Search results for: Kazakh speech dataset

Authors: Muzaffar Hussain

Abstract:

Requests strategies are considered as a part of the speech acts, which are frequently used in everyday communication. Each language provides speech acts to the speakers; therefore, the selection of appropriate form seems more culture-specific rather than language. The present paper investigates the gender-based difference in the use of request strategies by native speakers of Urdu/Punjabi male and female who are learning English as a second language. The data for the present study were collected from 68 graduate students, who are learning English as an L2 in Pakistan. They were given an online close-ended questionnaire, based on Discourse Completion Test (DCT). After analyzing the data, it was found that the L1 male Urdu/Punjabi speakers were inclined to use more direct request strategies while the female Urdu/Punjabi speakers used indirect request strategies. This paper also found that in some situations female participants used more direct strategies than male participants. The present study concludes that the use of request strategies is influenced by culture, social status, and power distribution in a society.

Keywords: gender variation, request strategies, face-threatening, second language pragmatics, language competence

Procedia PDF Downloads 189

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 68

Authors: Kenneth Fon Mbah, Arash Habibi Lashkari, Ali A. Ghorbani

Abstract:

Phishing e-mails are a security issue that not only annoys online users, but has also resulted in significant financial losses for businesses. Phishing advertisements and pornographic e-mails are difficult to detect as attackers have been becoming increasingly intelligent and professional. Attackers track users and adjust their attacks based on users’ attractions and hot topics that can be extracted from community news and journals. This research focuses on deceptive Phishing attacks and their variants such as attacks through advertisements and pornographic e-mails. We propose a framework called Phishing Alerting System (PHAS) to accurately classify e-mails as Phishing, advertisements or as pornographic. PHAS has the ability to detect and alert users for all types of deceptive e-mails to help users in decision making. A well-known email dataset has been used for these experiments and based on previously extracted features, 93.11% detection accuracy is obtainable by using J48 and KNN machine learning techniques. Our proposed framework achieved approximately the same accuracy as the benchmark while using this dataset.

Keywords: phishing e-mail, phishing detection, anti phishing, alarm system, machine learning

Procedia PDF Downloads 340

Authors: Rahul Mohite, Lahcen Ouarbya

Abstract:

This paper focuses on the interplay between humans and computer systems and the ability of these systems to understand and respond to human emotions, including non-verbal communication. Current emotion recognition systems are based solely on either facial or verbal expressions. The limitation of these systems is that it requires large training data sets. The paper proposes a system for recognizing human emotions that combines both speech and emotion recognition. The system utilizes advanced techniques such as deep learning and image recognition to identify facial expressions and comprehend emotions. The results show that the proposed system, based on the combination of facial expression and speech, outperforms existing ones, which are based solely either on facial or verbal expressions. The proposed system detects human emotion with an accuracy of 86%, whereas the existing systems have an accuracy of 70% using verbal expression only and 76% using facial expression only. In this paper, the increasing significance and demand for facial recognition technology in emotion recognition are also discussed.

Keywords: facial reputation, expression reputation, deep gaining knowledge of, photo reputation, facial technology, sign processing, photo type

Procedia PDF Downloads 121

Authors: Devatha Kalyan Kumar, R. Poovarasan

Abstract:

In this paper, we have taken certain important factors and health parameters of diabetes patients especially among children by birth (pediatric congenital) where using the above three metrics methods we are going to assess the importance of each attributes in the dataset and thereby determining the most highly responsible and co-related attribute causing diabetics among young patients. We use cost optimization, control chart and Spearmen methodologies for the real-time application of finding the data efficiency in this diabetes dataset. The Spearmen methodology is the correlation methodologies used in software development process to identify the complexity between the various modules of the software. Identifying the complexity is important because if the complexity is higher, then there is a higher chance of occurrence of the risk in the software. With the use of control; chart mean, variance and standard deviation of data are calculated. With the use of Cost optimization model, we find to optimize the variables. Hence we choose the Spearmen, control chart and cost optimization methods to assess the data efficiency in diabetes datasets.

