Search results for: speech dataset

Authors: Md Rafiqul Islam, Ashir Ahmed, Anwaar Ulhaq, Abu Raihan M. Kamal, Yuan Miao, Hua Wang

Abstract:

Mental health of people is equally important as of their physical health. Mental health and well-being are influenced not only by individual attributes but also by the social circumstances in which people find themselves and the environment in which they live. Like physical health, there is a number of internal and external factors such as biological, social and occupational factors that could influence the mental health of people. People living in poverty, suffering from chronic health conditions, minority groups, and those who exposed to/or displaced by war or conflict are generally more likely to develop mental health conditions. However, to authors’ best knowledge, there is dearth of knowledge on the impact of workplace (especially the highly stressed IT/Tech workplace) on the mental health of its workers. This study attempts to examine the factors influencing the mental health of tech workers. A publicly available dataset containing more than 65,000 cells and 100 attributes is examined for this purpose. Number of machine learning techniques such as ‘Decision Tree’, ‘K nearest neighbor’ ‘Support Vector Machine’ and ‘Ensemble’, are then applied to the selected dataset to draw the findings. It is anticipated that the analysis reported in this study would contribute in presenting useful insights on the attributes contributing in the mental health of tech workers using relevant machine learning techniques.

Keywords: mental disorder, diagnosis, occupational stress, IT workplace

Procedia PDF Downloads 278

Authors: Aditya Karade, Sharada Falane, Dhananjay Deshmukh, Vijaykumar Mantri

Abstract:

Brain tumors pose a significant challenge in healthcare due to their complex nature and impact on patient outcomes. The application of deep learning (DL) algorithms in medical imaging have shown promise in accurate and efficient brain tumour detection. This paper explores the performance of various pre-trained DL models ResNet50, Xception, InceptionV3, EfficientNetB0, DenseNet121, NASNetMobile, VGG19, VGG16, and MobileNet on a brain tumour dataset sourced from Figshare. The dataset consists of MRI scans categorizing different types of brain tumours, including meningioma, pituitary, glioma, and no tumour. The study involves a comprehensive evaluation of these models’ accuracy and effectiveness in classifying brain tumour images. Data preprocessing, augmentation, and finetuning techniques are employed to optimize model performance. Among the evaluated deep learning models for brain tumour detection, ResNet50 emerges as the top performer with an accuracy of 98.86%. Following closely is Xception, exhibiting a strong accuracy of 97.33%. These models showcase robust capabilities in accurately classifying brain tumour images. On the other end of the spectrum, VGG16 trails with the lowest accuracy at 89.02%.

Keywords: brain tumour, MRI image, detecting and classifying tumour, pre-trained models, transfer learning, image segmentation, data augmentation

Procedia PDF Downloads 58

Authors: Manasvi Pinnaka, Brianna Chrisman

Abstract:

Cystic fibrosis patients often develop lung infections that range anywhere in severity from mild to life-threatening due to the presence of thick and sticky mucus that fills their airways. Since many of these infections are chronic, they not only affect a patient’s ability to breathe but also increase the chances of mortality by respiratory failure. With a publicly available dataset of DNA sequences from bacterial species in the lung microbiome of cystic fibrosis patients, the correlations between different microbial species in the lung and the extent of deterioration of lung function were investigated. 16S sequencing technologies were used to determine the microbiome composition of the samples in the dataset. For the statistical analyses, referencing helped distinguish between taxonomies, and the proportions of certain taxa relative to another were determined. It was found that the Fusobacterium, Actinomyces, and Leptotrichia microbial types all had a positive correlation with the FEV1 score, indicating the potential displacement of these species by pathogens as the disease progresses. However, the dominant pathogens themselves, including Pseudomonas aeruginosa and Staphylococcus aureus, did not have statistically significant negative correlations with the FEV1 score as described by past literature. Examining the lung microbiology of cystic fibrosis patients can help with the prediction of the current condition of lung function, with the potential to guide doctors when designing personalized treatment plans for patients.

Keywords: bacterial infections, cystic fibrosis, lung microbiome, 16S sequencing

Procedia PDF Downloads 85

Authors: Ma. Gracia Corazon Cayanan, Kai Yuen Cheong, Li Sha

Abstract:

Training a language model for a minority language has been a challenging task. The lack of available corpora to train and fine-tune state-of-the-art language models is still a challenge in the area of Natural Language Processing (NLP). Moreover, the need for high computational resources and bulk data limit the attainment of this task. In this paper, we presented the following contributions: (1) we introduce and used a translation pair set of Tagalog and English (TL-EN) in pre-training a language model to a minority language resource; (2) we fine-tuned and evaluated top-ranking and pre-trained semantic textual similarity binary task (STSB) models, to both TL-EN and STS dataset pairs. (3) then, we reduced the size of the model to offset the need for high computational resources. Based on our results, the models that were pre-trained to translation pairs and STS pairs can perform well for STSB task. Also, having it reduced to a smaller dimension has no negative effect on the performance but rather has a notable increase on the similarity scores. Moreover, models that were pre-trained to a similar dataset have a tremendous effect on the model’s performance scores.

