Search results for: Kazakh speech dataset

Authors: Anshika Kankane, Dongshik Kang

Abstract:

Marine debris has a significant influence on coastal environments, damaging biodiversity, and causing loss and damage to marine and ocean sector. A functional cost-effective and automatic approach has been used to look up at this problem. Computer vision combined with a deep learning-based model is being proposed to identify and categorize marine debris of seven kinds on different beach locations of Japan. This research compares state-of-the-art deep learning models with a suggested model architecture that is utilized as a feature extractor for debris categorization. The model is being proposed to detect seven categories of litter using a manually constructed debris dataset, with the help of Mask R-CNN for instance segmentation and a shape matching network called HOGShape, which can then be cleaned on time by clean-up organizations using warning notifications of the system. The manually constructed dataset for this system is created by annotating the images taken by fixed KaKaXi camera using CVAT annotation tool with seven kinds of category labels. A pre-trained HOG feature extractor on LIBSVM is being used along with multiple templates matching on HOG maps of images and HOG maps of templates to improve the predicted masked images obtained via Mask R-CNN training. This system intends to timely alert the cleanup organizations with the warning notifications using live recorded beach debris data. The suggested network results in the improvement of misclassified debris masks of debris objects with different illuminations, shapes, viewpoints and litter with occlusions which have vague visibility.

Keywords: computer vision, debris, deep learning, fixed live camera images, histogram of gradients feature extractor, instance segmentation, manually annotated dataset, multiple template matching

Procedia PDF Downloads 106

Authors: Sultanbayeva Gulmira Serikbayevna, Golovchun Aleftina Anatolyevna

Abstract:

The development of any nation is directly related to the development of human capital in it. A human development is an increase its intellectual potential, its compliance with the requirements of time, present and future society. Demands of globalization cannot limit the processes of national traditions. The education system must be formed on the basis of international practice of cultural development. In Kazakhstan, where modernization changes are rapidly developing, the education system should be formed in two ways: first, on a national basis, and secondly, based on global best practices. There is the need to recognize and promote the importance of education as a value. The world community considers the problem of spiritual values. Along with individual values, spiritual values are also universal values. Formation of values such as the presence in young people a sense of respect for their homeland, social responsibility, respect the culture and traditions of its people is the most important task than the possession of material goods. When forming the intellectual nation, values in the field of education and science become investments for the development of the society, as well as education and science today transformed into the most important capital.

Keywords: human capital, humanitarian technology, intangible assets, intelligent nation, society of knowledge

Procedia PDF Downloads 317

Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan

Abstract:

Gliomas are most challenging and aggressive type of tumors which appear in different sizes, locations, and scattered boundaries. CNN is most efficient deep learning approach with outstanding capability of solving image analysis problems. A fully automatic deep learning based 2D-CNN model for brain tumor segmentation is presented in this paper. We used small convolution filters (3 x 3) to make architecture deeper. We increased convolutional layers for efficient learning of complex features from large dataset. We achieved better results by pushing convolutional layers up to 16 layers for HGG model. We achieved reliable and accurate results through fine-tuning among dataset and hyper-parameters. Pre-processing of this model includes generation of brain pipeline, intensity normalization, bias correction and data augmentation. We used the BRATS-2015, and Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.81 for complete, 0.79 for core, 0.80 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

Keywords: brain tumor segmentation, convolutional neural networks, deep learning, HGG

Procedia PDF Downloads 256

Authors: Hong Mengdi, Li Jianan, Ji Fei, Chen Aiting, Wang Qian

Abstract:

