to become a true profession with a strong position in society. However, Spirit of helping and sharing of social work has already existed in the daily life of Vietnamese people for a very long time, becoming a precious heritage passed down from ancestors to the next generations while expanding the territory, building and defending for the country. Following the stream of history, charity work in Vietnam has gradually transformed itself towards a more professional work, especially in the last 2 decades. Accordingly, more than 50 universities and educational institutions in Vietnam have been licensed to train social work, ensuring a stronger foundation on human resources working in this field. Despite the strong growth, social work profession, social work education and the recognition of the role of the social workers still need to be fueled to develop, responded to the increasing demand of Vietnam society.

Keywords: education, history, recognition, social work, Vietnam

Procedia PDF Downloads 319

Authors: Henni Sid Ahmed, Belbachir Mohamed Faouzi, Jean Caelen

Abstract:

Behavior recognition has been studied for realizing drivers assisting system and automated navigation and is an important studied field in the intelligent Building. In this paper, a recognition method of behavior recognition separated from a real image was studied. Images were divided into several categories according to the actual weather, distance and angle of view etc. SIFT was firstly used to detect key points and describe them because the SIFT (Scale Invariant Feature Transform) features were invariant to image scale and rotation and were robust to changes in the viewpoint and illumination. My goal is to develop a robust and reliable system which is composed of two fixed cameras in every room of intelligent building which are connected to a computer for acquisition of video sequences, with a program using these video sequences as inputs, we use SIFT represented different images of video sequences, and SVM (support vector machine) Lights as a programming tool for classification of images in order to classify people’s behaviors in the intelligent building in order to give maximum comfort with optimized energy consumption.

Keywords: video analysis, people behavior, intelligent building, classification

Procedia PDF Downloads 378

Authors: Z. Gharaee

Abstract:

Recognizing actions performed by others is important in our daily lives since it is necessary for communicating with others in a proper way. We perceive an action by observing the kinematics of motions involved in the performance. We use our experience and concepts to make a correct recognition of the actions. Although building the action concepts is a life-long process, which is repeated throughout life, we are very efficient in applying our learned concepts in analyzing motions and recognizing actions. Experiments on the subjects observing the actions performed by an actor show that an action is recognized after only about two hundred milliseconds of observation. In this study, hierarchical action recognition architecture is proposed by using growing grid layers. The first-layer growing grid receives the pre-processed data of consecutive 3D postures of joint positions and applies some heuristics during the growth phase to allocate areas of the map by inserting new neurons. As a result of training the first-layer growing grid, action pattern vectors are generated by connecting the elicited activations of the learned map. The ordered vector representation layer receives action pattern vectors to create time-invariant vectors of key elicited activations. Time-invariant vectors are sent to second-layer growing grid for categorization. This grid creates the clusters representing the actions. Finally, one-layer neural network developed by a delta rule labels the action categories in the last layer. System performance has been evaluated in an experiment with the publicly available MSR-Action3D dataset. There are actions performed by using different parts of human body: Hand Clap, Two Hands Wave, Side Boxing, Bend, Forward Kick, Side Kick, Jogging, Tennis Serve, Golf Swing, Pick Up and Throw. The growing grid architecture was trained by applying several random selections of generalization test data fed to the system during on average 100 epochs for each training of the first-layer growing grid and around 75 epochs for each training of the second-layer growing grid. The average generalization test accuracy is 92.6%. A comparison analysis between the performance of growing grid architecture and self-organizing map (SOM) architecture in terms of accuracy and learning speed show that the growing grid architecture is superior to the SOM architecture in action recognition task. The SOM architecture completes learning the same dataset of actions in around 150 epochs for each training of the first-layer SOM while it takes 1200 epochs for each training of the second-layer SOM and it achieves the average recognition accuracy of 90% for generalization test data. In summary, using the growing grid network preserves the fundamental features of SOMs, such as topographic organization of neurons, lateral interactions, the abilities of unsupervised learning and representing high dimensional input space in the lower dimensional maps. The architecture also benefits from an automatic size setting mechanism resulting in higher flexibility and robustness. Moreover, by utilizing growing grids the system automatically obtains a prior knowledge of input space during the growth phase and applies this information to expand the map by inserting new neurons wherever there is high representational demand.

