Search results for: spoken word recognition

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 125

Authors: Xiaoxiao Li, Shuangcheng Jia, Qian Li

Abstract:

Keypoint detection has always been a challenge in the field of image recognition. This paper proposes a novelty keypoint detection method which is called Multi-Scale Feature Fusion Convolutional Network with Attention (MFFCNA). We verified that the multi-scale features with the attention mechanism module have better feature expression capability. The feature fusion between different scales makes the information that the network model can express more abundant, and the network is easier to converge. On our self-made street sign corner dataset, we validate the MFFCNA model with an accuracy of 97.8% and a recall of 81%, which are 5 and 8 percentage points higher than the HRNet network, respectively. On the COCO dataset, the AP is 71.9%, and the AR is 75.3%, which are 3 points and 2 points higher than HRNet, respectively. Extensive experiments show that our method has a remarkable improvement in the keypoint recognition tasks, and the recognition effect is better than the existing methods. Moreover, our method can be applied not only to keypoint detection but also to image classification and semantic segmentation with good generality.

Keywords: keypoint detection, feature fusion, attention, semantic segmentation

Procedia PDF Downloads 97

Authors: Fadhl Qutaish

Abstract:

This paper examines the pharyngealization spread in one of the Yemeni Arabic dialects, namely, Ibbi Arabic (IA). It investigates how pharyngealized sounds spread their acoustic features onto the neighboring vowels and change their default features. This feature has been investigated quietly well in MSA but still has to be deeply studied in the different dialect of Arabic which will bring about a clearer picture of the similarities and the differences among these dialects and help in mapping them based on the way this feature is utilized. Though the studies are numerous, no one of them has illustrated how far in the multi-syllabic word the spread can be and whether it takes a steady or gradient manner. This study tries to fill this gap and give a satisfactory explanation of the pharyngealization spread in Ibbi Dialect. This study is the first step towards a larger investigation of the different dialects of Yemeni Arabic in the future. The data recorded are represented in minimal pairs in which the trigger (pharyngealized or the non-pharyngealized sound) is in the initial or final position of monosyllabic and multisyllabic words. A group of 24 words were divided into four groups and repeated three times by three subjects which will yield 216 tokens that are tested and analyzed. The subjects are three male speakers aged between 28 and 31 with no history of neurological, speaking or hearing problems. All of them are bilingual speakers of Arabic and English and native speakers of Ibbi-Dialect. Recordings were done in a sound-proof room and praat software was used for the analysis and coding of the trajectories of F1 and F2 for the low vowel /a/ to see the effect of pharyngealization on the formant trajectory within the same syllable and in other syllables of the same word by comparing the F1 and F2 formants to the non-pharyngealized environment. The results show that pharyngealization spread is gradient (progressively and regressively). The spread is reflected in the gradual raising of F1 as we move closer towards the trigger and the gradual lowering of F2 as well. The results of the F1 mean values in tri-syllabic words when the trigger is word initially show that there is a raise of 37.9 HZ in the first syllable, 26.8HZ in the second syllable and 14.2HZ in the third syllable. F2 mean values undergo a lowering of 239 HZ in the first syllable, 211.7 HZ in the second syllable and 176.5 in the third syllable. This gradual decrease in the difference of F2 values in the non-pharyngealized and pharyngealized context illustrates that the spread is gradient. A similar result was found when the trigger is word-final which proves that the spread is gradient (progressively and regressively.

Keywords: pharyngealization, Yemeni Arabic, Ibbi dialect, pharyngealization spread

Procedia PDF Downloads 197

Authors: Khadijat T. Bamigbade, Olufade F. W. Onifade

Abstract:

The field of automatic facial expression analysis has been an active research area in the last two decades. Its vast applicability in various domains has drawn so much attention into developing techniques and dataset that mirror real life scenarios. Many techniques such as Local Binary Patterns and its variants (CLBP, LBP-TOP) and lately, deep learning techniques, have been used for facial expression recognition. However, the problem of occlusion has not been sufficiently handled, making their results not applicable in real life situations. This paper develops a simple, yet highly efficient method tagged Local Binary Pattern-Histogram of Gradient (LBP-HOG) with occlusion detection in face image, using a multi-class SVM for Action Unit and in turn expression recognition. Our method was evaluated on three publicly available datasets which are JAFFE, CK, SFEW. Experimental results showed that our approach performed considerably well when compared with state-of-the-art algorithms and gave insight to occlusion detection as a key step to handling expression in wild.