Objective: To overcome the communication barriers that audiologists encounter during cochlear implant mapping, particularly the challenge of eliciting subjective feedback from recipients regarding electrical stimulation, and to enhance the capabilities of existing technologies, we teamed up with software engineers to design an interactive approach for patient-audiologist communication. This approach employs a tablet (PAD) as the interface for a communication and feedback system between patients and audiologists during the mapping process, known as the Cochlear Implant Mapping Assistance System. Methods: Capitalizing on the touchscreen functionality of the PAD, the recipients' subjective feedback during cochlear implant mapping is instantly transmitted to the audiologist's mapping computer. The system acts as a platform for auditory assessment instruments, facilitating immediate evaluation of recipients' post-mapping hearing and speech discrimination capabilities. Furthermore, the system is designed to augment the visual reinforcement audiometry (VRA) process. The system consists of six modules, including three testing projects: loudness testing, hearing threshold testing, and loudness balance testing; two assessment projects: warble tone testing and digit speech testing; and one VRA animation project. It also incorporates speech-to-text and text input display functions tailored to accommodate speech communication difficulties in hearing-impaired individuals, with pre-installed common exchange content between audiologists and recipients. Audiologists can input sentences by selecting options. The system supports switching between Chinese and English versions, suitable for audiologists and recipients who use English, facilitating international application of the system. Results: The Cochlear Implant Mapping Assistance System has been in use for over a year in the Auditory Implant Center of the Department of Otology and Neurotology, Medical Center of Otology and Head & Neck Surgery, Chinese PLA General Hospital, with more than 300 recipients using this mapping system. Currently, the system operates stably, with both audiologists and recipients providing positive feedback, indicating a significant improvement over previous methods. It is particularly well-received by pediatric recipients, significantly enhancing the work efficiency of audiologists and improving the feedback efficiency and accuracy of recipients. The system enhances the comprehensibility for cochlear implant recipients, improves wearing comfort and user experience, facilitates cochlear implant auditory mapping, and increases the collection of previously challenging-to-obtain data during the existing assisted mapping process, such as loudness testing data, electrical stimulation testing data, warble tone testing data, loudness balance testing data, digit speech testing data, and visual reinforcement audiometry testing data. Real-time data recording improves the accuracy of assisted mapping. The interface design is meticulously crafted to accommodate patients of varying ages and cognitive abilities, featuring an intuitive design that allows for effortless, guidance-free use by patients.

Keywords: audiologist, subjective feedback, mapping, cochlear implant

Procedia PDF Downloads 20

Authors: Billel Kenidra, Mohamed Benmohammed

Abstract:

Data mining technique used in the field of clustering is a subject of active research and assists in biological pattern recognition and extraction of new knowledge from raw data. Clustering means the act of partitioning an unlabeled dataset into groups of similar objects. Each group, called a cluster, consists of objects that are similar between themselves and dissimilar to objects of other groups. Several clustering methods are based on partitional clustering. This category attempts to directly decompose the dataset into a set of disjoint clusters leading to an integer number of clusters that optimizes a given criterion function. The criterion function may emphasize a local or a global structure of the data, and its optimization is an iterative relocation procedure. The K-Means algorithm is one of the most widely used partitional clustering techniques. Since K-Means is extremely sensitive to the initial choice of centers and a poor choice of centers may lead to a local optimum that is quite inferior to the global optimum, we propose a strategy to initiate K-Means centers. The improved K-Means algorithm is compared with the original K-Means, and the results prove how the efficiency has been significantly improved.

Keywords: microarray data mining, biological pattern recognition, partitional clustering, k-means algorithm, centroid initialization

Procedia PDF Downloads 190

Authors: Rasha Alsabbah

Abstract:

This study explores the relationship between polite language use and religion in the Iraqi culture in computer mediated communication. It tackles the speech acts where these expressions are employed, the frequency of their occurrence and the aims behind them. It also investigates if they have equivalent expressions in English and the possibility of translating them in intercultural communication. Despite the wide assumption that language is a reflection of culture and religion, it started to grant the attention sociologists during the recent 40 years when scholars have questioned the possible interconnection between religion and language in which religion is used as a mean of producing language and performing pragmatic functions. It is presumed that Arabs in general, and Iraqis in particular, have an inclination to use religious vocabulary in showing politeness in their greeting and other speech acts. Due to Islamic religion and culture’s influences, it is observed that Iraqis are very much concerned of maintaining social solidarity and harmonious relationships which make religion a politeness strategy that operates as the key point of their social behaviours. In addition, religion has found to influence almost all their interactions in which they have a tendency of invoking religious expressions, the lexicon of Allah (God), and Qur’anic verses in their daily politeness discourse. This aspect of Islamic culture may look strange, especially to people who come from individualist societies, such as England. Data collection in this study is based on messaging applications like Viber, WhatsApp, and Facebook. After gaining the approval of the participants, there was an investigation for the different aims behind these expressions and the pragmatic function that they perform. It is found that Iraqis tend to incorporate the lexicon of Allah in most of their communication. Such employment is not only by religious people but also by individuals who do not show strong commitment to religion. Furthermore, the social distance and social power between people do not play a significant role in increasing or reducing the rate of using these expressions. A number of these expressions, though can be translated into English, do not have one to one counterpart or reflect religious feeling. In addition, they might sound odd upon being translated or transliterated in oral and written communication in intercultural communication.

