Search results for: Kazakh speech dataset

Authors: Gabriele Borg, Alexei De Bono, 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.

Keywords: Big Data, vehicular traffic, traffic management, mobile data patterns

Procedia PDF Downloads 87

Authors: Mairo Musa Galadima, Phoebe Mshelia

Abstract:

In Nigeria, the national policy of education stipulates that the kindergarten-primary schools and the legislature are to use the three popular Nigerian Languages namely: Hausa, Igbo, and Yoruba. However, the English language seems to be preferred and this calls for this paper. Attempts were made to draw out the challenges faced by learners in understanding English speech sounds and using them to communicate effectively in English; using 5 (five) selected secondary school in Bauchi. It was discovered that challenges abound in the wrong use of stress and intonation, transfer of phonetic features from their first language. Others are inadequately qualified teachers and relevant materials including textbooks. It is recommended that teachers of English should lay more emphasis on the teaching of supra-segmental features and should be encouraged to go for further studies, seminars and refresher courses.

Keywords: stress and intonation, phonetic and challenges, teaching and learning English, secondary schools

Procedia PDF Downloads 330

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: computer vision, deep learning, object detection, semiconductor

Procedia PDF Downloads 115

Authors: L. Kamandulytė-Merfeldienė

Abstract:

The paper deals with the main issues of methodology of the Corpus of Spoken Lithuanian which was started to be developed in 2006. At present, the corpus consists of 300,000 grammatically annotated word forms. The creation of the corpus consists of three main stages: collecting the data, the transcription of the recorded data, and the grammatical annotation. Collecting the data was based on the principles of balance and naturality. The recorded speech was transcribed according to the CHAT requirements of CHILDES. The transcripts were double-checked and annotated grammatically using CHILDES. The development of the Corpus of Spoken Lithuanian has led to the constant increase in studies on spontaneous communication, and various papers have dealt with a distribution of parts of speech, use of different grammatical forms, variation of inflectional paradigms, distribution of fillers, syntactic functions of adjectives, the mean length of utterances.

Keywords: CHILDES, corpus of spoken Lithuanian, grammatical annotation, grammatical disambiguation, lexicon, Lithuanian

Procedia PDF Downloads 216

Authors: Ismail Baniadam, Nafisa Tadayyon, Javid Fereidoni

Abstract:

This study aimed to investigate medical students’ attitudes toward some teachers’ talking features regarding their gender in the Iranian context. To do so, 60 male and 60 female medical students of Urmia University of Medical Sciences (UMSU) participated in the research. A researcher made Likert-type questionnaire which was initially piloted and was used to gather the data. Comparing the four different factors regarding the features of teacher talk, it was revealed that visual and extra-linguistic information factor, Lexical and syntactic familiarity, Speed of speech, and the use of Persian language had the highest to the lowest mean score, respectively. It was also indicated that female students rather than male students were significantly more in favor of speed of speech and lexical and syntactic familiarity.

Keywords: attitude, gender, medical student, teacher talk

Procedia PDF Downloads 155

Authors: Rohan Bhasin

Abstract:

Agrammatism in non-fluent Aphasia Cases can be defined as a language disorder wherein a patient can only use content words ( nouns, verbs and adjectives ) for communication and their speech is devoid of functional word types like conjunctions and articles, generating speech of with extremely rudimentary grammar . Past approaches involve Speech Therapy of some order with conversation analysis used to analyse pre-therapy speech patterns and qualitative changes in conversational behaviour after therapy. We describe this approach as a novel method to generate functional words (prepositions, articles, ) around content words ( nouns, verbs and adjectives ) using a combination of Natural Language Processing and Deep Learning algorithms. The applications of this approach can be used to assist communication. The approach the paper investigates is : LSTMs or Seq2Seq: A sequence2sequence approach (seq2seq) or LSTM would take in a sequence of inputs and output sequence. This approach needs a significant amount of training data, with each training data containing pairs such as (content words, complete sentence). We generate such data by starting with complete sentences from a text source, removing functional words to get just the content words. However, this approach would require a lot of training data to get a coherent input. The assumptions of this approach is that the content words received in the inputs of both text models are to be preserved, i.e, won't alter after the functional grammar is slotted in. This is a potential limit to cases of severe Agrammatism where such order might not be inherently correct. The applications of this approach can be used to assist communication mild Agrammatism in non-fluent Aphasia Cases. Thus by generating these function words around the content words, we can provide meaningful sentence options to the patient for articulate conversations. Thus our project translates the use case of generating sentences from content-specific words into an assistive technology for non-Fluent Aphasia Patients.