Keywords: correlation, congenital diabetics, linear relationship, monotonic function, ranking samples, pediatric

Procedia PDF Downloads 256

Authors: Tahir Nawaz Cheema, Dumitru Baleanu, Ali Raza

Abstract:

In this research work, we design intelligent computing through Bayesian Regularization artificial neural networks (BRANNs) introduced to solve the mathematical modeling of infectious diseases (Covid-19). The dynamical transmission is due to the interaction of people and its mathematical representation based on the system's nonlinear differential equations. The generation of the dataset of the Covid-19 model is exploited by the power of the explicit Runge Kutta method for different countries of the world like India, Pakistan, Italy, and many more. The generated dataset is approximately used for training, testing, and validation processes for every frequent update in Bayesian Regularization backpropagation for numerical behavior of the dynamics of the Covid-19 model. The performance and effectiveness of designed methodology BRANNs are checked through mean squared error, error histograms, numerical solutions, absolute error, and regression analysis.

Keywords: mathematical models, beysian regularization, bayesian-regularization backpropagation networks, regression analysis, numerical computing

Procedia PDF Downloads 147

Authors: Eyibo Ebengeobong Eddie, Halil Zafer Alibaba

Abstract:

The neglect of classroom acoustics is dominant in most educational facilities, meanwhile, hearing and listening is the learning process in this kind of facilities. A classroom should therefore be an environment that encourages listening, without an obstacles to understanding what is being taught. Although different studies have shown teachers to complain that noise is the everyday factor that causes stress in classroom, the capacity of individuals to understand speech is further affected by Echoes, Reverberation, and room modes. It is therefore necessary for classrooms to have an ideal acoustics to aid the intelligibility of students in the learning process. The influence of these acoustical parameters on learning and teaching in schools needs to be further researched upon to enhance the teaching and learning capacity of both teacher and student. For this reason, there is a strong need to provide and collect data to analyse and define the suitable quality of classrooms needed for a learning environment. Research has shown that acoustical problems are still experienced in both newer and older schools. However, recently, principle of acoustics has been analysed and room acoustics can now be measured with various technologies and sound systems to improve and solve the problem of acoustics in classrooms. These acoustic solutions, materials, construction methods and integration processes would be discussed in this paper.

Keywords: classroom, acoustics, materials, integration, speech intelligibility

Procedia PDF Downloads 417

Authors: Rui Wang, Luodi Yu, Dan Huang, Hsuan-Chih Chen, Yang Zhang, Suiping Wang

Abstract:

Enhanced discrimination of pure tones but diminished discrimination of speech pitch (i.e., lexical tone) were found in children with autism who speak a tonal language (Mandarin), suggesting a speech-specific impairment of pitch perception in these children. However, in tonal languages, both lexical tone and vowel are phonemic cues and integrally dependent on each other. Therefore, it is unclear whether the presence of phonemic vowel dimension contributes to the observed lexical tone deficits in Mandarin-speaking children with autism. The current study employed a multi-feature oddball paradigm to examine how vowel and tone dimensions contribute to the neural responses for syllable change detection and involuntary attentional orienting in school-age Mandarin-speaking children with autism. In the oddball sequence, syllable /da1/ served as the standard stimulus. There were three deviant stimulus conditions, representing tone-only change (TO, /da4/), vowel-only change (VO, /du1/), and change of tone and vowel simultaneously (TV, /du4/). EEG data were collected from 25 children with autism and 20 age-matched normal controls during passive listening to the stimulation. For each deviant condition, difference waveform measuring mismatch negativity (MMN) was derived from subtracting the ERP waveform to the standard sound from that to the deviant sound for each participant. Additionally, the linear summation of TO and VO difference waveforms was compared to the TV difference waveform, to examine whether neural sensitivity for TV change detection reflects simple summation or nonlinear integration of the two individual dimensions. The MMN results showed that the autism group had smaller amplitude compared with the control group in the TO and VO conditions, suggesting impaired discriminative sensitivity for both dimensions. In the control group, amplitude of the TV difference waveform approximated the linear summation of the TO and VO waveforms only in the early time window but not in the late window, suggesting a time course from dimensional summation to nonlinear integration. In the autism group, however, the nonlinear TV integration was already present in the early window. These findings suggest that speech perception atypicality in children with autism rests not only in the processing of single phonemic dimensions, but also in the dimensional integration process.