Keywords: semantic matching, semantic textual similarity binary task, low resource minority language, fine-tuning, dimension reduction, transformer models

Procedia PDF Downloads 194

Authors: Cuneyt Yucelbas, Seral Ozsen, Sule Yucelbas, Gulay Tezel

Abstract:

Due to the fact that there exist only a small number of complex systems in artificial immune system (AIS) that work out nonlinear problems, nonlinear AIS approaches, among the well-known solution techniques, need to be developed. Gaussian function is usually used as similarity estimation in classification problems and pattern recognition. In this study, diagnosis of breast cancer, the second type of the most widespread cancer in women, was performed with different distance calculation functions that euclidean, gaussian and gaussian-euclidean hybrid function in the clonal selection model of classical AIS on Wisconsin Breast Cancer Dataset (WBCD), which was taken from the University of California, Irvine Machine-Learning Repository. We used 3-fold cross validation method to train and test the dataset. According to the results, the maximum test classification accuracy was reported as 97.35% by using of gaussian-euclidean hybrid function for fold-3. Also, mean of test classification accuracies for all of functions were obtained as 94.78%, 94.45% and 95.31% with use of euclidean, gaussian and gaussian-euclidean, respectively. With these results, gaussian-euclidean hybrid function seems to be a potential distance calculation method, and it may be considered as an alternative distance calculation method for hard nonlinear classification problems.

Keywords: artificial immune system, breast cancer diagnosis, Euclidean function, Gaussian function

Procedia PDF Downloads 424

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 259

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 88

Authors: O. Abiodun Adeyinka, B. Adeyemo Adesesan

Abstract:

The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses wherein a set of assumptions and methods for a given data set will be made. It is therefore important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR were presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of Law. The estimate of LR is fundamentally a Bayesian concept and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE) for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR has different confidence intervals which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the LoR performed better than the KDE when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.

Keywords: confidence interval, handwriting, kernel density estimator, KDE, logistic regression LoR, repeatability, reproducibility

Procedia PDF Downloads 109

Authors: Julia A. Ermakova

Abstract:

As a member of a multicultural society, it is imperative that individuals demonstrate the highest level of decorum in order to exemplify the beauty of their culture. Adab, the practice of praiseworthy words and deeds, as well as possessing good manners and pursuing that which is considered good, is a fundamental concept that guards against all types of mistakes. In Islam, etiquette for every situation in life is taught, and it constitutes the way of life for a Muslim. In light of this, the personality of an elegant Muslim woman can be described as one who embodies the following qualities: Firstly, cultural speech and erudition are essential components. Improving one's intellect, learning new things, reading diverse literature, expanding one's vocabulary, working on articulation, and avoiding obscene speech and verbosity are crucial. Additionally, listening more than speaking and being willing to discuss one's culture when asked are commendable qualities. Conversely, it is important to avoid discussing foolish matters with foolish people and to be able to respond appropriately and change the subject if someone attempts to hurt or manipulate. Secondly, the style of speech is also of paramount importance. It is recommended to speak in a measured tone with a quiet voice and deep breathing. Avoiding rushing and shortness of breath is also recommended. Thirdly, awareness of how to greet others is essential. Combining Shariah and small talk etiquette, such as making a gesture of respect by putting one's hand to the chest and smiling slightly when a man offers a handshake, is recommended. Understanding the rules of small talk, taboo topics, and self-presentation is also important. Fourthly, knowing how to give and receive compliments without devaluing them is imperative. Knowledge of the rules of good manners and etiquette, both secular and Shariah, is also essential. Fifthly, avoiding arguments and responding elegantly to rudeness and tactlessness is a sign of an elegant Muslim woman. Treating everyone with respect and avoiding prejudices, taboo topics, inappropriate questions, and bad habits are all aspects of politeness. Sixthly, a neat appearance appropriate to Shariah and the local community, as well as a well-put-together outfit with a touch of elegance and style, are crucial. Posture, graceful movement, and a pleasant gaze are also important. Finally, good spirits and inner calm are key to projecting a harmonious image, which encourages people to listen attentively. Giving thanks to Allah in every situation in life is the key to maintaining good spirits. In conclusion, an elegant Muslim woman in a multicultural society is characterized by her high moral qualities and adherence to Islamic etiquette. These qualities, such as cultural speech and erudition, style of speech, awareness of how to greet, knowledge of good manners and etiquette, avoiding arguments, politeness, a neat appearance, and good spirits, all contribute to projecting an image of elegance and respectability. By exemplifying these qualities, Muslim women can serve as positive ambassadors for their culture and religion in diverse societies.