Keywords: aphasia, expressive aphasia, assistive algorithms, neurology, machine learning, natural language processing, language disorder, behaviour disorder, sequence to sequence, LSTM

Procedia PDF Downloads 145

Authors: Somar Boubou, Tatsuo Narikiyo, Michihiro Kawanishi

Abstract:

In this work, we address the problem of 3D object recognition with depth sensors such as Kinect or Structure sensor. Compared with traditional approaches based on local descriptors, which depends on local information around the object key points, we propose a global features based descriptor. Proposed descriptor, which we name as Differential Histogram of Normal Vectors (DHONV), is designed particularly to capture the surface geometric characteristics of the 3D objects represented by depth images. We describe the 3D surface of an object in each frame using a 2D spatial histogram capturing the normalized distribution of differential angles of the surface normal vectors. The object recognition experiments on the benchmark RGB-D object dataset and a self-collected dataset show that our proposed descriptor outperforms two others descriptors based on spin-images and histogram of normal vectors with linear-SVM classifier.

Keywords: vision in control, robotics, histogram, differential histogram of normal vectors

Procedia PDF Downloads 257

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 60

Authors: Jindong Gu, Matthias Schubert, Volker Tresp

Abstract:

In many outlier detection tasks, only training data belonging to one class, i.e., the positive class, is available. The task is then to predict a new data point as belonging either to the positive class or to the negative class, in which case the data point is considered an outlier. For this task, we propose a novel corrupted Generative Adversarial Network (CorGAN). In the adversarial process of training CorGAN, the Generator generates outlier samples for the negative class, and the Discriminator is trained to distinguish the positive training data from the generated negative data. The proposed framework is evaluated using an image dataset and a real-world network intrusion dataset. Our outlier-detection method achieves state-of-the-art performance on both tasks.

Keywords: one-class classification, outlier detection, generative adversary networks, semi-supervised learning

Procedia PDF Downloads 131

Authors: Suzan Arslanturk, Mohammad-Reza Siadat, Theophilus Ogunyemi, Ananias Diokno

Abstract:

Missing data is a common challenge in statistical analyses of most clinical survey datasets. A variety of methods have been developed to enable analysis of survey data to deal with missing values. Imputation is the most commonly used among the above methods. However, in order to minimize the bias introduced due to imputation, one must choose the right imputation technique and apply it to the correct type of missing data. In this paper, we have identified different types of missing values: missing data due to skip pattern (SPMD), undetermined missing data (UMD), and genuine missing data (GMD) and applied rough set imputation on only the GMD portion of the missing data. We have used rough set imputation to evaluate the effect of such imputation on prediction by generating several simulation datasets based on an existing epidemiological dataset (MESA). To measure how well each dataset lends itself to the prediction model (logistic regression), we have used p-values from the Wald test. To evaluate the accuracy of the prediction, we have considered the width of 95% confidence interval for the probability of incontinence. Both imputed and non-imputed simulation datasets were fit to the prediction model, and they both turned out to be significant (p-value < 0.05). However, the Wald score shows a better fit for the imputed compared to non-imputed datasets (28.7 vs. 23.4). The average confidence interval width was decreased by 10.4% when the imputed dataset was used, meaning higher precision. The results show that using the rough set method for missing data imputation on GMD data improve the predictive capability of the logistic regression. Further studies are required to generalize this conclusion to other clinical survey datasets.

Keywords: rough set, imputation, clinical survey data simulation, genuine missing data, predictive index

Procedia PDF Downloads 146

Authors: Kuo-Kai Lin, Po-Lun Chang

Abstract:

Research Background and Purpose: Following the development of the Internet and multimedia, the Internet and information technology have become crucial avenues of modern communication and knowledge acquisition. The advantages of using mobile devices for learning include making learning borderless and accessible. Mobile learning has become a trend in disease management and health promotion in recent years. End-stage renal disease (ESRD) is an irreversible chronic disease, and patients who do not receive kidney transplants can only rely on hemodialysis or peritoneal dialysis to survive. Due to the complexities in caregiving for patients with ESRD that stem from their advanced age and other comorbidities, the patients’ incapacity of self-care leads to an increase in the need to rely on their families or primary caregivers, although whether the primary caregivers adequately understand and implement patient care is a topic of concern. Therefore, this study explored whether primary caregivers’ health care provisions can be improved through the intervention of an automatic speech intelligent system, thereby improving the objective health outcomes of patients undergoing long-term dialysis. Method: This study developed an automatic speech intelligent system with healthcare functions such as health information voice prompt, two-way feedback, real-time push notification, and health information delivery. Convenience sampling was adopted to recruit eligible patients from a hemodialysis center at a regional teaching hospital as research participants. A one-group pretest-posttest design was adopted. Descriptive and inferential statistics were calculated from the demographic information collected from questionnaires answered by patients and primary caregivers, and from a medical record review, a health care scale (recorded six months before and after the implementation of intervention measures), a subjective health assessment, and a report of objective physiological indicators. The changes in health care behaviors, subjective health status, and physiological indicators before and after the intervention of the proposed automatic speech intelligent system were then compared. Conclusion and Discussion: The preliminary automatic speech intelligent system developed in this study was tested with 20 pretest patients at the recruitment location, and their health care capacity scores improved from 59.1 to 72.8; comparisons through a nonparametric test indicated a significant difference (p < .01). The average score for their subjective health assessment rose from 2.8 to 3.3. A survey of their objective physiological indicators discovered that the compliance rate for the blood potassium level was the most significant indicator; its average compliance rate increased from 81% to 94%. The results demonstrated that this automatic speech intelligent system yielded a higher efficacy for chronic disease care than did conventional health education delivered by nurses. Therefore, future efforts will continue to increase the number of recruited patients and to refine the intelligent system. Future improvements to the intelligent system can be expected to enhance its effectiveness even further.

Keywords: automatic speech intelligent system for health care, primary caregiver, long-term hemodialysis, health care capabilities, health outcomes

Procedia PDF Downloads 97

Authors: Walid Moudani, Ahmad Shahin

Abstract:

This research presents a study to handle the recruitment services system. It aims to enhance a business intelligence system by embedding data mining in its core engine and to facilitate the link between job searchers and recruiters companies. The purpose of this study is to present an intelligent management system for supporting recruitment services based on data mining methods. It consists to apply segmentation on the extracted job postings offered by the different recruiters. The details of the job postings are associated to a set of relevant features that are extracted from the web and which are based on critical criterion in order to define consistent clusters. Thereafter, we assign the job searchers to the best cluster while providing a ranking according to the job postings of the selected cluster. The performance of the proposed model used is analyzed, based on a real case study, with the clustered job postings dataset and classified job searchers dataset by using some metrics.

Keywords: job postings, job searchers, clustering, genetic algorithms, business intelligence

Procedia PDF Downloads 312

Authors: Laszlo Vari

Abstract:

In the digital age, the spread of the mobile world and the nature of the cyberspace, offers many new opportunities for the prevalence of the fundamental right to free expression, and therefore, for free speech and freedom of the press; however, these new information communication technologies carry many new challenges. Defamation, censorship, fake news, misleading information, hate speech, breach of copyright etc., are only some of the violations, all of which can be derived from the harmful exercise of freedom of expression, all which become more salient in the internet. Here raises the question: how can we eliminate these problems, and practice our fundamental freedom rightfully? To answer this question, we should understand the elements and the characteristic of the nature of freedom of expression, and the role of the actors whose duties and responsibilities are crucial in the prevalence of this fundamental freedom. To achieve this goal, this paper will explore the European practice to understand instructions found in the case-law of the European Court of Human rights for the rightful exercise of freedom of expression.

Keywords: collision of rights, European case-law, freedom opinion and expression, media law, freedom of information, online expression

Procedia PDF Downloads 121

Authors: Ankita R. Bansal, Naren S. Burade

Abstract:

Idea is to create a cloud based virtual lab for Deaf Students, “A language acquisition program using Visual Phonics and Cued Speech” using VMware Virtual Lab. This lab will demonstrate students the sounds of letters associated with the Language, building letter blocks, making words, etc Virtual labs are used for demos, training, for the Lingual development of children in their vernacular language. The main potential benefits are reduced labour and hardware costs, faster response times to users. Virtual Computing Labs allows any of the software as a service solutions, virtualization solutions, and terminal services solutions available today to offer as a service on demand, where a single instance of the software runs on the cloud and services multiple end users. VMWare, XEN, MS Virtual Server, Virtuoso, and Citrix are typical examples.