Keywords: computer mediated communication (CMC), intercultural communication, politeness, religion, situation bound utterances rituals, speech acts

Procedia PDF Downloads 402

Authors: Barnali Saha

Abstract:

Dalit writing is the interventionalist voice of the dispossessed subaltern in the cultural economy of the society. As such, Dalit writing, including Dalit poetry, considers the contradictions that permeate the socio-cultural structure historically allocated and religiously sanctioned in the Indian subcontinent. As an epicenter of all Dalit experiences of trauma and violence, the poetics the Dalit body is deeply rooted in the peripheral space socially assigned to it by anachronistic caste-based litigation. An appraisal of Dalit creative-critical work by writers like Sharan Kumar Limbale, Arjun Dangle, Namdeo Dhasal, Om Prakash Valmiki, Muktibodh and others underscore the conjunction of the physical, psychical and the psychological in their interpretation of Dalit consciousness. They put forward the idea that Dalit poetry is begotten by the trauma of societal oppression and therefore, Dalit language and its revitalization are two elements obdurately linked to Dalit poetics. The present research paper seeks to read the problematization of the Dalit agency through the conduit of the Dalit voice wherein the anatomical category of the mouth is closely related to the question of Dalit identity. Theoretically aligned to Heidegger’s notion of language as the house of being and Bachelard’s assertion of a house as an ideal metaphor of poetic imagination and Dylan Trigg’s view of the coeval existence of space and body, the paper examines a series of selected poems by Dalit poetic voices to examine how their distinct Dalit point of view underscores Dalit speech and directs our attention to the historical abstraction of it. The paper further examines how speech as a category in Dalit writing places the Dalit somatic entity as a site of contestation with the ‘Mouth’ as a loaded symbolic category inspiring rebellion and resistance. And as the quintessential purpose of Dalit literature is the unleashing of Dalit voice from the anti-verbal domain of social decrepitude, Dalit poetry needs to be critically read based on the experience of the mouth and the patois.

Keywords: Dalit, poetry, speech, mouth, subaltern, minority, exploitation, space

Procedia PDF Downloads 194

Authors: Mouli Banga, Chaya Ravindra

Abstract:

Wound classification is a crucial step in wound diagnosis. An effective classifier can aid wound specialists in identifying wound types with reduced financial and time investments, facilitating the determination of optimal treatment procedures. This study presents a deep neural network-based classifier that leverages wound images and their corresponding locations to categorize wounds into various classes, such as diabetic, pressure, surgical, and venous ulcers. By incorporating a developed body map, the process of tagging wound locations is significantly enhanced, providing healthcare specialists with a more efficient tool for wound analysis. We conducted a comparative analysis between two prominent convolutional neural network models, ResNet50 and MobileNetV2, utilizing a dataset of 730 images. Our findings reveal that the RestNet50 outperforms MovileNetV2, achieving an accuracy of approximately 90%, compared to MobileNetV2’s 83%. This disparity highlights the superior capability of ResNet50 in the context of this dataset. The results underscore the potential of integrating deep learning with spatial data to improve the precision and efficiency of wound diagnosis, ultimately contributing to better patient outcomes and reducing healthcare costs.

Keywords: wound classification, MobileNetV2, ResNet50, multimodel

Procedia PDF Downloads 32

Authors: Semeh Ben Salem, Sami Naouali, Moetez Sallami

Abstract:

Clustering is a well known data mining technique used in pattern recognition and information retrieval. The initial dataset to be clustered can either contain categorical or numeric data. Each type of data has its own specific clustering algorithm. In this context, two algorithms are proposed: the k-means for clustering numeric datasets and the k-modes for categorical datasets. The main encountered problem in data mining applications is clustering categorical dataset so relevant in the datasets. One main issue to achieve the clustering process on categorical values is to transform the categorical attributes into numeric measures and directly apply the k-means algorithm instead the k-modes. In this paper, it is proposed to experiment an approach based on the previous issue by transforming the categorical values into numeric ones using the relative frequency of each modality in the attributes. The proposed approach is compared with a previously method based on transforming the categorical datasets into binary values. The scalability and accuracy of the two methods are experimented. The obtained results show that our proposed method outperforms the binary method in all cases.

Keywords: clustering, unsupervised learning, pattern recognition, categorical datasets, knowledge discovery, k-means

Procedia PDF Downloads 259

Authors: Monireh Ahmadi Bani, Adel Khorramrouz, Lalenoor Morvarid, Bagheri Mahtab

Abstract:

Background:- Foot disorders are common in musculoskeletal problems. Plantar pressure distribution measurement is one the most important part of foot disorders diagnosis for quantitative analysis. However, the association of plantar pressure and foot disorders is not clear. With the growth of dataset and machine learning methods, the relationship between foot disorders and plantar pressures can be detected. Significance of the study:- The purpose of this study was to predict the probability of common foot disorders based on peak plantar pressure distribution and center of pressure during walking. Methodologies:- 2323 participants were assessed in a foot therapy clinic between 2015 and 2021. Foot disorders were diagnosed by an experienced physician and then they were asked to walk on a force plate scanner. After the data preprocessing, due to the difference in walking time and foot size, we normalized the samples based on time and foot size. Some of force plate variables were selected as input to a deep neural network (DNN), and the probability of any each foot disorder was measured. In next step, we used support vector machine (SVM) and run dataset for each foot disorder (classification of yes or no). We compared DNN and SVM for foot disorders prediction based on plantar pressure distributions and center of pressure. Findings:- The results demonstrated that the accuracy of deep learning architecture is sufficient for most clinical and research applications in the study population. In addition, the SVM approach has more accuracy for predictions, enabling applications for foot disorders diagnosis. The detection accuracy was 71% by the deep learning algorithm and 78% by the SVM algorithm. Moreover, when we worked with peak plantar pressure distribution, it was more accurate than center of pressure dataset. Conclusion:- Both algorithms- deep learning and SVM will help therapist and patients to improve the data pool and enhance foot disorders prediction with less expense and error after removing some restrictions properly.

Keywords: deep neural network, foot disorder, plantar pressure, support vector machine

Procedia PDF Downloads 357

Authors: Seini G. Kaufusi

Abstract:

Background. Physician-assisted death (PAD) has and continues to be a controversial issue in the U.S. Dying with dignity statutes exists in 9 U.S. jurisdictions that permit competent adults diagnosed with a terminal illness and given a prognosis of 6 month or less to live to request medication to hasten death. Robust advocacy for and against PAD influences policy, and opinions vary. Aim. This study aims to explore the association between race and the attitudes toward physician-assisted death in the U.S. Methods. Data for this study derives from the General Social Survey (GSS) dataset, a national survey conducted by the National Opinion Research Center (NORC) that focuses on the opinions and values of American’s. A cross-sectional design and probability sample from the 2018 data set was used to randomly select respondents. Results. The results indicated that race is significantly associated with attitudes towards physician-assisted death. The level of significance suggests a strong positive association, and the direction indicated that Black and Other racial groups have higher rates of positive decision about PAD. Conclusion. Although attitudes towards PAD varied, Black and other racial groups had favorable decisions for PAD. Further research is crucial in the continuous debate on PAD and understanding the influences of predictors for or against PAD.

Keywords: attitudes, euthanasia, physician-assisted death, race

Procedia PDF Downloads 162

Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas

Abstract:

An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.

Keywords: anthrophony, hydrophone, k-means, machine learning

Procedia PDF Downloads 170

Authors: Jeng-Shin Sheu, Qi-Xun Zheng

Abstract:

This paper mainly discusses a method of separating speech when using a microphone array without knowing the number and direction of sound sources. In recent years, there have been many studies on the method of separating signals by using masking, but most of the separation methods must be operated under the condition of a known number of sound sources. Such methods cannot be used for real-time applications. In our method, this paper uses Circular-Integrated-Cross-Spectrum to estimate the statistical histogram distribution of the direction of arrival (DOA) to obtain the number of sound sources and sound in the mixed-signal Source direction. In calculating the relevant parameters of the ring integrated cross-spectrum, the phase (Phase of the Cross-Power Spectrum) and phase rotation factors (Phase Rotation Factors) calculated by the cross power spectrum of each microphone pair are used. In the part of separating speech, it uses the DOA weighting and shielding separation method to calculate the sound source direction (DOA) according to each T-F unit (time-frequency point). The weight corresponding to each T-F unit can be used to strengthen the intensity of each sound source from the T-F unit and reduce the influence of the remaining sound sources, thereby achieving voice separation.

Keywords: real-time, spectrum analysis, sound source localization, sound source separation

Procedia PDF Downloads 155

Authors: Laura C. Solzbacher, Caja Thimm

Abstract:

Journalists worldwide have been confronted with a variety of ethical challenges over the last years. Because of massive changes in media technology and the public sphere, especially online journalism has trouble to uphold the fundamental values of journalism. In particular, the increasing amount of fake news and hate speech puts journalists under more and more pressure. In order to understand better how journalists judge this development and how they adapt in their daily work, a survey with journalists in Germany was carried out. 303 professional journalists participated in an online questionnaire. Results show that 65% underline that economic pressure grows and nearly the same number describe a change in the role of journalists in society. Furthermore, 61% agree that they put more time into research to secure their work against accusations of fabricating fake news. Interestingly, over 60% see a change in the role of journalists in society. The majority (85%) confirms that print journalism has to give way for online platforms and that the influence of social media for journalism grows (75%). Half of the surveyed advocate for more personalized public activism on part of journalists, such as appearance in talk shows and public talks. The results of the study will be discussed in light of the ongoing debate on ethical standards as a condition for a sustainable and trustworthy digital public sphere.