Keywords: adab, elegance, muslim woman, multicultural societies, good manners, etiquette

Procedia PDF Downloads 59

Authors: Filip Rusak, Yulia Arzhaeva, Dadong Wang

Abstract:

Machine learning based Computer-Aided Diagnosis (CAD) is gaining much popularity in medical imaging and diagnostic radiology. However, it requires a large amount of high quality and labeled training image datasets. The training images may come from different sources and be acquired from different radiography machines produced by different manufacturers, digital or digitized copies of film radiographs, with various sizes as well as different pixel intensity distributions. In this paper, a content-aware image augmentation method is presented to deal with these variations. The results of the proposed method have been validated graphically by plotting the removed and added seams of pixels on original images. Two different chest X-ray (CXR) datasets are used in the experiments. The CXRs in the datasets defer in size, some are digital CXRs while the others are digitized from analog CXR films. With the proposed content-aware augmentation method, the Seam Carving algorithm is employed to resize CXRs and the corresponding labels in the form of image masks, followed by histogram matching used to normalize the pixel intensities of digital radiography, based on the pixel intensity values of digitized radiographs. We implemented the algorithms, resized the well-known Montgomery dataset, to the size of the most frequently used Japanese Society of Radiological Technology (JSRT) dataset and normalized our digital CXRs for testing. This work resulted in the unified off-the-shelf CXR dataset composed of radiographs included in both, Montgomery and JSRT datasets. The experimental results show that even though the amount of augmentation is large, our algorithm can preserve the important information in lung fields, local structures, and global visual effect adequately. The proposed method can be used to augment training and testing image data sets so that the trained machine learning model can be used to process CXRs from various sources, and it can be potentially used broadly in any medical imaging applications.

Keywords: computer-aided diagnosis, image augmentation, lung segmentation, medical imaging, seam carving

Procedia PDF Downloads 204

Authors: Thapasya J., Rajesh Kumar

Abstract:

Language plays complex roles in society. The previous studies on language and society explain their interconnected, complementary and complex interactions and, those studies were primarily focused on the variations in the language. Variation being the fundamental nature of languages, the question of personal and social identity navigated through language variation and established that there is an interconnection between language variation and identity. This paper analyses the sociolinguistic variation in language at the lexical level and how the lexical choice of the speaker(s) affects in shaping their identity. It obtains primary data from the lexicon of the Mappila dialect of Malayalam spoken by the members of Mappila (Muslim) community of Kerala. The variation in the lexical choice is analysed by collecting data from the speech samples of 15 minutes from four different age groups of Mappila dialect speakers. Various contexts were analysed and the frequency of borrowed words in each instance is calculated to reach a conclusion on how the variation is happening in the speech community. The paper shows how the lexical choice of the speakers could be socially motivated and involve in shaping and changing identities. Lexical items or vocabulary clearly signal the group identity and personal identity. Mappila dialect of Malayalam was rich in frequent use of borrowed words from Arabic, Persian and Urdu. There was a deliberate attempt to show their identity as a Mappila community member, which was derived from the socio-political situation during those days. This made a clear variation between the Mappila dialect and other dialects of Malayalam at the surface level, which was motivated to create and establish the identity of a person as the member of Mappila community. Historically, these kinds of linguistic variation were highly motivated because of the socio-political factors and, intertwined with the historical facts about the origin and spread of Islamism in the region; people from the Mappila community highly motivated to project their identity as a Mappila because of the social insecurities they had to face before accepting that religion. Thus the deliberate inclusion of Arabic, Persian and Urdu words in their speech helped in showing their identity. However, the socio-political situations and factors at the origin of Mappila community have been changed over a period of time. The social motivation for indicating their identity as a Mappila no longer exist and thus the frequency of borrowed words from Arabic, Persian and Urdu have been reduced from their speech. Apart from the religious terms, the borrowed words from these languages are very few at present. The analysis is carried out by the changes in the language of the people according to their age and found to have significant variations between generations and literacy plays a major role in this variation process. The need of projecting a specific identity of an individual would vary according to the change in the socio-political scenario and a variation in language can shape the identity in order to go with the varying socio-political situation in any language.

Keywords: borrowings, dialect, identity, lexical choice, literacy, variation

Procedia PDF Downloads 228

Authors: Kien-Trinh Thi Bui, Cuong Manh Nguyen

Abstract:

In order to simulate and reproduce the operational characteristics of a dam visually, it is necessary to capture the displacement at different measurement points and analyze the observed movement data promptly to forecast the dam safety. The accuracy of forecasts is further improved by applying machine learning methods to data analysis progress. In this study, the horizontal displacement monitoring data of the Ialy hydroelectric dam was applied to machine learning algorithms: Gaussian processes, multi-layer perceptron neural networks, and the M5-rules algorithm for modelling and forecasting of horizontal displacement of the Ialy hydropower dam (Vietnam), respectively, for analysing. The database which used in this research was built by collecting time series of data from 2006 to 2021 and divided into two parts: training dataset and validating dataset. The final results show all three algorithms have high performance for both training and model validation, but the MLPs is the best model. The usability of them are further investigated by comparison with a benchmark models created by multi-linear regression. The result show the performance which obtained from all the GP model, the MLPs model and the M5-Rules model are much better, therefore these three models should be used to analyze and predict the horizontal displacement of the dam.