Keywords: visual phonics, language acquisition, vernacular language, cued speech, virtual lab

Procedia PDF Downloads 580

Authors: Hidir S. Nogay

Abstract:

In this study, two systems were created to predict interior temperature in induction motor. One of them consisted of a simple ANN model which has two layers, ten input parameters and one output parameter. The other one consisted of eight ANN models connected each other as cascaded. Cascaded ANN system has 17 inputs. Main reason of cascaded system being used in this study is to accomplish more accurate estimation by increasing inputs in the ANN system. Cascaded ANN system is compared with simple conventional ANN model to prove mentioned advantages. Dataset was obtained from experimental applications. Small part of the dataset was used to obtain more understandable graphs. Number of data is 329. 30% of the data was used for testing and validation. Test data and validation data were determined for each ANN model separately and reliability of each model was tested. As a result of this study, it has been understood that the cascaded ANN system produced more accurate estimates than conventional ANN model.

Keywords: cascaded neural network, internal temperature, inverter, three-phase induction motor

Procedia PDF Downloads 327

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 173

Authors: Shariful Islam, Sharun Akter Khushbu, S. M. Shaqib, Shahriar Sultan Ramit

Abstract:

In the construction sector, ensuring worker safety is of the utmost significance. In this study, a deep learning-based technique is presented for identifying safety gear worn by construction workers, such as helmets, goggles, jackets, gloves, and footwear. The suggested method precisely locates these safety items by using the YOLO v7 (You Only Look Once) object detection algorithm. The dataset utilized in this work consists of labeled images split into training, testing and validation sets. Each image has bounding box labels that indicate where the safety equipment is located within the image. The model is trained to identify and categorize the safety equipment based on the labeled dataset through an iterative training approach. We used custom dataset to train this model. Our trained model performed admirably well, with good precision, recall, and F1-score for safety equipment recognition. Also, the model's evaluation produced encouraging results, with a [email protected] score of 87.7%. The model performs effectively, making it possible to quickly identify safety equipment violations on building sites. A thorough evaluation of the outcomes reveals the model's advantages and points up potential areas for development. By offering an automatic and trustworthy method for safety equipment detection, this research contributes to the fields of computer vision and workplace safety. The proposed deep learning-based approach will increase safety compliance and reduce the risk of accidents in the construction industry.

Keywords: deep learning, safety equipment detection, YOLOv7, computer vision, workplace safety

Procedia PDF Downloads 51

Authors: Vahid Anari, Leila Shahmohammadi

Abstract:

Diagnosing and interpreting manually from a large cohort dataset of immunohistochemically stained tissue of tumors using an optical microscope involves subjectivity and also is tedious for pathologist specialists. Moreover, digital pathology today represents more of an evolution than a revolution in pathology. In this paper, we develop and test an unsupervised algorithm that can automatically enhance the IHC image of a meningioma tumor and classify cells into positive (proliferative) and negative (normal) cells. A dataset including 150 images is used to test the scheme. In addition, a new adaptive color image enhancement method is proposed based on a vector directional filter (VDF) and statistical properties of filtering the window. Since the cells are distinguishable by the human eye, the accuracy and stability of the algorithm are quantitatively compared through application to a wide variety of real images.

Keywords: digital pathology, cell segmentation, immunohistochemically, noise reduction

Procedia PDF Downloads 47

Authors: Iris Sirirada Pattara-Angkoon, Rory Devine, Anja Lindberg, Wendy Browne, Sarah Foley, Gabrielle McHarg, Claire Hughes

Abstract:

Introduction: The “Terrible Twos” is a phrase used to describe toddlers 18-30 months old. It characterizes a transition from high dependency to their caregivers in infancy to more autonomy and mastery of the body and environment. Toddlers at this age may also show more willfulness and stubbornness that could predict a future trajectory leading to conduct disorders. Thus, an important goal for this age group is to promote responsiveness to their caregivers (i.e., compliance). Existing literature tends to focus on praise to increase desirable child behavior. However, this relationship is not always straightforward as some studies have found no or negative association between praise and child compliance. Research suggests positive emotions and affection showed through body language (e.g., smiles) and actions (e.g., hugs, kisses) along with positive parent-child relationship can strengthen the praise and child compliance association. Nonetheless, few studies have examined the influences of positive emotionality within the speech. This is important as implementing verbal positive emotionality is easier than physical adjustments. The literature also tends not to include fathers in the study sample as mothers were traditionally the primary caregiver. However, as child-caring duties are increasing shared equally between mothers and fathers, it is important to include fathers within the study as studies have frequently found differences between female and male caregiver characteristics. Thus, the study will address the literary gap in two ways: 1. explore the influences of positive emotionality in parental speech and 2. include an equal sample of mothers and fathers. Positive emotionality is expected to positively correlate with and predict child compliance. Methodology: This study analyzed toddlers (18-24 months) in their dyadic interactions with mothers and fathers. A Duplo (block) task was used where parents had to work with their children to build the Duplo according to the given photo for four minutes. Then, they would be told to clean up the blocks. Parental positive emotionality in different speech types (e.g., bids, praises, affirmations) and child compliance were measured. Results: The study found that mothers (M = 28.92, SD = 12.01) were significantly more likely than fathers (M = 23.01, SD = 12.28) to use positive verbal emotionality in their speech, t(105) = 4.35, p< .001. High positive emotionality in bids during Duplo task and Clean Up was positively correlated with more child compliance in each task, r(273) = .35, p< .001 and r(264) = .58, p< .001, respectively. Overall, parental positive emotionality in speech significantly predicted child compliance, F(6, 218) = 13.33, p< .001, R² = .27) with emotionality in verbal bids (t = 6.20, p< .001) and affirmations (t = 3.12, p = .002) being significant predictors. Conclusion: Positive verbal emotions may be useful for increasing compliance in toddlers. This can be beneficial for compliance interventions as well as to the parent-child relationship quality through reduction of conflict and child defiance. As this study is correlational in nature, it will be important for future research to test the directional influence of positive emotionality within speech.

Keywords: child temperament, compliance, positive emotion, toddler, verbal bids

Procedia PDF Downloads 158

Authors: Mounia El Jaouhari, Mira Goral, Samir Diouny

Abstract:

Introduction: Previous research has indicated that language impairments are recognized as a feature of many neurodegenerative disorders, including non-language-led dementia subtypes such as Alzheimer´s disease (AD). In this preliminary study, the focal aim is to quantify the semantic content of naming and connected speech samples of Moroccan patients diagnosed with AD using two tasks taken from the culturally adapted and validated Moroccan version of the Boston Diagnostic Aphasia Examination. Methods: Five individuals with AD and five neurologically healthy individuals matched for age, gender, and education will participate in the study. Participants with AD will be diagnosed on the basis of the Moroccan version of the Diagnostic and Statistial Manual of Mental Disorders (DSM-4) screening test, the Moroccan version of the Mini Mental State Examination (MMSE) test scores, and neuroimaging analyses. The participants will engage in two tasks taken from the MDAE-SF: 1) Picture description and 2) Naming. Expected findings: Consistent with previous studies conducted on English speaking AD patients, we expect to find significant word production and retrieval impairments in AD patients in all measures. Moreover, we expect to find category fluency impairments that further endorse semantic breakdown accounts. In sum, not only will the findings of the current study shed more light on the locus of word retrieval impairments noted in AD, but also reflect the nature of Arabic morphology. In addition, the error patterns are expected to be similar to those found in previous AD studies in other languages.

Keywords: alzheimer's disease, anomia, connected speech, semantic impairments, moroccan arabic

Procedia PDF Downloads 123

Authors: Hadri Hussain, M.Nasir Ibrahim, Chee-Ming Ting, Mariani Idroas, Fuad Numan, Alias Mohd Noor

Abstract:

A biometric security system has become an important application in client identification and verification system. A conventional biometric system is normally based on unimodal biometric that depends on either behavioural or physiological information for authentication purposes. The behavioural biometric depends on human body biometric signal (such as speech) and biosignal biometric (such as electrocardiogram (ECG) and phonocardiogram or heart sound (HS)). The speech signal is commonly used in a recognition system in biometric, while the ECG and the HS have been used to identify a person’s diseases uniquely related to its cluster. However, the conventional biometric system is liable to spoof attack that will affect the performance of the system. Therefore, a multimodal biometric security system is developed, which is based on biometric signal of ECG, HS, and speech. The biosignal data involved in the biometric system is initially segmented, with each segment Mel Frequency Cepstral Coefficients (MFCC) method is exploited for extracting the feature. The Hidden Markov Model (HMM) is used to model the client and to classify the unknown input with respect to the modal. The recognition system involved training and testing session that is known as client identification (CID). In this project, twenty clients are tested with the developed system. The best overall performance at 44 kHz was 93.92% for ECG and the worst overall performance was ECG at 88.47%. The results were compared to the best overall performance at 44 kHz for (20clients) to increment of clients, which was 90.00% for HS and the worst overall performance falls at ECG at 79.91%. It can be concluded that the difference multimodal biometric has a substantial effect on performance of the biometric system and with the increment of data, even with higher frequency sampling, the performance still decreased slightly as predicted.

Keywords: electrocardiogram, phonocardiogram, hidden markov model, mel frequency cepstral coeffiecients, client identification

Procedia PDF Downloads 262

Authors: Khayriniso Bakhtiyarovna Ganiyeva

Abstract:

The article explores the significance of punctuation in achieving communicative competence. It underscores that effective communication goes beyond simply using punctuation correctly. In the successful completion of a communicative activity, it is important not that the writer correctly uses punctuation marks but that he was able to achieve a goal aimed at expressing a certain meaning. The unanimity of the writer and the reader in the mutual understanding of the text is of primary importance. It should also be taken into account that situational communication provides special informative content and expressiveness of speech. Also, the norms of the situation are determined by the nature of the information in the text, and the punctuation marks expressed in accordance with the norm perform logical-semantic, highlighting expressive-emotional and signaling functions. It is a mistake to classify the signs subject to the norm of the situation as created by the author because they functionally reflect the general stylistic features of different texts. Such signs are among the common signs that are codified only by the semantics and structure of the created text.

Keywords: communicative-pragmatic approach, expressiveness of speech, stylistic features, comparative analysis

Procedia PDF Downloads 39

Authors: Kenan Morani, Esra Kaya Ayana

Abstract:

This study aimed to develop a novel pipeline for COVID-19 detection using a large and rigorously annotated database of computed tomography (CT) images. The pipeline consists of UNet-based segmentation, lung extraction, and a classification part, with the addition of optional slice removal techniques following the segmentation part. In this work, a batch normalization was added to the original UNet model to produce lighter and better localization, which is then utilized to build a full pipeline for COVID-19 diagnosis. To evaluate the effectiveness of the proposed pipeline, various segmentation methods were compared in terms of their performance and complexity. The proposed segmentation method with batch normalization outperformed traditional methods and other alternatives, resulting in a higher dice score on a publicly available dataset. Moreover, at the slice level, the proposed pipeline demonstrated high validation accuracy, indicating the efficiency of predicting 2D slices. At the patient level, the full approach exhibited higher validation accuracy and macro F1 score compared to other alternatives, surpassing the baseline. The classification component of the proposed pipeline utilizes a convolutional neural network (CNN) to make final diagnosis decisions. The COV19-CT-DB dataset, which contains a large number of CT scans with various types of slices and rigorously annotated for COVID-19 detection, was utilized for classification. The proposed pipeline outperformed many other alternatives on the dataset.

Keywords: classification, computed tomography, lung extraction, macro F1 score, UNet segmentation

Procedia PDF Downloads 108

Authors: Eshta Ranyal, Kamal Jain, Vikrant Ranyal

Abstract:

Potholes are a severe threat to road safety and a major contributing factor towards road distress. In the Indian context, they are a major road hazard. Timely detection of potholes and subsequent repair can prevent the roads from deteriorating. To facilitate the roadway authorities in the timely detection and repair of potholes, we propose a pothole detection methodology using convolutional neural networks. The YOLOv3 model is used as it is fast and accurate in comparison to other state-of-the-art models. You only look once v3 (YOLOv3) is a state-of-the-art, real-time object detection system that features multi-scale detection. A mean average precision(mAP) of 73% was obtained on a training dataset of 200 images. The dataset was then increased to 500 images, resulting in an increase in mAP. We further calculated the depth of the potholes using stereoscopic vision by reconstruction of 3D potholes. This enables calculating pothole volume, its extent, which can then be used to evaluate the pothole severity as low, moderate, high.