Keywords: ethics, fake news, journalism, public sphere

Procedia PDF Downloads 269

Authors: Lavanya Srinivasan

Abstract:

Biometric identification is to identify unique features in a person like fingerprints, iris, ear, and voice recognition that need the subject's permission and physical contact. Gait biometric is used to identify the unique gait of the person by extracting moving features. The main advantage of gait biometric to identify the gait of a person at a distance, without any physical contact. In this work, the gait biometric is used for person re-identification. The person walking naturally compared with the same person walking with bag, coat, and case recorded using longwave infrared, short wave infrared, medium wave infrared, and visible cameras. The videos are recorded in rural and in urban environments. The pre-processing technique includes human identified using YOLO, background subtraction, silhouettes extraction, and synthesis Gait Entropy Image by averaging the silhouettes. The moving features are extracted from the Gait Entropy Energy Image. The extracted features are dimensionality reduced by the principal component analysis and recognised using different classifiers. The comparative results with the different classifier show that linear discriminant analysis outperforms other classifiers with 95.8% for visible in the rural dataset and 94.8% for longwave infrared in the urban dataset.

Keywords: biometric, gait, silhouettes, YOLO

Procedia PDF Downloads 172

Authors: Hsin-Yang Wang, K. M. A. Salam, Ying-Jia Lin, Daniel Tan, Tzu-Hsuan Chou, Hung-Yu Kao

Abstract:

Detecting user intent from natural language expression has a wide variety of use cases in different natural language processing applications. Recently few-shot training has a spike of usage on commercial domains. Due to the lack of significant sample features, the downstream task performance has been limited or leads to an unstable result across different domains. As a state-of-the-art method, the pre-trained BERT model gathering the sentence-level information from a large text corpus shows improvement on several NLP benchmarks. In this research, we are proposing a method to change multi-class classification tasks into binary classification tasks, then use the confidence score to rank the results. As a language model, BERT performs well on sequence data. In our experiment, we change the objective from predicting labels into finding the relations between words in sequence data. Our proposed method achieved 71.0% accuracy in the internal intent detection dataset and 63.9% accuracy in the HuffPost dataset. Acknowledgment: This work was supported by NCKU-B109-K003, which is the collaboration between National Cheng Kung University, Taiwan, and SoftBank Corp., Tokyo.

Keywords: OSML, BERT, text classification, one shot

Procedia PDF Downloads 101

Authors: Vinay P., Srinivas K. S.

Abstract:

Low Light Image Enhancement is of utmost impor- tance in computer vision based tasks. Applications include vision systems for autonomous driving, night vision devices for defence systems, low light object detection tasks. Many of the existing deep learning methods are resource intensive during the inference step and take considerable time for processing. The algorithm should take considerably less than 41 milliseconds in order to process a real-time video feed with 24 frames per second and should be even less for a video with 30 or 60 frames per second. The paper presents a fast and efficient solution which has two main advantages, it has the potential to be used for a real-time video feed, and it can be used in low compute environments because of the lightweight nature. The proposed solution is a pipeline of three steps, the first one is the use of a simple function to map input RGB values to output RGB values, the second is to balance the colors and the final step is to adjust the contrast of the image. Hence a custom dataset is carefully prepared using images taken in low and bright lighting conditions. The preparation of the dataset, the proposed model, the processing time are discussed in detail and the quality of the enhanced images using different methods is shown.

Keywords: low light image enhancement, real-time video, computer vision, machine learning

Procedia PDF Downloads 204

Authors: Cyrus Addy, Venkata Sriram Siddhardh Nadendla, Kwame Awuah-Offei

Abstract:

Surface robots in modern underground mine rescue operations suffer from several limitations in enabling a prompt self-rescue. Therefore, the possibility of designing and deploying in-mine robots to expedite miner self-rescue can have a transformative impact on miner safety. These in-mine robots for miner self-rescue can be envisioned to carry out diverse tasks such as object detection, autonomous navigation, and payload delivery. Specifically, this paper investigates the challenges in the design of object detection algorithms for in-mine robots using thermal images, especially to detect people in real-time. A total of 125 thermal images were collected in the Missouri S&T Experimental Mine with the help of student volunteers using the FLIR TG 297 infrared camera, which were pre-processed into training and validation datasets with 100 and 25 images, respectively. Three state-of-the-art, pre-trained real-time object detection models, namely YOLOv5, YOLO-FIRI, and YOLOv8, were considered and re-trained using transfer learning techniques on the training dataset. On the validation dataset, the re-trained YOLOv8 outperforms the re-trained versions of both YOLOv5, and YOLO-FIRI.