Keywords: autism, event-related potentials , mismatch negativity, speech perception

Procedia PDF Downloads 219

Authors: Sophie Laurence, Catherine Rivard

Abstract:

The assessment of acquired language disorders in the adult population, whether for a bilingual or monolingual adult, is a complex process that requires the speech-language pathologist (SLP) to make a judicious choice when selecting the assessment method and tools. However, this task is even more complex with Ontario's bilingual population due to the lack of linguistically and culturally appropriate tools for this population. Numerous researches examined language assessment of the pediatric bilingual population; however, few studies have focused on assessing acquired language disorders in bilingual adults. This study's main objective is to identify the challenges that SLPs encounter when assessing language in the bilingual English-French adult population in Ontario to ultimately be able to serve this population in the future better. An online questionnaire was made available to 1325 members of the College of Audiologists and Speech-Language Pathologists of Ontario (CASLPO) who work with the adult population. The answers to this questionnaire (n = 71) allowed us to identify the tools and strategies most commonly used by SLPs in current practice, identify the assessment challenges faced by SLPs, and determine the causes of these challenges as well as potential solutions. In an English and French assessment, the Western Aphasia Battery, the Boston Diagnostic Aphasia Examination, and the Boston Naming Test were the three tools that respondents deemed to be the most relevant for the assessment. Besides, the results revealed that limited access to SLPs and interpreters who speak the client's language and the lack of standardized and normalized assessment tools for Ontario's French-speaking and bilingual English-French clientele are at the heart of the challenges of current SLP practice. Consistent with these findings, respondents highlighted two potential solutions to address these challenges: SLPs have access to standardized/normalized tools for the population under study and better access to SLPs and interpreters who speak the client's language.

Keywords: assessment, acquired language disorders, bilingualism, speech-Language pathology, adult population

Procedia PDF Downloads 138

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 78

Authors: Gaelle Candel, David Naccache

Abstract:

t-SNE is an embedding method that the data science community has widely used. It helps two main tasks: to display results by coloring items according to the item class or feature value; and for forensic, giving a first overview of the dataset distribution. Two interesting characteristics of t-SNE are the structure preservation property and the answer to the crowding problem, where all neighbors in high dimensional space cannot be represented correctly in low dimensional space. t-SNE preserves the local neighborhood, and similar items are nicely spaced by adjusting to the local density. These two characteristics produce a meaningful representation, where the cluster area is proportional to its size in number, and relationships between clusters are materialized by closeness on the embedding. This algorithm is non-parametric. The transformation from a high to low dimensional space is described but not learned. Two initializations of the algorithm would lead to two different embeddings. In a forensic approach, analysts would like to compare two or more datasets using their embedding. A naive approach would be to embed all datasets together. However, this process is costly as the complexity of t-SNE is quadratic and would be infeasible for too many datasets. Another approach would be to learn a parametric model over an embedding built with a subset of data. While this approach is highly scalable, points could be mapped at the same exact position, making them indistinguishable. This type of model would be unable to adapt to new outliers nor concept drift. This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved. The optimization process minimizes two costs, one relative to the embedding shape and the second relative to the support embedding’ match. The embedding with the support process can be repeated more than once, with the newly obtained embedding. The successive embedding can be used to study the impact of one variable over the dataset distribution or monitor changes over time. This method has the same complexity as t-SNE per embedding, and memory requirements are only doubled. For a dataset of n elements sorted and split into k subsets, the total embedding complexity would be reduced from O(n²) to O(n²=k), and the memory requirement from n² to 2(n=k)², which enables computation on recent laptops. The method showed promising results on a real-world dataset, allowing to observe the birth, evolution, and death of clusters. The proposed approach facilitates identifying significant trends and changes, which empowers the monitoring high dimensional datasets’ dynamics.

Keywords: concept drift, data visualization, dimension reduction, embedding, monitoring, reusability, t-SNE, unsupervised learning

Procedia PDF Downloads 144

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 103

Authors: Nutcha Taneepanichskul, Helen C. Hailes, Mark Miodownik

Abstract:

Plastic waste has emerged as a critical global environmental challenge, primarily driven by the prevalent use of conventional plastics derived from petrochemical refining and manufacturing processes in modern packaging. While these plastics serve vital functions, their persistence in the environment post-disposal poses significant threats to ecosystems. Addressing this issue necessitates approaches, one of which involves the development of biodegradable plastics designed to degrade under controlled conditions, such as industrial composting facilities. It is imperative to note that compostable plastics are engineered for degradation within specific environments and are not suited for uncontrolled settings, including natural landscapes and aquatic ecosystems. The full benefits of compostable packaging are realized when subjected to industrial composting, preventing environmental contamination and waste stream pollution. Therefore, effective sorting technologies are essential to enhance composting rates for these materials and diminish the risk of contaminating recycling streams. In this study, it leverage hyperspectral imaging technology (HSI) coupled with advanced machine learning algorithms to accurately identify various types of plastics, encompassing conventional variants like Polyethylene terephthalate (PET), Polypropylene (PP), Low density polyethylene (LDPE), High density polyethylene (HDPE) and biodegradable alternatives such as Polybutylene adipate terephthalate (PBAT), Polylactic acid (PLA), and Polyhydroxyalkanoates (PHA). The dataset is partitioned into three subsets: a training dataset comprising uncontaminated conventional and biodegradable plastics, a validation dataset encompassing contaminated plastics of both types, and a testing dataset featuring real-world packaging items in both pristine and contaminated states. Five distinct machine learning algorithms, namely Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Logistic Regression, and Decision Tree Algorithm, were developed and evaluated for their classification performance. Remarkably, the Logistic Regression and CNN model exhibited the most promising outcomes, achieving a perfect accuracy rate of 100% for the training and validation datasets. Notably, the testing dataset yielded an accuracy exceeding 80%. The successful implementation of this sorting technology within recycling and composting facilities holds the potential to significantly elevate recycling and composting rates. As a result, the envisioned circular economy for plastics can be established, thereby offering a viable solution to mitigate plastic pollution.

Keywords: biodegradable plastics, sorting technology, hyperspectral imaging technology, machine learning algorithms

Procedia PDF Downloads 79

Authors: Gabriele Borg, Alexei Debono, Charlie Abela

Abstract:

There on a constant rise in the availability of high volumes of data gathered from multiple sources, resulting in an abundance of unprocessed information that can be used to monitor patterns and trends in user behaviour. Similarly, year after year, Malta is also constantly experiencing ongoing population growth and an increase in mobilization demand. This research takes advantage of data which is continuously being sourced and converting it into useful information related to the traffic problem on the Maltese roads. The scope of this paper is to provide a methodology to create a custom dataset (MalTra - Malta Traffic) compiled from multiple participants from various locations across the island to identify the most common routes taken to expose the main areas of activity. This use of big data is seen being used in various technologies and is referred to as ITSs (Intelligent Transportation Systems), which has been concluded that there is significant potential in utilising such sources of data on a nationwide scale. Furthermore, a series of traffic prediction graph neural network models are conducted to compare MalTra to large-scale traffic datasets.

Keywords: graph neural networks, traffic management, big data, mobile data patterns

Procedia PDF Downloads 131

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 71

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 99

Authors: K. M. Saif Ur Rahman, Razib Mamun, Himica Arjuman, Fida Al Shams

Abstract:

Introduction: Autism spectrum disorder (ASD) has become an emerging neurodevelopmental disorder with increasing prevalence. It has become an important public health issue globally. Many approaches including speech and language therapy (SLT), occupational therapy, behavioral therapy etc. are being applied for the betterment of the ASD patients. This study aims to describe the characteristics of ASD patients and perception of caregiver regarding SLT in Bangladesh. Methods: This cross-sectional study was conducted in a therapy and rehabilitation center at Dhaka city. Caregivers of 48 ASD patients responded regarding their perception of SLT and characteristics of patients. Results: Among 48 ASD patients, 56.3% were between 3 to 5 years age group with a male predominance (87.5%). More than half of the participants (56.3%) initiated SLT at the age of 1-3 years and the majority (43.8%) were taking SLT for less than 1 year. Majority of the patients (64.6%) were taken to a physician for healthcare as a first contact of which 29.2% were referred to SLT by physicians. More than half (56.3%) of the caregivers were moderately satisfied with SLT and most of them (62.5%) mentioned moderate improvement through SLT. Improvement rate was 10-15% in specific symptoms such as eye contact, complex mannerism, pointing, imitation etc. Conclusion: This study reveals the self-reported perception of caregivers on SLT. Despite reported improvements, more exploration of different approaches and intervention for management of ASD is recommended.