Keywords: CNN, pothole detection, pothole severity, YOLO, stereovision

Procedia PDF Downloads 114

Authors: Himanshu Sharma, Karthik Kumar, Harish Kumar

Abstract:

The major problem in crop cultivation is the occurrence of multiple crop diseases. During the growth stage, timely identification of crop diseases is paramount to ensure the high yield of crops, lower production costs, and minimize pesticide usage. In most cases, crop diseases produce observable characteristics and symptoms. The Surveyors usually diagnose crop diseases when they walk through the fields. However, surveyor inspections tend to be biased and error-prone due to the nature of the monotonous task and the subjectivity of individuals. In addition, visual inspection of each leaf or plant is costly, time-consuming, and labour-intensive. Furthermore, the plant pathologists and experts who can often identify the disease within the plant according to their symptoms in early stages are not readily available in remote regions. Therefore, this study specifically addressed early detection of leaf scald, red rot, and eyespot types of diseases within sugarcane plants. The study proposes a computer vision-based approach using a convolutional neural network (CNN) for automatic identification of crop diseases. To facilitate this, firstly, images of sugarcane diseases were taken from google without modifying the scene, background, or controlling the illumination to build the training dataset. Then, the testing dataset was developed based on the real-time collected images from the sugarcane field from India. Then, the image dataset is pre-processed for feature extraction and selection. Finally, the CNN-based Visual Geometry Group (VGG) model was deployed on the training and testing dataset to classify the images into diseased and healthy sugarcane plants and measure the model's performance using various parameters, i.e., accuracy, sensitivity, specificity, and F1-score. The promising result of the proposed model lays the groundwork for the automatic early detection of sugarcane disease. The proposed research directly sustains an increase in crop yield.

Keywords: automatic classification, computer vision, convolutional neural network, image processing, sugarcane disease, visual geometry group

Procedia PDF Downloads 97

Authors: Subodh Chandra Shakya, Badal Shrestha, Suni Thapa, Ashutosh Chauhan, Saugat Adhikari

Abstract:

To tackle our problem of clothes identification, we used different architectures of Convolutional Neural Networks. Among different architectures, the outcome from Inception ResNet V2 and MobileNet V2 seemed promising. On comparison of the metrices, we observed that the Inception ResNet V2 slightly outperforms MobileNet V2 for this purpose. So this paper of ours proposes the cloth identifier using Inception ResNet V2 and also contains the comparison between the outcome of ResNet V2 and MobileNet V2. The document here contains the results and findings of the research that we performed on the DeepFashion Dataset. To improve the dataset, we used different image preprocessing techniques like image shearing, image rotation, and denoising. The whole experiment was conducted with the intention of testing the efficiency of convolutional neural networks on cloth identification so that we could develop a reliable system that is good enough in identifying the clothes worn by the users. The whole system can be integrated with some kind of recommendation system.

Keywords: inception ResNet, convolutional neural net, deep learning, confusion matrix, data augmentation, data preprocessing

Procedia PDF Downloads 166

Authors: Ali Ulvi Uzer

Abstract:

Data reduction is an important topic in the field of pattern recognition applications. The basic concept is the reduction of multitudinous amounts of data down to the meaningful parts. The Principal Component Analysis (PCA) method is frequently used for data reduction. The Support Vector Machine (SVM) method is a discriminative classifier formally defined by a separating hyperplane. In other words, given labeled training data, the algorithm outputs an optimal hyperplane which categorizes new examples. This study offers a hybrid approach that uses the PCA for data reduction and Support Vector Machines (SVM) for classification. In order to detect the accuracy of the suggested system, two boreholes taken from the soil sample was used. The classification accuracies for this dataset were obtained through using ten-fold cross-validation method. As the results suggest, this system, which is performed through size reduction, is a feasible system for faster recognition of dataset so our study result appears to be very promising.