Keywords: miner self-rescue, object detection, underground mine, YOLO

Procedia PDF Downloads 81

Authors: Mikheil Kalmakhelidze

Abstract:

Record linkage (RL) problem has become more and more important in recent years due to the growing interest towards big data analysis. The problem can be formulated in a very simple way: Given two entries a and b of a database, decide whether they represent the same object or not. There are two classical deterministic and probabilistic ways of solving the RL problem. Using simple Bayes classifier in many cases produces useful results but sometimes they show to be poor. In recent years several successful approaches have been made towards solving specific RL problems by neural network algorithms including single layer perception, multilayer back propagation network etc. In our work, we model the RL problem for specific dataset of student applications in fuzzy description logic (FDL) where linkage of specific pair (a,b) depends on the truth value of corresponding formula A(a,b) in a canonical FDL model. As a main result, we build neural network for deciding truth value of FDL formulas in a canonical model and thus link RL problem to machine learning. We apply the approach to dataset with 10000 entries and also compare to classical RL solving approaches. The results show to be more accurate than standard probabilistic approach.

Keywords: description logic, fuzzy logic, neural networks, record linkage

Procedia PDF Downloads 272

Authors: Hiromi Kawai

Abstract:

This study investigates the nature of EFL older children’s L2 perceptive and productive abilities using classroom data, in order to find a pedagogical solution to the teaching of L2 sounds at an early stage of learning in a formal school setting. It is still inconclusive whether older children with only EFL formal school instruction at the initial stage of L2 learning are able to attain native-like perception and production in English within the very limited amount of exposure to the target language available. Based on the notion of the lack of study of EFL Japanese children’s acquisition of English segments, the researcher uses a model of L1 speech processing which was developed for investigating L1 English children’s speech and literacy difficulties using a psycholinguistic framework. The model is composed of input channel, output channel, and lexical representation, and examines how a child receives information from spoken or written language, remembers and stores it within the lexical representations and how the child selects and produces spoken or written words. Concerning language universality and language specificity in the language acquisitional process, the aim of finding any sound errors in L1 English children seemed to conform to the author’s intention to find abilities of English sounds in older Japanese children at the novice level of English in an EFL setting. 104 students in Grade 5 (between the ages of 10 and 11 years old) of an elementary school in Tokyo participated in this study. Four tests to measure their perceptive ability and three oral repetition tests to measure their productive ability were conducted with/without reference to lexical representation. All the test items were analyzed to calculate item facility (IF) indices, and correlational analyses and Structural Equation Modeling (SEM) were conducted to examine the relationship between the receptive ability and the productive ability. IF analysis showed that (1) the participants were better at perceiving a segment than producing a segment, (2) they had difficulty in auditory discrimination of paired consonants when one of them does not exist in the Japanese inventory, (3) they had difficulty in both perceiving and producing English vowels, and (4) their L1 loan word knowledge had an influence on their ability to perceive and produce L2 sounds. The result of the Multiple Regression Modeling showed that the two production tests could predict the participants’ auditory ability of real words in English. The result of SEM showed that the hypothesis that perceptive ability affects productive ability was supported. Based on these findings, the author discusses the possible explicit method of teaching English segments to EFL older children in a formal school setting.

Keywords: EFL older children, english segments, perception, production, speech processing system

Procedia PDF Downloads 243

Authors: Mehran Asadi, Afrand Agah

Abstract:

In data mining, partitioning is used as a fundamental tool for classification. With the help of partitioning, we study the structure of data, which allows us to envision decision rules, which can be applied to classification trees. In this research, we used online social network dataset and all of its attributes (e.g., Node features, labels, etc.) to determine what constitutes an above average chance of being a divergent node. We used the R statistical computing language to conduct the analyses in this report. The data were found on the UC Irvine Machine Learning Repository. This research introduces the basic concepts of classification in online social networks. In this work, we utilize overfitting and describe different approaches for evaluation and performance comparison of different classification methods. In classification, the main objective is to categorize different items and assign them into different groups based on their properties and similarities. In data mining, recursive partitioning is being utilized to probe the structure of a data set, which allow us to envision decision rules and apply them to classify data into several groups. Estimating densities is hard, especially in high dimensions, with limited data. Of course, we do not know the densities, but we could estimate them using classical techniques. First, we calculated the correlation matrix of the dataset to see if any predictors are highly correlated with one another. By calculating the correlation coefficients for the predictor variables, we see that density is strongly correlated with transitivity. We initialized a data frame to easily compare the quality of the result classification methods and utilized decision trees (with k-fold cross validation to prune the tree). The method performed on this dataset is decision trees. Decision tree is a non-parametric classification method, which uses a set of rules to predict that each observation belongs to the most commonly occurring class label of the training data. Our method aggregates many decision trees to create an optimized model that is not susceptible to overfitting. When using a decision tree, however, it is important to use cross-validation to prune the tree in order to narrow it down to the most important variables.