Keywords: ASD, characteristics, SLT, Bangladesh

Procedia PDF Downloads 181

Authors: Hadeer R. M. Tawfik, Rania A. K. Birry, Amani A. Saad

Abstract:

Eyes are considered to be the most sensitive and important organ for human being. Thus, any eye disorder will affect the patient in all aspects of life. Cataract is one of those eye disorders that lead to blindness if not treated correctly and quickly. This paper demonstrates a model for automatic detection, classification, and grading of cataracts based on image processing techniques and artificial intelligence. The proposed system is developed to ease the cataract diagnosis process for both ophthalmologists and patients. The wavelet transform combined with 2D Log Gabor Wavelet transform was used as feature extraction techniques for a dataset of 120 eye images followed by a classification process that classified the image set into three classes; normal, early, and advanced stage. A comparison between the two used classifiers, the support vector machine SVM and the artificial neural network ANN were done for the same dataset of 120 eye images. It was concluded that SVM gave better results than ANN. SVM success rate result was 96.8% accuracy where ANN success rate result was 92.3% accuracy.

Keywords: cataract, classification, detection, feature extraction, grading, log-gabor, neural networks, support vector machines, wavelet

Procedia PDF Downloads 332

Authors: Othmane Touri, Sanaa El Filali, El Habib Benlahmar

Abstract:

Natural Language Processing (NLP) has gained significant attention lately. It has proved its ability to analyze and extract insights from unstructured text data in various languages. It is found that one of the most popular NLP applications is sentiment analysis which aims to identify the sentiment expressed in a piece of text, such as positive, negative, or neutral, in multiple languages. While there are several multilingual NLP models available for sentiment analysis, there is a need to investigate their effectiveness in different contexts and applications. In this study, we aim to investigate the effectiveness of different multilingual NLP models for sentiment analysis on a dataset of online product reviews in multiple languages. The performance of several NLP models, including Google Cloud Natural Language API, Microsoft Azure Cognitive Services, Amazon Comprehend, Stanford CoreNLP, spaCy, and Hugging Face Transformers are being compared. The models based on several metrics, including accuracy, precision, recall, and F1 score, are being evaluated and compared to their performance across different categories of product reviews. In order to run the study, preprocessing of the dataset has been performed by cleaning and tokenizing the text data in multiple languages. Then training and testing each model has been applied using a cross-validation approach where randomly dividing the dataset into training and testing sets and repeating the process multiple times has been used. A grid search approach to optimize the hyperparameters of each model and select the best-performing model for each category of product reviews and language has been applied. The findings of this study provide insights into the effectiveness of different multilingual NLP models for Multilingual Sentiment Analysis and their suitability for different languages and applications. The strengths and limitations of each model were identified, and recommendations for selecting the most performant model based on the specific requirements of a project were provided. This study contributes to the advancement of research methods in multilingual NLP and provides a practical guide for researchers and practitioners in the field.

Keywords: NLP, multilingual, sentiment analysis, texts

Procedia PDF Downloads 103

Authors: Maurice Ntahobari, Levin Kuhlmann, Mario Boley, Zhinoos Razavi Hesabi

Abstract:

For machine learning based epileptic seizure prediction, it is important for the model to be implemented in small implantable or wearable devices that can be used to monitor epilepsy patients; however, current state-of-the-art methods are complex and computationally intensive. We use Shapley Additive Explanation (SHAP) to find relevant intracranial electroencephalogram (iEEG) features and improve the computational efficiency of a state-of-the-art seizure prediction method based on the extra trees classifier while maintaining prediction performance. Results for a small contest dataset and a much larger dataset with continuous recordings of up to 3 years per patient from 15 patients yield better than chance prediction performance (p < 0.004). Moreover, while the performance of the SHAP-based model is comparable to that of the benchmark, the overall training and prediction time of the model has been reduced by a factor of 1.83. It can also be noted that the feature called zero crossing value is the best EEG feature for seizure prediction. These results suggest state-of-the-art seizure prediction performance can be achieved using efficient methods based on optimal feature selection.