Keywords: feature selection, sequential forward selection, support vector machines, soil sample

Procedia PDF Downloads 431

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 225

Authors: Ben Soltane Cheima, Ittansa Yonas Kelbesa

Abstract:

Speaker Identification (SI) is the task of establishing identity of an individual based on his/her voice characteristics. The SI task is typically achieved by two-stage signal processing: training and testing. The training process calculates speaker specific feature parameters from the speech and generates speaker models accordingly. In the testing phase, speech samples from unknown speakers are compared with the models and classified. Even though performance of speaker identification systems has improved due to recent advances in speech processing techniques, there is still need of improvement. In this paper, a Closed-Set Tex-Independent Speaker Identification System (CISI) based on a Multiple Classifier System (MCS) is proposed, using Mel Frequency Cepstrum Coefficient (MFCC) as feature extraction and suitable combination of vector quantization (VQ) and Gaussian Mixture Model (GMM) together with Expectation Maximization algorithm (EM) for speaker modeling. The use of Voice Activity Detector (VAD) with a hybrid approach based on Short Time Energy (STE) and Statistical Modeling of Background Noise in the pre-processing step of the feature extraction yields a better and more robust automatic speaker identification system. Also investigation of Linde-Buzo-Gray (LBG) clustering algorithm for initialization of GMM, for estimating the underlying parameters, in the EM step improved the convergence rate and systems performance. It also uses relative index as confidence measures in case of contradiction in identification process by GMM and VQ as well. Simulation results carried out on voxforge.org speech database using MATLAB highlight the efficacy of the proposed method compared to earlier work.

Keywords: feature extraction, speaker modeling, feature matching, Mel frequency cepstrum coefficient (MFCC), Gaussian mixture model (GMM), vector quantization (VQ), Linde-Buzo-Gray (LBG), expectation maximization (EM), pre-processing, voice activity detection (VAD), short time energy (STE), background noise statistical modeling, closed-set tex-independent speaker identification system (CISI)

Procedia PDF Downloads 285

Authors: Edwin Foo, Woei Wen, Lui, Meijun Zhao, Shigeru Kuchii, Chin Sai Wong, Chung Sern Goh, Yi Hao He

Abstract:

This presentation presents an elderly care and assistive social robot development work. We named this robot JOS and he is restricted to table top operation. JOS is designed to have a maximum volume of 3600 cm3 with its base restricted to 250 mm and his mission is to provide companion, assist and help the elderly. In order for JOS to accomplish his mission, he will be equipped with perception, reaction and cognition capability. His appearance will be not human like but more towards cute and approachable type. JOS will also be designed to be neutral gender. However, the robot will still have eyes, eyelid and a mouth. For his eyes and eyelids, they will be built entirely with Robotis Dynamixel AX18 motor. To realize this complex task, JOS will be also be equipped with micro-phone array, vision camera and Intel i5 NUC computer and a powered by a 12 V lithium battery that will be self-charging. His face is constructed using 1 motor each for the eyelid, 2 motors for the eyeballs, 3 motors for the neck mechanism and 1 motor for the lips movement. The vision senor will be house on JOS forehead and the microphone array will be somewhere below the mouth. For the vision system, Omron latest OKAO vision sensor is used. It is a compact and versatile sensor that is only 60mm by 40mm in size and operates with only 5V supply. In addition, OKAO vision sensor is capable of identifying the user and recognizing the expression of the user. With these functions, JOS is able to track and identify the user. If he cannot recognize the user, JOS will ask the user if he would want him to remember the user. If yes, JOS will store the user information together with the capture face image into a database. This will allow JOS to recognize the user the next time the user is with JOS. In addition, JOS is also able to interpret the mood of the user through the facial expression of the user. This will allow the robot to understand the user mood and behavior and react according. Machine learning will be later incorporated to learn the behavior of the user so as to understand the mood of the user and requirement better. For the speech system, Microsoft speech and grammar engine is used for the speech recognition. In order to use the speech engine, we need to build up a speech grammar database that captures the commonly used words by the elderly. This database is built from research journals and literature on elderly speech and also interviewing elderly what do they want to robot to assist them with. Using the result from the interview and research from journal, we are able to derive a set of common words the elderly frequently used to request for the help. It is from this set that we build up our grammar database. In situation where there is more than one person near JOS, he is able to identify the person who is talking to him through an in-house developed microphone array structure. In order to make the robot more interacting, we have also included the capability for the robot to express his emotion to the user through the facial expressions by changing the position and movement of the eyelids and mouth. All robot emotions will be in response to the user mood and request. Lastly, we are expecting to complete this phase of project and test it with elderly and also delirium patient by Feb 2015.

Keywords: social robot, vision, elderly care, machine learning

Procedia PDF Downloads 426