Keywords: online social networks, data mining, social cloud computing, interaction and collaboration

Procedia PDF Downloads 157

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 80

Authors: Fei Gao, Rodolfo C. Raga Jr.

Abstract:

This research proposal will ascertain the major risk factors for diabetes and to design a predictive model for risk assessment. The project aims to improve diabetes early detection and management by utilizing data science techniques, which may improve patient outcomes and healthcare efficiency. The phase relation values of each attribute were used to analyze and choose the attributes that might influence the examiner's survival probability using Diabetes Health Indicators Dataset from Kaggle’s data as the research data. We compare and evaluate eight machine learning algorithms. Our investigation begins with comprehensive data preprocessing, including feature engineering and dimensionality reduction, aimed at enhancing data quality. The dataset, comprising health indicators and medical data, serves as a foundation for training and testing these algorithms. A rigorous cross-validation process is applied, and we assess their performance using five key metrics like accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). After analyzing the data characteristics, investigate their impact on the likelihood of diabetes and develop corresponding risk indicators.

Keywords: diabetes, risk factors, predictive model, risk assessment, data science techniques, early detection, data analysis, Kaggle

Procedia PDF Downloads 74

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 128

Authors: A. M. John-Otumu, M. M. Rahman, O. C. Nwokonkwo, M. C. Onuoha

Abstract:

Online social media networks have long served as a primary arena for group conversations, gossip, text-based information sharing and distribution. The use of natural language processing techniques for text classification and unbiased decision-making has not been far-fetched. Proper classification of this textual information in a given context has also been very difficult. As a result, we decided to conduct a systematic review of previous literature on sentiment classification and AI-based techniques that have been used in order to gain a better understanding of the process of designing and developing a robust and more accurate sentiment classifier that can correctly classify social media textual information of a given context between hate speech and inverted compliments with a high level of accuracy by assessing different artificial intelligence techniques. We evaluated over 250 articles from digital sources like ScienceDirect, ACM, Google Scholar, and IEEE Xplore and whittled down the number of research to 31. Findings revealed that Deep learning approaches such as CNN, RNN, BERT, and LSTM outperformed various machine learning techniques in terms of performance accuracy. A large dataset is also necessary for developing a robust sentiment classifier and can be obtained from places like Twitter, movie reviews, Kaggle, SST, and SemEval Task4. Hybrid Deep Learning techniques like CNN+LSTM, CNN+GRU, CNN+BERT outperformed single Deep Learning techniques and machine learning techniques. Python programming language outperformed Java programming language in terms of sentiment analyzer development due to its simplicity and AI-based library functionalities. Based on some of the important findings from this study, we made a recommendation for future research.

Keywords: artificial intelligence, natural language processing, sentiment analysis, social network, text

Procedia PDF Downloads 115

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 72

Authors: Niousha Bagheri Khulenjani, Mohammad Saniee Abadeh

Abstract:

Learning from very big datasets is a significant problem for most present data mining and machine learning algorithms. MicroRNA (miRNA) is one of the important big genomic and non-coding datasets presenting the genome sequences. In this paper, a hybrid method for the classification of the miRNA data is proposed. Due to the variety of cancers and high number of genes, analyzing the miRNA dataset has been a challenging problem for researchers. The number of features corresponding to the number of samples is high and the data suffer from being imbalanced. The feature selection method has been used to select features having more ability to distinguish classes and eliminating obscures features. Afterward, a Convolutional Neural Network (CNN) classifier for classification of cancer types is utilized, which employs a Genetic Algorithm to highlight optimized hyper-parameters of CNN. In order to make the process of classification by CNN faster, Graphics Processing Unit (GPU) is recommended for calculating the mathematic equation in a parallel way. The proposed method is tested on a real-world dataset with 8,129 patients, 29 different types of tumors, and 1,046 miRNA biomarkers, taken from The Cancer Genome Atlas (TCGA) database.