Keywords: Gaussian processes, horizontal displacement, hydropower dam, Ialy dam, M5-Rules, multi-layer perception neural networks

Procedia PDF Downloads 190

Authors: Evan Lowhorn, Rocio Alba-Flores

Abstract:

The purpose of this work is to develop a method for classifying hand signals and using the output in a drone control algorithm. To achieve this, methods based on Convolutional Neural Networks (CNN) were applied. CNN's are a subset of deep learning, which allows grid-like inputs to be processed and passed through a neural network to be trained for classification. This type of neural network allows for classification via imaging, which is less intrusive than previous methods using biosensors, such as EMG sensors. Classification CNN's operate purely from the pixel values in an image; therefore they can be used without additional exteroceptive sensors. A development bench was constructed using a desktop computer connected to a high-definition webcam mounted on a scissor arm. This allowed the camera to be pointed downwards at the desk to provide a constant solid background for the dataset and a clear detection area for the user. A MATLAB script was created to automate dataset image capture at the development bench and save the images to the desktop. This allowed the user to create their own dataset of 12,000 images within three hours. These images were evenly distributed among seven classes. The defined classes include forward, backward, left, right, idle, and land. The drone has a popular flip function which was also included as an additional class. To simplify control, the corresponding hand signals chosen were the numerical hand signs for one through five for movements, a fist for land, and the universal “ok” sign for the flip command. Transfer learning with PyTorch (Python) was performed using a pre-trained 18-layer residual learning network (ResNet-18) to retrain the network for custom classification. An algorithm was created to interpret the classification and send encoded messages to a Ryze Tello drone over its 2.4 GHz Wi-Fi connection. The drone’s movements were performed in half-meter distance increments at a constant speed. When combined with the drone control algorithm, the classification performed as desired with negligible latency when compared to the delay in the drone’s movement commands.

Keywords: classification, computer vision, convolutional neural networks, drone control

Procedia PDF Downloads 194

Authors: Chaitanya Kanakamedala, Hansa Pradhan, Carter Gilbert

Abstract:

Social media platforms, such as Twitter, are excellent datasets for understanding human interactions and sentiments. This report explores social dynamics among US Congressional members through a network analysis applied to a dataset of tweets spanning 2008 to 2017 from the ’US Congressional Tweets Dataset’. In this report, we preform network analysis where connections between users (edges) are established based on a similarity threshold: two tweets are connected if the tweets they post are similar. By utilizing the Natural Language Toolkit (NLTK) and NetworkX, we quantified tweet similarity and constructed a graph comprising various interconnected components. Each component represents a cluster of users with closely aligned content. We then preform sentiment analysis on each cluster to explore the prevalent emotions and opinions within these groups. Our findings reveal that despite the initial expectation of distinct ideological divisions typically aligning with party lines, the analysis exposed a high degree of topical convergence across tweets from different political affiliations. The analysis preformed in this report not only highlights the potential of social media as a tool for political communication but also suggests a complex layer of interaction that transcends traditional partisan boundaries, reflecting a complicated landscape of politics in the digital age.

Keywords: natural language processing, sentiment analysis, centrality analysis, topic modeling

Procedia PDF Downloads 4

Authors: Paris Binos

Abstract:

The present work investigates developmental aspects of the duration of isolated vowels in infants with normal hearing compared to those who received cochlear implants (CIs) before two years of age. Infants with normal hearing produced shorter vowel duration since this find related with more mature production abilities. First isolated vowels are transparent during the protophonic stage as evidence of an increased motor and linguistic control. Vowel duration is a crucial factor for the transition of prelexical speech to normal adult speech. Despite current knowledge of data for infants with normal hearing more research is needed to unravel productions skills in early implanted children. Thus, isolated vowel productions by two congenitally hearing-impaired Greek infants (implantation ages 1:4-1:11; post-implant ages 0:6-1:3) were recorded and sampled for six months after implantation with a Nucleus-24. The results compared with the productions of three normal hearing infants (chronological ages 0:8-1:1). Vegetative data and vocalizations masked by external noise or sounds were excluded. Participants had no other disabilities and had unknown deafness etiology. Prior to implantation the infants had an average unaided hearing loss of 95-110 dB HL while the post-implantation PTA decreased to 10-38 dB HL. The current research offers a methodology for the processing of the prelinguistic productions based on a combination of acoustical and auditory analyses. Based on the current methodological framework, duration measured through spectrograms based on wideband analysis, from the voicing onset to the end of the vowel. The end marked by two co-occurring events: 1) The onset of aperiodicity with a rapid change in amplitude in the waveform and 2) a loss in formant’s energy. Cut-off levels of significance were set at 0.05 for all tests. Bonferroni post hoc tests indicated that difference was significant between the mean duration of vowels of infants wearing CIs and their normal hearing peers. Thus, the mean vowel duration of CIs measured longer compared to the normal hearing peers (0.000). The current longitudinal findings contribute to the existing data for the performance of children wearing CIs at a very young age and enrich also the data of the Greek language. The above described weakness for CI’s performance is a challenge for future work in speech processing and CI’s processing strategies.