Keywords: automatic facial expression analysis, local binary pattern, LBP-HOG, occlusion detection

Procedia PDF Downloads 146

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: brain-computer interface, speech recognition, artificial neural network, electroencephalography, EEG, wernicke area

Procedia PDF Downloads 249

Authors: Youhang Zhou, Weimin Zeng, Qi Xie

Abstract:

Abstract: In order to solve the wear recognition problem of the machine tool guide surface, a new machine tool guide surface recognition method based on the radar-graph barycentre feature is presented in this paper. Firstly, the gray mean value, skewness, projection variance, flat degrees and kurtosis features of the guide surface image data are defined as primary characteristics. Secondly, data Visualization technology based on radar graph is used. The visual barycentre graphical feature is demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology is used, the radar-graph barycentre feature and wear original feature are put into the classifier separately for classification and comparative analysis of classification and experiment results. The calculation and experimental results show that the method based on the radar-graph barycentre feature can detect the guide surface effectively.

Keywords: guide surface, wear defects, feature extraction, data visualization

Procedia PDF Downloads 484

Authors: Ria Ghosh, Soumendra Singh, Dipanjan Mukherjee, Susmita Mondal, Monojit Das, Uttam Pal, Aniruddha Adhikari, Aman Bhushan, Surajit Bose, Siddharth Sankar Bhattacharyya, Debasish Pal, Tanusri Saha-Dasgupta, Maitree Bhattacharyya, Debasis Bhattacharyya, Asim Kumar Mallick, Ranjan Das, Samir Kumar Pal

Abstract:

Drug delivery to a target without adverse effects is one of the major criteria for clinical use. Herein, we have made an attempt to explore the delivery efficacy of SDS surfactant in a monomer and micellar stage during the delivery of the model drug, Toluidine Blue (TB) from the micellar cavity to DNA. Molecular recognition of pre-micellar SDS encapsulated TB with DNA occurs at a rate constant of k1 ~652 s 1. However, no significant release of encapsulated TB at micellar concentration was observed within the experimental time frame. This originated from the higher binding affinity of TB towards the nano-cavity of SDS at micellar concentration which does not allow the delivery of TB from the nano-cavity of SDS micelles to DNA. Thus, molecular recognition controls the extent of DNA recognition by TB which in turn modulates the rate of delivery of TB from SDS in a concentration-dependent manner.

Keywords: DNA, drug delivery, micelle, pre-micelle, SDS, toluidine blue

Procedia PDF Downloads 78

Authors: Sara T. K. Li, Belinda H. J. Chung, Jeffery C. N. Yip, Janet H. Hsiao

Abstract:

Music notation and text reading both involve statistical learning of music or linguistic structures. However, it remains unclear how music reading expertise influences text reading behavior. The present study examined this issue through an eye-tracking study. Chinese-English bilingual musicians and non-musicians read English sentences, Chinese sentences, musical phrases, and sentences in Tibetan, a language novel to the participants, with their eye movement recorded. Each set of stimuli consisted of two conditions in terms of structural regularity: syntactically correct and syntactically incorrect musical phrases/sentences. They then completed a sentence comprehension (for syntactically correct sentences) or a musical segment/word recognition task afterwards to test their comprehension/recognition abilities. The results showed that in reading musical phrases, as compared with non-musicians, musicians had a higher accuracy in the recognition task, and had shorter reading time, fewer fixations, and shorter fixation duration when reading syntactically correct (i.e., in diatonic key) than incorrect (i.e., in non-diatonic key/atonal) musical phrases. This result reflects their expertise in music reading. Interestingly, in reading Tibetan sentences, which was novel to both participant groups, while non-musicians did not show any behavior differences between reading syntactically correct or incorrect Tibetan sentences, musicians showed a shorter reading time and had marginally fewer fixations when reading syntactically correct sentences than syntactically incorrect ones. However, none of the musicians reported discovering any structural regularities in the Tibetan stimuli after the experiment when being asked explicitly, suggesting that they may have implicitly acquired the structural regularities in Tibetan sentences. This group difference was not observed when they read English or Chinese sentences. This result suggests that music reading expertise facilities reading texts in a novel language (i.e., Tibetan), but not in languages that the readers are already familiar with (i.e., English and Chinese). This phenomenon may be due to the similarities between reading music notations and reading texts in a novel language, as in both cases the stimuli follow particular statistical structures but do not involve semantic or lexical processing. Thus, musicians may transfer their statistical learning skills stemmed from music notation reading experience to implicitly discover structures of sentences in a novel language. This speculation is consistent with a recent finding showing that music reading expertise modulates the processing of English nonwords (i.e., words that do not follow morphological or orthographic rules) but not pseudo- or real words. These results suggest that the modulation of music reading expertise on language processing depends on the similarities in the cognitive processes involved. It also has important implications for the benefits of music education on language and cognitive development.