Keywords: machine learning, seizure prediction, extra tree classifier, SHAP, epilepsy

Procedia PDF Downloads 113

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 146

Authors: Asma A. Alsufyani, Maram A. Alharthi, Maha J. Althobaiti, Manal S. Alharthi, Huda Rizq

Abstract:

Twitter is one of the most popular microblogging sites that allows users to publish short text messages called 'tweets'. Increasing the number of accounts to follow (followings) increases the number of tweets that will be displayed from different topics in an unclassified manner in the timeline of the user. Therefore, it can be a vital solution for many Twitter users to have their tweets in a timeline classified into general categories to save the user’s time and to provide easy and quick access to tweets based on topics. In this paper, we developed a classifier for timeline tweets trained on a dataset consisting of 3600 tweets in total, which were collected from Saudi Twitter and annotated manually. We experimented with the well-known Bag-of-Words approach to text classification, and we used support vector machines (SVM) in the training process. The trained classifier performed well on a test dataset, with an average F1-measure equal to 92.3%. The classifier has been integrated into an application, which practically proved the classifier’s ability to classify timeline tweets of the user.

Keywords: corpus creation, feature extraction, machine learning, short text classification, social media, support vector machine, Twitter

Procedia PDF Downloads 155

Authors: Lubna Alhinti, Heidi Christensen, Stuart Cunningham

Abstract:

People with speech disorders may rely on augmentative and alternative communication (AAC) technologies to help them communicate. However, the limitations of the current AAC technologies act as barriers to the optimal use of these technologies in daily communication settings. The ability to communicate effectively relies on a number of factors that are not limited to the intelligibility of the spoken words. In fact, non-verbal cues play a critical role in the correct comprehension of messages and having to rely on verbal communication only, as is the case with current AAC technology, may contribute to problems in communication. This is especially true for people’s ability to express their feelings and emotions, which are communicated to a large part through non-verbal cues. This paper focuses on understanding more about the non-verbal communication ability of people with dysarthria, with the overarching aim of this research being to improve AAC technology by allowing people with dysarthria to better communicate emotions. Preliminary survey results are presented that gives an understanding of how people with dysarthria convey emotions, what emotions that are important for them to get across, what emotions that are difficult for them to convey, and whether there is a difference in communicating emotions when speaking to familiar versus unfamiliar people.

Keywords: alternative and augmentative communication technology, dysarthria, speech emotion recognition, VIVOCA

Procedia PDF Downloads 164

Authors: Mawande Dlali

Abstract:

This paper examines the request strategies in commuter discourse involving taxi drivers and passengers in Khayelitsha as well as the responses to these requests. The present study considers requests in commuter transport as face threatening acts (FTAs), hence the need for the commuter crew to strategically shape their communicative actions to achieve their overall discourse goal of getting passengers to perform actions that are in their own interest with minimum resistance or confrontation. The crew presents itself by using communicative devices that prompt the passengers to evaluate it positively as warm, friendly, and respectful. However, the passengers' responses to requests range from compliance to resistance depending on their interpretation of the speaker’s motive and the probable social consequences. Participant observation by the researcher was the main method of collecting examples of requests and responses to the requests. Unstructured interviews and informal discussions were made with randomly selected taxi drivers and commuters. The findings and explanations presented in this article revealed the predominance of polite requests as speech acts in taxi discourse in Khayelitsha. This research makes a contribution to the contemporary pragmatics study of African languages in urban context.

Keywords: face threatening acts, speech acts, request strategies, discourse

Procedia PDF Downloads 164

Authors: Diana González, Marta Gràcia, Ana Luisa Adam-Alcocer

Abstract:

Incorporating digital tools into educational practices represents a valuable approach for enriching the quality of teachers' educational practices in oral competence and fostering improvements in student learning outcomes. This study aims to promote a collaborative and culturally sensitive approach to professional development between teachers and a speech therapist to enhance their self-awareness and reflection on high-quality educational practices that integrate school components to strengthen children’s oral communication and pragmatic skills. The study involved five bilingual teachers fluent in both English and Spanish, with three specializing in special education and two in general education. It focused on Spanish-English bilingual students, aged 3-6, who were experiencing speech delays or disorders in a New York City public school, with the collaboration of a speech therapist. Using EVALOE-DSS (Assessment Scale of Oral Language Teaching in the School Context - Decision Support System), teachers conducted self-assessments of their teaching practices, reflect and make-decisions throughout six classes from March to June, focusing on students' communicative competence across various activities. Concurrently, the speech therapist observed and evaluated six classes per teacher using EVALOE-DSS during the same period. Additionally, professional development meetings were held monthly between the speech therapist and teachers, centering on discussing classroom interactions, instructional strategies, and the progress of both teachers and students in their classes. Findings highlight the digital tool EVALOE-DSS's value in analyzing communication patterns and trends among bilingual children in inclusive settings. It helps in identifying improvement areas through teacher and speech therapist collaboration. After self-reflection meetings, teachers demonstrated increased awareness of student needs in oral language and pragmatic skills. They also exhibited enhanced utilization of strategies outlined in EVALOE-DSS, such as actively guiding and orienting students during oral language activities, promoting student-initiated communicative interactions, teaching students how to seek and provide information, and managing turn-taking to ensure inclusive participation. Teachers participating in the professional development program have shown positive progress in assessing their classes across all dimensions of the training tool, including instructional design, teacher conversation management, pupil conversation management, communicative functions, teacher strategies, and pupil communication functions. This includes aspects related to both teacher actions and child actions, particularly in child language development. This progress underscores the effectiveness of individual reflection (conducted weekly or biweekly using EVALOE-DSS) as well as collaborative reflection among teachers and the speech therapist during meetings. The EVALOE-SSD has proven effective in supporting teachers' self-reflection, decision-making, and classroom changes, leading to improved development of students' oral language and pragmatic skills. It has facilitated culturally sensitive evaluations of communication among bilingual children, cultivating collaboration between teachers and speech therapist to identify areas of growth. Participants in the professional development program demonstrated substantial progress across all dimensions assessed by EVALOE-DSS. This included improved management of pupil communication functions, implementation of effective teaching strategies, and better classroom dynamics. Regular reflection sessions using EVALOE-SSD supported continuous improvement in instructional practices, highlighting its role in fostering reflective teaching and enriching student learning experiences. Overall, EVALOE-DSS has proven invaluable for enhancing teaching effectiveness and promoting meaningful student interactions in diverse educational settings.

Keywords: bilingual students, collaboration, culturally sensitive, oral communication skills, self-reflection

Procedia PDF Downloads 35

Authors: Raghav Lakhotia, Chandra Kanth Nagesh, Krishna Madgula

Abstract:

A lot has been said and discussed regarding the rationale and significance of the Bechdel Score. It became a digital sensation in 2013, when Swedish cinemas began to showcase the Bechdel test score of a film alongside its rating. The test has drawn criticism from experts and the film fraternity regarding its use to rate the female presence in a movie. The pundits believe that the score is too simplified and the underlying criteria of a film to pass the test must include 1) at least two women, 2) who have at least one dialogue, 3) about something other than a man, is egregious. In this research, we have considered a few more parameters which highlight how we represent females in film, like the number of female dialogues in a movie, dialogue genre, and part of speech tags in the dialogue. The parameters were missing in the existing criteria to calculate the Bechdel score. The research aims to analyze 342 movies scripts to test a hypothesis if these extra parameters, above with the current Bechdel criteria, are significant in calculating the female representation score. The result of the Principal Component Analysis method concludes that the female dialogue content is a key component and should be considered while measuring the representation of women in a work of fiction.

Keywords: Bechdel test, dialogue genre, parts of speech tags, principal component analysis

Procedia PDF Downloads 142

Authors: Nizar Ibnus

Abstract:

The term 'pribumi' or indigenous people was originally coined in the colonisation era to differentiate between Dutch colonials and native Indonesian people. The term was also used to trigger nationalism among Indonesian people to liberate their country from any kind of colonialism which had seized their freedom for ages. However, after the war was over and the colonials had fled from the country, the usage began to be altered. It changed from nationalist propaganda term to somewhat racist term. Immigrants and half-blooded people were massively victimized. Then, in 1998 the government forbade the use of this term for public use. Apparently, this racial issue happens again. On 16th October 2017, Anies Baswedan as the new government of DKI Jakarta province mentioned this term in his inauguration speech. This indeed raises controversy among Indonesian people. Using critical discourse analysis, this paper examines how Indonesian media portray the figure of Anies Baswedan regarding the issue. The findings reveal that Indonesian media depict Anies Baswedan differently. Some view him guilty as he mentioned the controversial and forbidden term in public. While, the other media consider him as innocent as he used the term in different contexts. This various media point of view and framing is presumably emerged from their different ideologies.