Keywords: cochlear implant, duration, spectrogram, vowel

Procedia PDF Downloads 250

Authors: Shaik Ayesha Fathima, Shaik Noor Jahan, Duvvada Rajeswara Rao

Abstract:

Earth's environment and its evolution can be seen through satellite images in near real-time. Through satellite imagery, remote sensing data provide crucial information that can be used for a variety of applications, including image fusion, change detection, land cover classification, agriculture, mining, disaster mitigation, and monitoring climate change. The objective of this project is to propose a method for classifying satellite images according to multiple predefined land cover classes. The proposed approach involves collecting data in image format. The data is then pre-processed using data pre-processing techniques. The processed data is fed into the proposed algorithm and the obtained result is analyzed. Some of the algorithms used in satellite imagery classification are U-Net, Random Forest, Deep Labv3, CNN, ANN, Resnet etc. In this project, we are using the DeepLabv3 (Atrous convolution) algorithm for land cover classification. The dataset used is the deep globe land cover classification dataset. DeepLabv3 is a semantic segmentation system that uses atrous convolution to capture multi-scale context by adopting multiple atrous rates in cascade or in parallel to determine the scale of segments.

Keywords: area calculation, atrous convolution, deep globe land cover classification, deepLabv3, land cover classification, resnet 50

Procedia PDF Downloads 131

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 222

Authors: Tatiana Ivushkina

Abstract:

The paper is aimed at studying the use of literary words of foreign origin in modern fiction from a sociolinguistic point of view, which presupposes establishing correlation between this category of words in a speech portrayal or narrative and a social status of the speaker, verifying that it bears social implications and serves as a social marker or index of socially privileged identity in the British literature of the 21-st century. To this end, there were selected literary words of foreign origin in context (60 contexts) and subjected to careful examination. The study is carried out on two novels by Jeffrey Archer – Not a Penny More, Not a Penny Less and A Prisoner of Birth – who, being a graduate from Oxford, represents socially privileged classes himself and gives a wide depiction of characters with different social backgrounds and statuses. The analysis of the novels enabled us to categorize the selected words into four relevant groups. The first represented by terms (commodity, debenture, recuperation, syringe, luminescence, umpire, etc.) serves to unambiguously indicate education, occupation, a field of knowledge in which a character is involved or a situation of communication. The second group is formed of words used in conjunction with their Germanic counterparts (perspiration – sweat, padre – priest, convivial – friendly) to contrast social position of the characters: literary words serving as social indices of upper class speakers whereas their synonyms of Germanic origin characterize middle or lower class speech portrayals. The third class of words comprises socially marked words (verbs, nouns, and adjectives), or U-words (the term first coined by Allan Ross and Nancy Mitford), the status acquired in the course of social history development (elegant, excellent, sophistication, authoritative, preposterous, etc.). The fourth includes words used in a humorous or ironic meaning to convey the narrator’s attitude to the characters or situation itself (ministrations, histrionic, etc.). Words of this group are perceived as 'alien', stylistically distant as they create incongruity between style and subject matter. Social implication of the selected words is enhanced by French words and phrases often accompanying them.

Keywords: British literature of the XXI century, literary words of foreign origin, social context, social meaning

Procedia PDF Downloads 121

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 143

Authors: Adam Gorine, Faten Spondon

Abstract:

Python is considered the most popular programming language and offers its own ecosystem for archiving and maintaining open-source software packages. This system is called the python package index (PyPI), the repository of this programming language. Unfortunately, one-third of these software packages have vulnerabilities that allow attackers to execute code automatically when a vulnerable or malicious package is installed. This paper contributes to large-scale empirical studies investigating security issues in the python ecosystem by evaluating package vulnerabilities. These provide a series of implications that can help the security of software ecosystems by improving the process of discovering, fixing, and managing package vulnerabilities. The vulnerable dataset is generated using the NVD, the national vulnerability database, and the Snyk vulnerability dataset. In addition, we evaluated 807 vulnerability reports in the NVD and 3900 publicly known security vulnerabilities in Python Package Manager (pip) from the Snyk database from 2002 to 2022. As a result, many Python vulnerabilities appear in high severity, followed by medium severity. The most problematic areas have been improper input validation and denial of service attacks. A hybrid scanning tool that combines the three scanners bandit, snyk and dlint, which provide a clear report of the code vulnerability, is also described.