Keywords: eye movement behavior, eye-tracking, music reading expertise, sentence reading, structural regularity, visual processing

Procedia PDF Downloads 355

Authors: Uswah Khairuddin, Rubiyah Yusof, Nenny Ruthfalydia Rosli

Abstract:

This paper presents a comparative study between k-Nearest Neighbour (k-NN) and Multi-Layer Perceptron Neural Network (MLP-NN) classifier using Genetic Algorithm (GA) as feature selector for wood recognition system. The features have been extracted from the images using Grey Level Co-Occurrence Matrix (GLCM). The use of GA based feature selection is mainly to ensure that the database used for training the features for the wood species pattern classifier consists of only optimized features. The feature selection process is aimed at selecting only the most discriminating features of the wood species to reduce the confusion for the pattern classifier. This feature selection approach maintains the ‘good’ features that minimizes the inter-class distance and maximizes the intra-class distance. Wrapper GA is used with k-NN classifier as fitness evaluator (GA-kNN). The results shows that k-NN is the best choice of classifier because it uses a very simple distance calculation algorithm and classification tasks can be done in a short time with good classification accuracy.

Keywords: feature selection, genetic algorithm, optimization, wood recognition system

Procedia PDF Downloads 517

Authors: A. Shoiynbek, K. Kozhakhmet, P. Menezes, D. Kuanyshbay, D. Bayazitov

Abstract:

Speech emotion recognition has received increasing research interest all through current years. There was used emotional speech that was collected under controlled conditions in most research work. Actors imitating and artificially producing emotions in front of a microphone noted those records. There are four issues related to that approach, namely, (1) emotions are not natural, and it means that machines are learning to recognize fake emotions. (2) Emotions are very limited by quantity and poor in their variety of speaking. (3) There is language dependency on SER. (4) Consequently, each time when researchers want to start work with SER, they need to find a good emotional database on their language. In this paper, we propose the approach to create an automatic tool for speech emotion extraction based on facial emotion recognition and describe the sequence of actions of the proposed approach. One of the first objectives of the sequence of actions is a speech detection issue. The paper gives a detailed description of the speech detection model based on a fully connected deep neural network for Kazakh and Russian languages. Despite the high results in speech detection for Kazakh and Russian, the described process is suitable for any language. To illustrate the working capacity of the developed model, we have performed an analysis of speech detection and extraction from real tasks.

Keywords: deep neural networks, speech detection, speech emotion recognition, Mel-frequency cepstrum coefficients, collecting speech emotion corpus, collecting speech emotion dataset, Kazakh speech dataset

Procedia PDF Downloads 74

Authors: Mais Nijim, Rama Devi Chennuboyina, Waseem Al Aqqad

Abstract:

Advances in spatial and spectral resolution of satellite images have led to tremendous growth in large image databases. The data we acquire through satellites, radars and sensors consists of important geographical information that can be used for remote sensing applications such as region planning, disaster management. Spatial data classification and object recognition are important tasks for many applications. However, classifying objects and identifying them manually from images is a difficult task. Object recognition is often considered as a classification problem, this task can be performed using machine-learning techniques. Despite of many machine-learning algorithms, the classification is done using supervised classifiers such as Support Vector Machines (SVM) as the area of interest is known. We proposed a classification method, which considers neighboring pixels in a region for feature extraction and it evaluates classifications precisely according to neighboring classes for semantic interpretation of region of interest (ROI). A dataset has been created for training and testing purpose; we generated the attributes by considering pixel intensity values and mean values of reflectance. We demonstrated the benefits of using knowledge discovery and data-mining techniques, which can be on image data for accurate information extraction and classification from high spatial resolution remote sensing imagery.