Keywords: cancer classification, feature selection, deep learning, genetic algorithm

Procedia PDF Downloads 111

Authors: Mohammad Bakhshi, Firas Al Janabi

Abstract:

High resolution rain data are very important to fulfill the input of hydrological models. Among models of high-resolution rainfall data generation, the temporal disaggregation was chosen for this study. The paper attempts to generate three different rainfall resolutions (4-hourly, hourly and 10-minutes) from daily for around 20-year record period. The process was done by DiMoN tool which is based on random cascade model and method of fragment. Differences between observed and simulated rain dataset are evaluated with variety of statistical and empirical methods: Kolmogorov-Smirnov test (K-S), usual statistics, and Exceedance probability. The tool worked well at preserving the daily rainfall values in wet days, however, the generated data are cumulated in a shorter time period and made stronger storms. It is demonstrated that the difference between generated and observed cumulative distribution function curve of 4-hourly datasets is passed the K-S test criteria while in hourly and 10-minutes datasets the P-value should be employed to prove that their differences were reasonable. The results are encouraging considering the overestimation of generated high-resolution rainfall data.

Keywords: DiMoN Tool, disaggregation, exceedance probability, Kolmogorov-Smirnov test, rainfall

Procedia PDF Downloads 201

Authors: Mary Jane B. Suarez

Abstract:

Public speaking anxiety (PSA), also known as speech anxiety, is innumerably persistent in any traditional communication classes, especially for students who learn English as a second language. The speech anxiety intensifies when communication skills assessments have taken their toll in an online or a remote mode of learning due to the perils of the COVID-19 virus. Both teachers and students have experienced vast ambiguity on how to realize a still effective way to teach and learn speaking skills amidst the pandemic. Communication skills assessments like public speaking, oral presentations, and student reporting have defined their new meaning using Google Meet, Zoom, and other online platforms. Though using such technologies has paved for more creative ways for students to acquire and develop communication skills, the effectiveness of using such assessment tools stands in question. This mixed method study aimed to determine the factors that affected the public speaking skills of students in a communication class, to probe on the assessment gaps in assessing speaking skills of students attending online classes vis-à-vis the implementation of remote and blended modalities of learning, and to recommend ways on how to address the public speaking anxieties of students in performing a speaking task online and to bridge the assessment gaps based on the outcome of the study in order to achieve a smooth segue from online to on-ground instructions maneuvering towards a much better post-pandemic academic milieu. Using a convergent parallel design, both quantitative and qualitative data were reconciled by probing on the public speaking anxiety of students and the potential assessment gaps encountered in an online English communication class under remote and blended learning. There were four phases in applying the convergent parallel design. The first phase was the data collection, where both quantitative and qualitative data were collected using document reviews and focus group discussions. The second phase was data analysis, where quantitative data was treated using statistical testing, particularly frequency, percentage, and mean by using Microsoft Excel application and IBM Statistical Package for Social Sciences (SPSS) version 19, and qualitative data was examined using thematic analysis. The third phase was the merging of data analysis results to amalgamate varying comparisons between desired learning competencies versus the actual learning competencies of students. Finally, the fourth phase was the interpretation of merged data that led to the findings that there was a significantly high percentage of students' public speaking anxiety whenever students would deliver speaking tasks online. There were also assessment gaps identified by comparing the desired learning competencies of the formative and alternative assessments implemented and the actual speaking performances of students that showed evidence that public speaking anxiety of students was not properly identified and processed.

Keywords: blended learning, communication skills assessment, public speaking anxiety, speech anxiety

Procedia PDF Downloads 102

Authors: Shriya Shukla, Lachin Fernando

Abstract:

Pneumonia, a leading cause of mortality in young children globally, presents significant diagnostic challenges, particularly in resource-limited settings. This study presents an approach to diagnosing pediatric pneumonia using Chest X-Ray (CXR) images, employing a lightweight MobileNetV2 model enhanced with synthetic data augmentation. Addressing the challenge of dataset scarcity and imbalance, the study used a Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to generate synthetic CXR images, improving the representation of normal cases in the pediatric dataset. This approach not only addresses the issues of data imbalance and scarcity prevalent in medical imaging but also provides a more accessible and reliable diagnostic tool for early pneumonia detection. The augmented data improved the model’s accuracy and generalization, achieving an overall accuracy of 95% in pneumonia detection. These findings highlight the efficacy of the MobileNetV2 model, offering a computationally efficient yet robust solution well-suited for resource-constrained environments such as mobile health applications. This study demonstrates the potential of synthetic data augmentation in enhancing medical image analysis for critical conditions like pediatric pneumonia.

Keywords: pneumonia, MobileNetV2, image classification, GAN, VAE, deep learning

Procedia PDF Downloads 125