Keywords: Python vulnerabilities, bandit, Snyk, Dlint, Python package index, ecosystem, static analysis, malicious attacks

Procedia PDF Downloads 117

Authors: Salamatu Sani

Abstract:

This study is an investigation of how code-mixing manifests in the language development of a Nigerian child, especially in the Hausa speaking environment. It is hinged on the fact that the environment influences the first language acquired by a child regardless of the cultural and/or linguistic background of the parents. The child under investigation has been subjected to close monitoring on her speech hitherto. It is a longitudinal study covering a period of twelve months (January 2018 to December 2018); that was when the subject was between twenty-four and thirty months of age. The speeches have been recorded by means of a tape recorder, video, and a diary. The study employs as a theoretical framework, emergentism, which is an eclectic of the behaviourist and the mentalist theories to the study of language development, for analysis. This is in agreement with the positions of Skinner and Watson. Sequel to this investigation, it was discovered the environment is a major factor that influences the exposure of a child to a language more than the other factors and that, if a child is exposed to more than one language, there is a great tendency for such a child to code-mix and code-switch in her speech production. The child under investigation, in spite of the linguistic background of her parents, speaks the Hausa Language much better than the other languages around her though with remarkable code-mixing with other languages around her such as English and Ebira languages. The study concludes that although a child is born with the innate ability to acquire a particular language, the environment plays a key role to trigger the innate ability and consequently, the child is exposed to the acquisition of the dominant language around her at a particular given time.

Keywords: bilingual, code-mixing, emergentism, environment, Hausa

Procedia PDF Downloads 147

Authors: Yingkun Huang, Li Guo, Zekang Lan, Kai Tian

Abstract:

Hard disk drives (HDD) failure of the exascale supercomputing system may lead to service interruption and invalidate previous calculations, and it will cause permanent data loss. Therefore, initiating corrective actions before hard drive failures materialize is critical to the continued operation of jobs. In this paper, a highly accurate analysis model based on CNN-LSTM and oversampling technique was proposed, which can correctly predict the necessity of a disk replacement even ten days in advance. Generally, the learning-based method performs poorly on a training dataset with long-tail distribution, especially fault prediction is a very classic situation as the scarcity of failure data. To overcome the puzzle, a new oversampling was employed to augment the data, and then, an improved CNN-LSTM with the shortcut was built to learn more effective features. The shortcut transmits the results of the previous layer of CNN and is used as the input of the LSTM model after weighted fusion with the output of the next layer. Finally, a detailed, empirical comparison of 6 prediction methods is presented and discussed on a public dataset for evaluation. The experiments indicate that the proposed method predicts disk failure with 0.91 Precision, 0.91 Recall, 0.91 F-measure, and 0.90 MCC for 10 days prediction horizon. Thus, the proposed algorithm is an efficient algorithm for predicting HDD failure in supercomputing.

Keywords: HDD replacement, failure, CNN-LSTM, oversampling, prediction

Procedia PDF Downloads 66

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 122

Authors: Sandesh Achar

Abstract:

Personalized advertising holds greater potential for higher conversion rates compared to generic advertisements. However, its widespread application in the retail industry faces challenges due to complex implementation processes. These complexities impede the swift adoption of personalized advertisement on a large scale. Personalized advertisement, being a data-driven approach, necessitates consumer-related data, adding to its complexity. This paper introduces an innovative data-driven decision-making framework, D3Advert, which personalizes advertisements by analyzing personalities using a BiLSTM network. The framework utilizes the Myers–Briggs Type Indicator (MBTI) dataset for development. The employed BiLSTM network, specifically designed and optimized for D3Advert, classifies user personalities into one of the sixteen MBTI categories based on their social media posts. The classification accuracy is 86.42%, with precision, recall, and F1-Score values of 85.11%, 84.14%, and 83.89%, respectively. The D3Advert framework personalizes advertisements based on these personality classifications. Experimental implementation and performance analysis of D3Advert demonstrate a 40% improvement in impressions. D3Advert’s innovative and straightforward approach has the potential to transform personalized advertising and foster widespread personalized advertisement adoption in marketing.

Keywords: personalized advertisement, deep Learning, MBTI dataset, BiLSTM network, NLP.