Keywords: action recognition, growing grid, hierarchical architecture, neural networks, system performance

Procedia PDF Downloads 157

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 146

Authors: Rasha Salameh

Abstract:

In light of the tense relationship between Saudi Arabia and Iran, this research paper sheds some light on Al-Arabiya’s reporting of Coronavirus in the Gulf. Particularly because most of the cases, in the beginning, were coming from Iran, some programs of this Saudi channel embraced a conspiracy theory. Hate speech has been used in talking about the topic and discussing it. The results of these discussions will be detailed in this paper in percentages with regard to the research sample, which includes five programs on Al-Arabiya channel: ‘DNA’, ‘Marraya’ (Mirrors), ‘Panorama’, ‘Tafaolcom’ (Your Interaction) and the ‘Diplomatic Street’, in the period between January 19, that is, the date of the first case in Iran, and April 10, 2020. The research shows the use of a conspiracy theory in the programs, in addition to some professional violations. The surveyed sample also shows that the matter receded due to the Arab Gulf states' preoccupation with the successively increasing cases that have appeared there since the start of the pandemic. The results indicate that hate speech was present in the sample at a rate of 98.1% and that most of the programs that dealt with the Iranian issue under the Corona pandemic on Al Arabiya used the conspiracy theory at a rate of 75.5%.

Keywords: Al-Arabiya, Iran, Corona, hate speech, conspiracy theory, politicization of the pandemic

Procedia PDF Downloads 136

Authors: Hanan Al-Jabri

Abstract:

Simultaneous interpreting is deemed to be the most challenging mode of interpreting by many scholars. The special constraints involved in this task including time constraints, different linguistic systems, and stress pose a great challenge to most interpreters. These constraints are likely to maximise when the interpreting task is done live on TV. The TV interpreter is exposed to a wide variety of audiences with different backgrounds and needs and is mostly asked to interpret high profile tasks which raise his/her levels of stress, which further complicate the task. Under these constraints, which require fast and efficient performance, TV interpreters of four TV channels were asked to render Trump's victory speech into Arabic. However, they had also to deal with the burden of rendering English emotive overtones employed by the speaker into a whole different linguistic system. The current study aims at investigating the way TV interpreters, who worked in the simultaneous mode, handled this task; it aims at exploring and evaluating the TV interpreters’ linguistic choices and whether the original emotive effect was maintained, upgraded, downgraded or abandoned in their renditions. It also aims at exploring the possible difficulties and challenges that emerged during this process and might have influenced the interpreters’ linguistic choices. To achieve its aims, the study analysed Trump’s victory speech delivered on November 6, 2016, along with four Arabic simultaneous interpretations produced by four TV channels: Al-Jazeera, RT, CBC News, and France 24. The analysis of the study relied on two frameworks: a macro and a micro framework. The former presents an overview of the wider context of the English speech as well as an overview of the speaker and his political background to help understand the linguistic choices he made in the speech, and the latter framework investigates the linguistic tools which were employed by the speaker to stir people’s emotions. These tools were investigated based on Shamaa’s (1978) classification of emotive meaning according to their linguistic level: phonological, morphological, syntactic, and semantic and lexical levels. Moreover, this level investigates the patterns of rendition which were detected in the Arabic deliveries. The results of the study identified different rendition patterns in the Arabic deliveries, including parallel rendition, approximation, condensation, elaboration, transformation, expansion, generalisation, explicitation, paraphrase, and omission. The emerging patterns, as suggested by the analysis, were influenced by factors such as speedy and continuous delivery of some stretches, and highly-dense segments among other factors. The study aims to contribute to a better understanding of TV simultaneous interpreting between English and Arabic, as well as the practices of TV interpreters when rendering emotiveness especially that little is known about interpreting practices in the field of TV, particularly between Arabic and English.

Keywords: emotive overtones, interpreting strategies, political speeches, TV interpreting

Procedia PDF Downloads 159

Authors: Shantanu Arya, Sachin Sakhuja, Gunjan Mehta, Sanjay Munjal

Abstract:

Stuttering may be defined as a speech disorder affecting the fluency domain of speech and characterized by covert features like word substitution, omittance and circumlocution and overt features like prolongation of sound, syllables and blocks etc. Many etiologies have been postulated to explain stuttering based on various experiments and research. Moreover, Breathlessness has also been reported by many individuals with stuttering for which breathing exercises are generally advised. However, no studies reporting objective evaluation of the pulmonary capacity and further objective assessment of the efficacy of breathing exercises have been conducted. Pulmonary Function Test which evaluates parameters like Forced Vital Capacity, Peak Expiratory Flow Rate, Forced expiratory flow Rate can be used to study the pulmonary behavior of individuals with stuttering. The study aimed: a) To identify speech motor & physiologic behaviours associated with stuttering by administering PFT. b) To recognize possible reasons for an association between speech motor behaviour & stuttering severity. In this regard, PFT tests were administered on individuals who reported signs and symptoms of stuttering and showed abnormal scores on Stuttering Severity Index. Parameters like Forced Vital Capacity, Forced Expiratory Volume, Peak Expiratory Flow Rate (L/min), Forced Expiratory Flow Rate (L/min) were evaluated and correlated with scores of Stuttering Severity Index. Results showed significant decrease in the parameters (lower than normal scores) in individuals with established stuttering. Strong correlation was also found between degree of stuttering and the degree of decrease in the pulmonary volumes. Thus, it is evident that fluent speech requires strong support of lung pressure and requisite volumes. Further research in demonstrating the efficacy of abdominal breathing exercises in this regard is needed.

Keywords: forced expiratory flow rate, forced expiratory volume, forced vital capacity, peak expiratory flow rate, stuttering

Procedia PDF Downloads 275

Authors: Maha Jazouli

Abstract:

Suicide is one of the most important causes of death in the prison environment, both in Canada and internationally. Rates of attempts of suicide and self-harm have been on the rise in recent years, with hangings being the most frequent method resorted to. The objective of this article is to propose a method to automatically detect in real time suicidal behaviors. We present a gesture recognition system that consists of three modules: model-based movement tracking, feature extraction, and gesture recognition using machine learning algorithms (MLA). Our proposed system gives us satisfactory results. This smart video surveillance system can help assist staff responsible for the safety and health of inmates by alerting them when suicidal behavior is detected, which helps reduce mortality rates and save lives.

Keywords: suicide detection, Kinect azure, RGB-D camera, SVM, machine learning, gesture recognition

Procedia PDF Downloads 188

Authors: Oussama Hafferssas, Hiba Benyahia, Amina Madani, Nassima Zeriri

Abstract:

Although data nowadays has multiple forms; from text to images, and from audio to videos, yet text is still the most used one at a public level. At an academical and research level, and unlike other forms, text can be considered as the easiest form to process. Therefore, a brunch of Data Mining researches has been always under its shadow, called "Text Mining". Its concept is just like data mining’s, finding valuable patterns in data, from large collections and tremendous volumes of data, in this case: Text. Named entity recognition (NER) is one of Text Mining’s disciplines, it aims to extract and classify references such as proper names, locations, expressions of time and dates, organizations and more in a given text. Our approach "Octopub" does not aim to find new ways to improve named entity recognition process, rather than that it’s about finding a new, and yet smart way, to use NER in a way that we can extract sentiments of millions of people using Social Networks as a limitless information source, and Marketing for product promotion as the main domain of application.

Keywords: textmining, named entity recognition(NER), sentiment analysis, social media networks (SN, SMN), business intelligence(BI), marketing

Procedia PDF Downloads 589

Authors: Seham El Kareh, Miramar Etman

Abstract:

Recently, detecting liars and extracting features which distinguish them from truth-tellers have been the focus of a wide range of disciplines. To the author’s best knowledge, most of the work has been done on facial expressions and body gestures but only few works have been done on the language used by both liars and truth-tellers. This paper sheds light on four axes. The first axis copes with building an audio corpus for deceptive and truthful speech for Egyptian Arabic speakers. The second axis focuses on examining the human perception of lies and proving our need for computational linguistic-based methods to extract features which characterize truthful and deceptive speech. The third axis is concerned with building a linguistic analysis program that could extract from the corpus the inter- and intra-linguistic cues for deceptive and truthful speech. The program built here is based on selected categories from the Linguistic Inquiry and Word Count program. Our results demonstrated that Egyptian Arabic speakers on one hand preferred to use first-person pronouns and present tense compared to the past tense when lying and their lies lacked of second-person pronouns, and on the other hand, when telling the truth, they preferred to use the verbs related to motion and the nouns related to time. The results also showed that there is a need for bigger data to prove the significance of words related to emotions and numbers.

Keywords: Egyptian Arabic corpus, computational analysis, deceptive features, forensic linguistics, human perception, truthful features

Procedia PDF Downloads 206