Keywords: remote sensing, object recognition, classification, data mining, waterbody identification, feature extraction

Procedia PDF Downloads 316

Authors: Megan Weisbart

Abstract:

Background/Significance: The Intensive Care Unit (ICU) environment contributes to nurse burnout. Burnout costs include decreased employee compassion, missed workdays, worse patient outcomes, diminished job performance, high turnover, and higher organizational cost. Meaningful recognition, nurturing of interpersonal connections, and mindfulness-based interventions are associated with decreased burnout. The purpose of this quality improvement project was to decrease Neonatal ICU (NICU) nurse burnout using a Wellness Bundle that fosters meaningful recognition, interpersonal connections and includes mindfulness-based interventions. Methods: The Professional Quality of Life Scale Version 5 (ProQOL5) was used to measure burnout before Wellness Bundle implementation, after six months, and will be given yearly for three years. Meaningful recognition bundle items include Online submission and posting of staff shoutouts, recognition events, Nurses Week and Unit Practice Council member gifts, and an employee recognition program. Fostering of interpersonal connections bundle items include: Monthly staff games with prizes, social events, raffle fundraisers, unit blog, unit wellness basket, and a wellness resource sheet. Quick coherence techniques were implemented at staff meetings and huddles as a mindfulness-based intervention. Findings: The mean baseline burnout score of 14 NICU nurses was 20.71 (low burnout). The baseline range was 13-28, with 11 nurses experiencing low burnout, three nurses experiencing moderate burnout, and zero nurses experiencing high burnout. After six months of the Wellness Bundle Implementation, the mean burnout score of 39 NICU nurses was 22.28 (low burnout). The range was 14-31, with 22 nurses experiencing low burnout, 17 nurses experiencing moderate burnout, and zero nurses experiencing high burnout. Conclusion: A NICU Wellness Bundle that incorporated meaningful recognition, fostering of interpersonal connections, and mindfulness-based activities was implemented to improve work environments and decrease nurse burnout. Participation bias and low baseline response rate may have affected the reliability of the data and necessitate another comparative measure of burnout in one year.

Keywords: burnout, NICU, nurse, wellness

Procedia PDF Downloads 63

Authors: Aliaksandr Huminski

Abstract:

Semantic Role Labeling (SRL) as shallow semantic parsing approach includes recognition and labeling arguments of a verb in a sentence. Verb participants are linked with specific semantic roles (Agent, Patient, Instrument, Location, etc.). Thus, SRL can answer on key questions such as ‘Who’, ‘When’, ‘What’, ‘Where’ in a text and it is widely applied in dialog systems, question-answering, named entity recognition, information retrieval, and other fields of NLP. However, SRL has the following flaw: Two sentences with identical (or almost identical) meaning can have different semantic role structures. Let consider 2 sentences: (1) John put butter on the bread. (2) John buttered the bread. SRL for (1) and (2) will be significantly different. For the verb put in (1) it is [Agent + Patient + Goal], but for the verb butter in (2) it is [Agent + Goal]. It happens because of one of the most interesting and intriguing features of a verb: Its ability to capture participants as in the case of the verb butter, or their features as, say, in the case of the verb drink where the participant’s feature being liquid is shared with the verb. This capture looks like a total fusion of meaning and cannot be decomposed in direct way (in comparison with compound verbs like babysit or breastfeed). From this perspective, SRL looks really shallow to represent semantic structure. If the key point in semantic representation is an opportunity to use it for making inferences and finding hidden reasons, it assumes by default that two different but semantically identical sentences must have the same semantic structure. Otherwise we will have different inferences from the same meaning. To overcome the above-mentioned flaw, the following approach is suggested. Assume that: P is a participant of relation; F is a feature of a participant; Vcp is a verb that captures a participant; Vcf is a verb that captures a feature of a participant; Vpr is a primitive verb or a verb that does not capture any participant and represents only a relation. In another word, a primitive verb is a verb whose meaning does not include meanings from its surroundings. Then Vcp and Vcf can be decomposed as: Vcp = Vpr +P; Vcf = Vpr +F. If all Vcp and Vcf will be represented this way, then primitive verbs Vpr can be considered as a canonical form for SRL. As a result of that, there will be no hidden participants caught by a verb since all participants will be explicitly unfolded. An obvious example of Vpr is the verb go, which represents pure movement. In this case the verb drink can be represented as man-made movement of liquid into specific direction. Extraction and using primitive verbs for SRL create a canonical representation unique for semantically identical sentences. It leads to the unification of semantic representation. In this case, the critical flaw related to SRL will be resolved.