Procedia PDF Downloads 30

Authors: Sadeq Al Yaari, Fayza Alhammadi, Ayman Al Yaari, Montaha Al Yaari, Aayah Al Yaari, Adham Al Yaari, Sajedah Al Yaari, Saleh Al Yami

Abstract:

Background: A rapidly increasing number of studies that focus on the relationship between language and cortical (CD) and subcortical dementias (SCD) have recently shown that such correlation is existent. Mounting evidence suggests that cognitive impairments should be investigated against language disorders. Aims: This study aims at investigating how language is associated with dementia diseases namely CD &SCD in light of psychoneurolinguistic approach. Method: Data from multiple sources (e.g., theses, dissertations, articles, research, medical records, direct testing, staff reports, and client observations) have been integrated to provide a detailed analysis of the relationship between language and CD&SCD. The researchers identified over 20 most of dementia types, and described them. Having collected and described data, the researchers then analyzed these data independently to see to what extent CD&SCD are involved in matters concerning language. Results: Results of the present study demonstrate that language and CD&SCD are undoubtedly correlated with each other. The loss of the ability of some organs to perform certain functions (due to any of the dementia diseases) results in no way to the loss of some language aspects and /or speech skills. In clearer terms, it is rare to find a patient with dementia who is not suffering from partial or complete linguistic difficulties. Many deficits run through the current interpretation of linguistic disorders: language disorders, speech disorders, articulation disorders, or voice disorders.

Keywords: cortical dementia, subcortical dementia, diseases, psychoneurolinguistics, language, impairments, relationship

Procedia PDF Downloads 36

Authors: Mile Vuković, Lana Jerkić Rajić

Abstract:

Introduction: Broca's aphasia is a non-fluent type of aphasic syndrome, which is primarily manifested by impairment of language production. In connected speech, patients with this type of aphasia produce short sentences in which they often omit function words and morphemes or choose inadequate forms. Aim: This research was conducted to examine the morphosyntactic abilities of people with Broca's aphasia, comparing them with neurologically healthy subjects without a language disorder. Method: The sample included 15 patients with Broca's post-stroke aphasia, who had the relatively intact ability of auditory comprehension. The diagnosis of aphasia was based on the Boston Diagnostic Aphasia Examination. The control group comprised 16 neurologically healthy subjects without data on the presence of disorders in speech and language development. The patients' mother tongue was Serbian. The new Serbian Morphosyntactic Abilities Test (SMAT) was used. Descriptive (frequency, percentage, mean, SD, min, max) and inferential (Mann-Whitney U-test) statistics were used in data processing. Results: We noticed statistically significant differences between people with Broca's aphasia and neurotypical subjects on the SMAT (U = 1.500, z = -4.982, p = 0.000). The results showed that people with Broca's aphasia had achieved low scores on the SMAT, regardless of age (ρ = -0.045, p = 0.873) and time post onset (ρ = 0.330, p = 0.229). Conclusion: Preliminary results show that the SMAT has the potential to detect morphosyntactic deficits in Serbian speakers with Broca's aphasia.

Keywords: Broca’s aphasia, morphosyntactic abilities, agrammatism, Serbian language

Procedia PDF Downloads 54

Authors: Pamir Gogoi, Ratree Wayland

Abstract:

This study investigates the acoustic measures of breathiness when coarticulated with nasality. The acoustic correlates of breathiness and nasality that has already been well established after years of empirical research. Some of these acoustic parameters - like low frequency peaks and wider bandwidths- are common for both nasal and breathy voice. Therefore, it is likely that these parameters interact when a sound is coarticulated with breathiness and nasality. This leads to the hypothesis that the acoustic parameters, which usually act as robust cues in differentiating between breathy and modal voice, might not be reliable cues for differentiating between breathy and modal voice when breathiness is coarticulated with nasality. The effect of nasality on the perception of breathiness has been explored in earlier studies using synthesized speech. The results showed that perceptually, nasality and breathiness do interact. The current study investigates if a similar pattern is observed in natural speech. The study is conducted on Marathi, an Indo-Aryan language which has a three-way contrast between nasality and breathiness. That is, there is a phonemic distinction between nasals, breathy voice and breathy-nasals. Voice quality parameters like – H1-H2 (Difference between the amplitude of first and second harmonic), H1-A3 (Difference between the amplitude of first harmonic and third formant, CPP (Cepstral Peak Prominence), HNR (Harmonics to Noise ratio) and B1 (Bandwidth of first formant) were extracted. Statistical models like linear mixed effects regression and Random Forest classifiers show that measures that capture the noise component in the signal- like CPP and HNR- can classify breathy voice from modal voice better than spectral measures when breathy voice is coarticulated with nasality.

Keywords: breathiness, marathi, nasality, voice quality

Procedia PDF Downloads 77

Authors: A. Nawaz

Abstract:

The present study uses Halliday’s transitivity model to analyze and interpret ideological stance in PM Nawaz Sharif’s political discourse. His famous speech at the 71st UN assembly was analyzed qualitatively using clausal analysis approach to investigate the communicative functions of the linguistic choices made in the address. The study discovers that among the six process types under the transitivity model, material, relational and mental processes appear most frequently in the speech, making up almost 86% of the whole. Verbal processes rank 4th, whereas existential and behavioral are the least occurring processes covering only 2 and 1 percent respectively. The dominant use of material processes suggests that Nawaz Sharif and his government are the main actors working on several concrete projects to produce a sense of developmental progression and continuity. Using relational and mental processes the PM, along with establishing proximity with masses and especially Kashmiri, gives guarantees and promises. The linguistic analysis concludes Kashmir dispute as being the central theme of the address, since it covers more than half of the discourse. The address calls for a strong action instead of formal assurances and wishful thoughts. The study establishes that language structures can yield certain connotations and ideologies which are not overt for readers. This is in affirmation to the supposition that language form performs a communicative function and is not merely fortuitous.