Keywords: critical discourse analysis, media framing, racism, pribumi

Procedia PDF Downloads 188

Authors: Fabio Fabris, Alex A. Freitas

Abstract:

Hierarchical classification is a special type of classification task where the class labels are organised into a hierarchy, with more generic class labels being ancestors of more specific ones. Meta-learning for classification-algorithm recommendation consists of recommending to the user a classification algorithm, from a pool of candidate algorithms, for a dataset, based on the past performance of the candidate algorithms in other datasets. Meta-learning is normally used in conventional, non-hierarchical classification. By contrast, this paper proposes a meta-learning approach for more challenging task of hierarchical classification, and evaluates it in a large number of bioinformatics datasets. Hierarchical classification is especially relevant for bioinformatics problems, as protein and gene functions tend to be organised into a hierarchy of class labels. This work proposes meta-learning approach for recommending the best hierarchical classification algorithm to a hierarchical classification dataset. This work’s contributions are: 1) proposing an algorithm for splitting hierarchical datasets into new datasets to increase the number of meta-instances, 2) proposing meta-features for hierarchical classification, and 3) interpreting decision-tree meta-models for hierarchical classification algorithm recommendation.

Keywords: algorithm recommendation, meta-learning, bioinformatics, hierarchical classification

Procedia PDF Downloads 314

Authors: Sandhya Baskaran, Hari Kumar Nagabushanam

Abstract:

Sarcasm sentiment recognition is an area of natural language processing that is being probed into in the recent times. Even with the advancements in NLP, typical translations of words, sentences in its context fail to provide the exact information on a sentiment or emotion of a user. For example, if something bad happens, the statement ‘That's just what I need, great! Terrific!’ is expressed in a sarcastic tone which could be misread as a positive sign by any text-based analyzer. In this paper, we are presenting a unique real time ‘word with its tone’ spotting technique which would provide the sentiment analysis for a tone or pitch of a voice in combination with the words being expressed. This hybrid approach increases the probability for identification of special sentiment like sarcasm much closer to the real world than by mining text or speech individually. The system uses a tone analyzer such as YIN-FFT which extracts pitch segment-wise that would be used in parallel with a speech recognition system. The clustered data is classified for sentiments and sarcasm score for each of it determined. Our Simulations demonstrates the improvement in f-measure of around 12% compared to existing detection techniques with increased precision and recall.

Keywords: sarcasm recognition, tone-word spotting, natural language processing, pitch analyzer

Procedia PDF Downloads 293

Authors: Gertrude Yidanpoa Grumah

Abstract:

Ghana boasts of a rich linguistic diversity, with around eighty-seven indigenous languages coexisting with English, the official language. Within this multilingual environment, speech communities adopt bilingual code choices as a common practice, as people seamlessly switch between Ghanaian languages and English. Extensive research has delved into this phenomenon from various perspectives, including the role of bilingual code choices in teaching, its implications for language policy, and its significance in multilingual communities. Yet, a noticeable gap in the literature persists, with most studies focusing on codeswitching between English and the major southern Ghanaian languages like Twi, Ga, and Ewe. The intricate dynamics of codeswitching with minority indigenous languages, such as Mampruli spoken in northern Ghana, remain largely unexplored. This thesis embarks on an investigation into Mampruli-English codeswitching, delving into the linguistic practices of educated Mampruli speakers. The data collection methods encompass interviews, recorded radio programs, and ethnographic observation. The analytical framework employed draws upon the Ethnography of Communication, with observation notes and transcribed interviews thoughtfully classified into discernible themes. The research findings suggest that a bilingual's tendency to switch from Mampruli to English is significantly influenced by factors such as the level of education, age, gender, perceptions of language prestige, and religious beliefs. In essence, this study represents a pioneering endeavor, marking the first comprehensive study on codeswitching practices within the Mampruli-English context and making a significant contribution to our understanding of Mampruli linguistics, covering the social language codes reflecting the speech community. In a region where such research has been scarce for the past four decades, this study addresses a critical knowledge gap, shedding light on the intricate dynamics of language use in northern Ghana.

Keywords: codeswitching, English, ethnography of communication, Mampruli, sociolinguistics

Procedia PDF Downloads 62