Keywords: decomposition, labeling, primitive verbs, semantic roles

Procedia PDF Downloads 343

Authors: Abraham Kuruvilla

Abstract:

Since the inception of Christianity, one of the most important precepts has been that of the ‘word becoming flesh.’ Incarnation, as we understand it, is that the ‘word became flesh.’ As we know, it is a commonly held understanding that the concept of Logos was borrowed from the Greek religion. Such understanding has dominated our thought process. This is problematic as it does not draw out the deep roots of Logos. The understanding of Logos also existed in religion such as Hinduism. For the Hindu faith, the understanding of Shabd is pivotal. It could be arguably equated with the understanding of the Logos. The paper looks into the connection of the primal Christian doctrine of the Logos with that of the Hindu understanding of Shabd. The methodology of the paper would be a comparative theological analysis with the New Testament understanding of the Logos with that of the understanding of Shabd as perceived in the different Vedas of the Hindu faith. The paper would come to the conclusion that there is a conceptual connectivity between Logos and the Shabd. As such the understanding of Logos cannot just be attributed to the Greek understanding of Logos, but rather it predates the Greek understanding of Logos by being connected to the Hindu understanding of Shabd. Accordingly, such comparison brings out the implication for a constructive dialogue between Christianity and the Hindu faith.

Keywords: Christianity, Hinudism, Logos, Shabd

Procedia PDF Downloads 191

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 72

Authors: Subir Gupta, Subhas Ganguly

Abstract:

In this paper, we demonstrate the new area of application of image processing in metallurgical images to develop the more opportunity for structure-property correlation based approaches of alloy design. The present exercise focuses on the development of image processing tools suitable for phrase segmentation, grain boundary detection and recognition of micro-constituents in SEM micrographs of ferrite and pearlite steels. A comprehensive data of micrographs have been experimentally developed encompassing the variation of ferrite and pearlite volume fractions and taking images at different magnification (500X, 1000X, 15000X, 2000X, 3000X and 5000X) under scanning electron microscope. The variation in the volume fraction has been achieved using four different plain carbon steel containing 0.1, 0.22, 0.35 and 0.48 wt% C heat treated under annealing and normalizing treatments. The obtained data pool of micrographs arbitrarily divided into two parts to developing training and testing sets of micrographs. The statistical recognition features for ferrite and pearlite constituents have been developed by learning from training set of micrographs. The obtained features for microstructure pattern recognition are applied to test set of micrographs. The analysis of the result shows that the developed strategy can successfully detect the micro constitutes across the wide range of magnification and variation of volume fractions of the constituents in the structure with an accuracy of about +/- 5%.

Keywords: SEM micrograph, metallurgical image processing, ferrite pearlite steel, microstructure

Procedia PDF Downloads 177

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 272

Authors: Bahareh Yousefian, Laurel Smith Stvan

Abstract:

Linguistic structures have two facades: form and meaning. These structures could have either literal meaning or figurative meaning (although it could also depend on the context in which that structure appears). The literal meaning is understandable more easily, but for the figurative meaning, a word or concept is understood from a different word or concept. In linguistic structures with a figurative meaning, it’s more difficult to relate their forms to the meanings than structures with literal meaning. In these cases, the relationship between form and figurative meaning could be studied from different perspectives. Various linguists have been curious about what happens in someone’s mind to understand figurative meaning through the forms; they have used different perspectives and theories to explain this process. It has been studied through cognitive linguistics as well, in which mind and mental activities are really important. In this viewpoint, meaning (in other words, conceptualization) is considered a mental process. In this descriptive-analytic study, 20 Persian compound nouns with figurative meanings have been collected from the Persian-language Moeen Encyclopedic Dictionary and other sources. Examples include [“Sofreh Xaneh”] (traditional restaurant) and [“Dast Yar”] (Assistant). These were studied in a cognitive semantics framework using “Conceptual Blending Theory” which hasn’t been tested on Persian compound nouns before. It was noted that “Conceptual Blending Theory” could lead to the process of understanding the figurative meanings of Persian compound nouns. Many cognitive linguists believe that “Conceptual Blending” is not only a linguistic theory but it’s also a basic human cognitive ability that plays important roles in thought, imagination, and even everyday life as well (though unconsciously). The ability to use mental spaces and conceptual blending (which is exclusive to humankind) is such a basic but unconscious ability that we are unaware of its existence and importance. What differentiates Conceptual Blending Theory from other ways of understanding figurative meaning, are arising new semantic aspects (emergent structure) that lead to a more comprehensive and precise meaning. In this study, it was found that Conceptual Blending Theory could explain reaching the figurative meanings of Persian compound nouns from their forms, such as [talkative for compound word of “Bolbol + Zabani” (nightingale + tongue)] and [wage for compound word of “Dast + Ranj” (hand + suffering)].