Keywords: Hallidian perspective on language, implicit meanings, Nawaz Sharif, political ideologies, political speeches, transitivity, UN Assembly

Procedia PDF Downloads 197

Authors: Premalatha B. S., Shenoy A. M.

Abstract:

Background: Rehabilitation of swallowing is as vital as speech in surgically treated head and neck cancer patients to maintain nutritional support, enhance wound healing and improve quality of life. Aspiration following supraglottic laryngectomy is very common, and rehabilitation of the same is crucial which requires involvement of speech therapist in close contact with head and neck surgeon. Objectives: To examine the functions of swallowing outcomes after intensive therapy in supraglottic laryngectomy. Materials: Thirty-nine supra glottic laryngectomees were participated in the study. Of them, 36 subjects were males and 3 were females, in the age range of 32-68 years. Eighteen subjects had undergone standard supra glottis laryngectomy (Group1) for supraglottic lesions where as 21 of them for extended supraglottic laryngectomy (Group 2) for base tongue and lateral pharyngeal wall lesion. Prior to surgery visit by speech pathologist was mandatory to assess the sutability for surgery and rehabilitation. Dysphagia rehabilitation started after decannulation of tracheostoma by focusing on orientation about anatomy, physiological variation before and after surgery, which was tailor made for each individual based on their type and extent of surgery. Supraglottic diet - Soft solid with supraglottic swallow method was advocated to prevent aspiration. The success of intervention was documented as number of sessions taken to swallow different food consistency and also percentage of subjects who achieved satisfactory swallow in terms of number of weeks in both the groups. Results: Statistical data was computed in two ways in both the groups 1) to calculate percentage (%) of subjects who swallowed satisfactorily in the time frame of less than 3 weeks to more than 6 weeks, 2) number of sessions taken to swallow without aspiration as far as food consistency was concerned. The study indicated that in group 1 subjects of standard supraglottic laryngectomy, 61% (n=11) of them were successfully rehabilitated but their swallowing normalcy was delayed by an average 29th post operative day (3-6 weeks). Thirty three percentages (33%) (n=6) of the subjects could swallow satisfactorily without aspiration even before 3 weeks and only 5 % (n=1) of the needed more than 6 weeks to achieve normal swallowing ability. Group 2 subjects of extended SGL only 47 %( n=10) of them could achieved satisfactory swallow by 3-6 weeks and 24% (n=5) of them of them achieved normal swallowing ability before 3 weeks. Around 4% (n=1) needed more than 6 weeks and as high as 24 % (n=5) of them continued to be supplemented with naso gastric feeding even after 8-10 months post operative as they exhibited severe aspiration. As far as type of food consistencies were concerned group 1 subject could able to swallow all types without aspiration much earlier than group 2 subjects. Group 1 needed only 8 swallowing therapy sessions for thickened soft solid and 15 sessions for liquids whereas group 2 required 14 sessions for soft solid and 17 sessions for liquids to achieve swallowing normalcy without aspiration. Conclusion: The study highlights the importance of dysphagia intervention in supraglottic laryngectomees by speech pathologist.

Keywords: dysphagia management, supraglotic diet, supraglottic laryngectomy, supraglottic swallow

Procedia PDF Downloads 223

Authors: Qiang Wang, Hongyang Yu

Abstract:

Multi-human 3D pose estimation is a challenging task in computer vision, which aims to recover the 3D joint locations of multiple people from multi-view images. In contrast to traditional methods, which typically only use color (RGB) images as input, our approach utilizes both color and depth (D) information contained in RGB-D images. We also employ a transformer-based model as the backbone of our approach, which is able to capture long-range dependencies and has been shown to perform well on various sequence modeling tasks. Our method is trained and tested on the Carnegie Mellon University (CMU) Panoptic dataset, which contains a diverse set of indoor and outdoor scenes with multiple people in varying poses and clothing. We evaluate the performance of our model on the standard 3D pose estimation metrics of mean per-joint position error (MPJPE). Our results show that the transformer-based approach outperforms traditional methods and achieves competitive results on the CMU Panoptic dataset. We also perform an ablation study to understand the impact of different design choices on the overall performance of the model. In summary, our work demonstrates the effectiveness of using a transformer-based approach with RGB-D images for multi-human 3D pose estimation and has potential applications in real-world scenarios such as human-computer interaction, robotics, and augmented reality.

Keywords: multi-human 3D pose estimation, RGB-D images, transformer, 3D joint locations

Procedia PDF Downloads 66