Keywords: cognitive linguistics, conceptual blending, figurative meaning, Persian compound nouns

Procedia PDF Downloads 43

Authors: Yishu Gong, Liangliang Yang, Jianyu Zhang, Zhengyu Chen, Sihong He, Xusheng Zhang, Wei Zhang

Abstract:

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide and is characterized by cognitive decline and behavioral changes. People living with Alzheimer’s disease often find it hard to complete routine tasks. However, there are limited objective assessments that aim to quantify the difficulty of certain tasks for AD patients compared to non-AD people. In this study, we propose to use speech emotion recognition (SER), especially the frustration level, as a potential biomarker for quantifying the difficulty patients experience when describing a picture. We build an SER model using data from the IEMOCAP dataset and apply the model to the DementiaBank data to detect the AD/non-AD group difference and perform longitudinal analysis to track the AD disease progression. Our results show that the frustration level detected from the SER model can possibly be used as a cost-effective tool for objective tracking of AD progression in addition to the Mini-Mental State Examination (MMSE) score.

Keywords: Alzheimer’s disease, speech emotion recognition, longitudinal biomarker, machine learning

Procedia PDF Downloads 85

Authors: Wanqing He

Abstract:

The current study explores aspects of exploratory behaviors and social capacities in urban Chinese infants to examine whether these factors mediate the link between infant walking and receptive and productive vocabularies. The linkage between the onset of walking and language attainment proves solid, but little is known about the factors that drive such link. This study examined whether joint attention, gesture use, and object activities mediate the association between locomotion and language development. Results showed that both the frequency (p = .05) and duration (p = .03) of carrying an object are strong mediators that afford opportunities for word comprehension. Also, accessing distal objects may be beneficial to infants’ language expression. Further studies on why object carrying may account for word comprehension and why infants with autism could not benefit from walking onset in terms of language development may yield valuable clinical implications.

Keywords: exploratory behaviors, infancy, language acquisition, motor development, social communicative skills

Procedia PDF Downloads 96

Authors: Albatool Al Abdulwahid, Bayan Shakally, Mariam Mohamed, Wed Almokri

Abstract:

Artificial intelligence has infiltrated every part of our life and every field we can think of. With technical developments, artificial intelligence applications are becoming more prevalent. We chose ELSA speak because it is a magnificent example of Artificial intelligent applications, ELSA speak is a smartphone application that is free to download on both IOS and Android smartphones. ELSA speak utilizes artificial intelligence to help non-native English speakers pronounce words and phrases similar to a native speaker, as well as enhance their English skills. It employs speech-recognition technology that aids the application to excel the pronunciation of its users. This remarkable feature distinguishes ELSA from other voice recognition algorithms and increase the efficiency of the application. This study focused on evaluating ELSA speak application, by testing the degree of effectiveness based on survey questions. The results of the questionnaire were variable. The generality of the participants strongly agreed that ELSA has helped them enhance their pronunciation skills. However, a few participants were unconfident about the application’s ability to assist them in their learning journey.

Keywords: ELSA speak application, artificial intelligence, speech-recognition technology, language learning, english pronunciation

Procedia PDF Downloads 77

Authors: J. K. Adedeji, M. O. Oyekanmi

Abstract:

This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.

Keywords: biometric characters, facial recognition, neural network, OpenCV

Procedia PDF Downloads 231

Authors: Kothuri Sriraman, Mattupalli Komal Teja

Abstract:

In this paper, a novel algorithm is proposed for the recognition of hulls in a hand written images that might be irregular or digit or character shape. Identification of objects and internal objects is quite difficult to extract, when the structure of the image is having bulk of clusters. The estimation results are easily obtained while going through identifying the sub-regional objects by using the SASK algorithm. Focusing mainly to recognize the number of internal objects exist in a given image, so as it is shadow-free and error-free. The hard clustering and density clustering process of obtained image rough set is used to recognize the differentiated internal objects, if any. In order to find out the internal hull regions it involves three steps pre-processing, Boundary Extraction and finally, apply the Hull Detection system. By detecting the sub-regional hulls it can increase the machine learning capability in detection of characters and it can also be extend in order to get the hull recognition even in irregular shape objects like wise black holes in the space exploration with their intensities. Layered hulls are those having the structured layers inside while it is useful in the Military Services and Traffic to identify the number of vehicles or persons. This proposed SASK algorithm is helpful in making of that kind of identifying the regions and can useful in undergo for the decision process (to clear the traffic, to identify the number of persons in the opponent’s in the war).

Keywords: chain code, Hull regions, Hough transform, Hull recognition, Layered Outline Extraction, SASK algorithm

Procedia PDF Downloads 314

Authors: António J. R. Neves, Rui Garcia, Paulo Dias, Alina Trifan

Abstract:

With the aging of the world population and the continuous growth in technology, service robots are more and more explored nowadays as alternatives to healthcare givers or personal assistants for the elderly or disabled people. Any service robot should be capable of interacting with the human companion, receive commands, navigate through the environment, either known or unknown, and recognize objects. This paper proposes an approach for object recognition based on the use of depth information and color images for a service robot. We present a study on two of the most used methods for object detection, where 3D data is used to detect the position of objects to classify that are found on horizontal surfaces. Since most of the objects of interest accessible for service robots are on these surfaces, the proposed 3D segmentation reduces the processing time and simplifies the scene for object recognition. The first approach for object recognition is based on color histograms, while the second is based on the use of the SIFT and SURF feature descriptors. We present comparative experimental results obtained with a real service robot.

Keywords: object detection, feature, descriptors, SIFT, SURF, depth images, service robots

Procedia PDF Downloads 514

Authors: Mohammed S. Al-Rawi, J. Bastos, J. Rodriguez

Abstract:

Object detection and object recognition are essential components of every computer vision system. Despite the high computational complexity and other problems related to numerical stability and accuracy, Zernike moments of 2D images (ZMs) have shown resilience when used in object recognition and have been used in various image analysis applications. In this work, we propose a novel method for computing ZMs via Fast Fourier Transform (FFT). Notably, this is the first algorithm that can generate ZMs up to extremely high orders accurately, e.g., it can be used to generate ZMs for orders up to 1000 or even higher. Furthermore, the proposed method is also simpler and faster than the other methods due to the availability of FFT software and/or hardware. The accuracies and numerical stability of ZMs computed via FFT have been confirmed using the orthogonality property. We also introduce normalizing ZMs with Neumann factor when the image is embedded in a larger grid, and color image reconstruction based on RGB normalization of the reconstructed images. Astonishingly, higher-order image reconstruction experiments show that the proposed methods are superior, both quantitatively and subjectively, compared to the q-recursive method.

Keywords: Chebyshev polynomial, fourier transform, fast algorithms, image recognition, pseudo Zernike moments, Zernike moments

Procedia PDF Downloads 240

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 113

Authors: B. Afsharipoor, E. Nazemi

Abstract:

Artificial neural networks (ANNs) are powerful tool for prediction which can be trained based on a set of examples and thus, it would be useful for nonlinear image processing. The present paper reviews several paper regarding applications of ANN in image processing to shed the light on advantage and disadvantage of ANNs in this field. Different steps in the image processing chain including pre-processing, enhancement, segmentation, object recognition, image understanding and optimization by using ANN are summarized. Furthermore, results on using multi artificial neural networks are presented.

Keywords: neural networks, image processing, segmentation, object recognition, image understanding, optimization, MANN

Procedia PDF Downloads 369

Authors: Lise Paesen, Marielle Leijten

Abstract:

People diagnosed with probable Alzheimer disease suffer from an impairment of their language capacities; a gradual impairment which affects both their spoken and written communication. Our study aims at characterising the language decline in DAT patients with the use of congeneric elicited writing tasks. Within these tasks, a descriptive text has to be written based upon images with which the participants are confronted. A randomised set of images allows us to present the participants with a different task on every encounter, thus allowing us to avoid a recognition effect in this iterative study. This method is a revision from previous studies, in which participants were presented with a larger picture depicting an entire scene. In order to create the randomised set of images, existing pictures were adapted following strict criteria (e.g. frequency, AoA, colour, ...). The resulting data set contained 50 images, belonging to several categories (vehicles, animals, humans, and objects). A pre-test was constructed to validate the created picture set; most images had been used before in spoken picture naming tasks. Hence the same reaction times ought to be triggered in the typed picture naming task. Once validated, the effectiveness of the descriptive tasks was assessed. First, the participants (n=60 students, n=40 healthy elderly) performed a typing task, which provided information about the typing speed of each individual. Secondly, two descriptive writing tasks were carried out, one simple and one complex. The simple task contains 4 images (1 animal, 2 objects, 1 vehicle) and only contains elements with high frequency, a young AoA (<6 years), and fast reaction times. Slow reaction times, a later AoA (≥ 6 years) and low frequency were criteria for the complex task. This task uses 6 images (2 animals, 1 human, 2 objects and 1 vehicle). The data were collected with the keystroke logging programme Inputlog. Keystroke logging tools log and time stamp keystroke activity to reconstruct and describe text production processes. The data were analysed using a selection of writing process and product variables, such as general writing process measures, detailed pause analysis, linguistic analysis, and text length. As a covariate, the intrapersonal interkey transition times from the typing task were taken into account. The pre-test indicated that the new images lead to similar or even faster reaction times compared to the original images. All the images were therefore used in the main study. The produced texts of the description tasks were significantly longer compared to previous studies, providing sufficient text and process data for analyses. Preliminary analysis shows that the amount of words produced differed significantly between the healthy elderly and the students, as did the mean length of production bursts, even though both groups needed the same time to produce their texts. However, the elderly took significantly more time to produce the complex task than the simple task. Nevertheless, the amount of words per minute remained comparable between simple and complex. The pauses within and before words varied, even when taking personal typing abilities (obtained by the typing task) into account.

Keywords: Alzheimer's disease, experimental design, language decline, writing process

Procedia PDF Downloads 252

Authors: Rubin Dan, Xingcai Wang, Ziyang Chen

Abstract:

A chaotic time series noise reduction method based on the fusion of the local projection method, wavelet transform, and particle swarm algorithm (referred to as the LW-PSO method) is proposed to address the problem of false recognition due to noise in the recognition process of chaotic time series containing noise. The method first uses phase space reconstruction to recover the original dynamical system characteristics and removes the noise subspace by selecting the neighborhood radius; then it uses wavelet transform to remove D1-D3 high-frequency components to maximize the retention of signal information while least-squares optimization is performed by the particle swarm algorithm. The Lorenz system containing 30% Gaussian white noise is simulated and verified, and the phase space, SNR value, RMSE value, and K value of the 0-1 test method before and after noise reduction of the Schreiber method, local projection method, wavelet transform method, and LW-PSO method are compared and analyzed, which proves that the LW-PSO method has a better noise reduction effect compared with the other three common methods. The method is also applied to the classical system to evaluate the noise reduction effect of the four methods and the original system identification effect, which further verifies the superiority of the LW-PSO method. Finally, it is applied to the Chengdu rainfall chaotic sequence for research, and the results prove that the LW-PSO method can effectively reduce the noise and improve the chaos recognition rate.

Keywords: Schreiber noise reduction, wavelet transform, particle swarm optimization, 0-1 test method, chaotic sequence denoising

Procedia PDF Downloads 166

Authors: Hela Fathallah

Abstract:

With 6,500 spoken languages all over the world but 80 percent of online content available only in 10 languages – English, Chinese, Spanish, Japanese, Arabic, Portuguese, German, French, Russian, and Korean – language represents a barrier to the universal access to knowledge, information and services that the internet wants to provide. Translation and its related fields of localization, interpreting, globalization, and internationalization, remove that barrier for billions of people worldwide, unlocking new markets for technology companies, mobile device makers, service providers and language vendors as well. This paper gathers different surveys conducted in different regions of the world that demonstrate a growing demand for consumption of web content with distinctive values and in languages others than the aforementioned ones. It also adds new insights to the contribution of translation in languages preservation. The idea that English is the language of internet and that, in a globalized world, everyone should learn English to cope with new technologies is no longer true. This idea has reached its limits. It collides with cultural diversity and differences around the world and generates an accelerated rate of languages extinction. Studies prove that internet exacerbates this rate and web giants such as Facebook or Google are, today, facing the impact of such a misconception of globalization. For internet and dot-com companies, localization is the solution; they are spending a significant amount of time to understand what people want and to figure out how to provide it. They are committed to making their content accessible, if not in all the languages spoken today, at least in most of them, and to adapting it to most cultures. Technology has broken down the barriers of time and space, and it will break down the language barrier as well by undertaking a process of translation and localization and through a new definition of globalization that takes into consideration these two processes.

Keywords: globalization, internet, localization, translation

Procedia PDF Downloads 341